2022-05-26 15:07:31,889 INFO [train.py:906] (3/4) Training started
2022-05-26 15:07:31,889 INFO [train.py:916] (3/4) Device: cuda:3
2022-05-26 15:07:31,893 INFO [train.py:934] (3/4) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Debug', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming-conformer', 'icefall-git-sha1': '364bccb-dirty', 'icefall-git-date': 'Thu May 26 10:29:08 2022', 'icefall-path': '/ceph-kw/kangwei/code/icefall_reworked2', 'k2-path': '/ceph-kw/kangwei/code/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-hw/kangwei/dev_tools/anaconda3/envs/rnnt2/lib/python3.8/site-packages/lhotse-1.1.0-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-0307202051-57dc848959-8tmmp', 'IP address': '10.177.24.138'}, 'world_size': 4, 'master_port': 13498, 'tensorboard': True, 'num_epochs': 50, 'start_epoch': 2, 'start_batch': 0, 'exp_dir': PosixPath('streaming_pruned_transducer_stateless4/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 20, 'average_period': 100, 'use_fp16': False, 'dynamic_chunk_training': True, 'causal_convolution': True, 'short_chunk_size': 32, 'num_left_chunks': 4, 'delay_penalty': 0.0, 'return_sym_delay': False, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
2022-05-26 15:07:31,893 INFO [train.py:936] (3/4) About to create model
2022-05-26 15:07:32,331 INFO [train.py:940] (3/4) Number of model parameters: 78648040
2022-05-26 15:07:32,331 INFO [checkpoint.py:112] (3/4) Loading checkpoint from streaming_pruned_transducer_stateless4/exp/epoch-1.pt
2022-05-26 15:07:44,517 INFO [train.py:955] (3/4) Using DDP
2022-05-26 15:07:44,729 INFO [train.py:963] (3/4) Loading optimizer state dict
2022-05-26 15:07:45,495 INFO [train.py:971] (3/4) Loading scheduler state dict
2022-05-26 15:07:45,495 INFO [asr_datamodule.py:391] (3/4) About to get train-clean-100 cuts
2022-05-26 15:07:51,861 INFO [asr_datamodule.py:398] (3/4) About to get train-clean-360 cuts
2022-05-26 15:08:18,860 INFO [asr_datamodule.py:405] (3/4) About to get train-other-500 cuts
2022-05-26 15:09:04,148 INFO [asr_datamodule.py:209] (3/4) Enable MUSAN
2022-05-26 15:09:04,148 INFO [asr_datamodule.py:210] (3/4) About to get Musan cuts
2022-05-26 15:09:05,581 INFO [asr_datamodule.py:238] (3/4) Enable SpecAugment
2022-05-26 15:09:05,581 INFO [asr_datamodule.py:239] (3/4) Time warp factor: 80
2022-05-26 15:09:05,581 INFO [asr_datamodule.py:251] (3/4) Num frame mask: 10
2022-05-26 15:09:05,582 INFO [asr_datamodule.py:264] (3/4) About to create train dataset
2022-05-26 15:09:05,582 INFO [asr_datamodule.py:292] (3/4) Using BucketingSampler.
2022-05-26 15:09:10,720 INFO [asr_datamodule.py:308] (3/4) About to create train dataloader
2022-05-26 15:09:10,722 INFO [asr_datamodule.py:412] (3/4) About to get dev-clean cuts
2022-05-26 15:09:11,017 INFO [asr_datamodule.py:417] (3/4) About to get dev-other cuts
2022-05-26 15:09:11,168 INFO [asr_datamodule.py:339] (3/4) About to create dev dataset
2022-05-26 15:09:11,180 INFO [asr_datamodule.py:358] (3/4) About to create dev dataloader
2022-05-26 15:09:11,180 INFO [train.py:1082] (3/4) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
2022-05-26 15:09:21,056 INFO [distributed.py:874] (3/4) Reducer buckets have been rebuilt in this iteration.
2022-05-26 15:09:26,263 INFO [train.py:1023] (3/4) Loading grad scaler state dict
2022-05-26 15:09:38,896 INFO [train.py:842] (3/4) Epoch 2, batch 0, loss[loss=0.4612, simple_loss=0.4451, pruned_loss=0.2386, over 7129.00 frames.], tot_loss[loss=0.4612, simple_loss=0.4451, pruned_loss=0.2386, over 7129.00 frames.], batch size: 26, lr: 2.06e-03
2022-05-26 15:10:18,178 INFO [train.py:842] (3/4) Epoch 2, batch 50, loss[loss=0.3463, simple_loss=0.3984, pruned_loss=0.147, over 7240.00 frames.], tot_loss[loss=0.3521, simple_loss=0.3848, pruned_loss=0.1597, over 311642.06 frames.], batch size: 20, lr: 2.06e-03
2022-05-26 15:10:57,082 INFO [train.py:842] (3/4) Epoch 2, batch 100, loss[loss=0.3193, simple_loss=0.3492, pruned_loss=0.1447, over 7429.00 frames.], tot_loss[loss=0.3512, simple_loss=0.3846, pruned_loss=0.1589, over 559786.86 frames.], batch size: 20, lr: 2.05e-03
2022-05-26 15:11:36,020 INFO [train.py:842] (3/4) Epoch 2, batch 150, loss[loss=0.2895, simple_loss=0.3505, pruned_loss=0.1142, over 7327.00 frames.], tot_loss[loss=0.3469, simple_loss=0.3824, pruned_loss=0.1557, over 750853.81 frames.], batch size: 20, lr: 2.05e-03
2022-05-26 15:12:14,731 INFO [train.py:842] (3/4) Epoch 2, batch 200, loss[loss=0.3655, simple_loss=0.3788, pruned_loss=0.1761, over 7160.00 frames.], tot_loss[loss=0.3443, simple_loss=0.38, pruned_loss=0.1543, over 901095.45 frames.], batch size: 19, lr: 2.04e-03
2022-05-26 15:12:53,686 INFO [train.py:842] (3/4) Epoch 2, batch 250, loss[loss=0.3086, simple_loss=0.3712, pruned_loss=0.1229, over 7388.00 frames.], tot_loss[loss=0.3464, simple_loss=0.3818, pruned_loss=0.1555, over 1016036.36 frames.], batch size: 23, lr: 2.04e-03
2022-05-26 15:13:32,394 INFO [train.py:842] (3/4) Epoch 2, batch 300, loss[loss=0.3174, simple_loss=0.3584, pruned_loss=0.1382, over 7259.00 frames.], tot_loss[loss=0.3467, simple_loss=0.3822, pruned_loss=0.1557, over 1105768.98 frames.], batch size: 19, lr: 2.03e-03
2022-05-26 15:14:11,462 INFO [train.py:842] (3/4) Epoch 2, batch 350, loss[loss=0.4035, simple_loss=0.4332, pruned_loss=0.1869, over 7212.00 frames.], tot_loss[loss=0.3446, simple_loss=0.3815, pruned_loss=0.1539, over 1174418.99 frames.], batch size: 21, lr: 2.03e-03
2022-05-26 15:14:50,193 INFO [train.py:842] (3/4) Epoch 2, batch 400, loss[loss=0.3604, simple_loss=0.4, pruned_loss=0.1604, over 7155.00 frames.], tot_loss[loss=0.3446, simple_loss=0.3813, pruned_loss=0.1539, over 1230616.56 frames.], batch size: 20, lr: 2.03e-03
2022-05-26 15:15:28,842 INFO [train.py:842] (3/4) Epoch 2, batch 450, loss[loss=0.334, simple_loss=0.3702, pruned_loss=0.1489, over 7154.00 frames.], tot_loss[loss=0.344, simple_loss=0.3814, pruned_loss=0.1533, over 1275352.70 frames.], batch size: 19, lr: 2.02e-03
2022-05-26 15:16:07,195 INFO [train.py:842] (3/4) Epoch 2, batch 500, loss[loss=0.2313, simple_loss=0.2931, pruned_loss=0.08471, over 7162.00 frames.], tot_loss[loss=0.3397, simple_loss=0.3783, pruned_loss=0.1505, over 1306865.40 frames.], batch size: 18, lr: 2.02e-03
2022-05-26 15:16:46,592 INFO [train.py:842] (3/4) Epoch 2, batch 550, loss[loss=0.3171, simple_loss=0.3637, pruned_loss=0.1353, over 7359.00 frames.], tot_loss[loss=0.3409, simple_loss=0.3788, pruned_loss=0.1515, over 1332673.46 frames.], batch size: 19, lr: 2.01e-03
2022-05-26 15:17:25,160 INFO [train.py:842] (3/4) Epoch 2, batch 600, loss[loss=0.3453, simple_loss=0.3922, pruned_loss=0.1492, over 7372.00 frames.], tot_loss[loss=0.3436, simple_loss=0.3811, pruned_loss=0.153, over 1354293.37 frames.], batch size: 23, lr: 2.01e-03
2022-05-26 15:18:04,061 INFO [train.py:842] (3/4) Epoch 2, batch 650, loss[loss=0.2593, simple_loss=0.3201, pruned_loss=0.09925, over 7287.00 frames.], tot_loss[loss=0.338, simple_loss=0.3771, pruned_loss=0.1494, over 1368629.84 frames.], batch size: 18, lr: 2.01e-03
2022-05-26 15:18:42,829 INFO [train.py:842] (3/4) Epoch 2, batch 700, loss[loss=0.4093, simple_loss=0.4151, pruned_loss=0.2017, over 4778.00 frames.], tot_loss[loss=0.3361, simple_loss=0.3756, pruned_loss=0.1483, over 1380443.18 frames.], batch size: 52, lr: 2.00e-03
2022-05-26 15:19:21,651 INFO [train.py:842] (3/4) Epoch 2, batch 750, loss[loss=0.3672, simple_loss=0.3918, pruned_loss=0.1713, over 7253.00 frames.], tot_loss[loss=0.3376, simple_loss=0.3763, pruned_loss=0.1495, over 1391124.08 frames.], batch size: 19, lr: 2.00e-03
2022-05-26 15:20:00,309 INFO [train.py:842] (3/4) Epoch 2, batch 800, loss[loss=0.2589, simple_loss=0.32, pruned_loss=0.09891, over 7062.00 frames.], tot_loss[loss=0.3356, simple_loss=0.3751, pruned_loss=0.1481, over 1400771.24 frames.], batch size: 18, lr: 1.99e-03
2022-05-26 15:20:39,206 INFO [train.py:842] (3/4) Epoch 2, batch 850, loss[loss=0.4798, simple_loss=0.468, pruned_loss=0.2458, over 7323.00 frames.], tot_loss[loss=0.333, simple_loss=0.3733, pruned_loss=0.1464, over 1408962.37 frames.], batch size: 20, lr: 1.99e-03
2022-05-26 15:21:17,864 INFO [train.py:842] (3/4) Epoch 2, batch 900, loss[loss=0.3773, simple_loss=0.4017, pruned_loss=0.1764, over 7422.00 frames.], tot_loss[loss=0.335, simple_loss=0.3749, pruned_loss=0.1475, over 1413085.54 frames.], batch size: 20, lr: 1.99e-03
2022-05-26 15:21:56,751 INFO [train.py:842] (3/4) Epoch 2, batch 950, loss[loss=0.3033, simple_loss=0.3515, pruned_loss=0.1275, over 7260.00 frames.], tot_loss[loss=0.335, simple_loss=0.3753, pruned_loss=0.1473, over 1414718.19 frames.], batch size: 19, lr: 1.98e-03
2022-05-26 15:22:35,382 INFO [train.py:842] (3/4) Epoch 2, batch 1000, loss[loss=0.3362, simple_loss=0.3782, pruned_loss=0.147, over 6844.00 frames.], tot_loss[loss=0.3348, simple_loss=0.375, pruned_loss=0.1473, over 1416825.43 frames.], batch size: 31, lr: 1.98e-03
2022-05-26 15:23:14,156 INFO [train.py:842] (3/4) Epoch 2, batch 1050, loss[loss=0.2923, simple_loss=0.353, pruned_loss=0.1158, over 7429.00 frames.], tot_loss[loss=0.3324, simple_loss=0.373, pruned_loss=0.1459, over 1419355.46 frames.], batch size: 20, lr: 1.97e-03
2022-05-26 15:23:52,752 INFO [train.py:842] (3/4) Epoch 2, batch 1100, loss[loss=0.4031, simple_loss=0.4066, pruned_loss=0.1998, over 7154.00 frames.], tot_loss[loss=0.3365, simple_loss=0.376, pruned_loss=0.1486, over 1420261.87 frames.], batch size: 18, lr: 1.97e-03
2022-05-26 15:24:32,113 INFO [train.py:842] (3/4) Epoch 2, batch 1150, loss[loss=0.3062, simple_loss=0.373, pruned_loss=0.1197, over 7235.00 frames.], tot_loss[loss=0.3338, simple_loss=0.3743, pruned_loss=0.1466, over 1423797.12 frames.], batch size: 20, lr: 1.97e-03
2022-05-26 15:25:10,583 INFO [train.py:842] (3/4) Epoch 2, batch 1200, loss[loss=0.2952, simple_loss=0.3523, pruned_loss=0.1191, over 7043.00 frames.], tot_loss[loss=0.3336, simple_loss=0.3741, pruned_loss=0.1466, over 1422813.61 frames.], batch size: 28, lr: 1.96e-03
2022-05-26 15:25:49,497 INFO [train.py:842] (3/4) Epoch 2, batch 1250, loss[loss=0.2482, simple_loss=0.2991, pruned_loss=0.09863, over 7277.00 frames.], tot_loss[loss=0.3351, simple_loss=0.3748, pruned_loss=0.1477, over 1422444.80 frames.], batch size: 18, lr: 1.96e-03
2022-05-26 15:26:28,034 INFO [train.py:842] (3/4) Epoch 2, batch 1300, loss[loss=0.3467, simple_loss=0.4012, pruned_loss=0.1461, over 7223.00 frames.], tot_loss[loss=0.3354, simple_loss=0.3755, pruned_loss=0.1477, over 1416952.67 frames.], batch size: 21, lr: 1.95e-03
2022-05-26 15:27:06,805 INFO [train.py:842] (3/4) Epoch 2, batch 1350, loss[loss=0.2881, simple_loss=0.3391, pruned_loss=0.1186, over 7265.00 frames.], tot_loss[loss=0.3344, simple_loss=0.375, pruned_loss=0.1469, over 1419767.04 frames.], batch size: 17, lr: 1.95e-03
2022-05-26 15:27:45,161 INFO [train.py:842] (3/4) Epoch 2, batch 1400, loss[loss=0.36, simple_loss=0.3955, pruned_loss=0.1622, over 7221.00 frames.], tot_loss[loss=0.334, simple_loss=0.3744, pruned_loss=0.1468, over 1418015.29 frames.], batch size: 21, lr: 1.95e-03
2022-05-26 15:28:24,279 INFO [train.py:842] (3/4) Epoch 2, batch 1450, loss[loss=0.3452, simple_loss=0.3995, pruned_loss=0.1454, over 7202.00 frames.], tot_loss[loss=0.3352, simple_loss=0.375, pruned_loss=0.1477, over 1422041.50 frames.], batch size: 26, lr: 1.94e-03
2022-05-26 15:29:02,874 INFO [train.py:842] (3/4) Epoch 2, batch 1500, loss[loss=0.3312, simple_loss=0.3702, pruned_loss=0.146, over 6205.00 frames.], tot_loss[loss=0.3348, simple_loss=0.3749, pruned_loss=0.1474, over 1422460.75 frames.], batch size: 37, lr: 1.94e-03
2022-05-26 15:29:41,829 INFO [train.py:842] (3/4) Epoch 2, batch 1550, loss[loss=0.2996, simple_loss=0.3564, pruned_loss=0.1214, over 7430.00 frames.], tot_loss[loss=0.3319, simple_loss=0.3732, pruned_loss=0.1453, over 1425161.51 frames.], batch size: 20, lr: 1.94e-03
2022-05-26 15:30:20,577 INFO [train.py:842] (3/4) Epoch 2, batch 1600, loss[loss=0.3049, simple_loss=0.3459, pruned_loss=0.1319, over 7169.00 frames.], tot_loss[loss=0.3299, simple_loss=0.3715, pruned_loss=0.1442, over 1424715.11 frames.], batch size: 18, lr: 1.93e-03
2022-05-26 15:30:59,408 INFO [train.py:842] (3/4) Epoch 2, batch 1650, loss[loss=0.3323, simple_loss=0.378, pruned_loss=0.1433, over 7437.00 frames.], tot_loss[loss=0.3283, simple_loss=0.3706, pruned_loss=0.143, over 1424327.32 frames.], batch size: 20, lr: 1.93e-03
2022-05-26 15:31:38,113 INFO [train.py:842] (3/4) Epoch 2, batch 1700, loss[loss=0.4094, simple_loss=0.4352, pruned_loss=0.1917, over 7418.00 frames.], tot_loss[loss=0.3291, simple_loss=0.3714, pruned_loss=0.1434, over 1423792.97 frames.], batch size: 21, lr: 1.92e-03
2022-05-26 15:32:16,714 INFO [train.py:842] (3/4) Epoch 2, batch 1750, loss[loss=0.2706, simple_loss=0.3181, pruned_loss=0.1115, over 7279.00 frames.], tot_loss[loss=0.3309, simple_loss=0.3733, pruned_loss=0.1442, over 1423111.62 frames.], batch size: 18, lr: 1.92e-03
2022-05-26 15:32:55,331 INFO [train.py:842] (3/4) Epoch 2, batch 1800, loss[loss=0.2863, simple_loss=0.3359, pruned_loss=0.1184, over 7355.00 frames.], tot_loss[loss=0.3314, simple_loss=0.3734, pruned_loss=0.1447, over 1424344.77 frames.], batch size: 19, lr: 1.92e-03
2022-05-26 15:33:34,111 INFO [train.py:842] (3/4) Epoch 2, batch 1850, loss[loss=0.3064, simple_loss=0.3514, pruned_loss=0.1307, over 7319.00 frames.], tot_loss[loss=0.3289, simple_loss=0.3713, pruned_loss=0.1433, over 1424592.50 frames.], batch size: 20, lr: 1.91e-03
2022-05-26 15:34:12,729 INFO [train.py:842] (3/4) Epoch 2, batch 1900, loss[loss=0.3036, simple_loss=0.3379, pruned_loss=0.1347, over 6994.00 frames.], tot_loss[loss=0.3292, simple_loss=0.3721, pruned_loss=0.1432, over 1428527.22 frames.], batch size: 16, lr: 1.91e-03
2022-05-26 15:34:51,942 INFO [train.py:842] (3/4) Epoch 2, batch 1950, loss[loss=0.3811, simple_loss=0.3915, pruned_loss=0.1854, over 7288.00 frames.], tot_loss[loss=0.3294, simple_loss=0.372, pruned_loss=0.1435, over 1429081.33 frames.], batch size: 18, lr: 1.91e-03
2022-05-26 15:35:30,327 INFO [train.py:842] (3/4) Epoch 2, batch 2000, loss[loss=0.329, simple_loss=0.3786, pruned_loss=0.1397, over 7128.00 frames.], tot_loss[loss=0.331, simple_loss=0.3733, pruned_loss=0.1444, over 1422890.90 frames.], batch size: 21, lr: 1.90e-03
2022-05-26 15:36:09,259 INFO [train.py:842] (3/4) Epoch 2, batch 2050, loss[loss=0.316, simple_loss=0.3754, pruned_loss=0.1283, over 7011.00 frames.], tot_loss[loss=0.329, simple_loss=0.3721, pruned_loss=0.143, over 1424290.30 frames.], batch size: 28, lr: 1.90e-03
2022-05-26 15:36:48,117 INFO [train.py:842] (3/4) Epoch 2, batch 2100, loss[loss=0.2685, simple_loss=0.3164, pruned_loss=0.1103, over 7418.00 frames.], tot_loss[loss=0.3293, simple_loss=0.3723, pruned_loss=0.1432, over 1424669.56 frames.], batch size: 18, lr: 1.90e-03
2022-05-26 15:37:27,077 INFO [train.py:842] (3/4) Epoch 2, batch 2150, loss[loss=0.3366, simple_loss=0.3811, pruned_loss=0.146, over 7409.00 frames.], tot_loss[loss=0.3272, simple_loss=0.3707, pruned_loss=0.1418, over 1423784.11 frames.], batch size: 21, lr: 1.89e-03
2022-05-26 15:38:05,656 INFO [train.py:842] (3/4) Epoch 2, batch 2200, loss[loss=0.3669, simple_loss=0.3971, pruned_loss=0.1684, over 7119.00 frames.], tot_loss[loss=0.3236, simple_loss=0.3686, pruned_loss=0.1393, over 1422268.73 frames.], batch size: 21, lr: 1.89e-03
2022-05-26 15:38:44,484 INFO [train.py:842] (3/4) Epoch 2, batch 2250, loss[loss=0.2564, simple_loss=0.3137, pruned_loss=0.09956, over 7208.00 frames.], tot_loss[loss=0.3217, simple_loss=0.3671, pruned_loss=0.1382, over 1424052.19 frames.], batch size: 21, lr: 1.89e-03
2022-05-26 15:39:23,301 INFO [train.py:842] (3/4) Epoch 2, batch 2300, loss[loss=0.3588, simple_loss=0.3876, pruned_loss=0.165, over 7195.00 frames.], tot_loss[loss=0.3242, simple_loss=0.369, pruned_loss=0.1397, over 1425135.08 frames.], batch size: 22, lr: 1.88e-03
2022-05-26 15:40:02,240 INFO [train.py:842] (3/4) Epoch 2, batch 2350, loss[loss=0.3047, simple_loss=0.3611, pruned_loss=0.1241, over 7231.00 frames.], tot_loss[loss=0.323, simple_loss=0.3682, pruned_loss=0.1389, over 1423815.31 frames.], batch size: 20, lr: 1.88e-03
2022-05-26 15:40:40,751 INFO [train.py:842] (3/4) Epoch 2, batch 2400, loss[loss=0.346, simple_loss=0.3919, pruned_loss=0.15, over 7313.00 frames.], tot_loss[loss=0.3246, simple_loss=0.3692, pruned_loss=0.14, over 1423702.20 frames.], batch size: 21, lr: 1.87e-03
2022-05-26 15:41:19,579 INFO [train.py:842] (3/4) Epoch 2, batch 2450, loss[loss=0.3104, simple_loss=0.353, pruned_loss=0.1339, over 7315.00 frames.], tot_loss[loss=0.3252, simple_loss=0.3699, pruned_loss=0.1403, over 1427205.21 frames.], batch size: 21, lr: 1.87e-03
2022-05-26 15:41:58,128 INFO [train.py:842] (3/4) Epoch 2, batch 2500, loss[loss=0.3553, simple_loss=0.4043, pruned_loss=0.1532, over 7213.00 frames.], tot_loss[loss=0.3234, simple_loss=0.369, pruned_loss=0.1389, over 1427664.21 frames.], batch size: 26, lr: 1.87e-03
2022-05-26 15:42:36,863 INFO [train.py:842] (3/4) Epoch 2, batch 2550, loss[loss=0.2769, simple_loss=0.3143, pruned_loss=0.1197, over 6975.00 frames.], tot_loss[loss=0.3225, simple_loss=0.3681, pruned_loss=0.1384, over 1428149.82 frames.], batch size: 16, lr: 1.86e-03
2022-05-26 15:43:15,435 INFO [train.py:842] (3/4) Epoch 2, batch 2600, loss[loss=0.3533, simple_loss=0.3924, pruned_loss=0.1571, over 7161.00 frames.], tot_loss[loss=0.32, simple_loss=0.3659, pruned_loss=0.137, over 1430152.01 frames.], batch size: 26, lr: 1.86e-03
2022-05-26 15:43:54,096 INFO [train.py:842] (3/4) Epoch 2, batch 2650, loss[loss=0.3043, simple_loss=0.3486, pruned_loss=0.13, over 6120.00 frames.], tot_loss[loss=0.3191, simple_loss=0.365, pruned_loss=0.1366, over 1428766.13 frames.], batch size: 37, lr: 1.86e-03
2022-05-26 15:44:32,736 INFO [train.py:842] (3/4) Epoch 2, batch 2700, loss[loss=0.3263, simple_loss=0.3774, pruned_loss=0.1377, over 6670.00 frames.], tot_loss[loss=0.3167, simple_loss=0.363, pruned_loss=0.1351, over 1428259.79 frames.], batch size: 31, lr: 1.85e-03
2022-05-26 15:45:11,872 INFO [train.py:842] (3/4) Epoch 2, batch 2750, loss[loss=0.4057, simple_loss=0.4224, pruned_loss=0.1945, over 7278.00 frames.], tot_loss[loss=0.3159, simple_loss=0.3624, pruned_loss=0.1347, over 1424457.49 frames.], batch size: 24, lr: 1.85e-03
2022-05-26 15:45:50,276 INFO [train.py:842] (3/4) Epoch 2, batch 2800, loss[loss=0.3216, simple_loss=0.3661, pruned_loss=0.1385, over 7201.00 frames.], tot_loss[loss=0.3166, simple_loss=0.3632, pruned_loss=0.135, over 1426843.39 frames.], batch size: 23, lr: 1.85e-03
2022-05-26 15:46:29,157 INFO [train.py:842] (3/4) Epoch 2, batch 2850, loss[loss=0.3329, simple_loss=0.3943, pruned_loss=0.1357, over 7295.00 frames.], tot_loss[loss=0.3167, simple_loss=0.3637, pruned_loss=0.1349, over 1426603.30 frames.], batch size: 24, lr: 1.84e-03
2022-05-26 15:47:07,594 INFO [train.py:842] (3/4) Epoch 2, batch 2900, loss[loss=0.3516, simple_loss=0.396, pruned_loss=0.1536, over 7234.00 frames.], tot_loss[loss=0.319, simple_loss=0.3655, pruned_loss=0.1362, over 1421532.66 frames.], batch size: 20, lr: 1.84e-03
2022-05-26 15:47:46,395 INFO [train.py:842] (3/4) Epoch 2, batch 2950, loss[loss=0.3113, simple_loss=0.3617, pruned_loss=0.1304, over 7226.00 frames.], tot_loss[loss=0.3187, simple_loss=0.3653, pruned_loss=0.136, over 1422405.70 frames.], batch size: 20, lr: 1.84e-03
2022-05-26 15:48:24,992 INFO [train.py:842] (3/4) Epoch 2, batch 3000, loss[loss=0.2386, simple_loss=0.292, pruned_loss=0.09259, over 7270.00 frames.], tot_loss[loss=0.3183, simple_loss=0.365, pruned_loss=0.1358, over 1426015.89 frames.], batch size: 17, lr: 1.84e-03
2022-05-26 15:48:24,993 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 15:48:34,574 INFO [train.py:871] (3/4) Epoch 2, validation: loss=0.2365, simple_loss=0.3276, pruned_loss=0.07266, over 868885.00 frames.
2022-05-26 15:49:14,146 INFO [train.py:842] (3/4) Epoch 2, batch 3050, loss[loss=0.2716, simple_loss=0.3178, pruned_loss=0.1127, over 7274.00 frames.], tot_loss[loss=0.3195, simple_loss=0.3659, pruned_loss=0.1366, over 1421869.97 frames.], batch size: 18, lr: 1.83e-03
2022-05-26 15:49:52,543 INFO [train.py:842] (3/4) Epoch 2, batch 3100, loss[loss=0.3772, simple_loss=0.4048, pruned_loss=0.1748, over 5297.00 frames.], tot_loss[loss=0.3196, simple_loss=0.3655, pruned_loss=0.1368, over 1421548.84 frames.], batch size: 53, lr: 1.83e-03
2022-05-26 15:50:31,870 INFO [train.py:842] (3/4) Epoch 2, batch 3150, loss[loss=0.2615, simple_loss=0.3239, pruned_loss=0.09957, over 7237.00 frames.], tot_loss[loss=0.3182, simple_loss=0.3647, pruned_loss=0.1359, over 1423991.59 frames.], batch size: 16, lr: 1.83e-03
2022-05-26 15:51:10,264 INFO [train.py:842] (3/4) Epoch 2, batch 3200, loss[loss=0.3521, simple_loss=0.3793, pruned_loss=0.1624, over 5158.00 frames.], tot_loss[loss=0.3204, simple_loss=0.3666, pruned_loss=0.1371, over 1413847.47 frames.], batch size: 52, lr: 1.82e-03
2022-05-26 15:51:49,110 INFO [train.py:842] (3/4) Epoch 2, batch 3250, loss[loss=0.3026, simple_loss=0.3532, pruned_loss=0.126, over 7196.00 frames.], tot_loss[loss=0.3242, simple_loss=0.3692, pruned_loss=0.1395, over 1415862.24 frames.], batch size: 23, lr: 1.82e-03
2022-05-26 15:52:27,637 INFO [train.py:842] (3/4) Epoch 2, batch 3300, loss[loss=0.2767, simple_loss=0.3375, pruned_loss=0.1079, over 7205.00 frames.], tot_loss[loss=0.3203, simple_loss=0.3663, pruned_loss=0.1372, over 1420374.31 frames.], batch size: 22, lr: 1.82e-03
2022-05-26 15:53:06,350 INFO [train.py:842] (3/4) Epoch 2, batch 3350, loss[loss=0.3175, simple_loss=0.3724, pruned_loss=0.1313, over 7119.00 frames.], tot_loss[loss=0.32, simple_loss=0.3666, pruned_loss=0.1367, over 1422764.85 frames.], batch size: 26, lr: 1.81e-03
2022-05-26 15:53:45,054 INFO [train.py:842] (3/4) Epoch 2, batch 3400, loss[loss=0.2558, simple_loss=0.3107, pruned_loss=0.1004, over 7143.00 frames.], tot_loss[loss=0.3189, simple_loss=0.3656, pruned_loss=0.1361, over 1423831.16 frames.], batch size: 17, lr: 1.81e-03
2022-05-26 15:54:23,703 INFO [train.py:842] (3/4) Epoch 2, batch 3450, loss[loss=0.276, simple_loss=0.3334, pruned_loss=0.1093, over 7274.00 frames.], tot_loss[loss=0.3192, simple_loss=0.3656, pruned_loss=0.1364, over 1425946.39 frames.], batch size: 24, lr: 1.81e-03
2022-05-26 15:55:02,068 INFO [train.py:842] (3/4) Epoch 2, batch 3500, loss[loss=0.2829, simple_loss=0.3338, pruned_loss=0.116, over 6436.00 frames.], tot_loss[loss=0.3203, simple_loss=0.3667, pruned_loss=0.1369, over 1423212.87 frames.], batch size: 38, lr: 1.80e-03
2022-05-26 15:55:40,855 INFO [train.py:842] (3/4) Epoch 2, batch 3550, loss[loss=0.3148, simple_loss=0.3647, pruned_loss=0.1324, over 7286.00 frames.], tot_loss[loss=0.3203, simple_loss=0.3666, pruned_loss=0.137, over 1423340.90 frames.], batch size: 25, lr: 1.80e-03
2022-05-26 15:56:19,291 INFO [train.py:842] (3/4) Epoch 2, batch 3600, loss[loss=0.4255, simple_loss=0.4447, pruned_loss=0.2032, over 7241.00 frames.], tot_loss[loss=0.3179, simple_loss=0.3653, pruned_loss=0.1352, over 1425122.63 frames.], batch size: 20, lr: 1.80e-03
2022-05-26 15:56:58,196 INFO [train.py:842] (3/4) Epoch 2, batch 3650, loss[loss=0.2563, simple_loss=0.3048, pruned_loss=0.1039, over 6821.00 frames.], tot_loss[loss=0.3171, simple_loss=0.3648, pruned_loss=0.1347, over 1426525.05 frames.], batch size: 15, lr: 1.79e-03
2022-05-26 15:57:36,637 INFO [train.py:842] (3/4) Epoch 2, batch 3700, loss[loss=0.2795, simple_loss=0.3418, pruned_loss=0.1086, over 7171.00 frames.], tot_loss[loss=0.3152, simple_loss=0.3641, pruned_loss=0.1332, over 1428877.66 frames.], batch size: 19, lr: 1.79e-03
2022-05-26 15:58:15,387 INFO [train.py:842] (3/4) Epoch 2, batch 3750, loss[loss=0.3497, simple_loss=0.3882, pruned_loss=0.1556, over 7277.00 frames.], tot_loss[loss=0.317, simple_loss=0.3652, pruned_loss=0.1344, over 1429752.06 frames.], batch size: 24, lr: 1.79e-03
2022-05-26 15:58:54,106 INFO [train.py:842] (3/4) Epoch 2, batch 3800, loss[loss=0.3151, simple_loss=0.3431, pruned_loss=0.1436, over 6992.00 frames.], tot_loss[loss=0.3173, simple_loss=0.365, pruned_loss=0.1348, over 1430144.97 frames.], batch size: 16, lr: 1.79e-03
2022-05-26 15:59:32,922 INFO [train.py:842] (3/4) Epoch 2, batch 3850, loss[loss=0.3383, simple_loss=0.3876, pruned_loss=0.1445, over 7201.00 frames.], tot_loss[loss=0.3156, simple_loss=0.3641, pruned_loss=0.1335, over 1430331.51 frames.], batch size: 22, lr: 1.78e-03
2022-05-26 16:00:11,515 INFO [train.py:842] (3/4) Epoch 2, batch 3900, loss[loss=0.3268, simple_loss=0.3782, pruned_loss=0.1377, over 6163.00 frames.], tot_loss[loss=0.3147, simple_loss=0.3636, pruned_loss=0.1329, over 1432263.15 frames.], batch size: 37, lr: 1.78e-03
2022-05-26 16:00:50,507 INFO [train.py:842] (3/4) Epoch 2, batch 3950, loss[loss=0.3886, simple_loss=0.423, pruned_loss=0.1771, over 7311.00 frames.], tot_loss[loss=0.3136, simple_loss=0.3625, pruned_loss=0.1323, over 1429907.05 frames.], batch size: 21, lr: 1.78e-03
2022-05-26 16:01:29,042 INFO [train.py:842] (3/4) Epoch 2, batch 4000, loss[loss=0.4267, simple_loss=0.4319, pruned_loss=0.2107, over 4766.00 frames.], tot_loss[loss=0.3143, simple_loss=0.3631, pruned_loss=0.1328, over 1430035.56 frames.], batch size: 52, lr: 1.77e-03
2022-05-26 16:02:07,568 INFO [train.py:842] (3/4) Epoch 2, batch 4050, loss[loss=0.3098, simple_loss=0.3693, pruned_loss=0.1252, over 6809.00 frames.], tot_loss[loss=0.3155, simple_loss=0.364, pruned_loss=0.1335, over 1426030.23 frames.], batch size: 31, lr: 1.77e-03
2022-05-26 16:02:46,187 INFO [train.py:842] (3/4) Epoch 2, batch 4100, loss[loss=0.3654, simple_loss=0.3868, pruned_loss=0.172, over 7043.00 frames.], tot_loss[loss=0.3172, simple_loss=0.3649, pruned_loss=0.1348, over 1428306.10 frames.], batch size: 28, lr: 1.77e-03
2022-05-26 16:03:25,028 INFO [train.py:842] (3/4) Epoch 2, batch 4150, loss[loss=0.3264, simple_loss=0.3819, pruned_loss=0.1355, over 7101.00 frames.], tot_loss[loss=0.3159, simple_loss=0.3636, pruned_loss=0.1341, over 1424944.61 frames.], batch size: 26, lr: 1.76e-03
2022-05-26 16:04:03,615 INFO [train.py:842] (3/4) Epoch 2, batch 4200, loss[loss=0.2704, simple_loss=0.3268, pruned_loss=0.107, over 6991.00 frames.], tot_loss[loss=0.3167, simple_loss=0.3646, pruned_loss=0.1344, over 1424063.68 frames.], batch size: 16, lr: 1.76e-03
2022-05-26 16:04:42,409 INFO [train.py:842] (3/4) Epoch 2, batch 4250, loss[loss=0.3167, simple_loss=0.3706, pruned_loss=0.1314, over 7205.00 frames.], tot_loss[loss=0.3158, simple_loss=0.3641, pruned_loss=0.1338, over 1422513.76 frames.], batch size: 22, lr: 1.76e-03
2022-05-26 16:05:21,018 INFO [train.py:842] (3/4) Epoch 2, batch 4300, loss[loss=0.337, simple_loss=0.3891, pruned_loss=0.1424, over 7344.00 frames.], tot_loss[loss=0.3147, simple_loss=0.3633, pruned_loss=0.133, over 1425348.35 frames.], batch size: 22, lr: 1.76e-03
2022-05-26 16:05:59,684 INFO [train.py:842] (3/4) Epoch 2, batch 4350, loss[loss=0.2736, simple_loss=0.3348, pruned_loss=0.1062, over 7158.00 frames.], tot_loss[loss=0.3129, simple_loss=0.3617, pruned_loss=0.1321, over 1422371.50 frames.], batch size: 19, lr: 1.75e-03
2022-05-26 16:06:38,248 INFO [train.py:842] (3/4) Epoch 2, batch 4400, loss[loss=0.2519, simple_loss=0.3229, pruned_loss=0.09046, over 7282.00 frames.], tot_loss[loss=0.31, simple_loss=0.3598, pruned_loss=0.1301, over 1423774.00 frames.], batch size: 24, lr: 1.75e-03
2022-05-26 16:07:17,571 INFO [train.py:842] (3/4) Epoch 2, batch 4450, loss[loss=0.2911, simple_loss=0.3397, pruned_loss=0.1212, over 7419.00 frames.], tot_loss[loss=0.3092, simple_loss=0.3592, pruned_loss=0.1296, over 1424859.33 frames.], batch size: 18, lr: 1.75e-03
2022-05-26 16:07:56,070 INFO [train.py:842] (3/4) Epoch 2, batch 4500, loss[loss=0.3217, simple_loss=0.3735, pruned_loss=0.1349, over 7322.00 frames.], tot_loss[loss=0.3119, simple_loss=0.3608, pruned_loss=0.1315, over 1426409.15 frames.], batch size: 20, lr: 1.74e-03
2022-05-26 16:08:34,952 INFO [train.py:842] (3/4) Epoch 2, batch 4550, loss[loss=0.3876, simple_loss=0.4195, pruned_loss=0.1778, over 7274.00 frames.], tot_loss[loss=0.3112, simple_loss=0.3609, pruned_loss=0.1307, over 1426604.46 frames.], batch size: 18, lr: 1.74e-03
2022-05-26 16:09:13,327 INFO [train.py:842] (3/4) Epoch 2, batch 4600, loss[loss=0.3547, simple_loss=0.3961, pruned_loss=0.1567, over 7199.00 frames.], tot_loss[loss=0.3111, simple_loss=0.3609, pruned_loss=0.1306, over 1420687.62 frames.], batch size: 22, lr: 1.74e-03
2022-05-26 16:09:52,125 INFO [train.py:842] (3/4) Epoch 2, batch 4650, loss[loss=0.3369, simple_loss=0.3719, pruned_loss=0.1509, over 7324.00 frames.], tot_loss[loss=0.3105, simple_loss=0.3606, pruned_loss=0.1303, over 1423664.59 frames.], batch size: 25, lr: 1.74e-03
2022-05-26 16:10:30,656 INFO [train.py:842] (3/4) Epoch 2, batch 4700, loss[loss=0.3644, simple_loss=0.4117, pruned_loss=0.1585, over 7327.00 frames.], tot_loss[loss=0.3108, simple_loss=0.3612, pruned_loss=0.1302, over 1425316.62 frames.], batch size: 21, lr: 1.73e-03
2022-05-26 16:11:09,339 INFO [train.py:842] (3/4) Epoch 2, batch 4750, loss[loss=0.332, simple_loss=0.3842, pruned_loss=0.14, over 7414.00 frames.], tot_loss[loss=0.3129, simple_loss=0.3623, pruned_loss=0.1317, over 1417238.41 frames.], batch size: 21, lr: 1.73e-03
2022-05-26 16:11:47,787 INFO [train.py:842] (3/4) Epoch 2, batch 4800, loss[loss=0.2922, simple_loss=0.3553, pruned_loss=0.1145, over 7269.00 frames.], tot_loss[loss=0.3136, simple_loss=0.3633, pruned_loss=0.132, over 1415718.03 frames.], batch size: 24, lr: 1.73e-03
2022-05-26 16:12:26,413 INFO [train.py:842] (3/4) Epoch 2, batch 4850, loss[loss=0.3033, simple_loss=0.3426, pruned_loss=0.132, over 7160.00 frames.], tot_loss[loss=0.3151, simple_loss=0.3641, pruned_loss=0.1331, over 1416148.44 frames.], batch size: 18, lr: 1.73e-03
2022-05-26 16:13:04,891 INFO [train.py:842] (3/4) Epoch 2, batch 4900, loss[loss=0.2711, simple_loss=0.3319, pruned_loss=0.1051, over 7302.00 frames.], tot_loss[loss=0.3122, simple_loss=0.3619, pruned_loss=0.1312, over 1418752.55 frames.], batch size: 17, lr: 1.72e-03
2022-05-26 16:13:43,586 INFO [train.py:842] (3/4) Epoch 2, batch 4950, loss[loss=0.3156, simple_loss=0.3662, pruned_loss=0.1325, over 7235.00 frames.], tot_loss[loss=0.3114, simple_loss=0.3613, pruned_loss=0.1307, over 1421007.95 frames.], batch size: 20, lr: 1.72e-03
2022-05-26 16:14:22,297 INFO [train.py:842] (3/4) Epoch 2, batch 5000, loss[loss=0.2473, simple_loss=0.2966, pruned_loss=0.09896, over 7292.00 frames.], tot_loss[loss=0.3116, simple_loss=0.3611, pruned_loss=0.131, over 1423450.20 frames.], batch size: 17, lr: 1.72e-03
2022-05-26 16:15:00,739 INFO [train.py:842] (3/4) Epoch 2, batch 5050, loss[loss=0.3258, simple_loss=0.3677, pruned_loss=0.1419, over 7410.00 frames.], tot_loss[loss=0.3143, simple_loss=0.3628, pruned_loss=0.1328, over 1417422.27 frames.], batch size: 21, lr: 1.71e-03
2022-05-26 16:15:39,320 INFO [train.py:842] (3/4) Epoch 2, batch 5100, loss[loss=0.2724, simple_loss=0.3318, pruned_loss=0.1065, over 7165.00 frames.], tot_loss[loss=0.3099, simple_loss=0.36, pruned_loss=0.1299, over 1420209.52 frames.], batch size: 19, lr: 1.71e-03
2022-05-26 16:16:18,370 INFO [train.py:842] (3/4) Epoch 2, batch 5150, loss[loss=0.3404, simple_loss=0.3907, pruned_loss=0.145, over 7214.00 frames.], tot_loss[loss=0.311, simple_loss=0.3611, pruned_loss=0.1305, over 1421585.66 frames.], batch size: 21, lr: 1.71e-03
2022-05-26 16:16:56,916 INFO [train.py:842] (3/4) Epoch 2, batch 5200, loss[loss=0.3671, simple_loss=0.3987, pruned_loss=0.1677, over 7250.00 frames.], tot_loss[loss=0.3104, simple_loss=0.3611, pruned_loss=0.1298, over 1421911.00 frames.], batch size: 25, lr: 1.71e-03
2022-05-26 16:17:35,695 INFO [train.py:842] (3/4) Epoch 2, batch 5250, loss[loss=0.3253, simple_loss=0.3755, pruned_loss=0.1375, over 6863.00 frames.], tot_loss[loss=0.312, simple_loss=0.362, pruned_loss=0.131, over 1424294.58 frames.], batch size: 31, lr: 1.70e-03
2022-05-26 16:18:14,234 INFO [train.py:842] (3/4) Epoch 2, batch 5300, loss[loss=0.2967, simple_loss=0.3632, pruned_loss=0.1151, over 7369.00 frames.], tot_loss[loss=0.3094, simple_loss=0.3599, pruned_loss=0.1295, over 1420983.75 frames.], batch size: 23, lr: 1.70e-03
2022-05-26 16:18:53,034 INFO [train.py:842] (3/4) Epoch 2, batch 5350, loss[loss=0.2429, simple_loss=0.3103, pruned_loss=0.08772, over 7359.00 frames.], tot_loss[loss=0.3071, simple_loss=0.3577, pruned_loss=0.1283, over 1418496.45 frames.], batch size: 19, lr: 1.70e-03
2022-05-26 16:19:31,681 INFO [train.py:842] (3/4) Epoch 2, batch 5400, loss[loss=0.3101, simple_loss=0.3774, pruned_loss=0.1214, over 6545.00 frames.], tot_loss[loss=0.3068, simple_loss=0.357, pruned_loss=0.1283, over 1418527.16 frames.], batch size: 38, lr: 1.70e-03
2022-05-26 16:20:10,826 INFO [train.py:842] (3/4) Epoch 2, batch 5450, loss[loss=0.3225, simple_loss=0.3502, pruned_loss=0.1474, over 7216.00 frames.], tot_loss[loss=0.306, simple_loss=0.3566, pruned_loss=0.1277, over 1420110.43 frames.], batch size: 16, lr: 1.69e-03
2022-05-26 16:20:49,324 INFO [train.py:842] (3/4) Epoch 2, batch 5500, loss[loss=0.2555, simple_loss=0.3164, pruned_loss=0.09725, over 7127.00 frames.], tot_loss[loss=0.3058, simple_loss=0.3565, pruned_loss=0.1275, over 1421907.45 frames.], batch size: 17, lr: 1.69e-03
2022-05-26 16:21:28,406 INFO [train.py:842] (3/4) Epoch 2, batch 5550, loss[loss=0.2507, simple_loss=0.3025, pruned_loss=0.09949, over 7004.00 frames.], tot_loss[loss=0.3055, simple_loss=0.3562, pruned_loss=0.1274, over 1422986.50 frames.], batch size: 16, lr: 1.69e-03
2022-05-26 16:22:06,838 INFO [train.py:842] (3/4) Epoch 2, batch 5600, loss[loss=0.402, simple_loss=0.4468, pruned_loss=0.1786, over 7309.00 frames.], tot_loss[loss=0.3063, simple_loss=0.3573, pruned_loss=0.1276, over 1423246.86 frames.], batch size: 24, lr: 1.69e-03
2022-05-26 16:22:45,474 INFO [train.py:842] (3/4) Epoch 2, batch 5650, loss[loss=0.3095, simple_loss=0.3765, pruned_loss=0.1212, over 7201.00 frames.], tot_loss[loss=0.3084, simple_loss=0.3592, pruned_loss=0.1287, over 1424465.80 frames.], batch size: 23, lr: 1.68e-03
2022-05-26 16:23:24,177 INFO [train.py:842] (3/4) Epoch 2, batch 5700, loss[loss=0.2217, simple_loss=0.2776, pruned_loss=0.08293, over 7286.00 frames.], tot_loss[loss=0.3071, simple_loss=0.3578, pruned_loss=0.1281, over 1422926.36 frames.], batch size: 18, lr: 1.68e-03
2022-05-26 16:24:03,266 INFO [train.py:842] (3/4) Epoch 2, batch 5750, loss[loss=0.3468, simple_loss=0.3962, pruned_loss=0.1487, over 7312.00 frames.], tot_loss[loss=0.3074, simple_loss=0.3576, pruned_loss=0.1286, over 1421166.56 frames.], batch size: 21, lr: 1.68e-03
2022-05-26 16:24:41,898 INFO [train.py:842] (3/4) Epoch 2, batch 5800, loss[loss=0.3388, simple_loss=0.393, pruned_loss=0.1423, over 7127.00 frames.], tot_loss[loss=0.3071, simple_loss=0.3578, pruned_loss=0.1282, over 1425041.09 frames.], batch size: 26, lr: 1.68e-03
2022-05-26 16:25:20,724 INFO [train.py:842] (3/4) Epoch 2, batch 5850, loss[loss=0.2549, simple_loss=0.3239, pruned_loss=0.09289, over 7417.00 frames.], tot_loss[loss=0.308, simple_loss=0.3589, pruned_loss=0.1285, over 1420518.68 frames.], batch size: 21, lr: 1.67e-03
2022-05-26 16:26:08,852 INFO [train.py:842] (3/4) Epoch 2, batch 5900, loss[loss=0.295, simple_loss=0.3317, pruned_loss=0.1291, over 7280.00 frames.], tot_loss[loss=0.3068, simple_loss=0.3582, pruned_loss=0.1277, over 1423287.50 frames.], batch size: 17, lr: 1.67e-03
2022-05-26 16:26:47,929 INFO [train.py:842] (3/4) Epoch 2, batch 5950, loss[loss=0.3334, simple_loss=0.3849, pruned_loss=0.1409, over 7218.00 frames.], tot_loss[loss=0.3094, simple_loss=0.36, pruned_loss=0.1293, over 1422512.11 frames.], batch size: 22, lr: 1.67e-03
2022-05-26 16:27:26,500 INFO [train.py:842] (3/4) Epoch 2, batch 6000, loss[loss=0.2537, simple_loss=0.3173, pruned_loss=0.09505, over 7415.00 frames.], tot_loss[loss=0.3075, simple_loss=0.3588, pruned_loss=0.1281, over 1418877.91 frames.], batch size: 21, lr: 1.67e-03
2022-05-26 16:27:26,501 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 16:27:35,907 INFO [train.py:871] (3/4) Epoch 2, validation: loss=0.2259, simple_loss=0.3198, pruned_loss=0.06603, over 868885.00 frames.
2022-05-26 16:28:15,164 INFO [train.py:842] (3/4) Epoch 2, batch 6050, loss[loss=0.2603, simple_loss=0.3367, pruned_loss=0.09193, over 7194.00 frames.], tot_loss[loss=0.3069, simple_loss=0.3585, pruned_loss=0.1277, over 1423295.48 frames.], batch size: 23, lr: 1.66e-03
2022-05-26 16:28:53,614 INFO [train.py:842] (3/4) Epoch 2, batch 6100, loss[loss=0.2707, simple_loss=0.3451, pruned_loss=0.09815, over 7387.00 frames.], tot_loss[loss=0.3064, simple_loss=0.3579, pruned_loss=0.1274, over 1425355.55 frames.], batch size: 23, lr: 1.66e-03
2022-05-26 16:29:42,232 INFO [train.py:842] (3/4) Epoch 2, batch 6150, loss[loss=0.2945, simple_loss=0.3544, pruned_loss=0.1173, over 7080.00 frames.], tot_loss[loss=0.3037, simple_loss=0.3556, pruned_loss=0.1259, over 1425889.11 frames.], batch size: 28, lr: 1.66e-03
2022-05-26 16:30:39,581 INFO [train.py:842] (3/4) Epoch 2, batch 6200, loss[loss=0.3815, simple_loss=0.4174, pruned_loss=0.1728, over 6739.00 frames.], tot_loss[loss=0.3049, simple_loss=0.3566, pruned_loss=0.1266, over 1423370.45 frames.], batch size: 31, lr: 1.66e-03
2022-05-26 16:31:18,966 INFO [train.py:842] (3/4) Epoch 2, batch 6250, loss[loss=0.2656, simple_loss=0.3403, pruned_loss=0.09546, over 7111.00 frames.], tot_loss[loss=0.306, simple_loss=0.3573, pruned_loss=0.1273, over 1426520.31 frames.], batch size: 21, lr: 1.65e-03
2022-05-26 16:31:57,571 INFO [train.py:842] (3/4) Epoch 2, batch 6300, loss[loss=0.3223, simple_loss=0.3721, pruned_loss=0.1362, over 7201.00 frames.], tot_loss[loss=0.3026, simple_loss=0.3553, pruned_loss=0.125, over 1430635.94 frames.], batch size: 26, lr: 1.65e-03
2022-05-26 16:32:36,121 INFO [train.py:842] (3/4) Epoch 2, batch 6350, loss[loss=0.3285, simple_loss=0.3799, pruned_loss=0.1386, over 6315.00 frames.], tot_loss[loss=0.3044, simple_loss=0.3568, pruned_loss=0.1259, over 1429864.80 frames.], batch size: 38, lr: 1.65e-03
2022-05-26 16:33:14,722 INFO [train.py:842] (3/4) Epoch 2, batch 6400, loss[loss=0.3403, simple_loss=0.3824, pruned_loss=0.1492, over 6775.00 frames.], tot_loss[loss=0.3069, simple_loss=0.3578, pruned_loss=0.128, over 1425028.12 frames.], batch size: 31, lr: 1.65e-03
2022-05-26 16:33:53,452 INFO [train.py:842] (3/4) Epoch 2, batch 6450, loss[loss=0.2954, simple_loss=0.3373, pruned_loss=0.1268, over 7422.00 frames.], tot_loss[loss=0.306, simple_loss=0.3573, pruned_loss=0.1274, over 1425054.92 frames.], batch size: 18, lr: 1.64e-03
2022-05-26 16:34:31,952 INFO [train.py:842] (3/4) Epoch 2, batch 6500, loss[loss=0.3056, simple_loss=0.366, pruned_loss=0.1226, over 7227.00 frames.], tot_loss[loss=0.304, simple_loss=0.3562, pruned_loss=0.1259, over 1424925.62 frames.], batch size: 22, lr: 1.64e-03
2022-05-26 16:35:10,772 INFO [train.py:842] (3/4) Epoch 2, batch 6550, loss[loss=0.284, simple_loss=0.3311, pruned_loss=0.1184, over 7075.00 frames.], tot_loss[loss=0.3039, simple_loss=0.3562, pruned_loss=0.1258, over 1421260.50 frames.], batch size: 18, lr: 1.64e-03
2022-05-26 16:35:49,287 INFO [train.py:842] (3/4) Epoch 2, batch 6600, loss[loss=0.3251, simple_loss=0.3535, pruned_loss=0.1483, over 7280.00 frames.], tot_loss[loss=0.3025, simple_loss=0.3552, pruned_loss=0.1249, over 1420820.08 frames.], batch size: 18, lr: 1.64e-03
2022-05-26 16:36:27,752 INFO [train.py:842] (3/4) Epoch 2, batch 6650, loss[loss=0.3297, simple_loss=0.3852, pruned_loss=0.137, over 7209.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3551, pruned_loss=0.1248, over 1414368.08 frames.], batch size: 23, lr: 1.63e-03
2022-05-26 16:37:06,267 INFO [train.py:842] (3/4) Epoch 2, batch 6700, loss[loss=0.2378, simple_loss=0.2927, pruned_loss=0.0914, over 7292.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3533, pruned_loss=0.123, over 1419489.49 frames.], batch size: 17, lr: 1.63e-03
2022-05-26 16:37:45,016 INFO [train.py:842] (3/4) Epoch 2, batch 6750, loss[loss=0.2699, simple_loss=0.3403, pruned_loss=0.09972, over 7230.00 frames.], tot_loss[loss=0.3025, simple_loss=0.3557, pruned_loss=0.1247, over 1421944.63 frames.], batch size: 20, lr: 1.63e-03
2022-05-26 16:38:23,583 INFO [train.py:842] (3/4) Epoch 2, batch 6800, loss[loss=0.3524, simple_loss=0.4085, pruned_loss=0.1481, over 7117.00 frames.], tot_loss[loss=0.3034, simple_loss=0.3564, pruned_loss=0.1252, over 1424931.19 frames.], batch size: 21, lr: 1.63e-03
2022-05-26 16:39:05,229 INFO [train.py:842] (3/4) Epoch 2, batch 6850, loss[loss=0.3073, simple_loss=0.3554, pruned_loss=0.1296, over 7330.00 frames.], tot_loss[loss=0.3029, simple_loss=0.3563, pruned_loss=0.1248, over 1421837.80 frames.], batch size: 20, lr: 1.63e-03
2022-05-26 16:39:43,800 INFO [train.py:842] (3/4) Epoch 2, batch 6900, loss[loss=0.3378, simple_loss=0.387, pruned_loss=0.1443, over 7424.00 frames.], tot_loss[loss=0.3033, simple_loss=0.3567, pruned_loss=0.125, over 1422544.10 frames.], batch size: 20, lr: 1.62e-03
2022-05-26 16:40:22,603 INFO [train.py:842] (3/4) Epoch 2, batch 6950, loss[loss=0.2101, simple_loss=0.2854, pruned_loss=0.06742, over 7296.00 frames.], tot_loss[loss=0.3017, simple_loss=0.3555, pruned_loss=0.124, over 1422019.41 frames.], batch size: 18, lr: 1.62e-03
2022-05-26 16:41:01,162 INFO [train.py:842] (3/4) Epoch 2, batch 7000, loss[loss=0.2906, simple_loss=0.3481, pruned_loss=0.1165, over 7334.00 frames.], tot_loss[loss=0.3014, simple_loss=0.355, pruned_loss=0.1239, over 1424457.52 frames.], batch size: 21, lr: 1.62e-03
2022-05-26 16:41:40,653 INFO [train.py:842] (3/4) Epoch 2, batch 7050, loss[loss=0.3981, simple_loss=0.4136, pruned_loss=0.1913, over 5189.00 frames.], tot_loss[loss=0.2995, simple_loss=0.3532, pruned_loss=0.1229, over 1427301.70 frames.], batch size: 52, lr: 1.62e-03
2022-05-26 16:42:19,194 INFO [train.py:842] (3/4) Epoch 2, batch 7100, loss[loss=0.2532, simple_loss=0.3217, pruned_loss=0.09229, over 7114.00 frames.], tot_loss[loss=0.301, simple_loss=0.3543, pruned_loss=0.1239, over 1426429.00 frames.], batch size: 21, lr: 1.61e-03
2022-05-26 16:42:57,892 INFO [train.py:842] (3/4) Epoch 2, batch 7150, loss[loss=0.2651, simple_loss=0.3348, pruned_loss=0.09764, over 7412.00 frames.], tot_loss[loss=0.3036, simple_loss=0.3564, pruned_loss=0.1254, over 1422674.00 frames.], batch size: 21, lr: 1.61e-03
2022-05-26 16:43:36,584 INFO [train.py:842] (3/4) Epoch 2, batch 7200, loss[loss=0.2528, simple_loss=0.3046, pruned_loss=0.1005, over 6990.00 frames.], tot_loss[loss=0.3047, simple_loss=0.3571, pruned_loss=0.1262, over 1420277.64 frames.], batch size: 16, lr: 1.61e-03
2022-05-26 16:44:15,871 INFO [train.py:842] (3/4) Epoch 2, batch 7250, loss[loss=0.2869, simple_loss=0.3585, pruned_loss=0.1076, over 7233.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3557, pruned_loss=0.1244, over 1425372.70 frames.], batch size: 20, lr: 1.61e-03
2022-05-26 16:44:54,473 INFO [train.py:842] (3/4) Epoch 2, batch 7300, loss[loss=0.4295, simple_loss=0.4365, pruned_loss=0.2112, over 7228.00 frames.], tot_loss[loss=0.3015, simple_loss=0.355, pruned_loss=0.124, over 1427991.91 frames.], batch size: 21, lr: 1.60e-03
2022-05-26 16:45:33,707 INFO [train.py:842] (3/4) Epoch 2, batch 7350, loss[loss=0.3946, simple_loss=0.405, pruned_loss=0.1921, over 4979.00 frames.], tot_loss[loss=0.3013, simple_loss=0.354, pruned_loss=0.1243, over 1423924.97 frames.], batch size: 52, lr: 1.60e-03
2022-05-26 16:46:12,356 INFO [train.py:842] (3/4) Epoch 2, batch 7400, loss[loss=0.2593, simple_loss=0.3149, pruned_loss=0.1019, over 6982.00 frames.], tot_loss[loss=0.3027, simple_loss=0.3545, pruned_loss=0.1255, over 1423510.36 frames.], batch size: 16, lr: 1.60e-03
2022-05-26 16:46:51,035 INFO [train.py:842] (3/4) Epoch 2, batch 7450, loss[loss=0.2576, simple_loss=0.3222, pruned_loss=0.09646, over 7353.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3543, pruned_loss=0.1251, over 1418825.07 frames.], batch size: 19, lr: 1.60e-03
2022-05-26 16:47:29,545 INFO [train.py:842] (3/4) Epoch 2, batch 7500, loss[loss=0.2468, simple_loss=0.3207, pruned_loss=0.08641, over 7217.00 frames.], tot_loss[loss=0.3032, simple_loss=0.3548, pruned_loss=0.1258, over 1419837.47 frames.], batch size: 21, lr: 1.60e-03
2022-05-26 16:48:08,286 INFO [train.py:842] (3/4) Epoch 2, batch 7550, loss[loss=0.2963, simple_loss=0.3498, pruned_loss=0.1214, over 7400.00 frames.], tot_loss[loss=0.2997, simple_loss=0.353, pruned_loss=0.1232, over 1420707.99 frames.], batch size: 21, lr: 1.59e-03
2022-05-26 16:48:46,900 INFO [train.py:842] (3/4) Epoch 2, batch 7600, loss[loss=0.3536, simple_loss=0.4013, pruned_loss=0.1529, over 5214.00 frames.], tot_loss[loss=0.2985, simple_loss=0.3518, pruned_loss=0.1226, over 1420868.39 frames.], batch size: 52, lr: 1.59e-03
2022-05-26 16:49:26,111 INFO [train.py:842] (3/4) Epoch 2, batch 7650, loss[loss=0.3264, simple_loss=0.3779, pruned_loss=0.1374, over 7404.00 frames.], tot_loss[loss=0.2978, simple_loss=0.3513, pruned_loss=0.1222, over 1421445.41 frames.], batch size: 21, lr: 1.59e-03
2022-05-26 16:50:04,718 INFO [train.py:842] (3/4) Epoch 2, batch 7700, loss[loss=0.3715, simple_loss=0.4089, pruned_loss=0.1671, over 7335.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3518, pruned_loss=0.1223, over 1422074.30 frames.], batch size: 22, lr: 1.59e-03
2022-05-26 16:50:43,502 INFO [train.py:842] (3/4) Epoch 2, batch 7750, loss[loss=0.2759, simple_loss=0.3446, pruned_loss=0.1036, over 6970.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3524, pruned_loss=0.122, over 1424092.93 frames.], batch size: 28, lr: 1.59e-03
2022-05-26 16:51:21,999 INFO [train.py:842] (3/4) Epoch 2, batch 7800, loss[loss=0.3311, simple_loss=0.3951, pruned_loss=0.1335, over 7149.00 frames.], tot_loss[loss=0.297, simple_loss=0.3519, pruned_loss=0.121, over 1423096.84 frames.], batch size: 20, lr: 1.58e-03
2022-05-26 16:52:00,807 INFO [train.py:842] (3/4) Epoch 2, batch 7850, loss[loss=0.3166, simple_loss=0.3744, pruned_loss=0.1294, over 7338.00 frames.], tot_loss[loss=0.2983, simple_loss=0.3526, pruned_loss=0.122, over 1423634.63 frames.], batch size: 21, lr: 1.58e-03
2022-05-26 16:52:39,340 INFO [train.py:842] (3/4) Epoch 2, batch 7900, loss[loss=0.3521, simple_loss=0.3769, pruned_loss=0.1636, over 5241.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3528, pruned_loss=0.1224, over 1425831.81 frames.], batch size: 52, lr: 1.58e-03
2022-05-26 16:53:18,143 INFO [train.py:842] (3/4) Epoch 2, batch 7950, loss[loss=0.3197, simple_loss=0.3541, pruned_loss=0.1426, over 7180.00 frames.], tot_loss[loss=0.2983, simple_loss=0.3524, pruned_loss=0.1221, over 1428328.41 frames.], batch size: 18, lr: 1.58e-03
2022-05-26 16:53:56,772 INFO [train.py:842] (3/4) Epoch 2, batch 8000, loss[loss=0.3171, simple_loss=0.3721, pruned_loss=0.1311, over 7214.00 frames.], tot_loss[loss=0.2961, simple_loss=0.3514, pruned_loss=0.1204, over 1426872.51 frames.], batch size: 21, lr: 1.57e-03
2022-05-26 16:54:35,623 INFO [train.py:842] (3/4) Epoch 2, batch 8050, loss[loss=0.3108, simple_loss=0.3652, pruned_loss=0.1282, over 6374.00 frames.], tot_loss[loss=0.2959, simple_loss=0.3509, pruned_loss=0.1204, over 1425085.17 frames.], batch size: 38, lr: 1.57e-03
2022-05-26 16:55:14,286 INFO [train.py:842] (3/4) Epoch 2, batch 8100, loss[loss=0.3149, simple_loss=0.3661, pruned_loss=0.1318, over 7119.00 frames.], tot_loss[loss=0.2943, simple_loss=0.3496, pruned_loss=0.1195, over 1427266.96 frames.], batch size: 26, lr: 1.57e-03
2022-05-26 16:55:53,041 INFO [train.py:842] (3/4) Epoch 2, batch 8150, loss[loss=0.2791, simple_loss=0.3266, pruned_loss=0.1158, over 7068.00 frames.], tot_loss[loss=0.2926, simple_loss=0.3483, pruned_loss=0.1185, over 1429564.72 frames.], batch size: 18, lr: 1.57e-03
2022-05-26 16:56:31,572 INFO [train.py:842] (3/4) Epoch 2, batch 8200, loss[loss=0.2973, simple_loss=0.3407, pruned_loss=0.1269, over 7260.00 frames.], tot_loss[loss=0.297, simple_loss=0.3514, pruned_loss=0.1213, over 1424123.91 frames.], batch size: 18, lr: 1.57e-03
2022-05-26 16:57:10,908 INFO [train.py:842] (3/4) Epoch 2, batch 8250, loss[loss=0.2879, simple_loss=0.3561, pruned_loss=0.1098, over 6987.00 frames.], tot_loss[loss=0.2974, simple_loss=0.3514, pruned_loss=0.1217, over 1422567.10 frames.], batch size: 28, lr: 1.56e-03
2022-05-26 16:57:49,500 INFO [train.py:842] (3/4) Epoch 2, batch 8300, loss[loss=0.3251, simple_loss=0.3773, pruned_loss=0.1365, over 7134.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3523, pruned_loss=0.1227, over 1420468.30 frames.], batch size: 20, lr: 1.56e-03
2022-05-26 16:58:28,240 INFO [train.py:842] (3/4) Epoch 2, batch 8350, loss[loss=0.4564, simple_loss=0.4598, pruned_loss=0.2265, over 5121.00 frames.], tot_loss[loss=0.2992, simple_loss=0.3528, pruned_loss=0.1228, over 1417925.11 frames.], batch size: 52, lr: 1.56e-03
2022-05-26 16:59:06,611 INFO [train.py:842] (3/4) Epoch 2, batch 8400, loss[loss=0.2459, simple_loss=0.3113, pruned_loss=0.09026, over 7127.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3532, pruned_loss=0.1227, over 1417208.74 frames.], batch size: 17, lr: 1.56e-03
2022-05-26 16:59:45,124 INFO [train.py:842] (3/4) Epoch 2, batch 8450, loss[loss=0.3261, simple_loss=0.3845, pruned_loss=0.1338, over 7213.00 frames.], tot_loss[loss=0.2998, simple_loss=0.3539, pruned_loss=0.1229, over 1413238.75 frames.], batch size: 22, lr: 1.56e-03
2022-05-26 17:00:23,734 INFO [train.py:842] (3/4) Epoch 2, batch 8500, loss[loss=0.2602, simple_loss=0.3133, pruned_loss=0.1035, over 7123.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3544, pruned_loss=0.1234, over 1417758.02 frames.], batch size: 17, lr: 1.55e-03
2022-05-26 17:01:02,437 INFO [train.py:842] (3/4) Epoch 2, batch 8550, loss[loss=0.2796, simple_loss=0.3326, pruned_loss=0.1133, over 7357.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3547, pruned_loss=0.1233, over 1422680.65 frames.], batch size: 19, lr: 1.55e-03
2022-05-26 17:01:41,165 INFO [train.py:842] (3/4) Epoch 2, batch 8600, loss[loss=0.3315, simple_loss=0.3836, pruned_loss=0.1397, over 6588.00 frames.], tot_loss[loss=0.2969, simple_loss=0.3519, pruned_loss=0.121, over 1421311.22 frames.], batch size: 38, lr: 1.55e-03
2022-05-26 17:02:20,005 INFO [train.py:842] (3/4) Epoch 2, batch 8650, loss[loss=0.3347, simple_loss=0.3748, pruned_loss=0.1473, over 7153.00 frames.], tot_loss[loss=0.295, simple_loss=0.3503, pruned_loss=0.1198, over 1423705.99 frames.], batch size: 20, lr: 1.55e-03
2022-05-26 17:02:58,644 INFO [train.py:842] (3/4) Epoch 2, batch 8700, loss[loss=0.2555, simple_loss=0.314, pruned_loss=0.09852, over 7066.00 frames.], tot_loss[loss=0.2916, simple_loss=0.3476, pruned_loss=0.1177, over 1422456.19 frames.], batch size: 18, lr: 1.55e-03
2022-05-26 17:03:37,090 INFO [train.py:842] (3/4) Epoch 2, batch 8750, loss[loss=0.3512, simple_loss=0.3839, pruned_loss=0.1593, over 7171.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3496, pruned_loss=0.119, over 1420891.72 frames.], batch size: 18, lr: 1.54e-03
2022-05-26 17:04:15,675 INFO [train.py:842] (3/4) Epoch 2, batch 8800, loss[loss=0.3155, simple_loss=0.3721, pruned_loss=0.1295, over 7322.00 frames.], tot_loss[loss=0.2949, simple_loss=0.3494, pruned_loss=0.1202, over 1413784.11 frames.], batch size: 22, lr: 1.54e-03
2022-05-26 17:04:54,414 INFO [train.py:842] (3/4) Epoch 2, batch 8850, loss[loss=0.453, simple_loss=0.4633, pruned_loss=0.2214, over 7288.00 frames.], tot_loss[loss=0.2972, simple_loss=0.3513, pruned_loss=0.1215, over 1412079.63 frames.], batch size: 24, lr: 1.54e-03
2022-05-26 17:05:32,700 INFO [train.py:842] (3/4) Epoch 2, batch 8900, loss[loss=0.3818, simple_loss=0.4204, pruned_loss=0.1717, over 6693.00 frames.], tot_loss[loss=0.2994, simple_loss=0.353, pruned_loss=0.1229, over 1402096.89 frames.], batch size: 31, lr: 1.54e-03
2022-05-26 17:06:11,188 INFO [train.py:842] (3/4) Epoch 2, batch 8950, loss[loss=0.3094, simple_loss=0.3665, pruned_loss=0.1262, over 7114.00 frames.], tot_loss[loss=0.2986, simple_loss=0.3528, pruned_loss=0.1222, over 1401797.79 frames.], batch size: 21, lr: 1.54e-03
2022-05-26 17:06:49,712 INFO [train.py:842] (3/4) Epoch 2, batch 9000, loss[loss=0.3108, simple_loss=0.3551, pruned_loss=0.1332, over 7273.00 frames.], tot_loss[loss=0.2983, simple_loss=0.3528, pruned_loss=0.1219, over 1397092.03 frames.], batch size: 18, lr: 1.53e-03
2022-05-26 17:06:49,713 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 17:06:59,110 INFO [train.py:871] (3/4) Epoch 2, validation: loss=0.2204, simple_loss=0.3177, pruned_loss=0.06159, over 868885.00 frames.
2022-05-26 17:07:37,636 INFO [train.py:842] (3/4) Epoch 2, batch 9050, loss[loss=0.2399, simple_loss=0.3032, pruned_loss=0.08831, over 7295.00 frames.], tot_loss[loss=0.2991, simple_loss=0.3533, pruned_loss=0.1225, over 1381892.84 frames.], batch size: 18, lr: 1.53e-03
2022-05-26 17:08:15,233 INFO [train.py:842] (3/4) Epoch 2, batch 9100, loss[loss=0.3255, simple_loss=0.361, pruned_loss=0.145, over 4951.00 frames.], tot_loss[loss=0.304, simple_loss=0.357, pruned_loss=0.1255, over 1328823.15 frames.], batch size: 52, lr: 1.53e-03
2022-05-26 17:08:52,781 INFO [train.py:842] (3/4) Epoch 2, batch 9150, loss[loss=0.2951, simple_loss=0.3437, pruned_loss=0.1232, over 4852.00 frames.], tot_loss[loss=0.3135, simple_loss=0.3631, pruned_loss=0.132, over 1256508.25 frames.], batch size: 52, lr: 1.53e-03
2022-05-26 17:09:46,536 INFO [train.py:842] (3/4) Epoch 3, batch 0, loss[loss=0.2489, simple_loss=0.3158, pruned_loss=0.09099, over 7287.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3158, pruned_loss=0.09099, over 7287.00 frames.], batch size: 17, lr: 1.50e-03
2022-05-26 17:10:25,894 INFO [train.py:842] (3/4) Epoch 3, batch 50, loss[loss=0.3398, simple_loss=0.3931, pruned_loss=0.1433, over 7283.00 frames.], tot_loss[loss=0.2972, simple_loss=0.3515, pruned_loss=0.1214, over 322674.12 frames.], batch size: 25, lr: 1.49e-03
2022-05-26 17:11:04,580 INFO [train.py:842] (3/4) Epoch 3, batch 100, loss[loss=0.2579, simple_loss=0.3036, pruned_loss=0.1061, over 7428.00 frames.], tot_loss[loss=0.2949, simple_loss=0.3496, pruned_loss=0.1201, over 570038.54 frames.], batch size: 17, lr: 1.49e-03
2022-05-26 17:11:43,661 INFO [train.py:842] (3/4) Epoch 3, batch 150, loss[loss=0.2955, simple_loss=0.361, pruned_loss=0.115, over 6713.00 frames.], tot_loss[loss=0.2941, simple_loss=0.349, pruned_loss=0.1196, over 763207.43 frames.], batch size: 31, lr: 1.49e-03
2022-05-26 17:12:22,306 INFO [train.py:842] (3/4) Epoch 3, batch 200, loss[loss=0.3597, simple_loss=0.3738, pruned_loss=0.1728, over 6852.00 frames.], tot_loss[loss=0.2925, simple_loss=0.3475, pruned_loss=0.1187, over 901469.62 frames.], batch size: 15, lr: 1.49e-03
2022-05-26 17:13:00,909 INFO [train.py:842] (3/4) Epoch 3, batch 250, loss[loss=0.2796, simple_loss=0.3383, pruned_loss=0.1104, over 7361.00 frames.], tot_loss[loss=0.2924, simple_loss=0.348, pruned_loss=0.1184, over 1011554.83 frames.], batch size: 19, lr: 1.49e-03
2022-05-26 17:13:39,445 INFO [train.py:842] (3/4) Epoch 3, batch 300, loss[loss=0.2768, simple_loss=0.345, pruned_loss=0.1043, over 6785.00 frames.], tot_loss[loss=0.295, simple_loss=0.3501, pruned_loss=0.1199, over 1102312.64 frames.], batch size: 31, lr: 1.49e-03
2022-05-26 17:14:18,344 INFO [train.py:842] (3/4) Epoch 3, batch 350, loss[loss=0.2993, simple_loss=0.3665, pruned_loss=0.1161, over 7321.00 frames.], tot_loss[loss=0.2954, simple_loss=0.3506, pruned_loss=0.1201, over 1173518.28 frames.], batch size: 21, lr: 1.48e-03
2022-05-26 17:14:56,934 INFO [train.py:842] (3/4) Epoch 3, batch 400, loss[loss=0.3562, simple_loss=0.4006, pruned_loss=0.1559, over 7269.00 frames.], tot_loss[loss=0.2979, simple_loss=0.3524, pruned_loss=0.1217, over 1224127.83 frames.], batch size: 24, lr: 1.48e-03
2022-05-26 17:15:35,602 INFO [train.py:842] (3/4) Epoch 3, batch 450, loss[loss=0.2964, simple_loss=0.3672, pruned_loss=0.1128, over 7188.00 frames.], tot_loss[loss=0.2976, simple_loss=0.353, pruned_loss=0.1211, over 1264659.34 frames.], batch size: 22, lr: 1.48e-03
2022-05-26 17:16:14,218 INFO [train.py:842] (3/4) Epoch 3, batch 500, loss[loss=0.3152, simple_loss=0.3387, pruned_loss=0.1458, over 6996.00 frames.], tot_loss[loss=0.2944, simple_loss=0.3506, pruned_loss=0.1191, over 1302181.16 frames.], batch size: 16, lr: 1.48e-03
2022-05-26 17:16:53,117 INFO [train.py:842] (3/4) Epoch 3, batch 550, loss[loss=0.3163, simple_loss=0.3622, pruned_loss=0.1352, over 7225.00 frames.], tot_loss[loss=0.2945, simple_loss=0.3507, pruned_loss=0.1192, over 1332010.81 frames.], batch size: 21, lr: 1.48e-03
2022-05-26 17:17:31,921 INFO [train.py:842] (3/4) Epoch 3, batch 600, loss[loss=0.3128, simple_loss=0.36, pruned_loss=0.1328, over 7309.00 frames.], tot_loss[loss=0.2918, simple_loss=0.348, pruned_loss=0.1178, over 1353349.61 frames.], batch size: 25, lr: 1.47e-03
2022-05-26 17:18:10,653 INFO [train.py:842] (3/4) Epoch 3, batch 650, loss[loss=0.2779, simple_loss=0.3322, pruned_loss=0.1118, over 7357.00 frames.], tot_loss[loss=0.2909, simple_loss=0.3477, pruned_loss=0.1171, over 1368418.32 frames.], batch size: 19, lr: 1.47e-03
2022-05-26 17:18:49,285 INFO [train.py:842] (3/4) Epoch 3, batch 700, loss[loss=0.3152, simple_loss=0.3808, pruned_loss=0.1248, over 7225.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3474, pruned_loss=0.1166, over 1378163.13 frames.], batch size: 21, lr: 1.47e-03
2022-05-26 17:19:28,527 INFO [train.py:842] (3/4) Epoch 3, batch 750, loss[loss=0.3518, simple_loss=0.3844, pruned_loss=0.1596, over 7207.00 frames.], tot_loss[loss=0.2909, simple_loss=0.3474, pruned_loss=0.1172, over 1391780.38 frames.], batch size: 23, lr: 1.47e-03
2022-05-26 17:20:07,112 INFO [train.py:842] (3/4) Epoch 3, batch 800, loss[loss=0.2747, simple_loss=0.3443, pruned_loss=0.1025, over 7219.00 frames.], tot_loss[loss=0.2892, simple_loss=0.3465, pruned_loss=0.1159, over 1403210.33 frames.], batch size: 23, lr: 1.47e-03
2022-05-26 17:20:46,503 INFO [train.py:842] (3/4) Epoch 3, batch 850, loss[loss=0.3823, simple_loss=0.4152, pruned_loss=0.1747, over 7301.00 frames.], tot_loss[loss=0.2854, simple_loss=0.3434, pruned_loss=0.1137, over 1410628.48 frames.], batch size: 25, lr: 1.47e-03
2022-05-26 17:21:24,969 INFO [train.py:842] (3/4) Epoch 3, batch 900, loss[loss=0.2524, simple_loss=0.3185, pruned_loss=0.09315, over 7074.00 frames.], tot_loss[loss=0.287, simple_loss=0.345, pruned_loss=0.1145, over 1412792.71 frames.], batch size: 18, lr: 1.46e-03
2022-05-26 17:22:03,737 INFO [train.py:842] (3/4) Epoch 3, batch 950, loss[loss=0.3488, simple_loss=0.393, pruned_loss=0.1523, over 7150.00 frames.], tot_loss[loss=0.2899, simple_loss=0.3467, pruned_loss=0.1165, over 1418127.48 frames.], batch size: 20, lr: 1.46e-03
2022-05-26 17:22:42,275 INFO [train.py:842] (3/4) Epoch 3, batch 1000, loss[loss=0.2989, simple_loss=0.3667, pruned_loss=0.1156, over 6739.00 frames.], tot_loss[loss=0.29, simple_loss=0.3469, pruned_loss=0.1165, over 1417245.38 frames.], batch size: 31, lr: 1.46e-03
2022-05-26 17:23:21,003 INFO [train.py:842] (3/4) Epoch 3, batch 1050, loss[loss=0.2599, simple_loss=0.3272, pruned_loss=0.09629, over 7276.00 frames.], tot_loss[loss=0.2911, simple_loss=0.3484, pruned_loss=0.1169, over 1415100.99 frames.], batch size: 18, lr: 1.46e-03
2022-05-26 17:23:59,521 INFO [train.py:842] (3/4) Epoch 3, batch 1100, loss[loss=0.2911, simple_loss=0.3488, pruned_loss=0.1167, over 7213.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3471, pruned_loss=0.115, over 1419791.93 frames.], batch size: 21, lr: 1.46e-03
2022-05-26 17:24:38,357 INFO [train.py:842] (3/4) Epoch 3, batch 1150, loss[loss=0.3125, simple_loss=0.3657, pruned_loss=0.1297, over 7234.00 frames.], tot_loss[loss=0.2882, simple_loss=0.3466, pruned_loss=0.1149, over 1421355.20 frames.], batch size: 20, lr: 1.45e-03
2022-05-26 17:25:16,900 INFO [train.py:842] (3/4) Epoch 3, batch 1200, loss[loss=0.241, simple_loss=0.315, pruned_loss=0.08352, over 7434.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3468, pruned_loss=0.1151, over 1424525.51 frames.], batch size: 20, lr: 1.45e-03
2022-05-26 17:25:55,756 INFO [train.py:842] (3/4) Epoch 3, batch 1250, loss[loss=0.2797, simple_loss=0.3441, pruned_loss=0.1077, over 7408.00 frames.], tot_loss[loss=0.2911, simple_loss=0.348, pruned_loss=0.1171, over 1425227.62 frames.], batch size: 21, lr: 1.45e-03
2022-05-26 17:26:34,362 INFO [train.py:842] (3/4) Epoch 3, batch 1300, loss[loss=0.3205, simple_loss=0.3712, pruned_loss=0.1348, over 7308.00 frames.], tot_loss[loss=0.29, simple_loss=0.3474, pruned_loss=0.1164, over 1426889.71 frames.], batch size: 21, lr: 1.45e-03
2022-05-26 17:27:13,056 INFO [train.py:842] (3/4) Epoch 3, batch 1350, loss[loss=0.4163, simple_loss=0.4187, pruned_loss=0.207, over 7427.00 frames.], tot_loss[loss=0.2925, simple_loss=0.3497, pruned_loss=0.1177, over 1426523.09 frames.], batch size: 20, lr: 1.45e-03
2022-05-26 17:27:51,775 INFO [train.py:842] (3/4) Epoch 3, batch 1400, loss[loss=0.2066, simple_loss=0.2857, pruned_loss=0.06375, over 7148.00 frames.], tot_loss[loss=0.2902, simple_loss=0.3482, pruned_loss=0.1162, over 1423627.24 frames.], batch size: 19, lr: 1.45e-03
2022-05-26 17:28:30,425 INFO [train.py:842] (3/4) Epoch 3, batch 1450, loss[loss=0.2472, simple_loss=0.302, pruned_loss=0.09616, over 7126.00 frames.], tot_loss[loss=0.2894, simple_loss=0.3469, pruned_loss=0.116, over 1420212.21 frames.], batch size: 17, lr: 1.44e-03
2022-05-26 17:29:08,826 INFO [train.py:842] (3/4) Epoch 3, batch 1500, loss[loss=0.3665, simple_loss=0.4179, pruned_loss=0.1575, over 7330.00 frames.], tot_loss[loss=0.2909, simple_loss=0.3481, pruned_loss=0.1169, over 1419262.34 frames.], batch size: 21, lr: 1.44e-03
2022-05-26 17:29:47,559 INFO [train.py:842] (3/4) Epoch 3, batch 1550, loss[loss=0.3235, simple_loss=0.3867, pruned_loss=0.1302, over 7155.00 frames.], tot_loss[loss=0.2911, simple_loss=0.3487, pruned_loss=0.1168, over 1422432.07 frames.], batch size: 19, lr: 1.44e-03
2022-05-26 17:30:26,313 INFO [train.py:842] (3/4) Epoch 3, batch 1600, loss[loss=0.2795, simple_loss=0.3323, pruned_loss=0.1134, over 7166.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3481, pruned_loss=0.1162, over 1424403.70 frames.], batch size: 19, lr: 1.44e-03
2022-05-26 17:31:05,610 INFO [train.py:842] (3/4) Epoch 3, batch 1650, loss[loss=0.2785, simple_loss=0.3329, pruned_loss=0.1121, over 7433.00 frames.], tot_loss[loss=0.2871, simple_loss=0.3457, pruned_loss=0.1143, over 1426594.10 frames.], batch size: 20, lr: 1.44e-03
2022-05-26 17:31:43,973 INFO [train.py:842] (3/4) Epoch 3, batch 1700, loss[loss=0.2557, simple_loss=0.3257, pruned_loss=0.09288, over 7147.00 frames.], tot_loss[loss=0.2876, simple_loss=0.346, pruned_loss=0.1146, over 1417206.51 frames.], batch size: 20, lr: 1.44e-03
2022-05-26 17:32:23,196 INFO [train.py:842] (3/4) Epoch 3, batch 1750, loss[loss=0.2983, simple_loss=0.3571, pruned_loss=0.1197, over 7233.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3459, pruned_loss=0.1147, over 1424238.69 frames.], batch size: 20, lr: 1.43e-03
2022-05-26 17:33:01,596 INFO [train.py:842] (3/4) Epoch 3, batch 1800, loss[loss=0.3307, simple_loss=0.3832, pruned_loss=0.1391, over 7115.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3457, pruned_loss=0.1148, over 1417401.10 frames.], batch size: 21, lr: 1.43e-03
2022-05-26 17:33:40,966 INFO [train.py:842] (3/4) Epoch 3, batch 1850, loss[loss=0.3049, simple_loss=0.3655, pruned_loss=0.1221, over 7415.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3454, pruned_loss=0.1149, over 1418542.45 frames.], batch size: 21, lr: 1.43e-03
2022-05-26 17:34:19,489 INFO [train.py:842] (3/4) Epoch 3, batch 1900, loss[loss=0.3097, simple_loss=0.3502, pruned_loss=0.1346, over 7171.00 frames.], tot_loss[loss=0.2888, simple_loss=0.346, pruned_loss=0.1158, over 1417176.36 frames.], batch size: 18, lr: 1.43e-03
2022-05-26 17:34:58,250 INFO [train.py:842] (3/4) Epoch 3, batch 1950, loss[loss=0.3025, simple_loss=0.3703, pruned_loss=0.1174, over 6746.00 frames.], tot_loss[loss=0.2884, simple_loss=0.3455, pruned_loss=0.1156, over 1418166.75 frames.], batch size: 31, lr: 1.43e-03
2022-05-26 17:35:36,919 INFO [train.py:842] (3/4) Epoch 3, batch 2000, loss[loss=0.2832, simple_loss=0.3388, pruned_loss=0.1138, over 7146.00 frames.], tot_loss[loss=0.287, simple_loss=0.3448, pruned_loss=0.1146, over 1421920.35 frames.], batch size: 19, lr: 1.43e-03
2022-05-26 17:36:15,520 INFO [train.py:842] (3/4) Epoch 3, batch 2050, loss[loss=0.3586, simple_loss=0.3898, pruned_loss=0.1637, over 5000.00 frames.], tot_loss[loss=0.288, simple_loss=0.3462, pruned_loss=0.1149, over 1421397.79 frames.], batch size: 52, lr: 1.42e-03
2022-05-26 17:36:54,245 INFO [train.py:842] (3/4) Epoch 3, batch 2100, loss[loss=0.3061, simple_loss=0.3589, pruned_loss=0.1266, over 7327.00 frames.], tot_loss[loss=0.2884, simple_loss=0.3463, pruned_loss=0.1152, over 1424295.98 frames.], batch size: 21, lr: 1.42e-03
2022-05-26 17:37:33,231 INFO [train.py:842] (3/4) Epoch 3, batch 2150, loss[loss=0.2503, simple_loss=0.3117, pruned_loss=0.09446, over 7232.00 frames.], tot_loss[loss=0.2891, simple_loss=0.3469, pruned_loss=0.1156, over 1425848.80 frames.], batch size: 20, lr: 1.42e-03
2022-05-26 17:38:11,814 INFO [train.py:842] (3/4) Epoch 3, batch 2200, loss[loss=0.2884, simple_loss=0.3486, pruned_loss=0.1141, over 7150.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3463, pruned_loss=0.1153, over 1424654.68 frames.], batch size: 20, lr: 1.42e-03
2022-05-26 17:38:50,517 INFO [train.py:842] (3/4) Epoch 3, batch 2250, loss[loss=0.2758, simple_loss=0.3444, pruned_loss=0.1036, over 7330.00 frames.], tot_loss[loss=0.2878, simple_loss=0.346, pruned_loss=0.1148, over 1424326.11 frames.], batch size: 20, lr: 1.42e-03
2022-05-26 17:39:29,089 INFO [train.py:842] (3/4) Epoch 3, batch 2300, loss[loss=0.2643, simple_loss=0.3192, pruned_loss=0.1047, over 7364.00 frames.], tot_loss[loss=0.2866, simple_loss=0.3449, pruned_loss=0.1142, over 1412358.96 frames.], batch size: 19, lr: 1.42e-03
2022-05-26 17:40:07,878 INFO [train.py:842] (3/4) Epoch 3, batch 2350, loss[loss=0.2867, simple_loss=0.3531, pruned_loss=0.1101, over 7262.00 frames.], tot_loss[loss=0.2844, simple_loss=0.3432, pruned_loss=0.1128, over 1414018.24 frames.], batch size: 19, lr: 1.41e-03
2022-05-26 17:40:46,295 INFO [train.py:842] (3/4) Epoch 3, batch 2400, loss[loss=0.2487, simple_loss=0.3226, pruned_loss=0.08736, over 7266.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3434, pruned_loss=0.1121, over 1417855.03 frames.], batch size: 19, lr: 1.41e-03
2022-05-26 17:41:25,129 INFO [train.py:842] (3/4) Epoch 3, batch 2450, loss[loss=0.3047, simple_loss=0.3647, pruned_loss=0.1223, over 7230.00 frames.], tot_loss[loss=0.2863, simple_loss=0.3455, pruned_loss=0.1135, over 1414925.52 frames.], batch size: 20, lr: 1.41e-03
2022-05-26 17:42:03,938 INFO [train.py:842] (3/4) Epoch 3, batch 2500, loss[loss=0.2423, simple_loss=0.3009, pruned_loss=0.09186, over 7157.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3421, pruned_loss=0.1111, over 1413023.02 frames.], batch size: 19, lr: 1.41e-03
2022-05-26 17:42:42,668 INFO [train.py:842] (3/4) Epoch 3, batch 2550, loss[loss=0.3435, simple_loss=0.385, pruned_loss=0.1511, over 7220.00 frames.], tot_loss[loss=0.2831, simple_loss=0.3424, pruned_loss=0.1119, over 1411441.11 frames.], batch size: 21, lr: 1.41e-03
2022-05-26 17:43:21,457 INFO [train.py:842] (3/4) Epoch 3, batch 2600, loss[loss=0.2643, simple_loss=0.3227, pruned_loss=0.1029, over 7276.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3432, pruned_loss=0.113, over 1417814.91 frames.], batch size: 18, lr: 1.41e-03
2022-05-26 17:44:00,646 INFO [train.py:842] (3/4) Epoch 3, batch 2650, loss[loss=0.2345, simple_loss=0.3196, pruned_loss=0.07466, over 7331.00 frames.], tot_loss[loss=0.2834, simple_loss=0.3423, pruned_loss=0.1122, over 1417482.62 frames.], batch size: 20, lr: 1.41e-03
2022-05-26 17:44:39,142 INFO [train.py:842] (3/4) Epoch 3, batch 2700, loss[loss=0.3643, simple_loss=0.3915, pruned_loss=0.1686, over 7062.00 frames.], tot_loss[loss=0.2813, simple_loss=0.3409, pruned_loss=0.1109, over 1418995.08 frames.], batch size: 18, lr: 1.40e-03
2022-05-26 17:45:17,846 INFO [train.py:842] (3/4) Epoch 3, batch 2750, loss[loss=0.2778, simple_loss=0.3408, pruned_loss=0.1074, over 7172.00 frames.], tot_loss[loss=0.2811, simple_loss=0.3406, pruned_loss=0.1108, over 1417959.72 frames.], batch size: 26, lr: 1.40e-03
2022-05-26 17:45:56,583 INFO [train.py:842] (3/4) Epoch 3, batch 2800, loss[loss=0.2961, simple_loss=0.3544, pruned_loss=0.1189, over 5223.00 frames.], tot_loss[loss=0.2792, simple_loss=0.3394, pruned_loss=0.1095, over 1418367.63 frames.], batch size: 52, lr: 1.40e-03
2022-05-26 17:46:35,465 INFO [train.py:842] (3/4) Epoch 3, batch 2850, loss[loss=0.3084, simple_loss=0.3596, pruned_loss=0.1286, over 7218.00 frames.], tot_loss[loss=0.2821, simple_loss=0.3414, pruned_loss=0.1114, over 1421344.82 frames.], batch size: 21, lr: 1.40e-03
2022-05-26 17:47:13,946 INFO [train.py:842] (3/4) Epoch 3, batch 2900, loss[loss=0.3468, simple_loss=0.3855, pruned_loss=0.154, over 6500.00 frames.], tot_loss[loss=0.2837, simple_loss=0.3424, pruned_loss=0.1125, over 1416986.12 frames.], batch size: 38, lr: 1.40e-03
2022-05-26 17:47:52,719 INFO [train.py:842] (3/4) Epoch 3, batch 2950, loss[loss=0.3459, simple_loss=0.3952, pruned_loss=0.1483, over 7130.00 frames.], tot_loss[loss=0.288, simple_loss=0.3452, pruned_loss=0.1154, over 1416390.52 frames.], batch size: 26, lr: 1.40e-03
2022-05-26 17:48:31,454 INFO [train.py:842] (3/4) Epoch 3, batch 3000, loss[loss=0.3296, simple_loss=0.3835, pruned_loss=0.1378, over 7339.00 frames.], tot_loss[loss=0.287, simple_loss=0.345, pruned_loss=0.1144, over 1419226.51 frames.], batch size: 22, lr: 1.39e-03
2022-05-26 17:48:31,456 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 17:48:40,684 INFO [train.py:871] (3/4) Epoch 3, validation: loss=0.2137, simple_loss=0.3102, pruned_loss=0.05856, over 868885.00 frames.
2022-05-26 17:49:19,908 INFO [train.py:842] (3/4) Epoch 3, batch 3050, loss[loss=0.2868, simple_loss=0.3582, pruned_loss=0.1077, over 7406.00 frames.], tot_loss[loss=0.2874, simple_loss=0.3459, pruned_loss=0.1144, over 1424572.37 frames.], batch size: 21, lr: 1.39e-03
2022-05-26 17:49:58,629 INFO [train.py:842] (3/4) Epoch 3, batch 3100, loss[loss=0.2529, simple_loss=0.3129, pruned_loss=0.09647, over 7281.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3435, pruned_loss=0.1125, over 1427717.01 frames.], batch size: 18, lr: 1.39e-03
2022-05-26 17:50:37,610 INFO [train.py:842] (3/4) Epoch 3, batch 3150, loss[loss=0.2816, simple_loss=0.3486, pruned_loss=0.1073, over 7227.00 frames.], tot_loss[loss=0.283, simple_loss=0.3424, pruned_loss=0.1118, over 1423012.77 frames.], batch size: 21, lr: 1.39e-03
2022-05-26 17:51:16,018 INFO [train.py:842] (3/4) Epoch 3, batch 3200, loss[loss=0.3109, simple_loss=0.3668, pruned_loss=0.1274, over 7380.00 frames.], tot_loss[loss=0.2817, simple_loss=0.3421, pruned_loss=0.1107, over 1426245.57 frames.], batch size: 23, lr: 1.39e-03
2022-05-26 17:51:54,697 INFO [train.py:842] (3/4) Epoch 3, batch 3250, loss[loss=0.267, simple_loss=0.3282, pruned_loss=0.1029, over 7154.00 frames.], tot_loss[loss=0.2821, simple_loss=0.3425, pruned_loss=0.1108, over 1426803.15 frames.], batch size: 19, lr: 1.39e-03
2022-05-26 17:52:33,248 INFO [train.py:842] (3/4) Epoch 3, batch 3300, loss[loss=0.2786, simple_loss=0.3504, pruned_loss=0.1034, over 7181.00 frames.], tot_loss[loss=0.2823, simple_loss=0.3424, pruned_loss=0.1111, over 1428654.60 frames.], batch size: 26, lr: 1.39e-03
2022-05-26 17:53:11,853 INFO [train.py:842] (3/4) Epoch 3, batch 3350, loss[loss=0.2516, simple_loss=0.3154, pruned_loss=0.09391, over 7254.00 frames.], tot_loss[loss=0.2845, simple_loss=0.3444, pruned_loss=0.1122, over 1425608.58 frames.], batch size: 18, lr: 1.38e-03
2022-05-26 17:53:50,298 INFO [train.py:842] (3/4) Epoch 3, batch 3400, loss[loss=0.2448, simple_loss=0.3086, pruned_loss=0.09053, over 7410.00 frames.], tot_loss[loss=0.2841, simple_loss=0.3443, pruned_loss=0.1119, over 1423388.85 frames.], batch size: 18, lr: 1.38e-03
2022-05-26 17:54:29,394 INFO [train.py:842] (3/4) Epoch 3, batch 3450, loss[loss=0.282, simple_loss=0.3352, pruned_loss=0.1144, over 7251.00 frames.], tot_loss[loss=0.2826, simple_loss=0.3431, pruned_loss=0.1111, over 1420431.43 frames.], batch size: 19, lr: 1.38e-03
2022-05-26 17:55:07,998 INFO [train.py:842] (3/4) Epoch 3, batch 3500, loss[loss=0.335, simple_loss=0.385, pruned_loss=0.1425, over 7322.00 frames.], tot_loss[loss=0.282, simple_loss=0.342, pruned_loss=0.111, over 1422403.87 frames.], batch size: 25, lr: 1.38e-03
2022-05-26 17:55:46,669 INFO [train.py:842] (3/4) Epoch 3, batch 3550, loss[loss=0.2777, simple_loss=0.3447, pruned_loss=0.1053, over 7224.00 frames.], tot_loss[loss=0.2802, simple_loss=0.341, pruned_loss=0.1097, over 1421260.33 frames.], batch size: 21, lr: 1.38e-03
2022-05-26 17:56:25,362 INFO [train.py:842] (3/4) Epoch 3, batch 3600, loss[loss=0.2691, simple_loss=0.3427, pruned_loss=0.09779, over 7289.00 frames.], tot_loss[loss=0.2802, simple_loss=0.3405, pruned_loss=0.1099, over 1422579.47 frames.], batch size: 24, lr: 1.38e-03
2022-05-26 17:57:04,493 INFO [train.py:842] (3/4) Epoch 3, batch 3650, loss[loss=0.2892, simple_loss=0.36, pruned_loss=0.1092, over 7401.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3407, pruned_loss=0.1105, over 1422243.56 frames.], batch size: 23, lr: 1.37e-03
2022-05-26 17:57:43,098 INFO [train.py:842] (3/4) Epoch 3, batch 3700, loss[loss=0.1825, simple_loss=0.262, pruned_loss=0.05144, over 7405.00 frames.], tot_loss[loss=0.2805, simple_loss=0.3409, pruned_loss=0.11, over 1417290.67 frames.], batch size: 18, lr: 1.37e-03
2022-05-26 17:58:22,045 INFO [train.py:842] (3/4) Epoch 3, batch 3750, loss[loss=0.2402, simple_loss=0.2961, pruned_loss=0.0922, over 7281.00 frames.], tot_loss[loss=0.28, simple_loss=0.3406, pruned_loss=0.1098, over 1423904.19 frames.], batch size: 18, lr: 1.37e-03
2022-05-26 17:59:00,552 INFO [train.py:842] (3/4) Epoch 3, batch 3800, loss[loss=0.2015, simple_loss=0.277, pruned_loss=0.06306, over 7164.00 frames.], tot_loss[loss=0.2781, simple_loss=0.339, pruned_loss=0.1086, over 1424113.09 frames.], batch size: 18, lr: 1.37e-03
2022-05-26 17:59:39,248 INFO [train.py:842] (3/4) Epoch 3, batch 3850, loss[loss=0.2347, simple_loss=0.3104, pruned_loss=0.07951, over 7344.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3377, pruned_loss=0.1075, over 1423187.32 frames.], batch size: 22, lr: 1.37e-03
2022-05-26 18:00:17,894 INFO [train.py:842] (3/4) Epoch 3, batch 3900, loss[loss=0.2728, simple_loss=0.3432, pruned_loss=0.1012, over 7334.00 frames.], tot_loss[loss=0.2785, simple_loss=0.3392, pruned_loss=0.1089, over 1424964.09 frames.], batch size: 20, lr: 1.37e-03
2022-05-26 18:00:57,118 INFO [train.py:842] (3/4) Epoch 3, batch 3950, loss[loss=0.2791, simple_loss=0.3565, pruned_loss=0.1008, over 7321.00 frames.], tot_loss[loss=0.2801, simple_loss=0.3401, pruned_loss=0.11, over 1422231.73 frames.], batch size: 21, lr: 1.37e-03
2022-05-26 18:01:35,691 INFO [train.py:842] (3/4) Epoch 3, batch 4000, loss[loss=0.343, simple_loss=0.4117, pruned_loss=0.1371, over 7334.00 frames.], tot_loss[loss=0.2796, simple_loss=0.3397, pruned_loss=0.1098, over 1427021.69 frames.], batch size: 22, lr: 1.36e-03
2022-05-26 18:02:15,096 INFO [train.py:842] (3/4) Epoch 3, batch 4050, loss[loss=0.2191, simple_loss=0.2879, pruned_loss=0.07521, over 7423.00 frames.], tot_loss[loss=0.2787, simple_loss=0.3386, pruned_loss=0.1093, over 1426583.22 frames.], batch size: 20, lr: 1.36e-03
2022-05-26 18:02:53,409 INFO [train.py:842] (3/4) Epoch 3, batch 4100, loss[loss=0.2465, simple_loss=0.3124, pruned_loss=0.09036, over 7061.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3386, pruned_loss=0.1091, over 1417283.84 frames.], batch size: 18, lr: 1.36e-03
2022-05-26 18:03:32,200 INFO [train.py:842] (3/4) Epoch 3, batch 4150, loss[loss=0.2712, simple_loss=0.3431, pruned_loss=0.09959, over 7308.00 frames.], tot_loss[loss=0.2775, simple_loss=0.3384, pruned_loss=0.1083, over 1421541.94 frames.], batch size: 25, lr: 1.36e-03
2022-05-26 18:04:10,671 INFO [train.py:842] (3/4) Epoch 3, batch 4200, loss[loss=0.3586, simple_loss=0.4002, pruned_loss=0.1585, over 7204.00 frames.], tot_loss[loss=0.2816, simple_loss=0.3409, pruned_loss=0.1112, over 1419811.81 frames.], batch size: 22, lr: 1.36e-03
2022-05-26 18:04:49,681 INFO [train.py:842] (3/4) Epoch 3, batch 4250, loss[loss=0.2842, simple_loss=0.3508, pruned_loss=0.1088, over 7249.00 frames.], tot_loss[loss=0.2818, simple_loss=0.3409, pruned_loss=0.1113, over 1424772.34 frames.], batch size: 19, lr: 1.36e-03
2022-05-26 18:05:28,275 INFO [train.py:842] (3/4) Epoch 3, batch 4300, loss[loss=0.2863, simple_loss=0.3328, pruned_loss=0.12, over 6750.00 frames.], tot_loss[loss=0.2814, simple_loss=0.3407, pruned_loss=0.1111, over 1424565.22 frames.], batch size: 15, lr: 1.36e-03
2022-05-26 18:06:07,371 INFO [train.py:842] (3/4) Epoch 3, batch 4350, loss[loss=0.2252, simple_loss=0.2986, pruned_loss=0.07591, over 7351.00 frames.], tot_loss[loss=0.2776, simple_loss=0.338, pruned_loss=0.1086, over 1427344.20 frames.], batch size: 19, lr: 1.35e-03
2022-05-26 18:06:45,884 INFO [train.py:842] (3/4) Epoch 3, batch 4400, loss[loss=0.3199, simple_loss=0.3787, pruned_loss=0.1305, over 7438.00 frames.], tot_loss[loss=0.2795, simple_loss=0.3395, pruned_loss=0.1098, over 1428213.07 frames.], batch size: 20, lr: 1.35e-03
2022-05-26 18:07:24,813 INFO [train.py:842] (3/4) Epoch 3, batch 4450, loss[loss=0.2415, simple_loss=0.3061, pruned_loss=0.0885, over 6994.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3383, pruned_loss=0.109, over 1432176.17 frames.], batch size: 16, lr: 1.35e-03
2022-05-26 18:08:03,429 INFO [train.py:842] (3/4) Epoch 3, batch 4500, loss[loss=0.2737, simple_loss=0.3458, pruned_loss=0.1008, over 7201.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3384, pruned_loss=0.1085, over 1427527.94 frames.], batch size: 23, lr: 1.35e-03
2022-05-26 18:08:42,210 INFO [train.py:842] (3/4) Epoch 3, batch 4550, loss[loss=0.2554, simple_loss=0.3316, pruned_loss=0.08955, over 7334.00 frames.], tot_loss[loss=0.2763, simple_loss=0.337, pruned_loss=0.1078, over 1427141.12 frames.], batch size: 20, lr: 1.35e-03
2022-05-26 18:09:20,908 INFO [train.py:842] (3/4) Epoch 3, batch 4600, loss[loss=0.2347, simple_loss=0.3137, pruned_loss=0.07786, over 7412.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3365, pruned_loss=0.1067, over 1427953.91 frames.], batch size: 18, lr: 1.35e-03
2022-05-26 18:10:00,058 INFO [train.py:842] (3/4) Epoch 3, batch 4650, loss[loss=0.2611, simple_loss=0.3193, pruned_loss=0.1015, over 7012.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3394, pruned_loss=0.1086, over 1429581.96 frames.], batch size: 16, lr: 1.35e-03
2022-05-26 18:10:38,695 INFO [train.py:842] (3/4) Epoch 3, batch 4700, loss[loss=0.2112, simple_loss=0.2898, pruned_loss=0.06632, over 7263.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3383, pruned_loss=0.108, over 1433564.05 frames.], batch size: 19, lr: 1.34e-03
2022-05-26 18:11:17,521 INFO [train.py:842] (3/4) Epoch 3, batch 4750, loss[loss=0.2569, simple_loss=0.3269, pruned_loss=0.09342, over 7093.00 frames.], tot_loss[loss=0.279, simple_loss=0.3393, pruned_loss=0.1093, over 1434341.60 frames.], batch size: 28, lr: 1.34e-03
2022-05-26 18:11:55,926 INFO [train.py:842] (3/4) Epoch 3, batch 4800, loss[loss=0.2057, simple_loss=0.2754, pruned_loss=0.06803, over 7278.00 frames.], tot_loss[loss=0.2798, simple_loss=0.3401, pruned_loss=0.1098, over 1433717.69 frames.], batch size: 17, lr: 1.34e-03
2022-05-26 18:12:34,729 INFO [train.py:842] (3/4) Epoch 3, batch 4850, loss[loss=0.3038, simple_loss=0.3741, pruned_loss=0.1167, over 7311.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3393, pruned_loss=0.1085, over 1430297.20 frames.], batch size: 21, lr: 1.34e-03
2022-05-26 18:13:13,097 INFO [train.py:842] (3/4) Epoch 3, batch 4900, loss[loss=0.2478, simple_loss=0.3284, pruned_loss=0.08365, over 7230.00 frames.], tot_loss[loss=0.2786, simple_loss=0.34, pruned_loss=0.1087, over 1427468.80 frames.], batch size: 20, lr: 1.34e-03
2022-05-26 18:13:51,836 INFO [train.py:842] (3/4) Epoch 3, batch 4950, loss[loss=0.319, simple_loss=0.372, pruned_loss=0.133, over 7109.00 frames.], tot_loss[loss=0.2794, simple_loss=0.3408, pruned_loss=0.1089, over 1425915.04 frames.], batch size: 21, lr: 1.34e-03
2022-05-26 18:14:30,281 INFO [train.py:842] (3/4) Epoch 3, batch 5000, loss[loss=0.3285, simple_loss=0.3664, pruned_loss=0.1453, over 7155.00 frames.], tot_loss[loss=0.2796, simple_loss=0.3406, pruned_loss=0.1093, over 1419852.39 frames.], batch size: 19, lr: 1.34e-03
2022-05-26 18:15:09,125 INFO [train.py:842] (3/4) Epoch 3, batch 5050, loss[loss=0.276, simple_loss=0.3435, pruned_loss=0.1043, over 7320.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3387, pruned_loss=0.1084, over 1419460.46 frames.], batch size: 21, lr: 1.33e-03
2022-05-26 18:15:47,551 INFO [train.py:842] (3/4) Epoch 3, batch 5100, loss[loss=0.2644, simple_loss=0.3266, pruned_loss=0.101, over 7360.00 frames.], tot_loss[loss=0.2764, simple_loss=0.338, pruned_loss=0.1074, over 1421828.79 frames.], batch size: 19, lr: 1.33e-03
2022-05-26 18:16:26,341 INFO [train.py:842] (3/4) Epoch 3, batch 5150, loss[loss=0.2426, simple_loss=0.2997, pruned_loss=0.09278, over 7156.00 frames.], tot_loss[loss=0.2747, simple_loss=0.3367, pruned_loss=0.1064, over 1421949.25 frames.], batch size: 18, lr: 1.33e-03
2022-05-26 18:17:04,926 INFO [train.py:842] (3/4) Epoch 3, batch 5200, loss[loss=0.3296, simple_loss=0.3766, pruned_loss=0.1413, over 7215.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3377, pruned_loss=0.1075, over 1422596.26 frames.], batch size: 22, lr: 1.33e-03
2022-05-26 18:17:43,702 INFO [train.py:842] (3/4) Epoch 3, batch 5250, loss[loss=0.3031, simple_loss=0.3499, pruned_loss=0.1282, over 7328.00 frames.], tot_loss[loss=0.2792, simple_loss=0.3396, pruned_loss=0.1094, over 1423559.58 frames.], batch size: 20, lr: 1.33e-03
2022-05-26 18:18:22,109 INFO [train.py:842] (3/4) Epoch 3, batch 5300, loss[loss=0.2859, simple_loss=0.3353, pruned_loss=0.1183, over 7314.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3414, pruned_loss=0.1101, over 1420852.54 frames.], batch size: 25, lr: 1.33e-03
2022-05-26 18:19:00,853 INFO [train.py:842] (3/4) Epoch 3, batch 5350, loss[loss=0.2783, simple_loss=0.3413, pruned_loss=0.1077, over 7412.00 frames.], tot_loss[loss=0.2807, simple_loss=0.342, pruned_loss=0.1097, over 1417312.25 frames.], batch size: 21, lr: 1.33e-03
2022-05-26 18:19:39,511 INFO [train.py:842] (3/4) Epoch 3, batch 5400, loss[loss=0.3441, simple_loss=0.3969, pruned_loss=0.1456, over 7062.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3432, pruned_loss=0.1106, over 1416716.73 frames.], batch size: 18, lr: 1.33e-03
2022-05-26 18:20:18,506 INFO [train.py:842] (3/4) Epoch 3, batch 5450, loss[loss=0.2851, simple_loss=0.3403, pruned_loss=0.1149, over 7171.00 frames.], tot_loss[loss=0.2815, simple_loss=0.3417, pruned_loss=0.1107, over 1418051.78 frames.], batch size: 18, lr: 1.32e-03
2022-05-26 18:20:57,228 INFO [train.py:842] (3/4) Epoch 3, batch 5500, loss[loss=0.3245, simple_loss=0.3724, pruned_loss=0.1383, over 7213.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3391, pruned_loss=0.1087, over 1419508.55 frames.], batch size: 21, lr: 1.32e-03
2022-05-26 18:21:35,992 INFO [train.py:842] (3/4) Epoch 3, batch 5550, loss[loss=0.267, simple_loss=0.3244, pruned_loss=0.1048, over 6802.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3387, pruned_loss=0.1083, over 1418996.88 frames.], batch size: 15, lr: 1.32e-03
2022-05-26 18:22:14,558 INFO [train.py:842] (3/4) Epoch 3, batch 5600, loss[loss=0.2997, simple_loss=0.3581, pruned_loss=0.1206, over 7194.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3377, pruned_loss=0.1076, over 1423086.78 frames.], batch size: 26, lr: 1.32e-03
2022-05-26 18:22:55,854 INFO [train.py:842] (3/4) Epoch 3, batch 5650, loss[loss=0.22, simple_loss=0.2887, pruned_loss=0.07561, over 7293.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3372, pruned_loss=0.1072, over 1424438.32 frames.], batch size: 17, lr: 1.32e-03
2022-05-26 18:23:34,234 INFO [train.py:842] (3/4) Epoch 3, batch 5700, loss[loss=0.2847, simple_loss=0.3532, pruned_loss=0.1081, over 6501.00 frames.], tot_loss[loss=0.2764, simple_loss=0.338, pruned_loss=0.1075, over 1423634.46 frames.], batch size: 38, lr: 1.32e-03
2022-05-26 18:24:13,064 INFO [train.py:842] (3/4) Epoch 3, batch 5750, loss[loss=0.5087, simple_loss=0.4742, pruned_loss=0.2716, over 5049.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3377, pruned_loss=0.1077, over 1420659.92 frames.], batch size: 54, lr: 1.32e-03
2022-05-26 18:24:51,643 INFO [train.py:842] (3/4) Epoch 3, batch 5800, loss[loss=0.3306, simple_loss=0.3536, pruned_loss=0.1538, over 7139.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3374, pruned_loss=0.107, over 1425514.42 frames.], batch size: 17, lr: 1.31e-03
2022-05-26 18:25:30,398 INFO [train.py:842] (3/4) Epoch 3, batch 5850, loss[loss=0.3172, simple_loss=0.3605, pruned_loss=0.1369, over 5127.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3377, pruned_loss=0.1075, over 1424587.31 frames.], batch size: 52, lr: 1.31e-03
2022-05-26 18:26:08,884 INFO [train.py:842] (3/4) Epoch 3, batch 5900, loss[loss=0.2736, simple_loss=0.343, pruned_loss=0.1021, over 7216.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3385, pruned_loss=0.1076, over 1426724.71 frames.], batch size: 21, lr: 1.31e-03
2022-05-26 18:26:47,676 INFO [train.py:842] (3/4) Epoch 3, batch 5950, loss[loss=0.254, simple_loss=0.3225, pruned_loss=0.09275, over 7361.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3381, pruned_loss=0.1074, over 1423586.59 frames.], batch size: 23, lr: 1.31e-03
2022-05-26 18:27:26,263 INFO [train.py:842] (3/4) Epoch 3, batch 6000, loss[loss=0.1955, simple_loss=0.2689, pruned_loss=0.061, over 7288.00 frames.], tot_loss[loss=0.274, simple_loss=0.3362, pruned_loss=0.1059, over 1421901.56 frames.], batch size: 17, lr: 1.31e-03
2022-05-26 18:27:26,264 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 18:27:36,052 INFO [train.py:871] (3/4) Epoch 3, validation: loss=0.2084, simple_loss=0.3064, pruned_loss=0.05526, over 868885.00 frames.
2022-05-26 18:28:14,710 INFO [train.py:842] (3/4) Epoch 3, batch 6050, loss[loss=0.2795, simple_loss=0.3506, pruned_loss=0.1042, over 7150.00 frames.], tot_loss[loss=0.2744, simple_loss=0.337, pruned_loss=0.1059, over 1421187.93 frames.], batch size: 20, lr: 1.31e-03
2022-05-26 18:28:53,197 INFO [train.py:842] (3/4) Epoch 3, batch 6100, loss[loss=0.2833, simple_loss=0.3509, pruned_loss=0.1079, over 7170.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3386, pruned_loss=0.1079, over 1419016.42 frames.], batch size: 26, lr: 1.31e-03
2022-05-26 18:29:31,938 INFO [train.py:842] (3/4) Epoch 3, batch 6150, loss[loss=0.2824, simple_loss=0.3483, pruned_loss=0.1083, over 7409.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3369, pruned_loss=0.1071, over 1419593.91 frames.], batch size: 21, lr: 1.31e-03
2022-05-26 18:30:10,410 INFO [train.py:842] (3/4) Epoch 3, batch 6200, loss[loss=0.3252, simple_loss=0.3748, pruned_loss=0.1378, over 4891.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3371, pruned_loss=0.1073, over 1416942.94 frames.], batch size: 52, lr: 1.30e-03
2022-05-26 18:30:49,617 INFO [train.py:842] (3/4) Epoch 3, batch 6250, loss[loss=0.2573, simple_loss=0.3304, pruned_loss=0.09211, over 6741.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3373, pruned_loss=0.1072, over 1419612.73 frames.], batch size: 31, lr: 1.30e-03
2022-05-26 18:31:28,269 INFO [train.py:842] (3/4) Epoch 3, batch 6300, loss[loss=0.3616, simple_loss=0.3831, pruned_loss=0.17, over 7191.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3372, pruned_loss=0.1071, over 1414503.98 frames.], batch size: 18, lr: 1.30e-03
2022-05-26 18:32:07,488 INFO [train.py:842] (3/4) Epoch 3, batch 6350, loss[loss=0.2859, simple_loss=0.3313, pruned_loss=0.1203, over 7295.00 frames.], tot_loss[loss=0.2754, simple_loss=0.3365, pruned_loss=0.1071, over 1419654.82 frames.], batch size: 17, lr: 1.30e-03
2022-05-26 18:32:46,056 INFO [train.py:842] (3/4) Epoch 3, batch 6400, loss[loss=0.2862, simple_loss=0.3504, pruned_loss=0.111, over 7307.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3381, pruned_loss=0.1083, over 1419096.85 frames.], batch size: 25, lr: 1.30e-03
2022-05-26 18:33:24,829 INFO [train.py:842] (3/4) Epoch 3, batch 6450, loss[loss=0.295, simple_loss=0.3598, pruned_loss=0.1151, over 7115.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3379, pruned_loss=0.1081, over 1419146.97 frames.], batch size: 21, lr: 1.30e-03
2022-05-26 18:34:03,183 INFO [train.py:842] (3/4) Epoch 3, batch 6500, loss[loss=0.2392, simple_loss=0.3116, pruned_loss=0.08338, over 7275.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3385, pruned_loss=0.108, over 1417389.08 frames.], batch size: 18, lr: 1.30e-03
2022-05-26 18:34:42,305 INFO [train.py:842] (3/4) Epoch 3, batch 6550, loss[loss=0.2361, simple_loss=0.3072, pruned_loss=0.08245, over 7145.00 frames.], tot_loss[loss=0.2754, simple_loss=0.3375, pruned_loss=0.1067, over 1421750.14 frames.], batch size: 20, lr: 1.30e-03
2022-05-26 18:35:21,048 INFO [train.py:842] (3/4) Epoch 3, batch 6600, loss[loss=0.3523, simple_loss=0.3776, pruned_loss=0.1635, over 7118.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3359, pruned_loss=0.1058, over 1422355.92 frames.], batch size: 21, lr: 1.29e-03
2022-05-26 18:36:00,221 INFO [train.py:842] (3/4) Epoch 3, batch 6650, loss[loss=0.2499, simple_loss=0.3311, pruned_loss=0.08433, over 7113.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3353, pruned_loss=0.105, over 1422300.81 frames.], batch size: 21, lr: 1.29e-03
2022-05-26 18:36:38,888 INFO [train.py:842] (3/4) Epoch 3, batch 6700, loss[loss=0.3105, simple_loss=0.37, pruned_loss=0.1255, over 7213.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3361, pruned_loss=0.1056, over 1419393.73 frames.], batch size: 21, lr: 1.29e-03
2022-05-26 18:37:17,632 INFO [train.py:842] (3/4) Epoch 3, batch 6750, loss[loss=0.2626, simple_loss=0.3222, pruned_loss=0.1015, over 6807.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3378, pruned_loss=0.1063, over 1420544.09 frames.], batch size: 15, lr: 1.29e-03
2022-05-26 18:37:56,022 INFO [train.py:842] (3/4) Epoch 3, batch 6800, loss[loss=0.3295, simple_loss=0.3913, pruned_loss=0.1338, over 7182.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3371, pruned_loss=0.1057, over 1421622.92 frames.], batch size: 26, lr: 1.29e-03
2022-05-26 18:38:34,917 INFO [train.py:842] (3/4) Epoch 3, batch 6850, loss[loss=0.317, simple_loss=0.3708, pruned_loss=0.1316, over 7389.00 frames.], tot_loss[loss=0.2747, simple_loss=0.3369, pruned_loss=0.1063, over 1422865.12 frames.], batch size: 23, lr: 1.29e-03
2022-05-26 18:39:13,433 INFO [train.py:842] (3/4) Epoch 3, batch 6900, loss[loss=0.3253, simple_loss=0.3599, pruned_loss=0.1453, over 7123.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3376, pruned_loss=0.1067, over 1426196.12 frames.], batch size: 17, lr: 1.29e-03
2022-05-26 18:39:52,130 INFO [train.py:842] (3/4) Epoch 3, batch 6950, loss[loss=0.2579, simple_loss=0.3341, pruned_loss=0.09083, over 7214.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3371, pruned_loss=0.1067, over 1427124.12 frames.], batch size: 21, lr: 1.29e-03
2022-05-26 18:40:30,499 INFO [train.py:842] (3/4) Epoch 3, batch 7000, loss[loss=0.2372, simple_loss=0.3206, pruned_loss=0.07691, over 7325.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3373, pruned_loss=0.1068, over 1425436.58 frames.], batch size: 21, lr: 1.28e-03
2022-05-26 18:41:09,296 INFO [train.py:842] (3/4) Epoch 3, batch 7050, loss[loss=0.2754, simple_loss=0.336, pruned_loss=0.1074, over 7203.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3383, pruned_loss=0.108, over 1423308.70 frames.], batch size: 22, lr: 1.28e-03
2022-05-26 18:41:47,891 INFO [train.py:842] (3/4) Epoch 3, batch 7100, loss[loss=0.2792, simple_loss=0.3427, pruned_loss=0.1079, over 7221.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3388, pruned_loss=0.1084, over 1422666.79 frames.], batch size: 20, lr: 1.28e-03
2022-05-26 18:42:26,623 INFO [train.py:842] (3/4) Epoch 3, batch 7150, loss[loss=0.2953, simple_loss=0.3467, pruned_loss=0.1219, over 7162.00 frames.], tot_loss[loss=0.2762, simple_loss=0.3376, pruned_loss=0.1074, over 1422330.55 frames.], batch size: 19, lr: 1.28e-03
2022-05-26 18:43:05,181 INFO [train.py:842] (3/4) Epoch 3, batch 7200, loss[loss=0.365, simple_loss=0.3986, pruned_loss=0.1658, over 5195.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3391, pruned_loss=0.1082, over 1415514.26 frames.], batch size: 52, lr: 1.28e-03
2022-05-26 18:43:43,957 INFO [train.py:842] (3/4) Epoch 3, batch 7250, loss[loss=0.2301, simple_loss=0.2879, pruned_loss=0.08616, over 7282.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3398, pruned_loss=0.1082, over 1418149.68 frames.], batch size: 17, lr: 1.28e-03
2022-05-26 18:44:22,269 INFO [train.py:842] (3/4) Epoch 3, batch 7300, loss[loss=0.2398, simple_loss=0.324, pruned_loss=0.07784, over 7317.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3394, pruned_loss=0.1076, over 1420637.29 frames.], batch size: 21, lr: 1.28e-03
2022-05-26 18:45:01,019 INFO [train.py:842] (3/4) Epoch 3, batch 7350, loss[loss=0.3403, simple_loss=0.3967, pruned_loss=0.142, over 7307.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3388, pruned_loss=0.107, over 1422077.70 frames.], batch size: 24, lr: 1.28e-03
2022-05-26 18:45:39,605 INFO [train.py:842] (3/4) Epoch 3, batch 7400, loss[loss=0.2557, simple_loss=0.3174, pruned_loss=0.09699, over 7267.00 frames.], tot_loss[loss=0.2754, simple_loss=0.3377, pruned_loss=0.1066, over 1426293.92 frames.], batch size: 19, lr: 1.27e-03
2022-05-26 18:46:18,840 INFO [train.py:842] (3/4) Epoch 3, batch 7450, loss[loss=0.2347, simple_loss=0.3196, pruned_loss=0.07486, over 7407.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3374, pruned_loss=0.1065, over 1425109.90 frames.], batch size: 21, lr: 1.27e-03
2022-05-26 18:46:57,498 INFO [train.py:842] (3/4) Epoch 3, batch 7500, loss[loss=0.2805, simple_loss=0.329, pruned_loss=0.116, over 7118.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3366, pruned_loss=0.1062, over 1427908.61 frames.], batch size: 17, lr: 1.27e-03
2022-05-26 18:47:36,161 INFO [train.py:842] (3/4) Epoch 3, batch 7550, loss[loss=0.3093, simple_loss=0.3606, pruned_loss=0.129, over 7281.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3365, pruned_loss=0.106, over 1426813.81 frames.], batch size: 24, lr: 1.27e-03
2022-05-26 18:48:14,690 INFO [train.py:842] (3/4) Epoch 3, batch 7600, loss[loss=0.2599, simple_loss=0.3339, pruned_loss=0.09291, over 7320.00 frames.], tot_loss[loss=0.2745, simple_loss=0.3369, pruned_loss=0.1061, over 1423569.28 frames.], batch size: 22, lr: 1.27e-03
2022-05-26 18:48:53,770 INFO [train.py:842] (3/4) Epoch 3, batch 7650, loss[loss=0.2473, simple_loss=0.3054, pruned_loss=0.09459, over 7011.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3359, pruned_loss=0.1057, over 1417257.48 frames.], batch size: 16, lr: 1.27e-03
2022-05-26 18:49:32,406 INFO [train.py:842] (3/4) Epoch 3, batch 7700, loss[loss=0.342, simple_loss=0.3924, pruned_loss=0.1458, over 7085.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3364, pruned_loss=0.1061, over 1417249.21 frames.], batch size: 28, lr: 1.27e-03
2022-05-26 18:50:11,098 INFO [train.py:842] (3/4) Epoch 3, batch 7750, loss[loss=0.2068, simple_loss=0.277, pruned_loss=0.06835, over 7216.00 frames.], tot_loss[loss=0.2745, simple_loss=0.3367, pruned_loss=0.1061, over 1423176.35 frames.], batch size: 16, lr: 1.27e-03
2022-05-26 18:50:49,659 INFO [train.py:842] (3/4) Epoch 3, batch 7800, loss[loss=0.2488, simple_loss=0.3146, pruned_loss=0.09147, over 7378.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3366, pruned_loss=0.106, over 1423600.98 frames.], batch size: 23, lr: 1.27e-03
2022-05-26 18:51:28,463 INFO [train.py:842] (3/4) Epoch 3, batch 7850, loss[loss=0.2498, simple_loss=0.3196, pruned_loss=0.09001, over 7162.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3348, pruned_loss=0.1046, over 1424247.77 frames.], batch size: 26, lr: 1.26e-03
2022-05-26 18:52:07,141 INFO [train.py:842] (3/4) Epoch 3, batch 7900, loss[loss=0.3286, simple_loss=0.3566, pruned_loss=0.1503, over 7327.00 frames.], tot_loss[loss=0.2711, simple_loss=0.334, pruned_loss=0.1041, over 1425204.05 frames.], batch size: 20, lr: 1.26e-03
2022-05-26 18:52:45,868 INFO [train.py:842] (3/4) Epoch 3, batch 7950, loss[loss=0.3015, simple_loss=0.3677, pruned_loss=0.1177, over 7231.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3345, pruned_loss=0.1042, over 1424094.32 frames.], batch size: 20, lr: 1.26e-03
2022-05-26 18:53:24,294 INFO [train.py:842] (3/4) Epoch 3, batch 8000, loss[loss=0.3968, simple_loss=0.42, pruned_loss=0.1868, over 7185.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3364, pruned_loss=0.1061, over 1420713.59 frames.], batch size: 26, lr: 1.26e-03
2022-05-26 18:54:03,083 INFO [train.py:842] (3/4) Epoch 3, batch 8050, loss[loss=0.2705, simple_loss=0.3364, pruned_loss=0.1023, over 7145.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3362, pruned_loss=0.1062, over 1418754.67 frames.], batch size: 26, lr: 1.26e-03
2022-05-26 18:54:41,743 INFO [train.py:842] (3/4) Epoch 3, batch 8100, loss[loss=0.2988, simple_loss=0.347, pruned_loss=0.1253, over 7183.00 frames.], tot_loss[loss=0.2739, simple_loss=0.3358, pruned_loss=0.106, over 1418947.23 frames.], batch size: 22, lr: 1.26e-03
2022-05-26 18:55:20,577 INFO [train.py:842] (3/4) Epoch 3, batch 8150, loss[loss=0.2121, simple_loss=0.2848, pruned_loss=0.06972, over 7256.00 frames.], tot_loss[loss=0.2742, simple_loss=0.3356, pruned_loss=0.1064, over 1412360.31 frames.], batch size: 19, lr: 1.26e-03
2022-05-26 18:55:59,062 INFO [train.py:842] (3/4) Epoch 3, batch 8200, loss[loss=0.2596, simple_loss=0.337, pruned_loss=0.09109, over 7320.00 frames.], tot_loss[loss=0.2731, simple_loss=0.335, pruned_loss=0.1056, over 1414933.29 frames.], batch size: 20, lr: 1.26e-03
2022-05-26 18:56:37,966 INFO [train.py:842] (3/4) Epoch 3, batch 8250, loss[loss=0.2751, simple_loss=0.336, pruned_loss=0.1071, over 7261.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3332, pruned_loss=0.1036, over 1418683.88 frames.], batch size: 19, lr: 1.26e-03
2022-05-26 18:57:16,527 INFO [train.py:842] (3/4) Epoch 3, batch 8300, loss[loss=0.254, simple_loss=0.3388, pruned_loss=0.08465, over 7124.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3345, pruned_loss=0.1041, over 1420383.25 frames.], batch size: 21, lr: 1.25e-03
2022-05-26 18:57:55,088 INFO [train.py:842] (3/4) Epoch 3, batch 8350, loss[loss=0.373, simple_loss=0.4169, pruned_loss=0.1646, over 5467.00 frames.], tot_loss[loss=0.2745, simple_loss=0.337, pruned_loss=0.106, over 1417582.85 frames.], batch size: 52, lr: 1.25e-03
2022-05-26 18:58:33,826 INFO [train.py:842] (3/4) Epoch 3, batch 8400, loss[loss=0.2378, simple_loss=0.3137, pruned_loss=0.08094, over 7255.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3363, pruned_loss=0.1056, over 1418463.69 frames.], batch size: 19, lr: 1.25e-03
2022-05-26 18:59:12,595 INFO [train.py:842] (3/4) Epoch 3, batch 8450, loss[loss=0.4015, simple_loss=0.4216, pruned_loss=0.1907, over 7062.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3365, pruned_loss=0.1056, over 1418239.95 frames.], batch size: 28, lr: 1.25e-03
2022-05-26 19:00:01,258 INFO [train.py:842] (3/4) Epoch 3, batch 8500, loss[loss=0.3102, simple_loss=0.3615, pruned_loss=0.1294, over 7160.00 frames.], tot_loss[loss=0.2725, simple_loss=0.3358, pruned_loss=0.1046, over 1420575.15 frames.], batch size: 19, lr: 1.25e-03
2022-05-26 19:00:39,778 INFO [train.py:842] (3/4) Epoch 3, batch 8550, loss[loss=0.256, simple_loss=0.3254, pruned_loss=0.09334, over 6542.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3365, pruned_loss=0.1055, over 1417581.17 frames.], batch size: 38, lr: 1.25e-03
2022-05-26 19:01:18,437 INFO [train.py:842] (3/4) Epoch 3, batch 8600, loss[loss=0.2398, simple_loss=0.2915, pruned_loss=0.09409, over 7262.00 frames.], tot_loss[loss=0.2725, simple_loss=0.3351, pruned_loss=0.1049, over 1418633.60 frames.], batch size: 17, lr: 1.25e-03
2022-05-26 19:01:57,291 INFO [train.py:842] (3/4) Epoch 3, batch 8650, loss[loss=0.2816, simple_loss=0.3222, pruned_loss=0.1204, over 7282.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3346, pruned_loss=0.1048, over 1417187.68 frames.], batch size: 18, lr: 1.25e-03
2022-05-26 19:02:35,790 INFO [train.py:842] (3/4) Epoch 3, batch 8700, loss[loss=0.2619, simple_loss=0.3353, pruned_loss=0.09426, over 6988.00 frames.], tot_loss[loss=0.2724, simple_loss=0.3348, pruned_loss=0.105, over 1416565.94 frames.], batch size: 28, lr: 1.24e-03
2022-05-26 19:03:14,506 INFO [train.py:842] (3/4) Epoch 3, batch 8750, loss[loss=0.3008, simple_loss=0.3603, pruned_loss=0.1206, over 7069.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3345, pruned_loss=0.1047, over 1418197.74 frames.], batch size: 28, lr: 1.24e-03
2022-05-26 19:03:53,201 INFO [train.py:842] (3/4) Epoch 3, batch 8800, loss[loss=0.2523, simple_loss=0.3031, pruned_loss=0.1008, over 7278.00 frames.], tot_loss[loss=0.2704, simple_loss=0.3332, pruned_loss=0.1038, over 1418361.37 frames.], batch size: 18, lr: 1.24e-03
2022-05-26 19:04:31,962 INFO [train.py:842] (3/4) Epoch 3, batch 8850, loss[loss=0.2656, simple_loss=0.337, pruned_loss=0.09714, over 7350.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3337, pruned_loss=0.104, over 1419842.49 frames.], batch size: 22, lr: 1.24e-03
2022-05-26 19:05:10,533 INFO [train.py:842] (3/4) Epoch 3, batch 8900, loss[loss=0.287, simple_loss=0.3542, pruned_loss=0.1099, over 7117.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3341, pruned_loss=0.1041, over 1418314.80 frames.], batch size: 28, lr: 1.24e-03
2022-05-26 19:05:59,435 INFO [train.py:842] (3/4) Epoch 3, batch 8950, loss[loss=0.2481, simple_loss=0.3095, pruned_loss=0.09338, over 7265.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3351, pruned_loss=0.1045, over 1412120.33 frames.], batch size: 17, lr: 1.24e-03
2022-05-26 19:06:48,328 INFO [train.py:842] (3/4) Epoch 3, batch 9000, loss[loss=0.3316, simple_loss=0.3786, pruned_loss=0.1423, over 4836.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3366, pruned_loss=0.1052, over 1403144.11 frames.], batch size: 52, lr: 1.24e-03
2022-05-26 19:06:48,328 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 19:07:08,221 INFO [train.py:871] (3/4) Epoch 3, validation: loss=0.2052, simple_loss=0.3029, pruned_loss=0.0537, over 868885.00 frames.
2022-05-26 19:07:46,556 INFO [train.py:842] (3/4) Epoch 3, batch 9050, loss[loss=0.2883, simple_loss=0.3598, pruned_loss=0.1084, over 7284.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3389, pruned_loss=0.1061, over 1389255.21 frames.], batch size: 25, lr: 1.24e-03
2022-05-26 19:08:24,020 INFO [train.py:842] (3/4) Epoch 3, batch 9100, loss[loss=0.338, simple_loss=0.3808, pruned_loss=0.1476, over 5226.00 frames.], tot_loss[loss=0.2814, simple_loss=0.3435, pruned_loss=0.1097, over 1358915.25 frames.], batch size: 52, lr: 1.24e-03
2022-05-26 19:09:01,538 INFO [train.py:842] (3/4) Epoch 3, batch 9150, loss[loss=0.306, simple_loss=0.3589, pruned_loss=0.1266, over 5173.00 frames.], tot_loss[loss=0.2877, simple_loss=0.3478, pruned_loss=0.1138, over 1298086.38 frames.], batch size: 52, lr: 1.24e-03
2022-05-26 19:09:53,249 INFO [train.py:842] (3/4) Epoch 4, batch 0, loss[loss=0.3044, simple_loss=0.3653, pruned_loss=0.1217, over 7193.00 frames.], tot_loss[loss=0.3044, simple_loss=0.3653, pruned_loss=0.1217, over 7193.00 frames.], batch size: 23, lr: 1.20e-03
2022-05-26 19:10:32,531 INFO [train.py:842] (3/4) Epoch 4, batch 50, loss[loss=0.2852, simple_loss=0.3307, pruned_loss=0.1199, over 7281.00 frames.], tot_loss[loss=0.265, simple_loss=0.3294, pruned_loss=0.1003, over 317614.85 frames.], batch size: 17, lr: 1.20e-03
2022-05-26 19:11:11,270 INFO [train.py:842] (3/4) Epoch 4, batch 100, loss[loss=0.2593, simple_loss=0.2965, pruned_loss=0.111, over 7286.00 frames.], tot_loss[loss=0.271, simple_loss=0.3321, pruned_loss=0.1049, over 564665.58 frames.], batch size: 17, lr: 1.20e-03
2022-05-26 19:11:50,063 INFO [train.py:842] (3/4) Epoch 4, batch 150, loss[loss=0.2542, simple_loss=0.3354, pruned_loss=0.08654, over 7335.00 frames.], tot_loss[loss=0.2694, simple_loss=0.3323, pruned_loss=0.1033, over 755496.74 frames.], batch size: 22, lr: 1.20e-03
2022-05-26 19:12:28,806 INFO [train.py:842] (3/4) Epoch 4, batch 200, loss[loss=0.3485, simple_loss=0.3828, pruned_loss=0.1571, over 7207.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3342, pruned_loss=0.104, over 904759.85 frames.], batch size: 23, lr: 1.19e-03
2022-05-26 19:13:07,619 INFO [train.py:842] (3/4) Epoch 4, batch 250, loss[loss=0.27, simple_loss=0.3431, pruned_loss=0.09843, over 7326.00 frames.], tot_loss[loss=0.2714, simple_loss=0.335, pruned_loss=0.1039, over 1017143.07 frames.], batch size: 22, lr: 1.19e-03
2022-05-26 19:13:46,332 INFO [train.py:842] (3/4) Epoch 4, batch 300, loss[loss=0.3201, simple_loss=0.3757, pruned_loss=0.1322, over 7375.00 frames.], tot_loss[loss=0.2704, simple_loss=0.3347, pruned_loss=0.103, over 1111019.31 frames.], batch size: 23, lr: 1.19e-03
2022-05-26 19:14:25,612 INFO [train.py:842] (3/4) Epoch 4, batch 350, loss[loss=0.2101, simple_loss=0.2978, pruned_loss=0.06123, over 7324.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3341, pruned_loss=0.1028, over 1182944.53 frames.], batch size: 21, lr: 1.19e-03
2022-05-26 19:15:04,160 INFO [train.py:842] (3/4) Epoch 4, batch 400, loss[loss=0.2638, simple_loss=0.3343, pruned_loss=0.09663, over 7232.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3329, pruned_loss=0.1023, over 1232577.05 frames.], batch size: 20, lr: 1.19e-03
2022-05-26 19:15:42,989 INFO [train.py:842] (3/4) Epoch 4, batch 450, loss[loss=0.2822, simple_loss=0.3555, pruned_loss=0.1044, over 7152.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3335, pruned_loss=0.1034, over 1274563.53 frames.], batch size: 20, lr: 1.19e-03
2022-05-26 19:16:21,295 INFO [train.py:842] (3/4) Epoch 4, batch 500, loss[loss=0.294, simple_loss=0.3637, pruned_loss=0.1121, over 7154.00 frames.], tot_loss[loss=0.2685, simple_loss=0.333, pruned_loss=0.1021, over 1303850.12 frames.], batch size: 19, lr: 1.19e-03
2022-05-26 19:17:00,281 INFO [train.py:842] (3/4) Epoch 4, batch 550, loss[loss=0.2328, simple_loss=0.3011, pruned_loss=0.08223, over 7156.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3339, pruned_loss=0.1033, over 1329612.96 frames.], batch size: 18, lr: 1.19e-03
2022-05-26 19:17:38,807 INFO [train.py:842] (3/4) Epoch 4, batch 600, loss[loss=0.2968, simple_loss=0.3579, pruned_loss=0.1179, over 6494.00 frames.], tot_loss[loss=0.2699, simple_loss=0.3333, pruned_loss=0.1032, over 1347302.13 frames.], batch size: 38, lr: 1.19e-03
2022-05-26 19:18:17,895 INFO [train.py:842] (3/4) Epoch 4, batch 650, loss[loss=0.2223, simple_loss=0.2958, pruned_loss=0.07441, over 7437.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3324, pruned_loss=0.1022, over 1367582.79 frames.], batch size: 20, lr: 1.18e-03
2022-05-26 19:18:56,792 INFO [train.py:842] (3/4) Epoch 4, batch 700, loss[loss=0.335, simple_loss=0.3699, pruned_loss=0.1501, over 7299.00 frames.], tot_loss[loss=0.266, simple_loss=0.3304, pruned_loss=0.1008, over 1384375.07 frames.], batch size: 24, lr: 1.18e-03
2022-05-26 19:19:35,627 INFO [train.py:842] (3/4) Epoch 4, batch 750, loss[loss=0.265, simple_loss=0.3332, pruned_loss=0.09845, over 7285.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3293, pruned_loss=0.1001, over 1392354.38 frames.], batch size: 24, lr: 1.18e-03
2022-05-26 19:20:14,169 INFO [train.py:842] (3/4) Epoch 4, batch 800, loss[loss=0.2801, simple_loss=0.3454, pruned_loss=0.1074, over 7252.00 frames.], tot_loss[loss=0.2657, simple_loss=0.3306, pruned_loss=0.1004, over 1397060.22 frames.], batch size: 19, lr: 1.18e-03
2022-05-26 19:20:53,470 INFO [train.py:842] (3/4) Epoch 4, batch 850, loss[loss=0.2565, simple_loss=0.3214, pruned_loss=0.09586, over 7062.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3299, pruned_loss=0.1002, over 1407323.20 frames.], batch size: 18, lr: 1.18e-03
2022-05-26 19:21:32,128 INFO [train.py:842] (3/4) Epoch 4, batch 900, loss[loss=0.2536, simple_loss=0.3167, pruned_loss=0.09524, over 7122.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3292, pruned_loss=0.0991, over 1414727.18 frames.], batch size: 21, lr: 1.18e-03
2022-05-26 19:22:10,980 INFO [train.py:842] (3/4) Epoch 4, batch 950, loss[loss=0.2149, simple_loss=0.2947, pruned_loss=0.06755, over 7119.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3289, pruned_loss=0.0991, over 1419713.01 frames.], batch size: 26, lr: 1.18e-03
2022-05-26 19:22:49,576 INFO [train.py:842] (3/4) Epoch 4, batch 1000, loss[loss=0.2774, simple_loss=0.3366, pruned_loss=0.1091, over 7268.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3289, pruned_loss=0.09928, over 1419807.66 frames.], batch size: 18, lr: 1.18e-03
2022-05-26 19:23:28,202 INFO [train.py:842] (3/4) Epoch 4, batch 1050, loss[loss=0.2903, simple_loss=0.3602, pruned_loss=0.1102, over 6623.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3312, pruned_loss=0.101, over 1418219.65 frames.], batch size: 31, lr: 1.18e-03
2022-05-26 19:24:06,794 INFO [train.py:842] (3/4) Epoch 4, batch 1100, loss[loss=0.2256, simple_loss=0.3131, pruned_loss=0.06906, over 7410.00 frames.], tot_loss[loss=0.2662, simple_loss=0.331, pruned_loss=0.1007, over 1419132.73 frames.], batch size: 21, lr: 1.18e-03
2022-05-26 19:24:45,515 INFO [train.py:842] (3/4) Epoch 4, batch 1150, loss[loss=0.2581, simple_loss=0.3439, pruned_loss=0.08615, over 7307.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3333, pruned_loss=0.102, over 1416603.71 frames.], batch size: 21, lr: 1.17e-03
2022-05-26 19:25:24,170 INFO [train.py:842] (3/4) Epoch 4, batch 1200, loss[loss=0.2655, simple_loss=0.3389, pruned_loss=0.09605, over 7321.00 frames.], tot_loss[loss=0.2692, simple_loss=0.3341, pruned_loss=0.1021, over 1413895.82 frames.], batch size: 21, lr: 1.17e-03
2022-05-26 19:26:03,106 INFO [train.py:842] (3/4) Epoch 4, batch 1250, loss[loss=0.2555, simple_loss=0.3105, pruned_loss=0.1002, over 6775.00 frames.], tot_loss[loss=0.2691, simple_loss=0.334, pruned_loss=0.1021, over 1412230.10 frames.], batch size: 15, lr: 1.17e-03
2022-05-26 19:26:45,100 INFO [train.py:842] (3/4) Epoch 4, batch 1300, loss[loss=0.267, simple_loss=0.3409, pruned_loss=0.09653, over 7185.00 frames.], tot_loss[loss=0.267, simple_loss=0.3322, pruned_loss=0.1009, over 1415486.71 frames.], batch size: 23, lr: 1.17e-03
2022-05-26 19:27:23,922 INFO [train.py:842] (3/4) Epoch 4, batch 1350, loss[loss=0.2426, simple_loss=0.3277, pruned_loss=0.07879, over 7232.00 frames.], tot_loss[loss=0.2654, simple_loss=0.331, pruned_loss=0.09992, over 1415301.82 frames.], batch size: 20, lr: 1.17e-03
2022-05-26 19:28:02,856 INFO [train.py:842] (3/4) Epoch 4, batch 1400, loss[loss=0.2735, simple_loss=0.3453, pruned_loss=0.1009, over 7209.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3299, pruned_loss=0.09953, over 1418776.55 frames.], batch size: 22, lr: 1.17e-03
2022-05-26 19:28:42,074 INFO [train.py:842] (3/4) Epoch 4, batch 1450, loss[loss=0.26, simple_loss=0.3266, pruned_loss=0.09671, over 7284.00 frames.], tot_loss[loss=0.2657, simple_loss=0.3316, pruned_loss=0.09996, over 1420824.71 frames.], batch size: 24, lr: 1.17e-03
2022-05-26 19:29:23,393 INFO [train.py:842] (3/4) Epoch 4, batch 1500, loss[loss=0.3104, simple_loss=0.3755, pruned_loss=0.1226, over 7301.00 frames.], tot_loss[loss=0.266, simple_loss=0.3314, pruned_loss=0.1003, over 1418015.14 frames.], batch size: 24, lr: 1.17e-03
2022-05-26 19:30:02,822 INFO [train.py:842] (3/4) Epoch 4, batch 1550, loss[loss=0.3713, simple_loss=0.4193, pruned_loss=0.1617, over 5001.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3312, pruned_loss=0.09992, over 1416957.19 frames.], batch size: 52, lr: 1.17e-03
2022-05-26 19:30:42,133 INFO [train.py:842] (3/4) Epoch 4, batch 1600, loss[loss=0.3037, simple_loss=0.3571, pruned_loss=0.1252, over 7271.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3313, pruned_loss=0.09929, over 1414096.98 frames.], batch size: 25, lr: 1.17e-03
2022-05-26 19:31:21,044 INFO [train.py:842] (3/4) Epoch 4, batch 1650, loss[loss=0.2653, simple_loss=0.3285, pruned_loss=0.101, over 7333.00 frames.], tot_loss[loss=0.2661, simple_loss=0.3317, pruned_loss=0.1003, over 1416282.70 frames.], batch size: 20, lr: 1.17e-03
2022-05-26 19:31:59,640 INFO [train.py:842] (3/4) Epoch 4, batch 1700, loss[loss=0.3454, simple_loss=0.3809, pruned_loss=0.1549, over 7151.00 frames.], tot_loss[loss=0.2654, simple_loss=0.3314, pruned_loss=0.09965, over 1420316.26 frames.], batch size: 20, lr: 1.16e-03
2022-05-26 19:32:38,164 INFO [train.py:842] (3/4) Epoch 4, batch 1750, loss[loss=0.3226, simple_loss=0.376, pruned_loss=0.1345, over 7196.00 frames.], tot_loss[loss=0.2646, simple_loss=0.3309, pruned_loss=0.09917, over 1419812.51 frames.], batch size: 22, lr: 1.16e-03
2022-05-26 19:33:16,539 INFO [train.py:842] (3/4) Epoch 4, batch 1800, loss[loss=0.2604, simple_loss=0.3272, pruned_loss=0.09683, over 7222.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3321, pruned_loss=0.09972, over 1421308.29 frames.], batch size: 21, lr: 1.16e-03
2022-05-26 19:33:55,184 INFO [train.py:842] (3/4) Epoch 4, batch 1850, loss[loss=0.2556, simple_loss=0.314, pruned_loss=0.09864, over 7147.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3343, pruned_loss=0.1015, over 1420215.57 frames.], batch size: 17, lr: 1.16e-03
2022-05-26 19:34:33,651 INFO [train.py:842] (3/4) Epoch 4, batch 1900, loss[loss=0.2914, simple_loss=0.3524, pruned_loss=0.1152, over 7158.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3341, pruned_loss=0.1019, over 1423538.71 frames.], batch size: 19, lr: 1.16e-03
2022-05-26 19:35:12,545 INFO [train.py:842] (3/4) Epoch 4, batch 1950, loss[loss=0.284, simple_loss=0.3464, pruned_loss=0.1108, over 6553.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3327, pruned_loss=0.1003, over 1428213.30 frames.], batch size: 38, lr: 1.16e-03
2022-05-26 19:35:51,016 INFO [train.py:842] (3/4) Epoch 4, batch 2000, loss[loss=0.3019, simple_loss=0.3651, pruned_loss=0.1193, over 7116.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3334, pruned_loss=0.1009, over 1425373.62 frames.], batch size: 21, lr: 1.16e-03
2022-05-26 19:36:29,987 INFO [train.py:842] (3/4) Epoch 4, batch 2050, loss[loss=0.2799, simple_loss=0.3387, pruned_loss=0.1105, over 6599.00 frames.], tot_loss[loss=0.2686, simple_loss=0.334, pruned_loss=0.1016, over 1421817.26 frames.], batch size: 31, lr: 1.16e-03
2022-05-26 19:37:08,660 INFO [train.py:842] (3/4) Epoch 4, batch 2100, loss[loss=0.2564, simple_loss=0.3244, pruned_loss=0.0942, over 7325.00 frames.], tot_loss[loss=0.2661, simple_loss=0.332, pruned_loss=0.1001, over 1420478.89 frames.], batch size: 21, lr: 1.16e-03
2022-05-26 19:37:47,580 INFO [train.py:842] (3/4) Epoch 4, batch 2150, loss[loss=0.2781, simple_loss=0.3457, pruned_loss=0.1052, over 7347.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3313, pruned_loss=0.09956, over 1422997.76 frames.], batch size: 22, lr: 1.16e-03
2022-05-26 19:38:26,076 INFO [train.py:842] (3/4) Epoch 4, batch 2200, loss[loss=0.2753, simple_loss=0.3594, pruned_loss=0.09562, over 7224.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3292, pruned_loss=0.09817, over 1425835.05 frames.], batch size: 21, lr: 1.15e-03
2022-05-26 19:39:04,833 INFO [train.py:842] (3/4) Epoch 4, batch 2250, loss[loss=0.3028, simple_loss=0.355, pruned_loss=0.1253, over 4717.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3289, pruned_loss=0.09762, over 1427074.92 frames.], batch size: 53, lr: 1.15e-03
2022-05-26 19:39:43,439 INFO [train.py:842] (3/4) Epoch 4, batch 2300, loss[loss=0.2526, simple_loss=0.3177, pruned_loss=0.09379, over 7158.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3289, pruned_loss=0.09704, over 1429937.25 frames.], batch size: 19, lr: 1.15e-03
2022-05-26 19:40:22,289 INFO [train.py:842] (3/4) Epoch 4, batch 2350, loss[loss=0.2356, simple_loss=0.3074, pruned_loss=0.08195, over 7319.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3276, pruned_loss=0.09642, over 1431598.48 frames.], batch size: 20, lr: 1.15e-03
2022-05-26 19:41:00,760 INFO [train.py:842] (3/4) Epoch 4, batch 2400, loss[loss=0.2719, simple_loss=0.3417, pruned_loss=0.101, over 7296.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3286, pruned_loss=0.09725, over 1433319.73 frames.], batch size: 25, lr: 1.15e-03
2022-05-26 19:41:39,557 INFO [train.py:842] (3/4) Epoch 4, batch 2450, loss[loss=0.2937, simple_loss=0.3587, pruned_loss=0.1143, over 7385.00 frames.], tot_loss[loss=0.2611, simple_loss=0.3283, pruned_loss=0.09696, over 1436388.45 frames.], batch size: 23, lr: 1.15e-03
2022-05-26 19:42:18,028 INFO [train.py:842] (3/4) Epoch 4, batch 2500, loss[loss=0.3044, simple_loss=0.3682, pruned_loss=0.1203, over 7147.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3277, pruned_loss=0.09638, over 1434331.49 frames.], batch size: 19, lr: 1.15e-03
2022-05-26 19:42:56,658 INFO [train.py:842] (3/4) Epoch 4, batch 2550, loss[loss=0.2136, simple_loss=0.2775, pruned_loss=0.07486, over 7413.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3294, pruned_loss=0.09809, over 1425854.85 frames.], batch size: 18, lr: 1.15e-03
2022-05-26 19:43:35,183 INFO [train.py:842] (3/4) Epoch 4, batch 2600, loss[loss=0.2612, simple_loss=0.329, pruned_loss=0.09666, over 7241.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3292, pruned_loss=0.09751, over 1425414.02 frames.], batch size: 20, lr: 1.15e-03
2022-05-26 19:44:13,882 INFO [train.py:842] (3/4) Epoch 4, batch 2650, loss[loss=0.2151, simple_loss=0.279, pruned_loss=0.07563, over 7004.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3291, pruned_loss=0.0972, over 1419925.60 frames.], batch size: 16, lr: 1.15e-03
2022-05-26 19:44:52,288 INFO [train.py:842] (3/4) Epoch 4, batch 2700, loss[loss=0.2128, simple_loss=0.2929, pruned_loss=0.0664, over 6786.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3304, pruned_loss=0.0985, over 1418409.73 frames.], batch size: 15, lr: 1.15e-03
2022-05-26 19:45:31,382 INFO [train.py:842] (3/4) Epoch 4, batch 2750, loss[loss=0.2817, simple_loss=0.3347, pruned_loss=0.1143, over 7258.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3314, pruned_loss=0.0995, over 1421246.34 frames.], batch size: 19, lr: 1.14e-03
2022-05-26 19:46:09,947 INFO [train.py:842] (3/4) Epoch 4, batch 2800, loss[loss=0.3001, simple_loss=0.3466, pruned_loss=0.1268, over 7167.00 frames.], tot_loss[loss=0.264, simple_loss=0.3305, pruned_loss=0.09879, over 1423541.17 frames.], batch size: 19, lr: 1.14e-03
2022-05-26 19:46:48,798 INFO [train.py:842] (3/4) Epoch 4, batch 2850, loss[loss=0.3313, simple_loss=0.3819, pruned_loss=0.1403, over 5177.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3303, pruned_loss=0.09828, over 1422912.95 frames.], batch size: 52, lr: 1.14e-03
2022-05-26 19:47:27,319 INFO [train.py:842] (3/4) Epoch 4, batch 2900, loss[loss=0.2439, simple_loss=0.3218, pruned_loss=0.08296, over 6839.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3294, pruned_loss=0.09711, over 1423499.73 frames.], batch size: 31, lr: 1.14e-03
2022-05-26 19:48:06,165 INFO [train.py:842] (3/4) Epoch 4, batch 2950, loss[loss=0.2237, simple_loss=0.2994, pruned_loss=0.074, over 7064.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3296, pruned_loss=0.09748, over 1427435.21 frames.], batch size: 28, lr: 1.14e-03
2022-05-26 19:48:45,198 INFO [train.py:842] (3/4) Epoch 4, batch 3000, loss[loss=0.3339, simple_loss=0.3861, pruned_loss=0.1409, over 7157.00 frames.], tot_loss[loss=0.2641, simple_loss=0.331, pruned_loss=0.09857, over 1425982.73 frames.], batch size: 20, lr: 1.14e-03
2022-05-26 19:48:45,199 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 19:48:54,321 INFO [train.py:871] (3/4) Epoch 4, validation: loss=0.2021, simple_loss=0.3, pruned_loss=0.05209, over 868885.00 frames.
2022-05-26 19:49:33,152 INFO [train.py:842] (3/4) Epoch 4, batch 3050, loss[loss=0.2654, simple_loss=0.3249, pruned_loss=0.1029, over 7115.00 frames.], tot_loss[loss=0.2636, simple_loss=0.331, pruned_loss=0.0981, over 1421273.67 frames.], batch size: 21, lr: 1.14e-03
2022-05-26 19:50:11,918 INFO [train.py:842] (3/4) Epoch 4, batch 3100, loss[loss=0.3341, simple_loss=0.3879, pruned_loss=0.1402, over 7283.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3304, pruned_loss=0.09819, over 1418026.29 frames.], batch size: 24, lr: 1.14e-03
2022-05-26 19:50:51,358 INFO [train.py:842] (3/4) Epoch 4, batch 3150, loss[loss=0.3153, simple_loss=0.3772, pruned_loss=0.1267, over 7292.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3295, pruned_loss=0.09766, over 1422280.91 frames.], batch size: 25, lr: 1.14e-03
2022-05-26 19:51:30,079 INFO [train.py:842] (3/4) Epoch 4, batch 3200, loss[loss=0.21, simple_loss=0.2801, pruned_loss=0.06992, over 7070.00 frames.], tot_loss[loss=0.2619, simple_loss=0.3286, pruned_loss=0.09758, over 1423211.41 frames.], batch size: 18, lr: 1.14e-03
2022-05-26 19:52:09,200 INFO [train.py:842] (3/4) Epoch 4, batch 3250, loss[loss=0.3141, simple_loss=0.3607, pruned_loss=0.1337, over 7263.00 frames.], tot_loss[loss=0.2643, simple_loss=0.3302, pruned_loss=0.09925, over 1424280.86 frames.], batch size: 19, lr: 1.14e-03
2022-05-26 19:52:47,458 INFO [train.py:842] (3/4) Epoch 4, batch 3300, loss[loss=0.2566, simple_loss=0.3292, pruned_loss=0.09203, over 7193.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3305, pruned_loss=0.09861, over 1422339.52 frames.], batch size: 23, lr: 1.13e-03
2022-05-26 19:53:26,311 INFO [train.py:842] (3/4) Epoch 4, batch 3350, loss[loss=0.3196, simple_loss=0.3766, pruned_loss=0.1313, over 6322.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3279, pruned_loss=0.09682, over 1419863.36 frames.], batch size: 37, lr: 1.13e-03
2022-05-26 19:54:04,829 INFO [train.py:842] (3/4) Epoch 4, batch 3400, loss[loss=0.2179, simple_loss=0.2888, pruned_loss=0.07349, over 6999.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3271, pruned_loss=0.09586, over 1420367.98 frames.], batch size: 16, lr: 1.13e-03
2022-05-26 19:54:43,741 INFO [train.py:842] (3/4) Epoch 4, batch 3450, loss[loss=0.2058, simple_loss=0.2809, pruned_loss=0.06538, over 7166.00 frames.], tot_loss[loss=0.259, simple_loss=0.3261, pruned_loss=0.09597, over 1425398.08 frames.], batch size: 18, lr: 1.13e-03
2022-05-26 19:55:22,255 INFO [train.py:842] (3/4) Epoch 4, batch 3500, loss[loss=0.2696, simple_loss=0.3396, pruned_loss=0.09979, over 7392.00 frames.], tot_loss[loss=0.2589, simple_loss=0.3257, pruned_loss=0.09608, over 1427099.01 frames.], batch size: 23, lr: 1.13e-03
2022-05-26 19:56:01,289 INFO [train.py:842] (3/4) Epoch 4, batch 3550, loss[loss=0.212, simple_loss=0.3004, pruned_loss=0.06178, over 7280.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3251, pruned_loss=0.09609, over 1429176.00 frames.], batch size: 24, lr: 1.13e-03
2022-05-26 19:56:39,778 INFO [train.py:842] (3/4) Epoch 4, batch 3600, loss[loss=0.2269, simple_loss=0.3007, pruned_loss=0.07658, over 7004.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3278, pruned_loss=0.09759, over 1427342.90 frames.], batch size: 16, lr: 1.13e-03
2022-05-26 19:57:18,412 INFO [train.py:842] (3/4) Epoch 4, batch 3650, loss[loss=0.2, simple_loss=0.2813, pruned_loss=0.05938, over 7135.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3293, pruned_loss=0.09898, over 1428385.73 frames.], batch size: 17, lr: 1.13e-03
2022-05-26 19:57:56,892 INFO [train.py:842] (3/4) Epoch 4, batch 3700, loss[loss=0.2242, simple_loss=0.2879, pruned_loss=0.08027, over 7004.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3287, pruned_loss=0.09891, over 1427527.49 frames.], batch size: 16, lr: 1.13e-03
2022-05-26 19:58:35,905 INFO [train.py:842] (3/4) Epoch 4, batch 3750, loss[loss=0.3273, simple_loss=0.3696, pruned_loss=0.1425, over 7433.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3266, pruned_loss=0.09757, over 1425121.06 frames.], batch size: 20, lr: 1.13e-03
2022-05-26 19:59:14,466 INFO [train.py:842] (3/4) Epoch 4, batch 3800, loss[loss=0.2812, simple_loss=0.3297, pruned_loss=0.1163, over 7459.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3283, pruned_loss=0.09899, over 1421346.01 frames.], batch size: 19, lr: 1.13e-03
2022-05-26 19:59:53,437 INFO [train.py:842] (3/4) Epoch 4, batch 3850, loss[loss=0.2081, simple_loss=0.2854, pruned_loss=0.06543, over 7399.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3286, pruned_loss=0.09931, over 1425676.21 frames.], batch size: 18, lr: 1.12e-03
2022-05-26 20:00:32,056 INFO [train.py:842] (3/4) Epoch 4, batch 3900, loss[loss=0.3013, simple_loss=0.3508, pruned_loss=0.1259, over 4978.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3281, pruned_loss=0.0986, over 1426246.77 frames.], batch size: 52, lr: 1.12e-03
2022-05-26 20:01:10,952 INFO [train.py:842] (3/4) Epoch 4, batch 3950, loss[loss=0.2033, simple_loss=0.2713, pruned_loss=0.06766, over 6820.00 frames.], tot_loss[loss=0.261, simple_loss=0.3267, pruned_loss=0.09767, over 1425280.44 frames.], batch size: 15, lr: 1.12e-03
2022-05-26 20:01:49,429 INFO [train.py:842] (3/4) Epoch 4, batch 4000, loss[loss=0.3511, simple_loss=0.3992, pruned_loss=0.1515, over 7224.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3281, pruned_loss=0.09905, over 1417565.82 frames.], batch size: 21, lr: 1.12e-03
2022-05-26 20:02:28,197 INFO [train.py:842] (3/4) Epoch 4, batch 4050, loss[loss=0.2385, simple_loss=0.3211, pruned_loss=0.07797, over 7418.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3274, pruned_loss=0.09845, over 1420225.08 frames.], batch size: 21, lr: 1.12e-03
2022-05-26 20:03:06,978 INFO [train.py:842] (3/4) Epoch 4, batch 4100, loss[loss=0.2451, simple_loss=0.3153, pruned_loss=0.08745, over 7415.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3292, pruned_loss=0.09887, over 1424654.59 frames.], batch size: 18, lr: 1.12e-03
2022-05-26 20:03:45,843 INFO [train.py:842] (3/4) Epoch 4, batch 4150, loss[loss=0.2122, simple_loss=0.2874, pruned_loss=0.06845, over 7235.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3283, pruned_loss=0.09815, over 1426471.94 frames.], batch size: 16, lr: 1.12e-03
2022-05-26 20:04:24,282 INFO [train.py:842] (3/4) Epoch 4, batch 4200, loss[loss=0.2373, simple_loss=0.3111, pruned_loss=0.08174, over 7274.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3282, pruned_loss=0.09776, over 1426584.13 frames.], batch size: 17, lr: 1.12e-03
2022-05-26 20:05:03,080 INFO [train.py:842] (3/4) Epoch 4, batch 4250, loss[loss=0.2792, simple_loss=0.3594, pruned_loss=0.09951, over 7228.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3284, pruned_loss=0.09764, over 1423965.99 frames.], batch size: 20, lr: 1.12e-03
2022-05-26 20:05:41,577 INFO [train.py:842] (3/4) Epoch 4, batch 4300, loss[loss=0.2764, simple_loss=0.3418, pruned_loss=0.1055, over 7242.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3285, pruned_loss=0.09742, over 1422822.54 frames.], batch size: 19, lr: 1.12e-03
2022-05-26 20:06:20,311 INFO [train.py:842] (3/4) Epoch 4, batch 4350, loss[loss=0.303, simple_loss=0.3531, pruned_loss=0.1264, over 7188.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3285, pruned_loss=0.09694, over 1421635.56 frames.], batch size: 23, lr: 1.12e-03
2022-05-26 20:06:58,795 INFO [train.py:842] (3/4) Epoch 4, batch 4400, loss[loss=0.241, simple_loss=0.3187, pruned_loss=0.08168, over 7230.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3283, pruned_loss=0.09676, over 1421814.69 frames.], batch size: 20, lr: 1.12e-03
2022-05-26 20:07:40,553 INFO [train.py:842] (3/4) Epoch 4, batch 4450, loss[loss=0.1793, simple_loss=0.2702, pruned_loss=0.04423, over 7353.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3279, pruned_loss=0.09657, over 1423132.45 frames.], batch size: 19, lr: 1.11e-03
2022-05-26 20:08:19,181 INFO [train.py:842] (3/4) Epoch 4, batch 4500, loss[loss=0.2928, simple_loss=0.359, pruned_loss=0.1133, over 7114.00 frames.], tot_loss[loss=0.259, simple_loss=0.3267, pruned_loss=0.09563, over 1426519.79 frames.], batch size: 21, lr: 1.11e-03
2022-05-26 20:08:58,296 INFO [train.py:842] (3/4) Epoch 4, batch 4550, loss[loss=0.2327, simple_loss=0.2995, pruned_loss=0.08293, over 7410.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3248, pruned_loss=0.09487, over 1424708.76 frames.], batch size: 18, lr: 1.11e-03
2022-05-26 20:09:36,948 INFO [train.py:842] (3/4) Epoch 4, batch 4600, loss[loss=0.2453, simple_loss=0.3283, pruned_loss=0.08115, over 7423.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3249, pruned_loss=0.09521, over 1425597.68 frames.], batch size: 21, lr: 1.11e-03
2022-05-26 20:10:15,680 INFO [train.py:842] (3/4) Epoch 4, batch 4650, loss[loss=0.3075, simple_loss=0.3616, pruned_loss=0.1267, over 7420.00 frames.], tot_loss[loss=0.2561, simple_loss=0.3237, pruned_loss=0.09423, over 1425282.74 frames.], batch size: 21, lr: 1.11e-03
2022-05-26 20:10:54,172 INFO [train.py:842] (3/4) Epoch 4, batch 4700, loss[loss=0.3012, simple_loss=0.3681, pruned_loss=0.1172, over 6761.00 frames.], tot_loss[loss=0.2606, simple_loss=0.327, pruned_loss=0.09708, over 1424862.14 frames.], batch size: 31, lr: 1.11e-03
2022-05-26 20:11:33,097 INFO [train.py:842] (3/4) Epoch 4, batch 4750, loss[loss=0.2382, simple_loss=0.3199, pruned_loss=0.07824, over 7129.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3262, pruned_loss=0.09607, over 1425188.04 frames.], batch size: 21, lr: 1.11e-03
2022-05-26 20:12:11,638 INFO [train.py:842] (3/4) Epoch 4, batch 4800, loss[loss=0.2658, simple_loss=0.3135, pruned_loss=0.1091, over 7140.00 frames.], tot_loss[loss=0.261, simple_loss=0.3273, pruned_loss=0.09737, over 1425348.41 frames.], batch size: 17, lr: 1.11e-03
2022-05-26 20:12:51,130 INFO [train.py:842] (3/4) Epoch 4, batch 4850, loss[loss=0.2215, simple_loss=0.2846, pruned_loss=0.07921, over 7220.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3247, pruned_loss=0.09553, over 1425790.01 frames.], batch size: 16, lr: 1.11e-03
2022-05-26 20:13:29,719 INFO [train.py:842] (3/4) Epoch 4, batch 4900, loss[loss=0.2702, simple_loss=0.343, pruned_loss=0.09868, over 7283.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3249, pruned_loss=0.09607, over 1424721.33 frames.], batch size: 24, lr: 1.11e-03
2022-05-26 20:14:08,466 INFO [train.py:842] (3/4) Epoch 4, batch 4950, loss[loss=0.2364, simple_loss=0.3205, pruned_loss=0.07618, over 7115.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3254, pruned_loss=0.09657, over 1424554.59 frames.], batch size: 21, lr: 1.11e-03
2022-05-26 20:14:46,913 INFO [train.py:842] (3/4) Epoch 4, batch 5000, loss[loss=0.2345, simple_loss=0.3092, pruned_loss=0.07986, over 7327.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3261, pruned_loss=0.0965, over 1424419.61 frames.], batch size: 20, lr: 1.11e-03
2022-05-26 20:15:25,497 INFO [train.py:842] (3/4) Epoch 4, batch 5050, loss[loss=0.2728, simple_loss=0.3485, pruned_loss=0.09848, over 7114.00 frames.], tot_loss[loss=0.2617, simple_loss=0.328, pruned_loss=0.09773, over 1424641.69 frames.], batch size: 26, lr: 1.10e-03
2022-05-26 20:16:04,089 INFO [train.py:842] (3/4) Epoch 4, batch 5100, loss[loss=0.2975, simple_loss=0.3561, pruned_loss=0.1195, over 7047.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3289, pruned_loss=0.09815, over 1422819.64 frames.], batch size: 28, lr: 1.10e-03
2022-05-26 20:16:43,105 INFO [train.py:842] (3/4) Epoch 4, batch 5150, loss[loss=0.204, simple_loss=0.2715, pruned_loss=0.06823, over 7262.00 frames.], tot_loss[loss=0.259, simple_loss=0.3265, pruned_loss=0.09575, over 1427894.54 frames.], batch size: 17, lr: 1.10e-03
2022-05-26 20:17:21,946 INFO [train.py:842] (3/4) Epoch 4, batch 5200, loss[loss=0.3181, simple_loss=0.3615, pruned_loss=0.1373, over 7361.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3278, pruned_loss=0.09689, over 1428765.36 frames.], batch size: 19, lr: 1.10e-03
2022-05-26 20:18:00,744 INFO [train.py:842] (3/4) Epoch 4, batch 5250, loss[loss=0.2936, simple_loss=0.3616, pruned_loss=0.1128, over 7112.00 frames.], tot_loss[loss=0.26, simple_loss=0.3269, pruned_loss=0.09652, over 1427219.24 frames.], batch size: 21, lr: 1.10e-03
2022-05-26 20:18:39,353 INFO [train.py:842] (3/4) Epoch 4, batch 5300, loss[loss=0.2949, simple_loss=0.353, pruned_loss=0.1184, over 7061.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3246, pruned_loss=0.09508, over 1430910.20 frames.], batch size: 18, lr: 1.10e-03
2022-05-26 20:19:18,348 INFO [train.py:842] (3/4) Epoch 4, batch 5350, loss[loss=0.244, simple_loss=0.3003, pruned_loss=0.09381, over 7284.00 frames.], tot_loss[loss=0.256, simple_loss=0.3234, pruned_loss=0.09433, over 1432257.85 frames.], batch size: 17, lr: 1.10e-03
2022-05-26 20:19:56,810 INFO [train.py:842] (3/4) Epoch 4, batch 5400, loss[loss=0.2917, simple_loss=0.3242, pruned_loss=0.1296, over 7286.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3238, pruned_loss=0.0947, over 1431714.61 frames.], batch size: 17, lr: 1.10e-03
2022-05-26 20:20:35,582 INFO [train.py:842] (3/4) Epoch 4, batch 5450, loss[loss=0.2643, simple_loss=0.3347, pruned_loss=0.09694, over 7178.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3245, pruned_loss=0.09538, over 1431037.06 frames.], batch size: 23, lr: 1.10e-03
2022-05-26 20:21:14,033 INFO [train.py:842] (3/4) Epoch 4, batch 5500, loss[loss=0.2489, simple_loss=0.3239, pruned_loss=0.08692, over 7165.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3261, pruned_loss=0.09639, over 1428898.54 frames.], batch size: 26, lr: 1.10e-03
2022-05-26 20:21:52,998 INFO [train.py:842] (3/4) Epoch 4, batch 5550, loss[loss=0.3017, simple_loss=0.3584, pruned_loss=0.1225, over 6680.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3266, pruned_loss=0.09718, over 1422729.92 frames.], batch size: 31, lr: 1.10e-03
2022-05-26 20:22:31,510 INFO [train.py:842] (3/4) Epoch 4, batch 5600, loss[loss=0.2035, simple_loss=0.28, pruned_loss=0.0635, over 7288.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3271, pruned_loss=0.09786, over 1426222.97 frames.], batch size: 18, lr: 1.10e-03
2022-05-26 20:23:10,163 INFO [train.py:842] (3/4) Epoch 4, batch 5650, loss[loss=0.2559, simple_loss=0.3334, pruned_loss=0.08917, over 7202.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3264, pruned_loss=0.0972, over 1422110.25 frames.], batch size: 23, lr: 1.09e-03
2022-05-26 20:23:48,774 INFO [train.py:842] (3/4) Epoch 4, batch 5700, loss[loss=0.3245, simple_loss=0.3844, pruned_loss=0.1323, over 7228.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3266, pruned_loss=0.09688, over 1422785.95 frames.], batch size: 20, lr: 1.09e-03
2022-05-26 20:24:27,444 INFO [train.py:842] (3/4) Epoch 4, batch 5750, loss[loss=0.3419, simple_loss=0.3902, pruned_loss=0.1468, over 7293.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3276, pruned_loss=0.09772, over 1422262.49 frames.], batch size: 25, lr: 1.09e-03
2022-05-26 20:25:06,088 INFO [train.py:842] (3/4) Epoch 4, batch 5800, loss[loss=0.2692, simple_loss=0.3419, pruned_loss=0.09825, over 7314.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3295, pruned_loss=0.09876, over 1421549.68 frames.], batch size: 21, lr: 1.09e-03
2022-05-26 20:25:44,939 INFO [train.py:842] (3/4) Epoch 4, batch 5850, loss[loss=0.2283, simple_loss=0.3036, pruned_loss=0.0765, over 6256.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3292, pruned_loss=0.09887, over 1418249.09 frames.], batch size: 37, lr: 1.09e-03
2022-05-26 20:26:23,781 INFO [train.py:842] (3/4) Epoch 4, batch 5900, loss[loss=0.257, simple_loss=0.3306, pruned_loss=0.09173, over 7329.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3275, pruned_loss=0.09774, over 1423668.32 frames.], batch size: 21, lr: 1.09e-03
2022-05-26 20:27:02,269 INFO [train.py:842] (3/4) Epoch 4, batch 5950, loss[loss=0.2546, simple_loss=0.3162, pruned_loss=0.09657, over 7144.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3295, pruned_loss=0.09972, over 1422608.59 frames.], batch size: 19, lr: 1.09e-03
2022-05-26 20:27:41,336 INFO [train.py:842] (3/4) Epoch 4, batch 6000, loss[loss=0.2441, simple_loss=0.331, pruned_loss=0.07863, over 7189.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3281, pruned_loss=0.09814, over 1420824.69 frames.], batch size: 23, lr: 1.09e-03
2022-05-26 20:27:41,337 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 20:27:50,628 INFO [train.py:871] (3/4) Epoch 4, validation: loss=0.1997, simple_loss=0.2983, pruned_loss=0.05051, over 868885.00 frames.
2022-05-26 20:28:29,548 INFO [train.py:842] (3/4) Epoch 4, batch 6050, loss[loss=0.3206, simple_loss=0.3755, pruned_loss=0.1329, over 7241.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3275, pruned_loss=0.0976, over 1417197.76 frames.], batch size: 20, lr: 1.09e-03
2022-05-26 20:29:08,218 INFO [train.py:842] (3/4) Epoch 4, batch 6100, loss[loss=0.2869, simple_loss=0.359, pruned_loss=0.1074, over 7113.00 frames.], tot_loss[loss=0.2613, simple_loss=0.3277, pruned_loss=0.09748, over 1414153.29 frames.], batch size: 21, lr: 1.09e-03
2022-05-26 20:29:47,419 INFO [train.py:842] (3/4) Epoch 4, batch 6150, loss[loss=0.2682, simple_loss=0.3329, pruned_loss=0.1018, over 7316.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3278, pruned_loss=0.09729, over 1418385.32 frames.], batch size: 25, lr: 1.09e-03
2022-05-26 20:30:26,278 INFO [train.py:842] (3/4) Epoch 4, batch 6200, loss[loss=0.1824, simple_loss=0.2624, pruned_loss=0.05122, over 7161.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3255, pruned_loss=0.09557, over 1421076.46 frames.], batch size: 17, lr: 1.09e-03
2022-05-26 20:31:05,413 INFO [train.py:842] (3/4) Epoch 4, batch 6250, loss[loss=0.2729, simple_loss=0.3381, pruned_loss=0.1039, over 7423.00 frames.], tot_loss[loss=0.2563, simple_loss=0.324, pruned_loss=0.09425, over 1419980.48 frames.], batch size: 20, lr: 1.08e-03
2022-05-26 20:31:44,041 INFO [train.py:842] (3/4) Epoch 4, batch 6300, loss[loss=0.2052, simple_loss=0.2822, pruned_loss=0.06409, over 7327.00 frames.], tot_loss[loss=0.2552, simple_loss=0.323, pruned_loss=0.09366, over 1424236.29 frames.], batch size: 21, lr: 1.08e-03
2022-05-26 20:32:22,633 INFO [train.py:842] (3/4) Epoch 4, batch 6350, loss[loss=0.2695, simple_loss=0.3375, pruned_loss=0.1008, over 7435.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3248, pruned_loss=0.09467, over 1419940.18 frames.], batch size: 20, lr: 1.08e-03
2022-05-26 20:33:01,278 INFO [train.py:842] (3/4) Epoch 4, batch 6400, loss[loss=0.355, simple_loss=0.3938, pruned_loss=0.1581, over 7367.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3255, pruned_loss=0.09487, over 1418490.52 frames.], batch size: 23, lr: 1.08e-03
2022-05-26 20:33:40,217 INFO [train.py:842] (3/4) Epoch 4, batch 6450, loss[loss=0.2935, simple_loss=0.3633, pruned_loss=0.1118, over 7306.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3264, pruned_loss=0.09563, over 1420782.43 frames.], batch size: 21, lr: 1.08e-03
2022-05-26 20:34:18,862 INFO [train.py:842] (3/4) Epoch 4, batch 6500, loss[loss=0.2142, simple_loss=0.2745, pruned_loss=0.07695, over 7279.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3263, pruned_loss=0.0962, over 1421655.55 frames.], batch size: 16, lr: 1.08e-03
2022-05-26 20:34:57,621 INFO [train.py:842] (3/4) Epoch 4, batch 6550, loss[loss=0.2616, simple_loss=0.3294, pruned_loss=0.09685, over 7358.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3251, pruned_loss=0.09458, over 1425434.27 frames.], batch size: 19, lr: 1.08e-03
2022-05-26 20:35:36,127 INFO [train.py:842] (3/4) Epoch 4, batch 6600, loss[loss=0.2675, simple_loss=0.3348, pruned_loss=0.1001, over 7195.00 frames.], tot_loss[loss=0.257, simple_loss=0.3247, pruned_loss=0.09461, over 1420673.26 frames.], batch size: 22, lr: 1.08e-03
2022-05-26 20:36:14,973 INFO [train.py:842] (3/4) Epoch 4, batch 6650, loss[loss=0.2456, simple_loss=0.3199, pruned_loss=0.08561, over 7342.00 frames.], tot_loss[loss=0.259, simple_loss=0.3263, pruned_loss=0.0959, over 1423050.61 frames.], batch size: 22, lr: 1.08e-03
2022-05-26 20:36:53,543 INFO [train.py:842] (3/4) Epoch 4, batch 6700, loss[loss=0.1964, simple_loss=0.2715, pruned_loss=0.06062, over 7130.00 frames.], tot_loss[loss=0.257, simple_loss=0.3254, pruned_loss=0.09433, over 1421836.65 frames.], batch size: 17, lr: 1.08e-03
2022-05-26 20:37:32,293 INFO [train.py:842] (3/4) Epoch 4, batch 6750, loss[loss=0.2634, simple_loss=0.3322, pruned_loss=0.09734, over 7224.00 frames.], tot_loss[loss=0.2561, simple_loss=0.3247, pruned_loss=0.09381, over 1421679.59 frames.], batch size: 23, lr: 1.08e-03
2022-05-26 20:38:11,171 INFO [train.py:842] (3/4) Epoch 4, batch 6800, loss[loss=0.3168, simple_loss=0.3586, pruned_loss=0.1375, over 7414.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3243, pruned_loss=0.09405, over 1423771.74 frames.], batch size: 21, lr: 1.08e-03
2022-05-26 20:38:50,335 INFO [train.py:842] (3/4) Epoch 4, batch 6850, loss[loss=0.3141, simple_loss=0.3734, pruned_loss=0.1274, over 7305.00 frames.], tot_loss[loss=0.2584, simple_loss=0.3259, pruned_loss=0.09544, over 1423037.35 frames.], batch size: 25, lr: 1.08e-03
2022-05-26 20:39:29,165 INFO [train.py:842] (3/4) Epoch 4, batch 6900, loss[loss=0.2488, simple_loss=0.3175, pruned_loss=0.08999, over 7221.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3242, pruned_loss=0.09454, over 1424336.74 frames.], batch size: 22, lr: 1.07e-03
2022-05-26 20:40:08,054 INFO [train.py:842] (3/4) Epoch 4, batch 6950, loss[loss=0.2187, simple_loss=0.2972, pruned_loss=0.07014, over 7270.00 frames.], tot_loss[loss=0.2585, simple_loss=0.325, pruned_loss=0.09602, over 1423045.70 frames.], batch size: 19, lr: 1.07e-03
2022-05-26 20:40:46,540 INFO [train.py:842] (3/4) Epoch 4, batch 7000, loss[loss=0.2078, simple_loss=0.2889, pruned_loss=0.06332, over 7166.00 frames.], tot_loss[loss=0.26, simple_loss=0.3261, pruned_loss=0.09692, over 1421028.61 frames.], batch size: 19, lr: 1.07e-03
2022-05-26 20:41:25,589 INFO [train.py:842] (3/4) Epoch 4, batch 7050, loss[loss=0.2827, simple_loss=0.3478, pruned_loss=0.1088, over 7324.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3268, pruned_loss=0.09682, over 1419498.11 frames.], batch size: 21, lr: 1.07e-03
2022-05-26 20:42:04,341 INFO [train.py:842] (3/4) Epoch 4, batch 7100, loss[loss=0.2622, simple_loss=0.3398, pruned_loss=0.09228, over 7313.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3244, pruned_loss=0.09508, over 1422693.00 frames.], batch size: 21, lr: 1.07e-03
2022-05-26 20:42:43,535 INFO [train.py:842] (3/4) Epoch 4, batch 7150, loss[loss=0.2256, simple_loss=0.3072, pruned_loss=0.07206, over 7145.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3248, pruned_loss=0.09496, over 1421329.05 frames.], batch size: 20, lr: 1.07e-03
2022-05-26 20:43:22,296 INFO [train.py:842] (3/4) Epoch 4, batch 7200, loss[loss=0.2222, simple_loss=0.3045, pruned_loss=0.06991, over 7220.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3254, pruned_loss=0.09599, over 1419857.18 frames.], batch size: 21, lr: 1.07e-03
2022-05-26 20:44:01,269 INFO [train.py:842] (3/4) Epoch 4, batch 7250, loss[loss=0.2283, simple_loss=0.3117, pruned_loss=0.07247, over 7410.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3233, pruned_loss=0.09461, over 1419741.76 frames.], batch size: 21, lr: 1.07e-03
2022-05-26 20:44:39,863 INFO [train.py:842] (3/4) Epoch 4, batch 7300, loss[loss=0.2129, simple_loss=0.2947, pruned_loss=0.06557, over 7326.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3249, pruned_loss=0.09585, over 1421345.15 frames.], batch size: 22, lr: 1.07e-03
2022-05-26 20:45:18,997 INFO [train.py:842] (3/4) Epoch 4, batch 7350, loss[loss=0.281, simple_loss=0.3495, pruned_loss=0.1063, over 7315.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3247, pruned_loss=0.09541, over 1421021.29 frames.], batch size: 21, lr: 1.07e-03
2022-05-26 20:45:57,675 INFO [train.py:842] (3/4) Epoch 4, batch 7400, loss[loss=0.2289, simple_loss=0.3084, pruned_loss=0.0747, over 7326.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3238, pruned_loss=0.09432, over 1421464.06 frames.], batch size: 20, lr: 1.07e-03
2022-05-26 20:46:36,601 INFO [train.py:842] (3/4) Epoch 4, batch 7450, loss[loss=0.2601, simple_loss=0.3318, pruned_loss=0.0942, over 7275.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3229, pruned_loss=0.09386, over 1418538.33 frames.], batch size: 25, lr: 1.07e-03
2022-05-26 20:47:15,387 INFO [train.py:842] (3/4) Epoch 4, batch 7500, loss[loss=0.2251, simple_loss=0.3028, pruned_loss=0.07368, over 7363.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3227, pruned_loss=0.094, over 1421474.10 frames.], batch size: 19, lr: 1.07e-03
2022-05-26 20:47:54,205 INFO [train.py:842] (3/4) Epoch 4, batch 7550, loss[loss=0.2762, simple_loss=0.3388, pruned_loss=0.1068, over 6461.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3226, pruned_loss=0.09386, over 1424478.84 frames.], batch size: 38, lr: 1.07e-03
2022-05-26 20:48:32,777 INFO [train.py:842] (3/4) Epoch 4, batch 7600, loss[loss=0.2611, simple_loss=0.3201, pruned_loss=0.101, over 7136.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3216, pruned_loss=0.09311, over 1424400.64 frames.], batch size: 17, lr: 1.06e-03
2022-05-26 20:49:11,716 INFO [train.py:842] (3/4) Epoch 4, batch 7650, loss[loss=0.2656, simple_loss=0.326, pruned_loss=0.1026, over 7263.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3222, pruned_loss=0.09379, over 1427656.14 frames.], batch size: 19, lr: 1.06e-03
2022-05-26 20:49:50,453 INFO [train.py:842] (3/4) Epoch 4, batch 7700, loss[loss=0.2552, simple_loss=0.3351, pruned_loss=0.08769, over 7151.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3224, pruned_loss=0.09435, over 1427386.88 frames.], batch size: 19, lr: 1.06e-03
2022-05-26 20:50:29,408 INFO [train.py:842] (3/4) Epoch 4, batch 7750, loss[loss=0.3107, simple_loss=0.366, pruned_loss=0.1277, over 6369.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3223, pruned_loss=0.094, over 1428414.18 frames.], batch size: 38, lr: 1.06e-03
2022-05-26 20:51:08,062 INFO [train.py:842] (3/4) Epoch 4, batch 7800, loss[loss=0.2424, simple_loss=0.3066, pruned_loss=0.08916, over 7327.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3205, pruned_loss=0.09284, over 1426464.29 frames.], batch size: 20, lr: 1.06e-03
2022-05-26 20:51:46,880 INFO [train.py:842] (3/4) Epoch 4, batch 7850, loss[loss=0.305, simple_loss=0.3674, pruned_loss=0.1213, over 6519.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3199, pruned_loss=0.09232, over 1424079.66 frames.], batch size: 38, lr: 1.06e-03
2022-05-26 20:52:25,504 INFO [train.py:842] (3/4) Epoch 4, batch 7900, loss[loss=0.2607, simple_loss=0.3203, pruned_loss=0.1006, over 7435.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3204, pruned_loss=0.09205, over 1425687.70 frames.], batch size: 18, lr: 1.06e-03
2022-05-26 20:53:04,276 INFO [train.py:842] (3/4) Epoch 4, batch 7950, loss[loss=0.24, simple_loss=0.3096, pruned_loss=0.08522, over 7172.00 frames.], tot_loss[loss=0.2529, simple_loss=0.321, pruned_loss=0.09243, over 1425011.94 frames.], batch size: 18, lr: 1.06e-03
2022-05-26 20:53:42,692 INFO [train.py:842] (3/4) Epoch 4, batch 8000, loss[loss=0.2694, simple_loss=0.3401, pruned_loss=0.09928, over 6323.00 frames.], tot_loss[loss=0.2549, simple_loss=0.323, pruned_loss=0.0934, over 1424271.56 frames.], batch size: 37, lr: 1.06e-03
2022-05-26 20:54:21,451 INFO [train.py:842] (3/4) Epoch 4, batch 8050, loss[loss=0.2452, simple_loss=0.327, pruned_loss=0.08172, over 7319.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3228, pruned_loss=0.09343, over 1424465.77 frames.], batch size: 21, lr: 1.06e-03
2022-05-26 20:54:59,916 INFO [train.py:842] (3/4) Epoch 4, batch 8100, loss[loss=0.2356, simple_loss=0.3075, pruned_loss=0.08188, over 7061.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3243, pruned_loss=0.09451, over 1425200.66 frames.], batch size: 28, lr: 1.06e-03
2022-05-26 20:55:38,682 INFO [train.py:842] (3/4) Epoch 4, batch 8150, loss[loss=0.281, simple_loss=0.3376, pruned_loss=0.1122, over 7435.00 frames.], tot_loss[loss=0.2562, simple_loss=0.324, pruned_loss=0.09415, over 1428106.22 frames.], batch size: 20, lr: 1.06e-03
2022-05-26 20:56:17,365 INFO [train.py:842] (3/4) Epoch 4, batch 8200, loss[loss=0.2724, simple_loss=0.3452, pruned_loss=0.0998, over 7215.00 frames.], tot_loss[loss=0.255, simple_loss=0.3234, pruned_loss=0.0933, over 1430100.26 frames.], batch size: 23, lr: 1.06e-03
2022-05-26 20:56:56,004 INFO [train.py:842] (3/4) Epoch 4, batch 8250, loss[loss=0.2805, simple_loss=0.3521, pruned_loss=0.1045, over 7295.00 frames.], tot_loss[loss=0.2571, simple_loss=0.325, pruned_loss=0.0946, over 1419446.62 frames.], batch size: 25, lr: 1.05e-03
2022-05-26 20:57:34,478 INFO [train.py:842] (3/4) Epoch 4, batch 8300, loss[loss=0.2762, simple_loss=0.3576, pruned_loss=0.09744, over 7190.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3257, pruned_loss=0.09487, over 1420750.66 frames.], batch size: 26, lr: 1.05e-03
2022-05-26 20:58:13,601 INFO [train.py:842] (3/4) Epoch 4, batch 8350, loss[loss=0.2289, simple_loss=0.308, pruned_loss=0.07487, over 7170.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3243, pruned_loss=0.09414, over 1418083.76 frames.], batch size: 26, lr: 1.05e-03
2022-05-26 20:58:52,462 INFO [train.py:842] (3/4) Epoch 4, batch 8400, loss[loss=0.1804, simple_loss=0.2575, pruned_loss=0.05163, over 7057.00 frames.], tot_loss[loss=0.2564, simple_loss=0.324, pruned_loss=0.09445, over 1420044.01 frames.], batch size: 18, lr: 1.05e-03
2022-05-26 20:59:31,368 INFO [train.py:842] (3/4) Epoch 4, batch 8450, loss[loss=0.3254, simple_loss=0.3754, pruned_loss=0.1377, over 7359.00 frames.], tot_loss[loss=0.2568, simple_loss=0.3241, pruned_loss=0.09479, over 1420825.33 frames.], batch size: 19, lr: 1.05e-03
2022-05-26 21:00:09,904 INFO [train.py:842] (3/4) Epoch 4, batch 8500, loss[loss=0.2319, simple_loss=0.3092, pruned_loss=0.07728, over 7267.00 frames.], tot_loss[loss=0.2565, simple_loss=0.324, pruned_loss=0.09449, over 1421575.43 frames.], batch size: 19, lr: 1.05e-03
2022-05-26 21:00:48,720 INFO [train.py:842] (3/4) Epoch 4, batch 8550, loss[loss=0.275, simple_loss=0.334, pruned_loss=0.108, over 7416.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3251, pruned_loss=0.09576, over 1417008.35 frames.], batch size: 18, lr: 1.05e-03
2022-05-26 21:01:27,368 INFO [train.py:842] (3/4) Epoch 4, batch 8600, loss[loss=0.269, simple_loss=0.3465, pruned_loss=0.09573, over 7205.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3241, pruned_loss=0.09554, over 1418768.57 frames.], batch size: 26, lr: 1.05e-03
2022-05-26 21:02:06,572 INFO [train.py:842] (3/4) Epoch 4, batch 8650, loss[loss=0.2649, simple_loss=0.3355, pruned_loss=0.09712, over 7388.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3242, pruned_loss=0.0956, over 1418149.09 frames.], batch size: 23, lr: 1.05e-03
2022-05-26 21:02:45,058 INFO [train.py:842] (3/4) Epoch 4, batch 8700, loss[loss=0.2839, simple_loss=0.3486, pruned_loss=0.1096, over 7178.00 frames.], tot_loss[loss=0.2551, simple_loss=0.322, pruned_loss=0.09406, over 1415012.36 frames.], batch size: 26, lr: 1.05e-03
2022-05-26 21:03:23,722 INFO [train.py:842] (3/4) Epoch 4, batch 8750, loss[loss=0.27, simple_loss=0.3244, pruned_loss=0.1078, over 5159.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3217, pruned_loss=0.09421, over 1403307.91 frames.], batch size: 52, lr: 1.05e-03
2022-05-26 21:04:02,237 INFO [train.py:842] (3/4) Epoch 4, batch 8800, loss[loss=0.2507, simple_loss=0.3268, pruned_loss=0.08728, over 6626.00 frames.], tot_loss[loss=0.2561, simple_loss=0.3217, pruned_loss=0.09523, over 1401732.63 frames.], batch size: 31, lr: 1.05e-03
2022-05-26 21:04:40,831 INFO [train.py:842] (3/4) Epoch 4, batch 8850, loss[loss=0.2447, simple_loss=0.3115, pruned_loss=0.089, over 7156.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3202, pruned_loss=0.09451, over 1395318.33 frames.], batch size: 18, lr: 1.05e-03
2022-05-26 21:05:19,465 INFO [train.py:842] (3/4) Epoch 4, batch 8900, loss[loss=0.2461, simple_loss=0.3064, pruned_loss=0.09288, over 7154.00 frames.], tot_loss[loss=0.2554, simple_loss=0.3208, pruned_loss=0.09498, over 1391805.03 frames.], batch size: 18, lr: 1.05e-03
2022-05-26 21:05:58,252 INFO [train.py:842] (3/4) Epoch 4, batch 8950, loss[loss=0.2642, simple_loss=0.3224, pruned_loss=0.103, over 7356.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3208, pruned_loss=0.09591, over 1390976.31 frames.], batch size: 19, lr: 1.04e-03
2022-05-26 21:06:36,759 INFO [train.py:842] (3/4) Epoch 4, batch 9000, loss[loss=0.2332, simple_loss=0.3106, pruned_loss=0.07786, over 7165.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3216, pruned_loss=0.09629, over 1379743.00 frames.], batch size: 19, lr: 1.04e-03
2022-05-26 21:06:36,760 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 21:06:46,020 INFO [train.py:871] (3/4) Epoch 4, validation: loss=0.1922, simple_loss=0.292, pruned_loss=0.04621, over 868885.00 frames.
2022-05-26 21:07:24,222 INFO [train.py:842] (3/4) Epoch 4, batch 9050, loss[loss=0.2732, simple_loss=0.3313, pruned_loss=0.1076, over 5095.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3228, pruned_loss=0.09652, over 1362530.14 frames.], batch size: 52, lr: 1.04e-03
2022-05-26 21:08:01,822 INFO [train.py:842] (3/4) Epoch 4, batch 9100, loss[loss=0.2512, simple_loss=0.3326, pruned_loss=0.08485, over 6141.00 frames.], tot_loss[loss=0.262, simple_loss=0.3269, pruned_loss=0.09857, over 1340086.94 frames.], batch size: 37, lr: 1.04e-03
2022-05-26 21:08:39,500 INFO [train.py:842] (3/4) Epoch 4, batch 9150, loss[loss=0.3054, simple_loss=0.3576, pruned_loss=0.1266, over 5214.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3319, pruned_loss=0.1028, over 1283379.52 frames.], batch size: 52, lr: 1.04e-03
2022-05-26 21:09:32,018 INFO [train.py:842] (3/4) Epoch 5, batch 0, loss[loss=0.2925, simple_loss=0.3534, pruned_loss=0.1158, over 7202.00 frames.], tot_loss[loss=0.2925, simple_loss=0.3534, pruned_loss=0.1158, over 7202.00 frames.], batch size: 23, lr: 1.00e-03
2022-05-26 21:10:11,440 INFO [train.py:842] (3/4) Epoch 5, batch 50, loss[loss=0.3145, simple_loss=0.372, pruned_loss=0.1285, over 7344.00 frames.], tot_loss[loss=0.2487, simple_loss=0.318, pruned_loss=0.0897, over 320928.70 frames.], batch size: 22, lr: 1.00e-03
2022-05-26 21:10:50,258 INFO [train.py:842] (3/4) Epoch 5, batch 100, loss[loss=0.321, simple_loss=0.3844, pruned_loss=0.1288, over 7343.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3216, pruned_loss=0.09184, over 567454.20 frames.], batch size: 22, lr: 1.00e-03
2022-05-26 21:11:29,044 INFO [train.py:842] (3/4) Epoch 5, batch 150, loss[loss=0.2939, simple_loss=0.3529, pruned_loss=0.1175, over 5074.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3244, pruned_loss=0.09434, over 756038.58 frames.], batch size: 53, lr: 1.00e-03
2022-05-26 21:12:07,508 INFO [train.py:842] (3/4) Epoch 5, batch 200, loss[loss=0.2157, simple_loss=0.2975, pruned_loss=0.06697, over 7145.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3248, pruned_loss=0.0943, over 904313.39 frames.], batch size: 19, lr: 1.00e-03
2022-05-26 21:12:46,189 INFO [train.py:842] (3/4) Epoch 5, batch 250, loss[loss=0.2171, simple_loss=0.3067, pruned_loss=0.06375, over 7345.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3249, pruned_loss=0.09301, over 1021601.26 frames.], batch size: 22, lr: 1.00e-03
2022-05-26 21:13:25,004 INFO [train.py:842] (3/4) Epoch 5, batch 300, loss[loss=0.2051, simple_loss=0.2822, pruned_loss=0.06397, over 7285.00 frames.], tot_loss[loss=0.2514, simple_loss=0.321, pruned_loss=0.0909, over 1112858.45 frames.], batch size: 17, lr: 1.00e-03
2022-05-26 21:14:03,875 INFO [train.py:842] (3/4) Epoch 5, batch 350, loss[loss=0.2292, simple_loss=0.2881, pruned_loss=0.08515, over 7162.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3189, pruned_loss=0.09034, over 1181512.99 frames.], batch size: 19, lr: 1.00e-03
2022-05-26 21:14:42,439 INFO [train.py:842] (3/4) Epoch 5, batch 400, loss[loss=0.2849, simple_loss=0.3557, pruned_loss=0.107, over 7149.00 frames.], tot_loss[loss=0.2512, simple_loss=0.32, pruned_loss=0.09125, over 1232374.84 frames.], batch size: 28, lr: 9.99e-04
2022-05-26 21:15:21,502 INFO [train.py:842] (3/4) Epoch 5, batch 450, loss[loss=0.3035, simple_loss=0.3534, pruned_loss=0.1268, over 7108.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3217, pruned_loss=0.09233, over 1274301.86 frames.], batch size: 28, lr: 9.99e-04
2022-05-26 21:16:00,460 INFO [train.py:842] (3/4) Epoch 5, batch 500, loss[loss=0.2787, simple_loss=0.3461, pruned_loss=0.1057, over 7320.00 frames.], tot_loss[loss=0.2521, simple_loss=0.321, pruned_loss=0.09162, over 1309349.33 frames.], batch size: 21, lr: 9.98e-04
2022-05-26 21:16:39,274 INFO [train.py:842] (3/4) Epoch 5, batch 550, loss[loss=0.2697, simple_loss=0.3372, pruned_loss=0.1011, over 6811.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3194, pruned_loss=0.09001, over 1333871.05 frames.], batch size: 31, lr: 9.97e-04
2022-05-26 21:17:17,938 INFO [train.py:842] (3/4) Epoch 5, batch 600, loss[loss=0.272, simple_loss=0.3207, pruned_loss=0.1116, over 7004.00 frames.], tot_loss[loss=0.2498, simple_loss=0.319, pruned_loss=0.09027, over 1356016.12 frames.], batch size: 16, lr: 9.97e-04
2022-05-26 21:17:56,778 INFO [train.py:842] (3/4) Epoch 5, batch 650, loss[loss=0.2086, simple_loss=0.2957, pruned_loss=0.06079, over 7333.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3187, pruned_loss=0.08991, over 1371155.39 frames.], batch size: 20, lr: 9.96e-04
2022-05-26 21:18:35,187 INFO [train.py:842] (3/4) Epoch 5, batch 700, loss[loss=0.2588, simple_loss=0.3323, pruned_loss=0.0926, over 7295.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3202, pruned_loss=0.09039, over 1380937.66 frames.], batch size: 25, lr: 9.95e-04
2022-05-26 21:19:14,036 INFO [train.py:842] (3/4) Epoch 5, batch 750, loss[loss=0.2054, simple_loss=0.2826, pruned_loss=0.06413, over 7056.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3197, pruned_loss=0.09088, over 1385544.07 frames.], batch size: 18, lr: 9.95e-04
2022-05-26 21:19:52,744 INFO [train.py:842] (3/4) Epoch 5, batch 800, loss[loss=0.2214, simple_loss=0.2985, pruned_loss=0.07215, over 7063.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3179, pruned_loss=0.09027, over 1397104.81 frames.], batch size: 18, lr: 9.94e-04
2022-05-26 21:20:31,422 INFO [train.py:842] (3/4) Epoch 5, batch 850, loss[loss=0.2794, simple_loss=0.3411, pruned_loss=0.1089, over 7066.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3176, pruned_loss=0.08948, over 1396166.96 frames.], batch size: 18, lr: 9.93e-04
2022-05-26 21:21:09,964 INFO [train.py:842] (3/4) Epoch 5, batch 900, loss[loss=0.253, simple_loss=0.3398, pruned_loss=0.08308, over 7318.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3181, pruned_loss=0.08918, over 1403474.02 frames.], batch size: 21, lr: 9.93e-04
2022-05-26 21:21:48,890 INFO [train.py:842] (3/4) Epoch 5, batch 950, loss[loss=0.2724, simple_loss=0.3307, pruned_loss=0.107, over 7041.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3195, pruned_loss=0.09071, over 1407406.08 frames.], batch size: 28, lr: 9.92e-04
2022-05-26 21:22:27,574 INFO [train.py:842] (3/4) Epoch 5, batch 1000, loss[loss=0.2167, simple_loss=0.2946, pruned_loss=0.06939, over 7062.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3182, pruned_loss=0.09001, over 1411678.05 frames.], batch size: 18, lr: 9.91e-04
2022-05-26 21:23:06,453 INFO [train.py:842] (3/4) Epoch 5, batch 1050, loss[loss=0.2793, simple_loss=0.3505, pruned_loss=0.1041, over 7286.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3186, pruned_loss=0.08927, over 1417038.82 frames.], batch size: 24, lr: 9.91e-04
2022-05-26 21:23:44,733 INFO [train.py:842] (3/4) Epoch 5, batch 1100, loss[loss=0.3085, simple_loss=0.3639, pruned_loss=0.1265, over 6315.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3191, pruned_loss=0.08965, over 1413005.80 frames.], batch size: 38, lr: 9.90e-04
2022-05-26 21:24:23,633 INFO [train.py:842] (3/4) Epoch 5, batch 1150, loss[loss=0.2466, simple_loss=0.3214, pruned_loss=0.08588, over 7429.00 frames.], tot_loss[loss=0.25, simple_loss=0.32, pruned_loss=0.09003, over 1415737.05 frames.], batch size: 20, lr: 9.89e-04
2022-05-26 21:25:02,151 INFO [train.py:842] (3/4) Epoch 5, batch 1200, loss[loss=0.3576, simple_loss=0.3897, pruned_loss=0.1627, over 6322.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3192, pruned_loss=0.08991, over 1417679.88 frames.], batch size: 37, lr: 9.89e-04
2022-05-26 21:25:40,995 INFO [train.py:842] (3/4) Epoch 5, batch 1250, loss[loss=0.2071, simple_loss=0.2827, pruned_loss=0.0657, over 7261.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3189, pruned_loss=0.08978, over 1412074.18 frames.], batch size: 19, lr: 9.88e-04
2022-05-26 21:26:19,438 INFO [train.py:842] (3/4) Epoch 5, batch 1300, loss[loss=0.2202, simple_loss=0.3038, pruned_loss=0.06834, over 7328.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3193, pruned_loss=0.08998, over 1415487.86 frames.], batch size: 20, lr: 9.87e-04
2022-05-26 21:26:58,324 INFO [train.py:842] (3/4) Epoch 5, batch 1350, loss[loss=0.1629, simple_loss=0.2349, pruned_loss=0.04544, over 7116.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3201, pruned_loss=0.09071, over 1422219.19 frames.], batch size: 17, lr: 9.87e-04
2022-05-26 21:27:36,946 INFO [train.py:842] (3/4) Epoch 5, batch 1400, loss[loss=0.2679, simple_loss=0.3371, pruned_loss=0.09937, over 7240.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3213, pruned_loss=0.091, over 1418882.46 frames.], batch size: 20, lr: 9.86e-04
2022-05-26 21:28:15,799 INFO [train.py:842] (3/4) Epoch 5, batch 1450, loss[loss=0.211, simple_loss=0.2848, pruned_loss=0.0686, over 6998.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3215, pruned_loss=0.09063, over 1419592.55 frames.], batch size: 16, lr: 9.86e-04
2022-05-26 21:28:54,583 INFO [train.py:842] (3/4) Epoch 5, batch 1500, loss[loss=0.2502, simple_loss=0.321, pruned_loss=0.08975, over 7328.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3194, pruned_loss=0.08935, over 1422833.75 frames.], batch size: 20, lr: 9.85e-04
2022-05-26 21:29:33,928 INFO [train.py:842] (3/4) Epoch 5, batch 1550, loss[loss=0.2652, simple_loss=0.3284, pruned_loss=0.1011, over 7388.00 frames.], tot_loss[loss=0.248, simple_loss=0.3179, pruned_loss=0.08899, over 1424249.30 frames.], batch size: 23, lr: 9.84e-04
2022-05-26 21:30:12,539 INFO [train.py:842] (3/4) Epoch 5, batch 1600, loss[loss=0.3366, simple_loss=0.3877, pruned_loss=0.1428, over 7271.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3175, pruned_loss=0.08859, over 1423823.64 frames.], batch size: 25, lr: 9.84e-04
2022-05-26 21:31:01,970 INFO [train.py:842] (3/4) Epoch 5, batch 1650, loss[loss=0.2397, simple_loss=0.3211, pruned_loss=0.07915, over 7113.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3183, pruned_loss=0.08911, over 1421474.18 frames.], batch size: 21, lr: 9.83e-04
2022-05-26 21:31:40,737 INFO [train.py:842] (3/4) Epoch 5, batch 1700, loss[loss=0.2459, simple_loss=0.3278, pruned_loss=0.08194, over 7332.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3181, pruned_loss=0.08936, over 1423958.29 frames.], batch size: 22, lr: 9.82e-04
2022-05-26 21:32:19,660 INFO [train.py:842] (3/4) Epoch 5, batch 1750, loss[loss=0.2331, simple_loss=0.3192, pruned_loss=0.07353, over 7281.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3172, pruned_loss=0.08857, over 1423304.94 frames.], batch size: 24, lr: 9.82e-04
2022-05-26 21:32:58,283 INFO [train.py:842] (3/4) Epoch 5, batch 1800, loss[loss=0.2207, simple_loss=0.3054, pruned_loss=0.06799, over 7318.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3182, pruned_loss=0.08958, over 1426098.00 frames.], batch size: 21, lr: 9.81e-04
2022-05-26 21:33:37,270 INFO [train.py:842] (3/4) Epoch 5, batch 1850, loss[loss=0.2337, simple_loss=0.3176, pruned_loss=0.07488, over 6398.00 frames.], tot_loss[loss=0.2497, simple_loss=0.319, pruned_loss=0.09023, over 1426431.87 frames.], batch size: 38, lr: 9.81e-04
2022-05-26 21:34:15,860 INFO [train.py:842] (3/4) Epoch 5, batch 1900, loss[loss=0.2557, simple_loss=0.3356, pruned_loss=0.08789, over 7109.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3185, pruned_loss=0.08904, over 1427676.81 frames.], batch size: 21, lr: 9.80e-04
2022-05-26 21:34:55,039 INFO [train.py:842] (3/4) Epoch 5, batch 1950, loss[loss=0.2244, simple_loss=0.2967, pruned_loss=0.07607, over 7157.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3198, pruned_loss=0.09024, over 1428783.80 frames.], batch size: 18, lr: 9.79e-04
2022-05-26 21:35:33,839 INFO [train.py:842] (3/4) Epoch 5, batch 2000, loss[loss=0.2794, simple_loss=0.3485, pruned_loss=0.1051, over 7293.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3194, pruned_loss=0.09019, over 1425774.68 frames.], batch size: 25, lr: 9.79e-04
2022-05-26 21:36:12,766 INFO [train.py:842] (3/4) Epoch 5, batch 2050, loss[loss=0.2407, simple_loss=0.3096, pruned_loss=0.08588, over 7267.00 frames.], tot_loss[loss=0.25, simple_loss=0.3192, pruned_loss=0.09039, over 1431157.58 frames.], batch size: 24, lr: 9.78e-04
2022-05-26 21:36:51,531 INFO [train.py:842] (3/4) Epoch 5, batch 2100, loss[loss=0.2189, simple_loss=0.2852, pruned_loss=0.07631, over 7412.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3191, pruned_loss=0.09042, over 1434443.73 frames.], batch size: 18, lr: 9.77e-04
2022-05-26 21:37:30,128 INFO [train.py:842] (3/4) Epoch 5, batch 2150, loss[loss=0.2273, simple_loss=0.3039, pruned_loss=0.07541, over 7057.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3205, pruned_loss=0.0903, over 1432835.61 frames.], batch size: 18, lr: 9.77e-04
2022-05-26 21:38:08,837 INFO [train.py:842] (3/4) Epoch 5, batch 2200, loss[loss=0.2569, simple_loss=0.3366, pruned_loss=0.08861, over 7344.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3189, pruned_loss=0.08918, over 1433390.52 frames.], batch size: 22, lr: 9.76e-04
2022-05-26 21:38:47,526 INFO [train.py:842] (3/4) Epoch 5, batch 2250, loss[loss=0.2341, simple_loss=0.3105, pruned_loss=0.07883, over 7379.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3182, pruned_loss=0.08925, over 1431050.39 frames.], batch size: 23, lr: 9.76e-04
2022-05-26 21:39:26,221 INFO [train.py:842] (3/4) Epoch 5, batch 2300, loss[loss=0.1913, simple_loss=0.2615, pruned_loss=0.06058, over 7284.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3175, pruned_loss=0.08867, over 1429265.85 frames.], batch size: 17, lr: 9.75e-04
2022-05-26 21:40:05,066 INFO [train.py:842] (3/4) Epoch 5, batch 2350, loss[loss=0.2127, simple_loss=0.2919, pruned_loss=0.06673, over 7419.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3166, pruned_loss=0.08763, over 1432901.53 frames.], batch size: 18, lr: 9.74e-04
2022-05-26 21:40:53,748 INFO [train.py:842] (3/4) Epoch 5, batch 2400, loss[loss=0.2466, simple_loss=0.3203, pruned_loss=0.08644, over 7215.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3167, pruned_loss=0.0884, over 1434905.42 frames.], batch size: 21, lr: 9.74e-04
2022-05-26 21:41:32,666 INFO [train.py:842] (3/4) Epoch 5, batch 2450, loss[loss=0.2588, simple_loss=0.3211, pruned_loss=0.09825, over 7286.00 frames.], tot_loss[loss=0.248, simple_loss=0.3179, pruned_loss=0.0891, over 1434701.40 frames.], batch size: 18, lr: 9.73e-04
2022-05-26 21:42:21,533 INFO [train.py:842] (3/4) Epoch 5, batch 2500, loss[loss=0.2658, simple_loss=0.3291, pruned_loss=0.1012, over 7211.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3183, pruned_loss=0.08977, over 1432310.81 frames.], batch size: 22, lr: 9.73e-04
2022-05-26 21:43:11,049 INFO [train.py:842] (3/4) Epoch 5, batch 2550, loss[loss=0.2317, simple_loss=0.3053, pruned_loss=0.07903, over 7151.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3191, pruned_loss=0.08963, over 1432700.12 frames.], batch size: 20, lr: 9.72e-04
2022-05-26 21:43:49,614 INFO [train.py:842] (3/4) Epoch 5, batch 2600, loss[loss=0.2257, simple_loss=0.3119, pruned_loss=0.06974, over 7320.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3191, pruned_loss=0.08936, over 1430933.16 frames.], batch size: 21, lr: 9.71e-04
2022-05-26 21:44:28,569 INFO [train.py:842] (3/4) Epoch 5, batch 2650, loss[loss=0.2287, simple_loss=0.2956, pruned_loss=0.0809, over 6995.00 frames.], tot_loss[loss=0.2477, simple_loss=0.3178, pruned_loss=0.08883, over 1429332.75 frames.], batch size: 16, lr: 9.71e-04
2022-05-26 21:45:07,114 INFO [train.py:842] (3/4) Epoch 5, batch 2700, loss[loss=0.2398, simple_loss=0.3043, pruned_loss=0.08766, over 7282.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3164, pruned_loss=0.08762, over 1431924.00 frames.], batch size: 18, lr: 9.70e-04
2022-05-26 21:45:46,222 INFO [train.py:842] (3/4) Epoch 5, batch 2750, loss[loss=0.2401, simple_loss=0.3071, pruned_loss=0.08653, over 7364.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3164, pruned_loss=0.08766, over 1432403.27 frames.], batch size: 19, lr: 9.70e-04
2022-05-26 21:46:24,827 INFO [train.py:842] (3/4) Epoch 5, batch 2800, loss[loss=0.2105, simple_loss=0.2778, pruned_loss=0.07159, over 7146.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3162, pruned_loss=0.08802, over 1432734.95 frames.], batch size: 17, lr: 9.69e-04
2022-05-26 21:47:03,564 INFO [train.py:842] (3/4) Epoch 5, batch 2850, loss[loss=0.2757, simple_loss=0.3433, pruned_loss=0.1041, over 6699.00 frames.], tot_loss[loss=0.247, simple_loss=0.3171, pruned_loss=0.08847, over 1430055.56 frames.], batch size: 31, lr: 9.68e-04
2022-05-26 21:47:41,792 INFO [train.py:842] (3/4) Epoch 5, batch 2900, loss[loss=0.2622, simple_loss=0.3284, pruned_loss=0.09801, over 7266.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3169, pruned_loss=0.08747, over 1428019.66 frames.], batch size: 24, lr: 9.68e-04
2022-05-26 21:48:20,716 INFO [train.py:842] (3/4) Epoch 5, batch 2950, loss[loss=0.2717, simple_loss=0.3466, pruned_loss=0.09841, over 7337.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3161, pruned_loss=0.08736, over 1428670.17 frames.], batch size: 22, lr: 9.67e-04
2022-05-26 21:48:59,377 INFO [train.py:842] (3/4) Epoch 5, batch 3000, loss[loss=0.2238, simple_loss=0.3085, pruned_loss=0.06955, over 7166.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3156, pruned_loss=0.0871, over 1424589.49 frames.], batch size: 26, lr: 9.66e-04
2022-05-26 21:48:59,378 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 21:49:08,664 INFO [train.py:871] (3/4) Epoch 5, validation: loss=0.1927, simple_loss=0.2922, pruned_loss=0.04663, over 868885.00 frames.
2022-05-26 21:49:47,979 INFO [train.py:842] (3/4) Epoch 5, batch 3050, loss[loss=0.2506, simple_loss=0.3169, pruned_loss=0.09216, over 7213.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3169, pruned_loss=0.08767, over 1428973.16 frames.], batch size: 22, lr: 9.66e-04
2022-05-26 21:50:26,481 INFO [train.py:842] (3/4) Epoch 5, batch 3100, loss[loss=0.232, simple_loss=0.3134, pruned_loss=0.07529, over 7243.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3184, pruned_loss=0.08892, over 1427961.67 frames.], batch size: 20, lr: 9.65e-04
2022-05-26 21:51:05,268 INFO [train.py:842] (3/4) Epoch 5, batch 3150, loss[loss=0.2337, simple_loss=0.3068, pruned_loss=0.0803, over 7290.00 frames.], tot_loss[loss=0.248, simple_loss=0.3182, pruned_loss=0.08892, over 1429083.67 frames.], batch size: 25, lr: 9.65e-04
2022-05-26 21:51:43,972 INFO [train.py:842] (3/4) Epoch 5, batch 3200, loss[loss=0.2196, simple_loss=0.2984, pruned_loss=0.07041, over 7356.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3184, pruned_loss=0.08898, over 1429894.23 frames.], batch size: 19, lr: 9.64e-04
2022-05-26 21:52:25,513 INFO [train.py:842] (3/4) Epoch 5, batch 3250, loss[loss=0.1857, simple_loss=0.27, pruned_loss=0.05073, over 7168.00 frames.], tot_loss[loss=0.2486, simple_loss=0.318, pruned_loss=0.08956, over 1428390.33 frames.], batch size: 18, lr: 9.64e-04
2022-05-26 21:53:04,059 INFO [train.py:842] (3/4) Epoch 5, batch 3300, loss[loss=0.246, simple_loss=0.3141, pruned_loss=0.08899, over 7157.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3188, pruned_loss=0.09014, over 1422989.62 frames.], batch size: 26, lr: 9.63e-04
2022-05-26 21:53:43,104 INFO [train.py:842] (3/4) Epoch 5, batch 3350, loss[loss=0.2466, simple_loss=0.3369, pruned_loss=0.07809, over 7110.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3205, pruned_loss=0.09128, over 1425618.69 frames.], batch size: 21, lr: 9.62e-04
2022-05-26 21:54:21,706 INFO [train.py:842] (3/4) Epoch 5, batch 3400, loss[loss=0.2579, simple_loss=0.3237, pruned_loss=0.09605, over 7229.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3204, pruned_loss=0.09122, over 1427242.15 frames.], batch size: 20, lr: 9.62e-04
2022-05-26 21:55:00,660 INFO [train.py:842] (3/4) Epoch 5, batch 3450, loss[loss=0.2622, simple_loss=0.3368, pruned_loss=0.09387, over 7215.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3198, pruned_loss=0.09082, over 1427419.90 frames.], batch size: 23, lr: 9.61e-04
2022-05-26 21:55:39,267 INFO [train.py:842] (3/4) Epoch 5, batch 3500, loss[loss=0.2648, simple_loss=0.3346, pruned_loss=0.09751, over 7307.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3206, pruned_loss=0.09119, over 1429241.01 frames.], batch size: 21, lr: 9.61e-04
2022-05-26 21:56:18,081 INFO [train.py:842] (3/4) Epoch 5, batch 3550, loss[loss=0.2335, simple_loss=0.3031, pruned_loss=0.08197, over 7336.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3206, pruned_loss=0.09109, over 1426069.39 frames.], batch size: 20, lr: 9.60e-04
2022-05-26 21:56:56,521 INFO [train.py:842] (3/4) Epoch 5, batch 3600, loss[loss=0.2526, simple_loss=0.3187, pruned_loss=0.09323, over 7316.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3209, pruned_loss=0.09141, over 1421644.23 frames.], batch size: 20, lr: 9.59e-04
2022-05-26 21:57:35,260 INFO [train.py:842] (3/4) Epoch 5, batch 3650, loss[loss=0.2331, simple_loss=0.3052, pruned_loss=0.08054, over 7068.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3215, pruned_loss=0.09179, over 1412634.09 frames.], batch size: 18, lr: 9.59e-04
2022-05-26 21:58:13,850 INFO [train.py:842] (3/4) Epoch 5, batch 3700, loss[loss=0.2518, simple_loss=0.3207, pruned_loss=0.09148, over 7222.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3193, pruned_loss=0.09073, over 1418170.50 frames.], batch size: 21, lr: 9.58e-04
2022-05-26 21:58:52,975 INFO [train.py:842] (3/4) Epoch 5, batch 3750, loss[loss=0.2602, simple_loss=0.3248, pruned_loss=0.09778, over 4727.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3179, pruned_loss=0.0893, over 1417903.68 frames.], batch size: 52, lr: 9.58e-04
2022-05-26 21:59:31,656 INFO [train.py:842] (3/4) Epoch 5, batch 3800, loss[loss=0.258, simple_loss=0.3121, pruned_loss=0.102, over 7218.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3192, pruned_loss=0.08985, over 1419299.59 frames.], batch size: 16, lr: 9.57e-04
2022-05-26 22:00:10,491 INFO [train.py:842] (3/4) Epoch 5, batch 3850, loss[loss=0.2126, simple_loss=0.288, pruned_loss=0.06861, over 7404.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3174, pruned_loss=0.08867, over 1420623.83 frames.], batch size: 18, lr: 9.56e-04
2022-05-26 22:00:49,040 INFO [train.py:842] (3/4) Epoch 5, batch 3900, loss[loss=0.2422, simple_loss=0.3177, pruned_loss=0.08336, over 7358.00 frames.], tot_loss[loss=0.2493, simple_loss=0.319, pruned_loss=0.08984, over 1417530.47 frames.], batch size: 19, lr: 9.56e-04
2022-05-26 22:01:28,135 INFO [train.py:842] (3/4) Epoch 5, batch 3950, loss[loss=0.2195, simple_loss=0.2928, pruned_loss=0.07306, over 7257.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3193, pruned_loss=0.08998, over 1414420.24 frames.], batch size: 19, lr: 9.55e-04
2022-05-26 22:02:06,782 INFO [train.py:842] (3/4) Epoch 5, batch 4000, loss[loss=0.2706, simple_loss=0.3355, pruned_loss=0.1028, over 7332.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3185, pruned_loss=0.08945, over 1418025.83 frames.], batch size: 22, lr: 9.55e-04
2022-05-26 22:02:46,093 INFO [train.py:842] (3/4) Epoch 5, batch 4050, loss[loss=0.2295, simple_loss=0.2957, pruned_loss=0.08165, over 7276.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3186, pruned_loss=0.08909, over 1420780.71 frames.], batch size: 18, lr: 9.54e-04
2022-05-26 22:03:24,842 INFO [train.py:842] (3/4) Epoch 5, batch 4100, loss[loss=0.245, simple_loss=0.3328, pruned_loss=0.07857, over 7157.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3182, pruned_loss=0.08846, over 1421199.39 frames.], batch size: 26, lr: 9.54e-04
2022-05-26 22:04:03,574 INFO [train.py:842] (3/4) Epoch 5, batch 4150, loss[loss=0.2362, simple_loss=0.3047, pruned_loss=0.08388, over 7159.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3179, pruned_loss=0.08848, over 1416888.15 frames.], batch size: 26, lr: 9.53e-04
2022-05-26 22:04:42,308 INFO [train.py:842] (3/4) Epoch 5, batch 4200, loss[loss=0.2196, simple_loss=0.2926, pruned_loss=0.07332, over 7280.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3168, pruned_loss=0.0879, over 1420903.22 frames.], batch size: 18, lr: 9.52e-04
2022-05-26 22:05:21,085 INFO [train.py:842] (3/4) Epoch 5, batch 4250, loss[loss=0.3259, simple_loss=0.3711, pruned_loss=0.1403, over 7208.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3176, pruned_loss=0.0891, over 1420892.55 frames.], batch size: 22, lr: 9.52e-04
2022-05-26 22:05:59,627 INFO [train.py:842] (3/4) Epoch 5, batch 4300, loss[loss=0.2881, simple_loss=0.343, pruned_loss=0.1166, over 7157.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3166, pruned_loss=0.08855, over 1422205.52 frames.], batch size: 18, lr: 9.51e-04
2022-05-26 22:06:38,361 INFO [train.py:842] (3/4) Epoch 5, batch 4350, loss[loss=0.2444, simple_loss=0.3248, pruned_loss=0.08203, over 7116.00 frames.], tot_loss[loss=0.245, simple_loss=0.3153, pruned_loss=0.08731, over 1423842.12 frames.], batch size: 26, lr: 9.51e-04
2022-05-26 22:07:17,020 INFO [train.py:842] (3/4) Epoch 5, batch 4400, loss[loss=0.2429, simple_loss=0.3233, pruned_loss=0.08126, over 7150.00 frames.], tot_loss[loss=0.2442, simple_loss=0.315, pruned_loss=0.08673, over 1425235.45 frames.], batch size: 20, lr: 9.50e-04
2022-05-26 22:07:55,967 INFO [train.py:842] (3/4) Epoch 5, batch 4450, loss[loss=0.2122, simple_loss=0.2888, pruned_loss=0.06784, over 7167.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3153, pruned_loss=0.08693, over 1426210.49 frames.], batch size: 26, lr: 9.50e-04
2022-05-26 22:08:34,435 INFO [train.py:842] (3/4) Epoch 5, batch 4500, loss[loss=0.262, simple_loss=0.3358, pruned_loss=0.09404, over 7376.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3162, pruned_loss=0.0863, over 1426088.33 frames.], batch size: 23, lr: 9.49e-04
2022-05-26 22:09:13,384 INFO [train.py:842] (3/4) Epoch 5, batch 4550, loss[loss=0.2461, simple_loss=0.3178, pruned_loss=0.08717, over 7051.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3161, pruned_loss=0.08674, over 1427397.45 frames.], batch size: 28, lr: 9.48e-04
2022-05-26 22:09:51,894 INFO [train.py:842] (3/4) Epoch 5, batch 4600, loss[loss=0.2367, simple_loss=0.3099, pruned_loss=0.08178, over 7205.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3151, pruned_loss=0.0863, over 1424398.62 frames.], batch size: 22, lr: 9.48e-04
2022-05-26 22:10:31,326 INFO [train.py:842] (3/4) Epoch 5, batch 4650, loss[loss=0.2314, simple_loss=0.3091, pruned_loss=0.07691, over 7321.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3165, pruned_loss=0.08752, over 1425597.79 frames.], batch size: 21, lr: 9.47e-04
2022-05-26 22:11:09,881 INFO [train.py:842] (3/4) Epoch 5, batch 4700, loss[loss=0.2395, simple_loss=0.3238, pruned_loss=0.07758, over 7322.00 frames.], tot_loss[loss=0.246, simple_loss=0.3167, pruned_loss=0.08768, over 1425692.73 frames.], batch size: 20, lr: 9.47e-04
2022-05-26 22:11:48,478 INFO [train.py:842] (3/4) Epoch 5, batch 4750, loss[loss=0.2341, simple_loss=0.3148, pruned_loss=0.07664, over 7321.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3166, pruned_loss=0.08731, over 1424703.04 frames.], batch size: 20, lr: 9.46e-04
2022-05-26 22:12:26,974 INFO [train.py:842] (3/4) Epoch 5, batch 4800, loss[loss=0.2361, simple_loss=0.3205, pruned_loss=0.07591, over 7337.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3177, pruned_loss=0.08796, over 1423242.51 frames.], batch size: 22, lr: 9.46e-04
2022-05-26 22:13:05,807 INFO [train.py:842] (3/4) Epoch 5, batch 4850, loss[loss=0.1867, simple_loss=0.2733, pruned_loss=0.05006, over 7408.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3166, pruned_loss=0.08719, over 1426001.81 frames.], batch size: 18, lr: 9.45e-04
2022-05-26 22:13:44,304 INFO [train.py:842] (3/4) Epoch 5, batch 4900, loss[loss=0.3041, simple_loss=0.3541, pruned_loss=0.127, over 7212.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3167, pruned_loss=0.08725, over 1426134.32 frames.], batch size: 23, lr: 9.45e-04
2022-05-26 22:14:23,583 INFO [train.py:842] (3/4) Epoch 5, batch 4950, loss[loss=0.2395, simple_loss=0.3209, pruned_loss=0.07904, over 7374.00 frames.], tot_loss[loss=0.2463, simple_loss=0.317, pruned_loss=0.08785, over 1427955.72 frames.], batch size: 23, lr: 9.44e-04
2022-05-26 22:15:02,145 INFO [train.py:842] (3/4) Epoch 5, batch 5000, loss[loss=0.2943, simple_loss=0.3636, pruned_loss=0.1125, over 7029.00 frames.], tot_loss[loss=0.2491, simple_loss=0.319, pruned_loss=0.08954, over 1426192.83 frames.], batch size: 28, lr: 9.43e-04
2022-05-26 22:15:41,347 INFO [train.py:842] (3/4) Epoch 5, batch 5050, loss[loss=0.2372, simple_loss=0.3106, pruned_loss=0.0819, over 7409.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3178, pruned_loss=0.08829, over 1426377.46 frames.], batch size: 21, lr: 9.43e-04
2022-05-26 22:16:20,162 INFO [train.py:842] (3/4) Epoch 5, batch 5100, loss[loss=0.2022, simple_loss=0.2921, pruned_loss=0.05611, over 7342.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3181, pruned_loss=0.08856, over 1422082.56 frames.], batch size: 22, lr: 9.42e-04
2022-05-26 22:16:59,095 INFO [train.py:842] (3/4) Epoch 5, batch 5150, loss[loss=0.2498, simple_loss=0.3211, pruned_loss=0.08926, over 7329.00 frames.], tot_loss[loss=0.245, simple_loss=0.3161, pruned_loss=0.08697, over 1424198.90 frames.], batch size: 20, lr: 9.42e-04
2022-05-26 22:17:37,813 INFO [train.py:842] (3/4) Epoch 5, batch 5200, loss[loss=0.2219, simple_loss=0.3056, pruned_loss=0.0691, over 7446.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3175, pruned_loss=0.08819, over 1424491.42 frames.], batch size: 20, lr: 9.41e-04
2022-05-26 22:18:16,856 INFO [train.py:842] (3/4) Epoch 5, batch 5250, loss[loss=0.2199, simple_loss=0.3122, pruned_loss=0.06381, over 7226.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3158, pruned_loss=0.08725, over 1425452.58 frames.], batch size: 21, lr: 9.41e-04
2022-05-26 22:18:55,413 INFO [train.py:842] (3/4) Epoch 5, batch 5300, loss[loss=0.2912, simple_loss=0.3436, pruned_loss=0.1194, over 6792.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3176, pruned_loss=0.08873, over 1419849.98 frames.], batch size: 15, lr: 9.40e-04
2022-05-26 22:19:34,412 INFO [train.py:842] (3/4) Epoch 5, batch 5350, loss[loss=0.2571, simple_loss=0.3256, pruned_loss=0.09435, over 7439.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3171, pruned_loss=0.08852, over 1423353.16 frames.], batch size: 20, lr: 9.40e-04
2022-05-26 22:20:12,913 INFO [train.py:842] (3/4) Epoch 5, batch 5400, loss[loss=0.2517, simple_loss=0.3017, pruned_loss=0.1009, over 7278.00 frames.], tot_loss[loss=0.247, simple_loss=0.3167, pruned_loss=0.08859, over 1421066.47 frames.], batch size: 18, lr: 9.39e-04
2022-05-26 22:20:51,937 INFO [train.py:842] (3/4) Epoch 5, batch 5450, loss[loss=0.2156, simple_loss=0.3081, pruned_loss=0.0616, over 7322.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3157, pruned_loss=0.08775, over 1425736.40 frames.], batch size: 22, lr: 9.38e-04
2022-05-26 22:21:30,526 INFO [train.py:842] (3/4) Epoch 5, batch 5500, loss[loss=0.2738, simple_loss=0.3405, pruned_loss=0.1036, over 7229.00 frames.], tot_loss[loss=0.247, simple_loss=0.317, pruned_loss=0.08848, over 1418332.45 frames.], batch size: 20, lr: 9.38e-04
2022-05-26 22:22:09,563 INFO [train.py:842] (3/4) Epoch 5, batch 5550, loss[loss=0.2287, simple_loss=0.3037, pruned_loss=0.0768, over 7344.00 frames.], tot_loss[loss=0.247, simple_loss=0.317, pruned_loss=0.08852, over 1420542.54 frames.], batch size: 25, lr: 9.37e-04
2022-05-26 22:22:48,041 INFO [train.py:842] (3/4) Epoch 5, batch 5600, loss[loss=0.2306, simple_loss=0.317, pruned_loss=0.07213, over 7206.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3181, pruned_loss=0.0892, over 1417964.49 frames.], batch size: 22, lr: 9.37e-04
2022-05-26 22:23:26,833 INFO [train.py:842] (3/4) Epoch 5, batch 5650, loss[loss=0.2567, simple_loss=0.3137, pruned_loss=0.09984, over 7397.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3174, pruned_loss=0.08833, over 1416622.42 frames.], batch size: 18, lr: 9.36e-04
2022-05-26 22:24:05,337 INFO [train.py:842] (3/4) Epoch 5, batch 5700, loss[loss=0.2453, simple_loss=0.3189, pruned_loss=0.08588, over 7174.00 frames.], tot_loss[loss=0.246, simple_loss=0.3164, pruned_loss=0.08777, over 1419279.54 frames.], batch size: 26, lr: 9.36e-04
2022-05-26 22:24:44,534 INFO [train.py:842] (3/4) Epoch 5, batch 5750, loss[loss=0.1958, simple_loss=0.2704, pruned_loss=0.06059, over 7153.00 frames.], tot_loss[loss=0.246, simple_loss=0.3167, pruned_loss=0.08767, over 1424428.32 frames.], batch size: 18, lr: 9.35e-04
2022-05-26 22:25:23,057 INFO [train.py:842] (3/4) Epoch 5, batch 5800, loss[loss=0.3673, simple_loss=0.3966, pruned_loss=0.169, over 4530.00 frames.], tot_loss[loss=0.244, simple_loss=0.3148, pruned_loss=0.08662, over 1422321.46 frames.], batch size: 52, lr: 9.35e-04
2022-05-26 22:26:01,727 INFO [train.py:842] (3/4) Epoch 5, batch 5850, loss[loss=0.2437, simple_loss=0.3191, pruned_loss=0.08416, over 7147.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3156, pruned_loss=0.08733, over 1418840.64 frames.], batch size: 20, lr: 9.34e-04
2022-05-26 22:26:40,316 INFO [train.py:842] (3/4) Epoch 5, batch 5900, loss[loss=0.2173, simple_loss=0.3007, pruned_loss=0.067, over 6688.00 frames.], tot_loss[loss=0.244, simple_loss=0.3148, pruned_loss=0.08658, over 1420843.71 frames.], batch size: 31, lr: 9.34e-04
2022-05-26 22:27:19,120 INFO [train.py:842] (3/4) Epoch 5, batch 5950, loss[loss=0.1775, simple_loss=0.2643, pruned_loss=0.04535, over 7156.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3151, pruned_loss=0.08698, over 1422504.64 frames.], batch size: 19, lr: 9.33e-04
2022-05-26 22:27:58,411 INFO [train.py:842] (3/4) Epoch 5, batch 6000, loss[loss=0.2383, simple_loss=0.3142, pruned_loss=0.08125, over 7229.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3146, pruned_loss=0.08638, over 1425224.24 frames.], batch size: 20, lr: 9.32e-04
2022-05-26 22:27:58,412 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 22:28:07,776 INFO [train.py:871] (3/4) Epoch 5, validation: loss=0.1919, simple_loss=0.2921, pruned_loss=0.04582, over 868885.00 frames.
2022-05-26 22:28:46,664 INFO [train.py:842] (3/4) Epoch 5, batch 6050, loss[loss=0.2456, simple_loss=0.3126, pruned_loss=0.08933, over 7180.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3154, pruned_loss=0.08677, over 1425171.88 frames.], batch size: 18, lr: 9.32e-04
2022-05-26 22:29:25,215 INFO [train.py:842] (3/4) Epoch 5, batch 6100, loss[loss=0.2975, simple_loss=0.3459, pruned_loss=0.1245, over 5158.00 frames.], tot_loss[loss=0.2461, simple_loss=0.317, pruned_loss=0.08764, over 1422085.16 frames.], batch size: 52, lr: 9.31e-04
2022-05-26 22:30:04,156 INFO [train.py:842] (3/4) Epoch 5, batch 6150, loss[loss=0.2383, simple_loss=0.3137, pruned_loss=0.08143, over 7169.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3159, pruned_loss=0.08659, over 1424514.98 frames.], batch size: 18, lr: 9.31e-04
2022-05-26 22:30:42,870 INFO [train.py:842] (3/4) Epoch 5, batch 6200, loss[loss=0.2275, simple_loss=0.2839, pruned_loss=0.08554, over 7408.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3162, pruned_loss=0.08659, over 1427543.25 frames.], batch size: 18, lr: 9.30e-04
2022-05-26 22:31:21,511 INFO [train.py:842] (3/4) Epoch 5, batch 6250, loss[loss=0.2069, simple_loss=0.2911, pruned_loss=0.06137, over 7109.00 frames.], tot_loss[loss=0.247, simple_loss=0.3179, pruned_loss=0.08802, over 1428127.57 frames.], batch size: 21, lr: 9.30e-04
2022-05-26 22:32:00,106 INFO [train.py:842] (3/4) Epoch 5, batch 6300, loss[loss=0.2385, simple_loss=0.3073, pruned_loss=0.0848, over 7371.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3171, pruned_loss=0.08738, over 1429183.35 frames.], batch size: 23, lr: 9.29e-04
2022-05-26 22:32:38,991 INFO [train.py:842] (3/4) Epoch 5, batch 6350, loss[loss=0.2216, simple_loss=0.3001, pruned_loss=0.07159, over 7158.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3182, pruned_loss=0.08761, over 1430356.68 frames.], batch size: 18, lr: 9.29e-04
2022-05-26 22:33:17,679 INFO [train.py:842] (3/4) Epoch 5, batch 6400, loss[loss=0.2313, simple_loss=0.3066, pruned_loss=0.07799, over 7328.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3161, pruned_loss=0.08679, over 1429452.43 frames.], batch size: 20, lr: 9.28e-04
2022-05-26 22:33:56,744 INFO [train.py:842] (3/4) Epoch 5, batch 6450, loss[loss=0.1817, simple_loss=0.2528, pruned_loss=0.0553, over 6811.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3167, pruned_loss=0.08724, over 1431053.72 frames.], batch size: 15, lr: 9.28e-04
2022-05-26 22:34:35,287 INFO [train.py:842] (3/4) Epoch 5, batch 6500, loss[loss=0.2351, simple_loss=0.3028, pruned_loss=0.08371, over 7157.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3162, pruned_loss=0.08634, over 1429521.63 frames.], batch size: 18, lr: 9.27e-04
2022-05-26 22:35:13,833 INFO [train.py:842] (3/4) Epoch 5, batch 6550, loss[loss=0.2233, simple_loss=0.3115, pruned_loss=0.06756, over 7323.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3151, pruned_loss=0.08552, over 1422554.63 frames.], batch size: 21, lr: 9.27e-04
2022-05-26 22:35:52,478 INFO [train.py:842] (3/4) Epoch 5, batch 6600, loss[loss=0.2397, simple_loss=0.3206, pruned_loss=0.07937, over 6266.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3164, pruned_loss=0.08608, over 1423295.62 frames.], batch size: 37, lr: 9.26e-04
2022-05-26 22:36:31,324 INFO [train.py:842] (3/4) Epoch 5, batch 6650, loss[loss=0.2131, simple_loss=0.2921, pruned_loss=0.06704, over 7136.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3156, pruned_loss=0.08566, over 1422183.16 frames.], batch size: 20, lr: 9.26e-04
2022-05-26 22:37:09,786 INFO [train.py:842] (3/4) Epoch 5, batch 6700, loss[loss=0.2141, simple_loss=0.299, pruned_loss=0.06461, over 6777.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3165, pruned_loss=0.08653, over 1422728.58 frames.], batch size: 31, lr: 9.25e-04
2022-05-26 22:37:49,198 INFO [train.py:842] (3/4) Epoch 5, batch 6750, loss[loss=0.2835, simple_loss=0.3507, pruned_loss=0.1082, over 7319.00 frames.], tot_loss[loss=0.244, simple_loss=0.3158, pruned_loss=0.08608, over 1426186.81 frames.], batch size: 21, lr: 9.25e-04
2022-05-26 22:38:27,833 INFO [train.py:842] (3/4) Epoch 5, batch 6800, loss[loss=0.237, simple_loss=0.3296, pruned_loss=0.07217, over 7288.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3154, pruned_loss=0.08555, over 1424727.36 frames.], batch size: 24, lr: 9.24e-04
2022-05-26 22:39:06,774 INFO [train.py:842] (3/4) Epoch 5, batch 6850, loss[loss=0.2591, simple_loss=0.325, pruned_loss=0.09658, over 7324.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3151, pruned_loss=0.08534, over 1426918.53 frames.], batch size: 20, lr: 9.23e-04
2022-05-26 22:39:45,104 INFO [train.py:842] (3/4) Epoch 5, batch 6900, loss[loss=0.2387, simple_loss=0.3143, pruned_loss=0.08156, over 7213.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3152, pruned_loss=0.08576, over 1427768.78 frames.], batch size: 23, lr: 9.23e-04
2022-05-26 22:40:24,003 INFO [train.py:842] (3/4) Epoch 5, batch 6950, loss[loss=0.2645, simple_loss=0.335, pruned_loss=0.09706, over 7114.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3169, pruned_loss=0.08645, over 1430134.64 frames.], batch size: 21, lr: 9.22e-04
2022-05-26 22:41:02,656 INFO [train.py:842] (3/4) Epoch 5, batch 7000, loss[loss=0.236, simple_loss=0.2937, pruned_loss=0.08917, over 7449.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3163, pruned_loss=0.08614, over 1434022.46 frames.], batch size: 19, lr: 9.22e-04
2022-05-26 22:41:41,593 INFO [train.py:842] (3/4) Epoch 5, batch 7050, loss[loss=0.2389, simple_loss=0.3105, pruned_loss=0.0836, over 7155.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3159, pruned_loss=0.08653, over 1427056.16 frames.], batch size: 20, lr: 9.21e-04
2022-05-26 22:42:20,194 INFO [train.py:842] (3/4) Epoch 5, batch 7100, loss[loss=0.2627, simple_loss=0.3276, pruned_loss=0.09894, over 7235.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3163, pruned_loss=0.08699, over 1430355.49 frames.], batch size: 20, lr: 9.21e-04
2022-05-26 22:42:59,046 INFO [train.py:842] (3/4) Epoch 5, batch 7150, loss[loss=0.2028, simple_loss=0.287, pruned_loss=0.05928, over 7289.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3167, pruned_loss=0.08691, over 1429819.00 frames.], batch size: 17, lr: 9.20e-04
2022-05-26 22:43:37,789 INFO [train.py:842] (3/4) Epoch 5, batch 7200, loss[loss=0.1848, simple_loss=0.2696, pruned_loss=0.05002, over 7235.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3175, pruned_loss=0.08759, over 1428719.57 frames.], batch size: 16, lr: 9.20e-04
2022-05-26 22:44:16,574 INFO [train.py:842] (3/4) Epoch 5, batch 7250, loss[loss=0.2243, simple_loss=0.2987, pruned_loss=0.07501, over 6991.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3168, pruned_loss=0.08757, over 1424956.80 frames.], batch size: 16, lr: 9.19e-04
2022-05-26 22:44:55,183 INFO [train.py:842] (3/4) Epoch 5, batch 7300, loss[loss=0.2464, simple_loss=0.3226, pruned_loss=0.08508, over 6748.00 frames.], tot_loss[loss=0.2476, simple_loss=0.318, pruned_loss=0.08853, over 1422503.53 frames.], batch size: 31, lr: 9.19e-04
2022-05-26 22:45:33,965 INFO [train.py:842] (3/4) Epoch 5, batch 7350, loss[loss=0.2295, simple_loss=0.3072, pruned_loss=0.07592, over 7133.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3171, pruned_loss=0.08756, over 1423256.03 frames.], batch size: 28, lr: 9.18e-04
2022-05-26 22:46:12,465 INFO [train.py:842] (3/4) Epoch 5, batch 7400, loss[loss=0.2388, simple_loss=0.3068, pruned_loss=0.08538, over 7259.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3158, pruned_loss=0.08715, over 1418242.52 frames.], batch size: 19, lr: 9.18e-04
2022-05-26 22:46:51,153 INFO [train.py:842] (3/4) Epoch 5, batch 7450, loss[loss=0.2139, simple_loss=0.2747, pruned_loss=0.07654, over 7428.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3165, pruned_loss=0.0875, over 1419548.79 frames.], batch size: 18, lr: 9.17e-04
2022-05-26 22:47:29,612 INFO [train.py:842] (3/4) Epoch 5, batch 7500, loss[loss=0.2224, simple_loss=0.2782, pruned_loss=0.08333, over 7291.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3164, pruned_loss=0.08709, over 1421996.67 frames.], batch size: 18, lr: 9.17e-04
2022-05-26 22:48:08,436 INFO [train.py:842] (3/4) Epoch 5, batch 7550, loss[loss=0.243, simple_loss=0.3244, pruned_loss=0.0808, over 7339.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3165, pruned_loss=0.08707, over 1421045.86 frames.], batch size: 22, lr: 9.16e-04
2022-05-26 22:48:46,896 INFO [train.py:842] (3/4) Epoch 5, batch 7600, loss[loss=0.2735, simple_loss=0.352, pruned_loss=0.09749, over 7209.00 frames.], tot_loss[loss=0.2459, simple_loss=0.317, pruned_loss=0.08739, over 1419963.45 frames.], batch size: 22, lr: 9.16e-04
2022-05-26 22:49:25,701 INFO [train.py:842] (3/4) Epoch 5, batch 7650, loss[loss=0.213, simple_loss=0.2982, pruned_loss=0.06395, over 7430.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3161, pruned_loss=0.08722, over 1419515.88 frames.], batch size: 20, lr: 9.15e-04
2022-05-26 22:50:04,139 INFO [train.py:842] (3/4) Epoch 5, batch 7700, loss[loss=0.2173, simple_loss=0.3041, pruned_loss=0.06528, over 7149.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3158, pruned_loss=0.0864, over 1420402.47 frames.], batch size: 20, lr: 9.15e-04
2022-05-26 22:50:43,140 INFO [train.py:842] (3/4) Epoch 5, batch 7750, loss[loss=0.2021, simple_loss=0.278, pruned_loss=0.06312, over 7411.00 frames.], tot_loss[loss=0.244, simple_loss=0.3152, pruned_loss=0.08637, over 1422765.02 frames.], batch size: 18, lr: 9.14e-04
2022-05-26 22:51:21,838 INFO [train.py:842] (3/4) Epoch 5, batch 7800, loss[loss=0.2286, simple_loss=0.3016, pruned_loss=0.07783, over 7325.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3143, pruned_loss=0.0857, over 1425126.74 frames.], batch size: 20, lr: 9.14e-04
2022-05-26 22:52:00,601 INFO [train.py:842] (3/4) Epoch 5, batch 7850, loss[loss=0.2309, simple_loss=0.3111, pruned_loss=0.07537, over 7257.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3153, pruned_loss=0.08562, over 1427209.94 frames.], batch size: 19, lr: 9.13e-04
2022-05-26 22:52:39,118 INFO [train.py:842] (3/4) Epoch 5, batch 7900, loss[loss=0.2128, simple_loss=0.2816, pruned_loss=0.07196, over 7295.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3164, pruned_loss=0.08657, over 1428512.53 frames.], batch size: 17, lr: 9.13e-04
2022-05-26 22:53:18,015 INFO [train.py:842] (3/4) Epoch 5, batch 7950, loss[loss=0.2716, simple_loss=0.3503, pruned_loss=0.09645, over 7037.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3163, pruned_loss=0.08734, over 1427391.89 frames.], batch size: 28, lr: 9.12e-04
2022-05-26 22:53:56,515 INFO [train.py:842] (3/4) Epoch 5, batch 8000, loss[loss=0.1978, simple_loss=0.273, pruned_loss=0.0613, over 7134.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3168, pruned_loss=0.08723, over 1428322.93 frames.], batch size: 17, lr: 9.12e-04
2022-05-26 22:54:35,446 INFO [train.py:842] (3/4) Epoch 5, batch 8050, loss[loss=0.2107, simple_loss=0.2887, pruned_loss=0.06636, over 7363.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3164, pruned_loss=0.08707, over 1428281.70 frames.], batch size: 19, lr: 9.11e-04
2022-05-26 22:55:14,041 INFO [train.py:842] (3/4) Epoch 5, batch 8100, loss[loss=0.2664, simple_loss=0.3367, pruned_loss=0.09803, over 7092.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3172, pruned_loss=0.08775, over 1427808.04 frames.], batch size: 28, lr: 9.11e-04
2022-05-26 22:55:52,785 INFO [train.py:842] (3/4) Epoch 5, batch 8150, loss[loss=0.2523, simple_loss=0.3292, pruned_loss=0.08764, over 7171.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3176, pruned_loss=0.08799, over 1421188.12 frames.], batch size: 26, lr: 9.10e-04
2022-05-26 22:56:31,195 INFO [train.py:842] (3/4) Epoch 5, batch 8200, loss[loss=0.2304, simple_loss=0.3036, pruned_loss=0.07857, over 7230.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3175, pruned_loss=0.08781, over 1418514.61 frames.], batch size: 20, lr: 9.10e-04
2022-05-26 22:57:10,085 INFO [train.py:842] (3/4) Epoch 5, batch 8250, loss[loss=0.2823, simple_loss=0.3292, pruned_loss=0.1177, over 7267.00 frames.], tot_loss[loss=0.246, simple_loss=0.3168, pruned_loss=0.08755, over 1420179.03 frames.], batch size: 18, lr: 9.09e-04
2022-05-26 22:57:48,646 INFO [train.py:842] (3/4) Epoch 5, batch 8300, loss[loss=0.2616, simple_loss=0.3335, pruned_loss=0.09479, over 7088.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3171, pruned_loss=0.08805, over 1424080.46 frames.], batch size: 28, lr: 9.09e-04
2022-05-26 22:58:27,296 INFO [train.py:842] (3/4) Epoch 5, batch 8350, loss[loss=0.2365, simple_loss=0.3042, pruned_loss=0.08438, over 7414.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3163, pruned_loss=0.08772, over 1420888.18 frames.], batch size: 21, lr: 9.08e-04
2022-05-26 22:59:05,772 INFO [train.py:842] (3/4) Epoch 5, batch 8400, loss[loss=0.229, simple_loss=0.301, pruned_loss=0.07852, over 7245.00 frames.], tot_loss[loss=0.2428, simple_loss=0.314, pruned_loss=0.08584, over 1421492.78 frames.], batch size: 20, lr: 9.08e-04
2022-05-26 22:59:44,476 INFO [train.py:842] (3/4) Epoch 5, batch 8450, loss[loss=0.2199, simple_loss=0.2793, pruned_loss=0.08027, over 7146.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3156, pruned_loss=0.08738, over 1415310.56 frames.], batch size: 17, lr: 9.07e-04
2022-05-26 23:00:23,199 INFO [train.py:842] (3/4) Epoch 5, batch 8500, loss[loss=0.2173, simple_loss=0.2866, pruned_loss=0.07397, over 7280.00 frames.], tot_loss[loss=0.246, simple_loss=0.3162, pruned_loss=0.0879, over 1418708.92 frames.], batch size: 17, lr: 9.07e-04
2022-05-26 23:01:02,290 INFO [train.py:842] (3/4) Epoch 5, batch 8550, loss[loss=0.1958, simple_loss=0.2765, pruned_loss=0.05755, over 7266.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3156, pruned_loss=0.08748, over 1422014.30 frames.], batch size: 19, lr: 9.06e-04
2022-05-26 23:01:41,074 INFO [train.py:842] (3/4) Epoch 5, batch 8600, loss[loss=0.2298, simple_loss=0.302, pruned_loss=0.07883, over 7356.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3161, pruned_loss=0.08756, over 1423975.04 frames.], batch size: 19, lr: 9.06e-04
2022-05-26 23:02:19,906 INFO [train.py:842] (3/4) Epoch 5, batch 8650, loss[loss=0.2402, simple_loss=0.3198, pruned_loss=0.08034, over 7220.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3164, pruned_loss=0.0874, over 1418973.86 frames.], batch size: 21, lr: 9.05e-04
2022-05-26 23:02:58,461 INFO [train.py:842] (3/4) Epoch 5, batch 8700, loss[loss=0.2474, simple_loss=0.307, pruned_loss=0.09394, over 7240.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3151, pruned_loss=0.08655, over 1416953.12 frames.], batch size: 20, lr: 9.05e-04
2022-05-26 23:03:37,441 INFO [train.py:842] (3/4) Epoch 5, batch 8750, loss[loss=0.2164, simple_loss=0.3016, pruned_loss=0.06556, over 7164.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3151, pruned_loss=0.08653, over 1418969.14 frames.], batch size: 26, lr: 9.04e-04
2022-05-26 23:04:16,104 INFO [train.py:842] (3/4) Epoch 5, batch 8800, loss[loss=0.2557, simple_loss=0.3257, pruned_loss=0.09286, over 7267.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3169, pruned_loss=0.08784, over 1418997.00 frames.], batch size: 24, lr: 9.04e-04
2022-05-26 23:04:55,040 INFO [train.py:842] (3/4) Epoch 5, batch 8850, loss[loss=0.2804, simple_loss=0.3519, pruned_loss=0.1044, over 4714.00 frames.], tot_loss[loss=0.2442, simple_loss=0.315, pruned_loss=0.0867, over 1413106.01 frames.], batch size: 52, lr: 9.03e-04
2022-05-26 23:05:33,497 INFO [train.py:842] (3/4) Epoch 5, batch 8900, loss[loss=0.2419, simple_loss=0.3166, pruned_loss=0.08357, over 6324.00 frames.], tot_loss[loss=0.244, simple_loss=0.315, pruned_loss=0.08646, over 1412833.69 frames.], batch size: 37, lr: 9.03e-04
2022-05-26 23:06:11,784 INFO [train.py:842] (3/4) Epoch 5, batch 8950, loss[loss=0.2566, simple_loss=0.342, pruned_loss=0.08562, over 7206.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3172, pruned_loss=0.08754, over 1404223.10 frames.], batch size: 23, lr: 9.02e-04
2022-05-26 23:06:49,951 INFO [train.py:842] (3/4) Epoch 5, batch 9000, loss[loss=0.3052, simple_loss=0.367, pruned_loss=0.1217, over 6224.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3198, pruned_loss=0.08853, over 1396380.40 frames.], batch size: 37, lr: 9.02e-04
2022-05-26 23:06:49,952 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 23:06:59,289 INFO [train.py:871] (3/4) Epoch 5, validation: loss=0.191, simple_loss=0.2904, pruned_loss=0.04585, over 868885.00 frames.
2022-05-26 23:07:37,151 INFO [train.py:842] (3/4) Epoch 5, batch 9050, loss[loss=0.2308, simple_loss=0.2954, pruned_loss=0.08308, over 5172.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3223, pruned_loss=0.09015, over 1365636.21 frames.], batch size: 52, lr: 9.01e-04
2022-05-26 23:08:14,677 INFO [train.py:842] (3/4) Epoch 5, batch 9100, loss[loss=0.2805, simple_loss=0.3425, pruned_loss=0.1093, over 5192.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3263, pruned_loss=0.09428, over 1301437.21 frames.], batch size: 53, lr: 9.01e-04
2022-05-26 23:08:52,443 INFO [train.py:842] (3/4) Epoch 5, batch 9150, loss[loss=0.2452, simple_loss=0.3203, pruned_loss=0.08506, over 5168.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3295, pruned_loss=0.09785, over 1237707.58 frames.], batch size: 53, lr: 9.00e-04
2022-05-26 23:09:43,999 INFO [train.py:842] (3/4) Epoch 6, batch 0, loss[loss=0.2282, simple_loss=0.3007, pruned_loss=0.07789, over 7159.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3007, pruned_loss=0.07789, over 7159.00 frames.], batch size: 19, lr: 8.65e-04
2022-05-26 23:10:23,199 INFO [train.py:842] (3/4) Epoch 6, batch 50, loss[loss=0.3731, simple_loss=0.4154, pruned_loss=0.1654, over 4822.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3137, pruned_loss=0.08638, over 319306.78 frames.], batch size: 52, lr: 8.64e-04
2022-05-26 23:11:01,555 INFO [train.py:842] (3/4) Epoch 6, batch 100, loss[loss=0.2286, simple_loss=0.3143, pruned_loss=0.07144, over 7151.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3157, pruned_loss=0.08669, over 563012.06 frames.], batch size: 20, lr: 8.64e-04
2022-05-26 23:11:40,534 INFO [train.py:842] (3/4) Epoch 6, batch 150, loss[loss=0.2431, simple_loss=0.3168, pruned_loss=0.08471, over 6727.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3148, pruned_loss=0.08538, over 751297.96 frames.], batch size: 31, lr: 8.63e-04
2022-05-26 23:12:19,092 INFO [train.py:842] (3/4) Epoch 6, batch 200, loss[loss=0.2892, simple_loss=0.3417, pruned_loss=0.1183, over 7424.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3167, pruned_loss=0.08695, over 900632.84 frames.], batch size: 18, lr: 8.63e-04
2022-05-26 23:12:57,969 INFO [train.py:842] (3/4) Epoch 6, batch 250, loss[loss=0.2243, simple_loss=0.3032, pruned_loss=0.07272, over 7342.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3159, pruned_loss=0.08614, over 1020002.37 frames.], batch size: 22, lr: 8.62e-04
2022-05-26 23:13:36,471 INFO [train.py:842] (3/4) Epoch 6, batch 300, loss[loss=0.2392, simple_loss=0.315, pruned_loss=0.08163, over 7233.00 frames.], tot_loss[loss=0.245, simple_loss=0.3163, pruned_loss=0.08687, over 1112082.13 frames.], batch size: 20, lr: 8.62e-04
2022-05-26 23:14:15,754 INFO [train.py:842] (3/4) Epoch 6, batch 350, loss[loss=0.2176, simple_loss=0.3038, pruned_loss=0.06565, over 7329.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3141, pruned_loss=0.08481, over 1185115.88 frames.], batch size: 20, lr: 8.61e-04
2022-05-26 23:14:54,192 INFO [train.py:842] (3/4) Epoch 6, batch 400, loss[loss=0.2687, simple_loss=0.342, pruned_loss=0.09769, over 7385.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3134, pruned_loss=0.08388, over 1236680.69 frames.], batch size: 23, lr: 8.61e-04
2022-05-26 23:15:33,160 INFO [train.py:842] (3/4) Epoch 6, batch 450, loss[loss=0.2335, simple_loss=0.2953, pruned_loss=0.08583, over 7223.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3144, pruned_loss=0.08424, over 1280258.86 frames.], batch size: 16, lr: 8.61e-04
2022-05-26 23:16:11,610 INFO [train.py:842] (3/4) Epoch 6, batch 500, loss[loss=0.2639, simple_loss=0.3344, pruned_loss=0.09672, over 4914.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3143, pruned_loss=0.08405, over 1308997.34 frames.], batch size: 52, lr: 8.60e-04
2022-05-26 23:16:50,477 INFO [train.py:842] (3/4) Epoch 6, batch 550, loss[loss=0.2332, simple_loss=0.3076, pruned_loss=0.07943, over 6463.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3135, pruned_loss=0.08317, over 1332529.93 frames.], batch size: 38, lr: 8.60e-04
2022-05-26 23:17:29,206 INFO [train.py:842] (3/4) Epoch 6, batch 600, loss[loss=0.2454, simple_loss=0.3162, pruned_loss=0.08732, over 7149.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3121, pruned_loss=0.08337, over 1351409.74 frames.], batch size: 20, lr: 8.59e-04
2022-05-26 23:18:08,022 INFO [train.py:842] (3/4) Epoch 6, batch 650, loss[loss=0.2414, simple_loss=0.328, pruned_loss=0.0774, over 7406.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3118, pruned_loss=0.0835, over 1366815.87 frames.], batch size: 21, lr: 8.59e-04
2022-05-26 23:18:46,480 INFO [train.py:842] (3/4) Epoch 6, batch 700, loss[loss=0.1898, simple_loss=0.2602, pruned_loss=0.05973, over 6816.00 frames.], tot_loss[loss=0.241, simple_loss=0.3131, pruned_loss=0.08445, over 1378663.25 frames.], batch size: 15, lr: 8.58e-04
2022-05-26 23:19:25,319 INFO [train.py:842] (3/4) Epoch 6, batch 750, loss[loss=0.2364, simple_loss=0.3168, pruned_loss=0.07802, over 7229.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3131, pruned_loss=0.08417, over 1388788.33 frames.], batch size: 21, lr: 8.58e-04
2022-05-26 23:20:03,929 INFO [train.py:842] (3/4) Epoch 6, batch 800, loss[loss=0.2263, simple_loss=0.3084, pruned_loss=0.07208, over 7220.00 frames.], tot_loss[loss=0.239, simple_loss=0.3117, pruned_loss=0.08316, over 1399332.24 frames.], batch size: 21, lr: 8.57e-04
2022-05-26 23:20:42,692 INFO [train.py:842] (3/4) Epoch 6, batch 850, loss[loss=0.2274, simple_loss=0.3006, pruned_loss=0.07706, over 7214.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3115, pruned_loss=0.08274, over 1404223.03 frames.], batch size: 23, lr: 8.57e-04
2022-05-26 23:21:21,256 INFO [train.py:842] (3/4) Epoch 6, batch 900, loss[loss=0.2439, simple_loss=0.3265, pruned_loss=0.08064, over 7413.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3115, pruned_loss=0.08275, over 1405369.44 frames.], batch size: 21, lr: 8.56e-04
2022-05-26 23:21:59,943 INFO [train.py:842] (3/4) Epoch 6, batch 950, loss[loss=0.2114, simple_loss=0.2842, pruned_loss=0.06932, over 7163.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3139, pruned_loss=0.08451, over 1405642.55 frames.], batch size: 17, lr: 8.56e-04
2022-05-26 23:22:38,503 INFO [train.py:842] (3/4) Epoch 6, batch 1000, loss[loss=0.2337, simple_loss=0.3139, pruned_loss=0.07678, over 7410.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3141, pruned_loss=0.08486, over 1408102.44 frames.], batch size: 21, lr: 8.56e-04
2022-05-26 23:23:17,225 INFO [train.py:842] (3/4) Epoch 6, batch 1050, loss[loss=0.2004, simple_loss=0.2854, pruned_loss=0.05769, over 7340.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3152, pruned_loss=0.08591, over 1412739.30 frames.], batch size: 20, lr: 8.55e-04
2022-05-26 23:23:55,794 INFO [train.py:842] (3/4) Epoch 6, batch 1100, loss[loss=0.236, simple_loss=0.3011, pruned_loss=0.08548, over 7318.00 frames.], tot_loss[loss=0.2444, simple_loss=0.316, pruned_loss=0.08636, over 1407557.44 frames.], batch size: 21, lr: 8.55e-04
2022-05-26 23:24:34,793 INFO [train.py:842] (3/4) Epoch 6, batch 1150, loss[loss=0.2838, simple_loss=0.3577, pruned_loss=0.1049, over 7147.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3183, pruned_loss=0.0875, over 1412259.15 frames.], batch size: 20, lr: 8.54e-04
2022-05-26 23:25:13,306 INFO [train.py:842] (3/4) Epoch 6, batch 1200, loss[loss=0.241, simple_loss=0.3174, pruned_loss=0.08235, over 7173.00 frames.], tot_loss[loss=0.246, simple_loss=0.3176, pruned_loss=0.08717, over 1413684.97 frames.], batch size: 26, lr: 8.54e-04
2022-05-26 23:25:52,100 INFO [train.py:842] (3/4) Epoch 6, batch 1250, loss[loss=0.2768, simple_loss=0.3374, pruned_loss=0.1081, over 7140.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3181, pruned_loss=0.08737, over 1412805.48 frames.], batch size: 20, lr: 8.53e-04
2022-05-26 23:26:30,702 INFO [train.py:842] (3/4) Epoch 6, batch 1300, loss[loss=0.2054, simple_loss=0.2839, pruned_loss=0.06346, over 7373.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3163, pruned_loss=0.08669, over 1410703.74 frames.], batch size: 19, lr: 8.53e-04
2022-05-26 23:27:09,699 INFO [train.py:842] (3/4) Epoch 6, batch 1350, loss[loss=0.22, simple_loss=0.2931, pruned_loss=0.07341, over 7076.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3132, pruned_loss=0.08473, over 1414639.96 frames.], batch size: 28, lr: 8.52e-04
2022-05-26 23:27:48,112 INFO [train.py:842] (3/4) Epoch 6, batch 1400, loss[loss=0.2004, simple_loss=0.2867, pruned_loss=0.05704, over 7331.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3135, pruned_loss=0.08448, over 1418916.44 frames.], batch size: 20, lr: 8.52e-04
2022-05-26 23:28:26,821 INFO [train.py:842] (3/4) Epoch 6, batch 1450, loss[loss=0.3071, simple_loss=0.3679, pruned_loss=0.1231, over 7425.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3136, pruned_loss=0.08473, over 1420995.48 frames.], batch size: 20, lr: 8.52e-04
2022-05-26 23:29:05,433 INFO [train.py:842] (3/4) Epoch 6, batch 1500, loss[loss=0.2299, simple_loss=0.3055, pruned_loss=0.07712, over 7148.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3137, pruned_loss=0.08453, over 1421148.96 frames.], batch size: 20, lr: 8.51e-04
2022-05-26 23:29:44,053 INFO [train.py:842] (3/4) Epoch 6, batch 1550, loss[loss=0.1811, simple_loss=0.2506, pruned_loss=0.05584, over 7299.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3131, pruned_loss=0.08369, over 1423155.64 frames.], batch size: 17, lr: 8.51e-04
2022-05-26 23:30:22,457 INFO [train.py:842] (3/4) Epoch 6, batch 1600, loss[loss=0.2701, simple_loss=0.3144, pruned_loss=0.1129, over 7434.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3135, pruned_loss=0.08441, over 1417114.44 frames.], batch size: 20, lr: 8.50e-04
2022-05-26 23:31:01,145 INFO [train.py:842] (3/4) Epoch 6, batch 1650, loss[loss=0.2686, simple_loss=0.3354, pruned_loss=0.1009, over 7335.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3138, pruned_loss=0.08471, over 1416407.42 frames.], batch size: 25, lr: 8.50e-04
2022-05-26 23:31:39,587 INFO [train.py:842] (3/4) Epoch 6, batch 1700, loss[loss=0.2268, simple_loss=0.3019, pruned_loss=0.07583, over 7205.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3134, pruned_loss=0.08446, over 1414533.19 frames.], batch size: 22, lr: 8.49e-04
2022-05-26 23:32:18,321 INFO [train.py:842] (3/4) Epoch 6, batch 1750, loss[loss=0.2616, simple_loss=0.3188, pruned_loss=0.1023, over 7284.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3144, pruned_loss=0.08499, over 1410763.35 frames.], batch size: 18, lr: 8.49e-04
2022-05-26 23:32:56,827 INFO [train.py:842] (3/4) Epoch 6, batch 1800, loss[loss=0.2635, simple_loss=0.3274, pruned_loss=0.09977, over 5091.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3134, pruned_loss=0.08421, over 1411940.76 frames.], batch size: 52, lr: 8.48e-04
2022-05-26 23:33:35,708 INFO [train.py:842] (3/4) Epoch 6, batch 1850, loss[loss=0.2234, simple_loss=0.2883, pruned_loss=0.07923, over 7155.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3121, pruned_loss=0.08362, over 1414964.72 frames.], batch size: 18, lr: 8.48e-04
2022-05-26 23:34:14,179 INFO [train.py:842] (3/4) Epoch 6, batch 1900, loss[loss=0.2019, simple_loss=0.2726, pruned_loss=0.06556, over 7138.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3116, pruned_loss=0.08333, over 1414273.38 frames.], batch size: 17, lr: 8.48e-04
2022-05-26 23:34:53,008 INFO [train.py:842] (3/4) Epoch 6, batch 1950, loss[loss=0.2586, simple_loss=0.3333, pruned_loss=0.09194, over 7119.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3115, pruned_loss=0.08221, over 1419643.54 frames.], batch size: 21, lr: 8.47e-04
2022-05-26 23:35:31,656 INFO [train.py:842] (3/4) Epoch 6, batch 2000, loss[loss=0.2786, simple_loss=0.3399, pruned_loss=0.1086, over 7271.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3111, pruned_loss=0.0824, over 1423400.17 frames.], batch size: 18, lr: 8.47e-04
2022-05-26 23:36:13,258 INFO [train.py:842] (3/4) Epoch 6, batch 2050, loss[loss=0.2407, simple_loss=0.3227, pruned_loss=0.07939, over 7030.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3136, pruned_loss=0.08366, over 1423945.95 frames.], batch size: 28, lr: 8.46e-04
2022-05-26 23:36:51,815 INFO [train.py:842] (3/4) Epoch 6, batch 2100, loss[loss=0.2212, simple_loss=0.2993, pruned_loss=0.07159, over 6387.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3124, pruned_loss=0.08295, over 1425750.20 frames.], batch size: 37, lr: 8.46e-04
2022-05-26 23:37:30,937 INFO [train.py:842] (3/4) Epoch 6, batch 2150, loss[loss=0.2049, simple_loss=0.2964, pruned_loss=0.05668, over 7144.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3119, pruned_loss=0.08285, over 1430550.60 frames.], batch size: 20, lr: 8.45e-04
2022-05-26 23:38:09,317 INFO [train.py:842] (3/4) Epoch 6, batch 2200, loss[loss=0.2074, simple_loss=0.2959, pruned_loss=0.05949, over 7150.00 frames.], tot_loss[loss=0.239, simple_loss=0.312, pruned_loss=0.08301, over 1426912.12 frames.], batch size: 20, lr: 8.45e-04
2022-05-26 23:38:48,203 INFO [train.py:842] (3/4) Epoch 6, batch 2250, loss[loss=0.2121, simple_loss=0.2874, pruned_loss=0.06833, over 7352.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3105, pruned_loss=0.08199, over 1425779.49 frames.], batch size: 19, lr: 8.45e-04
2022-05-26 23:39:26,699 INFO [train.py:842] (3/4) Epoch 6, batch 2300, loss[loss=0.2296, simple_loss=0.3101, pruned_loss=0.0746, over 7271.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3113, pruned_loss=0.08261, over 1422041.35 frames.], batch size: 24, lr: 8.44e-04
2022-05-26 23:40:05,798 INFO [train.py:842] (3/4) Epoch 6, batch 2350, loss[loss=0.2331, simple_loss=0.302, pruned_loss=0.08214, over 7220.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3108, pruned_loss=0.08266, over 1421932.32 frames.], batch size: 21, lr: 8.44e-04
2022-05-26 23:40:44,307 INFO [train.py:842] (3/4) Epoch 6, batch 2400, loss[loss=0.2416, simple_loss=0.3191, pruned_loss=0.08204, over 7334.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3107, pruned_loss=0.08272, over 1422224.12 frames.], batch size: 20, lr: 8.43e-04
2022-05-26 23:41:23,356 INFO [train.py:842] (3/4) Epoch 6, batch 2450, loss[loss=0.2199, simple_loss=0.2842, pruned_loss=0.07779, over 6778.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3102, pruned_loss=0.08231, over 1421696.69 frames.], batch size: 15, lr: 8.43e-04
2022-05-26 23:42:01,771 INFO [train.py:842] (3/4) Epoch 6, batch 2500, loss[loss=0.2428, simple_loss=0.3197, pruned_loss=0.083, over 7344.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3107, pruned_loss=0.08241, over 1420902.15 frames.], batch size: 22, lr: 8.42e-04
2022-05-26 23:42:40,587 INFO [train.py:842] (3/4) Epoch 6, batch 2550, loss[loss=0.1921, simple_loss=0.268, pruned_loss=0.05806, over 6796.00 frames.], tot_loss[loss=0.2385, simple_loss=0.311, pruned_loss=0.08298, over 1423104.92 frames.], batch size: 15, lr: 8.42e-04
2022-05-26 23:43:19,154 INFO [train.py:842] (3/4) Epoch 6, batch 2600, loss[loss=0.2436, simple_loss=0.3207, pruned_loss=0.08324, over 7318.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3112, pruned_loss=0.08311, over 1426207.84 frames.], batch size: 21, lr: 8.42e-04
2022-05-26 23:43:57,912 INFO [train.py:842] (3/4) Epoch 6, batch 2650, loss[loss=0.2324, simple_loss=0.3049, pruned_loss=0.07995, over 7284.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3122, pruned_loss=0.08355, over 1424903.94 frames.], batch size: 25, lr: 8.41e-04
2022-05-26 23:44:36,539 INFO [train.py:842] (3/4) Epoch 6, batch 2700, loss[loss=0.2254, simple_loss=0.3027, pruned_loss=0.074, over 6812.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3114, pruned_loss=0.08262, over 1426688.62 frames.], batch size: 15, lr: 8.41e-04
2022-05-26 23:45:15,210 INFO [train.py:842] (3/4) Epoch 6, batch 2750, loss[loss=0.2264, simple_loss=0.2976, pruned_loss=0.07754, over 7223.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3118, pruned_loss=0.08276, over 1424380.84 frames.], batch size: 20, lr: 8.40e-04
2022-05-26 23:45:53,719 INFO [train.py:842] (3/4) Epoch 6, batch 2800, loss[loss=0.2196, simple_loss=0.2918, pruned_loss=0.07371, over 7284.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3108, pruned_loss=0.08219, over 1422070.31 frames.], batch size: 18, lr: 8.40e-04
2022-05-26 23:46:32,470 INFO [train.py:842] (3/4) Epoch 6, batch 2850, loss[loss=0.2122, simple_loss=0.2816, pruned_loss=0.07138, over 7284.00 frames.], tot_loss[loss=0.238, simple_loss=0.3112, pruned_loss=0.08246, over 1419271.93 frames.], batch size: 17, lr: 8.39e-04
2022-05-26 23:47:10,994 INFO [train.py:842] (3/4) Epoch 6, batch 2900, loss[loss=0.2306, simple_loss=0.3074, pruned_loss=0.0769, over 6783.00 frames.], tot_loss[loss=0.2366, simple_loss=0.31, pruned_loss=0.08166, over 1421671.15 frames.], batch size: 31, lr: 8.39e-04
2022-05-26 23:47:50,199 INFO [train.py:842] (3/4) Epoch 6, batch 2950, loss[loss=0.2059, simple_loss=0.2895, pruned_loss=0.06115, over 7140.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3101, pruned_loss=0.08162, over 1421059.14 frames.], batch size: 20, lr: 8.39e-04
2022-05-26 23:48:28,912 INFO [train.py:842] (3/4) Epoch 6, batch 3000, loss[loss=0.2205, simple_loss=0.3019, pruned_loss=0.06952, over 7226.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3107, pruned_loss=0.08218, over 1420015.98 frames.], batch size: 20, lr: 8.38e-04
2022-05-26 23:48:28,913 INFO [train.py:862] (3/4) Computing validation loss
2022-05-26 23:48:38,153 INFO [train.py:871] (3/4) Epoch 6, validation: loss=0.1895, simple_loss=0.2892, pruned_loss=0.04494, over 868885.00 frames.
2022-05-26 23:49:17,578 INFO [train.py:842] (3/4) Epoch 6, batch 3050, loss[loss=0.2418, simple_loss=0.3119, pruned_loss=0.0858, over 7205.00 frames.], tot_loss[loss=0.2369, simple_loss=0.31, pruned_loss=0.08188, over 1425777.10 frames.], batch size: 23, lr: 8.38e-04
2022-05-26 23:49:56,222 INFO [train.py:842] (3/4) Epoch 6, batch 3100, loss[loss=0.2835, simple_loss=0.3459, pruned_loss=0.1106, over 7325.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3098, pruned_loss=0.08203, over 1423354.25 frames.], batch size: 22, lr: 8.37e-04
2022-05-26 23:50:35,007 INFO [train.py:842] (3/4) Epoch 6, batch 3150, loss[loss=0.2118, simple_loss=0.2928, pruned_loss=0.06539, over 7194.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3115, pruned_loss=0.08277, over 1422619.06 frames.], batch size: 23, lr: 8.37e-04
2022-05-26 23:51:13,536 INFO [train.py:842] (3/4) Epoch 6, batch 3200, loss[loss=0.1924, simple_loss=0.2806, pruned_loss=0.05216, over 7226.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3136, pruned_loss=0.08384, over 1423370.08 frames.], batch size: 21, lr: 8.36e-04
2022-05-26 23:51:52,217 INFO [train.py:842] (3/4) Epoch 6, batch 3250, loss[loss=0.214, simple_loss=0.283, pruned_loss=0.07243, over 7359.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3131, pruned_loss=0.08282, over 1423566.26 frames.], batch size: 19, lr: 8.36e-04
2022-05-26 23:52:30,651 INFO [train.py:842] (3/4) Epoch 6, batch 3300, loss[loss=0.2741, simple_loss=0.3422, pruned_loss=0.103, over 7201.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3133, pruned_loss=0.08327, over 1419386.82 frames.], batch size: 23, lr: 8.36e-04
2022-05-26 23:53:09,691 INFO [train.py:842] (3/4) Epoch 6, batch 3350, loss[loss=0.2289, simple_loss=0.3004, pruned_loss=0.07873, over 7254.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3126, pruned_loss=0.08302, over 1424301.73 frames.], batch size: 19, lr: 8.35e-04
2022-05-26 23:53:48,179 INFO [train.py:842] (3/4) Epoch 6, batch 3400, loss[loss=0.2909, simple_loss=0.3543, pruned_loss=0.1138, over 7271.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3105, pruned_loss=0.08192, over 1423942.56 frames.], batch size: 24, lr: 8.35e-04
2022-05-26 23:54:27,004 INFO [train.py:842] (3/4) Epoch 6, batch 3450, loss[loss=0.2241, simple_loss=0.3057, pruned_loss=0.0713, over 7414.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3122, pruned_loss=0.0828, over 1426164.59 frames.], batch size: 21, lr: 8.34e-04
2022-05-26 23:55:05,842 INFO [train.py:842] (3/4) Epoch 6, batch 3500, loss[loss=0.2556, simple_loss=0.3326, pruned_loss=0.08925, over 7204.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3099, pruned_loss=0.08195, over 1423219.06 frames.], batch size: 22, lr: 8.34e-04
2022-05-26 23:55:44,593 INFO [train.py:842] (3/4) Epoch 6, batch 3550, loss[loss=0.2115, simple_loss=0.3008, pruned_loss=0.06115, over 7318.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3105, pruned_loss=0.08224, over 1426034.72 frames.], batch size: 21, lr: 8.33e-04
2022-05-26 23:56:22,938 INFO [train.py:842] (3/4) Epoch 6, batch 3600, loss[loss=0.2104, simple_loss=0.2771, pruned_loss=0.07185, over 7151.00 frames.], tot_loss[loss=0.2351, simple_loss=0.309, pruned_loss=0.08067, over 1427760.02 frames.], batch size: 18, lr: 8.33e-04
2022-05-26 23:57:01,915 INFO [train.py:842] (3/4) Epoch 6, batch 3650, loss[loss=0.2184, simple_loss=0.2998, pruned_loss=0.06848, over 7418.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3096, pruned_loss=0.08095, over 1427481.26 frames.], batch size: 21, lr: 8.33e-04
2022-05-26 23:57:40,542 INFO [train.py:842] (3/4) Epoch 6, batch 3700, loss[loss=0.2259, simple_loss=0.3022, pruned_loss=0.0748, over 7226.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3084, pruned_loss=0.07999, over 1425883.10 frames.], batch size: 20, lr: 8.32e-04
2022-05-26 23:58:19,405 INFO [train.py:842] (3/4) Epoch 6, batch 3750, loss[loss=0.2846, simple_loss=0.3556, pruned_loss=0.1068, over 7373.00 frames.], tot_loss[loss=0.237, simple_loss=0.3104, pruned_loss=0.0818, over 1424003.37 frames.], batch size: 23, lr: 8.32e-04
2022-05-26 23:58:57,946 INFO [train.py:842] (3/4) Epoch 6, batch 3800, loss[loss=0.2, simple_loss=0.2881, pruned_loss=0.05597, over 7275.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3089, pruned_loss=0.08087, over 1420600.65 frames.], batch size: 24, lr: 8.31e-04
2022-05-26 23:59:36,783 INFO [train.py:842] (3/4) Epoch 6, batch 3850, loss[loss=0.3518, simple_loss=0.3945, pruned_loss=0.1546, over 7344.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3101, pruned_loss=0.08118, over 1420434.07 frames.], batch size: 22, lr: 8.31e-04
2022-05-27 00:00:15,373 INFO [train.py:842] (3/4) Epoch 6, batch 3900, loss[loss=0.1965, simple_loss=0.2733, pruned_loss=0.05985, over 7289.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3102, pruned_loss=0.08146, over 1424481.08 frames.], batch size: 18, lr: 8.31e-04
2022-05-27 00:00:54,260 INFO [train.py:842] (3/4) Epoch 6, batch 3950, loss[loss=0.3179, simple_loss=0.3768, pruned_loss=0.1295, over 6799.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3094, pruned_loss=0.08092, over 1424866.88 frames.], batch size: 31, lr: 8.30e-04
2022-05-27 00:01:33,008 INFO [train.py:842] (3/4) Epoch 6, batch 4000, loss[loss=0.2269, simple_loss=0.3036, pruned_loss=0.07513, over 7381.00 frames.], tot_loss[loss=0.236, simple_loss=0.3095, pruned_loss=0.08126, over 1426544.28 frames.], batch size: 23, lr: 8.30e-04
2022-05-27 00:02:11,866 INFO [train.py:842] (3/4) Epoch 6, batch 4050, loss[loss=0.2188, simple_loss=0.2914, pruned_loss=0.07305, over 7152.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3103, pruned_loss=0.08162, over 1429206.86 frames.], batch size: 19, lr: 8.29e-04
2022-05-27 00:02:50,512 INFO [train.py:842] (3/4) Epoch 6, batch 4100, loss[loss=0.3568, simple_loss=0.4001, pruned_loss=0.1568, over 7391.00 frames.], tot_loss[loss=0.238, simple_loss=0.3111, pruned_loss=0.08248, over 1426631.67 frames.], batch size: 23, lr: 8.29e-04
2022-05-27 00:03:29,578 INFO [train.py:842] (3/4) Epoch 6, batch 4150, loss[loss=0.2318, simple_loss=0.2942, pruned_loss=0.08476, over 7129.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3097, pruned_loss=0.08188, over 1424974.17 frames.], batch size: 17, lr: 8.29e-04
2022-05-27 00:04:18,773 INFO [train.py:842] (3/4) Epoch 6, batch 4200, loss[loss=0.2644, simple_loss=0.3247, pruned_loss=0.1021, over 7419.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3101, pruned_loss=0.0821, over 1427305.54 frames.], batch size: 18, lr: 8.28e-04
2022-05-27 00:04:57,595 INFO [train.py:842] (3/4) Epoch 6, batch 4250, loss[loss=0.2056, simple_loss=0.2803, pruned_loss=0.06549, over 7304.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3094, pruned_loss=0.08186, over 1427063.68 frames.], batch size: 24, lr: 8.28e-04
2022-05-27 00:05:36,210 INFO [train.py:842] (3/4) Epoch 6, batch 4300, loss[loss=0.2978, simple_loss=0.3497, pruned_loss=0.123, over 7344.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3084, pruned_loss=0.0815, over 1429420.17 frames.], batch size: 22, lr: 8.27e-04
2022-05-27 00:06:15,206 INFO [train.py:842] (3/4) Epoch 6, batch 4350, loss[loss=0.2218, simple_loss=0.3033, pruned_loss=0.07019, over 7071.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3091, pruned_loss=0.08182, over 1430705.23 frames.], batch size: 18, lr: 8.27e-04
2022-05-27 00:06:53,753 INFO [train.py:842] (3/4) Epoch 6, batch 4400, loss[loss=0.211, simple_loss=0.2982, pruned_loss=0.06194, over 7229.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3101, pruned_loss=0.08201, over 1428428.20 frames.], batch size: 20, lr: 8.26e-04
2022-05-27 00:07:32,808 INFO [train.py:842] (3/4) Epoch 6, batch 4450, loss[loss=0.2318, simple_loss=0.3099, pruned_loss=0.0768, over 7241.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3098, pruned_loss=0.08175, over 1429426.16 frames.], batch size: 20, lr: 8.26e-04
2022-05-27 00:08:11,526 INFO [train.py:842] (3/4) Epoch 6, batch 4500, loss[loss=0.268, simple_loss=0.3198, pruned_loss=0.1081, over 5354.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3098, pruned_loss=0.08218, over 1428565.06 frames.], batch size: 53, lr: 8.26e-04
2022-05-27 00:08:50,462 INFO [train.py:842] (3/4) Epoch 6, batch 4550, loss[loss=0.2102, simple_loss=0.2841, pruned_loss=0.06819, over 7055.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3111, pruned_loss=0.08299, over 1428705.85 frames.], batch size: 18, lr: 8.25e-04
2022-05-27 00:09:28,910 INFO [train.py:842] (3/4) Epoch 6, batch 4600, loss[loss=0.2858, simple_loss=0.3481, pruned_loss=0.1118, over 7115.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3097, pruned_loss=0.08205, over 1428774.23 frames.], batch size: 28, lr: 8.25e-04
2022-05-27 00:10:07,618 INFO [train.py:842] (3/4) Epoch 6, batch 4650, loss[loss=0.3514, simple_loss=0.3963, pruned_loss=0.1533, over 7117.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3109, pruned_loss=0.0835, over 1418006.26 frames.], batch size: 21, lr: 8.24e-04
2022-05-27 00:10:46,049 INFO [train.py:842] (3/4) Epoch 6, batch 4700, loss[loss=0.2882, simple_loss=0.338, pruned_loss=0.1192, over 7006.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3122, pruned_loss=0.08412, over 1424445.01 frames.], batch size: 16, lr: 8.24e-04
2022-05-27 00:11:25,089 INFO [train.py:842] (3/4) Epoch 6, batch 4750, loss[loss=0.1821, simple_loss=0.2599, pruned_loss=0.0521, over 7415.00 frames.], tot_loss[loss=0.24, simple_loss=0.3125, pruned_loss=0.08377, over 1426763.81 frames.], batch size: 18, lr: 8.24e-04
2022-05-27 00:12:03,905 INFO [train.py:842] (3/4) Epoch 6, batch 4800, loss[loss=0.1961, simple_loss=0.2796, pruned_loss=0.05633, over 7274.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3116, pruned_loss=0.08329, over 1425551.92 frames.], batch size: 19, lr: 8.23e-04
2022-05-27 00:12:42,818 INFO [train.py:842] (3/4) Epoch 6, batch 4850, loss[loss=0.2532, simple_loss=0.3288, pruned_loss=0.0888, over 7412.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3103, pruned_loss=0.08239, over 1427409.16 frames.], batch size: 21, lr: 8.23e-04
2022-05-27 00:13:21,329 INFO [train.py:842] (3/4) Epoch 6, batch 4900, loss[loss=0.215, simple_loss=0.3044, pruned_loss=0.06277, over 7345.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3114, pruned_loss=0.08295, over 1430898.83 frames.], batch size: 22, lr: 8.22e-04
2022-05-27 00:14:00,189 INFO [train.py:842] (3/4) Epoch 6, batch 4950, loss[loss=0.2116, simple_loss=0.296, pruned_loss=0.06357, over 7073.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3101, pruned_loss=0.0818, over 1427743.80 frames.], batch size: 28, lr: 8.22e-04
2022-05-27 00:14:38,744 INFO [train.py:842] (3/4) Epoch 6, batch 5000, loss[loss=0.2552, simple_loss=0.3234, pruned_loss=0.09357, over 6778.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3096, pruned_loss=0.08162, over 1427034.47 frames.], batch size: 31, lr: 8.22e-04
2022-05-27 00:15:17,433 INFO [train.py:842] (3/4) Epoch 6, batch 5050, loss[loss=0.2246, simple_loss=0.2909, pruned_loss=0.07911, over 7146.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3093, pruned_loss=0.08102, over 1424017.03 frames.], batch size: 17, lr: 8.21e-04
2022-05-27 00:15:55,968 INFO [train.py:842] (3/4) Epoch 6, batch 5100, loss[loss=0.213, simple_loss=0.2836, pruned_loss=0.07121, over 7072.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3099, pruned_loss=0.0818, over 1425074.25 frames.], batch size: 18, lr: 8.21e-04
2022-05-27 00:16:34,572 INFO [train.py:842] (3/4) Epoch 6, batch 5150, loss[loss=0.2373, simple_loss=0.2958, pruned_loss=0.08945, over 7292.00 frames.], tot_loss[loss=0.2371, simple_loss=0.31, pruned_loss=0.0821, over 1423281.60 frames.], batch size: 17, lr: 8.20e-04
2022-05-27 00:17:13,251 INFO [train.py:842] (3/4) Epoch 6, batch 5200, loss[loss=0.221, simple_loss=0.3034, pruned_loss=0.06933, over 7387.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3091, pruned_loss=0.08131, over 1427931.30 frames.], batch size: 23, lr: 8.20e-04
2022-05-27 00:18:02,461 INFO [train.py:842] (3/4) Epoch 6, batch 5250, loss[loss=0.2554, simple_loss=0.3437, pruned_loss=0.08356, over 7309.00 frames.], tot_loss[loss=0.2345, simple_loss=0.308, pruned_loss=0.08057, over 1427614.67 frames.], batch size: 25, lr: 8.20e-04
2022-05-27 00:19:01,428 INFO [train.py:842] (3/4) Epoch 6, batch 5300, loss[loss=0.2188, simple_loss=0.2937, pruned_loss=0.07197, over 7108.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3106, pruned_loss=0.08245, over 1418235.12 frames.], batch size: 21, lr: 8.19e-04
2022-05-27 00:19:40,585 INFO [train.py:842] (3/4) Epoch 6, batch 5350, loss[loss=0.1668, simple_loss=0.2464, pruned_loss=0.04364, over 7415.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3101, pruned_loss=0.08168, over 1423502.89 frames.], batch size: 21, lr: 8.19e-04
2022-05-27 00:20:19,197 INFO [train.py:842] (3/4) Epoch 6, batch 5400, loss[loss=0.2476, simple_loss=0.3059, pruned_loss=0.09471, over 7295.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3098, pruned_loss=0.08193, over 1421031.46 frames.], batch size: 18, lr: 8.18e-04
2022-05-27 00:20:58,439 INFO [train.py:842] (3/4) Epoch 6, batch 5450, loss[loss=0.2224, simple_loss=0.3046, pruned_loss=0.07011, over 7335.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3099, pruned_loss=0.08163, over 1425239.80 frames.], batch size: 22, lr: 8.18e-04
2022-05-27 00:21:37,392 INFO [train.py:842] (3/4) Epoch 6, batch 5500, loss[loss=0.217, simple_loss=0.2907, pruned_loss=0.07159, over 7167.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3107, pruned_loss=0.08242, over 1421158.52 frames.], batch size: 18, lr: 8.18e-04
2022-05-27 00:22:16,132 INFO [train.py:842] (3/4) Epoch 6, batch 5550, loss[loss=0.2056, simple_loss=0.3007, pruned_loss=0.05522, over 7206.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3108, pruned_loss=0.08245, over 1418056.12 frames.], batch size: 22, lr: 8.17e-04
2022-05-27 00:22:54,578 INFO [train.py:842] (3/4) Epoch 6, batch 5600, loss[loss=0.2862, simple_loss=0.3539, pruned_loss=0.1092, over 7078.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3107, pruned_loss=0.08241, over 1420456.45 frames.], batch size: 28, lr: 8.17e-04
2022-05-27 00:23:33,374 INFO [train.py:842] (3/4) Epoch 6, batch 5650, loss[loss=0.2847, simple_loss=0.3614, pruned_loss=0.104, over 7208.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3095, pruned_loss=0.08158, over 1417551.71 frames.], batch size: 22, lr: 8.17e-04
2022-05-27 00:24:12,122 INFO [train.py:842] (3/4) Epoch 6, batch 5700, loss[loss=0.2522, simple_loss=0.3272, pruned_loss=0.0886, over 7101.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3088, pruned_loss=0.08147, over 1418584.20 frames.], batch size: 21, lr: 8.16e-04
2022-05-27 00:24:50,740 INFO [train.py:842] (3/4) Epoch 6, batch 5750, loss[loss=0.2129, simple_loss=0.29, pruned_loss=0.06784, over 7164.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3097, pruned_loss=0.0819, over 1419334.81 frames.], batch size: 19, lr: 8.16e-04
2022-05-27 00:25:29,334 INFO [train.py:842] (3/4) Epoch 6, batch 5800, loss[loss=0.2109, simple_loss=0.2977, pruned_loss=0.06208, over 7224.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3097, pruned_loss=0.08151, over 1419725.92 frames.], batch size: 21, lr: 8.15e-04
2022-05-27 00:26:08,348 INFO [train.py:842] (3/4) Epoch 6, batch 5850, loss[loss=0.1945, simple_loss=0.2686, pruned_loss=0.06017, over 7390.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3105, pruned_loss=0.08218, over 1424142.06 frames.], batch size: 18, lr: 8.15e-04
2022-05-27 00:26:46,778 INFO [train.py:842] (3/4) Epoch 6, batch 5900, loss[loss=0.3795, simple_loss=0.4196, pruned_loss=0.1698, over 7427.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3106, pruned_loss=0.08225, over 1424947.31 frames.], batch size: 21, lr: 8.15e-04
2022-05-27 00:27:25,999 INFO [train.py:842] (3/4) Epoch 6, batch 5950, loss[loss=0.1845, simple_loss=0.262, pruned_loss=0.05353, over 7356.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3098, pruned_loss=0.08175, over 1425389.05 frames.], batch size: 19, lr: 8.14e-04
2022-05-27 00:28:04,720 INFO [train.py:842] (3/4) Epoch 6, batch 6000, loss[loss=0.22, simple_loss=0.3051, pruned_loss=0.06742, over 7323.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3114, pruned_loss=0.08265, over 1424748.66 frames.], batch size: 22, lr: 8.14e-04
2022-05-27 00:28:04,721 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 00:28:13,973 INFO [train.py:871] (3/4) Epoch 6, validation: loss=0.1847, simple_loss=0.2853, pruned_loss=0.04201, over 868885.00 frames.
2022-05-27 00:28:52,856 INFO [train.py:842] (3/4) Epoch 6, batch 6050, loss[loss=0.1878, simple_loss=0.2699, pruned_loss=0.05281, over 7289.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3106, pruned_loss=0.08202, over 1428531.98 frames.], batch size: 18, lr: 8.13e-04
2022-05-27 00:29:31,601 INFO [train.py:842] (3/4) Epoch 6, batch 6100, loss[loss=0.2179, simple_loss=0.2828, pruned_loss=0.07653, over 6821.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3104, pruned_loss=0.08195, over 1424482.48 frames.], batch size: 15, lr: 8.13e-04
2022-05-27 00:30:10,447 INFO [train.py:842] (3/4) Epoch 6, batch 6150, loss[loss=0.3068, simple_loss=0.3528, pruned_loss=0.1304, over 7110.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3099, pruned_loss=0.08222, over 1415770.20 frames.], batch size: 21, lr: 8.13e-04
2022-05-27 00:30:48,859 INFO [train.py:842] (3/4) Epoch 6, batch 6200, loss[loss=0.2092, simple_loss=0.2917, pruned_loss=0.0633, over 6330.00 frames.], tot_loss[loss=0.237, simple_loss=0.3097, pruned_loss=0.08212, over 1411044.08 frames.], batch size: 37, lr: 8.12e-04
2022-05-27 00:31:27,495 INFO [train.py:842] (3/4) Epoch 6, batch 6250, loss[loss=0.3769, simple_loss=0.4094, pruned_loss=0.1722, over 6436.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3097, pruned_loss=0.0817, over 1414870.60 frames.], batch size: 37, lr: 8.12e-04
2022-05-27 00:32:06,071 INFO [train.py:842] (3/4) Epoch 6, batch 6300, loss[loss=0.2036, simple_loss=0.2829, pruned_loss=0.06216, over 7325.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3085, pruned_loss=0.08045, over 1418707.55 frames.], batch size: 20, lr: 8.11e-04
2022-05-27 00:32:44,919 INFO [train.py:842] (3/4) Epoch 6, batch 6350, loss[loss=0.187, simple_loss=0.2613, pruned_loss=0.05639, over 7419.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3083, pruned_loss=0.08065, over 1420630.09 frames.], batch size: 18, lr: 8.11e-04
2022-05-27 00:33:23,421 INFO [train.py:842] (3/4) Epoch 6, batch 6400, loss[loss=0.2126, simple_loss=0.2885, pruned_loss=0.06838, over 6989.00 frames.], tot_loss[loss=0.2343, simple_loss=0.308, pruned_loss=0.08031, over 1418551.29 frames.], batch size: 28, lr: 8.11e-04
2022-05-27 00:34:02,232 INFO [train.py:842] (3/4) Epoch 6, batch 6450, loss[loss=0.2318, simple_loss=0.3029, pruned_loss=0.08036, over 7298.00 frames.], tot_loss[loss=0.234, simple_loss=0.3079, pruned_loss=0.08004, over 1417975.04 frames.], batch size: 17, lr: 8.10e-04
2022-05-27 00:34:40,774 INFO [train.py:842] (3/4) Epoch 6, batch 6500, loss[loss=0.2124, simple_loss=0.2963, pruned_loss=0.06431, over 7307.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3075, pruned_loss=0.07973, over 1419718.24 frames.], batch size: 25, lr: 8.10e-04
2022-05-27 00:35:19,829 INFO [train.py:842] (3/4) Epoch 6, batch 6550, loss[loss=0.2582, simple_loss=0.3259, pruned_loss=0.09526, over 7114.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3082, pruned_loss=0.08054, over 1417556.01 frames.], batch size: 21, lr: 8.10e-04
2022-05-27 00:35:58,643 INFO [train.py:842] (3/4) Epoch 6, batch 6600, loss[loss=0.2219, simple_loss=0.3034, pruned_loss=0.07021, over 7306.00 frames.], tot_loss[loss=0.2346, simple_loss=0.308, pruned_loss=0.08057, over 1420240.93 frames.], batch size: 24, lr: 8.09e-04
2022-05-27 00:36:37,422 INFO [train.py:842] (3/4) Epoch 6, batch 6650, loss[loss=0.2448, simple_loss=0.321, pruned_loss=0.08436, over 7139.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3089, pruned_loss=0.08088, over 1420420.81 frames.], batch size: 20, lr: 8.09e-04
2022-05-27 00:37:16,131 INFO [train.py:842] (3/4) Epoch 6, batch 6700, loss[loss=0.2532, simple_loss=0.3235, pruned_loss=0.09139, over 7203.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3095, pruned_loss=0.08149, over 1419976.03 frames.], batch size: 23, lr: 8.08e-04
2022-05-27 00:37:54,966 INFO [train.py:842] (3/4) Epoch 6, batch 6750, loss[loss=0.2536, simple_loss=0.3288, pruned_loss=0.08919, over 7386.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3099, pruned_loss=0.08197, over 1417991.13 frames.], batch size: 23, lr: 8.08e-04
2022-05-27 00:38:33,408 INFO [train.py:842] (3/4) Epoch 6, batch 6800, loss[loss=0.2258, simple_loss=0.3033, pruned_loss=0.07413, over 7323.00 frames.], tot_loss[loss=0.237, simple_loss=0.31, pruned_loss=0.08201, over 1418969.57 frames.], batch size: 20, lr: 8.08e-04
2022-05-27 00:39:12,300 INFO [train.py:842] (3/4) Epoch 6, batch 6850, loss[loss=0.2207, simple_loss=0.2905, pruned_loss=0.07548, over 7069.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3088, pruned_loss=0.08084, over 1420521.14 frames.], batch size: 18, lr: 8.07e-04
2022-05-27 00:39:50,896 INFO [train.py:842] (3/4) Epoch 6, batch 6900, loss[loss=0.2053, simple_loss=0.2855, pruned_loss=0.0626, over 7148.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3096, pruned_loss=0.08181, over 1422441.63 frames.], batch size: 20, lr: 8.07e-04
2022-05-27 00:40:29,632 INFO [train.py:842] (3/4) Epoch 6, batch 6950, loss[loss=0.2483, simple_loss=0.319, pruned_loss=0.08876, over 7332.00 frames.], tot_loss[loss=0.239, simple_loss=0.3115, pruned_loss=0.08321, over 1427179.72 frames.], batch size: 20, lr: 8.07e-04
2022-05-27 00:41:08,371 INFO [train.py:842] (3/4) Epoch 6, batch 7000, loss[loss=0.2215, simple_loss=0.2965, pruned_loss=0.07328, over 7223.00 frames.], tot_loss[loss=0.2374, simple_loss=0.31, pruned_loss=0.08238, over 1429324.87 frames.], batch size: 20, lr: 8.06e-04
2022-05-27 00:41:47,469 INFO [train.py:842] (3/4) Epoch 6, batch 7050, loss[loss=0.2175, simple_loss=0.3027, pruned_loss=0.06611, over 7319.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3091, pruned_loss=0.08178, over 1425973.05 frames.], batch size: 22, lr: 8.06e-04
2022-05-27 00:42:26,218 INFO [train.py:842] (3/4) Epoch 6, batch 7100, loss[loss=0.2013, simple_loss=0.2708, pruned_loss=0.06591, over 7282.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3093, pruned_loss=0.08177, over 1423917.47 frames.], batch size: 17, lr: 8.05e-04
2022-05-27 00:43:05,063 INFO [train.py:842] (3/4) Epoch 6, batch 7150, loss[loss=0.232, simple_loss=0.3078, pruned_loss=0.07806, over 7411.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3082, pruned_loss=0.08081, over 1426224.52 frames.], batch size: 21, lr: 8.05e-04
2022-05-27 00:43:43,857 INFO [train.py:842] (3/4) Epoch 6, batch 7200, loss[loss=0.2943, simple_loss=0.3586, pruned_loss=0.115, over 7310.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3083, pruned_loss=0.08113, over 1428773.89 frames.], batch size: 24, lr: 8.05e-04
2022-05-27 00:44:22,635 INFO [train.py:842] (3/4) Epoch 6, batch 7250, loss[loss=0.2836, simple_loss=0.3397, pruned_loss=0.1138, over 7318.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3092, pruned_loss=0.0818, over 1425238.85 frames.], batch size: 20, lr: 8.04e-04
2022-05-27 00:45:01,201 INFO [train.py:842] (3/4) Epoch 6, batch 7300, loss[loss=0.2237, simple_loss=0.3045, pruned_loss=0.07151, over 7133.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3079, pruned_loss=0.08068, over 1424971.60 frames.], batch size: 20, lr: 8.04e-04
2022-05-27 00:45:40,192 INFO [train.py:842] (3/4) Epoch 6, batch 7350, loss[loss=0.2331, simple_loss=0.2966, pruned_loss=0.08478, over 7240.00 frames.], tot_loss[loss=0.233, simple_loss=0.3061, pruned_loss=0.07994, over 1425593.42 frames.], batch size: 16, lr: 8.04e-04
2022-05-27 00:46:18,809 INFO [train.py:842] (3/4) Epoch 6, batch 7400, loss[loss=0.2757, simple_loss=0.3342, pruned_loss=0.1086, over 7429.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3073, pruned_loss=0.08021, over 1431430.85 frames.], batch size: 20, lr: 8.03e-04
2022-05-27 00:46:57,750 INFO [train.py:842] (3/4) Epoch 6, batch 7450, loss[loss=0.2078, simple_loss=0.2757, pruned_loss=0.06992, over 7267.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3092, pruned_loss=0.08201, over 1425686.12 frames.], batch size: 17, lr: 8.03e-04
2022-05-27 00:47:36,443 INFO [train.py:842] (3/4) Epoch 6, batch 7500, loss[loss=0.198, simple_loss=0.2836, pruned_loss=0.05623, over 7209.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3082, pruned_loss=0.08098, over 1421700.59 frames.], batch size: 22, lr: 8.02e-04
2022-05-27 00:48:15,425 INFO [train.py:842] (3/4) Epoch 6, batch 7550, loss[loss=0.2129, simple_loss=0.2908, pruned_loss=0.06753, over 7333.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3098, pruned_loss=0.08222, over 1421896.87 frames.], batch size: 20, lr: 8.02e-04
2022-05-27 00:48:53,869 INFO [train.py:842] (3/4) Epoch 6, batch 7600, loss[loss=0.2505, simple_loss=0.3214, pruned_loss=0.08985, over 7409.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3111, pruned_loss=0.08239, over 1419925.66 frames.], batch size: 21, lr: 8.02e-04
2022-05-27 00:49:32,684 INFO [train.py:842] (3/4) Epoch 6, batch 7650, loss[loss=0.2579, simple_loss=0.3319, pruned_loss=0.09196, over 7299.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3099, pruned_loss=0.0817, over 1417007.96 frames.], batch size: 25, lr: 8.01e-04
2022-05-27 00:50:11,222 INFO [train.py:842] (3/4) Epoch 6, batch 7700, loss[loss=0.2047, simple_loss=0.2861, pruned_loss=0.0617, over 7067.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3089, pruned_loss=0.08143, over 1419073.43 frames.], batch size: 18, lr: 8.01e-04
2022-05-27 00:50:49,909 INFO [train.py:842] (3/4) Epoch 6, batch 7750, loss[loss=0.267, simple_loss=0.3292, pruned_loss=0.1025, over 7188.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3089, pruned_loss=0.08126, over 1413533.79 frames.], batch size: 26, lr: 8.01e-04
2022-05-27 00:51:28,328 INFO [train.py:842] (3/4) Epoch 6, batch 7800, loss[loss=0.2409, simple_loss=0.2969, pruned_loss=0.0925, over 7138.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3095, pruned_loss=0.08172, over 1413116.54 frames.], batch size: 17, lr: 8.00e-04
2022-05-27 00:52:07,419 INFO [train.py:842] (3/4) Epoch 6, batch 7850, loss[loss=0.2237, simple_loss=0.3014, pruned_loss=0.07303, over 7416.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3084, pruned_loss=0.08138, over 1411394.12 frames.], batch size: 21, lr: 8.00e-04
2022-05-27 00:52:46,286 INFO [train.py:842] (3/4) Epoch 6, batch 7900, loss[loss=0.1866, simple_loss=0.2556, pruned_loss=0.05885, over 6817.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3074, pruned_loss=0.08092, over 1413267.49 frames.], batch size: 15, lr: 7.99e-04
2022-05-27 00:53:25,064 INFO [train.py:842] (3/4) Epoch 6, batch 7950, loss[loss=0.3149, simple_loss=0.3887, pruned_loss=0.1205, over 7325.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3084, pruned_loss=0.0815, over 1419102.99 frames.], batch size: 25, lr: 7.99e-04
2022-05-27 00:54:03,690 INFO [train.py:842] (3/4) Epoch 6, batch 8000, loss[loss=0.2342, simple_loss=0.3085, pruned_loss=0.07998, over 7328.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3086, pruned_loss=0.08134, over 1420715.25 frames.], batch size: 21, lr: 7.99e-04
2022-05-27 00:54:42,722 INFO [train.py:842] (3/4) Epoch 6, batch 8050, loss[loss=0.3386, simple_loss=0.3889, pruned_loss=0.1442, over 4671.00 frames.], tot_loss[loss=0.2358, simple_loss=0.309, pruned_loss=0.08128, over 1417864.25 frames.], batch size: 52, lr: 7.98e-04
2022-05-27 00:55:21,171 INFO [train.py:842] (3/4) Epoch 6, batch 8100, loss[loss=0.2143, simple_loss=0.2953, pruned_loss=0.06663, over 7326.00 frames.], tot_loss[loss=0.238, simple_loss=0.3108, pruned_loss=0.08261, over 1421466.02 frames.], batch size: 20, lr: 7.98e-04
2022-05-27 00:55:59,920 INFO [train.py:842] (3/4) Epoch 6, batch 8150, loss[loss=0.3369, simple_loss=0.3795, pruned_loss=0.1472, over 7183.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3109, pruned_loss=0.08234, over 1418393.71 frames.], batch size: 26, lr: 7.98e-04
2022-05-27 00:56:38,274 INFO [train.py:842] (3/4) Epoch 6, batch 8200, loss[loss=0.274, simple_loss=0.3416, pruned_loss=0.1032, over 7336.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3104, pruned_loss=0.08176, over 1419775.21 frames.], batch size: 22, lr: 7.97e-04
2022-05-27 00:57:17,221 INFO [train.py:842] (3/4) Epoch 6, batch 8250, loss[loss=0.2718, simple_loss=0.334, pruned_loss=0.1048, over 6353.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3099, pruned_loss=0.08153, over 1420091.15 frames.], batch size: 38, lr: 7.97e-04
2022-05-27 00:57:55,663 INFO [train.py:842] (3/4) Epoch 6, batch 8300, loss[loss=0.2447, simple_loss=0.3226, pruned_loss=0.08343, over 7383.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3099, pruned_loss=0.08131, over 1424176.82 frames.], batch size: 23, lr: 7.97e-04
2022-05-27 00:58:34,563 INFO [train.py:842] (3/4) Epoch 6, batch 8350, loss[loss=0.2561, simple_loss=0.3204, pruned_loss=0.0959, over 7333.00 frames.], tot_loss[loss=0.2347, simple_loss=0.309, pruned_loss=0.08025, over 1425083.46 frames.], batch size: 22, lr: 7.96e-04
2022-05-27 00:59:13,022 INFO [train.py:842] (3/4) Epoch 6, batch 8400, loss[loss=0.2128, simple_loss=0.2829, pruned_loss=0.07138, over 7266.00 frames.], tot_loss[loss=0.2349, simple_loss=0.309, pruned_loss=0.08037, over 1422199.38 frames.], batch size: 17, lr: 7.96e-04
2022-05-27 00:59:52,130 INFO [train.py:842] (3/4) Epoch 6, batch 8450, loss[loss=0.2352, simple_loss=0.2971, pruned_loss=0.08663, over 7283.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3083, pruned_loss=0.08029, over 1424166.28 frames.], batch size: 17, lr: 7.95e-04
2022-05-27 01:00:31,037 INFO [train.py:842] (3/4) Epoch 6, batch 8500, loss[loss=0.2445, simple_loss=0.3236, pruned_loss=0.0827, over 7106.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3068, pruned_loss=0.07934, over 1424019.85 frames.], batch size: 21, lr: 7.95e-04
2022-05-27 01:01:10,181 INFO [train.py:842] (3/4) Epoch 6, batch 8550, loss[loss=0.2784, simple_loss=0.3377, pruned_loss=0.1096, over 7384.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3074, pruned_loss=0.07994, over 1428237.53 frames.], batch size: 23, lr: 7.95e-04
2022-05-27 01:01:48,828 INFO [train.py:842] (3/4) Epoch 6, batch 8600, loss[loss=0.2697, simple_loss=0.3478, pruned_loss=0.09579, over 7226.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3083, pruned_loss=0.08057, over 1428225.02 frames.], batch size: 21, lr: 7.94e-04
2022-05-27 01:02:27,497 INFO [train.py:842] (3/4) Epoch 6, batch 8650, loss[loss=0.2206, simple_loss=0.3015, pruned_loss=0.06985, over 7322.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3082, pruned_loss=0.08032, over 1425483.06 frames.], batch size: 20, lr: 7.94e-04
2022-05-27 01:03:06,090 INFO [train.py:842] (3/4) Epoch 6, batch 8700, loss[loss=0.2189, simple_loss=0.2894, pruned_loss=0.07423, over 7153.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3074, pruned_loss=0.07994, over 1419808.32 frames.], batch size: 17, lr: 7.94e-04
2022-05-27 01:03:44,909 INFO [train.py:842] (3/4) Epoch 6, batch 8750, loss[loss=0.1738, simple_loss=0.2496, pruned_loss=0.04899, over 7137.00 frames.], tot_loss[loss=0.234, simple_loss=0.3082, pruned_loss=0.07992, over 1417098.28 frames.], batch size: 17, lr: 7.93e-04
2022-05-27 01:04:23,734 INFO [train.py:842] (3/4) Epoch 6, batch 8800, loss[loss=0.194, simple_loss=0.2631, pruned_loss=0.06244, over 7132.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3084, pruned_loss=0.08006, over 1416289.55 frames.], batch size: 17, lr: 7.93e-04
2022-05-27 01:05:02,666 INFO [train.py:842] (3/4) Epoch 6, batch 8850, loss[loss=0.2437, simple_loss=0.3046, pruned_loss=0.09136, over 7273.00 frames.], tot_loss[loss=0.235, simple_loss=0.3086, pruned_loss=0.08067, over 1416882.08 frames.], batch size: 17, lr: 7.93e-04
2022-05-27 01:05:41,196 INFO [train.py:842] (3/4) Epoch 6, batch 8900, loss[loss=0.2396, simple_loss=0.3186, pruned_loss=0.08033, over 7164.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3074, pruned_loss=0.08021, over 1412522.93 frames.], batch size: 26, lr: 7.92e-04
2022-05-27 01:06:20,559 INFO [train.py:842] (3/4) Epoch 6, batch 8950, loss[loss=0.2313, simple_loss=0.3036, pruned_loss=0.07951, over 7365.00 frames.], tot_loss[loss=0.2332, simple_loss=0.306, pruned_loss=0.08023, over 1405848.52 frames.], batch size: 19, lr: 7.92e-04
2022-05-27 01:06:58,912 INFO [train.py:842] (3/4) Epoch 6, batch 9000, loss[loss=0.1478, simple_loss=0.2307, pruned_loss=0.03252, over 7268.00 frames.], tot_loss[loss=0.2346, simple_loss=0.307, pruned_loss=0.08106, over 1399906.08 frames.], batch size: 17, lr: 7.91e-04
2022-05-27 01:06:58,913 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 01:07:08,313 INFO [train.py:871] (3/4) Epoch 6, validation: loss=0.186, simple_loss=0.2866, pruned_loss=0.04271, over 868885.00 frames.
2022-05-27 01:07:46,573 INFO [train.py:842] (3/4) Epoch 6, batch 9050, loss[loss=0.1902, simple_loss=0.2692, pruned_loss=0.05557, over 7289.00 frames.], tot_loss[loss=0.237, simple_loss=0.3084, pruned_loss=0.08281, over 1366086.96 frames.], batch size: 17, lr: 7.91e-04
2022-05-27 01:08:24,107 INFO [train.py:842] (3/4) Epoch 6, batch 9100, loss[loss=0.2125, simple_loss=0.2982, pruned_loss=0.06337, over 7228.00 frames.], tot_loss[loss=0.241, simple_loss=0.3123, pruned_loss=0.08483, over 1339275.21 frames.], batch size: 21, lr: 7.91e-04
2022-05-27 01:09:01,946 INFO [train.py:842] (3/4) Epoch 6, batch 9150, loss[loss=0.3047, simple_loss=0.3531, pruned_loss=0.1281, over 4867.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3171, pruned_loss=0.08883, over 1289477.37 frames.], batch size: 52, lr: 7.90e-04
2022-05-27 01:09:54,889 INFO [train.py:842] (3/4) Epoch 7, batch 0, loss[loss=0.2241, simple_loss=0.2918, pruned_loss=0.0782, over 7411.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2918, pruned_loss=0.0782, over 7411.00 frames.], batch size: 18, lr: 7.58e-04
2022-05-27 01:10:33,941 INFO [train.py:842] (3/4) Epoch 7, batch 50, loss[loss=0.2007, simple_loss=0.2772, pruned_loss=0.06213, over 7422.00 frames.], tot_loss[loss=0.232, simple_loss=0.307, pruned_loss=0.07854, over 322174.37 frames.], batch size: 18, lr: 7.58e-04
2022-05-27 01:11:12,613 INFO [train.py:842] (3/4) Epoch 7, batch 100, loss[loss=0.2203, simple_loss=0.2919, pruned_loss=0.0744, over 7168.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3066, pruned_loss=0.07858, over 567257.72 frames.], batch size: 19, lr: 7.57e-04
2022-05-27 01:11:51,441 INFO [train.py:842] (3/4) Epoch 7, batch 150, loss[loss=0.2671, simple_loss=0.3295, pruned_loss=0.1024, over 7159.00 frames.], tot_loss[loss=0.2349, simple_loss=0.309, pruned_loss=0.08037, over 756397.13 frames.], batch size: 19, lr: 7.57e-04
2022-05-27 01:12:30,105 INFO [train.py:842] (3/4) Epoch 7, batch 200, loss[loss=0.2895, simple_loss=0.3573, pruned_loss=0.1108, over 7377.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3085, pruned_loss=0.08015, over 906711.57 frames.], batch size: 23, lr: 7.57e-04
2022-05-27 01:13:08,993 INFO [train.py:842] (3/4) Epoch 7, batch 250, loss[loss=0.2639, simple_loss=0.3421, pruned_loss=0.09288, over 7140.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3066, pruned_loss=0.07863, over 1021008.94 frames.], batch size: 20, lr: 7.56e-04
2022-05-27 01:13:47,468 INFO [train.py:842] (3/4) Epoch 7, batch 300, loss[loss=0.202, simple_loss=0.2626, pruned_loss=0.07074, over 6795.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3075, pruned_loss=0.07937, over 1107306.36 frames.], batch size: 15, lr: 7.56e-04
2022-05-27 01:14:26,509 INFO [train.py:842] (3/4) Epoch 7, batch 350, loss[loss=0.2256, simple_loss=0.3082, pruned_loss=0.07149, over 7112.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3078, pruned_loss=0.07952, over 1177815.85 frames.], batch size: 21, lr: 7.56e-04
2022-05-27 01:15:04,817 INFO [train.py:842] (3/4) Epoch 7, batch 400, loss[loss=0.2103, simple_loss=0.2759, pruned_loss=0.07237, over 7157.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3083, pruned_loss=0.0796, over 1230151.52 frames.], batch size: 18, lr: 7.55e-04
2022-05-27 01:15:43,931 INFO [train.py:842] (3/4) Epoch 7, batch 450, loss[loss=0.2095, simple_loss=0.2901, pruned_loss=0.06443, over 7359.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3088, pruned_loss=0.07993, over 1275532.66 frames.], batch size: 19, lr: 7.55e-04
2022-05-27 01:16:22,197 INFO [train.py:842] (3/4) Epoch 7, batch 500, loss[loss=0.2713, simple_loss=0.3395, pruned_loss=0.1015, over 6296.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3085, pruned_loss=0.07936, over 1304071.28 frames.], batch size: 37, lr: 7.55e-04
2022-05-27 01:17:01,073 INFO [train.py:842] (3/4) Epoch 7, batch 550, loss[loss=0.1854, simple_loss=0.2698, pruned_loss=0.05046, over 7117.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3081, pruned_loss=0.07944, over 1329699.81 frames.], batch size: 21, lr: 7.54e-04
2022-05-27 01:17:39,739 INFO [train.py:842] (3/4) Epoch 7, batch 600, loss[loss=0.2543, simple_loss=0.3282, pruned_loss=0.09017, over 7102.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3104, pruned_loss=0.08121, over 1347675.79 frames.], batch size: 28, lr: 7.54e-04
2022-05-27 01:18:18,871 INFO [train.py:842] (3/4) Epoch 7, batch 650, loss[loss=0.2779, simple_loss=0.3423, pruned_loss=0.1067, over 5047.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3092, pruned_loss=0.08082, over 1364082.93 frames.], batch size: 54, lr: 7.54e-04
2022-05-27 01:18:57,459 INFO [train.py:842] (3/4) Epoch 7, batch 700, loss[loss=0.1826, simple_loss=0.2598, pruned_loss=0.05271, over 7153.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3078, pruned_loss=0.07963, over 1378485.79 frames.], batch size: 18, lr: 7.53e-04
2022-05-27 01:19:36,362 INFO [train.py:842] (3/4) Epoch 7, batch 750, loss[loss=0.2201, simple_loss=0.2926, pruned_loss=0.0738, over 6900.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3076, pruned_loss=0.07968, over 1391345.62 frames.], batch size: 31, lr: 7.53e-04
2022-05-27 01:20:15,036 INFO [train.py:842] (3/4) Epoch 7, batch 800, loss[loss=0.1968, simple_loss=0.2884, pruned_loss=0.05255, over 7328.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3069, pruned_loss=0.07904, over 1391961.65 frames.], batch size: 20, lr: 7.53e-04
2022-05-27 01:20:56,590 INFO [train.py:842] (3/4) Epoch 7, batch 850, loss[loss=0.2569, simple_loss=0.3304, pruned_loss=0.09174, over 7305.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3063, pruned_loss=0.07851, over 1398831.53 frames.], batch size: 24, lr: 7.52e-04
2022-05-27 01:21:35,049 INFO [train.py:842] (3/4) Epoch 7, batch 900, loss[loss=0.2565, simple_loss=0.3364, pruned_loss=0.08831, over 7383.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3053, pruned_loss=0.07797, over 1403838.11 frames.], batch size: 23, lr: 7.52e-04
2022-05-27 01:22:13,826 INFO [train.py:842] (3/4) Epoch 7, batch 950, loss[loss=0.201, simple_loss=0.2809, pruned_loss=0.06054, over 7380.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3076, pruned_loss=0.07894, over 1408703.12 frames.], batch size: 23, lr: 7.52e-04
2022-05-27 01:22:52,362 INFO [train.py:842] (3/4) Epoch 7, batch 1000, loss[loss=0.2268, simple_loss=0.3111, pruned_loss=0.07122, over 7385.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3067, pruned_loss=0.07886, over 1409571.18 frames.], batch size: 23, lr: 7.51e-04
2022-05-27 01:23:31,627 INFO [train.py:842] (3/4) Epoch 7, batch 1050, loss[loss=0.2319, simple_loss=0.3126, pruned_loss=0.07567, over 7162.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3064, pruned_loss=0.0784, over 1416395.96 frames.], batch size: 19, lr: 7.51e-04
2022-05-27 01:24:10,646 INFO [train.py:842] (3/4) Epoch 7, batch 1100, loss[loss=0.2183, simple_loss=0.3013, pruned_loss=0.06763, over 7286.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3059, pruned_loss=0.07763, over 1419406.82 frames.], batch size: 25, lr: 7.51e-04
2022-05-27 01:24:49,515 INFO [train.py:842] (3/4) Epoch 7, batch 1150, loss[loss=0.1683, simple_loss=0.2536, pruned_loss=0.04151, over 7135.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3068, pruned_loss=0.07835, over 1417498.30 frames.], batch size: 17, lr: 7.50e-04
2022-05-27 01:25:28,093 INFO [train.py:842] (3/4) Epoch 7, batch 1200, loss[loss=0.184, simple_loss=0.2532, pruned_loss=0.05737, over 6813.00 frames.], tot_loss[loss=0.2312, simple_loss=0.306, pruned_loss=0.07818, over 1412222.34 frames.], batch size: 15, lr: 7.50e-04
2022-05-27 01:26:07,109 INFO [train.py:842] (3/4) Epoch 7, batch 1250, loss[loss=0.2062, simple_loss=0.2917, pruned_loss=0.0603, over 7228.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3053, pruned_loss=0.07792, over 1414417.93 frames.], batch size: 20, lr: 7.50e-04
2022-05-27 01:26:45,654 INFO [train.py:842] (3/4) Epoch 7, batch 1300, loss[loss=0.2354, simple_loss=0.2873, pruned_loss=0.09178, over 7271.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3053, pruned_loss=0.0777, over 1415136.18 frames.], batch size: 17, lr: 7.49e-04
2022-05-27 01:27:24,589 INFO [train.py:842] (3/4) Epoch 7, batch 1350, loss[loss=0.2293, simple_loss=0.3038, pruned_loss=0.07741, over 7413.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3056, pruned_loss=0.07765, over 1420725.39 frames.], batch size: 21, lr: 7.49e-04
2022-05-27 01:28:02,943 INFO [train.py:842] (3/4) Epoch 7, batch 1400, loss[loss=0.1932, simple_loss=0.2775, pruned_loss=0.05449, over 7167.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3066, pruned_loss=0.07852, over 1419705.95 frames.], batch size: 19, lr: 7.49e-04
2022-05-27 01:28:41,843 INFO [train.py:842] (3/4) Epoch 7, batch 1450, loss[loss=0.2165, simple_loss=0.2955, pruned_loss=0.06881, over 6800.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3072, pruned_loss=0.07866, over 1419899.86 frames.], batch size: 31, lr: 7.48e-04
2022-05-27 01:29:20,375 INFO [train.py:842] (3/4) Epoch 7, batch 1500, loss[loss=0.2258, simple_loss=0.3048, pruned_loss=0.07338, over 7419.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3065, pruned_loss=0.07811, over 1423650.68 frames.], batch size: 21, lr: 7.48e-04
2022-05-27 01:29:59,208 INFO [train.py:842] (3/4) Epoch 7, batch 1550, loss[loss=0.2294, simple_loss=0.3207, pruned_loss=0.06912, over 7167.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3062, pruned_loss=0.07816, over 1418600.50 frames.], batch size: 26, lr: 7.48e-04
2022-05-27 01:30:37,816 INFO [train.py:842] (3/4) Epoch 7, batch 1600, loss[loss=0.2661, simple_loss=0.3364, pruned_loss=0.09789, over 7099.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3069, pruned_loss=0.07826, over 1424898.93 frames.], batch size: 21, lr: 7.47e-04
2022-05-27 01:31:16,747 INFO [train.py:842] (3/4) Epoch 7, batch 1650, loss[loss=0.2733, simple_loss=0.3334, pruned_loss=0.1066, over 7063.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3074, pruned_loss=0.0791, over 1418999.52 frames.], batch size: 18, lr: 7.47e-04
2022-05-27 01:31:55,648 INFO [train.py:842] (3/4) Epoch 7, batch 1700, loss[loss=0.2521, simple_loss=0.3315, pruned_loss=0.0863, over 7203.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3069, pruned_loss=0.07902, over 1417305.16 frames.], batch size: 22, lr: 7.47e-04
2022-05-27 01:32:34,547 INFO [train.py:842] (3/4) Epoch 7, batch 1750, loss[loss=0.2019, simple_loss=0.2827, pruned_loss=0.06052, over 7339.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3068, pruned_loss=0.07907, over 1412344.43 frames.], batch size: 22, lr: 7.46e-04
2022-05-27 01:33:12,906 INFO [train.py:842] (3/4) Epoch 7, batch 1800, loss[loss=0.2302, simple_loss=0.3141, pruned_loss=0.07318, over 7336.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3082, pruned_loss=0.07874, over 1415248.24 frames.], batch size: 25, lr: 7.46e-04
2022-05-27 01:33:51,783 INFO [train.py:842] (3/4) Epoch 7, batch 1850, loss[loss=0.1806, simple_loss=0.2485, pruned_loss=0.05638, over 6994.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3068, pruned_loss=0.07819, over 1417140.02 frames.], batch size: 16, lr: 7.46e-04
2022-05-27 01:34:30,345 INFO [train.py:842] (3/4) Epoch 7, batch 1900, loss[loss=0.2388, simple_loss=0.3068, pruned_loss=0.08542, over 7071.00 frames.], tot_loss[loss=0.232, simple_loss=0.3068, pruned_loss=0.07865, over 1413932.90 frames.], batch size: 18, lr: 7.45e-04
2022-05-27 01:35:09,634 INFO [train.py:842] (3/4) Epoch 7, batch 1950, loss[loss=0.2292, simple_loss=0.2993, pruned_loss=0.07954, over 7275.00 frames.], tot_loss[loss=0.2327, simple_loss=0.307, pruned_loss=0.07923, over 1417817.93 frames.], batch size: 18, lr: 7.45e-04
2022-05-27 01:35:48,207 INFO [train.py:842] (3/4) Epoch 7, batch 2000, loss[loss=0.2489, simple_loss=0.3344, pruned_loss=0.0817, over 7285.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3066, pruned_loss=0.07908, over 1418886.37 frames.], batch size: 25, lr: 7.45e-04
2022-05-27 01:36:27,081 INFO [train.py:842] (3/4) Epoch 7, batch 2050, loss[loss=0.2178, simple_loss=0.2934, pruned_loss=0.07111, over 7287.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3069, pruned_loss=0.07923, over 1415986.72 frames.], batch size: 24, lr: 7.44e-04
2022-05-27 01:37:05,439 INFO [train.py:842] (3/4) Epoch 7, batch 2100, loss[loss=0.1767, simple_loss=0.2604, pruned_loss=0.04653, over 7001.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3055, pruned_loss=0.07837, over 1419464.22 frames.], batch size: 16, lr: 7.44e-04
2022-05-27 01:37:44,447 INFO [train.py:842] (3/4) Epoch 7, batch 2150, loss[loss=0.2468, simple_loss=0.32, pruned_loss=0.08675, over 7416.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3055, pruned_loss=0.07821, over 1424669.10 frames.], batch size: 21, lr: 7.44e-04
2022-05-27 01:38:22,884 INFO [train.py:842] (3/4) Epoch 7, batch 2200, loss[loss=0.1933, simple_loss=0.2648, pruned_loss=0.06088, over 7139.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3048, pruned_loss=0.07711, over 1422850.51 frames.], batch size: 17, lr: 7.43e-04
2022-05-27 01:39:01,898 INFO [train.py:842] (3/4) Epoch 7, batch 2250, loss[loss=0.2123, simple_loss=0.2894, pruned_loss=0.06763, over 7274.00 frames.], tot_loss[loss=0.2296, simple_loss=0.305, pruned_loss=0.07709, over 1417101.58 frames.], batch size: 17, lr: 7.43e-04
2022-05-27 01:39:40,363 INFO [train.py:842] (3/4) Epoch 7, batch 2300, loss[loss=0.2595, simple_loss=0.3369, pruned_loss=0.09106, over 7197.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3047, pruned_loss=0.07686, over 1420643.44 frames.], batch size: 23, lr: 7.43e-04
2022-05-27 01:40:19,218 INFO [train.py:842] (3/4) Epoch 7, batch 2350, loss[loss=0.25, simple_loss=0.3222, pruned_loss=0.08891, over 7416.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3042, pruned_loss=0.0764, over 1418836.43 frames.], batch size: 21, lr: 7.42e-04
2022-05-27 01:40:57,864 INFO [train.py:842] (3/4) Epoch 7, batch 2400, loss[loss=0.233, simple_loss=0.3117, pruned_loss=0.07712, over 7267.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3036, pruned_loss=0.07594, over 1422078.33 frames.], batch size: 18, lr: 7.42e-04
2022-05-27 01:41:36,526 INFO [train.py:842] (3/4) Epoch 7, batch 2450, loss[loss=0.1972, simple_loss=0.2846, pruned_loss=0.05495, over 7420.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3035, pruned_loss=0.07604, over 1417837.50 frames.], batch size: 21, lr: 7.42e-04
2022-05-27 01:42:14,980 INFO [train.py:842] (3/4) Epoch 7, batch 2500, loss[loss=0.2326, simple_loss=0.3115, pruned_loss=0.07687, over 7314.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3046, pruned_loss=0.07685, over 1418303.78 frames.], batch size: 21, lr: 7.42e-04
2022-05-27 01:42:53,984 INFO [train.py:842] (3/4) Epoch 7, batch 2550, loss[loss=0.208, simple_loss=0.2962, pruned_loss=0.05986, over 7429.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3051, pruned_loss=0.07687, over 1424567.86 frames.], batch size: 20, lr: 7.41e-04
2022-05-27 01:43:32,354 INFO [train.py:842] (3/4) Epoch 7, batch 2600, loss[loss=0.1925, simple_loss=0.2737, pruned_loss=0.05564, over 7164.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3046, pruned_loss=0.07658, over 1418383.42 frames.], batch size: 18, lr: 7.41e-04
2022-05-27 01:44:11,312 INFO [train.py:842] (3/4) Epoch 7, batch 2650, loss[loss=0.221, simple_loss=0.2906, pruned_loss=0.07574, over 7166.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3052, pruned_loss=0.07686, over 1416885.77 frames.], batch size: 18, lr: 7.41e-04
2022-05-27 01:44:49,758 INFO [train.py:842] (3/4) Epoch 7, batch 2700, loss[loss=0.3511, simple_loss=0.3717, pruned_loss=0.1652, over 6799.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3064, pruned_loss=0.07756, over 1418885.76 frames.], batch size: 15, lr: 7.40e-04
2022-05-27 01:45:28,487 INFO [train.py:842] (3/4) Epoch 7, batch 2750, loss[loss=0.265, simple_loss=0.315, pruned_loss=0.1075, over 7421.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3069, pruned_loss=0.07807, over 1419391.45 frames.], batch size: 18, lr: 7.40e-04
2022-05-27 01:46:06,989 INFO [train.py:842] (3/4) Epoch 7, batch 2800, loss[loss=0.1888, simple_loss=0.2598, pruned_loss=0.05895, over 7007.00 frames.], tot_loss[loss=0.2292, simple_loss=0.305, pruned_loss=0.07666, over 1418151.99 frames.], batch size: 16, lr: 7.40e-04
2022-05-27 01:46:46,096 INFO [train.py:842] (3/4) Epoch 7, batch 2850, loss[loss=0.2098, simple_loss=0.2859, pruned_loss=0.06691, over 7322.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3031, pruned_loss=0.07572, over 1423023.44 frames.], batch size: 21, lr: 7.39e-04
2022-05-27 01:47:24,750 INFO [train.py:842] (3/4) Epoch 7, batch 2900, loss[loss=0.2747, simple_loss=0.345, pruned_loss=0.1022, over 5274.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3049, pruned_loss=0.07665, over 1424826.75 frames.], batch size: 52, lr: 7.39e-04
2022-05-27 01:48:03,873 INFO [train.py:842] (3/4) Epoch 7, batch 2950, loss[loss=0.2963, simple_loss=0.366, pruned_loss=0.1133, over 7309.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3052, pruned_loss=0.07658, over 1425398.04 frames.], batch size: 25, lr: 7.39e-04
2022-05-27 01:48:42,445 INFO [train.py:842] (3/4) Epoch 7, batch 3000, loss[loss=0.2391, simple_loss=0.3213, pruned_loss=0.07848, over 7150.00 frames.], tot_loss[loss=0.23, simple_loss=0.3061, pruned_loss=0.07694, over 1426759.47 frames.], batch size: 26, lr: 7.38e-04
2022-05-27 01:48:42,446 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 01:48:51,662 INFO [train.py:871] (3/4) Epoch 7, validation: loss=0.1805, simple_loss=0.2812, pruned_loss=0.03987, over 868885.00 frames.
2022-05-27 01:49:30,595 INFO [train.py:842] (3/4) Epoch 7, batch 3050, loss[loss=0.1863, simple_loss=0.2769, pruned_loss=0.04785, over 7173.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3063, pruned_loss=0.07759, over 1426878.10 frames.], batch size: 26, lr: 7.38e-04
2022-05-27 01:50:09,085 INFO [train.py:842] (3/4) Epoch 7, batch 3100, loss[loss=0.3002, simple_loss=0.3747, pruned_loss=0.1129, over 7181.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3064, pruned_loss=0.07753, over 1423182.86 frames.], batch size: 26, lr: 7.38e-04
2022-05-27 01:50:47,935 INFO [train.py:842] (3/4) Epoch 7, batch 3150, loss[loss=0.2459, simple_loss=0.3203, pruned_loss=0.08574, over 7166.00 frames.], tot_loss[loss=0.232, simple_loss=0.3076, pruned_loss=0.07822, over 1426472.62 frames.], batch size: 28, lr: 7.37e-04
2022-05-27 01:51:26,358 INFO [train.py:842] (3/4) Epoch 7, batch 3200, loss[loss=0.2068, simple_loss=0.2828, pruned_loss=0.06534, over 7333.00 frames.], tot_loss[loss=0.2324, simple_loss=0.308, pruned_loss=0.0784, over 1422879.79 frames.], batch size: 22, lr: 7.37e-04
2022-05-27 01:52:05,362 INFO [train.py:842] (3/4) Epoch 7, batch 3250, loss[loss=0.288, simple_loss=0.3575, pruned_loss=0.1092, over 7061.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3064, pruned_loss=0.07734, over 1421981.97 frames.], batch size: 28, lr: 7.37e-04
2022-05-27 01:52:43,681 INFO [train.py:842] (3/4) Epoch 7, batch 3300, loss[loss=0.334, simple_loss=0.3895, pruned_loss=0.1393, over 7147.00 frames.], tot_loss[loss=0.2314, simple_loss=0.307, pruned_loss=0.0779, over 1417211.36 frames.], batch size: 20, lr: 7.36e-04
2022-05-27 01:53:22,485 INFO [train.py:842] (3/4) Epoch 7, batch 3350, loss[loss=0.272, simple_loss=0.3359, pruned_loss=0.1041, over 7160.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3068, pruned_loss=0.07773, over 1418249.98 frames.], batch size: 19, lr: 7.36e-04
2022-05-27 01:54:01,077 INFO [train.py:842] (3/4) Epoch 7, batch 3400, loss[loss=0.2519, simple_loss=0.3286, pruned_loss=0.08755, over 7106.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3065, pruned_loss=0.07786, over 1421298.50 frames.], batch size: 21, lr: 7.36e-04
2022-05-27 01:54:39,843 INFO [train.py:842] (3/4) Epoch 7, batch 3450, loss[loss=0.2994, simple_loss=0.356, pruned_loss=0.1214, over 7278.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3068, pruned_loss=0.07798, over 1419329.26 frames.], batch size: 24, lr: 7.36e-04
2022-05-27 01:55:18,276 INFO [train.py:842] (3/4) Epoch 7, batch 3500, loss[loss=0.2259, simple_loss=0.3144, pruned_loss=0.0687, over 7223.00 frames.], tot_loss[loss=0.2317, simple_loss=0.307, pruned_loss=0.07819, over 1421587.26 frames.], batch size: 21, lr: 7.35e-04
2022-05-27 01:55:57,343 INFO [train.py:842] (3/4) Epoch 7, batch 3550, loss[loss=0.2112, simple_loss=0.2997, pruned_loss=0.06137, over 7374.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3048, pruned_loss=0.07684, over 1422784.78 frames.], batch size: 23, lr: 7.35e-04
2022-05-27 01:56:36,211 INFO [train.py:842] (3/4) Epoch 7, batch 3600, loss[loss=0.2418, simple_loss=0.3203, pruned_loss=0.08171, over 7218.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3044, pruned_loss=0.07646, over 1424360.42 frames.], batch size: 21, lr: 7.35e-04
2022-05-27 01:57:15,153 INFO [train.py:842] (3/4) Epoch 7, batch 3650, loss[loss=0.2106, simple_loss=0.2914, pruned_loss=0.06486, over 7091.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3052, pruned_loss=0.07751, over 1420607.46 frames.], batch size: 28, lr: 7.34e-04
2022-05-27 01:57:53,804 INFO [train.py:842] (3/4) Epoch 7, batch 3700, loss[loss=0.2335, simple_loss=0.3077, pruned_loss=0.07965, over 7425.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3047, pruned_loss=0.0775, over 1422051.78 frames.], batch size: 20, lr: 7.34e-04
2022-05-27 01:58:32,580 INFO [train.py:842] (3/4) Epoch 7, batch 3750, loss[loss=0.2626, simple_loss=0.3262, pruned_loss=0.09953, over 4890.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3057, pruned_loss=0.07838, over 1422815.49 frames.], batch size: 53, lr: 7.34e-04
2022-05-27 01:59:10,988 INFO [train.py:842] (3/4) Epoch 7, batch 3800, loss[loss=0.2316, simple_loss=0.3064, pruned_loss=0.07846, over 7358.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3051, pruned_loss=0.0781, over 1420797.78 frames.], batch size: 19, lr: 7.33e-04
2022-05-27 01:59:50,100 INFO [train.py:842] (3/4) Epoch 7, batch 3850, loss[loss=0.2082, simple_loss=0.2805, pruned_loss=0.06802, over 7146.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3022, pruned_loss=0.07573, over 1423725.22 frames.], batch size: 17, lr: 7.33e-04
2022-05-27 02:00:28,959 INFO [train.py:842] (3/4) Epoch 7, batch 3900, loss[loss=0.2187, simple_loss=0.2983, pruned_loss=0.06957, over 7438.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3024, pruned_loss=0.07555, over 1424530.71 frames.], batch size: 20, lr: 7.33e-04
2022-05-27 02:01:07,928 INFO [train.py:842] (3/4) Epoch 7, batch 3950, loss[loss=0.1847, simple_loss=0.2671, pruned_loss=0.05113, over 7272.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3015, pruned_loss=0.07516, over 1423731.89 frames.], batch size: 18, lr: 7.32e-04
2022-05-27 02:01:46,441 INFO [train.py:842] (3/4) Epoch 7, batch 4000, loss[loss=0.2287, simple_loss=0.307, pruned_loss=0.0752, over 7323.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3023, pruned_loss=0.07466, over 1430081.82 frames.], batch size: 22, lr: 7.32e-04
2022-05-27 02:02:25,560 INFO [train.py:842] (3/4) Epoch 7, batch 4050, loss[loss=0.2871, simple_loss=0.3452, pruned_loss=0.1145, over 7334.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3028, pruned_loss=0.07532, over 1431571.82 frames.], batch size: 22, lr: 7.32e-04
2022-05-27 02:03:04,014 INFO [train.py:842] (3/4) Epoch 7, batch 4100, loss[loss=0.2595, simple_loss=0.3313, pruned_loss=0.09385, over 6714.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3028, pruned_loss=0.07513, over 1426564.55 frames.], batch size: 31, lr: 7.32e-04
2022-05-27 02:03:42,708 INFO [train.py:842] (3/4) Epoch 7, batch 4150, loss[loss=0.2234, simple_loss=0.2875, pruned_loss=0.07962, over 7256.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3016, pruned_loss=0.07471, over 1427079.38 frames.], batch size: 19, lr: 7.31e-04
2022-05-27 02:04:21,264 INFO [train.py:842] (3/4) Epoch 7, batch 4200, loss[loss=0.2264, simple_loss=0.3081, pruned_loss=0.07238, over 6533.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3015, pruned_loss=0.0748, over 1428486.86 frames.], batch size: 38, lr: 7.31e-04
2022-05-27 02:05:00,149 INFO [train.py:842] (3/4) Epoch 7, batch 4250, loss[loss=0.2187, simple_loss=0.3018, pruned_loss=0.06776, over 7112.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3017, pruned_loss=0.07485, over 1430463.65 frames.], batch size: 21, lr: 7.31e-04
2022-05-27 02:05:38,649 INFO [train.py:842] (3/4) Epoch 7, batch 4300, loss[loss=0.2505, simple_loss=0.3225, pruned_loss=0.08927, over 6759.00 frames.], tot_loss[loss=0.225, simple_loss=0.3007, pruned_loss=0.07468, over 1425967.47 frames.], batch size: 31, lr: 7.30e-04
2022-05-27 02:06:17,405 INFO [train.py:842] (3/4) Epoch 7, batch 4350, loss[loss=0.1941, simple_loss=0.281, pruned_loss=0.05358, over 7421.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3013, pruned_loss=0.07451, over 1420764.02 frames.], batch size: 20, lr: 7.30e-04
2022-05-27 02:06:55,820 INFO [train.py:842] (3/4) Epoch 7, batch 4400, loss[loss=0.2209, simple_loss=0.2968, pruned_loss=0.07254, over 7406.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3024, pruned_loss=0.07521, over 1415439.25 frames.], batch size: 18, lr: 7.30e-04
2022-05-27 02:07:34,691 INFO [train.py:842] (3/4) Epoch 7, batch 4450, loss[loss=0.2144, simple_loss=0.2991, pruned_loss=0.0649, over 7139.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3027, pruned_loss=0.07556, over 1417870.75 frames.], batch size: 20, lr: 7.29e-04
2022-05-27 02:08:13,178 INFO [train.py:842] (3/4) Epoch 7, batch 4500, loss[loss=0.2294, simple_loss=0.2917, pruned_loss=0.08357, over 7261.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3029, pruned_loss=0.07583, over 1420104.64 frames.], batch size: 17, lr: 7.29e-04
2022-05-27 02:08:52,145 INFO [train.py:842] (3/4) Epoch 7, batch 4550, loss[loss=0.3134, simple_loss=0.3513, pruned_loss=0.1377, over 7198.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3045, pruned_loss=0.0769, over 1419175.81 frames.], batch size: 16, lr: 7.29e-04
2022-05-27 02:09:30,759 INFO [train.py:842] (3/4) Epoch 7, batch 4600, loss[loss=0.2577, simple_loss=0.3245, pruned_loss=0.09544, over 7415.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3042, pruned_loss=0.07747, over 1417267.05 frames.], batch size: 21, lr: 7.28e-04
2022-05-27 02:10:09,744 INFO [train.py:842] (3/4) Epoch 7, batch 4650, loss[loss=0.1851, simple_loss=0.265, pruned_loss=0.05265, over 7161.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3046, pruned_loss=0.07717, over 1421748.82 frames.], batch size: 18, lr: 7.28e-04
2022-05-27 02:10:48,239 INFO [train.py:842] (3/4) Epoch 7, batch 4700, loss[loss=0.2477, simple_loss=0.3241, pruned_loss=0.08567, over 7283.00 frames.], tot_loss[loss=0.2282, simple_loss=0.304, pruned_loss=0.07623, over 1422895.74 frames.], batch size: 24, lr: 7.28e-04
2022-05-27 02:11:27,375 INFO [train.py:842] (3/4) Epoch 7, batch 4750, loss[loss=0.2108, simple_loss=0.2921, pruned_loss=0.06473, over 7358.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3036, pruned_loss=0.07637, over 1424136.24 frames.], batch size: 19, lr: 7.28e-04
2022-05-27 02:12:05,929 INFO [train.py:842] (3/4) Epoch 7, batch 4800, loss[loss=0.1636, simple_loss=0.2431, pruned_loss=0.04205, over 7287.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3032, pruned_loss=0.07622, over 1422319.94 frames.], batch size: 18, lr: 7.27e-04
2022-05-27 02:12:44,817 INFO [train.py:842] (3/4) Epoch 7, batch 4850, loss[loss=0.2009, simple_loss=0.2828, pruned_loss=0.05953, over 7409.00 frames.], tot_loss[loss=0.226, simple_loss=0.3017, pruned_loss=0.07511, over 1419345.82 frames.], batch size: 21, lr: 7.27e-04
2022-05-27 02:13:23,588 INFO [train.py:842] (3/4) Epoch 7, batch 4900, loss[loss=0.2474, simple_loss=0.3258, pruned_loss=0.08452, over 7203.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3018, pruned_loss=0.07496, over 1419775.70 frames.], batch size: 23, lr: 7.27e-04
2022-05-27 02:14:02,749 INFO [train.py:842] (3/4) Epoch 7, batch 4950, loss[loss=0.1926, simple_loss=0.2851, pruned_loss=0.05006, over 7329.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3002, pruned_loss=0.07399, over 1422342.96 frames.], batch size: 21, lr: 7.26e-04
2022-05-27 02:14:41,334 INFO [train.py:842] (3/4) Epoch 7, batch 5000, loss[loss=0.2407, simple_loss=0.3122, pruned_loss=0.08461, over 7205.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3003, pruned_loss=0.07429, over 1423303.01 frames.], batch size: 23, lr: 7.26e-04
2022-05-27 02:15:20,266 INFO [train.py:842] (3/4) Epoch 7, batch 5050, loss[loss=0.21, simple_loss=0.2902, pruned_loss=0.06489, over 7301.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3006, pruned_loss=0.07487, over 1414242.94 frames.], batch size: 25, lr: 7.26e-04
2022-05-27 02:15:58,684 INFO [train.py:842] (3/4) Epoch 7, batch 5100, loss[loss=0.2419, simple_loss=0.2928, pruned_loss=0.09547, over 7161.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3008, pruned_loss=0.07522, over 1416778.12 frames.], batch size: 18, lr: 7.25e-04
2022-05-27 02:16:37,769 INFO [train.py:842] (3/4) Epoch 7, batch 5150, loss[loss=0.1957, simple_loss=0.2697, pruned_loss=0.06087, over 7422.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3013, pruned_loss=0.07588, over 1418289.55 frames.], batch size: 18, lr: 7.25e-04
2022-05-27 02:17:16,404 INFO [train.py:842] (3/4) Epoch 7, batch 5200, loss[loss=0.2272, simple_loss=0.3106, pruned_loss=0.07187, over 7321.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3025, pruned_loss=0.07627, over 1420795.98 frames.], batch size: 20, lr: 7.25e-04
2022-05-27 02:17:55,310 INFO [train.py:842] (3/4) Epoch 7, batch 5250, loss[loss=0.242, simple_loss=0.3278, pruned_loss=0.07807, over 7317.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3023, pruned_loss=0.07616, over 1417125.16 frames.], batch size: 20, lr: 7.25e-04
2022-05-27 02:18:33,928 INFO [train.py:842] (3/4) Epoch 7, batch 5300, loss[loss=0.196, simple_loss=0.2795, pruned_loss=0.05626, over 7008.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3024, pruned_loss=0.07659, over 1420968.06 frames.], batch size: 16, lr: 7.24e-04
2022-05-27 02:19:12,838 INFO [train.py:842] (3/4) Epoch 7, batch 5350, loss[loss=0.2355, simple_loss=0.3034, pruned_loss=0.08378, over 7241.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3026, pruned_loss=0.07656, over 1422916.10 frames.], batch size: 20, lr: 7.24e-04
2022-05-27 02:19:51,746 INFO [train.py:842] (3/4) Epoch 7, batch 5400, loss[loss=0.2716, simple_loss=0.3384, pruned_loss=0.1024, over 5251.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3021, pruned_loss=0.0763, over 1414554.23 frames.], batch size: 52, lr: 7.24e-04
2022-05-27 02:20:30,648 INFO [train.py:842] (3/4) Epoch 7, batch 5450, loss[loss=0.3053, simple_loss=0.3765, pruned_loss=0.1171, over 7287.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3031, pruned_loss=0.07661, over 1416527.25 frames.], batch size: 24, lr: 7.23e-04
2022-05-27 02:21:09,287 INFO [train.py:842] (3/4) Epoch 7, batch 5500, loss[loss=0.1649, simple_loss=0.2517, pruned_loss=0.03903, over 7166.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3022, pruned_loss=0.07611, over 1418103.07 frames.], batch size: 19, lr: 7.23e-04
2022-05-27 02:21:48,180 INFO [train.py:842] (3/4) Epoch 7, batch 5550, loss[loss=0.2458, simple_loss=0.3225, pruned_loss=0.08458, over 7288.00 frames.], tot_loss[loss=0.2289, simple_loss=0.304, pruned_loss=0.07688, over 1418149.73 frames.], batch size: 24, lr: 7.23e-04
2022-05-27 02:22:26,587 INFO [train.py:842] (3/4) Epoch 7, batch 5600, loss[loss=0.1942, simple_loss=0.2802, pruned_loss=0.05407, over 7185.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3031, pruned_loss=0.0761, over 1417093.03 frames.], batch size: 23, lr: 7.22e-04
2022-05-27 02:23:05,525 INFO [train.py:842] (3/4) Epoch 7, batch 5650, loss[loss=0.1729, simple_loss=0.2529, pruned_loss=0.04651, over 7286.00 frames.], tot_loss[loss=0.2289, simple_loss=0.304, pruned_loss=0.07696, over 1416733.75 frames.], batch size: 17, lr: 7.22e-04
2022-05-27 02:23:44,708 INFO [train.py:842] (3/4) Epoch 7, batch 5700, loss[loss=0.169, simple_loss=0.2566, pruned_loss=0.04072, over 7148.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3038, pruned_loss=0.07672, over 1420969.23 frames.], batch size: 20, lr: 7.22e-04
2022-05-27 02:24:23,473 INFO [train.py:842] (3/4) Epoch 7, batch 5750, loss[loss=0.2344, simple_loss=0.3114, pruned_loss=0.07872, over 7258.00 frames.], tot_loss[loss=0.2278, simple_loss=0.303, pruned_loss=0.07632, over 1420400.37 frames.], batch size: 25, lr: 7.22e-04
2022-05-27 02:25:01,797 INFO [train.py:842] (3/4) Epoch 7, batch 5800, loss[loss=0.2329, simple_loss=0.3086, pruned_loss=0.07864, over 6480.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3025, pruned_loss=0.07583, over 1417762.61 frames.], batch size: 38, lr: 7.21e-04
2022-05-27 02:25:40,573 INFO [train.py:842] (3/4) Epoch 7, batch 5850, loss[loss=0.2099, simple_loss=0.2865, pruned_loss=0.06662, over 7406.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3044, pruned_loss=0.07691, over 1415308.46 frames.], batch size: 18, lr: 7.21e-04
2022-05-27 02:26:19,078 INFO [train.py:842] (3/4) Epoch 7, batch 5900, loss[loss=0.2061, simple_loss=0.2731, pruned_loss=0.06959, over 7289.00 frames.], tot_loss[loss=0.228, simple_loss=0.3034, pruned_loss=0.07629, over 1415924.01 frames.], batch size: 17, lr: 7.21e-04
2022-05-27 02:26:58,432 INFO [train.py:842] (3/4) Epoch 7, batch 5950, loss[loss=0.2455, simple_loss=0.3102, pruned_loss=0.0904, over 7431.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3045, pruned_loss=0.0767, over 1419946.29 frames.], batch size: 20, lr: 7.20e-04
2022-05-27 02:27:37,191 INFO [train.py:842] (3/4) Epoch 7, batch 6000, loss[loss=0.1935, simple_loss=0.2666, pruned_loss=0.06023, over 7168.00 frames.], tot_loss[loss=0.2276, simple_loss=0.303, pruned_loss=0.07606, over 1419109.06 frames.], batch size: 18, lr: 7.20e-04
2022-05-27 02:27:37,191 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 02:27:46,474 INFO [train.py:871] (3/4) Epoch 7, validation: loss=0.1828, simple_loss=0.2835, pruned_loss=0.04102, over 868885.00 frames.
2022-05-27 02:28:25,438 INFO [train.py:842] (3/4) Epoch 7, batch 6050, loss[loss=0.2029, simple_loss=0.2879, pruned_loss=0.05898, over 7312.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3022, pruned_loss=0.07539, over 1422212.09 frames.], batch size: 20, lr: 7.20e-04
2022-05-27 02:29:04,022 INFO [train.py:842] (3/4) Epoch 7, batch 6100, loss[loss=0.1758, simple_loss=0.2436, pruned_loss=0.05395, over 6812.00 frames.], tot_loss[loss=0.2263, simple_loss=0.302, pruned_loss=0.0753, over 1422819.53 frames.], batch size: 15, lr: 7.20e-04
2022-05-27 02:29:43,005 INFO [train.py:842] (3/4) Epoch 7, batch 6150, loss[loss=0.2043, simple_loss=0.2722, pruned_loss=0.06817, over 7409.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3015, pruned_loss=0.07517, over 1422974.83 frames.], batch size: 18, lr: 7.19e-04
2022-05-27 02:30:21,626 INFO [train.py:842] (3/4) Epoch 7, batch 6200, loss[loss=0.199, simple_loss=0.28, pruned_loss=0.05906, over 7293.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3022, pruned_loss=0.07501, over 1422474.74 frames.], batch size: 18, lr: 7.19e-04
2022-05-27 02:31:00,727 INFO [train.py:842] (3/4) Epoch 7, batch 6250, loss[loss=0.1788, simple_loss=0.254, pruned_loss=0.05175, over 6793.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3023, pruned_loss=0.07565, over 1422930.74 frames.], batch size: 15, lr: 7.19e-04
2022-05-27 02:31:39,602 INFO [train.py:842] (3/4) Epoch 7, batch 6300, loss[loss=0.1781, simple_loss=0.263, pruned_loss=0.04662, over 7355.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3031, pruned_loss=0.07627, over 1414504.28 frames.], batch size: 19, lr: 7.18e-04
2022-05-27 02:32:18,504 INFO [train.py:842] (3/4) Epoch 7, batch 6350, loss[loss=0.1685, simple_loss=0.2466, pruned_loss=0.04526, over 7285.00 frames.], tot_loss[loss=0.2272, simple_loss=0.302, pruned_loss=0.0762, over 1418870.18 frames.], batch size: 18, lr: 7.18e-04
2022-05-27 02:32:57,035 INFO [train.py:842] (3/4) Epoch 7, batch 6400, loss[loss=0.325, simple_loss=0.3733, pruned_loss=0.1383, over 5106.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3054, pruned_loss=0.07768, over 1421977.18 frames.], batch size: 52, lr: 7.18e-04
2022-05-27 02:33:36,093 INFO [train.py:842] (3/4) Epoch 7, batch 6450, loss[loss=0.2194, simple_loss=0.303, pruned_loss=0.06788, over 7194.00 frames.], tot_loss[loss=0.229, simple_loss=0.3037, pruned_loss=0.07713, over 1425789.35 frames.], batch size: 23, lr: 7.18e-04
2022-05-27 02:34:14,479 INFO [train.py:842] (3/4) Epoch 7, batch 6500, loss[loss=0.2573, simple_loss=0.3331, pruned_loss=0.0907, over 7089.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3028, pruned_loss=0.07625, over 1427402.40 frames.], batch size: 28, lr: 7.17e-04
2022-05-27 02:34:53,304 INFO [train.py:842] (3/4) Epoch 7, batch 6550, loss[loss=0.2398, simple_loss=0.3127, pruned_loss=0.0834, over 7331.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3035, pruned_loss=0.07655, over 1422930.46 frames.], batch size: 25, lr: 7.17e-04
2022-05-27 02:35:31,824 INFO [train.py:842] (3/4) Epoch 7, batch 6600, loss[loss=0.1948, simple_loss=0.2799, pruned_loss=0.05486, over 7417.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3027, pruned_loss=0.07656, over 1421447.13 frames.], batch size: 21, lr: 7.17e-04
2022-05-27 02:36:10,725 INFO [train.py:842] (3/4) Epoch 7, batch 6650, loss[loss=0.2361, simple_loss=0.3018, pruned_loss=0.08521, over 7063.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3026, pruned_loss=0.07585, over 1421131.71 frames.], batch size: 18, lr: 7.16e-04
2022-05-27 02:36:49,528 INFO [train.py:842] (3/4) Epoch 7, batch 6700, loss[loss=0.2145, simple_loss=0.2865, pruned_loss=0.07122, over 7072.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3038, pruned_loss=0.07678, over 1423923.53 frames.], batch size: 18, lr: 7.16e-04
2022-05-27 02:37:28,491 INFO [train.py:842] (3/4) Epoch 7, batch 6750, loss[loss=0.2737, simple_loss=0.3323, pruned_loss=0.1075, over 7158.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3032, pruned_loss=0.07657, over 1426048.61 frames.], batch size: 19, lr: 7.16e-04
2022-05-27 02:38:06,900 INFO [train.py:842] (3/4) Epoch 7, batch 6800, loss[loss=0.221, simple_loss=0.2981, pruned_loss=0.07197, over 7327.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3042, pruned_loss=0.07747, over 1423897.89 frames.], batch size: 25, lr: 7.16e-04
2022-05-27 02:38:45,857 INFO [train.py:842] (3/4) Epoch 7, batch 6850, loss[loss=0.2001, simple_loss=0.2634, pruned_loss=0.06841, over 7252.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3043, pruned_loss=0.07752, over 1421539.42 frames.], batch size: 16, lr: 7.15e-04
2022-05-27 02:39:35,211 INFO [train.py:842] (3/4) Epoch 7, batch 6900, loss[loss=0.235, simple_loss=0.3175, pruned_loss=0.07622, over 7338.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3041, pruned_loss=0.07755, over 1422618.31 frames.], batch size: 22, lr: 7.15e-04
2022-05-27 02:40:14,044 INFO [train.py:842] (3/4) Epoch 7, batch 6950, loss[loss=0.2421, simple_loss=0.3216, pruned_loss=0.08127, over 7413.00 frames.], tot_loss[loss=0.229, simple_loss=0.3036, pruned_loss=0.07716, over 1418634.91 frames.], batch size: 21, lr: 7.15e-04
2022-05-27 02:40:52,457 INFO [train.py:842] (3/4) Epoch 7, batch 7000, loss[loss=0.2191, simple_loss=0.311, pruned_loss=0.06358, over 6512.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3049, pruned_loss=0.07781, over 1420139.52 frames.], batch size: 38, lr: 7.14e-04
2022-05-27 02:41:31,360 INFO [train.py:842] (3/4) Epoch 7, batch 7050, loss[loss=0.2246, simple_loss=0.3089, pruned_loss=0.07013, over 7316.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3032, pruned_loss=0.07647, over 1424621.12 frames.], batch size: 25, lr: 7.14e-04
2022-05-27 02:42:09,942 INFO [train.py:842] (3/4) Epoch 7, batch 7100, loss[loss=0.2247, simple_loss=0.3125, pruned_loss=0.06845, over 7196.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3033, pruned_loss=0.07578, over 1425669.83 frames.], batch size: 23, lr: 7.14e-04
2022-05-27 02:42:49,042 INFO [train.py:842] (3/4) Epoch 7, batch 7150, loss[loss=0.2302, simple_loss=0.3056, pruned_loss=0.0774, over 7288.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3036, pruned_loss=0.07634, over 1423405.98 frames.], batch size: 17, lr: 7.14e-04
2022-05-27 02:43:27,666 INFO [train.py:842] (3/4) Epoch 7, batch 7200, loss[loss=0.2168, simple_loss=0.2903, pruned_loss=0.07167, over 7364.00 frames.], tot_loss[loss=0.2286, simple_loss=0.304, pruned_loss=0.07665, over 1414176.86 frames.], batch size: 19, lr: 7.13e-04
2022-05-27 02:44:06,751 INFO [train.py:842] (3/4) Epoch 7, batch 7250, loss[loss=0.2958, simple_loss=0.3709, pruned_loss=0.1103, over 7040.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3054, pruned_loss=0.07772, over 1415944.55 frames.], batch size: 28, lr: 7.13e-04
2022-05-27 02:44:45,258 INFO [train.py:842] (3/4) Epoch 7, batch 7300, loss[loss=0.2454, simple_loss=0.3147, pruned_loss=0.08802, over 7163.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3044, pruned_loss=0.07669, over 1419314.89 frames.], batch size: 26, lr: 7.13e-04
2022-05-27 02:45:24,106 INFO [train.py:842] (3/4) Epoch 7, batch 7350, loss[loss=0.2049, simple_loss=0.2768, pruned_loss=0.06651, over 7001.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3034, pruned_loss=0.07604, over 1420233.60 frames.], batch size: 16, lr: 7.12e-04
2022-05-27 02:46:02,472 INFO [train.py:842] (3/4) Epoch 7, batch 7400, loss[loss=0.2026, simple_loss=0.2788, pruned_loss=0.06314, over 7445.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3034, pruned_loss=0.0757, over 1417191.02 frames.], batch size: 19, lr: 7.12e-04
2022-05-27 02:46:41,246 INFO [train.py:842] (3/4) Epoch 7, batch 7450, loss[loss=0.2146, simple_loss=0.2847, pruned_loss=0.07228, over 7286.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3055, pruned_loss=0.07709, over 1416483.22 frames.], batch size: 17, lr: 7.12e-04
2022-05-27 02:47:19,882 INFO [train.py:842] (3/4) Epoch 7, batch 7500, loss[loss=0.2323, simple_loss=0.3138, pruned_loss=0.07541, over 7136.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3034, pruned_loss=0.07611, over 1418001.95 frames.], batch size: 20, lr: 7.12e-04
2022-05-27 02:47:58,787 INFO [train.py:842] (3/4) Epoch 7, batch 7550, loss[loss=0.2188, simple_loss=0.3008, pruned_loss=0.06834, over 7328.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3026, pruned_loss=0.07503, over 1416962.21 frames.], batch size: 21, lr: 7.11e-04
2022-05-27 02:48:37,256 INFO [train.py:842] (3/4) Epoch 7, batch 7600, loss[loss=0.1992, simple_loss=0.2826, pruned_loss=0.05789, over 7341.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3031, pruned_loss=0.07525, over 1420481.51 frames.], batch size: 22, lr: 7.11e-04
2022-05-27 02:49:16,279 INFO [train.py:842] (3/4) Epoch 7, batch 7650, loss[loss=0.3423, simple_loss=0.384, pruned_loss=0.1503, over 5080.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3022, pruned_loss=0.07475, over 1422714.64 frames.], batch size: 52, lr: 7.11e-04
2022-05-27 02:49:54,720 INFO [train.py:842] (3/4) Epoch 7, batch 7700, loss[loss=0.253, simple_loss=0.3187, pruned_loss=0.09364, over 7119.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3017, pruned_loss=0.07504, over 1419789.00 frames.], batch size: 21, lr: 7.10e-04
2022-05-27 02:50:33,592 INFO [train.py:842] (3/4) Epoch 7, batch 7750, loss[loss=0.2494, simple_loss=0.3263, pruned_loss=0.08623, over 7229.00 frames.], tot_loss[loss=0.2272, simple_loss=0.303, pruned_loss=0.07574, over 1424203.72 frames.], batch size: 20, lr: 7.10e-04
2022-05-27 02:51:12,172 INFO [train.py:842] (3/4) Epoch 7, batch 7800, loss[loss=0.2063, simple_loss=0.2952, pruned_loss=0.05868, over 7431.00 frames.], tot_loss[loss=0.227, simple_loss=0.303, pruned_loss=0.07552, over 1425635.43 frames.], batch size: 20, lr: 7.10e-04
2022-05-27 02:51:51,069 INFO [train.py:842] (3/4) Epoch 7, batch 7850, loss[loss=0.2265, simple_loss=0.2998, pruned_loss=0.07664, over 6822.00 frames.], tot_loss[loss=0.2269, simple_loss=0.303, pruned_loss=0.07533, over 1424928.39 frames.], batch size: 15, lr: 7.10e-04
2022-05-27 02:52:29,407 INFO [train.py:842] (3/4) Epoch 7, batch 7900, loss[loss=0.227, simple_loss=0.2974, pruned_loss=0.07824, over 7252.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3028, pruned_loss=0.07536, over 1422703.03 frames.], batch size: 19, lr: 7.09e-04
2022-05-27 02:53:07,969 INFO [train.py:842] (3/4) Epoch 7, batch 7950, loss[loss=0.2401, simple_loss=0.3106, pruned_loss=0.08479, over 7218.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3023, pruned_loss=0.07564, over 1417189.28 frames.], batch size: 23, lr: 7.09e-04
2022-05-27 02:53:46,564 INFO [train.py:842] (3/4) Epoch 7, batch 8000, loss[loss=0.2767, simple_loss=0.3367, pruned_loss=0.1083, over 5062.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3039, pruned_loss=0.07712, over 1415307.01 frames.], batch size: 52, lr: 7.09e-04
2022-05-27 02:54:25,429 INFO [train.py:842] (3/4) Epoch 7, batch 8050, loss[loss=0.2107, simple_loss=0.2963, pruned_loss=0.06258, over 7407.00 frames.], tot_loss[loss=0.2302, simple_loss=0.305, pruned_loss=0.07771, over 1415904.80 frames.], batch size: 21, lr: 7.08e-04
2022-05-27 02:55:24,485 INFO [train.py:842] (3/4) Epoch 7, batch 8100, loss[loss=0.2135, simple_loss=0.2986, pruned_loss=0.06424, over 6845.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3071, pruned_loss=0.07867, over 1416018.58 frames.], batch size: 31, lr: 7.08e-04
2022-05-27 02:56:13,877 INFO [train.py:842] (3/4) Epoch 7, batch 8150, loss[loss=0.2311, simple_loss=0.3208, pruned_loss=0.07069, over 7311.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3064, pruned_loss=0.07865, over 1420998.96 frames.], batch size: 21, lr: 7.08e-04
2022-05-27 02:56:52,277 INFO [train.py:842] (3/4) Epoch 7, batch 8200, loss[loss=0.2292, simple_loss=0.3015, pruned_loss=0.07848, over 7357.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3057, pruned_loss=0.07802, over 1420649.82 frames.], batch size: 19, lr: 7.08e-04
2022-05-27 02:57:31,165 INFO [train.py:842] (3/4) Epoch 7, batch 8250, loss[loss=0.2756, simple_loss=0.3391, pruned_loss=0.106, over 6828.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3052, pruned_loss=0.07785, over 1421283.48 frames.], batch size: 31, lr: 7.07e-04
2022-05-27 02:58:09,605 INFO [train.py:842] (3/4) Epoch 7, batch 8300, loss[loss=0.209, simple_loss=0.2838, pruned_loss=0.06706, over 7004.00 frames.], tot_loss[loss=0.2293, simple_loss=0.304, pruned_loss=0.07729, over 1415727.92 frames.], batch size: 16, lr: 7.07e-04
2022-05-27 02:58:48,452 INFO [train.py:842] (3/4) Epoch 7, batch 8350, loss[loss=0.1845, simple_loss=0.2766, pruned_loss=0.04616, over 7219.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3028, pruned_loss=0.07586, over 1420607.79 frames.], batch size: 21, lr: 7.07e-04
2022-05-27 02:59:26,876 INFO [train.py:842] (3/4) Epoch 7, batch 8400, loss[loss=0.2237, simple_loss=0.3119, pruned_loss=0.06776, over 7229.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3027, pruned_loss=0.07537, over 1422833.47 frames.], batch size: 20, lr: 7.06e-04
2022-05-27 03:00:05,688 INFO [train.py:842] (3/4) Epoch 7, batch 8450, loss[loss=0.2257, simple_loss=0.3102, pruned_loss=0.0706, over 7421.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3034, pruned_loss=0.07564, over 1423402.65 frames.], batch size: 21, lr: 7.06e-04
2022-05-27 03:00:44,407 INFO [train.py:842] (3/4) Epoch 7, batch 8500, loss[loss=0.2583, simple_loss=0.327, pruned_loss=0.09484, over 7347.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3033, pruned_loss=0.07593, over 1423109.98 frames.], batch size: 22, lr: 7.06e-04
2022-05-27 03:01:22,939 INFO [train.py:842] (3/4) Epoch 7, batch 8550, loss[loss=0.2315, simple_loss=0.3106, pruned_loss=0.07617, over 7152.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3044, pruned_loss=0.0767, over 1417061.61 frames.], batch size: 19, lr: 7.06e-04
2022-05-27 03:02:01,350 INFO [train.py:842] (3/4) Epoch 7, batch 8600, loss[loss=0.2043, simple_loss=0.2991, pruned_loss=0.05474, over 7165.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3049, pruned_loss=0.0768, over 1418171.20 frames.], batch size: 18, lr: 7.05e-04
2022-05-27 03:02:40,400 INFO [train.py:842] (3/4) Epoch 7, batch 8650, loss[loss=0.2309, simple_loss=0.3129, pruned_loss=0.07447, over 7339.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3027, pruned_loss=0.07528, over 1418284.81 frames.], batch size: 22, lr: 7.05e-04
2022-05-27 03:03:18,986 INFO [train.py:842] (3/4) Epoch 7, batch 8700, loss[loss=0.1483, simple_loss=0.2281, pruned_loss=0.03424, over 7418.00 frames.], tot_loss[loss=0.2259, simple_loss=0.302, pruned_loss=0.07485, over 1420529.55 frames.], batch size: 18, lr: 7.05e-04
2022-05-27 03:03:57,714 INFO [train.py:842] (3/4) Epoch 7, batch 8750, loss[loss=0.2179, simple_loss=0.3062, pruned_loss=0.06485, over 7224.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3037, pruned_loss=0.07528, over 1419925.55 frames.], batch size: 21, lr: 7.05e-04
2022-05-27 03:04:35,975 INFO [train.py:842] (3/4) Epoch 7, batch 8800, loss[loss=0.2847, simple_loss=0.3477, pruned_loss=0.1109, over 5506.00 frames.], tot_loss[loss=0.2278, simple_loss=0.304, pruned_loss=0.07582, over 1415401.21 frames.], batch size: 52, lr: 7.04e-04
2022-05-27 03:05:17,331 INFO [train.py:842] (3/4) Epoch 7, batch 8850, loss[loss=0.1915, simple_loss=0.2643, pruned_loss=0.05933, over 7411.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3035, pruned_loss=0.07576, over 1417518.45 frames.], batch size: 18, lr: 7.04e-04
2022-05-27 03:05:55,614 INFO [train.py:842] (3/4) Epoch 7, batch 8900, loss[loss=0.2116, simple_loss=0.287, pruned_loss=0.06813, over 7170.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3051, pruned_loss=0.07669, over 1413079.74 frames.], batch size: 18, lr: 7.04e-04
2022-05-27 03:06:34,509 INFO [train.py:842] (3/4) Epoch 7, batch 8950, loss[loss=0.1939, simple_loss=0.2905, pruned_loss=0.04871, over 7318.00 frames.], tot_loss[loss=0.2305, simple_loss=0.306, pruned_loss=0.07755, over 1407231.75 frames.], batch size: 22, lr: 7.03e-04
2022-05-27 03:07:12,765 INFO [train.py:842] (3/4) Epoch 7, batch 9000, loss[loss=0.2993, simple_loss=0.3463, pruned_loss=0.1262, over 7230.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3056, pruned_loss=0.07706, over 1402136.86 frames.], batch size: 21, lr: 7.03e-04
2022-05-27 03:07:12,765 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 03:07:22,108 INFO [train.py:871] (3/4) Epoch 7, validation: loss=0.1806, simple_loss=0.2819, pruned_loss=0.03969, over 868885.00 frames.
2022-05-27 03:08:00,677 INFO [train.py:842] (3/4) Epoch 7, batch 9050, loss[loss=0.2734, simple_loss=0.342, pruned_loss=0.1024, over 5102.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3067, pruned_loss=0.07737, over 1396665.69 frames.], batch size: 52, lr: 7.03e-04
2022-05-27 03:08:38,278 INFO [train.py:842] (3/4) Epoch 7, batch 9100, loss[loss=0.2254, simple_loss=0.3178, pruned_loss=0.06656, over 7305.00 frames.], tot_loss[loss=0.2317, simple_loss=0.308, pruned_loss=0.07767, over 1378639.07 frames.], batch size: 25, lr: 7.03e-04
2022-05-27 03:09:15,878 INFO [train.py:842] (3/4) Epoch 7, batch 9150, loss[loss=0.1925, simple_loss=0.2862, pruned_loss=0.04944, over 6473.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3099, pruned_loss=0.07943, over 1338209.52 frames.], batch size: 37, lr: 7.02e-04
2022-05-27 03:10:09,077 INFO [train.py:842] (3/4) Epoch 8, batch 0, loss[loss=0.264, simple_loss=0.3427, pruned_loss=0.09264, over 7332.00 frames.], tot_loss[loss=0.264, simple_loss=0.3427, pruned_loss=0.09264, over 7332.00 frames.], batch size: 22, lr: 6.74e-04
2022-05-27 03:10:47,730 INFO [train.py:842] (3/4) Epoch 8, batch 50, loss[loss=0.1965, simple_loss=0.2657, pruned_loss=0.06365, over 7132.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3061, pruned_loss=0.07629, over 321521.70 frames.], batch size: 17, lr: 6.73e-04
2022-05-27 03:11:26,549 INFO [train.py:842] (3/4) Epoch 8, batch 100, loss[loss=0.2308, simple_loss=0.3055, pruned_loss=0.07801, over 7313.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3041, pruned_loss=0.07379, over 569759.41 frames.], batch size: 25, lr: 6.73e-04
2022-05-27 03:12:05,191 INFO [train.py:842] (3/4) Epoch 8, batch 150, loss[loss=0.2328, simple_loss=0.3067, pruned_loss=0.07948, over 7110.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3011, pruned_loss=0.07324, over 758547.86 frames.], batch size: 21, lr: 6.73e-04
2022-05-27 03:12:43,922 INFO [train.py:842] (3/4) Epoch 8, batch 200, loss[loss=0.2004, simple_loss=0.2807, pruned_loss=0.06005, over 7206.00 frames.], tot_loss[loss=0.2233, simple_loss=0.301, pruned_loss=0.07277, over 907028.91 frames.], batch size: 22, lr: 6.73e-04
2022-05-27 03:13:22,344 INFO [train.py:842] (3/4) Epoch 8, batch 250, loss[loss=0.2165, simple_loss=0.2954, pruned_loss=0.06884, over 7108.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3012, pruned_loss=0.07291, over 1020397.94 frames.], batch size: 21, lr: 6.72e-04
2022-05-27 03:14:01,084 INFO [train.py:842] (3/4) Epoch 8, batch 300, loss[loss=0.2334, simple_loss=0.3044, pruned_loss=0.08121, over 7070.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3022, pruned_loss=0.07377, over 1105616.21 frames.], batch size: 18, lr: 6.72e-04
2022-05-27 03:14:39,759 INFO [train.py:842] (3/4) Epoch 8, batch 350, loss[loss=0.224, simple_loss=0.3111, pruned_loss=0.06847, over 7112.00 frames.], tot_loss[loss=0.2226, simple_loss=0.2998, pruned_loss=0.07269, over 1177454.33 frames.], batch size: 21, lr: 6.72e-04
2022-05-27 03:15:18,902 INFO [train.py:842] (3/4) Epoch 8, batch 400, loss[loss=0.2536, simple_loss=0.3211, pruned_loss=0.09309, over 5000.00 frames.], tot_loss[loss=0.2209, simple_loss=0.2984, pruned_loss=0.07172, over 1230499.56 frames.], batch size: 52, lr: 6.72e-04
2022-05-27 03:15:57,545 INFO [train.py:842] (3/4) Epoch 8, batch 450, loss[loss=0.2041, simple_loss=0.2726, pruned_loss=0.0678, over 6778.00 frames.], tot_loss[loss=0.2212, simple_loss=0.298, pruned_loss=0.07216, over 1271086.67 frames.], batch size: 15, lr: 6.71e-04
2022-05-27 03:16:36,530 INFO [train.py:842] (3/4) Epoch 8, batch 500, loss[loss=0.2162, simple_loss=0.3052, pruned_loss=0.06357, over 7205.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2974, pruned_loss=0.07136, over 1303917.64 frames.], batch size: 23, lr: 6.71e-04
2022-05-27 03:17:15,308 INFO [train.py:842] (3/4) Epoch 8, batch 550, loss[loss=0.2892, simple_loss=0.3438, pruned_loss=0.1173, over 7199.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2979, pruned_loss=0.07182, over 1332801.48 frames.], batch size: 23, lr: 6.71e-04
2022-05-27 03:17:54,049 INFO [train.py:842] (3/4) Epoch 8, batch 600, loss[loss=0.2578, simple_loss=0.3206, pruned_loss=0.09752, over 7210.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2987, pruned_loss=0.07225, over 1352720.02 frames.], batch size: 21, lr: 6.71e-04
2022-05-27 03:18:32,606 INFO [train.py:842] (3/4) Epoch 8, batch 650, loss[loss=0.1898, simple_loss=0.2704, pruned_loss=0.05455, over 7254.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2983, pruned_loss=0.07217, over 1367789.57 frames.], batch size: 19, lr: 6.70e-04
2022-05-27 03:19:11,320 INFO [train.py:842] (3/4) Epoch 8, batch 700, loss[loss=0.2601, simple_loss=0.3234, pruned_loss=0.09841, over 5054.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3003, pruned_loss=0.07328, over 1376534.46 frames.], batch size: 53, lr: 6.70e-04
2022-05-27 03:19:49,828 INFO [train.py:842] (3/4) Epoch 8, batch 750, loss[loss=0.2078, simple_loss=0.2827, pruned_loss=0.06645, over 7356.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2999, pruned_loss=0.0733, over 1384712.08 frames.], batch size: 19, lr: 6.70e-04
2022-05-27 03:20:28,428 INFO [train.py:842] (3/4) Epoch 8, batch 800, loss[loss=0.2213, simple_loss=0.3006, pruned_loss=0.07103, over 6379.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3016, pruned_loss=0.07366, over 1390005.97 frames.], batch size: 38, lr: 6.69e-04
2022-05-27 03:21:07,293 INFO [train.py:842] (3/4) Epoch 8, batch 850, loss[loss=0.1627, simple_loss=0.2475, pruned_loss=0.03893, over 7424.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2992, pruned_loss=0.07273, over 1398766.73 frames.], batch size: 18, lr: 6.69e-04
2022-05-27 03:21:46,365 INFO [train.py:842] (3/4) Epoch 8, batch 900, loss[loss=0.2436, simple_loss=0.3189, pruned_loss=0.08412, over 6786.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2992, pruned_loss=0.07275, over 1398679.27 frames.], batch size: 31, lr: 6.69e-04
2022-05-27 03:22:24,860 INFO [train.py:842] (3/4) Epoch 8, batch 950, loss[loss=0.2219, simple_loss=0.3078, pruned_loss=0.06802, over 7233.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2994, pruned_loss=0.07259, over 1405004.01 frames.], batch size: 20, lr: 6.69e-04
2022-05-27 03:23:03,647 INFO [train.py:842] (3/4) Epoch 8, batch 1000, loss[loss=0.283, simple_loss=0.3463, pruned_loss=0.1099, over 7229.00 frames.], tot_loss[loss=0.2214, simple_loss=0.299, pruned_loss=0.07196, over 1408693.47 frames.], batch size: 21, lr: 6.68e-04
2022-05-27 03:23:42,260 INFO [train.py:842] (3/4) Epoch 8, batch 1050, loss[loss=0.1695, simple_loss=0.2444, pruned_loss=0.0473, over 7149.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3003, pruned_loss=0.07322, over 1406902.86 frames.], batch size: 17, lr: 6.68e-04
2022-05-27 03:24:21,162 INFO [train.py:842] (3/4) Epoch 8, batch 1100, loss[loss=0.1979, simple_loss=0.2852, pruned_loss=0.05534, over 7201.00 frames.], tot_loss[loss=0.221, simple_loss=0.2985, pruned_loss=0.07174, over 1410938.60 frames.], batch size: 22, lr: 6.68e-04
2022-05-27 03:24:59,660 INFO [train.py:842] (3/4) Epoch 8, batch 1150, loss[loss=0.2743, simple_loss=0.3309, pruned_loss=0.1089, over 5094.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2993, pruned_loss=0.07152, over 1416534.32 frames.], batch size: 52, lr: 6.68e-04
2022-05-27 03:25:38,522 INFO [train.py:842] (3/4) Epoch 8, batch 1200, loss[loss=0.2134, simple_loss=0.3044, pruned_loss=0.06116, over 7148.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2995, pruned_loss=0.07186, over 1420057.05 frames.], batch size: 20, lr: 6.67e-04
2022-05-27 03:26:16,975 INFO [train.py:842] (3/4) Epoch 8, batch 1250, loss[loss=0.2277, simple_loss=0.3039, pruned_loss=0.07572, over 7297.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2988, pruned_loss=0.07189, over 1419470.77 frames.], batch size: 18, lr: 6.67e-04
2022-05-27 03:26:55,538 INFO [train.py:842] (3/4) Epoch 8, batch 1300, loss[loss=0.2323, simple_loss=0.3012, pruned_loss=0.08176, over 7150.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3003, pruned_loss=0.07317, over 1416685.91 frames.], batch size: 20, lr: 6.67e-04
2022-05-27 03:27:34,053 INFO [train.py:842] (3/4) Epoch 8, batch 1350, loss[loss=0.2037, simple_loss=0.2738, pruned_loss=0.06681, over 7149.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3008, pruned_loss=0.07328, over 1416438.13 frames.], batch size: 19, lr: 6.67e-04
2022-05-27 03:28:12,697 INFO [train.py:842] (3/4) Epoch 8, batch 1400, loss[loss=0.1952, simple_loss=0.2697, pruned_loss=0.06035, over 7273.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3002, pruned_loss=0.07251, over 1416976.38 frames.], batch size: 18, lr: 6.66e-04
2022-05-27 03:28:51,223 INFO [train.py:842] (3/4) Epoch 8, batch 1450, loss[loss=0.1628, simple_loss=0.244, pruned_loss=0.04082, over 7167.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3002, pruned_loss=0.07224, over 1416339.86 frames.], batch size: 18, lr: 6.66e-04
2022-05-27 03:29:30,497 INFO [train.py:842] (3/4) Epoch 8, batch 1500, loss[loss=0.2026, simple_loss=0.2706, pruned_loss=0.0673, over 7414.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2998, pruned_loss=0.07259, over 1416133.48 frames.], batch size: 18, lr: 6.66e-04
2022-05-27 03:30:08,998 INFO [train.py:842] (3/4) Epoch 8, batch 1550, loss[loss=0.257, simple_loss=0.3259, pruned_loss=0.09406, over 7199.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3018, pruned_loss=0.07418, over 1421512.85 frames.], batch size: 22, lr: 6.66e-04
2022-05-27 03:30:47,990 INFO [train.py:842] (3/4) Epoch 8, batch 1600, loss[loss=0.1897, simple_loss=0.28, pruned_loss=0.04973, over 6366.00 frames.], tot_loss[loss=0.2266, simple_loss=0.303, pruned_loss=0.07508, over 1421620.76 frames.], batch size: 38, lr: 6.65e-04
2022-05-27 03:31:26,468 INFO [train.py:842] (3/4) Epoch 8, batch 1650, loss[loss=0.2659, simple_loss=0.3402, pruned_loss=0.09582, over 7278.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3028, pruned_loss=0.0752, over 1419362.27 frames.], batch size: 24, lr: 6.65e-04
2022-05-27 03:32:05,107 INFO [train.py:842] (3/4) Epoch 8, batch 1700, loss[loss=0.2319, simple_loss=0.3139, pruned_loss=0.07493, over 7320.00 frames.], tot_loss[loss=0.226, simple_loss=0.3031, pruned_loss=0.07445, over 1420304.29 frames.], batch size: 21, lr: 6.65e-04
2022-05-27 03:32:43,709 INFO [train.py:842] (3/4) Epoch 8, batch 1750, loss[loss=0.235, simple_loss=0.3124, pruned_loss=0.07879, over 7348.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3037, pruned_loss=0.07489, over 1420214.58 frames.], batch size: 22, lr: 6.65e-04
2022-05-27 03:33:22,864 INFO [train.py:842] (3/4) Epoch 8, batch 1800, loss[loss=0.2057, simple_loss=0.2814, pruned_loss=0.06506, over 7333.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3011, pruned_loss=0.07337, over 1421805.25 frames.], batch size: 22, lr: 6.64e-04
2022-05-27 03:34:01,568 INFO [train.py:842] (3/4) Epoch 8, batch 1850, loss[loss=0.2108, simple_loss=0.2934, pruned_loss=0.06416, over 7223.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3027, pruned_loss=0.07433, over 1423854.95 frames.], batch size: 20, lr: 6.64e-04
2022-05-27 03:34:40,372 INFO [train.py:842] (3/4) Epoch 8, batch 1900, loss[loss=0.2961, simple_loss=0.3585, pruned_loss=0.1168, over 7268.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3018, pruned_loss=0.07431, over 1422739.48 frames.], batch size: 25, lr: 6.64e-04
2022-05-27 03:35:19,054 INFO [train.py:842] (3/4) Epoch 8, batch 1950, loss[loss=0.223, simple_loss=0.284, pruned_loss=0.08097, over 7004.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3014, pruned_loss=0.07403, over 1427434.95 frames.], batch size: 16, lr: 6.64e-04
2022-05-27 03:35:57,676 INFO [train.py:842] (3/4) Epoch 8, batch 2000, loss[loss=0.2062, simple_loss=0.291, pruned_loss=0.06072, over 7115.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3005, pruned_loss=0.07317, over 1428225.85 frames.], batch size: 21, lr: 6.63e-04
2022-05-27 03:36:36,055 INFO [train.py:842] (3/4) Epoch 8, batch 2050, loss[loss=0.2653, simple_loss=0.3248, pruned_loss=0.1029, over 4864.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3027, pruned_loss=0.07476, over 1421467.52 frames.], batch size: 52, lr: 6.63e-04
2022-05-27 03:37:14,887 INFO [train.py:842] (3/4) Epoch 8, batch 2100, loss[loss=0.2538, simple_loss=0.3351, pruned_loss=0.08621, over 7228.00 frames.], tot_loss[loss=0.2238, simple_loss=0.301, pruned_loss=0.07324, over 1418424.06 frames.], batch size: 20, lr: 6.63e-04
2022-05-27 03:37:53,572 INFO [train.py:842] (3/4) Epoch 8, batch 2150, loss[loss=0.2878, simple_loss=0.3584, pruned_loss=0.1086, over 7203.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3012, pruned_loss=0.07358, over 1418919.07 frames.], batch size: 22, lr: 6.63e-04
2022-05-27 03:38:32,400 INFO [train.py:842] (3/4) Epoch 8, batch 2200, loss[loss=0.2158, simple_loss=0.2902, pruned_loss=0.07068, over 7296.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2989, pruned_loss=0.07216, over 1418407.59 frames.], batch size: 24, lr: 6.62e-04
2022-05-27 03:39:11,115 INFO [train.py:842] (3/4) Epoch 8, batch 2250, loss[loss=0.2071, simple_loss=0.2876, pruned_loss=0.06326, over 7189.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2992, pruned_loss=0.07286, over 1412910.13 frames.], batch size: 23, lr: 6.62e-04
2022-05-27 03:39:49,981 INFO [train.py:842] (3/4) Epoch 8, batch 2300, loss[loss=0.2001, simple_loss=0.2803, pruned_loss=0.05993, over 7419.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2982, pruned_loss=0.07174, over 1413629.45 frames.], batch size: 18, lr: 6.62e-04
2022-05-27 03:40:28,573 INFO [train.py:842] (3/4) Epoch 8, batch 2350, loss[loss=0.2309, simple_loss=0.3063, pruned_loss=0.07775, over 7066.00 frames.], tot_loss[loss=0.2217, simple_loss=0.299, pruned_loss=0.07218, over 1414012.68 frames.], batch size: 18, lr: 6.62e-04
2022-05-27 03:41:07,416 INFO [train.py:842] (3/4) Epoch 8, batch 2400, loss[loss=0.2022, simple_loss=0.2817, pruned_loss=0.06135, over 7262.00 frames.], tot_loss[loss=0.221, simple_loss=0.2985, pruned_loss=0.07175, over 1417559.09 frames.], batch size: 19, lr: 6.61e-04
2022-05-27 03:41:46,090 INFO [train.py:842] (3/4) Epoch 8, batch 2450, loss[loss=0.2524, simple_loss=0.335, pruned_loss=0.08495, over 7299.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2994, pruned_loss=0.07201, over 1423842.13 frames.], batch size: 24, lr: 6.61e-04
2022-05-27 03:42:24,992 INFO [train.py:842] (3/4) Epoch 8, batch 2500, loss[loss=0.1989, simple_loss=0.2824, pruned_loss=0.05775, over 7314.00 frames.], tot_loss[loss=0.2236, simple_loss=0.301, pruned_loss=0.07311, over 1422265.57 frames.], batch size: 21, lr: 6.61e-04
2022-05-27 03:43:03,696 INFO [train.py:842] (3/4) Epoch 8, batch 2550, loss[loss=0.1998, simple_loss=0.279, pruned_loss=0.0603, over 7354.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3006, pruned_loss=0.07352, over 1426162.26 frames.], batch size: 19, lr: 6.61e-04
2022-05-27 03:43:43,046 INFO [train.py:842] (3/4) Epoch 8, batch 2600, loss[loss=0.2219, simple_loss=0.2912, pruned_loss=0.07625, over 6829.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3001, pruned_loss=0.07288, over 1425909.38 frames.], batch size: 15, lr: 6.60e-04
2022-05-27 03:44:21,516 INFO [train.py:842] (3/4) Epoch 8, batch 2650, loss[loss=0.2106, simple_loss=0.2875, pruned_loss=0.06684, over 7105.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2999, pruned_loss=0.07278, over 1427152.09 frames.], batch size: 21, lr: 6.60e-04
2022-05-27 03:45:00,455 INFO [train.py:842] (3/4) Epoch 8, batch 2700, loss[loss=0.2217, simple_loss=0.2932, pruned_loss=0.07504, over 6839.00 frames.], tot_loss[loss=0.2216, simple_loss=0.299, pruned_loss=0.07212, over 1429141.16 frames.], batch size: 15, lr: 6.60e-04
2022-05-27 03:45:39,002 INFO [train.py:842] (3/4) Epoch 8, batch 2750, loss[loss=0.1655, simple_loss=0.2429, pruned_loss=0.04408, over 7001.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2982, pruned_loss=0.07162, over 1427228.57 frames.], batch size: 16, lr: 6.60e-04
2022-05-27 03:46:17,909 INFO [train.py:842] (3/4) Epoch 8, batch 2800, loss[loss=0.2347, simple_loss=0.3092, pruned_loss=0.08013, over 7148.00 frames.], tot_loss[loss=0.2214, simple_loss=0.2988, pruned_loss=0.07195, over 1428283.15 frames.], batch size: 20, lr: 6.60e-04
2022-05-27 03:46:56,417 INFO [train.py:842] (3/4) Epoch 8, batch 2850, loss[loss=0.2124, simple_loss=0.297, pruned_loss=0.06391, over 7223.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2991, pruned_loss=0.07166, over 1426245.70 frames.], batch size: 22, lr: 6.59e-04
2022-05-27 03:47:35,368 INFO [train.py:842] (3/4) Epoch 8, batch 2900, loss[loss=0.2528, simple_loss=0.3198, pruned_loss=0.09292, over 7133.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2992, pruned_loss=0.07126, over 1425590.88 frames.], batch size: 17, lr: 6.59e-04
2022-05-27 03:48:13,890 INFO [train.py:842] (3/4) Epoch 8, batch 2950, loss[loss=0.1791, simple_loss=0.2658, pruned_loss=0.04618, over 7066.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2977, pruned_loss=0.07059, over 1424787.13 frames.], batch size: 18, lr: 6.59e-04
2022-05-27 03:48:52,478 INFO [train.py:842] (3/4) Epoch 8, batch 3000, loss[loss=0.2478, simple_loss=0.3156, pruned_loss=0.08993, over 5169.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2994, pruned_loss=0.07186, over 1421765.32 frames.], batch size: 52, lr: 6.59e-04
2022-05-27 03:48:52,479 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 03:49:01,707 INFO [train.py:871] (3/4) Epoch 8, validation: loss=0.1787, simple_loss=0.2793, pruned_loss=0.03905, over 868885.00 frames.
2022-05-27 03:49:40,139 INFO [train.py:842] (3/4) Epoch 8, batch 3050, loss[loss=0.2357, simple_loss=0.3114, pruned_loss=0.07994, over 6499.00 frames.], tot_loss[loss=0.2219, simple_loss=0.299, pruned_loss=0.07242, over 1415017.79 frames.], batch size: 38, lr: 6.58e-04
2022-05-27 03:50:18,980 INFO [train.py:842] (3/4) Epoch 8, batch 3100, loss[loss=0.2325, simple_loss=0.3046, pruned_loss=0.08016, over 7248.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2987, pruned_loss=0.0721, over 1419334.68 frames.], batch size: 19, lr: 6.58e-04
2022-05-27 03:50:57,755 INFO [train.py:842] (3/4) Epoch 8, batch 3150, loss[loss=0.2498, simple_loss=0.316, pruned_loss=0.0918, over 7436.00 frames.], tot_loss[loss=0.2203, simple_loss=0.297, pruned_loss=0.07182, over 1421183.33 frames.], batch size: 20, lr: 6.58e-04
2022-05-27 03:51:36,884 INFO [train.py:842] (3/4) Epoch 8, batch 3200, loss[loss=0.2166, simple_loss=0.311, pruned_loss=0.06107, over 7441.00 frames.], tot_loss[loss=0.2219, simple_loss=0.2984, pruned_loss=0.07273, over 1423831.18 frames.], batch size: 20, lr: 6.58e-04
2022-05-27 03:52:15,369 INFO [train.py:842] (3/4) Epoch 8, batch 3250, loss[loss=0.216, simple_loss=0.2934, pruned_loss=0.06932, over 7061.00 frames.], tot_loss[loss=0.224, simple_loss=0.3001, pruned_loss=0.07391, over 1423710.68 frames.], batch size: 28, lr: 6.57e-04
2022-05-27 03:52:54,466 INFO [train.py:842] (3/4) Epoch 8, batch 3300, loss[loss=0.2531, simple_loss=0.3289, pruned_loss=0.0886, over 6745.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3008, pruned_loss=0.07432, over 1421809.69 frames.], batch size: 31, lr: 6.57e-04
2022-05-27 03:53:33,008 INFO [train.py:842] (3/4) Epoch 8, batch 3350, loss[loss=0.2029, simple_loss=0.2924, pruned_loss=0.05671, over 7435.00 frames.], tot_loss[loss=0.224, simple_loss=0.3004, pruned_loss=0.07382, over 1420718.51 frames.], batch size: 20, lr: 6.57e-04
2022-05-27 03:54:11,884 INFO [train.py:842] (3/4) Epoch 8, batch 3400, loss[loss=0.3331, simple_loss=0.3849, pruned_loss=0.1406, over 6766.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3004, pruned_loss=0.07441, over 1418462.66 frames.], batch size: 31, lr: 6.57e-04
2022-05-27 03:54:50,304 INFO [train.py:842] (3/4) Epoch 8, batch 3450, loss[loss=0.3262, simple_loss=0.3603, pruned_loss=0.1461, over 7395.00 frames.], tot_loss[loss=0.226, simple_loss=0.302, pruned_loss=0.07502, over 1421755.30 frames.], batch size: 18, lr: 6.56e-04
2022-05-27 03:55:29,177 INFO [train.py:842] (3/4) Epoch 8, batch 3500, loss[loss=0.2522, simple_loss=0.3224, pruned_loss=0.09103, over 7362.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3025, pruned_loss=0.07506, over 1422096.54 frames.], batch size: 23, lr: 6.56e-04
2022-05-27 03:56:07,716 INFO [train.py:842] (3/4) Epoch 8, batch 3550, loss[loss=0.256, simple_loss=0.3204, pruned_loss=0.09581, over 7261.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3011, pruned_loss=0.07392, over 1423488.14 frames.], batch size: 19, lr: 6.56e-04
2022-05-27 03:56:46,653 INFO [train.py:842] (3/4) Epoch 8, batch 3600, loss[loss=0.1888, simple_loss=0.2636, pruned_loss=0.05694, over 7274.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2998, pruned_loss=0.0733, over 1422086.28 frames.], batch size: 17, lr: 6.56e-04
2022-05-27 03:57:25,070 INFO [train.py:842] (3/4) Epoch 8, batch 3650, loss[loss=0.2028, simple_loss=0.2887, pruned_loss=0.05845, over 7410.00 frames.], tot_loss[loss=0.2248, simple_loss=0.301, pruned_loss=0.07426, over 1416493.05 frames.], batch size: 21, lr: 6.55e-04
2022-05-27 03:58:03,910 INFO [train.py:842] (3/4) Epoch 8, batch 3700, loss[loss=0.1979, simple_loss=0.2888, pruned_loss=0.05353, over 7332.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3001, pruned_loss=0.07344, over 1419057.44 frames.], batch size: 22, lr: 6.55e-04
2022-05-27 03:58:42,486 INFO [train.py:842] (3/4) Epoch 8, batch 3750, loss[loss=0.2934, simple_loss=0.3527, pruned_loss=0.117, over 7384.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2995, pruned_loss=0.07289, over 1417683.29 frames.], batch size: 23, lr: 6.55e-04
2022-05-27 03:59:21,196 INFO [train.py:842] (3/4) Epoch 8, batch 3800, loss[loss=0.224, simple_loss=0.3008, pruned_loss=0.07363, over 7202.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3005, pruned_loss=0.0731, over 1418296.91 frames.], batch size: 22, lr: 6.55e-04
2022-05-27 03:59:59,638 INFO [train.py:842] (3/4) Epoch 8, batch 3850, loss[loss=0.2863, simple_loss=0.3447, pruned_loss=0.114, over 7315.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3015, pruned_loss=0.07384, over 1417999.34 frames.], batch size: 25, lr: 6.54e-04
2022-05-27 04:00:38,577 INFO [train.py:842] (3/4) Epoch 8, batch 3900, loss[loss=0.1951, simple_loss=0.2747, pruned_loss=0.05775, over 7068.00 frames.], tot_loss[loss=0.224, simple_loss=0.3005, pruned_loss=0.07379, over 1421804.39 frames.], batch size: 18, lr: 6.54e-04
2022-05-27 04:01:17,114 INFO [train.py:842] (3/4) Epoch 8, batch 3950, loss[loss=0.2131, simple_loss=0.3027, pruned_loss=0.06177, over 7205.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2997, pruned_loss=0.07269, over 1424022.79 frames.], batch size: 22, lr: 6.54e-04
2022-05-27 04:01:55,879 INFO [train.py:842] (3/4) Epoch 8, batch 4000, loss[loss=0.2196, simple_loss=0.3007, pruned_loss=0.06922, over 7417.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3005, pruned_loss=0.07324, over 1423307.26 frames.], batch size: 21, lr: 6.54e-04
2022-05-27 04:02:34,572 INFO [train.py:842] (3/4) Epoch 8, batch 4050, loss[loss=0.2103, simple_loss=0.276, pruned_loss=0.07229, over 6999.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3009, pruned_loss=0.07337, over 1424252.05 frames.], batch size: 16, lr: 6.53e-04
2022-05-27 04:03:13,369 INFO [train.py:842] (3/4) Epoch 8, batch 4100, loss[loss=0.2745, simple_loss=0.3506, pruned_loss=0.09923, over 7381.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3012, pruned_loss=0.07396, over 1418387.44 frames.], batch size: 23, lr: 6.53e-04
2022-05-27 04:03:51,874 INFO [train.py:842] (3/4) Epoch 8, batch 4150, loss[loss=0.2666, simple_loss=0.3448, pruned_loss=0.09423, over 6709.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3004, pruned_loss=0.07346, over 1418748.25 frames.], batch size: 31, lr: 6.53e-04
2022-05-27 04:04:30,528 INFO [train.py:842] (3/4) Epoch 8, batch 4200, loss[loss=0.1862, simple_loss=0.268, pruned_loss=0.05223, over 7065.00 frames.], tot_loss[loss=0.223, simple_loss=0.2998, pruned_loss=0.07308, over 1418849.36 frames.], batch size: 18, lr: 6.53e-04
2022-05-27 04:05:09,123 INFO [train.py:842] (3/4) Epoch 8, batch 4250, loss[loss=0.2979, simple_loss=0.3629, pruned_loss=0.1164, over 7203.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3021, pruned_loss=0.07421, over 1417972.07 frames.], batch size: 26, lr: 6.53e-04
2022-05-27 04:05:47,944 INFO [train.py:842] (3/4) Epoch 8, batch 4300, loss[loss=0.2145, simple_loss=0.2978, pruned_loss=0.06556, over 7051.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3012, pruned_loss=0.07321, over 1424953.16 frames.], batch size: 28, lr: 6.52e-04
2022-05-27 04:06:26,330 INFO [train.py:842] (3/4) Epoch 8, batch 4350, loss[loss=0.2315, simple_loss=0.3123, pruned_loss=0.07533, over 7205.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3004, pruned_loss=0.07272, over 1423447.55 frames.], batch size: 22, lr: 6.52e-04
2022-05-27 04:07:05,499 INFO [train.py:842] (3/4) Epoch 8, batch 4400, loss[loss=0.2005, simple_loss=0.2781, pruned_loss=0.06151, over 7169.00 frames.], tot_loss[loss=0.2215, simple_loss=0.299, pruned_loss=0.07198, over 1422274.38 frames.], batch size: 19, lr: 6.52e-04
2022-05-27 04:07:43,984 INFO [train.py:842] (3/4) Epoch 8, batch 4450, loss[loss=0.2507, simple_loss=0.3283, pruned_loss=0.08654, over 7344.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2975, pruned_loss=0.07096, over 1422806.91 frames.], batch size: 22, lr: 6.52e-04
2022-05-27 04:08:22,909 INFO [train.py:842] (3/4) Epoch 8, batch 4500, loss[loss=0.199, simple_loss=0.2638, pruned_loss=0.06715, over 7133.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2968, pruned_loss=0.07092, over 1423937.70 frames.], batch size: 17, lr: 6.51e-04
2022-05-27 04:09:01,456 INFO [train.py:842] (3/4) Epoch 8, batch 4550, loss[loss=0.2276, simple_loss=0.2993, pruned_loss=0.07792, over 7259.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2981, pruned_loss=0.0714, over 1426340.05 frames.], batch size: 19, lr: 6.51e-04
2022-05-27 04:09:40,159 INFO [train.py:842] (3/4) Epoch 8, batch 4600, loss[loss=0.2032, simple_loss=0.2853, pruned_loss=0.06051, over 6871.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3005, pruned_loss=0.07281, over 1424425.12 frames.], batch size: 31, lr: 6.51e-04
2022-05-27 04:10:18,856 INFO [train.py:842] (3/4) Epoch 8, batch 4650, loss[loss=0.2598, simple_loss=0.3299, pruned_loss=0.09483, over 7092.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3003, pruned_loss=0.07299, over 1421893.28 frames.], batch size: 28, lr: 6.51e-04
2022-05-27 04:10:57,630 INFO [train.py:842] (3/4) Epoch 8, batch 4700, loss[loss=0.2041, simple_loss=0.2877, pruned_loss=0.06023, over 7317.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2989, pruned_loss=0.0723, over 1423087.02 frames.], batch size: 25, lr: 6.50e-04
2022-05-27 04:11:36,348 INFO [train.py:842] (3/4) Epoch 8, batch 4750, loss[loss=0.2211, simple_loss=0.2887, pruned_loss=0.07677, over 7430.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2997, pruned_loss=0.07285, over 1420072.78 frames.], batch size: 20, lr: 6.50e-04
2022-05-27 04:12:15,135 INFO [train.py:842] (3/4) Epoch 8, batch 4800, loss[loss=0.2307, simple_loss=0.3146, pruned_loss=0.07335, over 7173.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3004, pruned_loss=0.07322, over 1422336.85 frames.], batch size: 26, lr: 6.50e-04
2022-05-27 04:12:53,776 INFO [train.py:842] (3/4) Epoch 8, batch 4850, loss[loss=0.1964, simple_loss=0.2769, pruned_loss=0.05793, over 7354.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2988, pruned_loss=0.07205, over 1428047.42 frames.], batch size: 19, lr: 6.50e-04
2022-05-27 04:13:32,381 INFO [train.py:842] (3/4) Epoch 8, batch 4900, loss[loss=0.2285, simple_loss=0.3087, pruned_loss=0.07418, over 6699.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2987, pruned_loss=0.07192, over 1425711.64 frames.], batch size: 31, lr: 6.49e-04
2022-05-27 04:14:10,925 INFO [train.py:842] (3/4) Epoch 8, batch 4950, loss[loss=0.2044, simple_loss=0.2829, pruned_loss=0.06297, over 7064.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2979, pruned_loss=0.07162, over 1424622.45 frames.], batch size: 18, lr: 6.49e-04
2022-05-27 04:14:50,207 INFO [train.py:842] (3/4) Epoch 8, batch 5000, loss[loss=0.1859, simple_loss=0.2687, pruned_loss=0.05151, over 7260.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2975, pruned_loss=0.07178, over 1420180.66 frames.], batch size: 19, lr: 6.49e-04
2022-05-27 04:15:28,676 INFO [train.py:842] (3/4) Epoch 8, batch 5050, loss[loss=0.2118, simple_loss=0.2969, pruned_loss=0.06333, over 6250.00 frames.], tot_loss[loss=0.224, simple_loss=0.3002, pruned_loss=0.0739, over 1419955.51 frames.], batch size: 37, lr: 6.49e-04
2022-05-27 04:16:07,699 INFO [train.py:842] (3/4) Epoch 8, batch 5100, loss[loss=0.1996, simple_loss=0.2656, pruned_loss=0.06673, over 7267.00 frames.], tot_loss[loss=0.223, simple_loss=0.2994, pruned_loss=0.07336, over 1425184.55 frames.], batch size: 17, lr: 6.49e-04
2022-05-27 04:16:46,301 INFO [train.py:842] (3/4) Epoch 8, batch 5150, loss[loss=0.2002, simple_loss=0.2834, pruned_loss=0.05854, over 7368.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2992, pruned_loss=0.07293, over 1427258.72 frames.], batch size: 19, lr: 6.48e-04
2022-05-27 04:17:25,425 INFO [train.py:842] (3/4) Epoch 8, batch 5200, loss[loss=0.2339, simple_loss=0.3139, pruned_loss=0.077, over 7268.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2988, pruned_loss=0.0723, over 1425298.08 frames.], batch size: 19, lr: 6.48e-04
2022-05-27 04:18:03,680 INFO [train.py:842] (3/4) Epoch 8, batch 5250, loss[loss=0.2262, simple_loss=0.2998, pruned_loss=0.07628, over 7164.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3001, pruned_loss=0.07352, over 1418816.91 frames.], batch size: 19, lr: 6.48e-04
2022-05-27 04:18:42,894 INFO [train.py:842] (3/4) Epoch 8, batch 5300, loss[loss=0.184, simple_loss=0.2617, pruned_loss=0.05318, over 7159.00 frames.], tot_loss[loss=0.223, simple_loss=0.3, pruned_loss=0.07297, over 1417288.50 frames.], batch size: 19, lr: 6.48e-04
2022-05-27 04:19:21,459 INFO [train.py:842] (3/4) Epoch 8, batch 5350, loss[loss=0.2112, simple_loss=0.2871, pruned_loss=0.06762, over 7156.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2988, pruned_loss=0.07209, over 1417838.00 frames.], batch size: 19, lr: 6.47e-04
2022-05-27 04:20:00,560 INFO [train.py:842] (3/4) Epoch 8, batch 5400, loss[loss=0.2001, simple_loss=0.2874, pruned_loss=0.05639, over 7317.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2991, pruned_loss=0.07287, over 1416085.72 frames.], batch size: 21, lr: 6.47e-04
2022-05-27 04:20:39,246 INFO [train.py:842] (3/4) Epoch 8, batch 5450, loss[loss=0.1738, simple_loss=0.2558, pruned_loss=0.04588, over 7352.00 frames.], tot_loss[loss=0.2226, simple_loss=0.299, pruned_loss=0.07307, over 1417194.94 frames.], batch size: 19, lr: 6.47e-04
2022-05-27 04:21:18,490 INFO [train.py:842] (3/4) Epoch 8, batch 5500, loss[loss=0.1789, simple_loss=0.2613, pruned_loss=0.04823, over 7364.00 frames.], tot_loss[loss=0.222, simple_loss=0.2984, pruned_loss=0.07284, over 1418894.79 frames.], batch size: 19, lr: 6.47e-04
2022-05-27 04:21:56,777 INFO [train.py:842] (3/4) Epoch 8, batch 5550, loss[loss=0.246, simple_loss=0.3169, pruned_loss=0.08756, over 7149.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2991, pruned_loss=0.07322, over 1414751.67 frames.], batch size: 20, lr: 6.46e-04
2022-05-27 04:22:35,517 INFO [train.py:842] (3/4) Epoch 8, batch 5600, loss[loss=0.2054, simple_loss=0.2732, pruned_loss=0.06882, over 7268.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2998, pruned_loss=0.07322, over 1415171.51 frames.], batch size: 18, lr: 6.46e-04
2022-05-27 04:23:14,181 INFO [train.py:842] (3/4) Epoch 8, batch 5650, loss[loss=0.1964, simple_loss=0.2847, pruned_loss=0.05403, over 7323.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2986, pruned_loss=0.07224, over 1416207.34 frames.], batch size: 22, lr: 6.46e-04
2022-05-27 04:23:53,487 INFO [train.py:842] (3/4) Epoch 8, batch 5700, loss[loss=0.2092, simple_loss=0.2952, pruned_loss=0.06158, over 7228.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2974, pruned_loss=0.07151, over 1422323.73 frames.], batch size: 20, lr: 6.46e-04
2022-05-27 04:24:32,081 INFO [train.py:842] (3/4) Epoch 8, batch 5750, loss[loss=0.1945, simple_loss=0.2803, pruned_loss=0.05435, over 7067.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2968, pruned_loss=0.07129, over 1426131.41 frames.], batch size: 18, lr: 6.46e-04
2022-05-27 04:25:10,897 INFO [train.py:842] (3/4) Epoch 8, batch 5800, loss[loss=0.1863, simple_loss=0.2633, pruned_loss=0.0547, over 7282.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2967, pruned_loss=0.07087, over 1425209.60 frames.], batch size: 17, lr: 6.45e-04
2022-05-27 04:25:49,430 INFO [train.py:842] (3/4) Epoch 8, batch 5850, loss[loss=0.2372, simple_loss=0.3231, pruned_loss=0.07564, over 7239.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2978, pruned_loss=0.07145, over 1427122.10 frames.], batch size: 20, lr: 6.45e-04
2022-05-27 04:26:28,998 INFO [train.py:842] (3/4) Epoch 8, batch 5900, loss[loss=0.199, simple_loss=0.2742, pruned_loss=0.06193, over 7285.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2981, pruned_loss=0.07165, over 1425937.74 frames.], batch size: 17, lr: 6.45e-04
2022-05-27 04:27:07,437 INFO [train.py:842] (3/4) Epoch 8, batch 5950, loss[loss=0.1721, simple_loss=0.2524, pruned_loss=0.04593, over 7275.00 frames.], tot_loss[loss=0.2214, simple_loss=0.2987, pruned_loss=0.07202, over 1424851.73 frames.], batch size: 17, lr: 6.45e-04
2022-05-27 04:27:46,634 INFO [train.py:842] (3/4) Epoch 8, batch 6000, loss[loss=0.222, simple_loss=0.3082, pruned_loss=0.06787, over 7319.00 frames.], tot_loss[loss=0.2209, simple_loss=0.2981, pruned_loss=0.07179, over 1425849.77 frames.], batch size: 21, lr: 6.44e-04
2022-05-27 04:27:46,634 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 04:27:55,933 INFO [train.py:871] (3/4) Epoch 8, validation: loss=0.1785, simple_loss=0.2788, pruned_loss=0.03907, over 868885.00 frames.
2022-05-27 04:28:34,553 INFO [train.py:842] (3/4) Epoch 8, batch 6050, loss[loss=0.1971, simple_loss=0.2777, pruned_loss=0.05824, over 7366.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2982, pruned_loss=0.07222, over 1426092.12 frames.], batch size: 19, lr: 6.44e-04
2022-05-27 04:29:13,575 INFO [train.py:842] (3/4) Epoch 8, batch 6100, loss[loss=0.2036, simple_loss=0.2772, pruned_loss=0.06503, over 7165.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2979, pruned_loss=0.07215, over 1428883.73 frames.], batch size: 18, lr: 6.44e-04
2022-05-27 04:29:52,017 INFO [train.py:842] (3/4) Epoch 8, batch 6150, loss[loss=0.1632, simple_loss=0.2462, pruned_loss=0.04009, over 7264.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2994, pruned_loss=0.07282, over 1427881.87 frames.], batch size: 18, lr: 6.44e-04
2022-05-27 04:30:30,813 INFO [train.py:842] (3/4) Epoch 8, batch 6200, loss[loss=0.2533, simple_loss=0.3321, pruned_loss=0.08723, over 7272.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2983, pruned_loss=0.07237, over 1427417.50 frames.], batch size: 25, lr: 6.43e-04
2022-05-27 04:31:09,320 INFO [train.py:842] (3/4) Epoch 8, batch 6250, loss[loss=0.2183, simple_loss=0.3051, pruned_loss=0.0657, over 7212.00 frames.], tot_loss[loss=0.2219, simple_loss=0.2988, pruned_loss=0.07254, over 1426537.95 frames.], batch size: 22, lr: 6.43e-04
2022-05-27 04:31:47,883 INFO [train.py:842] (3/4) Epoch 8, batch 6300, loss[loss=0.2725, simple_loss=0.3573, pruned_loss=0.09388, over 7195.00 frames.], tot_loss[loss=0.2219, simple_loss=0.2992, pruned_loss=0.07226, over 1426332.94 frames.], batch size: 23, lr: 6.43e-04
2022-05-27 04:32:26,546 INFO [train.py:842] (3/4) Epoch 8, batch 6350, loss[loss=0.1772, simple_loss=0.2528, pruned_loss=0.05084, over 7201.00 frames.], tot_loss[loss=0.221, simple_loss=0.2985, pruned_loss=0.07171, over 1426679.36 frames.], batch size: 16, lr: 6.43e-04
2022-05-27 04:33:05,977 INFO [train.py:842] (3/4) Epoch 8, batch 6400, loss[loss=0.2496, simple_loss=0.3133, pruned_loss=0.09297, over 7111.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3002, pruned_loss=0.07372, over 1423194.27 frames.], batch size: 21, lr: 6.43e-04
2022-05-27 04:33:44,699 INFO [train.py:842] (3/4) Epoch 8, batch 6450, loss[loss=0.2074, simple_loss=0.2724, pruned_loss=0.07123, over 7290.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2981, pruned_loss=0.07275, over 1427996.57 frames.], batch size: 18, lr: 6.42e-04
2022-05-27 04:34:23,944 INFO [train.py:842] (3/4) Epoch 8, batch 6500, loss[loss=0.2335, simple_loss=0.3137, pruned_loss=0.07662, over 7048.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2969, pruned_loss=0.07205, over 1426587.67 frames.], batch size: 28, lr: 6.42e-04
2022-05-27 04:35:02,482 INFO [train.py:842] (3/4) Epoch 8, batch 6550, loss[loss=0.1819, simple_loss=0.2486, pruned_loss=0.05759, over 7015.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2976, pruned_loss=0.07171, over 1429029.66 frames.], batch size: 16, lr: 6.42e-04
2022-05-27 04:35:41,393 INFO [train.py:842] (3/4) Epoch 8, batch 6600, loss[loss=0.2232, simple_loss=0.3108, pruned_loss=0.06775, over 7163.00 frames.], tot_loss[loss=0.2199, simple_loss=0.297, pruned_loss=0.07138, over 1427862.98 frames.], batch size: 19, lr: 6.42e-04
2022-05-27 04:36:20,203 INFO [train.py:842] (3/4) Epoch 8, batch 6650, loss[loss=0.2094, simple_loss=0.304, pruned_loss=0.05735, over 7290.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2973, pruned_loss=0.07171, over 1425149.24 frames.], batch size: 24, lr: 6.41e-04
2022-05-27 04:36:59,109 INFO [train.py:842] (3/4) Epoch 8, batch 6700, loss[loss=0.2015, simple_loss=0.2815, pruned_loss=0.06078, over 6369.00 frames.], tot_loss[loss=0.2189, simple_loss=0.2963, pruned_loss=0.07076, over 1425632.50 frames.], batch size: 37, lr: 6.41e-04
2022-05-27 04:37:37,754 INFO [train.py:842] (3/4) Epoch 8, batch 6750, loss[loss=0.2553, simple_loss=0.3299, pruned_loss=0.09035, over 7342.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2953, pruned_loss=0.06958, over 1429503.07 frames.], batch size: 22, lr: 6.41e-04
2022-05-27 04:38:16,601 INFO [train.py:842] (3/4) Epoch 8, batch 6800, loss[loss=0.2377, simple_loss=0.3109, pruned_loss=0.08227, over 7316.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2951, pruned_loss=0.06964, over 1429334.75 frames.], batch size: 21, lr: 6.41e-04
2022-05-27 04:38:55,346 INFO [train.py:842] (3/4) Epoch 8, batch 6850, loss[loss=0.2592, simple_loss=0.3378, pruned_loss=0.09027, over 7243.00 frames.], tot_loss[loss=0.2172, simple_loss=0.295, pruned_loss=0.06966, over 1430911.09 frames.], batch size: 20, lr: 6.41e-04
2022-05-27 04:39:34,237 INFO [train.py:842] (3/4) Epoch 8, batch 6900, loss[loss=0.2379, simple_loss=0.3021, pruned_loss=0.08682, over 7292.00 frames.], tot_loss[loss=0.2186, simple_loss=0.2954, pruned_loss=0.07092, over 1430121.90 frames.], batch size: 18, lr: 6.40e-04
2022-05-27 04:40:12,659 INFO [train.py:842] (3/4) Epoch 8, batch 6950, loss[loss=0.2602, simple_loss=0.3213, pruned_loss=0.09952, over 7260.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2963, pruned_loss=0.07111, over 1426787.22 frames.], batch size: 19, lr: 6.40e-04
2022-05-27 04:40:51,462 INFO [train.py:842] (3/4) Epoch 8, batch 7000, loss[loss=0.2372, simple_loss=0.3129, pruned_loss=0.08076, over 7382.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2966, pruned_loss=0.07112, over 1427177.42 frames.], batch size: 23, lr: 6.40e-04
2022-05-27 04:41:30,082 INFO [train.py:842] (3/4) Epoch 8, batch 7050, loss[loss=0.1774, simple_loss=0.2626, pruned_loss=0.04605, over 7168.00 frames.], tot_loss[loss=0.2198, simple_loss=0.2968, pruned_loss=0.07145, over 1426385.40 frames.], batch size: 18, lr: 6.40e-04
2022-05-27 04:42:09,270 INFO [train.py:842] (3/4) Epoch 8, batch 7100, loss[loss=0.1995, simple_loss=0.279, pruned_loss=0.06002, over 7404.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2977, pruned_loss=0.07179, over 1424018.14 frames.], batch size: 18, lr: 6.39e-04
2022-05-27 04:42:47,958 INFO [train.py:842] (3/4) Epoch 8, batch 7150, loss[loss=0.243, simple_loss=0.3108, pruned_loss=0.08762, over 7276.00 frames.], tot_loss[loss=0.2223, simple_loss=0.299, pruned_loss=0.07282, over 1421309.31 frames.], batch size: 18, lr: 6.39e-04
2022-05-27 04:43:26,613 INFO [train.py:842] (3/4) Epoch 8, batch 7200, loss[loss=0.2159, simple_loss=0.3022, pruned_loss=0.06478, over 7139.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2968, pruned_loss=0.07171, over 1422056.72 frames.], batch size: 20, lr: 6.39e-04
2022-05-27 04:44:05,035 INFO [train.py:842] (3/4) Epoch 8, batch 7250, loss[loss=0.1785, simple_loss=0.2528, pruned_loss=0.05205, over 6799.00 frames.], tot_loss[loss=0.2198, simple_loss=0.2964, pruned_loss=0.07162, over 1418333.80 frames.], batch size: 15, lr: 6.39e-04
2022-05-27 04:44:43,933 INFO [train.py:842] (3/4) Epoch 8, batch 7300, loss[loss=0.271, simple_loss=0.3326, pruned_loss=0.1047, over 7165.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2958, pruned_loss=0.07137, over 1416206.97 frames.], batch size: 19, lr: 6.39e-04
2022-05-27 04:45:22,497 INFO [train.py:842] (3/4) Epoch 8, batch 7350, loss[loss=0.2075, simple_loss=0.3004, pruned_loss=0.0573, over 7390.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2964, pruned_loss=0.07164, over 1417351.16 frames.], batch size: 23, lr: 6.38e-04
2022-05-27 04:46:01,499 INFO [train.py:842] (3/4) Epoch 8, batch 7400, loss[loss=0.1717, simple_loss=0.241, pruned_loss=0.05115, over 7426.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2963, pruned_loss=0.07151, over 1415590.66 frames.], batch size: 18, lr: 6.38e-04
2022-05-27 04:46:40,149 INFO [train.py:842] (3/4) Epoch 8, batch 7450, loss[loss=0.2275, simple_loss=0.3085, pruned_loss=0.07321, over 7270.00 frames.], tot_loss[loss=0.2189, simple_loss=0.2957, pruned_loss=0.07107, over 1414155.66 frames.], batch size: 18, lr: 6.38e-04
2022-05-27 04:47:19,044 INFO [train.py:842] (3/4) Epoch 8, batch 7500, loss[loss=0.2214, simple_loss=0.2967, pruned_loss=0.073, over 7069.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2961, pruned_loss=0.07122, over 1415313.41 frames.], batch size: 18, lr: 6.38e-04
2022-05-27 04:47:57,399 INFO [train.py:842] (3/4) Epoch 8, batch 7550, loss[loss=0.2123, simple_loss=0.2899, pruned_loss=0.06736, over 7253.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2974, pruned_loss=0.07175, over 1414218.95 frames.], batch size: 19, lr: 6.37e-04
2022-05-27 04:48:36,294 INFO [train.py:842] (3/4) Epoch 8, batch 7600, loss[loss=0.2399, simple_loss=0.3003, pruned_loss=0.08974, over 7400.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2962, pruned_loss=0.07109, over 1416127.06 frames.], batch size: 18, lr: 6.37e-04
2022-05-27 04:49:15,207 INFO [train.py:842] (3/4) Epoch 8, batch 7650, loss[loss=0.2803, simple_loss=0.3398, pruned_loss=0.1103, over 7341.00 frames.], tot_loss[loss=0.2214, simple_loss=0.2981, pruned_loss=0.07229, over 1418310.47 frames.], batch size: 25, lr: 6.37e-04
2022-05-27 04:49:56,840 INFO [train.py:842] (3/4) Epoch 8, batch 7700, loss[loss=0.3009, simple_loss=0.3592, pruned_loss=0.1214, over 7313.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2993, pruned_loss=0.07264, over 1416235.59 frames.], batch size: 21, lr: 6.37e-04
2022-05-27 04:50:35,227 INFO [train.py:842] (3/4) Epoch 8, batch 7750, loss[loss=0.2193, simple_loss=0.2882, pruned_loss=0.07521, over 7426.00 frames.], tot_loss[loss=0.221, simple_loss=0.2988, pruned_loss=0.07162, over 1418442.49 frames.], batch size: 18, lr: 6.37e-04
2022-05-27 04:51:14,013 INFO [train.py:842] (3/4) Epoch 8, batch 7800, loss[loss=0.2449, simple_loss=0.3122, pruned_loss=0.08878, over 7352.00 frames.], tot_loss[loss=0.2201, simple_loss=0.298, pruned_loss=0.07106, over 1419334.94 frames.], batch size: 19, lr: 6.36e-04
2022-05-27 04:51:52,489 INFO [train.py:842] (3/4) Epoch 8, batch 7850, loss[loss=0.2338, simple_loss=0.3249, pruned_loss=0.07128, over 7204.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2987, pruned_loss=0.07139, over 1416501.27 frames.], batch size: 22, lr: 6.36e-04
2022-05-27 04:52:31,263 INFO [train.py:842] (3/4) Epoch 8, batch 7900, loss[loss=0.265, simple_loss=0.3246, pruned_loss=0.1027, over 7341.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2996, pruned_loss=0.07197, over 1418752.68 frames.], batch size: 25, lr: 6.36e-04
2022-05-27 04:53:09,858 INFO [train.py:842] (3/4) Epoch 8, batch 7950, loss[loss=0.2203, simple_loss=0.2959, pruned_loss=0.07236, over 7143.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2997, pruned_loss=0.07241, over 1420544.84 frames.], batch size: 20, lr: 6.36e-04
2022-05-27 04:53:49,257 INFO [train.py:842] (3/4) Epoch 8, batch 8000, loss[loss=0.2732, simple_loss=0.3386, pruned_loss=0.1039, over 7322.00 frames.], tot_loss[loss=0.2195, simple_loss=0.2976, pruned_loss=0.07068, over 1421894.28 frames.], batch size: 25, lr: 6.35e-04
2022-05-27 04:54:27,877 INFO [train.py:842] (3/4) Epoch 8, batch 8050, loss[loss=0.1872, simple_loss=0.2729, pruned_loss=0.0507, over 7318.00 frames.], tot_loss[loss=0.22, simple_loss=0.298, pruned_loss=0.07101, over 1425981.85 frames.], batch size: 21, lr: 6.35e-04
2022-05-27 04:55:06,867 INFO [train.py:842] (3/4) Epoch 8, batch 8100, loss[loss=0.2015, simple_loss=0.2798, pruned_loss=0.06159, over 7263.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2977, pruned_loss=0.07123, over 1425252.98 frames.], batch size: 18, lr: 6.35e-04
2022-05-27 04:55:45,317 INFO [train.py:842] (3/4) Epoch 8, batch 8150, loss[loss=0.2187, simple_loss=0.2886, pruned_loss=0.07438, over 7169.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3001, pruned_loss=0.07269, over 1416534.85 frames.], batch size: 18, lr: 6.35e-04
2022-05-27 04:56:24,250 INFO [train.py:842] (3/4) Epoch 8, batch 8200, loss[loss=0.2129, simple_loss=0.3025, pruned_loss=0.0616, over 7316.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3002, pruned_loss=0.07333, over 1418590.76 frames.], batch size: 21, lr: 6.35e-04
2022-05-27 04:57:02,846 INFO [train.py:842] (3/4) Epoch 8, batch 8250, loss[loss=0.1691, simple_loss=0.2494, pruned_loss=0.04439, over 7162.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3004, pruned_loss=0.07297, over 1418715.82 frames.], batch size: 18, lr: 6.34e-04
2022-05-27 04:57:41,678 INFO [train.py:842] (3/4) Epoch 8, batch 8300, loss[loss=0.2096, simple_loss=0.2936, pruned_loss=0.06279, over 7139.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2999, pruned_loss=0.07277, over 1419372.02 frames.], batch size: 20, lr: 6.34e-04
2022-05-27 04:58:20,190 INFO [train.py:842] (3/4) Epoch 8, batch 8350, loss[loss=0.2048, simple_loss=0.2836, pruned_loss=0.06302, over 7147.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2989, pruned_loss=0.07204, over 1421526.90 frames.], batch size: 26, lr: 6.34e-04
2022-05-27 04:58:58,963 INFO [train.py:842] (3/4) Epoch 8, batch 8400, loss[loss=0.2002, simple_loss=0.2662, pruned_loss=0.06705, over 7268.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2986, pruned_loss=0.0722, over 1424472.45 frames.], batch size: 18, lr: 6.34e-04
2022-05-27 04:59:37,691 INFO [train.py:842] (3/4) Epoch 8, batch 8450, loss[loss=0.2285, simple_loss=0.3118, pruned_loss=0.0726, over 7149.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3002, pruned_loss=0.07311, over 1421148.71 frames.], batch size: 20, lr: 6.34e-04
2022-05-27 05:00:16,710 INFO [train.py:842] (3/4) Epoch 8, batch 8500, loss[loss=0.187, simple_loss=0.2816, pruned_loss=0.04619, over 7216.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2999, pruned_loss=0.07274, over 1421640.53 frames.], batch size: 22, lr: 6.33e-04
2022-05-27 05:00:55,189 INFO [train.py:842] (3/4) Epoch 8, batch 8550, loss[loss=0.2153, simple_loss=0.3018, pruned_loss=0.06439, over 7144.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2996, pruned_loss=0.07238, over 1418872.61 frames.], batch size: 20, lr: 6.33e-04
2022-05-27 05:01:34,191 INFO [train.py:842] (3/4) Epoch 8, batch 8600, loss[loss=0.268, simple_loss=0.3208, pruned_loss=0.1077, over 7259.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2978, pruned_loss=0.07156, over 1418612.60 frames.], batch size: 17, lr: 6.33e-04
2022-05-27 05:02:12,589 INFO [train.py:842] (3/4) Epoch 8, batch 8650, loss[loss=0.2132, simple_loss=0.2962, pruned_loss=0.06508, over 7110.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2982, pruned_loss=0.07201, over 1414281.14 frames.], batch size: 21, lr: 6.33e-04
2022-05-27 05:02:51,377 INFO [train.py:842] (3/4) Epoch 8, batch 8700, loss[loss=0.2854, simple_loss=0.3295, pruned_loss=0.1207, over 7272.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2995, pruned_loss=0.07255, over 1418346.98 frames.], batch size: 18, lr: 6.32e-04
2022-05-27 05:03:30,091 INFO [train.py:842] (3/4) Epoch 8, batch 8750, loss[loss=0.2264, simple_loss=0.2881, pruned_loss=0.08231, over 7172.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2975, pruned_loss=0.07136, over 1421917.04 frames.], batch size: 16, lr: 6.32e-04
2022-05-27 05:04:09,297 INFO [train.py:842] (3/4) Epoch 8, batch 8800, loss[loss=0.2786, simple_loss=0.3597, pruned_loss=0.0988, over 7317.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2988, pruned_loss=0.07246, over 1418724.53 frames.], batch size: 22, lr: 6.32e-04
2022-05-27 05:04:47,690 INFO [train.py:842] (3/4) Epoch 8, batch 8850, loss[loss=0.173, simple_loss=0.2436, pruned_loss=0.05125, over 7277.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2999, pruned_loss=0.07257, over 1417102.62 frames.], batch size: 17, lr: 6.32e-04
2022-05-27 05:05:27,279 INFO [train.py:842] (3/4) Epoch 8, batch 8900, loss[loss=0.1882, simple_loss=0.2686, pruned_loss=0.05395, over 7363.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3001, pruned_loss=0.07337, over 1410029.65 frames.], batch size: 19, lr: 6.32e-04
2022-05-27 05:06:05,783 INFO [train.py:842] (3/4) Epoch 8, batch 8950, loss[loss=0.2225, simple_loss=0.3004, pruned_loss=0.07226, over 6411.00 frames.], tot_loss[loss=0.223, simple_loss=0.3002, pruned_loss=0.07286, over 1408218.31 frames.], batch size: 37, lr: 6.31e-04
2022-05-27 05:06:44,588 INFO [train.py:842] (3/4) Epoch 8, batch 9000, loss[loss=0.2974, simple_loss=0.3519, pruned_loss=0.1214, over 4891.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2999, pruned_loss=0.07288, over 1404314.32 frames.], batch size: 52, lr: 6.31e-04
2022-05-27 05:06:44,589 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 05:06:53,926 INFO [train.py:871] (3/4) Epoch 8, validation: loss=0.1786, simple_loss=0.2794, pruned_loss=0.03893, over 868885.00 frames.
2022-05-27 05:07:32,093 INFO [train.py:842] (3/4) Epoch 8, batch 9050, loss[loss=0.2928, simple_loss=0.353, pruned_loss=0.1163, over 5341.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3008, pruned_loss=0.07402, over 1397358.77 frames.], batch size: 52, lr: 6.31e-04
2022-05-27 05:08:11,462 INFO [train.py:842] (3/4) Epoch 8, batch 9100, loss[loss=0.269, simple_loss=0.3301, pruned_loss=0.104, over 5238.00 frames.], tot_loss[loss=0.2234, simple_loss=0.2988, pruned_loss=0.07398, over 1382897.61 frames.], batch size: 52, lr: 6.31e-04
2022-05-27 05:08:49,208 INFO [train.py:842] (3/4) Epoch 8, batch 9150, loss[loss=0.2879, simple_loss=0.35, pruned_loss=0.1129, over 5087.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3053, pruned_loss=0.07967, over 1304202.50 frames.], batch size: 52, lr: 6.31e-04
2022-05-27 05:09:41,217 INFO [train.py:842] (3/4) Epoch 9, batch 0, loss[loss=0.2576, simple_loss=0.3272, pruned_loss=0.09395, over 7209.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3272, pruned_loss=0.09395, over 7209.00 frames.], batch size: 23, lr: 6.05e-04
2022-05-27 05:10:19,733 INFO [train.py:842] (3/4) Epoch 9, batch 50, loss[loss=0.2485, simple_loss=0.3217, pruned_loss=0.08766, over 7206.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3018, pruned_loss=0.07454, over 320064.70 frames.], batch size: 28, lr: 6.05e-04
2022-05-27 05:10:58,700 INFO [train.py:842] (3/4) Epoch 9, batch 100, loss[loss=0.2255, simple_loss=0.3142, pruned_loss=0.06839, over 7239.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2964, pruned_loss=0.07089, over 567867.38 frames.], batch size: 20, lr: 6.05e-04
2022-05-27 05:11:37,211 INFO [train.py:842] (3/4) Epoch 9, batch 150, loss[loss=0.2304, simple_loss=0.3025, pruned_loss=0.07911, over 4827.00 frames.], tot_loss[loss=0.22, simple_loss=0.2974, pruned_loss=0.07128, over 754628.43 frames.], batch size: 52, lr: 6.05e-04
2022-05-27 05:12:15,914 INFO [train.py:842] (3/4) Epoch 9, batch 200, loss[loss=0.2225, simple_loss=0.2976, pruned_loss=0.07369, over 7203.00 frames.], tot_loss[loss=0.2203, simple_loss=0.298, pruned_loss=0.07131, over 903540.42 frames.], batch size: 22, lr: 6.04e-04
2022-05-27 05:13:04,719 INFO [train.py:842] (3/4) Epoch 9, batch 250, loss[loss=0.2426, simple_loss=0.3251, pruned_loss=0.0801, over 7432.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2987, pruned_loss=0.07135, over 1020211.98 frames.], batch size: 20, lr: 6.04e-04
2022-05-27 05:13:43,504 INFO [train.py:842] (3/4) Epoch 9, batch 300, loss[loss=0.2796, simple_loss=0.3601, pruned_loss=0.09953, over 7344.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2976, pruned_loss=0.0705, over 1106522.39 frames.], batch size: 22, lr: 6.04e-04
2022-05-27 05:14:22,309 INFO [train.py:842] (3/4) Epoch 9, batch 350, loss[loss=0.1997, simple_loss=0.2831, pruned_loss=0.05816, over 7152.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2962, pruned_loss=0.0701, over 1180360.14 frames.], batch size: 19, lr: 6.04e-04
2022-05-27 05:15:01,139 INFO [train.py:842] (3/4) Epoch 9, batch 400, loss[loss=0.2469, simple_loss=0.3181, pruned_loss=0.0878, over 7153.00 frames.], tot_loss[loss=0.218, simple_loss=0.296, pruned_loss=0.07002, over 1238982.60 frames.], batch size: 17, lr: 6.04e-04
2022-05-27 05:15:39,713 INFO [train.py:842] (3/4) Epoch 9, batch 450, loss[loss=0.2088, simple_loss=0.2864, pruned_loss=0.06564, over 7265.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2945, pruned_loss=0.06926, over 1279396.85 frames.], batch size: 19, lr: 6.03e-04
2022-05-27 05:16:18,384 INFO [train.py:842] (3/4) Epoch 9, batch 500, loss[loss=0.169, simple_loss=0.2511, pruned_loss=0.04342, over 7409.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2959, pruned_loss=0.06982, over 1311841.79 frames.], batch size: 18, lr: 6.03e-04
2022-05-27 05:16:57,095 INFO [train.py:842] (3/4) Epoch 9, batch 550, loss[loss=0.2331, simple_loss=0.3022, pruned_loss=0.08197, over 7054.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2954, pruned_loss=0.06953, over 1341151.82 frames.], batch size: 18, lr: 6.03e-04
2022-05-27 05:17:36,154 INFO [train.py:842] (3/4) Epoch 9, batch 600, loss[loss=0.1651, simple_loss=0.2552, pruned_loss=0.03747, over 7072.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2947, pruned_loss=0.06941, over 1362738.09 frames.], batch size: 18, lr: 6.03e-04
2022-05-27 05:18:14,774 INFO [train.py:842] (3/4) Epoch 9, batch 650, loss[loss=0.1831, simple_loss=0.2681, pruned_loss=0.04908, over 7358.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2956, pruned_loss=0.0699, over 1375925.10 frames.], batch size: 19, lr: 6.03e-04
2022-05-27 05:18:53,501 INFO [train.py:842] (3/4) Epoch 9, batch 700, loss[loss=0.2292, simple_loss=0.3032, pruned_loss=0.07763, over 7434.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2965, pruned_loss=0.07011, over 1387552.71 frames.], batch size: 20, lr: 6.02e-04
2022-05-27 05:19:32,050 INFO [train.py:842] (3/4) Epoch 9, batch 750, loss[loss=0.1986, simple_loss=0.2677, pruned_loss=0.06475, over 7168.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2957, pruned_loss=0.06905, over 1390067.65 frames.], batch size: 18, lr: 6.02e-04
2022-05-27 05:20:11,011 INFO [train.py:842] (3/4) Epoch 9, batch 800, loss[loss=0.2174, simple_loss=0.297, pruned_loss=0.06889, over 7385.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2955, pruned_loss=0.06921, over 1395173.55 frames.], batch size: 23, lr: 6.02e-04
2022-05-27 05:20:49,563 INFO [train.py:842] (3/4) Epoch 9, batch 850, loss[loss=0.1904, simple_loss=0.2762, pruned_loss=0.05233, over 7301.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2953, pruned_loss=0.06858, over 1400363.78 frames.], batch size: 21, lr: 6.02e-04
2022-05-27 05:21:28,801 INFO [train.py:842] (3/4) Epoch 9, batch 900, loss[loss=0.2746, simple_loss=0.3402, pruned_loss=0.1045, over 7225.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2962, pruned_loss=0.06932, over 1410047.73 frames.], batch size: 21, lr: 6.02e-04
2022-05-27 05:22:07,459 INFO [train.py:842] (3/4) Epoch 9, batch 950, loss[loss=0.1916, simple_loss=0.2735, pruned_loss=0.05483, over 7334.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2959, pruned_loss=0.06933, over 1408332.89 frames.], batch size: 20, lr: 6.01e-04
2022-05-27 05:22:46,352 INFO [train.py:842] (3/4) Epoch 9, batch 1000, loss[loss=0.2217, simple_loss=0.2991, pruned_loss=0.07218, over 7428.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2937, pruned_loss=0.06786, over 1412595.45 frames.], batch size: 20, lr: 6.01e-04
2022-05-27 05:23:24,849 INFO [train.py:842] (3/4) Epoch 9, batch 1050, loss[loss=0.1836, simple_loss=0.2671, pruned_loss=0.05005, over 7250.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2933, pruned_loss=0.06798, over 1417572.31 frames.], batch size: 19, lr: 6.01e-04
2022-05-27 05:24:03,718 INFO [train.py:842] (3/4) Epoch 9, batch 1100, loss[loss=0.2307, simple_loss=0.2894, pruned_loss=0.08598, over 7277.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2935, pruned_loss=0.06741, over 1420828.59 frames.], batch size: 17, lr: 6.01e-04
2022-05-27 05:24:42,293 INFO [train.py:842] (3/4) Epoch 9, batch 1150, loss[loss=0.3525, simple_loss=0.3863, pruned_loss=0.1593, over 7282.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2929, pruned_loss=0.0674, over 1420867.18 frames.], batch size: 25, lr: 6.01e-04
2022-05-27 05:25:21,219 INFO [train.py:842] (3/4) Epoch 9, batch 1200, loss[loss=0.199, simple_loss=0.2781, pruned_loss=0.06001, over 7434.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2937, pruned_loss=0.06867, over 1420997.18 frames.], batch size: 20, lr: 6.00e-04
2022-05-27 05:25:59,837 INFO [train.py:842] (3/4) Epoch 9, batch 1250, loss[loss=0.2264, simple_loss=0.2888, pruned_loss=0.08196, over 6774.00 frames.], tot_loss[loss=0.2172, simple_loss=0.295, pruned_loss=0.0697, over 1417270.64 frames.], batch size: 15, lr: 6.00e-04
2022-05-27 05:26:38,577 INFO [train.py:842] (3/4) Epoch 9, batch 1300, loss[loss=0.2328, simple_loss=0.302, pruned_loss=0.08184, over 7155.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2959, pruned_loss=0.06988, over 1413859.96 frames.], batch size: 19, lr: 6.00e-04
2022-05-27 05:27:17,257 INFO [train.py:842] (3/4) Epoch 9, batch 1350, loss[loss=0.2044, simple_loss=0.2837, pruned_loss=0.06259, over 7430.00 frames.], tot_loss[loss=0.2179, simple_loss=0.296, pruned_loss=0.06995, over 1418687.59 frames.], batch size: 20, lr: 6.00e-04
2022-05-27 05:27:56,089 INFO [train.py:842] (3/4) Epoch 9, batch 1400, loss[loss=0.1978, simple_loss=0.2852, pruned_loss=0.05516, over 7223.00 frames.], tot_loss[loss=0.218, simple_loss=0.2959, pruned_loss=0.0701, over 1415512.00 frames.], batch size: 21, lr: 6.00e-04
2022-05-27 05:28:34,837 INFO [train.py:842] (3/4) Epoch 9, batch 1450, loss[loss=0.3218, simple_loss=0.3776, pruned_loss=0.1329, over 7321.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2958, pruned_loss=0.07041, over 1420376.28 frames.], batch size: 21, lr: 5.99e-04
2022-05-27 05:29:13,618 INFO [train.py:842] (3/4) Epoch 9, batch 1500, loss[loss=0.264, simple_loss=0.339, pruned_loss=0.09447, over 7221.00 frames.], tot_loss[loss=0.218, simple_loss=0.296, pruned_loss=0.07, over 1422813.05 frames.], batch size: 20, lr: 5.99e-04
2022-05-27 05:29:52,249 INFO [train.py:842] (3/4) Epoch 9, batch 1550, loss[loss=0.2391, simple_loss=0.3126, pruned_loss=0.08281, over 7205.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2957, pruned_loss=0.06979, over 1421588.10 frames.], batch size: 22, lr: 5.99e-04
2022-05-27 05:30:51,695 INFO [train.py:842] (3/4) Epoch 9, batch 1600, loss[loss=0.1845, simple_loss=0.2632, pruned_loss=0.0529, over 7067.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2963, pruned_loss=0.06958, over 1419941.44 frames.], batch size: 18, lr: 5.99e-04
2022-05-27 05:31:40,494 INFO [train.py:842] (3/4) Epoch 9, batch 1650, loss[loss=0.2457, simple_loss=0.3309, pruned_loss=0.08024, over 7103.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2963, pruned_loss=0.06933, over 1420899.10 frames.], batch size: 21, lr: 5.99e-04
2022-05-27 05:32:19,075 INFO [train.py:842] (3/4) Epoch 9, batch 1700, loss[loss=0.2126, simple_loss=0.2965, pruned_loss=0.06442, over 7156.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2977, pruned_loss=0.06995, over 1418887.12 frames.], batch size: 20, lr: 5.98e-04
2022-05-27 05:32:57,927 INFO [train.py:842] (3/4) Epoch 9, batch 1750, loss[loss=0.2247, simple_loss=0.32, pruned_loss=0.06476, over 7318.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2974, pruned_loss=0.07039, over 1420535.56 frames.], batch size: 21, lr: 5.98e-04
2022-05-27 05:33:36,460 INFO [train.py:842] (3/4) Epoch 9, batch 1800, loss[loss=0.222, simple_loss=0.3048, pruned_loss=0.06963, over 7233.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2974, pruned_loss=0.0704, over 1417646.26 frames.], batch size: 20, lr: 5.98e-04
2022-05-27 05:34:14,943 INFO [train.py:842] (3/4) Epoch 9, batch 1850, loss[loss=0.2464, simple_loss=0.3189, pruned_loss=0.08694, over 7234.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2981, pruned_loss=0.07068, over 1420938.70 frames.], batch size: 20, lr: 5.98e-04
2022-05-27 05:34:54,165 INFO [train.py:842] (3/4) Epoch 9, batch 1900, loss[loss=0.2292, simple_loss=0.2988, pruned_loss=0.07983, over 7151.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2987, pruned_loss=0.07121, over 1420479.01 frames.], batch size: 19, lr: 5.98e-04
2022-05-27 05:35:32,765 INFO [train.py:842] (3/4) Epoch 9, batch 1950, loss[loss=0.1916, simple_loss=0.277, pruned_loss=0.0531, over 7123.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2979, pruned_loss=0.07044, over 1422121.23 frames.], batch size: 21, lr: 5.97e-04
2022-05-27 05:36:11,649 INFO [train.py:842] (3/4) Epoch 9, batch 2000, loss[loss=0.2663, simple_loss=0.3364, pruned_loss=0.09817, over 7294.00 frames.], tot_loss[loss=0.218, simple_loss=0.2963, pruned_loss=0.06982, over 1422963.75 frames.], batch size: 24, lr: 5.97e-04
2022-05-27 05:36:50,200 INFO [train.py:842] (3/4) Epoch 9, batch 2050, loss[loss=0.1734, simple_loss=0.2475, pruned_loss=0.04959, over 7269.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2961, pruned_loss=0.06989, over 1422479.14 frames.], batch size: 17, lr: 5.97e-04
2022-05-27 05:37:28,899 INFO [train.py:842] (3/4) Epoch 9, batch 2100, loss[loss=0.2632, simple_loss=0.3213, pruned_loss=0.1026, over 7254.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2972, pruned_loss=0.07074, over 1423681.04 frames.], batch size: 19, lr: 5.97e-04
2022-05-27 05:38:07,469 INFO [train.py:842] (3/4) Epoch 9, batch 2150, loss[loss=0.1987, simple_loss=0.285, pruned_loss=0.05621, over 7069.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2965, pruned_loss=0.07004, over 1426413.04 frames.], batch size: 18, lr: 5.97e-04
2022-05-27 05:38:46,499 INFO [train.py:842] (3/4) Epoch 9, batch 2200, loss[loss=0.1931, simple_loss=0.2648, pruned_loss=0.06063, over 7270.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2952, pruned_loss=0.06924, over 1423850.80 frames.], batch size: 17, lr: 5.96e-04
2022-05-27 05:39:25,141 INFO [train.py:842] (3/4) Epoch 9, batch 2250, loss[loss=0.1853, simple_loss=0.2616, pruned_loss=0.05448, over 7157.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2947, pruned_loss=0.06927, over 1424217.48 frames.], batch size: 18, lr: 5.96e-04
2022-05-27 05:40:03,867 INFO [train.py:842] (3/4) Epoch 9, batch 2300, loss[loss=0.2064, simple_loss=0.2928, pruned_loss=0.06004, over 7133.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2946, pruned_loss=0.06881, over 1425367.82 frames.], batch size: 20, lr: 5.96e-04
2022-05-27 05:40:42,449 INFO [train.py:842] (3/4) Epoch 9, batch 2350, loss[loss=0.2103, simple_loss=0.2862, pruned_loss=0.06722, over 6791.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2948, pruned_loss=0.069, over 1423617.66 frames.], batch size: 31, lr: 5.96e-04
2022-05-27 05:41:21,201 INFO [train.py:842] (3/4) Epoch 9, batch 2400, loss[loss=0.205, simple_loss=0.2802, pruned_loss=0.06495, over 7285.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2947, pruned_loss=0.06881, over 1424448.66 frames.], batch size: 18, lr: 5.96e-04
2022-05-27 05:41:59,641 INFO [train.py:842] (3/4) Epoch 9, batch 2450, loss[loss=0.168, simple_loss=0.2488, pruned_loss=0.04358, over 7407.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2942, pruned_loss=0.0685, over 1425847.91 frames.], batch size: 18, lr: 5.95e-04
2022-05-27 05:42:38,369 INFO [train.py:842] (3/4) Epoch 9, batch 2500, loss[loss=0.228, simple_loss=0.3125, pruned_loss=0.07171, over 7215.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2948, pruned_loss=0.06916, over 1424275.07 frames.], batch size: 22, lr: 5.95e-04
2022-05-27 05:43:16,895 INFO [train.py:842] (3/4) Epoch 9, batch 2550, loss[loss=0.186, simple_loss=0.2702, pruned_loss=0.05089, over 7140.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2943, pruned_loss=0.0692, over 1421822.17 frames.], batch size: 17, lr: 5.95e-04
2022-05-27 05:43:55,672 INFO [train.py:842] (3/4) Epoch 9, batch 2600, loss[loss=0.2361, simple_loss=0.3188, pruned_loss=0.07671, over 7389.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2952, pruned_loss=0.06906, over 1418800.44 frames.], batch size: 23, lr: 5.95e-04
2022-05-27 05:44:34,270 INFO [train.py:842] (3/4) Epoch 9, batch 2650, loss[loss=0.2463, simple_loss=0.3098, pruned_loss=0.09136, over 4799.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2951, pruned_loss=0.06899, over 1417167.04 frames.], batch size: 52, lr: 5.95e-04
2022-05-27 05:45:13,033 INFO [train.py:842] (3/4) Epoch 9, batch 2700, loss[loss=0.2327, simple_loss=0.3097, pruned_loss=0.07784, over 7341.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2959, pruned_loss=0.06949, over 1418785.65 frames.], batch size: 22, lr: 5.94e-04
2022-05-27 05:45:51,580 INFO [train.py:842] (3/4) Epoch 9, batch 2750, loss[loss=0.1821, simple_loss=0.2703, pruned_loss=0.04697, over 7315.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2954, pruned_loss=0.06922, over 1423247.75 frames.], batch size: 20, lr: 5.94e-04
2022-05-27 05:46:30,155 INFO [train.py:842] (3/4) Epoch 9, batch 2800, loss[loss=0.2139, simple_loss=0.3042, pruned_loss=0.06178, over 7205.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2963, pruned_loss=0.06936, over 1425995.01 frames.], batch size: 22, lr: 5.94e-04
2022-05-27 05:47:08,824 INFO [train.py:842] (3/4) Epoch 9, batch 2850, loss[loss=0.2457, simple_loss=0.3033, pruned_loss=0.09403, over 7162.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2953, pruned_loss=0.06879, over 1428655.96 frames.], batch size: 19, lr: 5.94e-04
2022-05-27 05:47:47,793 INFO [train.py:842] (3/4) Epoch 9, batch 2900, loss[loss=0.2206, simple_loss=0.3045, pruned_loss=0.06835, over 7326.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2955, pruned_loss=0.06873, over 1427692.54 frames.], batch size: 21, lr: 5.94e-04
2022-05-27 05:48:26,348 INFO [train.py:842] (3/4) Epoch 9, batch 2950, loss[loss=0.2035, simple_loss=0.2825, pruned_loss=0.06227, over 7277.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2956, pruned_loss=0.06868, over 1424040.83 frames.], batch size: 18, lr: 5.94e-04
2022-05-27 05:49:05,592 INFO [train.py:842] (3/4) Epoch 9, batch 3000, loss[loss=0.2153, simple_loss=0.3012, pruned_loss=0.06471, over 7285.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2958, pruned_loss=0.06933, over 1421264.11 frames.], batch size: 24, lr: 5.93e-04
2022-05-27 05:49:05,593 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 05:49:14,865 INFO [train.py:871] (3/4) Epoch 9, validation: loss=0.1779, simple_loss=0.2778, pruned_loss=0.039, over 868885.00 frames.
2022-05-27 05:49:53,744 INFO [train.py:842] (3/4) Epoch 9, batch 3050, loss[loss=0.2131, simple_loss=0.2935, pruned_loss=0.06632, over 7326.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2967, pruned_loss=0.07035, over 1417907.24 frames.], batch size: 20, lr: 5.93e-04
2022-05-27 05:50:32,334 INFO [train.py:842] (3/4) Epoch 9, batch 3100, loss[loss=0.2811, simple_loss=0.3512, pruned_loss=0.1055, over 6761.00 frames.], tot_loss[loss=0.218, simple_loss=0.2963, pruned_loss=0.06982, over 1413155.81 frames.], batch size: 31, lr: 5.93e-04
2022-05-27 05:51:11,005 INFO [train.py:842] (3/4) Epoch 9, batch 3150, loss[loss=0.2058, simple_loss=0.2884, pruned_loss=0.06161, over 7160.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2951, pruned_loss=0.06868, over 1416729.79 frames.], batch size: 19, lr: 5.93e-04
2022-05-27 05:51:50,054 INFO [train.py:842] (3/4) Epoch 9, batch 3200, loss[loss=0.1818, simple_loss=0.268, pruned_loss=0.04779, over 7148.00 frames.], tot_loss[loss=0.216, simple_loss=0.2951, pruned_loss=0.06842, over 1421345.29 frames.], batch size: 20, lr: 5.93e-04
2022-05-27 05:52:28,403 INFO [train.py:842] (3/4) Epoch 9, batch 3250, loss[loss=0.2361, simple_loss=0.307, pruned_loss=0.08255, over 5102.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2964, pruned_loss=0.06903, over 1420042.35 frames.], batch size: 53, lr: 5.92e-04
2022-05-27 05:53:07,207 INFO [train.py:842] (3/4) Epoch 9, batch 3300, loss[loss=0.2531, simple_loss=0.3316, pruned_loss=0.08731, over 7214.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2967, pruned_loss=0.06949, over 1419990.11 frames.], batch size: 22, lr: 5.92e-04
2022-05-27 05:53:45,788 INFO [train.py:842] (3/4) Epoch 9, batch 3350, loss[loss=0.2173, simple_loss=0.2967, pruned_loss=0.06892, over 7267.00 frames.], tot_loss[loss=0.216, simple_loss=0.2955, pruned_loss=0.06825, over 1424197.83 frames.], batch size: 19, lr: 5.92e-04
2022-05-27 05:54:24,456 INFO [train.py:842] (3/4) Epoch 9, batch 3400, loss[loss=0.2051, simple_loss=0.2935, pruned_loss=0.05831, over 6826.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2953, pruned_loss=0.06794, over 1421399.35 frames.], batch size: 31, lr: 5.92e-04
2022-05-27 05:55:02,984 INFO [train.py:842] (3/4) Epoch 9, batch 3450, loss[loss=0.1775, simple_loss=0.2522, pruned_loss=0.05143, over 7405.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2944, pruned_loss=0.06758, over 1423593.25 frames.], batch size: 18, lr: 5.92e-04
2022-05-27 05:55:41,932 INFO [train.py:842] (3/4) Epoch 9, batch 3500, loss[loss=0.2605, simple_loss=0.3305, pruned_loss=0.0952, over 7145.00 frames.], tot_loss[loss=0.217, simple_loss=0.2957, pruned_loss=0.06917, over 1424283.14 frames.], batch size: 19, lr: 5.91e-04
2022-05-27 05:56:20,582 INFO [train.py:842] (3/4) Epoch 9, batch 3550, loss[loss=0.1763, simple_loss=0.2534, pruned_loss=0.0496, over 7165.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2933, pruned_loss=0.06778, over 1426773.53 frames.], batch size: 18, lr: 5.91e-04
2022-05-27 05:56:59,457 INFO [train.py:842] (3/4) Epoch 9, batch 3600, loss[loss=0.2, simple_loss=0.2728, pruned_loss=0.06361, over 7294.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2945, pruned_loss=0.06853, over 1424670.20 frames.], batch size: 18, lr: 5.91e-04
2022-05-27 05:57:38,132 INFO [train.py:842] (3/4) Epoch 9, batch 3650, loss[loss=0.1896, simple_loss=0.2587, pruned_loss=0.06028, over 7134.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2933, pruned_loss=0.06821, over 1427067.30 frames.], batch size: 17, lr: 5.91e-04
2022-05-27 05:58:16,866 INFO [train.py:842] (3/4) Epoch 9, batch 3700, loss[loss=0.1917, simple_loss=0.2748, pruned_loss=0.05433, over 7333.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2942, pruned_loss=0.0682, over 1427413.85 frames.], batch size: 25, lr: 5.91e-04
2022-05-27 05:58:55,437 INFO [train.py:842] (3/4) Epoch 9, batch 3750, loss[loss=0.1856, simple_loss=0.2719, pruned_loss=0.04967, over 7424.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2959, pruned_loss=0.069, over 1426732.90 frames.], batch size: 20, lr: 5.90e-04
2022-05-27 05:59:34,174 INFO [train.py:842] (3/4) Epoch 9, batch 3800, loss[loss=0.2244, simple_loss=0.3112, pruned_loss=0.06873, over 7321.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2959, pruned_loss=0.06882, over 1429056.23 frames.], batch size: 21, lr: 5.90e-04
2022-05-27 06:00:12,815 INFO [train.py:842] (3/4) Epoch 9, batch 3850, loss[loss=0.1781, simple_loss=0.2675, pruned_loss=0.04438, over 7429.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2957, pruned_loss=0.06833, over 1430349.24 frames.], batch size: 20, lr: 5.90e-04
2022-05-27 06:00:51,518 INFO [train.py:842] (3/4) Epoch 9, batch 3900, loss[loss=0.2082, simple_loss=0.2826, pruned_loss=0.0669, over 7255.00 frames.], tot_loss[loss=0.2166, simple_loss=0.296, pruned_loss=0.06856, over 1429350.22 frames.], batch size: 19, lr: 5.90e-04
2022-05-27 06:01:30,201 INFO [train.py:842] (3/4) Epoch 9, batch 3950, loss[loss=0.2077, simple_loss=0.2883, pruned_loss=0.06356, over 7250.00 frames.], tot_loss[loss=0.2171, simple_loss=0.296, pruned_loss=0.06908, over 1428052.35 frames.], batch size: 19, lr: 5.90e-04
2022-05-27 06:02:08,920 INFO [train.py:842] (3/4) Epoch 9, batch 4000, loss[loss=0.2011, simple_loss=0.2831, pruned_loss=0.05956, over 7130.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2961, pruned_loss=0.06926, over 1425245.23 frames.], batch size: 21, lr: 5.89e-04
2022-05-27 06:02:47,516 INFO [train.py:842] (3/4) Epoch 9, batch 4050, loss[loss=0.1875, simple_loss=0.2808, pruned_loss=0.04716, over 7336.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2969, pruned_loss=0.06982, over 1422266.32 frames.], batch size: 20, lr: 5.89e-04
2022-05-27 06:03:26,341 INFO [train.py:842] (3/4) Epoch 9, batch 4100, loss[loss=0.1893, simple_loss=0.258, pruned_loss=0.06024, over 7298.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2964, pruned_loss=0.06963, over 1424902.39 frames.], batch size: 17, lr: 5.89e-04
2022-05-27 06:04:05,014 INFO [train.py:842] (3/4) Epoch 9, batch 4150, loss[loss=0.2589, simple_loss=0.3299, pruned_loss=0.09397, over 7210.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2964, pruned_loss=0.06927, over 1428161.72 frames.], batch size: 22, lr: 5.89e-04
2022-05-27 06:04:43,796 INFO [train.py:842] (3/4) Epoch 9, batch 4200, loss[loss=0.1826, simple_loss=0.2595, pruned_loss=0.05287, over 6993.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2958, pruned_loss=0.06882, over 1423405.26 frames.], batch size: 16, lr: 5.89e-04
2022-05-27 06:05:22,393 INFO [train.py:842] (3/4) Epoch 9, batch 4250, loss[loss=0.2014, simple_loss=0.2855, pruned_loss=0.05862, over 7091.00 frames.], tot_loss[loss=0.2165, simple_loss=0.295, pruned_loss=0.06898, over 1423291.50 frames.], batch size: 28, lr: 5.89e-04
2022-05-27 06:06:01,308 INFO [train.py:842] (3/4) Epoch 9, batch 4300, loss[loss=0.2307, simple_loss=0.3144, pruned_loss=0.07349, over 7414.00 frames.], tot_loss[loss=0.216, simple_loss=0.2949, pruned_loss=0.06855, over 1424698.37 frames.], batch size: 21, lr: 5.88e-04
2022-05-27 06:06:39,833 INFO [train.py:842] (3/4) Epoch 9, batch 4350, loss[loss=0.174, simple_loss=0.254, pruned_loss=0.04704, over 6994.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2961, pruned_loss=0.06948, over 1419011.50 frames.], batch size: 16, lr: 5.88e-04
2022-05-27 06:07:18,601 INFO [train.py:842] (3/4) Epoch 9, batch 4400, loss[loss=0.2342, simple_loss=0.3242, pruned_loss=0.07211, over 6452.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2963, pruned_loss=0.06999, over 1417647.00 frames.], batch size: 37, lr: 5.88e-04
2022-05-27 06:07:57,171 INFO [train.py:842] (3/4) Epoch 9, batch 4450, loss[loss=0.2609, simple_loss=0.3352, pruned_loss=0.09326, over 7401.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2969, pruned_loss=0.06987, over 1420009.32 frames.], batch size: 23, lr: 5.88e-04
2022-05-27 06:08:35,961 INFO [train.py:842] (3/4) Epoch 9, batch 4500, loss[loss=0.2339, simple_loss=0.3156, pruned_loss=0.07608, over 7206.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2963, pruned_loss=0.06971, over 1422371.76 frames.], batch size: 23, lr: 5.88e-04
2022-05-27 06:09:14,579 INFO [train.py:842] (3/4) Epoch 9, batch 4550, loss[loss=0.203, simple_loss=0.2856, pruned_loss=0.06021, over 7162.00 frames.], tot_loss[loss=0.217, simple_loss=0.2954, pruned_loss=0.0693, over 1422873.59 frames.], batch size: 26, lr: 5.87e-04
2022-05-27 06:09:53,662 INFO [train.py:842] (3/4) Epoch 9, batch 4600, loss[loss=0.1928, simple_loss=0.2749, pruned_loss=0.05539, over 7064.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2937, pruned_loss=0.06858, over 1422987.41 frames.], batch size: 18, lr: 5.87e-04
2022-05-27 06:10:32,399 INFO [train.py:842] (3/4) Epoch 9, batch 4650, loss[loss=0.2057, simple_loss=0.2842, pruned_loss=0.06361, over 7163.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2939, pruned_loss=0.06841, over 1422498.04 frames.], batch size: 19, lr: 5.87e-04
2022-05-27 06:11:11,208 INFO [train.py:842] (3/4) Epoch 9, batch 4700, loss[loss=0.2398, simple_loss=0.3136, pruned_loss=0.08302, over 7291.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2921, pruned_loss=0.06749, over 1421070.81 frames.], batch size: 24, lr: 5.87e-04
2022-05-27 06:11:49,748 INFO [train.py:842] (3/4) Epoch 9, batch 4750, loss[loss=0.2154, simple_loss=0.2943, pruned_loss=0.06827, over 7187.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2943, pruned_loss=0.06931, over 1418593.63 frames.], batch size: 23, lr: 5.87e-04
2022-05-27 06:12:28,770 INFO [train.py:842] (3/4) Epoch 9, batch 4800, loss[loss=0.2508, simple_loss=0.3137, pruned_loss=0.09399, over 7409.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2938, pruned_loss=0.06915, over 1417037.80 frames.], batch size: 18, lr: 5.86e-04
2022-05-27 06:13:07,357 INFO [train.py:842] (3/4) Epoch 9, batch 4850, loss[loss=0.1647, simple_loss=0.2442, pruned_loss=0.04262, over 7268.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2935, pruned_loss=0.06919, over 1421451.88 frames.], batch size: 17, lr: 5.86e-04
2022-05-27 06:13:46,262 INFO [train.py:842] (3/4) Epoch 9, batch 4900, loss[loss=0.3118, simple_loss=0.3591, pruned_loss=0.1323, over 4924.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2941, pruned_loss=0.06949, over 1419593.45 frames.], batch size: 52, lr: 5.86e-04
2022-05-27 06:14:24,892 INFO [train.py:842] (3/4) Epoch 9, batch 4950, loss[loss=0.2618, simple_loss=0.3334, pruned_loss=0.09511, over 7301.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2924, pruned_loss=0.06846, over 1420415.20 frames.], batch size: 25, lr: 5.86e-04
2022-05-27 06:15:03,644 INFO [train.py:842] (3/4) Epoch 9, batch 5000, loss[loss=0.2273, simple_loss=0.3088, pruned_loss=0.07287, over 7308.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2938, pruned_loss=0.06896, over 1418069.92 frames.], batch size: 24, lr: 5.86e-04
2022-05-27 06:15:42,263 INFO [train.py:842] (3/4) Epoch 9, batch 5050, loss[loss=0.2023, simple_loss=0.2853, pruned_loss=0.05961, over 7441.00 frames.], tot_loss[loss=0.2144, simple_loss=0.293, pruned_loss=0.06787, over 1419972.50 frames.], batch size: 20, lr: 5.86e-04
2022-05-27 06:16:21,089 INFO [train.py:842] (3/4) Epoch 9, batch 5100, loss[loss=0.26, simple_loss=0.3323, pruned_loss=0.0939, over 6413.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2946, pruned_loss=0.06855, over 1421577.15 frames.], batch size: 38, lr: 5.85e-04
2022-05-27 06:16:59,718 INFO [train.py:842] (3/4) Epoch 9, batch 5150, loss[loss=0.2062, simple_loss=0.3009, pruned_loss=0.05571, over 7153.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2949, pruned_loss=0.06868, over 1422913.59 frames.], batch size: 20, lr: 5.85e-04
2022-05-27 06:17:38,714 INFO [train.py:842] (3/4) Epoch 9, batch 5200, loss[loss=0.1677, simple_loss=0.2616, pruned_loss=0.03695, over 7333.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2965, pruned_loss=0.07028, over 1424128.79 frames.], batch size: 20, lr: 5.85e-04
2022-05-27 06:18:17,381 INFO [train.py:842] (3/4) Epoch 9, batch 5250, loss[loss=0.225, simple_loss=0.3099, pruned_loss=0.07005, over 7232.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2962, pruned_loss=0.06995, over 1425469.74 frames.], batch size: 20, lr: 5.85e-04
2022-05-27 06:18:56,025 INFO [train.py:842] (3/4) Epoch 9, batch 5300, loss[loss=0.2159, simple_loss=0.2982, pruned_loss=0.06679, over 7426.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2965, pruned_loss=0.07046, over 1421111.11 frames.], batch size: 20, lr: 5.85e-04
2022-05-27 06:19:34,531 INFO [train.py:842] (3/4) Epoch 9, batch 5350, loss[loss=0.2191, simple_loss=0.3038, pruned_loss=0.06713, over 7261.00 frames.], tot_loss[loss=0.2195, simple_loss=0.2973, pruned_loss=0.07081, over 1422495.31 frames.], batch size: 24, lr: 5.84e-04
2022-05-27 06:20:13,329 INFO [train.py:842] (3/4) Epoch 9, batch 5400, loss[loss=0.2368, simple_loss=0.3041, pruned_loss=0.08478, over 5123.00 frames.], tot_loss[loss=0.2204, simple_loss=0.298, pruned_loss=0.07134, over 1416938.50 frames.], batch size: 52, lr: 5.84e-04
2022-05-27 06:20:51,805 INFO [train.py:842] (3/4) Epoch 9, batch 5450, loss[loss=0.2146, simple_loss=0.2957, pruned_loss=0.06671, over 6783.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2971, pruned_loss=0.0708, over 1417526.66 frames.], batch size: 31, lr: 5.84e-04
2022-05-27 06:21:30,690 INFO [train.py:842] (3/4) Epoch 9, batch 5500, loss[loss=0.2559, simple_loss=0.3303, pruned_loss=0.0907, over 7120.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2974, pruned_loss=0.07036, over 1417178.29 frames.], batch size: 21, lr: 5.84e-04
2022-05-27 06:22:09,251 INFO [train.py:842] (3/4) Epoch 9, batch 5550, loss[loss=0.2878, simple_loss=0.3362, pruned_loss=0.1197, over 5152.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2965, pruned_loss=0.07021, over 1417804.66 frames.], batch size: 52, lr: 5.84e-04
2022-05-27 06:22:47,831 INFO [train.py:842] (3/4) Epoch 9, batch 5600, loss[loss=0.224, simple_loss=0.2948, pruned_loss=0.07656, over 6771.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2957, pruned_loss=0.06941, over 1417698.40 frames.], batch size: 31, lr: 5.84e-04
2022-05-27 06:23:26,383 INFO [train.py:842] (3/4) Epoch 9, batch 5650, loss[loss=0.2391, simple_loss=0.3089, pruned_loss=0.0846, over 7119.00 frames.], tot_loss[loss=0.2163, simple_loss=0.295, pruned_loss=0.06879, over 1419675.97 frames.], batch size: 21, lr: 5.83e-04
2022-05-27 06:24:05,342 INFO [train.py:842] (3/4) Epoch 9, batch 5700, loss[loss=0.2281, simple_loss=0.3116, pruned_loss=0.07234, over 7238.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2942, pruned_loss=0.06856, over 1417761.44 frames.], batch size: 20, lr: 5.83e-04
2022-05-27 06:24:44,106 INFO [train.py:842] (3/4) Epoch 9, batch 5750, loss[loss=0.2186, simple_loss=0.3024, pruned_loss=0.06733, over 7103.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2948, pruned_loss=0.06834, over 1422012.10 frames.], batch size: 21, lr: 5.83e-04
2022-05-27 06:25:23,078 INFO [train.py:842] (3/4) Epoch 9, batch 5800, loss[loss=0.256, simple_loss=0.3392, pruned_loss=0.08642, over 7322.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2954, pruned_loss=0.06872, over 1420727.77 frames.], batch size: 21, lr: 5.83e-04
2022-05-27 06:26:01,770 INFO [train.py:842] (3/4) Epoch 9, batch 5850, loss[loss=0.2341, simple_loss=0.2962, pruned_loss=0.08601, over 7156.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2959, pruned_loss=0.06955, over 1417041.93 frames.], batch size: 19, lr: 5.83e-04
2022-05-27 06:26:41,218 INFO [train.py:842] (3/4) Epoch 9, batch 5900, loss[loss=0.1742, simple_loss=0.2566, pruned_loss=0.04587, over 7408.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2947, pruned_loss=0.0685, over 1421222.64 frames.], batch size: 18, lr: 5.82e-04
2022-05-27 06:27:19,685 INFO [train.py:842] (3/4) Epoch 9, batch 5950, loss[loss=0.2452, simple_loss=0.3274, pruned_loss=0.0815, over 7281.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2942, pruned_loss=0.06849, over 1420859.52 frames.], batch size: 24, lr: 5.82e-04
2022-05-27 06:27:58,516 INFO [train.py:842] (3/4) Epoch 9, batch 6000, loss[loss=0.1713, simple_loss=0.2509, pruned_loss=0.04579, over 6993.00 frames.], tot_loss[loss=0.214, simple_loss=0.2929, pruned_loss=0.0675, over 1420624.03 frames.], batch size: 16, lr: 5.82e-04
2022-05-27 06:27:58,517 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 06:28:07,748 INFO [train.py:871] (3/4) Epoch 9, validation: loss=0.1769, simple_loss=0.2771, pruned_loss=0.03838, over 868885.00 frames.
2022-05-27 06:28:46,378 INFO [train.py:842] (3/4) Epoch 9, batch 6050, loss[loss=0.2001, simple_loss=0.2645, pruned_loss=0.0678, over 6778.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2932, pruned_loss=0.06814, over 1421193.91 frames.], batch size: 15, lr: 5.82e-04
2022-05-27 06:29:25,576 INFO [train.py:842] (3/4) Epoch 9, batch 6100, loss[loss=0.1618, simple_loss=0.2404, pruned_loss=0.04159, over 7277.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2931, pruned_loss=0.06769, over 1419932.27 frames.], batch size: 17, lr: 5.82e-04
2022-05-27 06:30:04,197 INFO [train.py:842] (3/4) Epoch 9, batch 6150, loss[loss=0.1748, simple_loss=0.2458, pruned_loss=0.05192, over 7265.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2926, pruned_loss=0.06748, over 1417746.45 frames.], batch size: 18, lr: 5.82e-04
2022-05-27 06:30:42,924 INFO [train.py:842] (3/4) Epoch 9, batch 6200, loss[loss=0.1957, simple_loss=0.2706, pruned_loss=0.06035, over 7144.00 frames.], tot_loss[loss=0.213, simple_loss=0.2918, pruned_loss=0.06708, over 1419316.45 frames.], batch size: 17, lr: 5.81e-04
2022-05-27 06:31:21,490 INFO [train.py:842] (3/4) Epoch 9, batch 6250, loss[loss=0.2155, simple_loss=0.2946, pruned_loss=0.06815, over 7434.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2915, pruned_loss=0.06703, over 1419451.07 frames.], batch size: 20, lr: 5.81e-04
2022-05-27 06:32:00,448 INFO [train.py:842] (3/4) Epoch 9, batch 6300, loss[loss=0.2016, simple_loss=0.2861, pruned_loss=0.05856, over 5150.00 frames.], tot_loss[loss=0.214, simple_loss=0.2924, pruned_loss=0.06783, over 1419404.62 frames.], batch size: 52, lr: 5.81e-04
2022-05-27 06:32:38,980 INFO [train.py:842] (3/4) Epoch 9, batch 6350, loss[loss=0.1836, simple_loss=0.2781, pruned_loss=0.04451, over 7404.00 frames.], tot_loss[loss=0.2136, simple_loss=0.292, pruned_loss=0.06753, over 1420394.68 frames.], batch size: 21, lr: 5.81e-04
2022-05-27 06:33:17,803 INFO [train.py:842] (3/4) Epoch 9, batch 6400, loss[loss=0.2406, simple_loss=0.3102, pruned_loss=0.08547, over 7116.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2919, pruned_loss=0.06793, over 1421215.42 frames.], batch size: 21, lr: 5.81e-04
2022-05-27 06:33:56,400 INFO [train.py:842] (3/4) Epoch 9, batch 6450, loss[loss=0.1754, simple_loss=0.2615, pruned_loss=0.04462, over 7346.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2923, pruned_loss=0.06777, over 1421351.89 frames.], batch size: 19, lr: 5.80e-04
2022-05-27 06:34:38,053 INFO [train.py:842] (3/4) Epoch 9, batch 6500, loss[loss=0.2011, simple_loss=0.2816, pruned_loss=0.06027, over 7403.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2923, pruned_loss=0.06747, over 1422169.66 frames.], batch size: 21, lr: 5.80e-04
2022-05-27 06:35:16,528 INFO [train.py:842] (3/4) Epoch 9, batch 6550, loss[loss=0.2559, simple_loss=0.3297, pruned_loss=0.09101, over 7139.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2925, pruned_loss=0.06739, over 1422941.37 frames.], batch size: 20, lr: 5.80e-04
2022-05-27 06:35:55,357 INFO [train.py:842] (3/4) Epoch 9, batch 6600, loss[loss=0.2154, simple_loss=0.2921, pruned_loss=0.0694, over 7069.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2942, pruned_loss=0.06832, over 1424625.91 frames.], batch size: 18, lr: 5.80e-04
2022-05-27 06:36:34,069 INFO [train.py:842] (3/4) Epoch 9, batch 6650, loss[loss=0.1957, simple_loss=0.2881, pruned_loss=0.0517, over 7062.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2942, pruned_loss=0.06827, over 1425142.20 frames.], batch size: 18, lr: 5.80e-04
2022-05-27 06:37:12,646 INFO [train.py:842] (3/4) Epoch 9, batch 6700, loss[loss=0.1943, simple_loss=0.2538, pruned_loss=0.06738, over 7281.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2943, pruned_loss=0.06819, over 1423005.42 frames.], batch size: 17, lr: 5.80e-04
2022-05-27 06:37:51,240 INFO [train.py:842] (3/4) Epoch 9, batch 6750, loss[loss=0.1983, simple_loss=0.2831, pruned_loss=0.05679, over 7260.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2949, pruned_loss=0.06803, over 1423090.00 frames.], batch size: 19, lr: 5.79e-04
2022-05-27 06:38:30,292 INFO [train.py:842] (3/4) Epoch 9, batch 6800, loss[loss=0.2579, simple_loss=0.332, pruned_loss=0.09188, over 7330.00 frames.], tot_loss[loss=0.2159, simple_loss=0.295, pruned_loss=0.0684, over 1426440.09 frames.], batch size: 22, lr: 5.79e-04
2022-05-27 06:39:08,704 INFO [train.py:842] (3/4) Epoch 9, batch 6850, loss[loss=0.2303, simple_loss=0.3118, pruned_loss=0.07435, over 7107.00 frames.], tot_loss[loss=0.216, simple_loss=0.2955, pruned_loss=0.06827, over 1426861.05 frames.], batch size: 21, lr: 5.79e-04
2022-05-27 06:39:47,802 INFO [train.py:842] (3/4) Epoch 9, batch 6900, loss[loss=0.2215, simple_loss=0.312, pruned_loss=0.06552, over 7331.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2948, pruned_loss=0.06744, over 1423729.33 frames.], batch size: 20, lr: 5.79e-04
2022-05-27 06:40:26,413 INFO [train.py:842] (3/4) Epoch 9, batch 6950, loss[loss=0.1711, simple_loss=0.2526, pruned_loss=0.0448, over 7372.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2961, pruned_loss=0.06838, over 1420709.62 frames.], batch size: 19, lr: 5.79e-04
2022-05-27 06:41:05,240 INFO [train.py:842] (3/4) Epoch 9, batch 7000, loss[loss=0.204, simple_loss=0.2936, pruned_loss=0.05726, over 6782.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2949, pruned_loss=0.06778, over 1421138.72 frames.], batch size: 31, lr: 5.78e-04
2022-05-27 06:41:43,608 INFO [train.py:842] (3/4) Epoch 9, batch 7050, loss[loss=0.2223, simple_loss=0.311, pruned_loss=0.06678, over 7123.00 frames.], tot_loss[loss=0.2153, simple_loss=0.295, pruned_loss=0.06776, over 1418784.79 frames.], batch size: 21, lr: 5.78e-04
2022-05-27 06:42:22,523 INFO [train.py:842] (3/4) Epoch 9, batch 7100, loss[loss=0.1763, simple_loss=0.2565, pruned_loss=0.04801, over 7457.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2937, pruned_loss=0.06672, over 1423121.93 frames.], batch size: 19, lr: 5.78e-04
2022-05-27 06:43:01,110 INFO [train.py:842] (3/4) Epoch 9, batch 7150, loss[loss=0.2599, simple_loss=0.3362, pruned_loss=0.09178, over 7158.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2942, pruned_loss=0.06748, over 1417786.52 frames.], batch size: 26, lr: 5.78e-04
2022-05-27 06:43:40,014 INFO [train.py:842] (3/4) Epoch 9, batch 7200, loss[loss=0.2211, simple_loss=0.2908, pruned_loss=0.07564, over 7368.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2948, pruned_loss=0.06803, over 1421699.65 frames.], batch size: 19, lr: 5.78e-04
2022-05-27 06:44:18,610 INFO [train.py:842] (3/4) Epoch 9, batch 7250, loss[loss=0.3264, simple_loss=0.3796, pruned_loss=0.1366, over 6263.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2931, pruned_loss=0.06749, over 1423799.69 frames.], batch size: 37, lr: 5.78e-04
2022-05-27 06:44:57,365 INFO [train.py:842] (3/4) Epoch 9, batch 7300, loss[loss=0.2129, simple_loss=0.2938, pruned_loss=0.06599, over 7059.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2935, pruned_loss=0.06755, over 1426473.80 frames.], batch size: 18, lr: 5.77e-04
2022-05-27 06:45:35,782 INFO [train.py:842] (3/4) Epoch 9, batch 7350, loss[loss=0.2015, simple_loss=0.2821, pruned_loss=0.06042, over 7194.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2947, pruned_loss=0.0681, over 1426100.85 frames.], batch size: 23, lr: 5.77e-04
2022-05-27 06:46:15,087 INFO [train.py:842] (3/4) Epoch 9, batch 7400, loss[loss=0.2245, simple_loss=0.2912, pruned_loss=0.07889, over 7413.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2945, pruned_loss=0.06811, over 1428595.69 frames.], batch size: 18, lr: 5.77e-04
2022-05-27 06:46:53,827 INFO [train.py:842] (3/4) Epoch 9, batch 7450, loss[loss=0.2614, simple_loss=0.3411, pruned_loss=0.09079, over 7293.00 frames.], tot_loss[loss=0.215, simple_loss=0.2943, pruned_loss=0.06783, over 1430009.42 frames.], batch size: 25, lr: 5.77e-04
2022-05-27 06:47:32,689 INFO [train.py:842] (3/4) Epoch 9, batch 7500, loss[loss=0.3017, simple_loss=0.3512, pruned_loss=0.1261, over 4949.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2949, pruned_loss=0.06816, over 1420030.35 frames.], batch size: 52, lr: 5.77e-04
2022-05-27 06:48:11,222 INFO [train.py:842] (3/4) Epoch 9, batch 7550, loss[loss=0.2266, simple_loss=0.3108, pruned_loss=0.07125, over 7215.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2949, pruned_loss=0.06796, over 1417893.74 frames.], batch size: 23, lr: 5.76e-04
2022-05-27 06:48:50,197 INFO [train.py:842] (3/4) Epoch 9, batch 7600, loss[loss=0.1808, simple_loss=0.2587, pruned_loss=0.0514, over 7128.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2959, pruned_loss=0.06896, over 1417245.50 frames.], batch size: 17, lr: 5.76e-04
2022-05-27 06:49:28,755 INFO [train.py:842] (3/4) Epoch 9, batch 7650, loss[loss=0.1959, simple_loss=0.2904, pruned_loss=0.05066, over 7140.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2953, pruned_loss=0.06827, over 1419418.71 frames.], batch size: 20, lr: 5.76e-04
2022-05-27 06:50:07,691 INFO [train.py:842] (3/4) Epoch 9, batch 7700, loss[loss=0.1983, simple_loss=0.2603, pruned_loss=0.06817, over 7406.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2953, pruned_loss=0.06867, over 1420295.61 frames.], batch size: 18, lr: 5.76e-04
2022-05-27 06:50:46,216 INFO [train.py:842] (3/4) Epoch 9, batch 7750, loss[loss=0.2238, simple_loss=0.3002, pruned_loss=0.07372, over 6415.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2938, pruned_loss=0.06802, over 1415450.40 frames.], batch size: 38, lr: 5.76e-04
2022-05-27 06:51:25,048 INFO [train.py:842] (3/4) Epoch 9, batch 7800, loss[loss=0.1937, simple_loss=0.2716, pruned_loss=0.05793, over 7360.00 frames.], tot_loss[loss=0.215, simple_loss=0.2938, pruned_loss=0.06812, over 1422164.42 frames.], batch size: 19, lr: 5.76e-04
2022-05-27 06:52:03,439 INFO [train.py:842] (3/4) Epoch 9, batch 7850, loss[loss=0.218, simple_loss=0.2983, pruned_loss=0.06885, over 7292.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2949, pruned_loss=0.06874, over 1426898.43 frames.], batch size: 24, lr: 5.75e-04
2022-05-27 06:52:42,341 INFO [train.py:842] (3/4) Epoch 9, batch 7900, loss[loss=0.2452, simple_loss=0.3103, pruned_loss=0.09003, over 7355.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2944, pruned_loss=0.06806, over 1430368.89 frames.], batch size: 19, lr: 5.75e-04
2022-05-27 06:53:21,015 INFO [train.py:842] (3/4) Epoch 9, batch 7950, loss[loss=0.2393, simple_loss=0.3173, pruned_loss=0.08065, over 7145.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2944, pruned_loss=0.06856, over 1428507.15 frames.], batch size: 20, lr: 5.75e-04
2022-05-27 06:53:59,866 INFO [train.py:842] (3/4) Epoch 9, batch 8000, loss[loss=0.1928, simple_loss=0.2611, pruned_loss=0.06229, over 7157.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2943, pruned_loss=0.06901, over 1425724.24 frames.], batch size: 18, lr: 5.75e-04
2022-05-27 06:54:38,293 INFO [train.py:842] (3/4) Epoch 9, batch 8050, loss[loss=0.1902, simple_loss=0.2803, pruned_loss=0.05011, over 7267.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2947, pruned_loss=0.06905, over 1425854.17 frames.], batch size: 19, lr: 5.75e-04
2022-05-27 06:55:17,195 INFO [train.py:842] (3/4) Epoch 9, batch 8100, loss[loss=0.1987, simple_loss=0.272, pruned_loss=0.06273, over 7066.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2945, pruned_loss=0.06868, over 1425418.24 frames.], batch size: 18, lr: 5.75e-04
2022-05-27 06:55:55,749 INFO [train.py:842] (3/4) Epoch 9, batch 8150, loss[loss=0.2583, simple_loss=0.3362, pruned_loss=0.0902, over 6733.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2944, pruned_loss=0.06838, over 1423348.74 frames.], batch size: 31, lr: 5.74e-04
2022-05-27 06:56:34,509 INFO [train.py:842] (3/4) Epoch 9, batch 8200, loss[loss=0.2056, simple_loss=0.2884, pruned_loss=0.06137, over 7100.00 frames.], tot_loss[loss=0.2164, simple_loss=0.295, pruned_loss=0.06887, over 1417500.74 frames.], batch size: 21, lr: 5.74e-04
2022-05-27 06:57:13,131 INFO [train.py:842] (3/4) Epoch 9, batch 8250, loss[loss=0.1842, simple_loss=0.2561, pruned_loss=0.05617, over 7276.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2955, pruned_loss=0.06951, over 1421455.38 frames.], batch size: 17, lr: 5.74e-04
2022-05-27 06:57:51,736 INFO [train.py:842] (3/4) Epoch 9, batch 8300, loss[loss=0.2442, simple_loss=0.3416, pruned_loss=0.07343, over 7319.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2965, pruned_loss=0.07023, over 1411885.89 frames.], batch size: 21, lr: 5.74e-04
2022-05-27 06:58:30,529 INFO [train.py:842] (3/4) Epoch 9, batch 8350, loss[loss=0.1992, simple_loss=0.2901, pruned_loss=0.05414, over 7321.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2939, pruned_loss=0.06859, over 1416452.24 frames.], batch size: 21, lr: 5.74e-04
2022-05-27 06:59:09,808 INFO [train.py:842] (3/4) Epoch 9, batch 8400, loss[loss=0.1828, simple_loss=0.2752, pruned_loss=0.04519, over 7099.00 frames.], tot_loss[loss=0.215, simple_loss=0.2936, pruned_loss=0.0682, over 1422459.22 frames.], batch size: 28, lr: 5.74e-04
2022-05-27 06:59:48,385 INFO [train.py:842] (3/4) Epoch 9, batch 8450, loss[loss=0.2177, simple_loss=0.3013, pruned_loss=0.06712, over 7123.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2922, pruned_loss=0.06705, over 1424902.77 frames.], batch size: 21, lr: 5.73e-04
2022-05-27 07:00:27,399 INFO [train.py:842] (3/4) Epoch 9, batch 8500, loss[loss=0.1885, simple_loss=0.271, pruned_loss=0.05296, over 7163.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2926, pruned_loss=0.06696, over 1424197.60 frames.], batch size: 19, lr: 5.73e-04
2022-05-27 07:01:05,909 INFO [train.py:842] (3/4) Epoch 9, batch 8550, loss[loss=0.2443, simple_loss=0.3227, pruned_loss=0.08302, over 6263.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2935, pruned_loss=0.06742, over 1419819.62 frames.], batch size: 37, lr: 5.73e-04
2022-05-27 07:01:44,712 INFO [train.py:842] (3/4) Epoch 9, batch 8600, loss[loss=0.3531, simple_loss=0.4087, pruned_loss=0.1488, over 5476.00 frames.], tot_loss[loss=0.2156, simple_loss=0.295, pruned_loss=0.06816, over 1416868.15 frames.], batch size: 52, lr: 5.73e-04
2022-05-27 07:02:23,124 INFO [train.py:842] (3/4) Epoch 9, batch 8650, loss[loss=0.2151, simple_loss=0.298, pruned_loss=0.06613, over 7324.00 frames.], tot_loss[loss=0.2163, simple_loss=0.296, pruned_loss=0.0683, over 1421177.44 frames.], batch size: 21, lr: 5.73e-04
2022-05-27 07:03:02,353 INFO [train.py:842] (3/4) Epoch 9, batch 8700, loss[loss=0.1558, simple_loss=0.2433, pruned_loss=0.03414, over 7354.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2939, pruned_loss=0.06778, over 1421588.96 frames.], batch size: 19, lr: 5.72e-04
2022-05-27 07:03:40,725 INFO [train.py:842] (3/4) Epoch 9, batch 8750, loss[loss=0.2188, simple_loss=0.301, pruned_loss=0.06833, over 7168.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2947, pruned_loss=0.06778, over 1418874.80 frames.], batch size: 18, lr: 5.72e-04
2022-05-27 07:04:19,478 INFO [train.py:842] (3/4) Epoch 9, batch 8800, loss[loss=0.2714, simple_loss=0.3485, pruned_loss=0.09716, over 7185.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2954, pruned_loss=0.06786, over 1419517.98 frames.], batch size: 23, lr: 5.72e-04
2022-05-27 07:04:57,938 INFO [train.py:842] (3/4) Epoch 9, batch 8850, loss[loss=0.2094, simple_loss=0.3064, pruned_loss=0.0562, over 7303.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2944, pruned_loss=0.06774, over 1410315.22 frames.], batch size: 24, lr: 5.72e-04
2022-05-27 07:05:37,294 INFO [train.py:842] (3/4) Epoch 9, batch 8900, loss[loss=0.2583, simple_loss=0.338, pruned_loss=0.08931, over 7389.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2941, pruned_loss=0.06821, over 1405854.47 frames.], batch size: 23, lr: 5.72e-04
2022-05-27 07:06:15,876 INFO [train.py:842] (3/4) Epoch 9, batch 8950, loss[loss=0.2352, simple_loss=0.3092, pruned_loss=0.08059, over 7379.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2949, pruned_loss=0.06966, over 1399727.88 frames.], batch size: 19, lr: 5.72e-04
2022-05-27 07:06:55,100 INFO [train.py:842] (3/4) Epoch 9, batch 9000, loss[loss=0.2041, simple_loss=0.2834, pruned_loss=0.06241, over 6525.00 frames.], tot_loss[loss=0.216, simple_loss=0.2933, pruned_loss=0.06937, over 1392721.04 frames.], batch size: 38, lr: 5.71e-04
2022-05-27 07:06:55,100 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 07:07:04,565 INFO [train.py:871] (3/4) Epoch 9, validation: loss=0.1768, simple_loss=0.2774, pruned_loss=0.03806, over 868885.00 frames.
2022-05-27 07:07:43,600 INFO [train.py:842] (3/4) Epoch 9, batch 9050, loss[loss=0.2447, simple_loss=0.3129, pruned_loss=0.0882, over 7288.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2949, pruned_loss=0.07041, over 1386529.84 frames.], batch size: 18, lr: 5.71e-04
2022-05-27 07:08:21,640 INFO [train.py:842] (3/4) Epoch 9, batch 9100, loss[loss=0.242, simple_loss=0.3318, pruned_loss=0.07608, over 4934.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2997, pruned_loss=0.07344, over 1351590.00 frames.], batch size: 53, lr: 5.71e-04
2022-05-27 07:08:59,055 INFO [train.py:842] (3/4) Epoch 9, batch 9150, loss[loss=0.2375, simple_loss=0.3077, pruned_loss=0.08365, over 4780.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3035, pruned_loss=0.07614, over 1299302.42 frames.], batch size: 52, lr: 5.71e-04
2022-05-27 07:09:51,890 INFO [train.py:842] (3/4) Epoch 10, batch 0, loss[loss=0.2181, simple_loss=0.3051, pruned_loss=0.06557, over 7412.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3051, pruned_loss=0.06557, over 7412.00 frames.], batch size: 21, lr: 5.49e-04
2022-05-27 07:10:30,751 INFO [train.py:842] (3/4) Epoch 10, batch 50, loss[loss=0.2152, simple_loss=0.298, pruned_loss=0.06616, over 7210.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2968, pruned_loss=0.06923, over 321422.94 frames.], batch size: 23, lr: 5.49e-04
2022-05-27 07:11:09,445 INFO [train.py:842] (3/4) Epoch 10, batch 100, loss[loss=0.2273, simple_loss=0.3061, pruned_loss=0.07426, over 4850.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2931, pruned_loss=0.06731, over 556837.84 frames.], batch size: 52, lr: 5.48e-04
2022-05-27 07:11:48,013 INFO [train.py:842] (3/4) Epoch 10, batch 150, loss[loss=0.1907, simple_loss=0.2753, pruned_loss=0.05307, over 7431.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2931, pruned_loss=0.06661, over 750477.91 frames.], batch size: 20, lr: 5.48e-04
2022-05-27 07:12:26,863 INFO [train.py:842] (3/4) Epoch 10, batch 200, loss[loss=0.2104, simple_loss=0.2925, pruned_loss=0.06413, over 7439.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2947, pruned_loss=0.06753, over 897599.08 frames.], batch size: 20, lr: 5.48e-04
2022-05-27 07:13:05,275 INFO [train.py:842] (3/4) Epoch 10, batch 250, loss[loss=0.1804, simple_loss=0.2651, pruned_loss=0.04791, over 7170.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2961, pruned_loss=0.06826, over 1010500.62 frames.], batch size: 18, lr: 5.48e-04
2022-05-27 07:13:44,145 INFO [train.py:842] (3/4) Epoch 10, batch 300, loss[loss=0.193, simple_loss=0.2791, pruned_loss=0.05344, over 7325.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2953, pruned_loss=0.06764, over 1104207.83 frames.], batch size: 20, lr: 5.48e-04
2022-05-27 07:14:22,644 INFO [train.py:842] (3/4) Epoch 10, batch 350, loss[loss=0.2003, simple_loss=0.2892, pruned_loss=0.05566, over 7193.00 frames.], tot_loss[loss=0.2134, simple_loss=0.294, pruned_loss=0.06645, over 1172631.69 frames.], batch size: 23, lr: 5.48e-04
2022-05-27 07:15:01,361 INFO [train.py:842] (3/4) Epoch 10, batch 400, loss[loss=0.3016, simple_loss=0.3641, pruned_loss=0.1196, over 7202.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2953, pruned_loss=0.06722, over 1222623.62 frames.], batch size: 26, lr: 5.47e-04
2022-05-27 07:15:39,910 INFO [train.py:842] (3/4) Epoch 10, batch 450, loss[loss=0.2422, simple_loss=0.3192, pruned_loss=0.08257, over 6442.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2949, pruned_loss=0.06641, over 1260738.44 frames.], batch size: 38, lr: 5.47e-04
2022-05-27 07:16:18,864 INFO [train.py:842] (3/4) Epoch 10, batch 500, loss[loss=0.2149, simple_loss=0.2943, pruned_loss=0.06771, over 7154.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2952, pruned_loss=0.06705, over 1296248.67 frames.], batch size: 19, lr: 5.47e-04
2022-05-27 07:16:57,398 INFO [train.py:842] (3/4) Epoch 10, batch 550, loss[loss=0.2109, simple_loss=0.2902, pruned_loss=0.06578, over 7142.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2948, pruned_loss=0.06707, over 1324960.80 frames.], batch size: 17, lr: 5.47e-04
2022-05-27 07:17:36,426 INFO [train.py:842] (3/4) Epoch 10, batch 600, loss[loss=0.193, simple_loss=0.264, pruned_loss=0.06094, over 7279.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2948, pruned_loss=0.06739, over 1346270.67 frames.], batch size: 18, lr: 5.47e-04
2022-05-27 07:18:15,052 INFO [train.py:842] (3/4) Epoch 10, batch 650, loss[loss=0.2401, simple_loss=0.3143, pruned_loss=0.08298, over 7148.00 frames.], tot_loss[loss=0.213, simple_loss=0.2935, pruned_loss=0.06632, over 1362492.69 frames.], batch size: 26, lr: 5.47e-04
2022-05-27 07:18:53,923 INFO [train.py:842] (3/4) Epoch 10, batch 700, loss[loss=0.228, simple_loss=0.3142, pruned_loss=0.07088, over 7317.00 frames.], tot_loss[loss=0.213, simple_loss=0.2935, pruned_loss=0.06625, over 1377328.20 frames.], batch size: 25, lr: 5.46e-04
2022-05-27 07:19:32,421 INFO [train.py:842] (3/4) Epoch 10, batch 750, loss[loss=0.2146, simple_loss=0.2894, pruned_loss=0.06989, over 7426.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2929, pruned_loss=0.06598, over 1386503.26 frames.], batch size: 20, lr: 5.46e-04
2022-05-27 07:20:11,294 INFO [train.py:842] (3/4) Epoch 10, batch 800, loss[loss=0.2686, simple_loss=0.3532, pruned_loss=0.09196, over 7286.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2916, pruned_loss=0.06503, over 1393692.08 frames.], batch size: 24, lr: 5.46e-04
2022-05-27 07:20:50,042 INFO [train.py:842] (3/4) Epoch 10, batch 850, loss[loss=0.2137, simple_loss=0.2953, pruned_loss=0.06602, over 6349.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2915, pruned_loss=0.06482, over 1396709.94 frames.], batch size: 37, lr: 5.46e-04
2022-05-27 07:21:29,286 INFO [train.py:842] (3/4) Epoch 10, batch 900, loss[loss=0.2624, simple_loss=0.3324, pruned_loss=0.09621, over 7319.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2914, pruned_loss=0.06504, over 1407196.74 frames.], batch size: 21, lr: 5.46e-04
2022-05-27 07:22:07,882 INFO [train.py:842] (3/4) Epoch 10, batch 950, loss[loss=0.1972, simple_loss=0.2966, pruned_loss=0.04891, over 7155.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2933, pruned_loss=0.06624, over 1407318.03 frames.], batch size: 26, lr: 5.46e-04
2022-05-27 07:22:46,824 INFO [train.py:842] (3/4) Epoch 10, batch 1000, loss[loss=0.2852, simple_loss=0.3387, pruned_loss=0.1158, over 7327.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2929, pruned_loss=0.06593, over 1414860.79 frames.], batch size: 20, lr: 5.46e-04
2022-05-27 07:23:25,638 INFO [train.py:842] (3/4) Epoch 10, batch 1050, loss[loss=0.1907, simple_loss=0.2727, pruned_loss=0.05433, over 7171.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2915, pruned_loss=0.06522, over 1416967.97 frames.], batch size: 28, lr: 5.45e-04
2022-05-27 07:24:04,255 INFO [train.py:842] (3/4) Epoch 10, batch 1100, loss[loss=0.2252, simple_loss=0.3073, pruned_loss=0.07151, over 7116.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2925, pruned_loss=0.0663, over 1417277.45 frames.], batch size: 28, lr: 5.45e-04
2022-05-27 07:24:42,902 INFO [train.py:842] (3/4) Epoch 10, batch 1150, loss[loss=0.2041, simple_loss=0.2881, pruned_loss=0.06002, over 7323.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2935, pruned_loss=0.06674, over 1421646.59 frames.], batch size: 20, lr: 5.45e-04
2022-05-27 07:25:21,666 INFO [train.py:842] (3/4) Epoch 10, batch 1200, loss[loss=0.2568, simple_loss=0.3299, pruned_loss=0.09191, over 7210.00 frames.], tot_loss[loss=0.214, simple_loss=0.294, pruned_loss=0.06702, over 1420895.38 frames.], batch size: 23, lr: 5.45e-04
2022-05-27 07:26:00,242 INFO [train.py:842] (3/4) Epoch 10, batch 1250, loss[loss=0.2413, simple_loss=0.3028, pruned_loss=0.08995, over 7277.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2944, pruned_loss=0.06756, over 1418304.37 frames.], batch size: 17, lr: 5.45e-04
2022-05-27 07:26:39,228 INFO [train.py:842] (3/4) Epoch 10, batch 1300, loss[loss=0.1864, simple_loss=0.2569, pruned_loss=0.05796, over 7000.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2949, pruned_loss=0.06917, over 1416140.40 frames.], batch size: 16, lr: 5.45e-04
2022-05-27 07:27:17,673 INFO [train.py:842] (3/4) Epoch 10, batch 1350, loss[loss=0.1889, simple_loss=0.2767, pruned_loss=0.05053, over 7311.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2942, pruned_loss=0.06856, over 1414659.10 frames.], batch size: 21, lr: 5.44e-04
2022-05-27 07:27:56,266 INFO [train.py:842] (3/4) Epoch 10, batch 1400, loss[loss=0.2398, simple_loss=0.3184, pruned_loss=0.0806, over 7116.00 frames.], tot_loss[loss=0.2158, simple_loss=0.295, pruned_loss=0.06827, over 1418110.33 frames.], batch size: 21, lr: 5.44e-04
2022-05-27 07:28:35,058 INFO [train.py:842] (3/4) Epoch 10, batch 1450, loss[loss=0.2263, simple_loss=0.3082, pruned_loss=0.0722, over 7277.00 frames.], tot_loss[loss=0.2148, simple_loss=0.294, pruned_loss=0.06778, over 1418640.92 frames.], batch size: 25, lr: 5.44e-04
2022-05-27 07:29:13,794 INFO [train.py:842] (3/4) Epoch 10, batch 1500, loss[loss=0.2576, simple_loss=0.3238, pruned_loss=0.09571, over 5288.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2951, pruned_loss=0.06878, over 1414601.89 frames.], batch size: 52, lr: 5.44e-04
2022-05-27 07:29:52,334 INFO [train.py:842] (3/4) Epoch 10, batch 1550, loss[loss=0.1733, simple_loss=0.2537, pruned_loss=0.04645, over 7356.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2937, pruned_loss=0.06735, over 1419319.88 frames.], batch size: 19, lr: 5.44e-04
2022-05-27 07:30:31,302 INFO [train.py:842] (3/4) Epoch 10, batch 1600, loss[loss=0.1916, simple_loss=0.2769, pruned_loss=0.05313, over 7259.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2929, pruned_loss=0.06693, over 1419101.49 frames.], batch size: 19, lr: 5.44e-04
2022-05-27 07:31:09,817 INFO [train.py:842] (3/4) Epoch 10, batch 1650, loss[loss=0.2225, simple_loss=0.3019, pruned_loss=0.07155, over 7412.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2932, pruned_loss=0.06698, over 1416731.84 frames.], batch size: 21, lr: 5.43e-04
2022-05-27 07:31:48,612 INFO [train.py:842] (3/4) Epoch 10, batch 1700, loss[loss=0.2282, simple_loss=0.3135, pruned_loss=0.07144, over 7292.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2929, pruned_loss=0.06637, over 1414498.51 frames.], batch size: 24, lr: 5.43e-04
2022-05-27 07:32:27,166 INFO [train.py:842] (3/4) Epoch 10, batch 1750, loss[loss=0.2076, simple_loss=0.2811, pruned_loss=0.06703, over 6757.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2928, pruned_loss=0.06666, over 1405917.29 frames.], batch size: 15, lr: 5.43e-04
2022-05-27 07:33:05,912 INFO [train.py:842] (3/4) Epoch 10, batch 1800, loss[loss=0.1738, simple_loss=0.26, pruned_loss=0.04385, over 7360.00 frames.], tot_loss[loss=0.2132, simple_loss=0.293, pruned_loss=0.06674, over 1410667.26 frames.], batch size: 19, lr: 5.43e-04
2022-05-27 07:33:44,443 INFO [train.py:842] (3/4) Epoch 10, batch 1850, loss[loss=0.1821, simple_loss=0.2632, pruned_loss=0.05051, over 7341.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2937, pruned_loss=0.06688, over 1411345.52 frames.], batch size: 19, lr: 5.43e-04
2022-05-27 07:34:23,392 INFO [train.py:842] (3/4) Epoch 10, batch 1900, loss[loss=0.2101, simple_loss=0.2815, pruned_loss=0.06936, over 7288.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2936, pruned_loss=0.0671, over 1414934.50 frames.], batch size: 18, lr: 5.43e-04
2022-05-27 07:35:02,031 INFO [train.py:842] (3/4) Epoch 10, batch 1950, loss[loss=0.2478, simple_loss=0.3216, pruned_loss=0.08701, over 7198.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2937, pruned_loss=0.06731, over 1414199.83 frames.], batch size: 23, lr: 5.42e-04
2022-05-27 07:35:40,864 INFO [train.py:842] (3/4) Epoch 10, batch 2000, loss[loss=0.1865, simple_loss=0.2731, pruned_loss=0.05, over 7238.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2926, pruned_loss=0.06661, over 1417654.39 frames.], batch size: 20, lr: 5.42e-04
2022-05-27 07:36:19,554 INFO [train.py:842] (3/4) Epoch 10, batch 2050, loss[loss=0.2153, simple_loss=0.3098, pruned_loss=0.06042, over 7199.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2928, pruned_loss=0.06642, over 1420045.15 frames.], batch size: 23, lr: 5.42e-04
2022-05-27 07:36:58,490 INFO [train.py:842] (3/4) Epoch 10, batch 2100, loss[loss=0.1745, simple_loss=0.2763, pruned_loss=0.03636, over 7140.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2905, pruned_loss=0.06466, over 1424655.62 frames.], batch size: 20, lr: 5.42e-04
2022-05-27 07:37:37,363 INFO [train.py:842] (3/4) Epoch 10, batch 2150, loss[loss=0.2267, simple_loss=0.2886, pruned_loss=0.08244, over 7397.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2895, pruned_loss=0.06454, over 1427302.89 frames.], batch size: 18, lr: 5.42e-04
2022-05-27 07:38:16,089 INFO [train.py:842] (3/4) Epoch 10, batch 2200, loss[loss=0.2148, simple_loss=0.2906, pruned_loss=0.06949, over 6469.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2907, pruned_loss=0.06508, over 1427467.53 frames.], batch size: 38, lr: 5.42e-04
2022-05-27 07:38:54,671 INFO [train.py:842] (3/4) Epoch 10, batch 2250, loss[loss=0.2141, simple_loss=0.2957, pruned_loss=0.06628, over 7323.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2897, pruned_loss=0.06465, over 1429087.19 frames.], batch size: 21, lr: 5.42e-04
2022-05-27 07:39:33,347 INFO [train.py:842] (3/4) Epoch 10, batch 2300, loss[loss=0.1837, simple_loss=0.2797, pruned_loss=0.04387, over 7146.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2899, pruned_loss=0.06451, over 1426384.20 frames.], batch size: 20, lr: 5.41e-04
2022-05-27 07:40:11,937 INFO [train.py:842] (3/4) Epoch 10, batch 2350, loss[loss=0.2535, simple_loss=0.328, pruned_loss=0.0895, over 7211.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2898, pruned_loss=0.06496, over 1424875.50 frames.], batch size: 22, lr: 5.41e-04
2022-05-27 07:40:50,770 INFO [train.py:842] (3/4) Epoch 10, batch 2400, loss[loss=0.2029, simple_loss=0.2789, pruned_loss=0.06345, over 7283.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2896, pruned_loss=0.06466, over 1426189.88 frames.], batch size: 18, lr: 5.41e-04
2022-05-27 07:41:29,392 INFO [train.py:842] (3/4) Epoch 10, batch 2450, loss[loss=0.2, simple_loss=0.2807, pruned_loss=0.05962, over 7062.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2895, pruned_loss=0.06449, over 1429532.16 frames.], batch size: 18, lr: 5.41e-04
2022-05-27 07:42:08,594 INFO [train.py:842] (3/4) Epoch 10, batch 2500, loss[loss=0.1625, simple_loss=0.2563, pruned_loss=0.03434, over 7316.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2907, pruned_loss=0.06541, over 1428474.60 frames.], batch size: 21, lr: 5.41e-04
2022-05-27 07:42:47,183 INFO [train.py:842] (3/4) Epoch 10, batch 2550, loss[loss=0.2952, simple_loss=0.3581, pruned_loss=0.1162, over 7208.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2915, pruned_loss=0.06609, over 1425903.69 frames.], batch size: 21, lr: 5.41e-04
2022-05-27 07:43:26,347 INFO [train.py:842] (3/4) Epoch 10, batch 2600, loss[loss=0.2691, simple_loss=0.3472, pruned_loss=0.0955, over 7174.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2927, pruned_loss=0.06689, over 1428753.76 frames.], batch size: 26, lr: 5.40e-04
2022-05-27 07:44:04,678 INFO [train.py:842] (3/4) Epoch 10, batch 2650, loss[loss=0.1945, simple_loss=0.2733, pruned_loss=0.05784, over 7326.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2914, pruned_loss=0.06568, over 1424671.25 frames.], batch size: 22, lr: 5.40e-04
2022-05-27 07:44:43,520 INFO [train.py:842] (3/4) Epoch 10, batch 2700, loss[loss=0.2112, simple_loss=0.3009, pruned_loss=0.06073, over 6739.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2906, pruned_loss=0.06543, over 1424836.07 frames.], batch size: 31, lr: 5.40e-04
2022-05-27 07:45:22,194 INFO [train.py:842] (3/4) Epoch 10, batch 2750, loss[loss=0.2656, simple_loss=0.338, pruned_loss=0.09661, over 6696.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2901, pruned_loss=0.06519, over 1423060.44 frames.], batch size: 31, lr: 5.40e-04
2022-05-27 07:46:01,459 INFO [train.py:842] (3/4) Epoch 10, batch 2800, loss[loss=0.256, simple_loss=0.3194, pruned_loss=0.09631, over 7382.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2896, pruned_loss=0.06472, over 1428901.55 frames.], batch size: 23, lr: 5.40e-04
2022-05-27 07:46:50,673 INFO [train.py:842] (3/4) Epoch 10, batch 2850, loss[loss=0.2146, simple_loss=0.2969, pruned_loss=0.06619, over 7342.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2891, pruned_loss=0.06463, over 1426512.14 frames.], batch size: 22, lr: 5.40e-04
2022-05-27 07:47:29,744 INFO [train.py:842] (3/4) Epoch 10, batch 2900, loss[loss=0.1915, simple_loss=0.2777, pruned_loss=0.05267, over 7443.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2888, pruned_loss=0.06451, over 1425721.83 frames.], batch size: 22, lr: 5.39e-04
2022-05-27 07:48:08,431 INFO [train.py:842] (3/4) Epoch 10, batch 2950, loss[loss=0.1868, simple_loss=0.2593, pruned_loss=0.05715, over 7259.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2883, pruned_loss=0.06449, over 1426419.96 frames.], batch size: 18, lr: 5.39e-04
2022-05-27 07:48:47,537 INFO [train.py:842] (3/4) Epoch 10, batch 3000, loss[loss=0.2043, simple_loss=0.2675, pruned_loss=0.07059, over 7276.00 frames.], tot_loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06485, over 1426008.34 frames.], batch size: 17, lr: 5.39e-04
2022-05-27 07:48:47,538 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 07:48:56,971 INFO [train.py:871] (3/4) Epoch 10, validation: loss=0.1722, simple_loss=0.2729, pruned_loss=0.03575, over 868885.00 frames.
2022-05-27 07:49:35,672 INFO [train.py:842] (3/4) Epoch 10, batch 3050, loss[loss=0.2537, simple_loss=0.3362, pruned_loss=0.08558, over 7161.00 frames.], tot_loss[loss=0.21, simple_loss=0.2894, pruned_loss=0.06535, over 1425593.59 frames.], batch size: 19, lr: 5.39e-04
2022-05-27 07:50:14,630 INFO [train.py:842] (3/4) Epoch 10, batch 3100, loss[loss=0.2486, simple_loss=0.3216, pruned_loss=0.08776, over 7115.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2915, pruned_loss=0.06661, over 1428340.94 frames.], batch size: 21, lr: 5.39e-04
2022-05-27 07:50:53,138 INFO [train.py:842] (3/4) Epoch 10, batch 3150, loss[loss=0.2272, simple_loss=0.3146, pruned_loss=0.06987, over 7317.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2917, pruned_loss=0.0667, over 1424868.65 frames.], batch size: 21, lr: 5.39e-04
2022-05-27 07:51:32,415 INFO [train.py:842] (3/4) Epoch 10, batch 3200, loss[loss=0.1822, simple_loss=0.2804, pruned_loss=0.04206, over 7238.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2909, pruned_loss=0.06579, over 1426180.06 frames.], batch size: 20, lr: 5.39e-04
2022-05-27 07:52:11,120 INFO [train.py:842] (3/4) Epoch 10, batch 3250, loss[loss=0.1871, simple_loss=0.2774, pruned_loss=0.04838, over 7405.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2912, pruned_loss=0.06612, over 1427416.67 frames.], batch size: 21, lr: 5.38e-04
2022-05-27 07:52:49,913 INFO [train.py:842] (3/4) Epoch 10, batch 3300, loss[loss=0.2084, simple_loss=0.3037, pruned_loss=0.05652, over 7212.00 frames.], tot_loss[loss=0.2115, simple_loss=0.2916, pruned_loss=0.06568, over 1428165.70 frames.], batch size: 22, lr: 5.38e-04
2022-05-27 07:53:28,341 INFO [train.py:842] (3/4) Epoch 10, batch 3350, loss[loss=0.1941, simple_loss=0.2868, pruned_loss=0.05071, over 7188.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2919, pruned_loss=0.06581, over 1429348.11 frames.], batch size: 23, lr: 5.38e-04
2022-05-27 07:54:07,104 INFO [train.py:842] (3/4) Epoch 10, batch 3400, loss[loss=0.1488, simple_loss=0.227, pruned_loss=0.0353, over 7265.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2921, pruned_loss=0.06603, over 1426261.44 frames.], batch size: 17, lr: 5.38e-04
2022-05-27 07:54:45,627 INFO [train.py:842] (3/4) Epoch 10, batch 3450, loss[loss=0.2139, simple_loss=0.3066, pruned_loss=0.06064, over 7316.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2911, pruned_loss=0.06519, over 1425683.11 frames.], batch size: 24, lr: 5.38e-04
2022-05-27 07:55:24,452 INFO [train.py:842] (3/4) Epoch 10, batch 3500, loss[loss=0.1964, simple_loss=0.2739, pruned_loss=0.05942, over 7425.00 frames.], tot_loss[loss=0.2097, simple_loss=0.29, pruned_loss=0.06469, over 1425717.13 frames.], batch size: 21, lr: 5.38e-04
2022-05-27 07:56:03,149 INFO [train.py:842] (3/4) Epoch 10, batch 3550, loss[loss=0.2087, simple_loss=0.293, pruned_loss=0.0622, over 7079.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2887, pruned_loss=0.064, over 1428178.05 frames.], batch size: 28, lr: 5.37e-04
2022-05-27 07:56:42,269 INFO [train.py:842] (3/4) Epoch 10, batch 3600, loss[loss=0.241, simple_loss=0.3093, pruned_loss=0.0864, over 7076.00 frames.], tot_loss[loss=0.2087, simple_loss=0.289, pruned_loss=0.06423, over 1427775.09 frames.], batch size: 28, lr: 5.37e-04
2022-05-27 07:57:20,971 INFO [train.py:842] (3/4) Epoch 10, batch 3650, loss[loss=0.1936, simple_loss=0.267, pruned_loss=0.06014, over 7054.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2899, pruned_loss=0.06493, over 1423057.25 frames.], batch size: 18, lr: 5.37e-04
2022-05-27 07:57:59,623 INFO [train.py:842] (3/4) Epoch 10, batch 3700, loss[loss=0.2197, simple_loss=0.2885, pruned_loss=0.07544, over 7276.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2906, pruned_loss=0.06516, over 1425175.88 frames.], batch size: 17, lr: 5.37e-04
2022-05-27 07:58:38,200 INFO [train.py:842] (3/4) Epoch 10, batch 3750, loss[loss=0.2067, simple_loss=0.3065, pruned_loss=0.05341, over 7159.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2912, pruned_loss=0.06507, over 1428285.13 frames.], batch size: 19, lr: 5.37e-04
2022-05-27 07:59:17,019 INFO [train.py:842] (3/4) Epoch 10, batch 3800, loss[loss=0.1917, simple_loss=0.2705, pruned_loss=0.05649, over 7425.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2921, pruned_loss=0.06531, over 1426349.18 frames.], batch size: 20, lr: 5.37e-04
2022-05-27 07:59:55,532 INFO [train.py:842] (3/4) Epoch 10, batch 3850, loss[loss=0.1937, simple_loss=0.2737, pruned_loss=0.05686, over 7069.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2921, pruned_loss=0.06536, over 1425415.22 frames.], batch size: 18, lr: 5.36e-04
2022-05-27 08:00:34,405 INFO [train.py:842] (3/4) Epoch 10, batch 3900, loss[loss=0.2763, simple_loss=0.3442, pruned_loss=0.1042, over 7141.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2919, pruned_loss=0.06575, over 1427127.92 frames.], batch size: 20, lr: 5.36e-04
2022-05-27 08:01:13,255 INFO [train.py:842] (3/4) Epoch 10, batch 3950, loss[loss=0.1959, simple_loss=0.2713, pruned_loss=0.06023, over 7067.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2909, pruned_loss=0.06477, over 1425402.66 frames.], batch size: 18, lr: 5.36e-04
2022-05-27 08:01:51,965 INFO [train.py:842] (3/4) Epoch 10, batch 4000, loss[loss=0.1846, simple_loss=0.2539, pruned_loss=0.05765, over 7269.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2924, pruned_loss=0.06574, over 1423788.28 frames.], batch size: 17, lr: 5.36e-04
2022-05-27 08:02:30,698 INFO [train.py:842] (3/4) Epoch 10, batch 4050, loss[loss=0.1991, simple_loss=0.2818, pruned_loss=0.05818, over 7236.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2921, pruned_loss=0.06616, over 1423922.76 frames.], batch size: 20, lr: 5.36e-04
2022-05-27 08:03:09,549 INFO [train.py:842] (3/4) Epoch 10, batch 4100, loss[loss=0.1932, simple_loss=0.2827, pruned_loss=0.0518, over 7331.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2922, pruned_loss=0.06647, over 1423494.76 frames.], batch size: 20, lr: 5.36e-04
2022-05-27 08:03:48,071 INFO [train.py:842] (3/4) Epoch 10, batch 4150, loss[loss=0.3095, simple_loss=0.3658, pruned_loss=0.1266, over 7375.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2919, pruned_loss=0.06627, over 1426805.14 frames.], batch size: 23, lr: 5.36e-04
2022-05-27 08:04:26,991 INFO [train.py:842] (3/4) Epoch 10, batch 4200, loss[loss=0.2573, simple_loss=0.3342, pruned_loss=0.09018, over 7298.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2927, pruned_loss=0.06669, over 1425465.52 frames.], batch size: 24, lr: 5.35e-04
2022-05-27 08:05:05,678 INFO [train.py:842] (3/4) Epoch 10, batch 4250, loss[loss=0.2394, simple_loss=0.3123, pruned_loss=0.08324, over 6684.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2925, pruned_loss=0.06607, over 1427899.54 frames.], batch size: 31, lr: 5.35e-04
2022-05-27 08:05:44,546 INFO [train.py:842] (3/4) Epoch 10, batch 4300, loss[loss=0.2103, simple_loss=0.2746, pruned_loss=0.07296, over 7279.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2934, pruned_loss=0.0664, over 1427042.22 frames.], batch size: 17, lr: 5.35e-04
2022-05-27 08:06:22,944 INFO [train.py:842] (3/4) Epoch 10, batch 4350, loss[loss=0.2512, simple_loss=0.3278, pruned_loss=0.08731, over 7165.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2952, pruned_loss=0.06783, over 1419260.23 frames.], batch size: 26, lr: 5.35e-04
2022-05-27 08:07:01,894 INFO [train.py:842] (3/4) Epoch 10, batch 4400, loss[loss=0.1929, simple_loss=0.2771, pruned_loss=0.05429, over 7144.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2941, pruned_loss=0.0675, over 1420262.46 frames.], batch size: 20, lr: 5.35e-04
2022-05-27 08:08:01,223 INFO [train.py:842] (3/4) Epoch 10, batch 4450, loss[loss=0.2476, simple_loss=0.3195, pruned_loss=0.08785, over 7338.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2956, pruned_loss=0.06878, over 1419384.24 frames.], batch size: 22, lr: 5.35e-04
2022-05-27 08:08:50,713 INFO [train.py:842] (3/4) Epoch 10, batch 4500, loss[loss=0.2448, simple_loss=0.3279, pruned_loss=0.08087, over 7104.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2952, pruned_loss=0.06898, over 1419658.70 frames.], batch size: 21, lr: 5.35e-04
2022-05-27 08:09:29,253 INFO [train.py:842] (3/4) Epoch 10, batch 4550, loss[loss=0.2089, simple_loss=0.2918, pruned_loss=0.06301, over 7414.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2949, pruned_loss=0.06863, over 1417783.66 frames.], batch size: 20, lr: 5.34e-04
2022-05-27 08:10:07,950 INFO [train.py:842] (3/4) Epoch 10, batch 4600, loss[loss=0.2055, simple_loss=0.2799, pruned_loss=0.06552, over 7226.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2954, pruned_loss=0.0682, over 1421918.18 frames.], batch size: 21, lr: 5.34e-04
2022-05-27 08:10:46,422 INFO [train.py:842] (3/4) Epoch 10, batch 4650, loss[loss=0.2001, simple_loss=0.295, pruned_loss=0.0526, over 7195.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2952, pruned_loss=0.06816, over 1419428.26 frames.], batch size: 23, lr: 5.34e-04
2022-05-27 08:11:25,346 INFO [train.py:842] (3/4) Epoch 10, batch 4700, loss[loss=0.2179, simple_loss=0.2978, pruned_loss=0.06903, over 7220.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2945, pruned_loss=0.06778, over 1412148.62 frames.], batch size: 21, lr: 5.34e-04
2022-05-27 08:12:03,851 INFO [train.py:842] (3/4) Epoch 10, batch 4750, loss[loss=0.1763, simple_loss=0.2587, pruned_loss=0.04694, over 7003.00 frames.], tot_loss[loss=0.213, simple_loss=0.2931, pruned_loss=0.06648, over 1415602.05 frames.], batch size: 16, lr: 5.34e-04
2022-05-27 08:12:42,497 INFO [train.py:842] (3/4) Epoch 10, batch 4800, loss[loss=0.2061, simple_loss=0.2919, pruned_loss=0.06016, over 7297.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2928, pruned_loss=0.06646, over 1416403.24 frames.], batch size: 25, lr: 5.34e-04
2022-05-27 08:13:21,011 INFO [train.py:842] (3/4) Epoch 10, batch 4850, loss[loss=0.1972, simple_loss=0.291, pruned_loss=0.0517, over 7107.00 frames.], tot_loss[loss=0.213, simple_loss=0.2928, pruned_loss=0.0666, over 1418729.68 frames.], batch size: 21, lr: 5.33e-04
2022-05-27 08:14:00,184 INFO [train.py:842] (3/4) Epoch 10, batch 4900, loss[loss=0.2305, simple_loss=0.2917, pruned_loss=0.08467, over 7405.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2918, pruned_loss=0.06594, over 1422907.17 frames.], batch size: 18, lr: 5.33e-04
2022-05-27 08:14:38,922 INFO [train.py:842] (3/4) Epoch 10, batch 4950, loss[loss=0.2338, simple_loss=0.2941, pruned_loss=0.08675, over 7293.00 frames.], tot_loss[loss=0.2099, simple_loss=0.29, pruned_loss=0.06486, over 1423970.53 frames.], batch size: 16, lr: 5.33e-04
2022-05-27 08:15:17,740 INFO [train.py:842] (3/4) Epoch 10, batch 5000, loss[loss=0.1733, simple_loss=0.2546, pruned_loss=0.04606, over 7176.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2908, pruned_loss=0.0654, over 1425312.74 frames.], batch size: 18, lr: 5.33e-04
2022-05-27 08:15:56,162 INFO [train.py:842] (3/4) Epoch 10, batch 5050, loss[loss=0.166, simple_loss=0.2512, pruned_loss=0.04035, over 7273.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2916, pruned_loss=0.06563, over 1423471.05 frames.], batch size: 17, lr: 5.33e-04
2022-05-27 08:16:34,976 INFO [train.py:842] (3/4) Epoch 10, batch 5100, loss[loss=0.2226, simple_loss=0.3056, pruned_loss=0.06973, over 7026.00 frames.], tot_loss[loss=0.212, simple_loss=0.292, pruned_loss=0.06601, over 1421353.31 frames.], batch size: 28, lr: 5.33e-04
2022-05-27 08:17:13,476 INFO [train.py:842] (3/4) Epoch 10, batch 5150, loss[loss=0.1908, simple_loss=0.2879, pruned_loss=0.04691, over 7338.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2918, pruned_loss=0.06565, over 1418535.02 frames.], batch size: 22, lr: 5.33e-04
2022-05-27 08:17:52,732 INFO [train.py:842] (3/4) Epoch 10, batch 5200, loss[loss=0.2105, simple_loss=0.2924, pruned_loss=0.06431, over 7163.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2928, pruned_loss=0.06625, over 1424257.06 frames.], batch size: 19, lr: 5.32e-04
2022-05-27 08:18:31,270 INFO [train.py:842] (3/4) Epoch 10, batch 5250, loss[loss=0.2777, simple_loss=0.3547, pruned_loss=0.1003, over 7315.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2934, pruned_loss=0.06667, over 1425847.47 frames.], batch size: 24, lr: 5.32e-04
2022-05-27 08:19:12,940 INFO [train.py:842] (3/4) Epoch 10, batch 5300, loss[loss=0.192, simple_loss=0.2706, pruned_loss=0.05663, over 7407.00 frames.], tot_loss[loss=0.211, simple_loss=0.2913, pruned_loss=0.0654, over 1426778.44 frames.], batch size: 18, lr: 5.32e-04
2022-05-27 08:19:51,546 INFO [train.py:842] (3/4) Epoch 10, batch 5350, loss[loss=0.1904, simple_loss=0.2866, pruned_loss=0.04708, over 7383.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2924, pruned_loss=0.06597, over 1428088.66 frames.], batch size: 23, lr: 5.32e-04
2022-05-27 08:20:30,721 INFO [train.py:842] (3/4) Epoch 10, batch 5400, loss[loss=0.1699, simple_loss=0.2537, pruned_loss=0.04308, over 7282.00 frames.], tot_loss[loss=0.211, simple_loss=0.2911, pruned_loss=0.06545, over 1432281.38 frames.], batch size: 18, lr: 5.32e-04
2022-05-27 08:21:09,281 INFO [train.py:842] (3/4) Epoch 10, batch 5450, loss[loss=0.218, simple_loss=0.2967, pruned_loss=0.06962, over 7408.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2912, pruned_loss=0.06581, over 1429207.61 frames.], batch size: 21, lr: 5.32e-04
2022-05-27 08:21:48,004 INFO [train.py:842] (3/4) Epoch 10, batch 5500, loss[loss=0.1838, simple_loss=0.2625, pruned_loss=0.05253, over 6997.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2931, pruned_loss=0.06683, over 1425011.80 frames.], batch size: 16, lr: 5.31e-04
2022-05-27 08:22:26,516 INFO [train.py:842] (3/4) Epoch 10, batch 5550, loss[loss=0.2405, simple_loss=0.3296, pruned_loss=0.0757, over 7276.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2921, pruned_loss=0.0663, over 1425153.93 frames.], batch size: 24, lr: 5.31e-04
2022-05-27 08:23:05,399 INFO [train.py:842] (3/4) Epoch 10, batch 5600, loss[loss=0.2455, simple_loss=0.33, pruned_loss=0.08053, over 7144.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2929, pruned_loss=0.06678, over 1423870.56 frames.], batch size: 20, lr: 5.31e-04
2022-05-27 08:23:44,293 INFO [train.py:842] (3/4) Epoch 10, batch 5650, loss[loss=0.2306, simple_loss=0.3012, pruned_loss=0.08002, over 7055.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2925, pruned_loss=0.06642, over 1428675.99 frames.], batch size: 18, lr: 5.31e-04
2022-05-27 08:24:23,135 INFO [train.py:842] (3/4) Epoch 10, batch 5700, loss[loss=0.1967, simple_loss=0.2686, pruned_loss=0.06243, over 7063.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2926, pruned_loss=0.06692, over 1430434.05 frames.], batch size: 18, lr: 5.31e-04
2022-05-27 08:25:01,712 INFO [train.py:842] (3/4) Epoch 10, batch 5750, loss[loss=0.2185, simple_loss=0.3002, pruned_loss=0.06835, over 6816.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2938, pruned_loss=0.06724, over 1424876.67 frames.], batch size: 31, lr: 5.31e-04
2022-05-27 08:25:40,656 INFO [train.py:842] (3/4) Epoch 10, batch 5800, loss[loss=0.1678, simple_loss=0.2427, pruned_loss=0.04648, over 7271.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2926, pruned_loss=0.06657, over 1425896.36 frames.], batch size: 17, lr: 5.31e-04
2022-05-27 08:26:19,947 INFO [train.py:842] (3/4) Epoch 10, batch 5850, loss[loss=0.1983, simple_loss=0.2834, pruned_loss=0.05661, over 7346.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2923, pruned_loss=0.06665, over 1427139.64 frames.], batch size: 22, lr: 5.30e-04
2022-05-27 08:26:58,603 INFO [train.py:842] (3/4) Epoch 10, batch 5900, loss[loss=0.2369, simple_loss=0.3206, pruned_loss=0.07663, over 7205.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2928, pruned_loss=0.06689, over 1425664.40 frames.], batch size: 23, lr: 5.30e-04
2022-05-27 08:27:37,151 INFO [train.py:842] (3/4) Epoch 10, batch 5950, loss[loss=0.2035, simple_loss=0.2755, pruned_loss=0.06572, over 7292.00 frames.], tot_loss[loss=0.2119, simple_loss=0.292, pruned_loss=0.06592, over 1422904.87 frames.], batch size: 18, lr: 5.30e-04
2022-05-27 08:28:15,987 INFO [train.py:842] (3/4) Epoch 10, batch 6000, loss[loss=0.2162, simple_loss=0.311, pruned_loss=0.06069, over 7143.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2925, pruned_loss=0.06586, over 1425165.50 frames.], batch size: 20, lr: 5.30e-04
2022-05-27 08:28:15,989 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 08:28:25,356 INFO [train.py:871] (3/4) Epoch 10, validation: loss=0.173, simple_loss=0.2732, pruned_loss=0.0364, over 868885.00 frames.
2022-05-27 08:29:04,363 INFO [train.py:842] (3/4) Epoch 10, batch 6050, loss[loss=0.2032, simple_loss=0.2921, pruned_loss=0.05712, over 7428.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2924, pruned_loss=0.06615, over 1427047.94 frames.], batch size: 20, lr: 5.30e-04
2022-05-27 08:29:43,212 INFO [train.py:842] (3/4) Epoch 10, batch 6100, loss[loss=0.2672, simple_loss=0.3407, pruned_loss=0.09682, over 7376.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2923, pruned_loss=0.06578, over 1424207.10 frames.], batch size: 23, lr: 5.30e-04
2022-05-27 08:30:22,056 INFO [train.py:842] (3/4) Epoch 10, batch 6150, loss[loss=0.1795, simple_loss=0.2543, pruned_loss=0.05237, over 6797.00 frames.], tot_loss[loss=0.213, simple_loss=0.2925, pruned_loss=0.06673, over 1423680.91 frames.], batch size: 15, lr: 5.30e-04
2022-05-27 08:31:00,965 INFO [train.py:842] (3/4) Epoch 10, batch 6200, loss[loss=0.225, simple_loss=0.3149, pruned_loss=0.06759, over 7311.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2922, pruned_loss=0.06641, over 1428032.42 frames.], batch size: 24, lr: 5.29e-04
2022-05-27 08:31:39,420 INFO [train.py:842] (3/4) Epoch 10, batch 6250, loss[loss=0.1738, simple_loss=0.2649, pruned_loss=0.04133, over 7163.00 frames.], tot_loss[loss=0.2123, simple_loss=0.292, pruned_loss=0.06629, over 1419065.34 frames.], batch size: 19, lr: 5.29e-04
2022-05-27 08:32:18,046 INFO [train.py:842] (3/4) Epoch 10, batch 6300, loss[loss=0.2513, simple_loss=0.3246, pruned_loss=0.089, over 7149.00 frames.], tot_loss[loss=0.2131, simple_loss=0.293, pruned_loss=0.06659, over 1422923.01 frames.], batch size: 20, lr: 5.29e-04
2022-05-27 08:32:56,607 INFO [train.py:842] (3/4) Epoch 10, batch 6350, loss[loss=0.2491, simple_loss=0.326, pruned_loss=0.08612, over 7149.00 frames.], tot_loss[loss=0.213, simple_loss=0.2932, pruned_loss=0.06641, over 1421747.88 frames.], batch size: 20, lr: 5.29e-04
2022-05-27 08:33:35,409 INFO [train.py:842] (3/4) Epoch 10, batch 6400, loss[loss=0.1946, simple_loss=0.2779, pruned_loss=0.05563, over 7406.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2926, pruned_loss=0.0658, over 1423865.53 frames.], batch size: 21, lr: 5.29e-04
2022-05-27 08:34:14,100 INFO [train.py:842] (3/4) Epoch 10, batch 6450, loss[loss=0.1965, simple_loss=0.2669, pruned_loss=0.06308, over 7292.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2918, pruned_loss=0.06571, over 1422238.89 frames.], batch size: 17, lr: 5.29e-04
2022-05-27 08:34:52,937 INFO [train.py:842] (3/4) Epoch 10, batch 6500, loss[loss=0.1965, simple_loss=0.2798, pruned_loss=0.05667, over 6795.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2905, pruned_loss=0.06502, over 1420740.23 frames.], batch size: 31, lr: 5.28e-04
2022-05-27 08:35:31,468 INFO [train.py:842] (3/4) Epoch 10, batch 6550, loss[loss=0.2473, simple_loss=0.3118, pruned_loss=0.09138, over 7296.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2912, pruned_loss=0.0657, over 1422957.19 frames.], batch size: 24, lr: 5.28e-04
2022-05-27 08:36:10,170 INFO [train.py:842] (3/4) Epoch 10, batch 6600, loss[loss=0.2379, simple_loss=0.3201, pruned_loss=0.07783, over 7314.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2923, pruned_loss=0.06621, over 1425532.71 frames.], batch size: 25, lr: 5.28e-04
2022-05-27 08:36:48,782 INFO [train.py:842] (3/4) Epoch 10, batch 6650, loss[loss=0.1613, simple_loss=0.2399, pruned_loss=0.0414, over 7415.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2903, pruned_loss=0.06459, over 1427395.01 frames.], batch size: 18, lr: 5.28e-04
2022-05-27 08:37:27,509 INFO [train.py:842] (3/4) Epoch 10, batch 6700, loss[loss=0.2212, simple_loss=0.2936, pruned_loss=0.07442, over 7072.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2921, pruned_loss=0.06576, over 1422301.91 frames.], batch size: 18, lr: 5.28e-04
2022-05-27 08:38:06,115 INFO [train.py:842] (3/4) Epoch 10, batch 6750, loss[loss=0.1965, simple_loss=0.2772, pruned_loss=0.05788, over 7400.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2943, pruned_loss=0.06699, over 1424954.11 frames.], batch size: 18, lr: 5.28e-04
2022-05-27 08:38:45,076 INFO [train.py:842] (3/4) Epoch 10, batch 6800, loss[loss=0.2058, simple_loss=0.2877, pruned_loss=0.06198, over 7010.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2927, pruned_loss=0.06624, over 1423769.28 frames.], batch size: 28, lr: 5.28e-04
2022-05-27 08:39:23,818 INFO [train.py:842] (3/4) Epoch 10, batch 6850, loss[loss=0.19, simple_loss=0.2762, pruned_loss=0.05186, over 6856.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2914, pruned_loss=0.06558, over 1428934.93 frames.], batch size: 31, lr: 5.27e-04
2022-05-27 08:40:02,436 INFO [train.py:842] (3/4) Epoch 10, batch 6900, loss[loss=0.1972, simple_loss=0.2804, pruned_loss=0.057, over 7197.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2928, pruned_loss=0.06638, over 1424728.04 frames.], batch size: 23, lr: 5.27e-04
2022-05-27 08:40:40,973 INFO [train.py:842] (3/4) Epoch 10, batch 6950, loss[loss=0.199, simple_loss=0.2894, pruned_loss=0.05433, over 7369.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2936, pruned_loss=0.0669, over 1421905.00 frames.], batch size: 23, lr: 5.27e-04
2022-05-27 08:41:19,726 INFO [train.py:842] (3/4) Epoch 10, batch 7000, loss[loss=0.2055, simple_loss=0.2941, pruned_loss=0.05847, over 7156.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2921, pruned_loss=0.06588, over 1423814.28 frames.], batch size: 20, lr: 5.27e-04
2022-05-27 08:41:58,256 INFO [train.py:842] (3/4) Epoch 10, batch 7050, loss[loss=0.2664, simple_loss=0.3306, pruned_loss=0.1011, over 7237.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2921, pruned_loss=0.06565, over 1420667.11 frames.], batch size: 20, lr: 5.27e-04
2022-05-27 08:42:37,045 INFO [train.py:842] (3/4) Epoch 10, batch 7100, loss[loss=0.2065, simple_loss=0.2917, pruned_loss=0.06068, over 7330.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2923, pruned_loss=0.06625, over 1422307.98 frames.], batch size: 22, lr: 5.27e-04
2022-05-27 08:43:15,638 INFO [train.py:842] (3/4) Epoch 10, batch 7150, loss[loss=0.2534, simple_loss=0.3209, pruned_loss=0.09293, over 7364.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2909, pruned_loss=0.06543, over 1424640.81 frames.], batch size: 23, lr: 5.27e-04
2022-05-27 08:43:54,150 INFO [train.py:842] (3/4) Epoch 10, batch 7200, loss[loss=0.3453, simple_loss=0.3909, pruned_loss=0.1498, over 4809.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2916, pruned_loss=0.06627, over 1417842.03 frames.], batch size: 52, lr: 5.26e-04
2022-05-27 08:44:32,602 INFO [train.py:842] (3/4) Epoch 10, batch 7250, loss[loss=0.1843, simple_loss=0.2673, pruned_loss=0.05059, over 7300.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2922, pruned_loss=0.06637, over 1412521.62 frames.], batch size: 25, lr: 5.26e-04
2022-05-27 08:45:11,721 INFO [train.py:842] (3/4) Epoch 10, batch 7300, loss[loss=0.2154, simple_loss=0.3121, pruned_loss=0.05935, over 7428.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2925, pruned_loss=0.06657, over 1417115.12 frames.], batch size: 20, lr: 5.26e-04
2022-05-27 08:45:50,413 INFO [train.py:842] (3/4) Epoch 10, batch 7350, loss[loss=0.185, simple_loss=0.2562, pruned_loss=0.05687, over 7124.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2931, pruned_loss=0.06661, over 1421578.57 frames.], batch size: 17, lr: 5.26e-04
2022-05-27 08:46:29,239 INFO [train.py:842] (3/4) Epoch 10, batch 7400, loss[loss=0.1893, simple_loss=0.2769, pruned_loss=0.0508, over 7409.00 frames.], tot_loss[loss=0.2131, simple_loss=0.293, pruned_loss=0.06663, over 1422036.55 frames.], batch size: 21, lr: 5.26e-04
2022-05-27 08:47:07,767 INFO [train.py:842] (3/4) Epoch 10, batch 7450, loss[loss=0.2133, simple_loss=0.2785, pruned_loss=0.07408, over 7240.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2943, pruned_loss=0.06772, over 1419077.60 frames.], batch size: 16, lr: 5.26e-04
2022-05-27 08:47:46,319 INFO [train.py:842] (3/4) Epoch 10, batch 7500, loss[loss=0.2133, simple_loss=0.293, pruned_loss=0.06677, over 7228.00 frames.], tot_loss[loss=0.214, simple_loss=0.2937, pruned_loss=0.06715, over 1419720.99 frames.], batch size: 21, lr: 5.26e-04
2022-05-27 08:48:24,830 INFO [train.py:842] (3/4) Epoch 10, batch 7550, loss[loss=0.1933, simple_loss=0.2879, pruned_loss=0.04938, over 7145.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2929, pruned_loss=0.0668, over 1421521.05 frames.], batch size: 20, lr: 5.25e-04
2022-05-27 08:49:03,935 INFO [train.py:842] (3/4) Epoch 10, batch 7600, loss[loss=0.1815, simple_loss=0.2621, pruned_loss=0.05045, over 7278.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2912, pruned_loss=0.06546, over 1422725.50 frames.], batch size: 18, lr: 5.25e-04
2022-05-27 08:49:42,456 INFO [train.py:842] (3/4) Epoch 10, batch 7650, loss[loss=0.1976, simple_loss=0.2704, pruned_loss=0.06242, over 7011.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2906, pruned_loss=0.0654, over 1420691.71 frames.], batch size: 16, lr: 5.25e-04
2022-05-27 08:50:21,197 INFO [train.py:842] (3/4) Epoch 10, batch 7700, loss[loss=0.2331, simple_loss=0.3102, pruned_loss=0.07798, over 7335.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2904, pruned_loss=0.06502, over 1419417.54 frames.], batch size: 22, lr: 5.25e-04
2022-05-27 08:50:59,826 INFO [train.py:842] (3/4) Epoch 10, batch 7750, loss[loss=0.1984, simple_loss=0.2834, pruned_loss=0.05674, over 6834.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2904, pruned_loss=0.06464, over 1423983.44 frames.], batch size: 31, lr: 5.25e-04
2022-05-27 08:51:38,591 INFO [train.py:842] (3/4) Epoch 10, batch 7800, loss[loss=0.2145, simple_loss=0.2987, pruned_loss=0.06512, over 7167.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2906, pruned_loss=0.06459, over 1426339.98 frames.], batch size: 18, lr: 5.25e-04
2022-05-27 08:52:17,204 INFO [train.py:842] (3/4) Epoch 10, batch 7850, loss[loss=0.2081, simple_loss=0.2988, pruned_loss=0.0587, over 7313.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2907, pruned_loss=0.06499, over 1421951.89 frames.], batch size: 21, lr: 5.25e-04
2022-05-27 08:52:56,081 INFO [train.py:842] (3/4) Epoch 10, batch 7900, loss[loss=0.1803, simple_loss=0.266, pruned_loss=0.04732, over 7168.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2907, pruned_loss=0.06524, over 1423652.58 frames.], batch size: 19, lr: 5.24e-04
2022-05-27 08:53:34,567 INFO [train.py:842] (3/4) Epoch 10, batch 7950, loss[loss=0.1799, simple_loss=0.2654, pruned_loss=0.04718, over 7281.00 frames.], tot_loss[loss=0.2106, simple_loss=0.291, pruned_loss=0.06507, over 1425362.80 frames.], batch size: 18, lr: 5.24e-04
2022-05-27 08:54:13,269 INFO [train.py:842] (3/4) Epoch 10, batch 8000, loss[loss=0.1777, simple_loss=0.2599, pruned_loss=0.04779, over 7064.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2897, pruned_loss=0.06421, over 1425006.42 frames.], batch size: 18, lr: 5.24e-04
2022-05-27 08:54:51,841 INFO [train.py:842] (3/4) Epoch 10, batch 8050, loss[loss=0.2391, simple_loss=0.3069, pruned_loss=0.08569, over 5175.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2907, pruned_loss=0.06485, over 1421205.51 frames.], batch size: 52, lr: 5.24e-04
2022-05-27 08:55:30,398 INFO [train.py:842] (3/4) Epoch 10, batch 8100, loss[loss=0.1754, simple_loss=0.2555, pruned_loss=0.04766, over 7287.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2909, pruned_loss=0.06484, over 1416906.44 frames.], batch size: 17, lr: 5.24e-04
2022-05-27 08:56:08,980 INFO [train.py:842] (3/4) Epoch 10, batch 8150, loss[loss=0.2394, simple_loss=0.3158, pruned_loss=0.08152, over 7311.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2905, pruned_loss=0.06502, over 1417588.33 frames.], batch size: 25, lr: 5.24e-04
2022-05-27 08:56:47,766 INFO [train.py:842] (3/4) Epoch 10, batch 8200, loss[loss=0.2186, simple_loss=0.3053, pruned_loss=0.06589, over 6737.00 frames.], tot_loss[loss=0.21, simple_loss=0.2899, pruned_loss=0.065, over 1417242.43 frames.], batch size: 31, lr: 5.24e-04
2022-05-27 08:57:26,306 INFO [train.py:842] (3/4) Epoch 10, batch 8250, loss[loss=0.2, simple_loss=0.2769, pruned_loss=0.0616, over 7362.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2914, pruned_loss=0.066, over 1417601.31 frames.], batch size: 19, lr: 5.23e-04
2022-05-27 08:58:04,881 INFO [train.py:842] (3/4) Epoch 10, batch 8300, loss[loss=0.2138, simple_loss=0.2787, pruned_loss=0.07445, over 7139.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2916, pruned_loss=0.06634, over 1413610.56 frames.], batch size: 17, lr: 5.23e-04
2022-05-27 08:58:43,223 INFO [train.py:842] (3/4) Epoch 10, batch 8350, loss[loss=0.2254, simple_loss=0.2995, pruned_loss=0.07565, over 4941.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2927, pruned_loss=0.06674, over 1415901.77 frames.], batch size: 52, lr: 5.23e-04
2022-05-27 08:59:21,884 INFO [train.py:842] (3/4) Epoch 10, batch 8400, loss[loss=0.2101, simple_loss=0.2919, pruned_loss=0.06409, over 7286.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2921, pruned_loss=0.06632, over 1415104.70 frames.], batch size: 24, lr: 5.23e-04
2022-05-27 09:00:00,374 INFO [train.py:842] (3/4) Epoch 10, batch 8450, loss[loss=0.2164, simple_loss=0.3022, pruned_loss=0.06525, over 6721.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2921, pruned_loss=0.066, over 1413947.63 frames.], batch size: 31, lr: 5.23e-04
2022-05-27 09:00:39,089 INFO [train.py:842] (3/4) Epoch 10, batch 8500, loss[loss=0.1809, simple_loss=0.2604, pruned_loss=0.05072, over 7160.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2926, pruned_loss=0.06628, over 1414303.16 frames.], batch size: 18, lr: 5.23e-04
2022-05-27 09:01:17,522 INFO [train.py:842] (3/4) Epoch 10, batch 8550, loss[loss=0.2119, simple_loss=0.2911, pruned_loss=0.06635, over 7272.00 frames.], tot_loss[loss=0.2133, simple_loss=0.293, pruned_loss=0.06677, over 1412889.81 frames.], batch size: 24, lr: 5.23e-04
2022-05-27 09:01:56,486 INFO [train.py:842] (3/4) Epoch 10, batch 8600, loss[loss=0.1982, simple_loss=0.2858, pruned_loss=0.05536, over 7115.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2933, pruned_loss=0.06717, over 1417328.80 frames.], batch size: 21, lr: 5.22e-04
2022-05-27 09:02:35,170 INFO [train.py:842] (3/4) Epoch 10, batch 8650, loss[loss=0.1755, simple_loss=0.2499, pruned_loss=0.05056, over 7138.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2918, pruned_loss=0.0659, over 1422457.22 frames.], batch size: 17, lr: 5.22e-04
2022-05-27 09:03:14,149 INFO [train.py:842] (3/4) Epoch 10, batch 8700, loss[loss=0.183, simple_loss=0.2645, pruned_loss=0.05076, over 7162.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2897, pruned_loss=0.06452, over 1419896.78 frames.], batch size: 18, lr: 5.22e-04
2022-05-27 09:03:52,586 INFO [train.py:842] (3/4) Epoch 10, batch 8750, loss[loss=0.2381, simple_loss=0.3262, pruned_loss=0.07501, over 7196.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2899, pruned_loss=0.0646, over 1414986.36 frames.], batch size: 23, lr: 5.22e-04
2022-05-27 09:04:31,540 INFO [train.py:842] (3/4) Epoch 10, batch 8800, loss[loss=0.1959, simple_loss=0.2857, pruned_loss=0.05301, over 7189.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2887, pruned_loss=0.06409, over 1415650.70 frames.], batch size: 23, lr: 5.22e-04
2022-05-27 09:05:10,763 INFO [train.py:842] (3/4) Epoch 10, batch 8850, loss[loss=0.2462, simple_loss=0.3377, pruned_loss=0.07734, over 7058.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2888, pruned_loss=0.06494, over 1419000.43 frames.], batch size: 28, lr: 5.22e-04
2022-05-27 09:05:49,807 INFO [train.py:842] (3/4) Epoch 10, batch 8900, loss[loss=0.1666, simple_loss=0.2479, pruned_loss=0.04266, over 7142.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2879, pruned_loss=0.06419, over 1419927.61 frames.], batch size: 17, lr: 5.22e-04
2022-05-27 09:06:28,600 INFO [train.py:842] (3/4) Epoch 10, batch 8950, loss[loss=0.1681, simple_loss=0.2535, pruned_loss=0.04139, over 7134.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2881, pruned_loss=0.0645, over 1421254.84 frames.], batch size: 17, lr: 5.21e-04
2022-05-27 09:07:07,859 INFO [train.py:842] (3/4) Epoch 10, batch 9000, loss[loss=0.1747, simple_loss=0.2582, pruned_loss=0.0456, over 6785.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2876, pruned_loss=0.06441, over 1418749.01 frames.], batch size: 15, lr: 5.21e-04
2022-05-27 09:07:07,861 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 09:07:17,179 INFO [train.py:871] (3/4) Epoch 10, validation: loss=0.1756, simple_loss=0.2759, pruned_loss=0.03767, over 868885.00 frames.
2022-05-27 09:07:56,088 INFO [train.py:842] (3/4) Epoch 10, batch 9050, loss[loss=0.2733, simple_loss=0.3445, pruned_loss=0.101, over 6170.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2884, pruned_loss=0.06486, over 1405167.12 frames.], batch size: 37, lr: 5.21e-04
2022-05-27 09:08:34,934 INFO [train.py:842] (3/4) Epoch 10, batch 9100, loss[loss=0.1981, simple_loss=0.2734, pruned_loss=0.06145, over 7124.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2918, pruned_loss=0.06746, over 1363529.94 frames.], batch size: 17, lr: 5.21e-04
2022-05-27 09:09:12,746 INFO [train.py:842] (3/4) Epoch 10, batch 9150, loss[loss=0.2557, simple_loss=0.3239, pruned_loss=0.09374, over 5074.00 frames.], tot_loss[loss=0.2196, simple_loss=0.2963, pruned_loss=0.07145, over 1287561.81 frames.], batch size: 52, lr: 5.21e-04
2022-05-27 09:10:05,829 INFO [train.py:842] (3/4) Epoch 11, batch 0, loss[loss=0.2254, simple_loss=0.3016, pruned_loss=0.07457, over 7434.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3016, pruned_loss=0.07457, over 7434.00 frames.], batch size: 20, lr: 5.01e-04
2022-05-27 09:10:44,603 INFO [train.py:842] (3/4) Epoch 11, batch 50, loss[loss=0.1878, simple_loss=0.2762, pruned_loss=0.04965, over 7438.00 frames.], tot_loss[loss=0.2088, simple_loss=0.29, pruned_loss=0.06374, over 322802.12 frames.], batch size: 20, lr: 5.01e-04
2022-05-27 09:11:23,551 INFO [train.py:842] (3/4) Epoch 11, batch 100, loss[loss=0.2171, simple_loss=0.2866, pruned_loss=0.07382, over 7269.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2885, pruned_loss=0.06306, over 567639.14 frames.], batch size: 18, lr: 5.01e-04
2022-05-27 09:12:02,347 INFO [train.py:842] (3/4) Epoch 11, batch 150, loss[loss=0.2137, simple_loss=0.29, pruned_loss=0.06871, over 6809.00 frames.], tot_loss[loss=0.209, simple_loss=0.2905, pruned_loss=0.06374, over 760074.11 frames.], batch size: 15, lr: 5.01e-04
2022-05-27 09:12:41,239 INFO [train.py:842] (3/4) Epoch 11, batch 200, loss[loss=0.2516, simple_loss=0.3075, pruned_loss=0.09785, over 7401.00 frames.], tot_loss[loss=0.2102, simple_loss=0.291, pruned_loss=0.06471, over 907028.93 frames.], batch size: 18, lr: 5.01e-04
2022-05-27 09:13:20,000 INFO [train.py:842] (3/4) Epoch 11, batch 250, loss[loss=0.2475, simple_loss=0.3112, pruned_loss=0.0919, over 6217.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2896, pruned_loss=0.06464, over 1021998.85 frames.], batch size: 37, lr: 5.01e-04
2022-05-27 09:13:59,436 INFO [train.py:842] (3/4) Epoch 11, batch 300, loss[loss=0.215, simple_loss=0.2844, pruned_loss=0.07278, over 5178.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2887, pruned_loss=0.06401, over 1113686.62 frames.], batch size: 52, lr: 5.01e-04
2022-05-27 09:14:38,185 INFO [train.py:842] (3/4) Epoch 11, batch 350, loss[loss=0.1835, simple_loss=0.2835, pruned_loss=0.04175, over 6798.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2887, pruned_loss=0.06351, over 1186484.09 frames.], batch size: 31, lr: 5.01e-04
2022-05-27 09:15:17,108 INFO [train.py:842] (3/4) Epoch 11, batch 400, loss[loss=0.202, simple_loss=0.2833, pruned_loss=0.06033, over 7443.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2883, pruned_loss=0.0631, over 1240317.24 frames.], batch size: 20, lr: 5.00e-04
2022-05-27 09:15:56,242 INFO [train.py:842] (3/4) Epoch 11, batch 450, loss[loss=0.1812, simple_loss=0.2813, pruned_loss=0.04052, over 7237.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2866, pruned_loss=0.06274, over 1281093.82 frames.], batch size: 20, lr: 5.00e-04
2022-05-27 09:16:35,463 INFO [train.py:842] (3/4) Epoch 11, batch 500, loss[loss=0.1572, simple_loss=0.2544, pruned_loss=0.03, over 7326.00 frames.], tot_loss[loss=0.2065, simple_loss=0.287, pruned_loss=0.06295, over 1316233.09 frames.], batch size: 20, lr: 5.00e-04
2022-05-27 09:17:14,286 INFO [train.py:842] (3/4) Epoch 11, batch 550, loss[loss=0.1782, simple_loss=0.2632, pruned_loss=0.04661, over 7055.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2891, pruned_loss=0.06405, over 1341923.39 frames.], batch size: 18, lr: 5.00e-04
2022-05-27 09:17:53,343 INFO [train.py:842] (3/4) Epoch 11, batch 600, loss[loss=0.1632, simple_loss=0.2392, pruned_loss=0.04356, over 7001.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2901, pruned_loss=0.06476, over 1361189.26 frames.], batch size: 16, lr: 5.00e-04
2022-05-27 09:18:32,245 INFO [train.py:842] (3/4) Epoch 11, batch 650, loss[loss=0.1644, simple_loss=0.2471, pruned_loss=0.04079, over 7123.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2908, pruned_loss=0.06545, over 1365709.23 frames.], batch size: 17, lr: 5.00e-04
2022-05-27 09:19:11,359 INFO [train.py:842] (3/4) Epoch 11, batch 700, loss[loss=0.1843, simple_loss=0.257, pruned_loss=0.05585, over 6811.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2914, pruned_loss=0.06563, over 1375752.65 frames.], batch size: 15, lr: 5.00e-04
2022-05-27 09:19:50,252 INFO [train.py:842] (3/4) Epoch 11, batch 750, loss[loss=0.2479, simple_loss=0.3349, pruned_loss=0.08049, over 7141.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2904, pruned_loss=0.06469, over 1382163.82 frames.], batch size: 20, lr: 4.99e-04
2022-05-27 09:20:29,344 INFO [train.py:842] (3/4) Epoch 11, batch 800, loss[loss=0.2905, simple_loss=0.3656, pruned_loss=0.1077, over 7211.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2918, pruned_loss=0.06575, over 1393877.00 frames.], batch size: 26, lr: 4.99e-04
2022-05-27 09:21:08,043 INFO [train.py:842] (3/4) Epoch 11, batch 850, loss[loss=0.2546, simple_loss=0.3311, pruned_loss=0.08906, over 7326.00 frames.], tot_loss[loss=0.21, simple_loss=0.2903, pruned_loss=0.06486, over 1397883.54 frames.], batch size: 20, lr: 4.99e-04
2022-05-27 09:21:46,917 INFO [train.py:842] (3/4) Epoch 11, batch 900, loss[loss=0.2191, simple_loss=0.3125, pruned_loss=0.06284, over 7431.00 frames.], tot_loss[loss=0.21, simple_loss=0.2907, pruned_loss=0.06471, over 1406724.12 frames.], batch size: 20, lr: 4.99e-04
2022-05-27 09:22:25,678 INFO [train.py:842] (3/4) Epoch 11, batch 950, loss[loss=0.2336, simple_loss=0.2936, pruned_loss=0.08683, over 7014.00 frames.], tot_loss[loss=0.211, simple_loss=0.2912, pruned_loss=0.06538, over 1408579.68 frames.], batch size: 16, lr: 4.99e-04
2022-05-27 09:23:05,046 INFO [train.py:842] (3/4) Epoch 11, batch 1000, loss[loss=0.236, simple_loss=0.3209, pruned_loss=0.07555, over 7269.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2916, pruned_loss=0.06531, over 1412994.37 frames.], batch size: 25, lr: 4.99e-04
2022-05-27 09:23:43,664 INFO [train.py:842] (3/4) Epoch 11, batch 1050, loss[loss=0.1936, simple_loss=0.2739, pruned_loss=0.05662, over 7250.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2925, pruned_loss=0.06602, over 1408142.90 frames.], batch size: 19, lr: 4.99e-04
2022-05-27 09:24:22,814 INFO [train.py:842] (3/4) Epoch 11, batch 1100, loss[loss=0.2089, simple_loss=0.2827, pruned_loss=0.06748, over 7174.00 frames.], tot_loss[loss=0.2106, simple_loss=0.291, pruned_loss=0.06511, over 1413019.14 frames.], batch size: 18, lr: 4.99e-04
2022-05-27 09:25:01,969 INFO [train.py:842] (3/4) Epoch 11, batch 1150, loss[loss=0.2094, simple_loss=0.2926, pruned_loss=0.06306, over 7453.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2898, pruned_loss=0.06442, over 1417645.92 frames.], batch size: 19, lr: 4.98e-04
2022-05-27 09:25:40,989 INFO [train.py:842] (3/4) Epoch 11, batch 1200, loss[loss=0.1598, simple_loss=0.2397, pruned_loss=0.03999, over 6811.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2868, pruned_loss=0.06304, over 1420095.36 frames.], batch size: 15, lr: 4.98e-04
2022-05-27 09:26:19,796 INFO [train.py:842] (3/4) Epoch 11, batch 1250, loss[loss=0.2304, simple_loss=0.298, pruned_loss=0.08139, over 7131.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2873, pruned_loss=0.06324, over 1423873.60 frames.], batch size: 17, lr: 4.98e-04
2022-05-27 09:26:58,841 INFO [train.py:842] (3/4) Epoch 11, batch 1300, loss[loss=0.2134, simple_loss=0.3007, pruned_loss=0.06305, over 7321.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2869, pruned_loss=0.06294, over 1420473.80 frames.], batch size: 21, lr: 4.98e-04
2022-05-27 09:27:37,532 INFO [train.py:842] (3/4) Epoch 11, batch 1350, loss[loss=0.217, simple_loss=0.2933, pruned_loss=0.07033, over 7321.00 frames.], tot_loss[loss=0.206, simple_loss=0.2869, pruned_loss=0.06253, over 1424600.83 frames.], batch size: 21, lr: 4.98e-04
2022-05-27 09:28:16,458 INFO [train.py:842] (3/4) Epoch 11, batch 1400, loss[loss=0.1778, simple_loss=0.2699, pruned_loss=0.04288, over 7155.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2863, pruned_loss=0.06219, over 1427582.65 frames.], batch size: 19, lr: 4.98e-04
2022-05-27 09:28:55,144 INFO [train.py:842] (3/4) Epoch 11, batch 1450, loss[loss=0.1679, simple_loss=0.2547, pruned_loss=0.04052, over 7301.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2869, pruned_loss=0.06213, over 1427493.58 frames.], batch size: 17, lr: 4.98e-04
2022-05-27 09:29:34,212 INFO [train.py:842] (3/4) Epoch 11, batch 1500, loss[loss=0.2065, simple_loss=0.2871, pruned_loss=0.06296, over 7052.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2869, pruned_loss=0.06227, over 1425743.62 frames.], batch size: 28, lr: 4.97e-04
2022-05-27 09:30:12,916 INFO [train.py:842] (3/4) Epoch 11, batch 1550, loss[loss=0.1847, simple_loss=0.27, pruned_loss=0.04974, over 7435.00 frames.], tot_loss[loss=0.2071, simple_loss=0.288, pruned_loss=0.06307, over 1423585.17 frames.], batch size: 20, lr: 4.97e-04
2022-05-27 09:30:51,664 INFO [train.py:842] (3/4) Epoch 11, batch 1600, loss[loss=0.232, simple_loss=0.322, pruned_loss=0.07105, over 6865.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2887, pruned_loss=0.06349, over 1417462.27 frames.], batch size: 31, lr: 4.97e-04
2022-05-27 09:31:30,351 INFO [train.py:842] (3/4) Epoch 11, batch 1650, loss[loss=0.173, simple_loss=0.2542, pruned_loss=0.04589, over 6814.00 frames.], tot_loss[loss=0.207, simple_loss=0.2878, pruned_loss=0.0631, over 1416848.52 frames.], batch size: 15, lr: 4.97e-04
2022-05-27 09:32:09,194 INFO [train.py:842] (3/4) Epoch 11, batch 1700, loss[loss=0.1851, simple_loss=0.2572, pruned_loss=0.05649, over 7190.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2875, pruned_loss=0.06266, over 1417479.64 frames.], batch size: 16, lr: 4.97e-04
2022-05-27 09:32:47,725 INFO [train.py:842] (3/4) Epoch 11, batch 1750, loss[loss=0.1834, simple_loss=0.2786, pruned_loss=0.04406, over 7117.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2867, pruned_loss=0.06238, over 1413654.65 frames.], batch size: 21, lr: 4.97e-04
2022-05-27 09:33:26,553 INFO [train.py:842] (3/4) Epoch 11, batch 1800, loss[loss=0.3053, simple_loss=0.3585, pruned_loss=0.1261, over 4888.00 frames.], tot_loss[loss=0.207, simple_loss=0.288, pruned_loss=0.06301, over 1413232.83 frames.], batch size: 52, lr: 4.97e-04
2022-05-27 09:34:05,169 INFO [train.py:842] (3/4) Epoch 11, batch 1850, loss[loss=0.3171, simple_loss=0.3773, pruned_loss=0.1285, over 6491.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2877, pruned_loss=0.06287, over 1417399.21 frames.], batch size: 38, lr: 4.97e-04
2022-05-27 09:34:44,025 INFO [train.py:842] (3/4) Epoch 11, batch 1900, loss[loss=0.1992, simple_loss=0.2866, pruned_loss=0.0559, over 7328.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2871, pruned_loss=0.06213, over 1422100.05 frames.], batch size: 21, lr: 4.96e-04
2022-05-27 09:35:22,644 INFO [train.py:842] (3/4) Epoch 11, batch 1950, loss[loss=0.2108, simple_loss=0.2902, pruned_loss=0.06568, over 7360.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2862, pruned_loss=0.062, over 1422727.54 frames.], batch size: 19, lr: 4.96e-04
2022-05-27 09:36:01,474 INFO [train.py:842] (3/4) Epoch 11, batch 2000, loss[loss=0.1755, simple_loss=0.2653, pruned_loss=0.04289, over 7170.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2874, pruned_loss=0.06256, over 1423822.08 frames.], batch size: 18, lr: 4.96e-04
2022-05-27 09:36:40,068 INFO [train.py:842] (3/4) Epoch 11, batch 2050, loss[loss=0.1673, simple_loss=0.241, pruned_loss=0.04679, over 7273.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2882, pruned_loss=0.06329, over 1426032.44 frames.], batch size: 17, lr: 4.96e-04
2022-05-27 09:37:19,136 INFO [train.py:842] (3/4) Epoch 11, batch 2100, loss[loss=0.2205, simple_loss=0.2997, pruned_loss=0.07068, over 7366.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2878, pruned_loss=0.06319, over 1426892.03 frames.], batch size: 23, lr: 4.96e-04
2022-05-27 09:37:57,702 INFO [train.py:842] (3/4) Epoch 11, batch 2150, loss[loss=0.1614, simple_loss=0.2523, pruned_loss=0.03521, over 7165.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2872, pruned_loss=0.06279, over 1426843.81 frames.], batch size: 18, lr: 4.96e-04
2022-05-27 09:38:36,770 INFO [train.py:842] (3/4) Epoch 11, batch 2200, loss[loss=0.2247, simple_loss=0.3117, pruned_loss=0.06889, over 7227.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2858, pruned_loss=0.06222, over 1424652.21 frames.], batch size: 20, lr: 4.96e-04
2022-05-27 09:39:15,384 INFO [train.py:842] (3/4) Epoch 11, batch 2250, loss[loss=0.2852, simple_loss=0.3536, pruned_loss=0.1084, over 7333.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2865, pruned_loss=0.06211, over 1427484.29 frames.], batch size: 22, lr: 4.95e-04
2022-05-27 09:39:54,344 INFO [train.py:842] (3/4) Epoch 11, batch 2300, loss[loss=0.2556, simple_loss=0.3363, pruned_loss=0.08744, over 7166.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2869, pruned_loss=0.06225, over 1428112.14 frames.], batch size: 26, lr: 4.95e-04
2022-05-27 09:40:33,047 INFO [train.py:842] (3/4) Epoch 11, batch 2350, loss[loss=0.2301, simple_loss=0.3055, pruned_loss=0.07736, over 6758.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2867, pruned_loss=0.06194, over 1430218.75 frames.], batch size: 31, lr: 4.95e-04
2022-05-27 09:41:11,949 INFO [train.py:842] (3/4) Epoch 11, batch 2400, loss[loss=0.2187, simple_loss=0.2998, pruned_loss=0.0688, over 7332.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2867, pruned_loss=0.06222, over 1424098.34 frames.], batch size: 21, lr: 4.95e-04
2022-05-27 09:41:50,643 INFO [train.py:842] (3/4) Epoch 11, batch 2450, loss[loss=0.2026, simple_loss=0.28, pruned_loss=0.06259, over 6985.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2857, pruned_loss=0.0616, over 1424832.15 frames.], batch size: 16, lr: 4.95e-04
2022-05-27 09:42:29,507 INFO [train.py:842] (3/4) Epoch 11, batch 2500, loss[loss=0.1846, simple_loss=0.2726, pruned_loss=0.04829, over 7162.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2869, pruned_loss=0.06229, over 1424059.52 frames.], batch size: 19, lr: 4.95e-04
2022-05-27 09:43:08,219 INFO [train.py:842] (3/4) Epoch 11, batch 2550, loss[loss=0.2143, simple_loss=0.2827, pruned_loss=0.07299, over 6764.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2871, pruned_loss=0.06184, over 1428165.11 frames.], batch size: 15, lr: 4.95e-04
2022-05-27 09:43:47,157 INFO [train.py:842] (3/4) Epoch 11, batch 2600, loss[loss=0.1976, simple_loss=0.2763, pruned_loss=0.05944, over 7368.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2875, pruned_loss=0.06264, over 1430039.07 frames.], batch size: 23, lr: 4.95e-04
2022-05-27 09:44:25,676 INFO [train.py:842] (3/4) Epoch 11, batch 2650, loss[loss=0.1908, simple_loss=0.2629, pruned_loss=0.05933, over 6984.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2878, pruned_loss=0.06266, over 1424750.15 frames.], batch size: 16, lr: 4.94e-04
2022-05-27 09:45:04,588 INFO [train.py:842] (3/4) Epoch 11, batch 2700, loss[loss=0.2084, simple_loss=0.3027, pruned_loss=0.05707, over 7417.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2896, pruned_loss=0.06378, over 1427614.34 frames.], batch size: 21, lr: 4.94e-04
2022-05-27 09:45:43,288 INFO [train.py:842] (3/4) Epoch 11, batch 2750, loss[loss=0.1907, simple_loss=0.2722, pruned_loss=0.05459, over 7275.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2897, pruned_loss=0.06409, over 1425821.61 frames.], batch size: 18, lr: 4.94e-04
2022-05-27 09:46:22,114 INFO [train.py:842] (3/4) Epoch 11, batch 2800, loss[loss=0.2266, simple_loss=0.2943, pruned_loss=0.07945, over 7159.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2897, pruned_loss=0.06405, over 1424791.35 frames.], batch size: 19, lr: 4.94e-04
2022-05-27 09:47:01,425 INFO [train.py:842] (3/4) Epoch 11, batch 2850, loss[loss=0.2101, simple_loss=0.2933, pruned_loss=0.06347, over 7315.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2884, pruned_loss=0.06332, over 1425143.02 frames.], batch size: 21, lr: 4.94e-04
2022-05-27 09:47:40,663 INFO [train.py:842] (3/4) Epoch 11, batch 2900, loss[loss=0.2096, simple_loss=0.2942, pruned_loss=0.0625, over 7195.00 frames.], tot_loss[loss=0.206, simple_loss=0.2871, pruned_loss=0.06245, over 1427486.93 frames.], batch size: 23, lr: 4.94e-04
2022-05-27 09:48:19,196 INFO [train.py:842] (3/4) Epoch 11, batch 2950, loss[loss=0.1792, simple_loss=0.2706, pruned_loss=0.04393, over 7220.00 frames.], tot_loss[loss=0.2069, simple_loss=0.288, pruned_loss=0.06292, over 1424797.72 frames.], batch size: 22, lr: 4.94e-04
2022-05-27 09:48:58,071 INFO [train.py:842] (3/4) Epoch 11, batch 3000, loss[loss=0.2306, simple_loss=0.3138, pruned_loss=0.07369, over 7160.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2886, pruned_loss=0.06263, over 1422831.20 frames.], batch size: 18, lr: 4.94e-04
2022-05-27 09:48:58,071 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 09:49:07,579 INFO [train.py:871] (3/4) Epoch 11, validation: loss=0.1731, simple_loss=0.2734, pruned_loss=0.03642, over 868885.00 frames.
2022-05-27 09:49:46,393 INFO [train.py:842] (3/4) Epoch 11, batch 3050, loss[loss=0.2214, simple_loss=0.3027, pruned_loss=0.07009, over 7147.00 frames.], tot_loss[loss=0.208, simple_loss=0.2893, pruned_loss=0.0634, over 1427346.51 frames.], batch size: 26, lr: 4.93e-04
2022-05-27 09:50:25,537 INFO [train.py:842] (3/4) Epoch 11, batch 3100, loss[loss=0.1971, simple_loss=0.2729, pruned_loss=0.06068, over 7401.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2879, pruned_loss=0.06277, over 1424902.15 frames.], batch size: 18, lr: 4.93e-04
2022-05-27 09:51:04,382 INFO [train.py:842] (3/4) Epoch 11, batch 3150, loss[loss=0.1919, simple_loss=0.2765, pruned_loss=0.05363, over 7262.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2874, pruned_loss=0.06276, over 1426588.05 frames.], batch size: 18, lr: 4.93e-04
2022-05-27 09:51:43,761 INFO [train.py:842] (3/4) Epoch 11, batch 3200, loss[loss=0.1871, simple_loss=0.2657, pruned_loss=0.05422, over 7164.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2854, pruned_loss=0.06164, over 1428619.89 frames.], batch size: 18, lr: 4.93e-04
2022-05-27 09:52:22,391 INFO [train.py:842] (3/4) Epoch 11, batch 3250, loss[loss=0.2325, simple_loss=0.3018, pruned_loss=0.08161, over 7069.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2849, pruned_loss=0.06127, over 1430138.19 frames.], batch size: 18, lr: 4.93e-04
2022-05-27 09:53:01,438 INFO [train.py:842] (3/4) Epoch 11, batch 3300, loss[loss=0.2231, simple_loss=0.2999, pruned_loss=0.0732, over 6361.00 frames.], tot_loss[loss=0.204, simple_loss=0.2852, pruned_loss=0.06136, over 1429802.82 frames.], batch size: 38, lr: 4.93e-04
2022-05-27 09:53:39,890 INFO [train.py:842] (3/4) Epoch 11, batch 3350, loss[loss=0.1632, simple_loss=0.2548, pruned_loss=0.03577, over 7117.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2865, pruned_loss=0.06253, over 1424451.05 frames.], batch size: 21, lr: 4.93e-04
2022-05-27 09:54:18,847 INFO [train.py:842] (3/4) Epoch 11, batch 3400, loss[loss=0.2169, simple_loss=0.2848, pruned_loss=0.07453, over 7004.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2873, pruned_loss=0.06269, over 1422108.18 frames.], batch size: 16, lr: 4.92e-04
2022-05-27 09:54:57,578 INFO [train.py:842] (3/4) Epoch 11, batch 3450, loss[loss=0.2027, simple_loss=0.2852, pruned_loss=0.06013, over 7101.00 frames.], tot_loss[loss=0.206, simple_loss=0.2876, pruned_loss=0.06219, over 1424822.89 frames.], batch size: 21, lr: 4.92e-04
2022-05-27 09:55:36,323 INFO [train.py:842] (3/4) Epoch 11, batch 3500, loss[loss=0.1759, simple_loss=0.2559, pruned_loss=0.04799, over 7418.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2878, pruned_loss=0.06284, over 1425188.03 frames.], batch size: 18, lr: 4.92e-04
2022-05-27 09:56:14,793 INFO [train.py:842] (3/4) Epoch 11, batch 3550, loss[loss=0.2465, simple_loss=0.3111, pruned_loss=0.09095, over 6337.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2874, pruned_loss=0.06284, over 1423825.90 frames.], batch size: 37, lr: 4.92e-04
2022-05-27 09:56:53,642 INFO [train.py:842] (3/4) Epoch 11, batch 3600, loss[loss=0.2204, simple_loss=0.3028, pruned_loss=0.06901, over 6326.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2886, pruned_loss=0.06342, over 1419608.33 frames.], batch size: 38, lr: 4.92e-04
2022-05-27 09:57:32,186 INFO [train.py:842] (3/4) Epoch 11, batch 3650, loss[loss=0.2014, simple_loss=0.2853, pruned_loss=0.05877, over 7128.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2876, pruned_loss=0.06266, over 1421631.38 frames.], batch size: 21, lr: 4.92e-04
2022-05-27 09:58:10,905 INFO [train.py:842] (3/4) Epoch 11, batch 3700, loss[loss=0.1698, simple_loss=0.2602, pruned_loss=0.0397, over 7117.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2874, pruned_loss=0.06238, over 1419149.18 frames.], batch size: 21, lr: 4.92e-04
2022-05-27 09:58:49,443 INFO [train.py:842] (3/4) Epoch 11, batch 3750, loss[loss=0.1693, simple_loss=0.2531, pruned_loss=0.04275, over 7434.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2895, pruned_loss=0.06362, over 1424502.65 frames.], batch size: 20, lr: 4.92e-04
2022-05-27 09:59:28,310 INFO [train.py:842] (3/4) Epoch 11, batch 3800, loss[loss=0.2127, simple_loss=0.301, pruned_loss=0.06219, over 7281.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2892, pruned_loss=0.06347, over 1423797.35 frames.], batch size: 24, lr: 4.91e-04
2022-05-27 10:00:06,881 INFO [train.py:842] (3/4) Epoch 11, batch 3850, loss[loss=0.2426, simple_loss=0.3168, pruned_loss=0.08424, over 7137.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2874, pruned_loss=0.0625, over 1427363.12 frames.], batch size: 28, lr: 4.91e-04
2022-05-27 10:00:45,738 INFO [train.py:842] (3/4) Epoch 11, batch 3900, loss[loss=0.229, simple_loss=0.3059, pruned_loss=0.07605, over 7347.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2866, pruned_loss=0.06189, over 1427425.48 frames.], batch size: 22, lr: 4.91e-04
2022-05-27 10:01:24,362 INFO [train.py:842] (3/4) Epoch 11, batch 3950, loss[loss=0.2194, simple_loss=0.3019, pruned_loss=0.06846, over 7412.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2882, pruned_loss=0.0627, over 1428065.06 frames.], batch size: 21, lr: 4.91e-04
2022-05-27 10:02:03,405 INFO [train.py:842] (3/4) Epoch 11, batch 4000, loss[loss=0.2439, simple_loss=0.3273, pruned_loss=0.08023, over 7295.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2882, pruned_loss=0.06323, over 1423941.11 frames.], batch size: 25, lr: 4.91e-04
2022-05-27 10:02:42,053 INFO [train.py:842] (3/4) Epoch 11, batch 4050, loss[loss=0.242, simple_loss=0.3183, pruned_loss=0.08289, over 7222.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2884, pruned_loss=0.06321, over 1422922.90 frames.], batch size: 26, lr: 4.91e-04
2022-05-27 10:03:23,535 INFO [train.py:842] (3/4) Epoch 11, batch 4100, loss[loss=0.2156, simple_loss=0.2757, pruned_loss=0.07771, over 7133.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2886, pruned_loss=0.06296, over 1421906.73 frames.], batch size: 17, lr: 4.91e-04
2022-05-27 10:04:02,275 INFO [train.py:842] (3/4) Epoch 11, batch 4150, loss[loss=0.1946, simple_loss=0.2878, pruned_loss=0.05064, over 7114.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2891, pruned_loss=0.06364, over 1422859.59 frames.], batch size: 21, lr: 4.91e-04
2022-05-27 10:04:40,834 INFO [train.py:842] (3/4) Epoch 11, batch 4200, loss[loss=0.23, simple_loss=0.3156, pruned_loss=0.07224, over 7202.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2897, pruned_loss=0.0635, over 1420298.35 frames.], batch size: 23, lr: 4.90e-04
2022-05-27 10:05:19,324 INFO [train.py:842] (3/4) Epoch 11, batch 4250, loss[loss=0.2291, simple_loss=0.3037, pruned_loss=0.07729, over 7449.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2909, pruned_loss=0.06441, over 1421896.28 frames.], batch size: 19, lr: 4.90e-04
2022-05-27 10:05:58,294 INFO [train.py:842] (3/4) Epoch 11, batch 4300, loss[loss=0.1932, simple_loss=0.2759, pruned_loss=0.05526, over 7062.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2899, pruned_loss=0.06411, over 1426868.32 frames.], batch size: 18, lr: 4.90e-04
2022-05-27 10:06:36,945 INFO [train.py:842] (3/4) Epoch 11, batch 4350, loss[loss=0.2136, simple_loss=0.2935, pruned_loss=0.06683, over 7354.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2906, pruned_loss=0.0646, over 1426799.05 frames.], batch size: 19, lr: 4.90e-04
2022-05-27 10:07:16,049 INFO [train.py:842] (3/4) Epoch 11, batch 4400, loss[loss=0.2072, simple_loss=0.274, pruned_loss=0.07022, over 6778.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2893, pruned_loss=0.064, over 1425810.14 frames.], batch size: 15, lr: 4.90e-04
2022-05-27 10:07:55,083 INFO [train.py:842] (3/4) Epoch 11, batch 4450, loss[loss=0.2126, simple_loss=0.2874, pruned_loss=0.06888, over 7163.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2886, pruned_loss=0.06384, over 1421403.13 frames.], batch size: 18, lr: 4.90e-04
2022-05-27 10:08:33,892 INFO [train.py:842] (3/4) Epoch 11, batch 4500, loss[loss=0.1741, simple_loss=0.2537, pruned_loss=0.0472, over 7363.00 frames.], tot_loss[loss=0.208, simple_loss=0.2886, pruned_loss=0.06369, over 1420988.81 frames.], batch size: 19, lr: 4.90e-04
2022-05-27 10:09:12,439 INFO [train.py:842] (3/4) Epoch 11, batch 4550, loss[loss=0.1928, simple_loss=0.2706, pruned_loss=0.05755, over 7355.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2896, pruned_loss=0.06459, over 1424299.36 frames.], batch size: 19, lr: 4.90e-04
2022-05-27 10:09:51,213 INFO [train.py:842] (3/4) Epoch 11, batch 4600, loss[loss=0.2395, simple_loss=0.3179, pruned_loss=0.08056, over 7155.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2901, pruned_loss=0.06469, over 1428486.27 frames.], batch size: 18, lr: 4.89e-04
2022-05-27 10:10:29,814 INFO [train.py:842] (3/4) Epoch 11, batch 4650, loss[loss=0.1539, simple_loss=0.2355, pruned_loss=0.03609, over 7275.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2889, pruned_loss=0.06387, over 1427362.05 frames.], batch size: 17, lr: 4.89e-04
2022-05-27 10:11:08,721 INFO [train.py:842] (3/4) Epoch 11, batch 4700, loss[loss=0.1639, simple_loss=0.252, pruned_loss=0.03792, over 7160.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2877, pruned_loss=0.06263, over 1428813.07 frames.], batch size: 19, lr: 4.89e-04
2022-05-27 10:11:47,163 INFO [train.py:842] (3/4) Epoch 11, batch 4750, loss[loss=0.2391, simple_loss=0.3122, pruned_loss=0.08296, over 7320.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2882, pruned_loss=0.06327, over 1427950.99 frames.], batch size: 21, lr: 4.89e-04
2022-05-27 10:12:26,010 INFO [train.py:842] (3/4) Epoch 11, batch 4800, loss[loss=0.1949, simple_loss=0.2827, pruned_loss=0.05354, over 7354.00 frames.], tot_loss[loss=0.2069, simple_loss=0.288, pruned_loss=0.06285, over 1427970.51 frames.], batch size: 19, lr: 4.89e-04
2022-05-27 10:13:04,715 INFO [train.py:842] (3/4) Epoch 11, batch 4850, loss[loss=0.1592, simple_loss=0.241, pruned_loss=0.03865, over 7279.00 frames.], tot_loss[loss=0.2089, simple_loss=0.29, pruned_loss=0.06389, over 1425642.58 frames.], batch size: 18, lr: 4.89e-04
2022-05-27 10:13:44,141 INFO [train.py:842] (3/4) Epoch 11, batch 4900, loss[loss=0.2127, simple_loss=0.2783, pruned_loss=0.07355, over 6833.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2896, pruned_loss=0.06402, over 1428233.30 frames.], batch size: 15, lr: 4.89e-04
2022-05-27 10:14:22,588 INFO [train.py:842] (3/4) Epoch 11, batch 4950, loss[loss=0.2426, simple_loss=0.3279, pruned_loss=0.07866, over 7323.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2885, pruned_loss=0.06332, over 1427636.19 frames.], batch size: 21, lr: 4.89e-04
2022-05-27 10:15:01,230 INFO [train.py:842] (3/4) Epoch 11, batch 5000, loss[loss=0.196, simple_loss=0.283, pruned_loss=0.05447, over 7326.00 frames.], tot_loss[loss=0.208, simple_loss=0.2889, pruned_loss=0.06349, over 1423433.12 frames.], batch size: 20, lr: 4.88e-04
2022-05-27 10:15:39,775 INFO [train.py:842] (3/4) Epoch 11, batch 5050, loss[loss=0.2136, simple_loss=0.3128, pruned_loss=0.05724, over 7293.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2888, pruned_loss=0.0632, over 1424749.70 frames.], batch size: 24, lr: 4.88e-04
2022-05-27 10:16:18,515 INFO [train.py:842] (3/4) Epoch 11, batch 5100, loss[loss=0.1953, simple_loss=0.2718, pruned_loss=0.05941, over 7162.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2882, pruned_loss=0.06278, over 1427681.39 frames.], batch size: 18, lr: 4.88e-04
2022-05-27 10:16:57,145 INFO [train.py:842] (3/4) Epoch 11, batch 5150, loss[loss=0.2169, simple_loss=0.2987, pruned_loss=0.06755, over 7150.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2885, pruned_loss=0.0635, over 1421377.56 frames.], batch size: 20, lr: 4.88e-04
2022-05-27 10:17:36,115 INFO [train.py:842] (3/4) Epoch 11, batch 5200, loss[loss=0.2292, simple_loss=0.3138, pruned_loss=0.07225, over 7197.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2904, pruned_loss=0.06492, over 1421318.18 frames.], batch size: 23, lr: 4.88e-04
2022-05-27 10:18:14,669 INFO [train.py:842] (3/4) Epoch 11, batch 5250, loss[loss=0.1741, simple_loss=0.2594, pruned_loss=0.04444, over 7251.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2909, pruned_loss=0.06523, over 1424293.38 frames.], batch size: 19, lr: 4.88e-04
2022-05-27 10:18:53,621 INFO [train.py:842] (3/4) Epoch 11, batch 5300, loss[loss=0.2, simple_loss=0.2929, pruned_loss=0.05356, over 7387.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2904, pruned_loss=0.06473, over 1425165.47 frames.], batch size: 23, lr: 4.88e-04
2022-05-27 10:19:32,059 INFO [train.py:842] (3/4) Epoch 11, batch 5350, loss[loss=0.2032, simple_loss=0.2811, pruned_loss=0.06265, over 7233.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2899, pruned_loss=0.06415, over 1427404.99 frames.], batch size: 20, lr: 4.88e-04
2022-05-27 10:20:10,531 INFO [train.py:842] (3/4) Epoch 11, batch 5400, loss[loss=0.2539, simple_loss=0.3408, pruned_loss=0.08355, over 7205.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2911, pruned_loss=0.06466, over 1428115.58 frames.], batch size: 23, lr: 4.87e-04
2022-05-27 10:20:49,093 INFO [train.py:842] (3/4) Epoch 11, batch 5450, loss[loss=0.2014, simple_loss=0.2908, pruned_loss=0.05601, over 7302.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2895, pruned_loss=0.06369, over 1428363.01 frames.], batch size: 24, lr: 4.87e-04
2022-05-27 10:21:28,153 INFO [train.py:842] (3/4) Epoch 11, batch 5500, loss[loss=0.1923, simple_loss=0.2708, pruned_loss=0.05692, over 7277.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2892, pruned_loss=0.06345, over 1426225.47 frames.], batch size: 18, lr: 4.87e-04
2022-05-27 10:22:16,777 INFO [train.py:842] (3/4) Epoch 11, batch 5550, loss[loss=0.163, simple_loss=0.2427, pruned_loss=0.04161, over 7148.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2886, pruned_loss=0.06341, over 1426302.43 frames.], batch size: 19, lr: 4.87e-04
2022-05-27 10:22:55,822 INFO [train.py:842] (3/4) Epoch 11, batch 5600, loss[loss=0.2643, simple_loss=0.331, pruned_loss=0.09875, over 4783.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2884, pruned_loss=0.06361, over 1423675.67 frames.], batch size: 53, lr: 4.87e-04
2022-05-27 10:23:34,190 INFO [train.py:842] (3/4) Epoch 11, batch 5650, loss[loss=0.2371, simple_loss=0.3184, pruned_loss=0.07791, over 7421.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2907, pruned_loss=0.06485, over 1425135.42 frames.], batch size: 21, lr: 4.87e-04
2022-05-27 10:24:13,277 INFO [train.py:842] (3/4) Epoch 11, batch 5700, loss[loss=0.207, simple_loss=0.2945, pruned_loss=0.05977, over 7379.00 frames.], tot_loss[loss=0.209, simple_loss=0.2897, pruned_loss=0.06417, over 1425363.44 frames.], batch size: 23, lr: 4.87e-04
2022-05-27 10:24:51,712 INFO [train.py:842] (3/4) Epoch 11, batch 5750, loss[loss=0.2021, simple_loss=0.2838, pruned_loss=0.06018, over 7245.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2891, pruned_loss=0.06375, over 1419291.39 frames.], batch size: 20, lr: 4.87e-04
2022-05-27 10:25:30,813 INFO [train.py:842] (3/4) Epoch 11, batch 5800, loss[loss=0.3013, simple_loss=0.3623, pruned_loss=0.1202, over 5182.00 frames.], tot_loss[loss=0.206, simple_loss=0.2875, pruned_loss=0.06224, over 1423165.47 frames.], batch size: 52, lr: 4.86e-04
2022-05-27 10:26:09,459 INFO [train.py:842] (3/4) Epoch 11, batch 5850, loss[loss=0.2988, simple_loss=0.3639, pruned_loss=0.1168, over 7054.00 frames.], tot_loss[loss=0.2074, simple_loss=0.289, pruned_loss=0.06292, over 1423003.17 frames.], batch size: 28, lr: 4.86e-04
2022-05-27 10:26:48,399 INFO [train.py:842] (3/4) Epoch 11, batch 5900, loss[loss=0.205, simple_loss=0.2868, pruned_loss=0.0616, over 7418.00 frames.], tot_loss[loss=0.207, simple_loss=0.2884, pruned_loss=0.06281, over 1424889.58 frames.], batch size: 20, lr: 4.86e-04
2022-05-27 10:27:26,942 INFO [train.py:842] (3/4) Epoch 11, batch 5950, loss[loss=0.2219, simple_loss=0.2962, pruned_loss=0.07383, over 7164.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2877, pruned_loss=0.06241, over 1428136.81 frames.], batch size: 26, lr: 4.86e-04
2022-05-27 10:28:06,064 INFO [train.py:842] (3/4) Epoch 11, batch 6000, loss[loss=0.2595, simple_loss=0.3245, pruned_loss=0.09725, over 7145.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2889, pruned_loss=0.06339, over 1431406.66 frames.], batch size: 20, lr: 4.86e-04
2022-05-27 10:28:06,065 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 10:28:15,409 INFO [train.py:871] (3/4) Epoch 11, validation: loss=0.1722, simple_loss=0.2724, pruned_loss=0.03599, over 868885.00 frames.
2022-05-27 10:28:54,246 INFO [train.py:842] (3/4) Epoch 11, batch 6050, loss[loss=0.1975, simple_loss=0.2844, pruned_loss=0.0553, over 7289.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2885, pruned_loss=0.06329, over 1427777.09 frames.], batch size: 24, lr: 4.86e-04
2022-05-27 10:29:33,430 INFO [train.py:842] (3/4) Epoch 11, batch 6100, loss[loss=0.1988, simple_loss=0.2916, pruned_loss=0.05301, over 7306.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2871, pruned_loss=0.06281, over 1427863.90 frames.], batch size: 24, lr: 4.86e-04
2022-05-27 10:30:11,965 INFO [train.py:842] (3/4) Epoch 11, batch 6150, loss[loss=0.2212, simple_loss=0.2968, pruned_loss=0.07275, over 7159.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2879, pruned_loss=0.06351, over 1432004.82 frames.], batch size: 19, lr: 4.86e-04
2022-05-27 10:30:50,898 INFO [train.py:842] (3/4) Epoch 11, batch 6200, loss[loss=0.2396, simple_loss=0.325, pruned_loss=0.07712, over 7302.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2881, pruned_loss=0.0637, over 1431957.29 frames.], batch size: 24, lr: 4.85e-04
2022-05-27 10:31:29,396 INFO [train.py:842] (3/4) Epoch 11, batch 6250, loss[loss=0.2492, simple_loss=0.3204, pruned_loss=0.08896, over 6825.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2879, pruned_loss=0.06353, over 1434146.30 frames.], batch size: 31, lr: 4.85e-04
2022-05-27 10:32:08,641 INFO [train.py:842] (3/4) Epoch 11, batch 6300, loss[loss=0.1871, simple_loss=0.2627, pruned_loss=0.05579, over 7014.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2872, pruned_loss=0.06301, over 1431046.51 frames.], batch size: 16, lr: 4.85e-04
2022-05-27 10:32:47,168 INFO [train.py:842] (3/4) Epoch 11, batch 6350, loss[loss=0.2413, simple_loss=0.3179, pruned_loss=0.08233, over 7132.00 frames.], tot_loss[loss=0.207, simple_loss=0.2875, pruned_loss=0.06325, over 1428709.50 frames.], batch size: 26, lr: 4.85e-04
2022-05-27 10:33:25,799 INFO [train.py:842] (3/4) Epoch 11, batch 6400, loss[loss=0.1766, simple_loss=0.2468, pruned_loss=0.05321, over 7165.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2884, pruned_loss=0.06368, over 1423717.23 frames.], batch size: 18, lr: 4.85e-04
2022-05-27 10:34:04,324 INFO [train.py:842] (3/4) Epoch 11, batch 6450, loss[loss=0.1871, simple_loss=0.2828, pruned_loss=0.04567, over 7332.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2895, pruned_loss=0.06448, over 1416057.69 frames.], batch size: 22, lr: 4.85e-04
2022-05-27 10:34:42,922 INFO [train.py:842] (3/4) Epoch 11, batch 6500, loss[loss=0.1932, simple_loss=0.2782, pruned_loss=0.05408, over 7225.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2889, pruned_loss=0.06342, over 1415704.69 frames.], batch size: 20, lr: 4.85e-04
2022-05-27 10:35:21,593 INFO [train.py:842] (3/4) Epoch 11, batch 6550, loss[loss=0.2076, simple_loss=0.2836, pruned_loss=0.06575, over 7260.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2889, pruned_loss=0.06391, over 1417021.43 frames.], batch size: 19, lr: 4.85e-04
2022-05-27 10:36:00,499 INFO [train.py:842] (3/4) Epoch 11, batch 6600, loss[loss=0.2311, simple_loss=0.3128, pruned_loss=0.07468, over 6966.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2876, pruned_loss=0.06304, over 1415803.73 frames.], batch size: 28, lr: 4.84e-04
2022-05-27 10:36:39,108 INFO [train.py:842] (3/4) Epoch 11, batch 6650, loss[loss=0.2188, simple_loss=0.3008, pruned_loss=0.06841, over 7254.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2883, pruned_loss=0.06365, over 1413787.86 frames.], batch size: 24, lr: 4.84e-04
2022-05-27 10:37:18,316 INFO [train.py:842] (3/4) Epoch 11, batch 6700, loss[loss=0.1908, simple_loss=0.2662, pruned_loss=0.05769, over 7377.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2888, pruned_loss=0.06399, over 1417482.05 frames.], batch size: 23, lr: 4.84e-04
2022-05-27 10:37:56,931 INFO [train.py:842] (3/4) Epoch 11, batch 6750, loss[loss=0.2082, simple_loss=0.2993, pruned_loss=0.05856, over 7332.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2896, pruned_loss=0.06407, over 1417673.01 frames.], batch size: 22, lr: 4.84e-04
2022-05-27 10:38:35,770 INFO [train.py:842] (3/4) Epoch 11, batch 6800, loss[loss=0.1702, simple_loss=0.2368, pruned_loss=0.05176, over 6807.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2884, pruned_loss=0.06356, over 1421187.10 frames.], batch size: 15, lr: 4.84e-04
2022-05-27 10:39:14,378 INFO [train.py:842] (3/4) Epoch 11, batch 6850, loss[loss=0.1716, simple_loss=0.247, pruned_loss=0.04807, over 6992.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2879, pruned_loss=0.06338, over 1423076.23 frames.], batch size: 16, lr: 4.84e-04
2022-05-27 10:39:53,319 INFO [train.py:842] (3/4) Epoch 11, batch 6900, loss[loss=0.1867, simple_loss=0.2744, pruned_loss=0.04954, over 7224.00 frames.], tot_loss[loss=0.208, simple_loss=0.2888, pruned_loss=0.06367, over 1426812.17 frames.], batch size: 21, lr: 4.84e-04
2022-05-27 10:40:31,865 INFO [train.py:842] (3/4) Epoch 11, batch 6950, loss[loss=0.2223, simple_loss=0.316, pruned_loss=0.06428, over 7146.00 frames.], tot_loss[loss=0.209, simple_loss=0.29, pruned_loss=0.06401, over 1429901.16 frames.], batch size: 20, lr: 4.84e-04
2022-05-27 10:41:10,673 INFO [train.py:842] (3/4) Epoch 11, batch 7000, loss[loss=0.2135, simple_loss=0.2949, pruned_loss=0.066, over 6866.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2899, pruned_loss=0.0635, over 1426594.72 frames.], batch size: 31, lr: 4.83e-04
2022-05-27 10:41:49,515 INFO [train.py:842] (3/4) Epoch 11, batch 7050, loss[loss=0.187, simple_loss=0.2584, pruned_loss=0.05786, over 7165.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2906, pruned_loss=0.06424, over 1424346.87 frames.], batch size: 18, lr: 4.83e-04
2022-05-27 10:42:28,464 INFO [train.py:842] (3/4) Epoch 11, batch 7100, loss[loss=0.2038, simple_loss=0.2771, pruned_loss=0.06521, over 6747.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2898, pruned_loss=0.0642, over 1423923.36 frames.], batch size: 15, lr: 4.83e-04
2022-05-27 10:43:06,962 INFO [train.py:842] (3/4) Epoch 11, batch 7150, loss[loss=0.1936, simple_loss=0.2689, pruned_loss=0.05917, over 7419.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2896, pruned_loss=0.06398, over 1424815.60 frames.], batch size: 20, lr: 4.83e-04
2022-05-27 10:43:45,961 INFO [train.py:842] (3/4) Epoch 11, batch 7200, loss[loss=0.1953, simple_loss=0.2863, pruned_loss=0.05208, over 7225.00 frames.], tot_loss[loss=0.2067, simple_loss=0.288, pruned_loss=0.06271, over 1424498.73 frames.], batch size: 20, lr: 4.83e-04
2022-05-27 10:44:24,374 INFO [train.py:842] (3/4) Epoch 11, batch 7250, loss[loss=0.2308, simple_loss=0.318, pruned_loss=0.07181, over 7148.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2893, pruned_loss=0.06311, over 1424071.26 frames.], batch size: 20, lr: 4.83e-04
2022-05-27 10:45:23,845 INFO [train.py:842] (3/4) Epoch 11, batch 7300, loss[loss=0.2135, simple_loss=0.3038, pruned_loss=0.06158, over 6728.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2907, pruned_loss=0.06395, over 1422577.83 frames.], batch size: 31, lr: 4.83e-04
2022-05-27 10:46:12,725 INFO [train.py:842] (3/4) Epoch 11, batch 7350, loss[loss=0.2039, simple_loss=0.2851, pruned_loss=0.06131, over 7118.00 frames.], tot_loss[loss=0.207, simple_loss=0.2883, pruned_loss=0.06289, over 1426121.88 frames.], batch size: 28, lr: 4.83e-04
2022-05-27 10:46:51,440 INFO [train.py:842] (3/4) Epoch 11, batch 7400, loss[loss=0.2814, simple_loss=0.3369, pruned_loss=0.1129, over 7234.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2895, pruned_loss=0.06377, over 1425155.29 frames.], batch size: 20, lr: 4.83e-04
2022-05-27 10:47:30,240 INFO [train.py:842] (3/4) Epoch 11, batch 7450, loss[loss=0.2293, simple_loss=0.3091, pruned_loss=0.07476, over 7265.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2895, pruned_loss=0.06378, over 1425353.00 frames.], batch size: 25, lr: 4.82e-04
2022-05-27 10:48:09,493 INFO [train.py:842] (3/4) Epoch 11, batch 7500, loss[loss=0.2229, simple_loss=0.3003, pruned_loss=0.07278, over 7340.00 frames.], tot_loss[loss=0.2084, simple_loss=0.289, pruned_loss=0.06389, over 1426975.42 frames.], batch size: 20, lr: 4.82e-04
2022-05-27 10:48:48,116 INFO [train.py:842] (3/4) Epoch 11, batch 7550, loss[loss=0.204, simple_loss=0.2956, pruned_loss=0.05615, over 7336.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2884, pruned_loss=0.06375, over 1424863.27 frames.], batch size: 22, lr: 4.82e-04
2022-05-27 10:49:26,807 INFO [train.py:842] (3/4) Epoch 11, batch 7600, loss[loss=0.1756, simple_loss=0.2578, pruned_loss=0.04669, over 7270.00 frames.], tot_loss[loss=0.207, simple_loss=0.2882, pruned_loss=0.06296, over 1423433.69 frames.], batch size: 19, lr: 4.82e-04
2022-05-27 10:50:05,347 INFO [train.py:842] (3/4) Epoch 11, batch 7650, loss[loss=0.1823, simple_loss=0.2569, pruned_loss=0.05379, over 6778.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2875, pruned_loss=0.06287, over 1417420.01 frames.], batch size: 15, lr: 4.82e-04
2022-05-27 10:50:44,222 INFO [train.py:842] (3/4) Epoch 11, batch 7700, loss[loss=0.2021, simple_loss=0.2878, pruned_loss=0.05821, over 7208.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2886, pruned_loss=0.06338, over 1421948.64 frames.], batch size: 22, lr: 4.82e-04
2022-05-27 10:51:22,655 INFO [train.py:842] (3/4) Epoch 11, batch 7750, loss[loss=0.186, simple_loss=0.2876, pruned_loss=0.04222, over 7220.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2889, pruned_loss=0.06324, over 1421150.03 frames.], batch size: 21, lr: 4.82e-04
2022-05-27 10:52:01,626 INFO [train.py:842] (3/4) Epoch 11, batch 7800, loss[loss=0.2116, simple_loss=0.2832, pruned_loss=0.06999, over 7073.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2897, pruned_loss=0.06373, over 1421418.79 frames.], batch size: 18, lr: 4.82e-04
2022-05-27 10:52:40,115 INFO [train.py:842] (3/4) Epoch 11, batch 7850, loss[loss=0.1743, simple_loss=0.2663, pruned_loss=0.04121, over 7220.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2891, pruned_loss=0.06329, over 1420624.68 frames.], batch size: 21, lr: 4.81e-04
2022-05-27 10:53:18,871 INFO [train.py:842] (3/4) Epoch 11, batch 7900, loss[loss=0.1503, simple_loss=0.239, pruned_loss=0.03075, over 7164.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2896, pruned_loss=0.0637, over 1422344.03 frames.], batch size: 18, lr: 4.81e-04
2022-05-27 10:53:57,420 INFO [train.py:842] (3/4) Epoch 11, batch 7950, loss[loss=0.2056, simple_loss=0.2954, pruned_loss=0.05786, over 7417.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2885, pruned_loss=0.063, over 1424844.89 frames.], batch size: 21, lr: 4.81e-04
2022-05-27 10:54:36,324 INFO [train.py:842] (3/4) Epoch 11, batch 8000, loss[loss=0.201, simple_loss=0.2892, pruned_loss=0.05639, over 7423.00 frames.], tot_loss[loss=0.207, simple_loss=0.2882, pruned_loss=0.06286, over 1425147.97 frames.], batch size: 21, lr: 4.81e-04
2022-05-27 10:55:14,880 INFO [train.py:842] (3/4) Epoch 11, batch 8050, loss[loss=0.2015, simple_loss=0.2926, pruned_loss=0.05518, over 7322.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2884, pruned_loss=0.06323, over 1429520.92 frames.], batch size: 25, lr: 4.81e-04
2022-05-27 10:55:53,857 INFO [train.py:842] (3/4) Epoch 11, batch 8100, loss[loss=0.1906, simple_loss=0.2767, pruned_loss=0.05225, over 7270.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2866, pruned_loss=0.06247, over 1429686.31 frames.], batch size: 24, lr: 4.81e-04
2022-05-27 10:56:32,351 INFO [train.py:842] (3/4) Epoch 11, batch 8150, loss[loss=0.2547, simple_loss=0.3294, pruned_loss=0.09001, over 7380.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2866, pruned_loss=0.06231, over 1430065.40 frames.], batch size: 23, lr: 4.81e-04
2022-05-27 10:57:11,048 INFO [train.py:842] (3/4) Epoch 11, batch 8200, loss[loss=0.1928, simple_loss=0.2765, pruned_loss=0.05453, over 7280.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2876, pruned_loss=0.0626, over 1423613.44 frames.], batch size: 24, lr: 4.81e-04
2022-05-27 10:57:49,606 INFO [train.py:842] (3/4) Epoch 11, batch 8250, loss[loss=0.1776, simple_loss=0.2704, pruned_loss=0.04243, over 7424.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2881, pruned_loss=0.06279, over 1426475.97 frames.], batch size: 20, lr: 4.80e-04
2022-05-27 10:58:28,741 INFO [train.py:842] (3/4) Epoch 11, batch 8300, loss[loss=0.2023, simple_loss=0.2972, pruned_loss=0.05367, over 7220.00 frames.], tot_loss[loss=0.208, simple_loss=0.2892, pruned_loss=0.06336, over 1429318.07 frames.], batch size: 22, lr: 4.80e-04
2022-05-27 10:59:07,278 INFO [train.py:842] (3/4) Epoch 11, batch 8350, loss[loss=0.1975, simple_loss=0.2725, pruned_loss=0.06125, over 7409.00 frames.], tot_loss[loss=0.2081, simple_loss=0.289, pruned_loss=0.0636, over 1427206.96 frames.], batch size: 18, lr: 4.80e-04
2022-05-27 10:59:46,103 INFO [train.py:842] (3/4) Epoch 11, batch 8400, loss[loss=0.256, simple_loss=0.3262, pruned_loss=0.09292, over 7301.00 frames.], tot_loss[loss=0.207, simple_loss=0.288, pruned_loss=0.06305, over 1428974.03 frames.], batch size: 25, lr: 4.80e-04
2022-05-27 11:00:24,523 INFO [train.py:842] (3/4) Epoch 11, batch 8450, loss[loss=0.1904, simple_loss=0.2878, pruned_loss=0.04649, over 7298.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2874, pruned_loss=0.06272, over 1423803.64 frames.], batch size: 24, lr: 4.80e-04
2022-05-27 11:01:03,514 INFO [train.py:842] (3/4) Epoch 11, batch 8500, loss[loss=0.2012, simple_loss=0.2931, pruned_loss=0.05461, over 7197.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2867, pruned_loss=0.06259, over 1421637.62 frames.], batch size: 22, lr: 4.80e-04
2022-05-27 11:01:42,123 INFO [train.py:842] (3/4) Epoch 11, batch 8550, loss[loss=0.1748, simple_loss=0.2588, pruned_loss=0.04539, over 7360.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2858, pruned_loss=0.06218, over 1422300.30 frames.], batch size: 19, lr: 4.80e-04
2022-05-27 11:02:21,313 INFO [train.py:842] (3/4) Epoch 11, batch 8600, loss[loss=0.1866, simple_loss=0.2613, pruned_loss=0.05599, over 7160.00 frames.], tot_loss[loss=0.2044, simple_loss=0.285, pruned_loss=0.06192, over 1420831.68 frames.], batch size: 17, lr: 4.80e-04
2022-05-27 11:02:59,936 INFO [train.py:842] (3/4) Epoch 11, batch 8650, loss[loss=0.1883, simple_loss=0.2756, pruned_loss=0.05055, over 7419.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2847, pruned_loss=0.06149, over 1424994.12 frames.], batch size: 18, lr: 4.80e-04
2022-05-27 11:03:38,560 INFO [train.py:842] (3/4) Epoch 11, batch 8700, loss[loss=0.1632, simple_loss=0.2419, pruned_loss=0.04226, over 7411.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2845, pruned_loss=0.06153, over 1419833.29 frames.], batch size: 18, lr: 4.79e-04
2022-05-27 11:04:16,857 INFO [train.py:842] (3/4) Epoch 11, batch 8750, loss[loss=0.2155, simple_loss=0.2948, pruned_loss=0.06814, over 7189.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2857, pruned_loss=0.06264, over 1419113.96 frames.], batch size: 26, lr: 4.79e-04
2022-05-27 11:04:55,660 INFO [train.py:842] (3/4) Epoch 11, batch 8800, loss[loss=0.1679, simple_loss=0.2452, pruned_loss=0.04527, over 7358.00 frames.], tot_loss[loss=0.205, simple_loss=0.2857, pruned_loss=0.06216, over 1418421.93 frames.], batch size: 19, lr: 4.79e-04
2022-05-27 11:05:34,681 INFO [train.py:842] (3/4) Epoch 11, batch 8850, loss[loss=0.2065, simple_loss=0.2762, pruned_loss=0.06838, over 7414.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2866, pruned_loss=0.06321, over 1412642.24 frames.], batch size: 18, lr: 4.79e-04
2022-05-27 11:06:13,199 INFO [train.py:842] (3/4) Epoch 11, batch 8900, loss[loss=0.2027, simple_loss=0.2912, pruned_loss=0.05713, over 7215.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2867, pruned_loss=0.06322, over 1413962.04 frames.], batch size: 21, lr: 4.79e-04
2022-05-27 11:06:51,392 INFO [train.py:842] (3/4) Epoch 11, batch 8950, loss[loss=0.2152, simple_loss=0.2961, pruned_loss=0.06712, over 7190.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2875, pruned_loss=0.0636, over 1400498.54 frames.], batch size: 26, lr: 4.79e-04
2022-05-27 11:07:29,533 INFO [train.py:842] (3/4) Epoch 11, batch 9000, loss[loss=0.2101, simple_loss=0.2949, pruned_loss=0.06265, over 6692.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2892, pruned_loss=0.06498, over 1384213.90 frames.], batch size: 31, lr: 4.79e-04
2022-05-27 11:07:29,534 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 11:07:39,052 INFO [train.py:871] (3/4) Epoch 11, validation: loss=0.1709, simple_loss=0.2721, pruned_loss=0.03482, over 868885.00 frames.
2022-05-27 11:08:17,103 INFO [train.py:842] (3/4) Epoch 11, batch 9050, loss[loss=0.3031, simple_loss=0.3653, pruned_loss=0.1205, over 4877.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2924, pruned_loss=0.06667, over 1370237.26 frames.], batch size: 52, lr: 4.79e-04
2022-05-27 11:08:55,110 INFO [train.py:842] (3/4) Epoch 11, batch 9100, loss[loss=0.2578, simple_loss=0.3243, pruned_loss=0.09569, over 4825.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2967, pruned_loss=0.07036, over 1294737.36 frames.], batch size: 52, lr: 4.78e-04
2022-05-27 11:09:32,716 INFO [train.py:842] (3/4) Epoch 11, batch 9150, loss[loss=0.2171, simple_loss=0.2971, pruned_loss=0.06852, over 5300.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3012, pruned_loss=0.07421, over 1232673.99 frames.], batch size: 52, lr: 4.78e-04
2022-05-27 11:10:24,905 INFO [train.py:842] (3/4) Epoch 12, batch 0, loss[loss=0.2211, simple_loss=0.3029, pruned_loss=0.06959, over 7410.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3029, pruned_loss=0.06959, over 7410.00 frames.], batch size: 21, lr: 4.61e-04
2022-05-27 11:11:03,745 INFO [train.py:842] (3/4) Epoch 12, batch 50, loss[loss=0.2903, simple_loss=0.3587, pruned_loss=0.111, over 5526.00 frames.], tot_loss[loss=0.2107, simple_loss=0.291, pruned_loss=0.06518, over 319764.55 frames.], batch size: 52, lr: 4.61e-04
2022-05-27 11:11:42,662 INFO [train.py:842] (3/4) Epoch 12, batch 100, loss[loss=0.211, simple_loss=0.299, pruned_loss=0.06146, over 6208.00 frames.], tot_loss[loss=0.2086, simple_loss=0.29, pruned_loss=0.06362, over 559251.62 frames.], batch size: 38, lr: 4.61e-04
2022-05-27 11:12:21,211 INFO [train.py:842] (3/4) Epoch 12, batch 150, loss[loss=0.1595, simple_loss=0.251, pruned_loss=0.03393, over 7288.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2897, pruned_loss=0.06222, over 749134.95 frames.], batch size: 17, lr: 4.61e-04
2022-05-27 11:12:59,975 INFO [train.py:842] (3/4) Epoch 12, batch 200, loss[loss=0.2098, simple_loss=0.2994, pruned_loss=0.06013, over 7207.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2903, pruned_loss=0.06234, over 897480.76 frames.], batch size: 22, lr: 4.61e-04
2022-05-27 11:13:38,465 INFO [train.py:842] (3/4) Epoch 12, batch 250, loss[loss=0.2234, simple_loss=0.3028, pruned_loss=0.07202, over 6816.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2882, pruned_loss=0.06139, over 1014653.84 frames.], batch size: 31, lr: 4.61e-04
2022-05-27 11:14:17,098 INFO [train.py:842] (3/4) Epoch 12, batch 300, loss[loss=0.2672, simple_loss=0.3442, pruned_loss=0.09515, over 7205.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2901, pruned_loss=0.06285, over 1098758.36 frames.], batch size: 22, lr: 4.61e-04
2022-05-27 11:14:55,698 INFO [train.py:842] (3/4) Epoch 12, batch 350, loss[loss=0.1879, simple_loss=0.276, pruned_loss=0.04994, over 7333.00 frames.], tot_loss[loss=0.206, simple_loss=0.2881, pruned_loss=0.06198, over 1166222.83 frames.], batch size: 22, lr: 4.61e-04
2022-05-27 11:15:34,542 INFO [train.py:842] (3/4) Epoch 12, batch 400, loss[loss=0.1976, simple_loss=0.2898, pruned_loss=0.05271, over 7335.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2867, pruned_loss=0.06102, over 1221526.78 frames.], batch size: 22, lr: 4.60e-04
2022-05-27 11:16:13,179 INFO [train.py:842] (3/4) Epoch 12, batch 450, loss[loss=0.1939, simple_loss=0.2789, pruned_loss=0.05447, over 7166.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2868, pruned_loss=0.06142, over 1269655.08 frames.], batch size: 19, lr: 4.60e-04
2022-05-27 11:16:52,034 INFO [train.py:842] (3/4) Epoch 12, batch 500, loss[loss=0.2295, simple_loss=0.3248, pruned_loss=0.06707, over 7397.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2881, pruned_loss=0.06257, over 1303292.47 frames.], batch size: 23, lr: 4.60e-04
2022-05-27 11:17:30,962 INFO [train.py:842] (3/4) Epoch 12, batch 550, loss[loss=0.1995, simple_loss=0.2871, pruned_loss=0.056, over 7413.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2876, pruned_loss=0.06229, over 1330604.71 frames.], batch size: 21, lr: 4.60e-04
2022-05-27 11:18:10,104 INFO [train.py:842] (3/4) Epoch 12, batch 600, loss[loss=0.2021, simple_loss=0.2875, pruned_loss=0.05836, over 7335.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2873, pruned_loss=0.06279, over 1349379.29 frames.], batch size: 22, lr: 4.60e-04
2022-05-27 11:18:48,946 INFO [train.py:842] (3/4) Epoch 12, batch 650, loss[loss=0.2043, simple_loss=0.3008, pruned_loss=0.05394, over 7372.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2857, pruned_loss=0.06186, over 1369818.27 frames.], batch size: 23, lr: 4.60e-04
2022-05-27 11:19:27,779 INFO [train.py:842] (3/4) Epoch 12, batch 700, loss[loss=0.2279, simple_loss=0.3066, pruned_loss=0.07458, over 7305.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2862, pruned_loss=0.06183, over 1379335.84 frames.], batch size: 24, lr: 4.60e-04
2022-05-27 11:20:06,293 INFO [train.py:842] (3/4) Epoch 12, batch 750, loss[loss=0.1718, simple_loss=0.2574, pruned_loss=0.04312, over 7321.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2881, pruned_loss=0.06333, over 1385098.86 frames.], batch size: 20, lr: 4.60e-04
2022-05-27 11:20:45,317 INFO [train.py:842] (3/4) Epoch 12, batch 800, loss[loss=0.2029, simple_loss=0.277, pruned_loss=0.06439, over 7406.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2871, pruned_loss=0.063, over 1398260.94 frames.], batch size: 18, lr: 4.60e-04
2022-05-27 11:21:23,950 INFO [train.py:842] (3/4) Epoch 12, batch 850, loss[loss=0.2356, simple_loss=0.3108, pruned_loss=0.08016, over 6713.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2864, pruned_loss=0.06234, over 1401896.70 frames.], batch size: 31, lr: 4.59e-04
2022-05-27 11:22:02,925 INFO [train.py:842] (3/4) Epoch 12, batch 900, loss[loss=0.2638, simple_loss=0.3317, pruned_loss=0.09792, over 7332.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2869, pruned_loss=0.06204, over 1406110.10 frames.], batch size: 22, lr: 4.59e-04
2022-05-27 11:22:41,564 INFO [train.py:842] (3/4) Epoch 12, batch 950, loss[loss=0.1772, simple_loss=0.2666, pruned_loss=0.04386, over 7429.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2868, pruned_loss=0.06198, over 1411730.69 frames.], batch size: 20, lr: 4.59e-04
2022-05-27 11:23:20,323 INFO [train.py:842] (3/4) Epoch 12, batch 1000, loss[loss=0.1797, simple_loss=0.2679, pruned_loss=0.04574, over 7147.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2875, pruned_loss=0.06183, over 1415025.55 frames.], batch size: 19, lr: 4.59e-04
2022-05-27 11:23:58,899 INFO [train.py:842] (3/4) Epoch 12, batch 1050, loss[loss=0.1693, simple_loss=0.2445, pruned_loss=0.04706, over 6995.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2874, pruned_loss=0.06195, over 1415052.14 frames.], batch size: 16, lr: 4.59e-04
2022-05-27 11:24:37,602 INFO [train.py:842] (3/4) Epoch 12, batch 1100, loss[loss=0.1616, simple_loss=0.2483, pruned_loss=0.03741, over 7153.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2878, pruned_loss=0.06221, over 1417949.24 frames.], batch size: 19, lr: 4.59e-04
2022-05-27 11:25:16,154 INFO [train.py:842] (3/4) Epoch 12, batch 1150, loss[loss=0.2166, simple_loss=0.2923, pruned_loss=0.07047, over 4856.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2872, pruned_loss=0.06176, over 1420635.32 frames.], batch size: 52, lr: 4.59e-04
2022-05-27 11:25:55,243 INFO [train.py:842] (3/4) Epoch 12, batch 1200, loss[loss=0.2252, simple_loss=0.3183, pruned_loss=0.06606, over 7126.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2862, pruned_loss=0.06041, over 1423658.44 frames.], batch size: 21, lr: 4.59e-04
2022-05-27 11:26:33,785 INFO [train.py:842] (3/4) Epoch 12, batch 1250, loss[loss=0.165, simple_loss=0.2501, pruned_loss=0.03999, over 7022.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2866, pruned_loss=0.06088, over 1425501.40 frames.], batch size: 16, lr: 4.59e-04
2022-05-27 11:27:12,550 INFO [train.py:842] (3/4) Epoch 12, batch 1300, loss[loss=0.1932, simple_loss=0.2738, pruned_loss=0.05631, over 7336.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2865, pruned_loss=0.06091, over 1427847.52 frames.], batch size: 20, lr: 4.58e-04
2022-05-27 11:27:51,024 INFO [train.py:842] (3/4) Epoch 12, batch 1350, loss[loss=0.1884, simple_loss=0.278, pruned_loss=0.04935, over 7317.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2865, pruned_loss=0.06085, over 1424528.71 frames.], batch size: 21, lr: 4.58e-04
2022-05-27 11:28:30,046 INFO [train.py:842] (3/4) Epoch 12, batch 1400, loss[loss=0.1613, simple_loss=0.2519, pruned_loss=0.03537, over 7313.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2866, pruned_loss=0.06135, over 1421586.42 frames.], batch size: 21, lr: 4.58e-04
2022-05-27 11:29:08,599 INFO [train.py:842] (3/4) Epoch 12, batch 1450, loss[loss=0.1864, simple_loss=0.2752, pruned_loss=0.04877, over 7065.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2869, pruned_loss=0.06143, over 1421522.65 frames.], batch size: 18, lr: 4.58e-04
2022-05-27 11:29:47,665 INFO [train.py:842] (3/4) Epoch 12, batch 1500, loss[loss=0.2244, simple_loss=0.3103, pruned_loss=0.06926, over 7181.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2869, pruned_loss=0.06219, over 1425351.90 frames.], batch size: 23, lr: 4.58e-04
2022-05-27 11:30:26,259 INFO [train.py:842] (3/4) Epoch 12, batch 1550, loss[loss=0.1802, simple_loss=0.2637, pruned_loss=0.04838, over 7247.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2852, pruned_loss=0.06115, over 1424818.96 frames.], batch size: 20, lr: 4.58e-04
2022-05-27 11:31:04,965 INFO [train.py:842] (3/4) Epoch 12, batch 1600, loss[loss=0.2005, simple_loss=0.2748, pruned_loss=0.06316, over 7362.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2856, pruned_loss=0.06111, over 1425637.38 frames.], batch size: 19, lr: 4.58e-04
2022-05-27 11:31:43,502 INFO [train.py:842] (3/4) Epoch 12, batch 1650, loss[loss=0.2166, simple_loss=0.3007, pruned_loss=0.06629, over 7382.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2854, pruned_loss=0.06098, over 1426453.11 frames.], batch size: 23, lr: 4.58e-04
2022-05-27 11:32:22,290 INFO [train.py:842] (3/4) Epoch 12, batch 1700, loss[loss=0.2061, simple_loss=0.2912, pruned_loss=0.06055, over 7222.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2852, pruned_loss=0.06058, over 1427462.13 frames.], batch size: 21, lr: 4.58e-04
2022-05-27 11:33:00,976 INFO [train.py:842] (3/4) Epoch 12, batch 1750, loss[loss=0.2431, simple_loss=0.3297, pruned_loss=0.07823, over 7118.00 frames.], tot_loss[loss=0.204, simple_loss=0.286, pruned_loss=0.06099, over 1428212.15 frames.], batch size: 26, lr: 4.57e-04
2022-05-27 11:33:40,072 INFO [train.py:842] (3/4) Epoch 12, batch 1800, loss[loss=0.2085, simple_loss=0.2839, pruned_loss=0.06653, over 6994.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2853, pruned_loss=0.06096, over 1427715.32 frames.], batch size: 16, lr: 4.57e-04
2022-05-27 11:34:18,707 INFO [train.py:842] (3/4) Epoch 12, batch 1850, loss[loss=0.2294, simple_loss=0.3077, pruned_loss=0.0755, over 7104.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2853, pruned_loss=0.06088, over 1426124.28 frames.], batch size: 26, lr: 4.57e-04
2022-05-27 11:34:57,830 INFO [train.py:842] (3/4) Epoch 12, batch 1900, loss[loss=0.1891, simple_loss=0.275, pruned_loss=0.05162, over 7419.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2854, pruned_loss=0.06051, over 1428442.58 frames.], batch size: 20, lr: 4.57e-04
2022-05-27 11:35:36,406 INFO [train.py:842] (3/4) Epoch 12, batch 1950, loss[loss=0.1661, simple_loss=0.2475, pruned_loss=0.04234, over 6999.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2855, pruned_loss=0.06068, over 1426693.19 frames.], batch size: 16, lr: 4.57e-04
2022-05-27 11:36:15,183 INFO [train.py:842] (3/4) Epoch 12, batch 2000, loss[loss=0.2085, simple_loss=0.2913, pruned_loss=0.06287, over 6603.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2854, pruned_loss=0.06073, over 1424759.30 frames.], batch size: 38, lr: 4.57e-04
2022-05-27 11:36:53,632 INFO [train.py:842] (3/4) Epoch 12, batch 2050, loss[loss=0.2039, simple_loss=0.2907, pruned_loss=0.05851, over 7381.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2861, pruned_loss=0.06145, over 1423636.09 frames.], batch size: 23, lr: 4.57e-04
2022-05-27 11:37:32,474 INFO [train.py:842] (3/4) Epoch 12, batch 2100, loss[loss=0.1894, simple_loss=0.2852, pruned_loss=0.04678, over 6718.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2859, pruned_loss=0.06121, over 1428532.77 frames.], batch size: 31, lr: 4.57e-04
2022-05-27 11:38:11,264 INFO [train.py:842] (3/4) Epoch 12, batch 2150, loss[loss=0.188, simple_loss=0.2552, pruned_loss=0.06041, over 6813.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2848, pruned_loss=0.06068, over 1422945.62 frames.], batch size: 15, lr: 4.57e-04
2022-05-27 11:38:50,373 INFO [train.py:842] (3/4) Epoch 12, batch 2200, loss[loss=0.2021, simple_loss=0.2744, pruned_loss=0.06487, over 7430.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2847, pruned_loss=0.06044, over 1427171.33 frames.], batch size: 20, lr: 4.56e-04
2022-05-27 11:39:29,075 INFO [train.py:842] (3/4) Epoch 12, batch 2250, loss[loss=0.1833, simple_loss=0.2601, pruned_loss=0.05319, over 7120.00 frames.], tot_loss[loss=0.203, simple_loss=0.2849, pruned_loss=0.06053, over 1426318.57 frames.], batch size: 17, lr: 4.56e-04
2022-05-27 11:40:07,787 INFO [train.py:842] (3/4) Epoch 12, batch 2300, loss[loss=0.1945, simple_loss=0.2724, pruned_loss=0.0583, over 7352.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2856, pruned_loss=0.0604, over 1424878.77 frames.], batch size: 19, lr: 4.56e-04
2022-05-27 11:40:46,478 INFO [train.py:842] (3/4) Epoch 12, batch 2350, loss[loss=0.2298, simple_loss=0.3081, pruned_loss=0.07581, over 7303.00 frames.], tot_loss[loss=0.203, simple_loss=0.2851, pruned_loss=0.0604, over 1426149.94 frames.], batch size: 24, lr: 4.56e-04
2022-05-27 11:41:25,326 INFO [train.py:842] (3/4) Epoch 12, batch 2400, loss[loss=0.2263, simple_loss=0.3126, pruned_loss=0.06995, over 7114.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2851, pruned_loss=0.05987, over 1428359.40 frames.], batch size: 21, lr: 4.56e-04
2022-05-27 11:42:03,666 INFO [train.py:842] (3/4) Epoch 12, batch 2450, loss[loss=0.1936, simple_loss=0.2843, pruned_loss=0.05146, over 7233.00 frames.], tot_loss[loss=0.204, simple_loss=0.2865, pruned_loss=0.06078, over 1426260.86 frames.], batch size: 20, lr: 4.56e-04
2022-05-27 11:42:42,648 INFO [train.py:842] (3/4) Epoch 12, batch 2500, loss[loss=0.1983, simple_loss=0.2603, pruned_loss=0.06809, over 7063.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2856, pruned_loss=0.06034, over 1425678.67 frames.], batch size: 18, lr: 4.56e-04
2022-05-27 11:43:21,064 INFO [train.py:842] (3/4) Epoch 12, batch 2550, loss[loss=0.1717, simple_loss=0.2475, pruned_loss=0.04798, over 7286.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2862, pruned_loss=0.06075, over 1427796.63 frames.], batch size: 17, lr: 4.56e-04
2022-05-27 11:43:59,774 INFO [train.py:842] (3/4) Epoch 12, batch 2600, loss[loss=0.1982, simple_loss=0.2867, pruned_loss=0.05489, over 7284.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2869, pruned_loss=0.06185, over 1421809.49 frames.], batch size: 24, lr: 4.56e-04
2022-05-27 11:44:38,251 INFO [train.py:842] (3/4) Epoch 12, batch 2650, loss[loss=0.1897, simple_loss=0.2706, pruned_loss=0.05445, over 7257.00 frames.], tot_loss[loss=0.205, simple_loss=0.2868, pruned_loss=0.06156, over 1418764.23 frames.], batch size: 19, lr: 4.55e-04
2022-05-27 11:45:17,044 INFO [train.py:842] (3/4) Epoch 12, batch 2700, loss[loss=0.1929, simple_loss=0.2883, pruned_loss=0.04874, over 7299.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2871, pruned_loss=0.06172, over 1422395.26 frames.], batch size: 25, lr: 4.55e-04
2022-05-27 11:45:55,571 INFO [train.py:842] (3/4) Epoch 12, batch 2750, loss[loss=0.1808, simple_loss=0.2712, pruned_loss=0.04523, over 7430.00 frames.], tot_loss[loss=0.2053, simple_loss=0.287, pruned_loss=0.06179, over 1425796.78 frames.], batch size: 20, lr: 4.55e-04
2022-05-27 11:46:34,714 INFO [train.py:842] (3/4) Epoch 12, batch 2800, loss[loss=0.2395, simple_loss=0.3221, pruned_loss=0.07848, over 7132.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2862, pruned_loss=0.06116, over 1426318.43 frames.], batch size: 21, lr: 4.55e-04
2022-05-27 11:47:13,259 INFO [train.py:842] (3/4) Epoch 12, batch 2850, loss[loss=0.193, simple_loss=0.2809, pruned_loss=0.05251, over 7313.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2855, pruned_loss=0.06084, over 1428547.50 frames.], batch size: 21, lr: 4.55e-04
2022-05-27 11:47:54,670 INFO [train.py:842] (3/4) Epoch 12, batch 2900, loss[loss=0.2244, simple_loss=0.309, pruned_loss=0.06993, over 7296.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2877, pruned_loss=0.06185, over 1424320.81 frames.], batch size: 24, lr: 4.55e-04
2022-05-27 11:48:33,254 INFO [train.py:842] (3/4) Epoch 12, batch 2950, loss[loss=0.2902, simple_loss=0.3472, pruned_loss=0.1166, over 7208.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2879, pruned_loss=0.06224, over 1419664.30 frames.], batch size: 21, lr: 4.55e-04
2022-05-27 11:49:12,204 INFO [train.py:842] (3/4) Epoch 12, batch 3000, loss[loss=0.2792, simple_loss=0.3476, pruned_loss=0.1054, over 7339.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2874, pruned_loss=0.06203, over 1421566.00 frames.], batch size: 25, lr: 4.55e-04
2022-05-27 11:49:12,206 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 11:49:21,566 INFO [train.py:871] (3/4) Epoch 12, validation: loss=0.172, simple_loss=0.2724, pruned_loss=0.03584, over 868885.00 frames.
2022-05-27 11:49:59,999 INFO [train.py:842] (3/4) Epoch 12, batch 3050, loss[loss=0.2119, simple_loss=0.2975, pruned_loss=0.06312, over 7378.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2871, pruned_loss=0.06176, over 1420179.89 frames.], batch size: 23, lr: 4.55e-04
2022-05-27 11:50:39,186 INFO [train.py:842] (3/4) Epoch 12, batch 3100, loss[loss=0.2134, simple_loss=0.293, pruned_loss=0.06689, over 7335.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2865, pruned_loss=0.06137, over 1422192.36 frames.], batch size: 20, lr: 4.54e-04
2022-05-27 11:51:17,936 INFO [train.py:842] (3/4) Epoch 12, batch 3150, loss[loss=0.2172, simple_loss=0.2982, pruned_loss=0.06813, over 7374.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2865, pruned_loss=0.06123, over 1424574.36 frames.], batch size: 23, lr: 4.54e-04
2022-05-27 11:51:56,850 INFO [train.py:842] (3/4) Epoch 12, batch 3200, loss[loss=0.2103, simple_loss=0.2965, pruned_loss=0.062, over 7107.00 frames.], tot_loss[loss=0.205, simple_loss=0.2868, pruned_loss=0.06159, over 1424715.92 frames.], batch size: 21, lr: 4.54e-04
2022-05-27 11:52:35,718 INFO [train.py:842] (3/4) Epoch 12, batch 3250, loss[loss=0.1909, simple_loss=0.2706, pruned_loss=0.05559, over 7417.00 frames.], tot_loss[loss=0.204, simple_loss=0.2857, pruned_loss=0.0612, over 1425760.78 frames.], batch size: 21, lr: 4.54e-04
2022-05-27 11:53:14,316 INFO [train.py:842] (3/4) Epoch 12, batch 3300, loss[loss=0.1639, simple_loss=0.2493, pruned_loss=0.0392, over 6984.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2865, pruned_loss=0.06131, over 1426290.11 frames.], batch size: 16, lr: 4.54e-04
2022-05-27 11:53:52,893 INFO [train.py:842] (3/4) Epoch 12, batch 3350, loss[loss=0.1729, simple_loss=0.2513, pruned_loss=0.04729, over 7268.00 frames.], tot_loss[loss=0.2054, simple_loss=0.287, pruned_loss=0.06195, over 1426689.19 frames.], batch size: 18, lr: 4.54e-04
2022-05-27 11:54:31,808 INFO [train.py:842] (3/4) Epoch 12, batch 3400, loss[loss=0.2101, simple_loss=0.2921, pruned_loss=0.06406, over 6432.00 frames.], tot_loss[loss=0.2056, simple_loss=0.287, pruned_loss=0.06211, over 1420674.91 frames.], batch size: 38, lr: 4.54e-04
2022-05-27 11:55:10,442 INFO [train.py:842] (3/4) Epoch 12, batch 3450, loss[loss=0.2453, simple_loss=0.324, pruned_loss=0.08329, over 7114.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2866, pruned_loss=0.06197, over 1418726.07 frames.], batch size: 21, lr: 4.54e-04
2022-05-27 11:55:49,197 INFO [train.py:842] (3/4) Epoch 12, batch 3500, loss[loss=0.2085, simple_loss=0.2973, pruned_loss=0.05987, over 7326.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2872, pruned_loss=0.06217, over 1425287.29 frames.], batch size: 21, lr: 4.54e-04
2022-05-27 11:56:27,757 INFO [train.py:842] (3/4) Epoch 12, batch 3550, loss[loss=0.1866, simple_loss=0.2644, pruned_loss=0.05442, over 6993.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2862, pruned_loss=0.06139, over 1422986.92 frames.], batch size: 16, lr: 4.53e-04
2022-05-27 11:57:06,225 INFO [train.py:842] (3/4) Epoch 12, batch 3600, loss[loss=0.1803, simple_loss=0.2679, pruned_loss=0.04634, over 7231.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2869, pruned_loss=0.06123, over 1424740.28 frames.], batch size: 20, lr: 4.53e-04
2022-05-27 11:57:44,690 INFO [train.py:842] (3/4) Epoch 12, batch 3650, loss[loss=0.1675, simple_loss=0.2554, pruned_loss=0.0398, over 7427.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2867, pruned_loss=0.06082, over 1423549.93 frames.], batch size: 20, lr: 4.53e-04
2022-05-27 11:58:23,624 INFO [train.py:842] (3/4) Epoch 12, batch 3700, loss[loss=0.2283, simple_loss=0.3089, pruned_loss=0.07382, over 6803.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2874, pruned_loss=0.06137, over 1419983.90 frames.], batch size: 31, lr: 4.53e-04
2022-05-27 11:59:02,233 INFO [train.py:842] (3/4) Epoch 12, batch 3750, loss[loss=0.2454, simple_loss=0.3217, pruned_loss=0.08458, over 7381.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2863, pruned_loss=0.06099, over 1424488.88 frames.], batch size: 23, lr: 4.53e-04
2022-05-27 11:59:41,091 INFO [train.py:842] (3/4) Epoch 12, batch 3800, loss[loss=0.2046, simple_loss=0.2906, pruned_loss=0.05929, over 7183.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2863, pruned_loss=0.0612, over 1427164.42 frames.], batch size: 26, lr: 4.53e-04
2022-05-27 12:00:19,491 INFO [train.py:842] (3/4) Epoch 12, batch 3850, loss[loss=0.1812, simple_loss=0.2639, pruned_loss=0.04927, over 7066.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2853, pruned_loss=0.06006, over 1428076.46 frames.], batch size: 18, lr: 4.53e-04
2022-05-27 12:00:58,250 INFO [train.py:842] (3/4) Epoch 12, batch 3900, loss[loss=0.2332, simple_loss=0.3079, pruned_loss=0.07921, over 5224.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2853, pruned_loss=0.06016, over 1429653.53 frames.], batch size: 52, lr: 4.53e-04
2022-05-27 12:01:36,969 INFO [train.py:842] (3/4) Epoch 12, batch 3950, loss[loss=0.1946, simple_loss=0.2736, pruned_loss=0.05777, over 7265.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2859, pruned_loss=0.06112, over 1430616.61 frames.], batch size: 19, lr: 4.53e-04
2022-05-27 12:02:15,759 INFO [train.py:842] (3/4) Epoch 12, batch 4000, loss[loss=0.1763, simple_loss=0.2666, pruned_loss=0.04303, over 7364.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2863, pruned_loss=0.06142, over 1427705.79 frames.], batch size: 19, lr: 4.53e-04
2022-05-27 12:02:54,555 INFO [train.py:842] (3/4) Epoch 12, batch 4050, loss[loss=0.2769, simple_loss=0.3365, pruned_loss=0.1087, over 7420.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2873, pruned_loss=0.06247, over 1426715.21 frames.], batch size: 18, lr: 4.52e-04
2022-05-27 12:03:33,385 INFO [train.py:842] (3/4) Epoch 12, batch 4100, loss[loss=0.2004, simple_loss=0.2908, pruned_loss=0.05503, over 7122.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2872, pruned_loss=0.06258, over 1422333.09 frames.], batch size: 21, lr: 4.52e-04
2022-05-27 12:04:12,134 INFO [train.py:842] (3/4) Epoch 12, batch 4150, loss[loss=0.2356, simple_loss=0.3249, pruned_loss=0.07314, over 7212.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2865, pruned_loss=0.06146, over 1423641.89 frames.], batch size: 22, lr: 4.52e-04
2022-05-27 12:04:50,973 INFO [train.py:842] (3/4) Epoch 12, batch 4200, loss[loss=0.2022, simple_loss=0.2881, pruned_loss=0.05813, over 7152.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2864, pruned_loss=0.06129, over 1425297.20 frames.], batch size: 20, lr: 4.52e-04
2022-05-27 12:05:29,425 INFO [train.py:842] (3/4) Epoch 12, batch 4250, loss[loss=0.1969, simple_loss=0.287, pruned_loss=0.0534, over 6772.00 frames.], tot_loss[loss=0.205, simple_loss=0.287, pruned_loss=0.06153, over 1423400.78 frames.], batch size: 31, lr: 4.52e-04
2022-05-27 12:06:08,255 INFO [train.py:842] (3/4) Epoch 12, batch 4300, loss[loss=0.2058, simple_loss=0.2674, pruned_loss=0.07213, over 7275.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2857, pruned_loss=0.06064, over 1424252.14 frames.], batch size: 17, lr: 4.52e-04
2022-05-27 12:06:46,755 INFO [train.py:842] (3/4) Epoch 12, batch 4350, loss[loss=0.1881, simple_loss=0.2707, pruned_loss=0.05277, over 7168.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2876, pruned_loss=0.06162, over 1417603.30 frames.], batch size: 18, lr: 4.52e-04
2022-05-27 12:07:25,739 INFO [train.py:842] (3/4) Epoch 12, batch 4400, loss[loss=0.1729, simple_loss=0.2696, pruned_loss=0.0381, over 7111.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2884, pruned_loss=0.06198, over 1421347.26 frames.], batch size: 21, lr: 4.52e-04
2022-05-27 12:08:04,059 INFO [train.py:842] (3/4) Epoch 12, batch 4450, loss[loss=0.1645, simple_loss=0.2463, pruned_loss=0.04131, over 7256.00 frames.], tot_loss[loss=0.204, simple_loss=0.2864, pruned_loss=0.06076, over 1419771.91 frames.], batch size: 19, lr: 4.52e-04
2022-05-27 12:08:43,217 INFO [train.py:842] (3/4) Epoch 12, batch 4500, loss[loss=0.1574, simple_loss=0.2317, pruned_loss=0.04162, over 7413.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2852, pruned_loss=0.06031, over 1422574.45 frames.], batch size: 18, lr: 4.51e-04
2022-05-27 12:09:22,014 INFO [train.py:842] (3/4) Epoch 12, batch 4550, loss[loss=0.1819, simple_loss=0.275, pruned_loss=0.04442, over 7143.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2848, pruned_loss=0.06013, over 1423977.24 frames.], batch size: 20, lr: 4.51e-04
2022-05-27 12:10:00,757 INFO [train.py:842] (3/4) Epoch 12, batch 4600, loss[loss=0.215, simple_loss=0.2999, pruned_loss=0.06502, over 7106.00 frames.], tot_loss[loss=0.2027, simple_loss=0.285, pruned_loss=0.0602, over 1420701.10 frames.], batch size: 28, lr: 4.51e-04
2022-05-27 12:10:39,206 INFO [train.py:842] (3/4) Epoch 12, batch 4650, loss[loss=0.212, simple_loss=0.3047, pruned_loss=0.05967, over 7319.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2856, pruned_loss=0.06011, over 1423167.83 frames.], batch size: 21, lr: 4.51e-04
2022-05-27 12:11:18,050 INFO [train.py:842] (3/4) Epoch 12, batch 4700, loss[loss=0.2568, simple_loss=0.3209, pruned_loss=0.09636, over 4694.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2861, pruned_loss=0.06044, over 1419840.92 frames.], batch size: 53, lr: 4.51e-04
2022-05-27 12:11:56,432 INFO [train.py:842] (3/4) Epoch 12, batch 4750, loss[loss=0.1886, simple_loss=0.2693, pruned_loss=0.05392, over 7266.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2877, pruned_loss=0.06164, over 1421716.14 frames.], batch size: 19, lr: 4.51e-04
2022-05-27 12:12:35,446 INFO [train.py:842] (3/4) Epoch 12, batch 4800, loss[loss=0.179, simple_loss=0.2635, pruned_loss=0.04725, over 7361.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2873, pruned_loss=0.06145, over 1422607.84 frames.], batch size: 19, lr: 4.51e-04
2022-05-27 12:13:13,837 INFO [train.py:842] (3/4) Epoch 12, batch 4850, loss[loss=0.2426, simple_loss=0.3042, pruned_loss=0.09045, over 7166.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2878, pruned_loss=0.06189, over 1425152.28 frames.], batch size: 18, lr: 4.51e-04
2022-05-27 12:13:52,891 INFO [train.py:842] (3/4) Epoch 12, batch 4900, loss[loss=0.2189, simple_loss=0.29, pruned_loss=0.07394, over 7415.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2867, pruned_loss=0.06144, over 1425281.49 frames.], batch size: 18, lr: 4.51e-04
2022-05-27 12:14:31,303 INFO [train.py:842] (3/4) Epoch 12, batch 4950, loss[loss=0.2011, simple_loss=0.2858, pruned_loss=0.05822, over 7165.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2873, pruned_loss=0.06221, over 1422933.98 frames.], batch size: 26, lr: 4.50e-04
2022-05-27 12:15:10,326 INFO [train.py:842] (3/4) Epoch 12, batch 5000, loss[loss=0.1686, simple_loss=0.2493, pruned_loss=0.04393, over 7391.00 frames.], tot_loss[loss=0.205, simple_loss=0.2863, pruned_loss=0.06181, over 1417051.16 frames.], batch size: 18, lr: 4.50e-04
2022-05-27 12:15:48,942 INFO [train.py:842] (3/4) Epoch 12, batch 5050, loss[loss=0.1847, simple_loss=0.267, pruned_loss=0.05117, over 7069.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2847, pruned_loss=0.06091, over 1421850.41 frames.], batch size: 18, lr: 4.50e-04
2022-05-27 12:16:27,515 INFO [train.py:842] (3/4) Epoch 12, batch 5100, loss[loss=0.2232, simple_loss=0.3047, pruned_loss=0.07088, over 7200.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2852, pruned_loss=0.06105, over 1415862.48 frames.], batch size: 22, lr: 4.50e-04
2022-05-27 12:17:06,096 INFO [train.py:842] (3/4) Epoch 12, batch 5150, loss[loss=0.1762, simple_loss=0.2646, pruned_loss=0.04387, over 7206.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2847, pruned_loss=0.06074, over 1419969.96 frames.], batch size: 22, lr: 4.50e-04
2022-05-27 12:17:44,841 INFO [train.py:842] (3/4) Epoch 12, batch 5200, loss[loss=0.2297, simple_loss=0.3203, pruned_loss=0.06956, over 7238.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2844, pruned_loss=0.0605, over 1421157.39 frames.], batch size: 20, lr: 4.50e-04
2022-05-27 12:18:23,386 INFO [train.py:842] (3/4) Epoch 12, batch 5250, loss[loss=0.2237, simple_loss=0.3021, pruned_loss=0.07266, over 7294.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2848, pruned_loss=0.06068, over 1420144.31 frames.], batch size: 24, lr: 4.50e-04
2022-05-27 12:19:02,163 INFO [train.py:842] (3/4) Epoch 12, batch 5300, loss[loss=0.1721, simple_loss=0.2541, pruned_loss=0.04502, over 6731.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2841, pruned_loss=0.06038, over 1418741.88 frames.], batch size: 15, lr: 4.50e-04
2022-05-27 12:19:41,038 INFO [train.py:842] (3/4) Epoch 12, batch 5350, loss[loss=0.1815, simple_loss=0.2714, pruned_loss=0.04582, over 6449.00 frames.], tot_loss[loss=0.2037, simple_loss=0.285, pruned_loss=0.06116, over 1420015.09 frames.], batch size: 38, lr: 4.50e-04
2022-05-27 12:20:19,741 INFO [train.py:842] (3/4) Epoch 12, batch 5400, loss[loss=0.1882, simple_loss=0.2735, pruned_loss=0.05142, over 7213.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2854, pruned_loss=0.06067, over 1420378.44 frames.], batch size: 21, lr: 4.50e-04
2022-05-27 12:20:58,146 INFO [train.py:842] (3/4) Epoch 12, batch 5450, loss[loss=0.2458, simple_loss=0.3199, pruned_loss=0.0858, over 7328.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2852, pruned_loss=0.06057, over 1420120.60 frames.], batch size: 20, lr: 4.49e-04
2022-05-27 12:21:37,202 INFO [train.py:842] (3/4) Epoch 12, batch 5500, loss[loss=0.205, simple_loss=0.2717, pruned_loss=0.0692, over 7278.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2853, pruned_loss=0.06096, over 1418453.98 frames.], batch size: 18, lr: 4.49e-04
2022-05-27 12:22:15,897 INFO [train.py:842] (3/4) Epoch 12, batch 5550, loss[loss=0.2017, simple_loss=0.289, pruned_loss=0.05717, over 7323.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2839, pruned_loss=0.06034, over 1423981.94 frames.], batch size: 21, lr: 4.49e-04
2022-05-27 12:22:54,578 INFO [train.py:842] (3/4) Epoch 12, batch 5600, loss[loss=0.1897, simple_loss=0.2755, pruned_loss=0.05193, over 7145.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2844, pruned_loss=0.06098, over 1419956.27 frames.], batch size: 20, lr: 4.49e-04
2022-05-27 12:23:33,113 INFO [train.py:842] (3/4) Epoch 12, batch 5650, loss[loss=0.2204, simple_loss=0.3135, pruned_loss=0.06368, over 7199.00 frames.], tot_loss[loss=0.2037, simple_loss=0.285, pruned_loss=0.06124, over 1424306.35 frames.], batch size: 26, lr: 4.49e-04
2022-05-27 12:24:12,166 INFO [train.py:842] (3/4) Epoch 12, batch 5700, loss[loss=0.1941, simple_loss=0.2776, pruned_loss=0.05531, over 7354.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2846, pruned_loss=0.06092, over 1423366.47 frames.], batch size: 19, lr: 4.49e-04
2022-05-27 12:24:50,785 INFO [train.py:842] (3/4) Epoch 12, batch 5750, loss[loss=0.177, simple_loss=0.2671, pruned_loss=0.04344, over 7102.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2849, pruned_loss=0.06087, over 1426308.91 frames.], batch size: 21, lr: 4.49e-04
2022-05-27 12:25:29,900 INFO [train.py:842] (3/4) Epoch 12, batch 5800, loss[loss=0.1812, simple_loss=0.2751, pruned_loss=0.04362, over 7277.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2854, pruned_loss=0.06091, over 1424010.31 frames.], batch size: 25, lr: 4.49e-04
2022-05-27 12:26:08,565 INFO [train.py:842] (3/4) Epoch 12, batch 5850, loss[loss=0.2144, simple_loss=0.2826, pruned_loss=0.07309, over 6827.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2857, pruned_loss=0.06145, over 1422571.99 frames.], batch size: 15, lr: 4.49e-04
2022-05-27 12:26:47,345 INFO [train.py:842] (3/4) Epoch 12, batch 5900, loss[loss=0.3062, simple_loss=0.3802, pruned_loss=0.1161, over 6852.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2862, pruned_loss=0.06172, over 1426327.25 frames.], batch size: 31, lr: 4.48e-04
2022-05-27 12:27:25,900 INFO [train.py:842] (3/4) Epoch 12, batch 5950, loss[loss=0.1737, simple_loss=0.2607, pruned_loss=0.04337, over 7433.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2857, pruned_loss=0.06123, over 1429732.78 frames.], batch size: 20, lr: 4.48e-04
2022-05-27 12:28:04,963 INFO [train.py:842] (3/4) Epoch 12, batch 6000, loss[loss=0.2019, simple_loss=0.2936, pruned_loss=0.05506, over 7082.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2851, pruned_loss=0.06123, over 1427796.75 frames.], batch size: 28, lr: 4.48e-04
2022-05-27 12:28:04,964 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 12:28:14,266 INFO [train.py:871] (3/4) Epoch 12, validation: loss=0.1696, simple_loss=0.2704, pruned_loss=0.03442, over 868885.00 frames.
2022-05-27 12:28:52,735 INFO [train.py:842] (3/4) Epoch 12, batch 6050, loss[loss=0.1804, simple_loss=0.2604, pruned_loss=0.05022, over 6986.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2854, pruned_loss=0.06055, over 1428735.85 frames.], batch size: 16, lr: 4.48e-04
2022-05-27 12:29:32,058 INFO [train.py:842] (3/4) Epoch 12, batch 6100, loss[loss=0.1871, simple_loss=0.272, pruned_loss=0.05112, over 7155.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2838, pruned_loss=0.06, over 1431634.72 frames.], batch size: 19, lr: 4.48e-04
2022-05-27 12:30:10,610 INFO [train.py:842] (3/4) Epoch 12, batch 6150, loss[loss=0.2021, simple_loss=0.2882, pruned_loss=0.05798, over 7266.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2853, pruned_loss=0.06076, over 1430419.86 frames.], batch size: 19, lr: 4.48e-04
2022-05-27 12:30:49,472 INFO [train.py:842] (3/4) Epoch 12, batch 6200, loss[loss=0.1818, simple_loss=0.2707, pruned_loss=0.04647, over 7226.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2851, pruned_loss=0.06112, over 1428727.80 frames.], batch size: 20, lr: 4.48e-04
2022-05-27 12:31:27,917 INFO [train.py:842] (3/4) Epoch 12, batch 6250, loss[loss=0.1919, simple_loss=0.2733, pruned_loss=0.05521, over 7150.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2858, pruned_loss=0.06144, over 1425067.10 frames.], batch size: 18, lr: 4.48e-04
2022-05-27 12:32:06,961 INFO [train.py:842] (3/4) Epoch 12, batch 6300, loss[loss=0.2065, simple_loss=0.3038, pruned_loss=0.05464, over 6804.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2853, pruned_loss=0.06093, over 1426643.40 frames.], batch size: 31, lr: 4.48e-04
2022-05-27 12:32:45,636 INFO [train.py:842] (3/4) Epoch 12, batch 6350, loss[loss=0.2136, simple_loss=0.298, pruned_loss=0.06459, over 7148.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2873, pruned_loss=0.06157, over 1425464.09 frames.], batch size: 20, lr: 4.48e-04
2022-05-27 12:33:24,541 INFO [train.py:842] (3/4) Epoch 12, batch 6400, loss[loss=0.2017, simple_loss=0.2827, pruned_loss=0.06034, over 7150.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2867, pruned_loss=0.0615, over 1417302.56 frames.], batch size: 26, lr: 4.47e-04
2022-05-27 12:34:03,174 INFO [train.py:842] (3/4) Epoch 12, batch 6450, loss[loss=0.1787, simple_loss=0.2602, pruned_loss=0.04863, over 7156.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2855, pruned_loss=0.06134, over 1417616.31 frames.], batch size: 18, lr: 4.47e-04
2022-05-27 12:34:41,822 INFO [train.py:842] (3/4) Epoch 12, batch 6500, loss[loss=0.2412, simple_loss=0.3173, pruned_loss=0.08256, over 7221.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2859, pruned_loss=0.06113, over 1421699.10 frames.], batch size: 22, lr: 4.47e-04
2022-05-27 12:35:20,547 INFO [train.py:842] (3/4) Epoch 12, batch 6550, loss[loss=0.2057, simple_loss=0.2764, pruned_loss=0.06746, over 7160.00 frames.], tot_loss[loss=0.2044, simple_loss=0.286, pruned_loss=0.06143, over 1420733.94 frames.], batch size: 18, lr: 4.47e-04
2022-05-27 12:35:59,585 INFO [train.py:842] (3/4) Epoch 12, batch 6600, loss[loss=0.19, simple_loss=0.2768, pruned_loss=0.05155, over 7435.00 frames.], tot_loss[loss=0.204, simple_loss=0.2854, pruned_loss=0.06131, over 1420931.91 frames.], batch size: 20, lr: 4.47e-04
2022-05-27 12:36:38,274 INFO [train.py:842] (3/4) Epoch 12, batch 6650, loss[loss=0.1977, simple_loss=0.2775, pruned_loss=0.05899, over 7289.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2858, pruned_loss=0.06141, over 1422213.53 frames.], batch size: 17, lr: 4.47e-04
2022-05-27 12:37:17,224 INFO [train.py:842] (3/4) Epoch 12, batch 6700, loss[loss=0.2026, simple_loss=0.2905, pruned_loss=0.05739, over 7147.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2862, pruned_loss=0.06157, over 1420647.91 frames.], batch size: 20, lr: 4.47e-04
2022-05-27 12:37:56,145 INFO [train.py:842] (3/4) Epoch 12, batch 6750, loss[loss=0.1976, simple_loss=0.2903, pruned_loss=0.05248, over 7333.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2856, pruned_loss=0.06096, over 1422034.22 frames.], batch size: 22, lr: 4.47e-04
2022-05-27 12:38:35,130 INFO [train.py:842] (3/4) Epoch 12, batch 6800, loss[loss=0.218, simple_loss=0.2859, pruned_loss=0.07507, over 7165.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2853, pruned_loss=0.06093, over 1423342.47 frames.], batch size: 19, lr: 4.47e-04
2022-05-27 12:39:13,704 INFO [train.py:842] (3/4) Epoch 12, batch 6850, loss[loss=0.1934, simple_loss=0.2817, pruned_loss=0.05257, over 7232.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2851, pruned_loss=0.06038, over 1424376.23 frames.], batch size: 20, lr: 4.47e-04
2022-05-27 12:39:52,702 INFO [train.py:842] (3/4) Epoch 12, batch 6900, loss[loss=0.2146, simple_loss=0.3014, pruned_loss=0.06393, over 6648.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2857, pruned_loss=0.06142, over 1421948.68 frames.], batch size: 31, lr: 4.46e-04
2022-05-27 12:40:31,035 INFO [train.py:842] (3/4) Epoch 12, batch 6950, loss[loss=0.2189, simple_loss=0.2967, pruned_loss=0.07051, over 7113.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2875, pruned_loss=0.06217, over 1417369.83 frames.], batch size: 21, lr: 4.46e-04
2022-05-27 12:41:09,845 INFO [train.py:842] (3/4) Epoch 12, batch 7000, loss[loss=0.1756, simple_loss=0.2721, pruned_loss=0.03951, over 7185.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2881, pruned_loss=0.06276, over 1416045.70 frames.], batch size: 23, lr: 4.46e-04
2022-05-27 12:41:48,368 INFO [train.py:842] (3/4) Epoch 12, batch 7050, loss[loss=0.2309, simple_loss=0.3212, pruned_loss=0.07023, over 6487.00 frames.], tot_loss[loss=0.2063, simple_loss=0.288, pruned_loss=0.06233, over 1419471.00 frames.], batch size: 38, lr: 4.46e-04
2022-05-27 12:42:27,207 INFO [train.py:842] (3/4) Epoch 12, batch 7100, loss[loss=0.1807, simple_loss=0.2684, pruned_loss=0.04648, over 7143.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2872, pruned_loss=0.06212, over 1416891.92 frames.], batch size: 20, lr: 4.46e-04
2022-05-27 12:43:05,928 INFO [train.py:842] (3/4) Epoch 12, batch 7150, loss[loss=0.1852, simple_loss=0.278, pruned_loss=0.04624, over 7427.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2869, pruned_loss=0.06193, over 1420618.39 frames.], batch size: 20, lr: 4.46e-04
2022-05-27 12:43:44,465 INFO [train.py:842] (3/4) Epoch 12, batch 7200, loss[loss=0.2376, simple_loss=0.3197, pruned_loss=0.07777, over 7418.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2878, pruned_loss=0.06234, over 1423212.03 frames.], batch size: 21, lr: 4.46e-04
2022-05-27 12:44:23,124 INFO [train.py:842] (3/4) Epoch 12, batch 7250, loss[loss=0.2893, simple_loss=0.3507, pruned_loss=0.114, over 7117.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2871, pruned_loss=0.06165, over 1418453.20 frames.], batch size: 21, lr: 4.46e-04
2022-05-27 12:45:01,914 INFO [train.py:842] (3/4) Epoch 12, batch 7300, loss[loss=0.1533, simple_loss=0.236, pruned_loss=0.03533, over 6997.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2868, pruned_loss=0.06144, over 1421629.86 frames.], batch size: 16, lr: 4.46e-04
2022-05-27 12:45:40,539 INFO [train.py:842] (3/4) Epoch 12, batch 7350, loss[loss=0.1871, simple_loss=0.2617, pruned_loss=0.05627, over 7129.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2872, pruned_loss=0.06175, over 1422626.99 frames.], batch size: 17, lr: 4.45e-04
2022-05-27 12:46:19,315 INFO [train.py:842] (3/4) Epoch 12, batch 7400, loss[loss=0.1682, simple_loss=0.2459, pruned_loss=0.04528, over 7400.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2862, pruned_loss=0.06128, over 1423566.78 frames.], batch size: 18, lr: 4.45e-04
2022-05-27 12:46:57,760 INFO [train.py:842] (3/4) Epoch 12, batch 7450, loss[loss=0.1608, simple_loss=0.2538, pruned_loss=0.03391, over 7275.00 frames.], tot_loss[loss=0.204, simple_loss=0.2864, pruned_loss=0.06077, over 1425838.33 frames.], batch size: 18, lr: 4.45e-04
2022-05-27 12:47:36,480 INFO [train.py:842] (3/4) Epoch 12, batch 7500, loss[loss=0.2078, simple_loss=0.3069, pruned_loss=0.05431, over 6877.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2867, pruned_loss=0.06087, over 1426978.56 frames.], batch size: 31, lr: 4.45e-04
2022-05-27 12:48:15,143 INFO [train.py:842] (3/4) Epoch 12, batch 7550, loss[loss=0.1903, simple_loss=0.279, pruned_loss=0.05076, over 7151.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2853, pruned_loss=0.05975, over 1427513.15 frames.], batch size: 20, lr: 4.45e-04
2022-05-27 12:48:54,050 INFO [train.py:842] (3/4) Epoch 12, batch 7600, loss[loss=0.2611, simple_loss=0.3343, pruned_loss=0.09389, over 7322.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2851, pruned_loss=0.05926, over 1432807.31 frames.], batch size: 21, lr: 4.45e-04
2022-05-27 12:49:32,598 INFO [train.py:842] (3/4) Epoch 12, batch 7650, loss[loss=0.2518, simple_loss=0.318, pruned_loss=0.09283, over 7142.00 frames.], tot_loss[loss=0.205, simple_loss=0.2873, pruned_loss=0.06137, over 1424981.40 frames.], batch size: 20, lr: 4.45e-04
2022-05-27 12:50:11,564 INFO [train.py:842] (3/4) Epoch 12, batch 7700, loss[loss=0.169, simple_loss=0.2363, pruned_loss=0.05083, over 7295.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2877, pruned_loss=0.06166, over 1424872.88 frames.], batch size: 17, lr: 4.45e-04
2022-05-27 12:50:50,212 INFO [train.py:842] (3/4) Epoch 12, batch 7750, loss[loss=0.1635, simple_loss=0.2477, pruned_loss=0.0397, over 6799.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2877, pruned_loss=0.06205, over 1422517.57 frames.], batch size: 15, lr: 4.45e-04
2022-05-27 12:51:28,921 INFO [train.py:842] (3/4) Epoch 12, batch 7800, loss[loss=0.2003, simple_loss=0.2877, pruned_loss=0.05647, over 7322.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2878, pruned_loss=0.06199, over 1421322.63 frames.], batch size: 20, lr: 4.45e-04
2022-05-27 12:52:07,447 INFO [train.py:842] (3/4) Epoch 12, batch 7850, loss[loss=0.3226, simple_loss=0.3781, pruned_loss=0.1335, over 5011.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2884, pruned_loss=0.06252, over 1418721.56 frames.], batch size: 53, lr: 4.44e-04
2022-05-27 12:52:46,478 INFO [train.py:842] (3/4) Epoch 12, batch 7900, loss[loss=0.2213, simple_loss=0.3155, pruned_loss=0.06356, over 7195.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2868, pruned_loss=0.06177, over 1423274.97 frames.], batch size: 23, lr: 4.44e-04
2022-05-27 12:53:25,064 INFO [train.py:842] (3/4) Epoch 12, batch 7950, loss[loss=0.2131, simple_loss=0.2981, pruned_loss=0.06411, over 7272.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2883, pruned_loss=0.06261, over 1424394.87 frames.], batch size: 24, lr: 4.44e-04
2022-05-27 12:54:03,981 INFO [train.py:842] (3/4) Epoch 12, batch 8000, loss[loss=0.1789, simple_loss=0.2542, pruned_loss=0.05182, over 7149.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2871, pruned_loss=0.06184, over 1424228.91 frames.], batch size: 18, lr: 4.44e-04
2022-05-27 12:54:42,611 INFO [train.py:842] (3/4) Epoch 12, batch 8050, loss[loss=0.2406, simple_loss=0.321, pruned_loss=0.0801, over 7374.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2873, pruned_loss=0.06201, over 1428647.32 frames.], batch size: 23, lr: 4.44e-04
2022-05-27 12:55:21,326 INFO [train.py:842] (3/4) Epoch 12, batch 8100, loss[loss=0.2091, simple_loss=0.2848, pruned_loss=0.06669, over 7213.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2889, pruned_loss=0.06313, over 1429590.30 frames.], batch size: 21, lr: 4.44e-04
2022-05-27 12:55:59,858 INFO [train.py:842] (3/4) Epoch 12, batch 8150, loss[loss=0.2098, simple_loss=0.2926, pruned_loss=0.06352, over 7151.00 frames.], tot_loss[loss=0.207, simple_loss=0.2886, pruned_loss=0.06275, over 1425385.41 frames.], batch size: 20, lr: 4.44e-04
2022-05-27 12:56:49,257 INFO [train.py:842] (3/4) Epoch 12, batch 8200, loss[loss=0.1555, simple_loss=0.2496, pruned_loss=0.03071, over 7215.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2869, pruned_loss=0.0617, over 1426750.41 frames.], batch size: 21, lr: 4.44e-04
2022-05-27 12:57:27,637 INFO [train.py:842] (3/4) Epoch 12, batch 8250, loss[loss=0.2303, simple_loss=0.3222, pruned_loss=0.06919, over 7204.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2868, pruned_loss=0.06145, over 1425537.01 frames.], batch size: 26, lr: 4.44e-04
2022-05-27 12:58:06,340 INFO [train.py:842] (3/4) Epoch 12, batch 8300, loss[loss=0.2756, simple_loss=0.3463, pruned_loss=0.1025, over 7204.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2872, pruned_loss=0.06152, over 1424028.82 frames.], batch size: 22, lr: 4.44e-04
2022-05-27 12:58:44,898 INFO [train.py:842] (3/4) Epoch 12, batch 8350, loss[loss=0.2272, simple_loss=0.3083, pruned_loss=0.07307, over 5348.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2845, pruned_loss=0.05999, over 1428060.44 frames.], batch size: 52, lr: 4.43e-04
2022-05-27 12:59:23,806 INFO [train.py:842] (3/4) Epoch 12, batch 8400, loss[loss=0.2498, simple_loss=0.3191, pruned_loss=0.09028, over 7285.00 frames.], tot_loss[loss=0.203, simple_loss=0.2848, pruned_loss=0.06056, over 1428906.44 frames.], batch size: 24, lr: 4.43e-04
2022-05-27 13:00:02,259 INFO [train.py:842] (3/4) Epoch 12, batch 8450, loss[loss=0.2295, simple_loss=0.3077, pruned_loss=0.0757, over 6820.00 frames.], tot_loss[loss=0.2019, simple_loss=0.284, pruned_loss=0.0599, over 1428989.13 frames.], batch size: 31, lr: 4.43e-04
2022-05-27 13:00:41,061 INFO [train.py:842] (3/4) Epoch 12, batch 8500, loss[loss=0.1968, simple_loss=0.2741, pruned_loss=0.05979, over 7145.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2839, pruned_loss=0.0604, over 1428579.91 frames.], batch size: 19, lr: 4.43e-04
2022-05-27 13:01:19,607 INFO [train.py:842] (3/4) Epoch 12, batch 8550, loss[loss=0.1879, simple_loss=0.2673, pruned_loss=0.0542, over 7135.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2832, pruned_loss=0.06003, over 1426221.34 frames.], batch size: 17, lr: 4.43e-04
2022-05-27 13:01:58,557 INFO [train.py:842] (3/4) Epoch 12, batch 8600, loss[loss=0.2119, simple_loss=0.2765, pruned_loss=0.07365, over 7284.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2856, pruned_loss=0.06142, over 1424572.43 frames.], batch size: 18, lr: 4.43e-04
2022-05-27 13:02:36,976 INFO [train.py:842] (3/4) Epoch 12, batch 8650, loss[loss=0.196, simple_loss=0.2693, pruned_loss=0.06137, over 7108.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2863, pruned_loss=0.06172, over 1420789.86 frames.], batch size: 17, lr: 4.43e-04
2022-05-27 13:03:15,862 INFO [train.py:842] (3/4) Epoch 12, batch 8700, loss[loss=0.2217, simple_loss=0.3078, pruned_loss=0.06782, over 7044.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2858, pruned_loss=0.06139, over 1420832.04 frames.], batch size: 28, lr: 4.43e-04
2022-05-27 13:03:54,278 INFO [train.py:842] (3/4) Epoch 12, batch 8750, loss[loss=0.2227, simple_loss=0.2941, pruned_loss=0.07564, over 4880.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2848, pruned_loss=0.06078, over 1417654.97 frames.], batch size: 52, lr: 4.43e-04
2022-05-27 13:04:33,568 INFO [train.py:842] (3/4) Epoch 12, batch 8800, loss[loss=0.227, simple_loss=0.2977, pruned_loss=0.07817, over 7221.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2837, pruned_loss=0.06032, over 1414432.36 frames.], batch size: 26, lr: 4.43e-04
2022-05-27 13:05:12,103 INFO [train.py:842] (3/4) Epoch 12, batch 8850, loss[loss=0.1871, simple_loss=0.2689, pruned_loss=0.05263, over 7120.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2821, pruned_loss=0.05954, over 1412462.19 frames.], batch size: 21, lr: 4.42e-04
2022-05-27 13:05:50,826 INFO [train.py:842] (3/4) Epoch 12, batch 8900, loss[loss=0.2041, simple_loss=0.2959, pruned_loss=0.05612, over 7299.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2817, pruned_loss=0.05945, over 1408820.62 frames.], batch size: 24, lr: 4.42e-04
2022-05-27 13:06:29,101 INFO [train.py:842] (3/4) Epoch 12, batch 8950, loss[loss=0.1984, simple_loss=0.2898, pruned_loss=0.05354, over 6315.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2814, pruned_loss=0.06013, over 1394792.75 frames.], batch size: 37, lr: 4.42e-04
2022-05-27 13:07:07,599 INFO [train.py:842] (3/4) Epoch 12, batch 9000, loss[loss=0.2813, simple_loss=0.3325, pruned_loss=0.1151, over 5377.00 frames.], tot_loss[loss=0.202, simple_loss=0.2821, pruned_loss=0.06101, over 1386544.75 frames.], batch size: 52, lr: 4.42e-04
2022-05-27 13:07:07,600 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 13:07:16,708 INFO [train.py:871] (3/4) Epoch 12, validation: loss=0.1688, simple_loss=0.2696, pruned_loss=0.03404, over 868885.00 frames.
2022-05-27 13:07:54,048 INFO [train.py:842] (3/4) Epoch 12, batch 9050, loss[loss=0.174, simple_loss=0.2621, pruned_loss=0.04295, over 7456.00 frames.], tot_loss[loss=0.2033, simple_loss=0.283, pruned_loss=0.06175, over 1361882.34 frames.], batch size: 19, lr: 4.42e-04
2022-05-27 13:08:31,799 INFO [train.py:842] (3/4) Epoch 12, batch 9100, loss[loss=0.2029, simple_loss=0.2808, pruned_loss=0.06252, over 5051.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2855, pruned_loss=0.06416, over 1334038.83 frames.], batch size: 52, lr: 4.42e-04
2022-05-27 13:09:08,596 INFO [train.py:842] (3/4) Epoch 12, batch 9150, loss[loss=0.2354, simple_loss=0.3118, pruned_loss=0.07954, over 5286.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2897, pruned_loss=0.06768, over 1262091.26 frames.], batch size: 52, lr: 4.42e-04
2022-05-27 13:09:59,355 INFO [train.py:842] (3/4) Epoch 13, batch 0, loss[loss=0.203, simple_loss=0.2949, pruned_loss=0.05556, over 7150.00 frames.], tot_loss[loss=0.203, simple_loss=0.2949, pruned_loss=0.05556, over 7150.00 frames.], batch size: 20, lr: 4.27e-04
2022-05-27 13:10:37,604 INFO [train.py:842] (3/4) Epoch 13, batch 50, loss[loss=0.1906, simple_loss=0.2853, pruned_loss=0.048, over 7228.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2865, pruned_loss=0.06089, over 319043.84 frames.], batch size: 20, lr: 4.27e-04
2022-05-27 13:11:15,861 INFO [train.py:842] (3/4) Epoch 13, batch 100, loss[loss=0.213, simple_loss=0.3031, pruned_loss=0.06146, over 7208.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2862, pruned_loss=0.05902, over 565788.29 frames.], batch size: 23, lr: 4.27e-04
2022-05-27 13:11:53,602 INFO [train.py:842] (3/4) Epoch 13, batch 150, loss[loss=0.1898, simple_loss=0.2752, pruned_loss=0.05224, over 7157.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2853, pruned_loss=0.05855, over 754690.03 frames.], batch size: 20, lr: 4.27e-04
2022-05-27 13:12:31,964 INFO [train.py:842] (3/4) Epoch 13, batch 200, loss[loss=0.1712, simple_loss=0.2658, pruned_loss=0.0383, over 7149.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2852, pruned_loss=0.05961, over 901902.95 frames.], batch size: 20, lr: 4.27e-04
2022-05-27 13:13:10,002 INFO [train.py:842] (3/4) Epoch 13, batch 250, loss[loss=0.1641, simple_loss=0.2385, pruned_loss=0.04486, over 7222.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2864, pruned_loss=0.06057, over 1015531.56 frames.], batch size: 16, lr: 4.26e-04
2022-05-27 13:13:48,340 INFO [train.py:842] (3/4) Epoch 13, batch 300, loss[loss=0.1826, simple_loss=0.2593, pruned_loss=0.05292, over 7146.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2851, pruned_loss=0.0603, over 1103882.35 frames.], batch size: 20, lr: 4.26e-04
2022-05-27 13:14:26,164 INFO [train.py:842] (3/4) Epoch 13, batch 350, loss[loss=0.2289, simple_loss=0.3068, pruned_loss=0.07544, over 7115.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2854, pruned_loss=0.06038, over 1175724.69 frames.], batch size: 28, lr: 4.26e-04
2022-05-27 13:15:04,466 INFO [train.py:842] (3/4) Epoch 13, batch 400, loss[loss=0.1682, simple_loss=0.2554, pruned_loss=0.04052, over 7347.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2836, pruned_loss=0.05911, over 1233065.42 frames.], batch size: 19, lr: 4.26e-04
2022-05-27 13:15:42,487 INFO [train.py:842] (3/4) Epoch 13, batch 450, loss[loss=0.1943, simple_loss=0.283, pruned_loss=0.05284, over 7318.00 frames.], tot_loss[loss=0.2, simple_loss=0.2826, pruned_loss=0.05874, over 1277113.56 frames.], batch size: 21, lr: 4.26e-04
2022-05-27 13:16:21,025 INFO [train.py:842] (3/4) Epoch 13, batch 500, loss[loss=0.1836, simple_loss=0.2756, pruned_loss=0.04586, over 6592.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2808, pruned_loss=0.05775, over 1311227.73 frames.], batch size: 38, lr: 4.26e-04
2022-05-27 13:16:59,161 INFO [train.py:842] (3/4) Epoch 13, batch 550, loss[loss=0.2079, simple_loss=0.2824, pruned_loss=0.06674, over 7368.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2807, pruned_loss=0.05823, over 1333565.22 frames.], batch size: 23, lr: 4.26e-04
2022-05-27 13:17:37,518 INFO [train.py:842] (3/4) Epoch 13, batch 600, loss[loss=0.1873, simple_loss=0.2524, pruned_loss=0.06111, over 6795.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2805, pruned_loss=0.05855, over 1347095.45 frames.], batch size: 15, lr: 4.26e-04
2022-05-27 13:18:15,532 INFO [train.py:842] (3/4) Epoch 13, batch 650, loss[loss=0.1774, simple_loss=0.2508, pruned_loss=0.05197, over 7284.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2806, pruned_loss=0.05811, over 1366558.25 frames.], batch size: 18, lr: 4.26e-04
2022-05-27 13:19:03,256 INFO [train.py:842] (3/4) Epoch 13, batch 700, loss[loss=0.2174, simple_loss=0.2888, pruned_loss=0.07299, over 6845.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2821, pruned_loss=0.05874, over 1383255.08 frames.], batch size: 15, lr: 4.26e-04
2022-05-27 13:19:50,638 INFO [train.py:842] (3/4) Epoch 13, batch 750, loss[loss=0.2292, simple_loss=0.3121, pruned_loss=0.07318, over 7193.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2824, pruned_loss=0.05861, over 1395583.50 frames.], batch size: 23, lr: 4.25e-04
2022-05-27 13:20:38,511 INFO [train.py:842] (3/4) Epoch 13, batch 800, loss[loss=0.1997, simple_loss=0.2802, pruned_loss=0.05954, over 7216.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2822, pruned_loss=0.05833, over 1404726.26 frames.], batch size: 22, lr: 4.25e-04
2022-05-27 13:21:16,373 INFO [train.py:842] (3/4) Epoch 13, batch 850, loss[loss=0.2143, simple_loss=0.2908, pruned_loss=0.06892, over 7141.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2835, pruned_loss=0.05908, over 1410701.37 frames.], batch size: 17, lr: 4.25e-04
2022-05-27 13:21:54,761 INFO [train.py:842] (3/4) Epoch 13, batch 900, loss[loss=0.2087, simple_loss=0.2866, pruned_loss=0.06543, over 7319.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2823, pruned_loss=0.05849, over 1413361.05 frames.], batch size: 20, lr: 4.25e-04
2022-05-27 13:22:32,531 INFO [train.py:842] (3/4) Epoch 13, batch 950, loss[loss=0.1961, simple_loss=0.2909, pruned_loss=0.05064, over 7175.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2836, pruned_loss=0.05961, over 1413820.45 frames.], batch size: 26, lr: 4.25e-04
2022-05-27 13:23:10,787 INFO [train.py:842] (3/4) Epoch 13, batch 1000, loss[loss=0.2138, simple_loss=0.2942, pruned_loss=0.06671, over 6363.00 frames.], tot_loss[loss=0.2017, simple_loss=0.284, pruned_loss=0.05968, over 1413954.90 frames.], batch size: 38, lr: 4.25e-04
2022-05-27 13:23:48,824 INFO [train.py:842] (3/4) Epoch 13, batch 1050, loss[loss=0.1799, simple_loss=0.2656, pruned_loss=0.04707, over 7261.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2835, pruned_loss=0.05953, over 1415664.75 frames.], batch size: 19, lr: 4.25e-04
2022-05-27 13:24:27,312 INFO [train.py:842] (3/4) Epoch 13, batch 1100, loss[loss=0.2069, simple_loss=0.298, pruned_loss=0.05788, over 7366.00 frames.], tot_loss[loss=0.2014, simple_loss=0.284, pruned_loss=0.05937, over 1421871.29 frames.], batch size: 23, lr: 4.25e-04
2022-05-27 13:25:05,358 INFO [train.py:842] (3/4) Epoch 13, batch 1150, loss[loss=0.1901, simple_loss=0.2801, pruned_loss=0.05006, over 7349.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2842, pruned_loss=0.05934, over 1425266.84 frames.], batch size: 20, lr: 4.25e-04
2022-05-27 13:25:43,701 INFO [train.py:842] (3/4) Epoch 13, batch 1200, loss[loss=0.311, simple_loss=0.36, pruned_loss=0.131, over 5235.00 frames.], tot_loss[loss=0.201, simple_loss=0.2835, pruned_loss=0.05924, over 1422476.34 frames.], batch size: 53, lr: 4.25e-04
2022-05-27 13:26:21,651 INFO [train.py:842] (3/4) Epoch 13, batch 1250, loss[loss=0.1877, simple_loss=0.2676, pruned_loss=0.05386, over 7168.00 frames.], tot_loss[loss=0.201, simple_loss=0.2835, pruned_loss=0.05929, over 1420438.02 frames.], batch size: 19, lr: 4.25e-04
2022-05-27 13:27:00,090 INFO [train.py:842] (3/4) Epoch 13, batch 1300, loss[loss=0.1704, simple_loss=0.2569, pruned_loss=0.04191, over 7062.00 frames.], tot_loss[loss=0.1996, simple_loss=0.282, pruned_loss=0.05866, over 1420229.79 frames.], batch size: 18, lr: 4.24e-04
2022-05-27 13:27:37,830 INFO [train.py:842] (3/4) Epoch 13, batch 1350, loss[loss=0.2307, simple_loss=0.3058, pruned_loss=0.07786, over 5060.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2838, pruned_loss=0.05949, over 1417760.73 frames.], batch size: 56, lr: 4.24e-04
2022-05-27 13:28:15,974 INFO [train.py:842] (3/4) Epoch 13, batch 1400, loss[loss=0.1896, simple_loss=0.2891, pruned_loss=0.04503, over 7300.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2841, pruned_loss=0.05949, over 1416947.73 frames.], batch size: 25, lr: 4.24e-04
2022-05-27 13:28:53,719 INFO [train.py:842] (3/4) Epoch 13, batch 1450, loss[loss=0.2021, simple_loss=0.3001, pruned_loss=0.05207, over 7313.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2843, pruned_loss=0.0593, over 1415298.31 frames.], batch size: 21, lr: 4.24e-04
2022-05-27 13:29:31,935 INFO [train.py:842] (3/4) Epoch 13, batch 1500, loss[loss=0.1568, simple_loss=0.2465, pruned_loss=0.03349, over 7194.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2835, pruned_loss=0.05905, over 1418781.01 frames.], batch size: 23, lr: 4.24e-04
2022-05-27 13:30:10,032 INFO [train.py:842] (3/4) Epoch 13, batch 1550, loss[loss=0.1958, simple_loss=0.2787, pruned_loss=0.05641, over 7063.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2842, pruned_loss=0.05997, over 1421013.95 frames.], batch size: 28, lr: 4.24e-04
2022-05-27 13:30:48,262 INFO [train.py:842] (3/4) Epoch 13, batch 1600, loss[loss=0.182, simple_loss=0.2757, pruned_loss=0.04416, over 7294.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2845, pruned_loss=0.06001, over 1419526.78 frames.], batch size: 25, lr: 4.24e-04
2022-05-27 13:31:26,210 INFO [train.py:842] (3/4) Epoch 13, batch 1650, loss[loss=0.2034, simple_loss=0.2965, pruned_loss=0.05508, over 7291.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2843, pruned_loss=0.05976, over 1422301.62 frames.], batch size: 24, lr: 4.24e-04
2022-05-27 13:32:07,096 INFO [train.py:842] (3/4) Epoch 13, batch 1700, loss[loss=0.1876, simple_loss=0.2587, pruned_loss=0.05829, over 7145.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2831, pruned_loss=0.05921, over 1418947.16 frames.], batch size: 17, lr: 4.24e-04
2022-05-27 13:32:45,290 INFO [train.py:842] (3/4) Epoch 13, batch 1750, loss[loss=0.2017, simple_loss=0.285, pruned_loss=0.05917, over 7182.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2808, pruned_loss=0.05789, over 1421565.77 frames.], batch size: 26, lr: 4.24e-04
2022-05-27 13:33:23,703 INFO [train.py:842] (3/4) Epoch 13, batch 1800, loss[loss=0.163, simple_loss=0.2406, pruned_loss=0.04266, over 7439.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2803, pruned_loss=0.05728, over 1427430.48 frames.], batch size: 17, lr: 4.23e-04
2022-05-27 13:34:01,774 INFO [train.py:842] (3/4) Epoch 13, batch 1850, loss[loss=0.192, simple_loss=0.2904, pruned_loss=0.0468, over 7342.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2815, pruned_loss=0.05794, over 1428307.67 frames.], batch size: 22, lr: 4.23e-04
2022-05-27 13:34:40,135 INFO [train.py:842] (3/4) Epoch 13, batch 1900, loss[loss=0.1875, simple_loss=0.2812, pruned_loss=0.04688, over 7229.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2842, pruned_loss=0.0594, over 1428629.75 frames.], batch size: 20, lr: 4.23e-04
2022-05-27 13:35:17,979 INFO [train.py:842] (3/4) Epoch 13, batch 1950, loss[loss=0.2432, simple_loss=0.3061, pruned_loss=0.09022, over 7267.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2849, pruned_loss=0.06016, over 1428480.53 frames.], batch size: 17, lr: 4.23e-04
2022-05-27 13:35:56,460 INFO [train.py:842] (3/4) Epoch 13, batch 2000, loss[loss=0.1438, simple_loss=0.2234, pruned_loss=0.03215, over 7009.00 frames.], tot_loss[loss=0.202, simple_loss=0.2839, pruned_loss=0.06006, over 1427872.09 frames.], batch size: 16, lr: 4.23e-04
2022-05-27 13:36:34,506 INFO [train.py:842] (3/4) Epoch 13, batch 2050, loss[loss=0.1745, simple_loss=0.2632, pruned_loss=0.04287, over 7154.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2835, pruned_loss=0.06021, over 1421380.88 frames.], batch size: 19, lr: 4.23e-04
2022-05-27 13:37:12,815 INFO [train.py:842] (3/4) Epoch 13, batch 2100, loss[loss=0.187, simple_loss=0.2711, pruned_loss=0.05139, over 7158.00 frames.], tot_loss[loss=0.2026, simple_loss=0.284, pruned_loss=0.0606, over 1420863.66 frames.], batch size: 19, lr: 4.23e-04
2022-05-27 13:37:50,700 INFO [train.py:842] (3/4) Epoch 13, batch 2150, loss[loss=0.1741, simple_loss=0.2508, pruned_loss=0.04876, over 7266.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2834, pruned_loss=0.05957, over 1421830.12 frames.], batch size: 18, lr: 4.23e-04
2022-05-27 13:38:28,995 INFO [train.py:842] (3/4) Epoch 13, batch 2200, loss[loss=0.2122, simple_loss=0.2916, pruned_loss=0.06642, over 7323.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2825, pruned_loss=0.0591, over 1422616.70 frames.], batch size: 20, lr: 4.23e-04
2022-05-27 13:39:06,924 INFO [train.py:842] (3/4) Epoch 13, batch 2250, loss[loss=0.2323, simple_loss=0.324, pruned_loss=0.07037, over 7054.00 frames.], tot_loss[loss=0.201, simple_loss=0.2831, pruned_loss=0.05946, over 1421255.48 frames.], batch size: 28, lr: 4.23e-04
2022-05-27 13:39:45,196 INFO [train.py:842] (3/4) Epoch 13, batch 2300, loss[loss=0.1503, simple_loss=0.2466, pruned_loss=0.02695, over 7098.00 frames.], tot_loss[loss=0.2021, simple_loss=0.284, pruned_loss=0.06005, over 1424298.44 frames.], batch size: 21, lr: 4.23e-04
2022-05-27 13:40:23,245 INFO [train.py:842] (3/4) Epoch 13, batch 2350, loss[loss=0.2122, simple_loss=0.2906, pruned_loss=0.06687, over 7172.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2842, pruned_loss=0.05998, over 1425234.20 frames.], batch size: 19, lr: 4.22e-04
2022-05-27 13:41:01,583 INFO [train.py:842] (3/4) Epoch 13, batch 2400, loss[loss=0.1859, simple_loss=0.2682, pruned_loss=0.05182, over 7144.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2833, pruned_loss=0.05942, over 1426218.68 frames.], batch size: 17, lr: 4.22e-04
2022-05-27 13:41:39,480 INFO [train.py:842] (3/4) Epoch 13, batch 2450, loss[loss=0.2124, simple_loss=0.2875, pruned_loss=0.06867, over 7219.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2836, pruned_loss=0.05938, over 1425432.31 frames.], batch size: 21, lr: 4.22e-04
2022-05-27 13:42:17,603 INFO [train.py:842] (3/4) Epoch 13, batch 2500, loss[loss=0.1915, simple_loss=0.2684, pruned_loss=0.0573, over 7267.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2843, pruned_loss=0.05994, over 1426010.14 frames.], batch size: 18, lr: 4.22e-04
2022-05-27 13:42:55,547 INFO [train.py:842] (3/4) Epoch 13, batch 2550, loss[loss=0.1929, simple_loss=0.2475, pruned_loss=0.06909, over 6821.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2837, pruned_loss=0.05924, over 1427036.68 frames.], batch size: 15, lr: 4.22e-04
2022-05-27 13:43:33,886 INFO [train.py:842] (3/4) Epoch 13, batch 2600, loss[loss=0.1964, simple_loss=0.272, pruned_loss=0.06035, over 6820.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2833, pruned_loss=0.05953, over 1422915.53 frames.], batch size: 15, lr: 4.22e-04
2022-05-27 13:44:11,777 INFO [train.py:842] (3/4) Epoch 13, batch 2650, loss[loss=0.1855, simple_loss=0.2528, pruned_loss=0.0591, over 6986.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2835, pruned_loss=0.05941, over 1421569.96 frames.], batch size: 16, lr: 4.22e-04
2022-05-27 13:44:50,118 INFO [train.py:842] (3/4) Epoch 13, batch 2700, loss[loss=0.1805, simple_loss=0.2604, pruned_loss=0.05025, over 7010.00 frames.], tot_loss[loss=0.202, simple_loss=0.2836, pruned_loss=0.06015, over 1423687.86 frames.], batch size: 16, lr: 4.22e-04
2022-05-27 13:45:27,944 INFO [train.py:842] (3/4) Epoch 13, batch 2750, loss[loss=0.2226, simple_loss=0.307, pruned_loss=0.06915, over 7111.00 frames.], tot_loss[loss=0.202, simple_loss=0.2839, pruned_loss=0.06012, over 1420604.05 frames.], batch size: 21, lr: 4.22e-04
2022-05-27 13:46:05,894 INFO [train.py:842] (3/4) Epoch 13, batch 2800, loss[loss=0.1803, simple_loss=0.2533, pruned_loss=0.05369, over 7130.00 frames.], tot_loss[loss=0.2032, simple_loss=0.285, pruned_loss=0.06064, over 1420387.50 frames.], batch size: 17, lr: 4.22e-04
2022-05-27 13:46:44,101 INFO [train.py:842] (3/4) Epoch 13, batch 2850, loss[loss=0.1949, simple_loss=0.2835, pruned_loss=0.05318, over 7393.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2841, pruned_loss=0.0595, over 1426552.24 frames.], batch size: 23, lr: 4.22e-04
2022-05-27 13:47:22,070 INFO [train.py:842] (3/4) Epoch 13, batch 2900, loss[loss=0.1665, simple_loss=0.2528, pruned_loss=0.04009, over 7353.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2844, pruned_loss=0.05947, over 1424826.95 frames.], batch size: 19, lr: 4.21e-04
2022-05-27 13:48:00,134 INFO [train.py:842] (3/4) Epoch 13, batch 2950, loss[loss=0.2226, simple_loss=0.3013, pruned_loss=0.07196, over 7123.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2835, pruned_loss=0.05918, over 1426006.19 frames.], batch size: 21, lr: 4.21e-04
2022-05-27 13:48:38,462 INFO [train.py:842] (3/4) Epoch 13, batch 3000, loss[loss=0.1696, simple_loss=0.2501, pruned_loss=0.04454, over 7288.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2847, pruned_loss=0.06008, over 1427245.65 frames.], batch size: 17, lr: 4.21e-04
2022-05-27 13:48:38,463 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 13:48:47,488 INFO [train.py:871] (3/4) Epoch 13, validation: loss=0.1706, simple_loss=0.2707, pruned_loss=0.03524, over 868885.00 frames.
2022-05-27 13:49:25,654 INFO [train.py:842] (3/4) Epoch 13, batch 3050, loss[loss=0.1794, simple_loss=0.2482, pruned_loss=0.05533, over 7154.00 frames.], tot_loss[loss=0.2004, simple_loss=0.283, pruned_loss=0.05892, over 1427940.25 frames.], batch size: 17, lr: 4.21e-04
2022-05-27 13:50:04,005 INFO [train.py:842] (3/4) Epoch 13, batch 3100, loss[loss=0.187, simple_loss=0.2736, pruned_loss=0.05019, over 7111.00 frames.], tot_loss[loss=0.1998, simple_loss=0.282, pruned_loss=0.05878, over 1427172.11 frames.], batch size: 21, lr: 4.21e-04
2022-05-27 13:50:41,769 INFO [train.py:842] (3/4) Epoch 13, batch 3150, loss[loss=0.2096, simple_loss=0.2945, pruned_loss=0.06236, over 7281.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2838, pruned_loss=0.05957, over 1424825.53 frames.], batch size: 25, lr: 4.21e-04
2022-05-27 13:51:19,892 INFO [train.py:842] (3/4) Epoch 13, batch 3200, loss[loss=0.2274, simple_loss=0.3057, pruned_loss=0.07454, over 5440.00 frames.], tot_loss[loss=0.2018, simple_loss=0.284, pruned_loss=0.05976, over 1426442.02 frames.], batch size: 52, lr: 4.21e-04
2022-05-27 13:51:58,065 INFO [train.py:842] (3/4) Epoch 13, batch 3250, loss[loss=0.1701, simple_loss=0.2496, pruned_loss=0.04535, over 7288.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2836, pruned_loss=0.05936, over 1428450.32 frames.], batch size: 17, lr: 4.21e-04
2022-05-27 13:52:36,366 INFO [train.py:842] (3/4) Epoch 13, batch 3300, loss[loss=0.2431, simple_loss=0.3182, pruned_loss=0.08396, over 7323.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2844, pruned_loss=0.06006, over 1428391.50 frames.], batch size: 20, lr: 4.21e-04
2022-05-27 13:53:14,266 INFO [train.py:842] (3/4) Epoch 13, batch 3350, loss[loss=0.1647, simple_loss=0.2428, pruned_loss=0.04323, over 6987.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2855, pruned_loss=0.06041, over 1420932.89 frames.], batch size: 16, lr: 4.21e-04
2022-05-27 13:53:52,556 INFO [train.py:842] (3/4) Epoch 13, batch 3400, loss[loss=0.2334, simple_loss=0.3146, pruned_loss=0.07612, over 7377.00 frames.], tot_loss[loss=0.204, simple_loss=0.2864, pruned_loss=0.0608, over 1424031.51 frames.], batch size: 23, lr: 4.20e-04
2022-05-27 13:54:30,244 INFO [train.py:842] (3/4) Epoch 13, batch 3450, loss[loss=0.1953, simple_loss=0.2709, pruned_loss=0.05986, over 7403.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2872, pruned_loss=0.06123, over 1413421.86 frames.], batch size: 18, lr: 4.20e-04
2022-05-27 13:55:08,619 INFO [train.py:842] (3/4) Epoch 13, batch 3500, loss[loss=0.2164, simple_loss=0.3058, pruned_loss=0.06356, over 6683.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2868, pruned_loss=0.06091, over 1415514.21 frames.], batch size: 31, lr: 4.20e-04
2022-05-27 13:55:47,227 INFO [train.py:842] (3/4) Epoch 13, batch 3550, loss[loss=0.1613, simple_loss=0.2325, pruned_loss=0.04509, over 6990.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2868, pruned_loss=0.06111, over 1420430.98 frames.], batch size: 16, lr: 4.20e-04
2022-05-27 13:56:25,873 INFO [train.py:842] (3/4) Epoch 13, batch 3600, loss[loss=0.1994, simple_loss=0.2842, pruned_loss=0.05734, over 7276.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2857, pruned_loss=0.0603, over 1420538.31 frames.], batch size: 18, lr: 4.20e-04
2022-05-27 13:57:04,087 INFO [train.py:842] (3/4) Epoch 13, batch 3650, loss[loss=0.201, simple_loss=0.2922, pruned_loss=0.05491, over 7421.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2856, pruned_loss=0.05964, over 1423811.82 frames.], batch size: 21, lr: 4.20e-04
2022-05-27 13:57:43,032 INFO [train.py:842] (3/4) Epoch 13, batch 3700, loss[loss=0.1548, simple_loss=0.2437, pruned_loss=0.03297, over 7256.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2844, pruned_loss=0.05929, over 1424980.85 frames.], batch size: 19, lr: 4.20e-04
2022-05-27 13:58:21,608 INFO [train.py:842] (3/4) Epoch 13, batch 3750, loss[loss=0.1695, simple_loss=0.2625, pruned_loss=0.03827, over 7413.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2838, pruned_loss=0.05866, over 1425162.79 frames.], batch size: 21, lr: 4.20e-04
2022-05-27 13:59:00,734 INFO [train.py:842] (3/4) Epoch 13, batch 3800, loss[loss=0.196, simple_loss=0.2818, pruned_loss=0.05507, over 7010.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2837, pruned_loss=0.05867, over 1429218.58 frames.], batch size: 28, lr: 4.20e-04
2022-05-27 13:59:39,291 INFO [train.py:842] (3/4) Epoch 13, batch 3850, loss[loss=0.2021, simple_loss=0.2882, pruned_loss=0.05796, over 7197.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2841, pruned_loss=0.05865, over 1427251.85 frames.], batch size: 22, lr: 4.20e-04
2022-05-27 14:00:18,607 INFO [train.py:842] (3/4) Epoch 13, batch 3900, loss[loss=0.2379, simple_loss=0.3178, pruned_loss=0.07903, over 7014.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2829, pruned_loss=0.05823, over 1426616.42 frames.], batch size: 28, lr: 4.20e-04
2022-05-27 14:00:57,297 INFO [train.py:842] (3/4) Epoch 13, batch 3950, loss[loss=0.1767, simple_loss=0.2457, pruned_loss=0.05383, over 6783.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2845, pruned_loss=0.05906, over 1426226.51 frames.], batch size: 15, lr: 4.19e-04
2022-05-27 14:01:36,263 INFO [train.py:842] (3/4) Epoch 13, batch 4000, loss[loss=0.2167, simple_loss=0.3002, pruned_loss=0.06662, over 7118.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2843, pruned_loss=0.05947, over 1424130.95 frames.], batch size: 28, lr: 4.19e-04
2022-05-27 14:02:15,244 INFO [train.py:842] (3/4) Epoch 13, batch 4050, loss[loss=0.1897, simple_loss=0.2852, pruned_loss=0.04705, over 7199.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2843, pruned_loss=0.05956, over 1428934.94 frames.], batch size: 22, lr: 4.19e-04
2022-05-27 14:02:54,513 INFO [train.py:842] (3/4) Epoch 13, batch 4100, loss[loss=0.2131, simple_loss=0.2915, pruned_loss=0.06732, over 7161.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2833, pruned_loss=0.05922, over 1429516.79 frames.], batch size: 19, lr: 4.19e-04
2022-05-27 14:03:33,670 INFO [train.py:842] (3/4) Epoch 13, batch 4150, loss[loss=0.1481, simple_loss=0.2337, pruned_loss=0.03122, over 6989.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2834, pruned_loss=0.05924, over 1429361.01 frames.], batch size: 16, lr: 4.19e-04
2022-05-27 14:04:12,677 INFO [train.py:842] (3/4) Epoch 13, batch 4200, loss[loss=0.1975, simple_loss=0.2892, pruned_loss=0.0529, over 6276.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2844, pruned_loss=0.05996, over 1424200.44 frames.], batch size: 37, lr: 4.19e-04
2022-05-27 14:04:51,222 INFO [train.py:842] (3/4) Epoch 13, batch 4250, loss[loss=0.2273, simple_loss=0.3049, pruned_loss=0.07485, over 7422.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2837, pruned_loss=0.05899, over 1426729.85 frames.], batch size: 20, lr: 4.19e-04
2022-05-27 14:05:30,464 INFO [train.py:842] (3/4) Epoch 13, batch 4300, loss[loss=0.1719, simple_loss=0.252, pruned_loss=0.04593, over 6818.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2833, pruned_loss=0.05928, over 1423653.48 frames.], batch size: 15, lr: 4.19e-04
2022-05-27 14:06:09,114 INFO [train.py:842] (3/4) Epoch 13, batch 4350, loss[loss=0.2539, simple_loss=0.3266, pruned_loss=0.09056, over 4932.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2825, pruned_loss=0.05855, over 1424748.90 frames.], batch size: 52, lr: 4.19e-04
2022-05-27 14:06:48,128 INFO [train.py:842] (3/4) Epoch 13, batch 4400, loss[loss=0.1592, simple_loss=0.2397, pruned_loss=0.03935, over 7132.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2826, pruned_loss=0.05879, over 1424810.14 frames.], batch size: 17, lr: 4.19e-04
2022-05-27 14:07:27,261 INFO [train.py:842] (3/4) Epoch 13, batch 4450, loss[loss=0.2031, simple_loss=0.2689, pruned_loss=0.06869, over 7267.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2824, pruned_loss=0.05911, over 1429418.01 frames.], batch size: 17, lr: 4.19e-04
2022-05-27 14:08:06,635 INFO [train.py:842] (3/4) Epoch 13, batch 4500, loss[loss=0.2057, simple_loss=0.2864, pruned_loss=0.06255, over 7234.00 frames.], tot_loss[loss=0.201, simple_loss=0.283, pruned_loss=0.05943, over 1427986.28 frames.], batch size: 20, lr: 4.18e-04
2022-05-27 14:08:45,559 INFO [train.py:842] (3/4) Epoch 13, batch 4550, loss[loss=0.2158, simple_loss=0.2964, pruned_loss=0.06753, over 7037.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2827, pruned_loss=0.05921, over 1426992.63 frames.], batch size: 28, lr: 4.18e-04
2022-05-27 14:09:25,127 INFO [train.py:842] (3/4) Epoch 13, batch 4600, loss[loss=0.2255, simple_loss=0.3158, pruned_loss=0.06757, over 7151.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2823, pruned_loss=0.05866, over 1423993.01 frames.], batch size: 20, lr: 4.18e-04
2022-05-27 14:10:04,102 INFO [train.py:842] (3/4) Epoch 13, batch 4650, loss[loss=0.2632, simple_loss=0.329, pruned_loss=0.09869, over 7059.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2832, pruned_loss=0.05981, over 1420777.38 frames.], batch size: 18, lr: 4.18e-04
2022-05-27 14:10:43,284 INFO [train.py:842] (3/4) Epoch 13, batch 4700, loss[loss=0.2162, simple_loss=0.2995, pruned_loss=0.06645, over 6847.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2824, pruned_loss=0.05899, over 1425859.22 frames.], batch size: 32, lr: 4.18e-04
2022-05-27 14:11:22,099 INFO [train.py:842] (3/4) Epoch 13, batch 4750, loss[loss=0.2402, simple_loss=0.3204, pruned_loss=0.08004, over 7195.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2844, pruned_loss=0.05998, over 1424100.28 frames.], batch size: 22, lr: 4.18e-04
2022-05-27 14:12:01,227 INFO [train.py:842] (3/4) Epoch 13, batch 4800, loss[loss=0.2467, simple_loss=0.3176, pruned_loss=0.08792, over 7173.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2843, pruned_loss=0.06, over 1419076.28 frames.], batch size: 26, lr: 4.18e-04
2022-05-27 14:12:40,081 INFO [train.py:842] (3/4) Epoch 13, batch 4850, loss[loss=0.2331, simple_loss=0.323, pruned_loss=0.07156, over 7143.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2843, pruned_loss=0.06049, over 1413244.63 frames.], batch size: 20, lr: 4.18e-04
2022-05-27 14:13:19,446 INFO [train.py:842] (3/4) Epoch 13, batch 4900, loss[loss=0.1641, simple_loss=0.245, pruned_loss=0.04154, over 7282.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2837, pruned_loss=0.05984, over 1411098.31 frames.], batch size: 18, lr: 4.18e-04
2022-05-27 14:13:58,358 INFO [train.py:842] (3/4) Epoch 13, batch 4950, loss[loss=0.2109, simple_loss=0.2967, pruned_loss=0.0626, over 7232.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2836, pruned_loss=0.06003, over 1408433.20 frames.], batch size: 20, lr: 4.18e-04
2022-05-27 14:14:37,865 INFO [train.py:842] (3/4) Epoch 13, batch 5000, loss[loss=0.1887, simple_loss=0.2892, pruned_loss=0.04413, over 7188.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2841, pruned_loss=0.06018, over 1410379.68 frames.], batch size: 23, lr: 4.18e-04
2022-05-27 14:15:16,560 INFO [train.py:842] (3/4) Epoch 13, batch 5050, loss[loss=0.1612, simple_loss=0.2364, pruned_loss=0.043, over 7293.00 frames.], tot_loss[loss=0.201, simple_loss=0.283, pruned_loss=0.05949, over 1410830.43 frames.], batch size: 17, lr: 4.17e-04
2022-05-27 14:15:55,750 INFO [train.py:842] (3/4) Epoch 13, batch 5100, loss[loss=0.1732, simple_loss=0.2463, pruned_loss=0.0501, over 7258.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2834, pruned_loss=0.05958, over 1414292.41 frames.], batch size: 19, lr: 4.17e-04
2022-05-27 14:16:34,512 INFO [train.py:842] (3/4) Epoch 13, batch 5150, loss[loss=0.2156, simple_loss=0.3166, pruned_loss=0.05729, over 7308.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2855, pruned_loss=0.06008, over 1414788.95 frames.], batch size: 24, lr: 4.17e-04
2022-05-27 14:17:13,817 INFO [train.py:842] (3/4) Epoch 13, batch 5200, loss[loss=0.2044, simple_loss=0.2921, pruned_loss=0.05838, over 7092.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2844, pruned_loss=0.05943, over 1417337.01 frames.], batch size: 28, lr: 4.17e-04
2022-05-27 14:17:52,712 INFO [train.py:842] (3/4) Epoch 13, batch 5250, loss[loss=0.2047, simple_loss=0.2877, pruned_loss=0.0609, over 7199.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2852, pruned_loss=0.06033, over 1420102.26 frames.], batch size: 23, lr: 4.17e-04
2022-05-27 14:18:31,891 INFO [train.py:842] (3/4) Epoch 13, batch 5300, loss[loss=0.1921, simple_loss=0.2811, pruned_loss=0.05158, over 7236.00 frames.], tot_loss[loss=0.203, simple_loss=0.2852, pruned_loss=0.06037, over 1424650.81 frames.], batch size: 20, lr: 4.17e-04
2022-05-27 14:19:11,019 INFO [train.py:842] (3/4) Epoch 13, batch 5350, loss[loss=0.1318, simple_loss=0.2116, pruned_loss=0.02594, over 7144.00 frames.], tot_loss[loss=0.2004, simple_loss=0.283, pruned_loss=0.05887, over 1429458.65 frames.], batch size: 17, lr: 4.17e-04
2022-05-27 14:19:50,003 INFO [train.py:842] (3/4) Epoch 13, batch 5400, loss[loss=0.2219, simple_loss=0.2962, pruned_loss=0.07381, over 7126.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2826, pruned_loss=0.05904, over 1426988.84 frames.], batch size: 17, lr: 4.17e-04
2022-05-27 14:20:28,974 INFO [train.py:842] (3/4) Epoch 13, batch 5450, loss[loss=0.2243, simple_loss=0.2924, pruned_loss=0.07813, over 6807.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2834, pruned_loss=0.05993, over 1423450.16 frames.], batch size: 15, lr: 4.17e-04
2022-05-27 14:21:08,154 INFO [train.py:842] (3/4) Epoch 13, batch 5500, loss[loss=0.1575, simple_loss=0.2373, pruned_loss=0.03883, over 7252.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2824, pruned_loss=0.05909, over 1422708.29 frames.], batch size: 17, lr: 4.17e-04
2022-05-27 14:21:46,681 INFO [train.py:842] (3/4) Epoch 13, batch 5550, loss[loss=0.2207, simple_loss=0.2906, pruned_loss=0.07539, over 7372.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2829, pruned_loss=0.05891, over 1424991.57 frames.], batch size: 19, lr: 4.17e-04
2022-05-27 14:22:26,143 INFO [train.py:842] (3/4) Epoch 13, batch 5600, loss[loss=0.2202, simple_loss=0.2975, pruned_loss=0.07146, over 7316.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2824, pruned_loss=0.05861, over 1424486.21 frames.], batch size: 20, lr: 4.16e-04
2022-05-27 14:23:05,065 INFO [train.py:842] (3/4) Epoch 13, batch 5650, loss[loss=0.1919, simple_loss=0.2802, pruned_loss=0.05181, over 7336.00 frames.], tot_loss[loss=0.201, simple_loss=0.2833, pruned_loss=0.05933, over 1424039.19 frames.], batch size: 20, lr: 4.16e-04
2022-05-27 14:23:43,984 INFO [train.py:842] (3/4) Epoch 13, batch 5700, loss[loss=0.1815, simple_loss=0.2707, pruned_loss=0.04608, over 7355.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2835, pruned_loss=0.05891, over 1420639.87 frames.], batch size: 19, lr: 4.16e-04
2022-05-27 14:24:22,952 INFO [train.py:842] (3/4) Epoch 13, batch 5750, loss[loss=0.1822, simple_loss=0.2817, pruned_loss=0.04133, over 7218.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2842, pruned_loss=0.0596, over 1423588.56 frames.], batch size: 21, lr: 4.16e-04
2022-05-27 14:25:02,246 INFO [train.py:842] (3/4) Epoch 13, batch 5800, loss[loss=0.1782, simple_loss=0.2703, pruned_loss=0.04303, over 7231.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2843, pruned_loss=0.05972, over 1421878.38 frames.], batch size: 20, lr: 4.16e-04
2022-05-27 14:25:41,209 INFO [train.py:842] (3/4) Epoch 13, batch 5850, loss[loss=0.1749, simple_loss=0.2602, pruned_loss=0.04487, over 7361.00 frames.], tot_loss[loss=0.2001, simple_loss=0.283, pruned_loss=0.05859, over 1425207.50 frames.], batch size: 19, lr: 4.16e-04
2022-05-27 14:26:20,591 INFO [train.py:842] (3/4) Epoch 13, batch 5900, loss[loss=0.2643, simple_loss=0.3365, pruned_loss=0.09603, over 7148.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2826, pruned_loss=0.0586, over 1425846.31 frames.], batch size: 20, lr: 4.16e-04
2022-05-27 14:26:59,220 INFO [train.py:842] (3/4) Epoch 13, batch 5950, loss[loss=0.2066, simple_loss=0.2823, pruned_loss=0.06542, over 7198.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2838, pruned_loss=0.05952, over 1425625.66 frames.], batch size: 23, lr: 4.16e-04
2022-05-27 14:27:38,228 INFO [train.py:842] (3/4) Epoch 13, batch 6000, loss[loss=0.1692, simple_loss=0.2444, pruned_loss=0.04701, over 7359.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2827, pruned_loss=0.05889, over 1423407.40 frames.], batch size: 19, lr: 4.16e-04
2022-05-27 14:27:38,228 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 14:27:48,003 INFO [train.py:871] (3/4) Epoch 13, validation: loss=0.1712, simple_loss=0.2713, pruned_loss=0.03553, over 868885.00 frames.
2022-05-27 14:28:27,131 INFO [train.py:842] (3/4) Epoch 13, batch 6050, loss[loss=0.1773, simple_loss=0.263, pruned_loss=0.0458, over 7067.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2821, pruned_loss=0.0583, over 1421398.94 frames.], batch size: 18, lr: 4.16e-04
2022-05-27 14:29:06,296 INFO [train.py:842] (3/4) Epoch 13, batch 6100, loss[loss=0.2036, simple_loss=0.2905, pruned_loss=0.05834, over 7129.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2815, pruned_loss=0.05791, over 1425386.99 frames.], batch size: 21, lr: 4.16e-04
2022-05-27 14:29:45,167 INFO [train.py:842] (3/4) Epoch 13, batch 6150, loss[loss=0.1867, simple_loss=0.2748, pruned_loss=0.04932, over 7237.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2817, pruned_loss=0.0583, over 1422168.61 frames.], batch size: 20, lr: 4.16e-04
2022-05-27 14:30:23,988 INFO [train.py:842] (3/4) Epoch 13, batch 6200, loss[loss=0.1921, simple_loss=0.2864, pruned_loss=0.04894, over 7215.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2829, pruned_loss=0.05851, over 1425419.01 frames.], batch size: 23, lr: 4.15e-04
2022-05-27 14:31:03,022 INFO [train.py:842] (3/4) Epoch 13, batch 6250, loss[loss=0.1889, simple_loss=0.2678, pruned_loss=0.055, over 6777.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2818, pruned_loss=0.05762, over 1424435.82 frames.], batch size: 15, lr: 4.15e-04
2022-05-27 14:31:41,864 INFO [train.py:842] (3/4) Epoch 13, batch 6300, loss[loss=0.194, simple_loss=0.2792, pruned_loss=0.05437, over 6355.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2822, pruned_loss=0.05774, over 1422615.06 frames.], batch size: 38, lr: 4.15e-04
2022-05-27 14:32:20,565 INFO [train.py:842] (3/4) Epoch 13, batch 6350, loss[loss=0.2438, simple_loss=0.3166, pruned_loss=0.08549, over 5149.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2821, pruned_loss=0.05772, over 1419335.47 frames.], batch size: 52, lr: 4.15e-04
2022-05-27 14:32:59,601 INFO [train.py:842] (3/4) Epoch 13, batch 6400, loss[loss=0.1538, simple_loss=0.2486, pruned_loss=0.02954, over 7056.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2823, pruned_loss=0.05808, over 1418335.63 frames.], batch size: 18, lr: 4.15e-04
2022-05-27 14:33:38,358 INFO [train.py:842] (3/4) Epoch 13, batch 6450, loss[loss=0.2632, simple_loss=0.3357, pruned_loss=0.09533, over 7170.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2826, pruned_loss=0.05827, over 1419458.76 frames.], batch size: 26, lr: 4.15e-04
2022-05-27 14:34:17,578 INFO [train.py:842] (3/4) Epoch 13, batch 6500, loss[loss=0.1719, simple_loss=0.2649, pruned_loss=0.03948, over 7133.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2836, pruned_loss=0.05952, over 1417787.70 frames.], batch size: 17, lr: 4.15e-04
2022-05-27 14:34:56,671 INFO [train.py:842] (3/4) Epoch 13, batch 6550, loss[loss=0.1692, simple_loss=0.2586, pruned_loss=0.03983, over 7264.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2818, pruned_loss=0.0585, over 1419901.07 frames.], batch size: 18, lr: 4.15e-04
2022-05-27 14:35:36,250 INFO [train.py:842] (3/4) Epoch 13, batch 6600, loss[loss=0.1911, simple_loss=0.2786, pruned_loss=0.05178, over 7142.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2816, pruned_loss=0.05812, over 1421818.48 frames.], batch size: 26, lr: 4.15e-04
2022-05-27 14:36:15,583 INFO [train.py:842] (3/4) Epoch 13, batch 6650, loss[loss=0.26, simple_loss=0.33, pruned_loss=0.09501, over 7080.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2822, pruned_loss=0.05863, over 1424679.96 frames.], batch size: 28, lr: 4.15e-04
2022-05-27 14:36:54,860 INFO [train.py:842] (3/4) Epoch 13, batch 6700, loss[loss=0.2162, simple_loss=0.3024, pruned_loss=0.06499, over 7239.00 frames.], tot_loss[loss=0.201, simple_loss=0.2834, pruned_loss=0.05933, over 1422335.33 frames.], batch size: 20, lr: 4.15e-04
2022-05-27 14:37:33,699 INFO [train.py:842] (3/4) Epoch 13, batch 6750, loss[loss=0.1987, simple_loss=0.2905, pruned_loss=0.0534, over 7420.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2816, pruned_loss=0.05852, over 1423132.55 frames.], batch size: 21, lr: 4.14e-04
2022-05-27 14:38:12,760 INFO [train.py:842] (3/4) Epoch 13, batch 6800, loss[loss=0.1848, simple_loss=0.2686, pruned_loss=0.05055, over 7408.00 frames.], tot_loss[loss=0.199, simple_loss=0.2818, pruned_loss=0.05814, over 1424741.69 frames.], batch size: 18, lr: 4.14e-04
2022-05-27 14:38:51,497 INFO [train.py:842] (3/4) Epoch 13, batch 6850, loss[loss=0.2119, simple_loss=0.3014, pruned_loss=0.06126, over 7396.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2806, pruned_loss=0.05743, over 1422361.26 frames.], batch size: 23, lr: 4.14e-04
2022-05-27 14:39:30,668 INFO [train.py:842] (3/4) Epoch 13, batch 6900, loss[loss=0.1915, simple_loss=0.2839, pruned_loss=0.04949, over 7424.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2806, pruned_loss=0.05712, over 1421988.64 frames.], batch size: 20, lr: 4.14e-04
2022-05-27 14:40:09,785 INFO [train.py:842] (3/4) Epoch 13, batch 6950, loss[loss=0.2265, simple_loss=0.3137, pruned_loss=0.06962, over 7151.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2811, pruned_loss=0.05739, over 1422665.67 frames.], batch size: 20, lr: 4.14e-04
2022-05-27 14:40:48,919 INFO [train.py:842] (3/4) Epoch 13, batch 7000, loss[loss=0.1643, simple_loss=0.2435, pruned_loss=0.04261, over 7373.00 frames.], tot_loss[loss=0.2002, simple_loss=0.283, pruned_loss=0.05867, over 1421163.14 frames.], batch size: 19, lr: 4.14e-04
2022-05-27 14:41:27,979 INFO [train.py:842] (3/4) Epoch 13, batch 7050, loss[loss=0.2138, simple_loss=0.2901, pruned_loss=0.06876, over 7165.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2845, pruned_loss=0.05967, over 1424292.82 frames.], batch size: 18, lr: 4.14e-04
2022-05-27 14:42:07,613 INFO [train.py:842] (3/4) Epoch 13, batch 7100, loss[loss=0.2489, simple_loss=0.3222, pruned_loss=0.08784, over 7343.00 frames.], tot_loss[loss=0.2014, simple_loss=0.284, pruned_loss=0.05944, over 1425774.14 frames.], batch size: 22, lr: 4.14e-04
2022-05-27 14:42:46,584 INFO [train.py:842] (3/4) Epoch 13, batch 7150, loss[loss=0.2273, simple_loss=0.3027, pruned_loss=0.07594, over 7187.00 frames.], tot_loss[loss=0.201, simple_loss=0.2834, pruned_loss=0.05927, over 1424672.58 frames.], batch size: 22, lr: 4.14e-04
2022-05-27 14:43:25,711 INFO [train.py:842] (3/4) Epoch 13, batch 7200, loss[loss=0.1989, simple_loss=0.2778, pruned_loss=0.05998, over 7148.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2841, pruned_loss=0.05976, over 1423654.75 frames.], batch size: 17, lr: 4.14e-04
2022-05-27 14:44:04,770 INFO [train.py:842] (3/4) Epoch 13, batch 7250, loss[loss=0.1923, simple_loss=0.2748, pruned_loss=0.05486, over 6471.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2846, pruned_loss=0.06026, over 1418341.30 frames.], batch size: 38, lr: 4.14e-04
2022-05-27 14:44:43,668 INFO [train.py:842] (3/4) Epoch 13, batch 7300, loss[loss=0.1648, simple_loss=0.2536, pruned_loss=0.03803, over 7457.00 frames.], tot_loss[loss=0.203, simple_loss=0.2853, pruned_loss=0.06032, over 1421787.07 frames.], batch size: 19, lr: 4.13e-04
2022-05-27 14:45:22,118 INFO [train.py:842] (3/4) Epoch 13, batch 7350, loss[loss=0.1904, simple_loss=0.279, pruned_loss=0.05086, over 7245.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2846, pruned_loss=0.05944, over 1421380.27 frames.], batch size: 20, lr: 4.13e-04
2022-05-27 14:46:01,437 INFO [train.py:842] (3/4) Epoch 13, batch 7400, loss[loss=0.2166, simple_loss=0.3054, pruned_loss=0.06386, over 7121.00 frames.], tot_loss[loss=0.202, simple_loss=0.2851, pruned_loss=0.05944, over 1418524.67 frames.], batch size: 21, lr: 4.13e-04
2022-05-27 14:46:40,466 INFO [train.py:842] (3/4) Epoch 13, batch 7450, loss[loss=0.1888, simple_loss=0.2818, pruned_loss=0.04792, over 6816.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2847, pruned_loss=0.05927, over 1422230.28 frames.], batch size: 31, lr: 4.13e-04
2022-05-27 14:47:19,657 INFO [train.py:842] (3/4) Epoch 13, batch 7500, loss[loss=0.1762, simple_loss=0.2743, pruned_loss=0.03909, over 7079.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2845, pruned_loss=0.05956, over 1420677.87 frames.], batch size: 28, lr: 4.13e-04
2022-05-27 14:47:58,786 INFO [train.py:842] (3/4) Epoch 13, batch 7550, loss[loss=0.1707, simple_loss=0.2532, pruned_loss=0.04405, over 7428.00 frames.], tot_loss[loss=0.201, simple_loss=0.2834, pruned_loss=0.05934, over 1422992.12 frames.], batch size: 20, lr: 4.13e-04
2022-05-27 14:48:37,998 INFO [train.py:842] (3/4) Epoch 13, batch 7600, loss[loss=0.2019, simple_loss=0.2893, pruned_loss=0.05726, over 7330.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2832, pruned_loss=0.05959, over 1421202.39 frames.], batch size: 20, lr: 4.13e-04
2022-05-27 14:49:16,790 INFO [train.py:842] (3/4) Epoch 13, batch 7650, loss[loss=0.186, simple_loss=0.2724, pruned_loss=0.04982, over 7062.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2841, pruned_loss=0.06002, over 1421919.40 frames.], batch size: 18, lr: 4.13e-04
2022-05-27 14:49:56,157 INFO [train.py:842] (3/4) Epoch 13, batch 7700, loss[loss=0.2052, simple_loss=0.2921, pruned_loss=0.05912, over 7207.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2838, pruned_loss=0.05987, over 1424552.11 frames.], batch size: 22, lr: 4.13e-04
2022-05-27 14:50:35,218 INFO [train.py:842] (3/4) Epoch 13, batch 7750, loss[loss=0.1846, simple_loss=0.2767, pruned_loss=0.04627, over 7417.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2839, pruned_loss=0.05918, over 1418767.66 frames.], batch size: 21, lr: 4.13e-04
2022-05-27 14:51:14,289 INFO [train.py:842] (3/4) Epoch 13, batch 7800, loss[loss=0.2162, simple_loss=0.3014, pruned_loss=0.06545, over 7117.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2824, pruned_loss=0.05886, over 1421179.42 frames.], batch size: 28, lr: 4.13e-04
2022-05-27 14:51:53,604 INFO [train.py:842] (3/4) Epoch 13, batch 7850, loss[loss=0.2837, simple_loss=0.3585, pruned_loss=0.1045, over 6567.00 frames.], tot_loss[loss=0.199, simple_loss=0.282, pruned_loss=0.05797, over 1426226.84 frames.], batch size: 37, lr: 4.13e-04
2022-05-27 14:52:33,072 INFO [train.py:842] (3/4) Epoch 13, batch 7900, loss[loss=0.1934, simple_loss=0.2688, pruned_loss=0.059, over 7396.00 frames.], tot_loss[loss=0.2, simple_loss=0.2824, pruned_loss=0.05876, over 1425744.72 frames.], batch size: 18, lr: 4.12e-04
2022-05-27 14:53:11,961 INFO [train.py:842] (3/4) Epoch 13, batch 7950, loss[loss=0.1889, simple_loss=0.2742, pruned_loss=0.05178, over 7105.00 frames.], tot_loss[loss=0.1982, simple_loss=0.281, pruned_loss=0.0577, over 1425169.05 frames.], batch size: 21, lr: 4.12e-04
2022-05-27 14:53:51,102 INFO [train.py:842] (3/4) Epoch 13, batch 8000, loss[loss=0.2655, simple_loss=0.3224, pruned_loss=0.1043, over 6776.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2821, pruned_loss=0.05837, over 1426886.55 frames.], batch size: 15, lr: 4.12e-04
2022-05-27 14:54:29,907 INFO [train.py:842] (3/4) Epoch 13, batch 8050, loss[loss=0.2023, simple_loss=0.2749, pruned_loss=0.0649, over 7289.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2816, pruned_loss=0.05809, over 1425688.71 frames.], batch size: 18, lr: 4.12e-04
2022-05-27 14:55:09,284 INFO [train.py:842] (3/4) Epoch 13, batch 8100, loss[loss=0.2306, simple_loss=0.3, pruned_loss=0.08054, over 7155.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2818, pruned_loss=0.05862, over 1424038.50 frames.], batch size: 19, lr: 4.12e-04
2022-05-27 14:55:48,012 INFO [train.py:842] (3/4) Epoch 13, batch 8150, loss[loss=0.204, simple_loss=0.2932, pruned_loss=0.05737, over 7296.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2828, pruned_loss=0.05879, over 1426087.91 frames.], batch size: 25, lr: 4.12e-04
2022-05-27 14:56:27,297 INFO [train.py:842] (3/4) Epoch 13, batch 8200, loss[loss=0.2779, simple_loss=0.3454, pruned_loss=0.1052, over 7198.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2825, pruned_loss=0.05918, over 1428068.22 frames.], batch size: 22, lr: 4.12e-04
2022-05-27 14:57:06,468 INFO [train.py:842] (3/4) Epoch 13, batch 8250, loss[loss=0.1963, simple_loss=0.2799, pruned_loss=0.05641, over 7063.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2836, pruned_loss=0.05976, over 1431778.87 frames.], batch size: 18, lr: 4.12e-04
2022-05-27 14:57:45,605 INFO [train.py:842] (3/4) Epoch 13, batch 8300, loss[loss=0.1986, simple_loss=0.2788, pruned_loss=0.05916, over 6786.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2838, pruned_loss=0.06016, over 1434299.30 frames.], batch size: 31, lr: 4.12e-04
2022-05-27 14:58:24,379 INFO [train.py:842] (3/4) Epoch 13, batch 8350, loss[loss=0.1677, simple_loss=0.2538, pruned_loss=0.04084, over 7280.00 frames.], tot_loss[loss=0.2008, simple_loss=0.283, pruned_loss=0.0593, over 1434248.39 frames.], batch size: 17, lr: 4.12e-04
2022-05-27 14:59:03,770 INFO [train.py:842] (3/4) Epoch 13, batch 8400, loss[loss=0.2046, simple_loss=0.2896, pruned_loss=0.0598, over 7176.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2827, pruned_loss=0.059, over 1435092.56 frames.], batch size: 18, lr: 4.12e-04
2022-05-27 14:59:42,402 INFO [train.py:842] (3/4) Epoch 13, batch 8450, loss[loss=0.2176, simple_loss=0.3, pruned_loss=0.0676, over 7137.00 frames.], tot_loss[loss=0.2, simple_loss=0.2822, pruned_loss=0.05891, over 1427717.07 frames.], batch size: 26, lr: 4.11e-04
2022-05-27 15:00:21,279 INFO [train.py:842] (3/4) Epoch 13, batch 8500, loss[loss=0.1922, simple_loss=0.2681, pruned_loss=0.05811, over 7285.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2818, pruned_loss=0.05834, over 1426887.90 frames.], batch size: 17, lr: 4.11e-04
2022-05-27 15:00:59,993 INFO [train.py:842] (3/4) Epoch 13, batch 8550, loss[loss=0.1929, simple_loss=0.2784, pruned_loss=0.0537, over 7153.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2808, pruned_loss=0.05766, over 1423595.74 frames.], batch size: 26, lr: 4.11e-04
2022-05-27 15:01:38,579 INFO [train.py:842] (3/4) Epoch 13, batch 8600, loss[loss=0.2004, simple_loss=0.2794, pruned_loss=0.06071, over 6308.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2808, pruned_loss=0.05705, over 1425630.02 frames.], batch size: 37, lr: 4.11e-04
2022-05-27 15:02:17,373 INFO [train.py:842] (3/4) Epoch 13, batch 8650, loss[loss=0.2116, simple_loss=0.2899, pruned_loss=0.06667, over 7417.00 frames.], tot_loss[loss=0.1976, simple_loss=0.281, pruned_loss=0.05706, over 1428675.15 frames.], batch size: 20, lr: 4.11e-04
2022-05-27 15:02:56,161 INFO [train.py:842] (3/4) Epoch 13, batch 8700, loss[loss=0.1929, simple_loss=0.2731, pruned_loss=0.05633, over 7170.00 frames.], tot_loss[loss=0.198, simple_loss=0.2816, pruned_loss=0.05715, over 1425551.38 frames.], batch size: 18, lr: 4.11e-04
2022-05-27 15:03:34,674 INFO [train.py:842] (3/4) Epoch 13, batch 8750, loss[loss=0.2567, simple_loss=0.3236, pruned_loss=0.09485, over 7207.00 frames.], tot_loss[loss=0.199, simple_loss=0.2826, pruned_loss=0.05774, over 1423278.01 frames.], batch size: 21, lr: 4.11e-04
2022-05-27 15:04:13,443 INFO [train.py:842] (3/4) Epoch 13, batch 8800, loss[loss=0.2168, simple_loss=0.3001, pruned_loss=0.06677, over 7111.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2837, pruned_loss=0.05825, over 1419415.30 frames.], batch size: 21, lr: 4.11e-04
2022-05-27 15:04:52,096 INFO [train.py:842] (3/4) Epoch 13, batch 8850, loss[loss=0.264, simple_loss=0.3328, pruned_loss=0.09765, over 4838.00 frames.], tot_loss[loss=0.203, simple_loss=0.2859, pruned_loss=0.06006, over 1415297.41 frames.], batch size: 52, lr: 4.11e-04
2022-05-27 15:05:30,825 INFO [train.py:842] (3/4) Epoch 13, batch 8900, loss[loss=0.1831, simple_loss=0.2699, pruned_loss=0.04818, over 7168.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2859, pruned_loss=0.05998, over 1409736.85 frames.], batch size: 19, lr: 4.11e-04
2022-05-27 15:06:09,672 INFO [train.py:842] (3/4) Epoch 13, batch 8950, loss[loss=0.218, simple_loss=0.3045, pruned_loss=0.06569, over 7114.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2842, pruned_loss=0.05934, over 1402781.52 frames.], batch size: 26, lr: 4.11e-04
2022-05-27 15:06:48,232 INFO [train.py:842] (3/4) Epoch 13, batch 9000, loss[loss=0.1964, simple_loss=0.2843, pruned_loss=0.05428, over 6531.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2847, pruned_loss=0.05987, over 1388109.40 frames.], batch size: 39, lr: 4.11e-04
2022-05-27 15:06:48,233 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 15:06:57,716 INFO [train.py:871] (3/4) Epoch 13, validation: loss=0.1693, simple_loss=0.2699, pruned_loss=0.03436, over 868885.00 frames.
2022-05-27 15:07:34,934 INFO [train.py:842] (3/4) Epoch 13, batch 9050, loss[loss=0.2778, simple_loss=0.3513, pruned_loss=0.1022, over 6444.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2884, pruned_loss=0.06254, over 1351711.76 frames.], batch size: 38, lr: 4.10e-04
2022-05-27 15:08:12,260 INFO [train.py:842] (3/4) Epoch 13, batch 9100, loss[loss=0.1928, simple_loss=0.2865, pruned_loss=0.04955, over 6348.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2915, pruned_loss=0.06467, over 1308250.27 frames.], batch size: 38, lr: 4.10e-04
2022-05-27 15:08:49,673 INFO [train.py:842] (3/4) Epoch 13, batch 9150, loss[loss=0.2311, simple_loss=0.3121, pruned_loss=0.07504, over 5150.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2938, pruned_loss=0.06685, over 1258214.76 frames.], batch size: 52, lr: 4.10e-04
2022-05-27 15:09:36,409 INFO [train.py:842] (3/4) Epoch 14, batch 0, loss[loss=0.1898, simple_loss=0.2691, pruned_loss=0.05528, over 7372.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2691, pruned_loss=0.05528, over 7372.00 frames.], batch size: 23, lr: 3.97e-04
2022-05-27 15:10:16,195 INFO [train.py:842] (3/4) Epoch 14, batch 50, loss[loss=0.18, simple_loss=0.2737, pruned_loss=0.04311, over 7128.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2799, pruned_loss=0.05753, over 322473.34 frames.], batch size: 21, lr: 3.97e-04
2022-05-27 15:10:55,372 INFO [train.py:842] (3/4) Epoch 14, batch 100, loss[loss=0.189, simple_loss=0.2795, pruned_loss=0.04929, over 7145.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2783, pruned_loss=0.05494, over 572283.77 frames.], batch size: 20, lr: 3.97e-04
2022-05-27 15:11:34,739 INFO [train.py:842] (3/4) Epoch 14, batch 150, loss[loss=0.1739, simple_loss=0.2511, pruned_loss=0.04834, over 7000.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2798, pruned_loss=0.05674, over 763390.45 frames.], batch size: 16, lr: 3.97e-04
2022-05-27 15:12:13,400 INFO [train.py:842] (3/4) Epoch 14, batch 200, loss[loss=0.2146, simple_loss=0.2987, pruned_loss=0.0652, over 7202.00 frames.], tot_loss[loss=0.197, simple_loss=0.2804, pruned_loss=0.05677, over 910236.30 frames.], batch size: 22, lr: 3.97e-04
2022-05-27 15:12:52,356 INFO [train.py:842] (3/4) Epoch 14, batch 250, loss[loss=0.1982, simple_loss=0.2796, pruned_loss=0.05841, over 7212.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2819, pruned_loss=0.05734, over 1025897.26 frames.], batch size: 22, lr: 3.97e-04
2022-05-27 15:13:30,935 INFO [train.py:842] (3/4) Epoch 14, batch 300, loss[loss=0.184, simple_loss=0.2663, pruned_loss=0.05083, over 7412.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2835, pruned_loss=0.05788, over 1112653.77 frames.], batch size: 21, lr: 3.97e-04
2022-05-27 15:14:09,859 INFO [train.py:842] (3/4) Epoch 14, batch 350, loss[loss=0.1849, simple_loss=0.2739, pruned_loss=0.04796, over 7433.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2825, pruned_loss=0.05758, over 1181458.30 frames.], batch size: 20, lr: 3.96e-04
2022-05-27 15:14:48,799 INFO [train.py:842] (3/4) Epoch 14, batch 400, loss[loss=0.1928, simple_loss=0.2884, pruned_loss=0.04854, over 7013.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2823, pruned_loss=0.0575, over 1231876.09 frames.], batch size: 28, lr: 3.96e-04
2022-05-27 15:15:28,283 INFO [train.py:842] (3/4) Epoch 14, batch 450, loss[loss=0.2045, simple_loss=0.2899, pruned_loss=0.05958, over 6528.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2821, pruned_loss=0.05746, over 1273842.36 frames.], batch size: 38, lr: 3.96e-04
2022-05-27 15:16:07,091 INFO [train.py:842] (3/4) Epoch 14, batch 500, loss[loss=0.1774, simple_loss=0.2744, pruned_loss=0.04017, over 7043.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2824, pruned_loss=0.05792, over 1300496.34 frames.], batch size: 28, lr: 3.96e-04
2022-05-27 15:16:48,802 INFO [train.py:842] (3/4) Epoch 14, batch 550, loss[loss=0.1665, simple_loss=0.2633, pruned_loss=0.03487, over 6327.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2814, pruned_loss=0.05713, over 1325689.55 frames.], batch size: 37, lr: 3.96e-04
2022-05-27 15:17:27,797 INFO [train.py:842] (3/4) Epoch 14, batch 600, loss[loss=0.2222, simple_loss=0.3076, pruned_loss=0.06842, over 7328.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2812, pruned_loss=0.05722, over 1347501.73 frames.], batch size: 21, lr: 3.96e-04
2022-05-27 15:18:06,503 INFO [train.py:842] (3/4) Epoch 14, batch 650, loss[loss=0.1541, simple_loss=0.2422, pruned_loss=0.03305, over 7077.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2819, pruned_loss=0.05749, over 1360129.13 frames.], batch size: 18, lr: 3.96e-04
2022-05-27 15:18:45,294 INFO [train.py:842] (3/4) Epoch 14, batch 700, loss[loss=0.1959, simple_loss=0.2779, pruned_loss=0.05695, over 7275.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2812, pruned_loss=0.05697, over 1375909.75 frames.], batch size: 18, lr: 3.96e-04
2022-05-27 15:19:24,159 INFO [train.py:842] (3/4) Epoch 14, batch 750, loss[loss=0.2005, simple_loss=0.2785, pruned_loss=0.06121, over 7205.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2817, pruned_loss=0.05744, over 1384091.40 frames.], batch size: 23, lr: 3.96e-04
2022-05-27 15:20:03,036 INFO [train.py:842] (3/4) Epoch 14, batch 800, loss[loss=0.206, simple_loss=0.291, pruned_loss=0.06049, over 7324.00 frames.], tot_loss[loss=0.2006, simple_loss=0.284, pruned_loss=0.05862, over 1393506.39 frames.], batch size: 25, lr: 3.96e-04
2022-05-27 15:20:42,386 INFO [train.py:842] (3/4) Epoch 14, batch 850, loss[loss=0.1981, simple_loss=0.2902, pruned_loss=0.05302, over 7220.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2836, pruned_loss=0.05856, over 1401461.10 frames.], batch size: 21, lr: 3.96e-04
2022-05-27 15:21:21,202 INFO [train.py:842] (3/4) Epoch 14, batch 900, loss[loss=0.2122, simple_loss=0.2958, pruned_loss=0.06433, over 7167.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2832, pruned_loss=0.05827, over 1404191.52 frames.], batch size: 18, lr: 3.96e-04
2022-05-27 15:21:59,906 INFO [train.py:842] (3/4) Epoch 14, batch 950, loss[loss=0.2843, simple_loss=0.3503, pruned_loss=0.1092, over 7219.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2852, pruned_loss=0.05918, over 1404132.65 frames.], batch size: 21, lr: 3.96e-04
2022-05-27 15:22:39,015 INFO [train.py:842] (3/4) Epoch 14, batch 1000, loss[loss=0.2053, simple_loss=0.291, pruned_loss=0.05984, over 7217.00 frames.], tot_loss[loss=0.1993, simple_loss=0.283, pruned_loss=0.05786, over 1411364.56 frames.], batch size: 22, lr: 3.95e-04
2022-05-27 15:23:18,296 INFO [train.py:842] (3/4) Epoch 14, batch 1050, loss[loss=0.1725, simple_loss=0.2628, pruned_loss=0.04112, over 7416.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2825, pruned_loss=0.05794, over 1412856.18 frames.], batch size: 21, lr: 3.95e-04
2022-05-27 15:23:57,028 INFO [train.py:842] (3/4) Epoch 14, batch 1100, loss[loss=0.1825, simple_loss=0.2714, pruned_loss=0.04684, over 6686.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2817, pruned_loss=0.05769, over 1412630.14 frames.], batch size: 31, lr: 3.95e-04
2022-05-27 15:24:35,955 INFO [train.py:842] (3/4) Epoch 14, batch 1150, loss[loss=0.271, simple_loss=0.3369, pruned_loss=0.1026, over 7330.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2836, pruned_loss=0.05859, over 1412077.05 frames.], batch size: 22, lr: 3.95e-04
2022-05-27 15:25:14,714 INFO [train.py:842] (3/4) Epoch 14, batch 1200, loss[loss=0.2125, simple_loss=0.2945, pruned_loss=0.06528, over 5162.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2831, pruned_loss=0.05842, over 1411354.39 frames.], batch size: 52, lr: 3.95e-04
2022-05-27 15:25:53,904 INFO [train.py:842] (3/4) Epoch 14, batch 1250, loss[loss=0.178, simple_loss=0.2659, pruned_loss=0.04508, over 7431.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2823, pruned_loss=0.05762, over 1415664.54 frames.], batch size: 20, lr: 3.95e-04
2022-05-27 15:26:32,842 INFO [train.py:842] (3/4) Epoch 14, batch 1300, loss[loss=0.241, simple_loss=0.321, pruned_loss=0.08051, over 7267.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2822, pruned_loss=0.05722, over 1418429.86 frames.], batch size: 19, lr: 3.95e-04
2022-05-27 15:27:22,208 INFO [train.py:842] (3/4) Epoch 14, batch 1350, loss[loss=0.1891, simple_loss=0.2785, pruned_loss=0.04986, over 7270.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2808, pruned_loss=0.05641, over 1421882.24 frames.], batch size: 18, lr: 3.95e-04
2022-05-27 15:28:01,189 INFO [train.py:842] (3/4) Epoch 14, batch 1400, loss[loss=0.2032, simple_loss=0.2682, pruned_loss=0.06912, over 7158.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2811, pruned_loss=0.05669, over 1417525.85 frames.], batch size: 18, lr: 3.95e-04
2022-05-27 15:28:40,391 INFO [train.py:842] (3/4) Epoch 14, batch 1450, loss[loss=0.1873, simple_loss=0.2665, pruned_loss=0.05398, over 7283.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2812, pruned_loss=0.05664, over 1421718.12 frames.], batch size: 17, lr: 3.95e-04
2022-05-27 15:29:19,115 INFO [train.py:842] (3/4) Epoch 14, batch 1500, loss[loss=0.1811, simple_loss=0.2459, pruned_loss=0.05812, over 7279.00 frames.], tot_loss[loss=0.1965, simple_loss=0.28, pruned_loss=0.05648, over 1423219.02 frames.], batch size: 17, lr: 3.95e-04
2022-05-27 15:29:58,080 INFO [train.py:842] (3/4) Epoch 14, batch 1550, loss[loss=0.2138, simple_loss=0.2957, pruned_loss=0.0659, over 6151.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2811, pruned_loss=0.05739, over 1417709.45 frames.], batch size: 37, lr: 3.95e-04
2022-05-27 15:30:37,040 INFO [train.py:842] (3/4) Epoch 14, batch 1600, loss[loss=0.1936, simple_loss=0.2827, pruned_loss=0.0522, over 7418.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2831, pruned_loss=0.0589, over 1417776.45 frames.], batch size: 21, lr: 3.94e-04
2022-05-27 15:31:16,025 INFO [train.py:842] (3/4) Epoch 14, batch 1650, loss[loss=0.181, simple_loss=0.2711, pruned_loss=0.04542, over 7231.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2836, pruned_loss=0.05898, over 1419896.96 frames.], batch size: 20, lr: 3.94e-04
2022-05-27 15:31:54,476 INFO [train.py:842] (3/4) Epoch 14, batch 1700, loss[loss=0.1786, simple_loss=0.2663, pruned_loss=0.04541, over 6604.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2851, pruned_loss=0.05976, over 1419437.32 frames.], batch size: 38, lr: 3.94e-04
2022-05-27 15:32:33,876 INFO [train.py:842] (3/4) Epoch 14, batch 1750, loss[loss=0.1602, simple_loss=0.237, pruned_loss=0.04167, over 7268.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2835, pruned_loss=0.05872, over 1422133.53 frames.], batch size: 17, lr: 3.94e-04
2022-05-27 15:33:12,972 INFO [train.py:842] (3/4) Epoch 14, batch 1800, loss[loss=0.1734, simple_loss=0.2639, pruned_loss=0.04145, over 7149.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2817, pruned_loss=0.05773, over 1426357.49 frames.], batch size: 20, lr: 3.94e-04
2022-05-27 15:33:51,970 INFO [train.py:842] (3/4) Epoch 14, batch 1850, loss[loss=0.1921, simple_loss=0.289, pruned_loss=0.04766, over 7301.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2816, pruned_loss=0.05729, over 1425793.87 frames.], batch size: 25, lr: 3.94e-04
2022-05-27 15:34:30,693 INFO [train.py:842] (3/4) Epoch 14, batch 1900, loss[loss=0.1986, simple_loss=0.2823, pruned_loss=0.05746, over 6182.00 frames.], tot_loss[loss=0.1985, simple_loss=0.282, pruned_loss=0.05751, over 1421235.31 frames.], batch size: 37, lr: 3.94e-04
2022-05-27 15:35:09,524 INFO [train.py:842] (3/4) Epoch 14, batch 1950, loss[loss=0.1785, simple_loss=0.2659, pruned_loss=0.04558, over 7254.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2821, pruned_loss=0.05724, over 1422456.67 frames.], batch size: 19, lr: 3.94e-04
2022-05-27 15:35:48,300 INFO [train.py:842] (3/4) Epoch 14, batch 2000, loss[loss=0.1811, simple_loss=0.2779, pruned_loss=0.0421, over 7338.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2823, pruned_loss=0.05761, over 1424382.89 frames.], batch size: 22, lr: 3.94e-04
2022-05-27 15:36:27,730 INFO [train.py:842] (3/4) Epoch 14, batch 2050, loss[loss=0.1861, simple_loss=0.2709, pruned_loss=0.05067, over 7379.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2816, pruned_loss=0.05738, over 1425611.07 frames.], batch size: 23, lr: 3.94e-04
2022-05-27 15:37:06,334 INFO [train.py:842] (3/4) Epoch 14, batch 2100, loss[loss=0.2238, simple_loss=0.301, pruned_loss=0.07333, over 7239.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2829, pruned_loss=0.058, over 1425336.62 frames.], batch size: 20, lr: 3.94e-04
2022-05-27 15:37:45,665 INFO [train.py:842] (3/4) Epoch 14, batch 2150, loss[loss=0.1785, simple_loss=0.2748, pruned_loss=0.04106, over 7229.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2815, pruned_loss=0.05687, over 1427617.18 frames.], batch size: 26, lr: 3.94e-04
2022-05-27 15:38:24,815 INFO [train.py:842] (3/4) Epoch 14, batch 2200, loss[loss=0.1799, simple_loss=0.2679, pruned_loss=0.04594, over 7430.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2823, pruned_loss=0.05767, over 1426575.53 frames.], batch size: 20, lr: 3.93e-04
2022-05-27 15:39:04,002 INFO [train.py:842] (3/4) Epoch 14, batch 2250, loss[loss=0.1855, simple_loss=0.2765, pruned_loss=0.04725, over 7237.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2816, pruned_loss=0.05726, over 1427996.83 frames.], batch size: 20, lr: 3.93e-04
2022-05-27 15:39:42,983 INFO [train.py:842] (3/4) Epoch 14, batch 2300, loss[loss=0.2128, simple_loss=0.2961, pruned_loss=0.06476, over 7067.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2797, pruned_loss=0.05628, over 1428294.41 frames.], batch size: 28, lr: 3.93e-04
2022-05-27 15:40:22,162 INFO [train.py:842] (3/4) Epoch 14, batch 2350, loss[loss=0.2281, simple_loss=0.2951, pruned_loss=0.08049, over 5118.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2808, pruned_loss=0.05694, over 1427702.92 frames.], batch size: 53, lr: 3.93e-04
2022-05-27 15:41:00,897 INFO [train.py:842] (3/4) Epoch 14, batch 2400, loss[loss=0.179, simple_loss=0.2526, pruned_loss=0.05273, over 7292.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2814, pruned_loss=0.05773, over 1429118.00 frames.], batch size: 17, lr: 3.93e-04
2022-05-27 15:41:40,007 INFO [train.py:842] (3/4) Epoch 14, batch 2450, loss[loss=0.1834, simple_loss=0.2782, pruned_loss=0.04427, over 6827.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2816, pruned_loss=0.05736, over 1431248.31 frames.], batch size: 31, lr: 3.93e-04
2022-05-27 15:42:19,157 INFO [train.py:842] (3/4) Epoch 14, batch 2500, loss[loss=0.2012, simple_loss=0.2761, pruned_loss=0.06313, over 7279.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2829, pruned_loss=0.05779, over 1427298.43 frames.], batch size: 17, lr: 3.93e-04
2022-05-27 15:42:58,102 INFO [train.py:842] (3/4) Epoch 14, batch 2550, loss[loss=0.2103, simple_loss=0.2963, pruned_loss=0.06213, over 7295.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2832, pruned_loss=0.05821, over 1423252.31 frames.], batch size: 25, lr: 3.93e-04
2022-05-27 15:43:37,315 INFO [train.py:842] (3/4) Epoch 14, batch 2600, loss[loss=0.1928, simple_loss=0.2886, pruned_loss=0.04849, over 7419.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2834, pruned_loss=0.05819, over 1419358.69 frames.], batch size: 21, lr: 3.93e-04
2022-05-27 15:44:16,182 INFO [train.py:842] (3/4) Epoch 14, batch 2650, loss[loss=0.1707, simple_loss=0.2662, pruned_loss=0.03757, over 7122.00 frames.], tot_loss[loss=0.2007, simple_loss=0.284, pruned_loss=0.05869, over 1417311.32 frames.], batch size: 21, lr: 3.93e-04
2022-05-27 15:44:55,685 INFO [train.py:842] (3/4) Epoch 14, batch 2700, loss[loss=0.1549, simple_loss=0.2377, pruned_loss=0.03606, over 6997.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2824, pruned_loss=0.05771, over 1422351.24 frames.], batch size: 16, lr: 3.93e-04
2022-05-27 15:45:35,124 INFO [train.py:842] (3/4) Epoch 14, batch 2750, loss[loss=0.2278, simple_loss=0.3066, pruned_loss=0.07453, over 7280.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2813, pruned_loss=0.05654, over 1426912.85 frames.], batch size: 24, lr: 3.93e-04
2022-05-27 15:46:13,971 INFO [train.py:842] (3/4) Epoch 14, batch 2800, loss[loss=0.1624, simple_loss=0.237, pruned_loss=0.04392, over 7122.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2811, pruned_loss=0.05656, over 1425388.50 frames.], batch size: 17, lr: 3.93e-04
2022-05-27 15:46:53,104 INFO [train.py:842] (3/4) Epoch 14, batch 2850, loss[loss=0.1679, simple_loss=0.2682, pruned_loss=0.03378, over 7413.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2809, pruned_loss=0.05668, over 1426241.68 frames.], batch size: 21, lr: 3.92e-04
2022-05-27 15:47:31,772 INFO [train.py:842] (3/4) Epoch 14, batch 2900, loss[loss=0.2068, simple_loss=0.2896, pruned_loss=0.06203, over 7112.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2804, pruned_loss=0.05586, over 1427734.37 frames.], batch size: 21, lr: 3.92e-04
2022-05-27 15:48:10,962 INFO [train.py:842] (3/4) Epoch 14, batch 2950, loss[loss=0.2002, simple_loss=0.2969, pruned_loss=0.05174, over 7189.00 frames.], tot_loss[loss=0.196, simple_loss=0.2807, pruned_loss=0.05567, over 1429010.14 frames.], batch size: 23, lr: 3.92e-04
2022-05-27 15:48:50,363 INFO [train.py:842] (3/4) Epoch 14, batch 3000, loss[loss=0.1996, simple_loss=0.2917, pruned_loss=0.05377, over 7297.00 frames.], tot_loss[loss=0.1956, simple_loss=0.28, pruned_loss=0.05562, over 1429353.53 frames.], batch size: 24, lr: 3.92e-04
2022-05-27 15:48:50,363 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 15:48:59,799 INFO [train.py:871] (3/4) Epoch 14, validation: loss=0.17, simple_loss=0.2697, pruned_loss=0.03515, over 868885.00 frames.
2022-05-27 15:49:39,106 INFO [train.py:842] (3/4) Epoch 14, batch 3050, loss[loss=0.1608, simple_loss=0.2407, pruned_loss=0.04047, over 7267.00 frames.], tot_loss[loss=0.1949, simple_loss=0.279, pruned_loss=0.05543, over 1430194.28 frames.], batch size: 17, lr: 3.92e-04
2022-05-27 15:50:17,916 INFO [train.py:842] (3/4) Epoch 14, batch 3100, loss[loss=0.2079, simple_loss=0.3029, pruned_loss=0.05643, over 7204.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2806, pruned_loss=0.05652, over 1430675.50 frames.], batch size: 23, lr: 3.92e-04
2022-05-27 15:50:57,007 INFO [train.py:842] (3/4) Epoch 14, batch 3150, loss[loss=0.2538, simple_loss=0.3226, pruned_loss=0.09254, over 5301.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2792, pruned_loss=0.05613, over 1430067.28 frames.], batch size: 52, lr: 3.92e-04
2022-05-27 15:51:35,896 INFO [train.py:842] (3/4) Epoch 14, batch 3200, loss[loss=0.2503, simple_loss=0.3244, pruned_loss=0.08807, over 7355.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2801, pruned_loss=0.05655, over 1429920.07 frames.], batch size: 22, lr: 3.92e-04
2022-05-27 15:52:14,789 INFO [train.py:842] (3/4) Epoch 14, batch 3250, loss[loss=0.2288, simple_loss=0.3137, pruned_loss=0.07199, over 7198.00 frames.], tot_loss[loss=0.197, simple_loss=0.2806, pruned_loss=0.05668, over 1427402.64 frames.], batch size: 26, lr: 3.92e-04
2022-05-27 15:52:53,671 INFO [train.py:842] (3/4) Epoch 14, batch 3300, loss[loss=0.1863, simple_loss=0.2714, pruned_loss=0.05058, over 7162.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2803, pruned_loss=0.05653, over 1424238.51 frames.], batch size: 18, lr: 3.92e-04
2022-05-27 15:53:32,478 INFO [train.py:842] (3/4) Epoch 14, batch 3350, loss[loss=0.2081, simple_loss=0.2854, pruned_loss=0.06539, over 7403.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2811, pruned_loss=0.05716, over 1425827.32 frames.], batch size: 18, lr: 3.92e-04
2022-05-27 15:54:11,136 INFO [train.py:842] (3/4) Epoch 14, batch 3400, loss[loss=0.1712, simple_loss=0.2556, pruned_loss=0.04342, over 7156.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2809, pruned_loss=0.05702, over 1427283.72 frames.], batch size: 18, lr: 3.92e-04
2022-05-27 15:55:00,328 INFO [train.py:842] (3/4) Epoch 14, batch 3450, loss[loss=0.1644, simple_loss=0.2592, pruned_loss=0.03482, over 7113.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2805, pruned_loss=0.05665, over 1426412.87 frames.], batch size: 21, lr: 3.91e-04
2022-05-27 15:55:39,248 INFO [train.py:842] (3/4) Epoch 14, batch 3500, loss[loss=0.2648, simple_loss=0.3495, pruned_loss=0.0901, over 7326.00 frames.], tot_loss[loss=0.197, simple_loss=0.2804, pruned_loss=0.05677, over 1427478.82 frames.], batch size: 22, lr: 3.91e-04
2022-05-27 15:56:28,932 INFO [train.py:842] (3/4) Epoch 14, batch 3550, loss[loss=0.1791, simple_loss=0.2709, pruned_loss=0.04369, over 7318.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2798, pruned_loss=0.05588, over 1427936.16 frames.], batch size: 21, lr: 3.91e-04
2022-05-27 15:57:08,503 INFO [train.py:842] (3/4) Epoch 14, batch 3600, loss[loss=0.1816, simple_loss=0.26, pruned_loss=0.0516, over 7358.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2785, pruned_loss=0.0553, over 1430762.30 frames.], batch size: 19, lr: 3.91e-04
2022-05-27 15:57:57,903 INFO [train.py:842] (3/4) Epoch 14, batch 3650, loss[loss=0.1905, simple_loss=0.2743, pruned_loss=0.05337, over 7231.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2787, pruned_loss=0.05538, over 1429884.61 frames.], batch size: 20, lr: 3.91e-04
2022-05-27 15:58:36,742 INFO [train.py:842] (3/4) Epoch 14, batch 3700, loss[loss=0.1948, simple_loss=0.2914, pruned_loss=0.04907, over 7288.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2801, pruned_loss=0.05649, over 1420816.84 frames.], batch size: 24, lr: 3.91e-04
2022-05-27 15:59:15,373 INFO [train.py:842] (3/4) Epoch 14, batch 3750, loss[loss=0.216, simple_loss=0.2946, pruned_loss=0.06868, over 5045.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2813, pruned_loss=0.05713, over 1419795.49 frames.], batch size: 52, lr: 3.91e-04
2022-05-27 15:59:54,258 INFO [train.py:842] (3/4) Epoch 14, batch 3800, loss[loss=0.1716, simple_loss=0.2554, pruned_loss=0.04388, over 7247.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2812, pruned_loss=0.05681, over 1419358.37 frames.], batch size: 19, lr: 3.91e-04
2022-05-27 16:00:33,480 INFO [train.py:842] (3/4) Epoch 14, batch 3850, loss[loss=0.1743, simple_loss=0.2702, pruned_loss=0.0392, over 6286.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2799, pruned_loss=0.05579, over 1421120.05 frames.], batch size: 37, lr: 3.91e-04
2022-05-27 16:01:12,317 INFO [train.py:842] (3/4) Epoch 14, batch 3900, loss[loss=0.1635, simple_loss=0.2471, pruned_loss=0.03998, over 7112.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2802, pruned_loss=0.05606, over 1422110.83 frames.], batch size: 21, lr: 3.91e-04
2022-05-27 16:01:51,358 INFO [train.py:842] (3/4) Epoch 14, batch 3950, loss[loss=0.2285, simple_loss=0.295, pruned_loss=0.08103, over 4907.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2809, pruned_loss=0.05712, over 1421339.67 frames.], batch size: 52, lr: 3.91e-04
2022-05-27 16:02:30,315 INFO [train.py:842] (3/4) Epoch 14, batch 4000, loss[loss=0.1632, simple_loss=0.2524, pruned_loss=0.03698, over 7162.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2802, pruned_loss=0.05636, over 1421795.65 frames.], batch size: 18, lr: 3.91e-04
2022-05-27 16:03:09,214 INFO [train.py:842] (3/4) Epoch 14, batch 4050, loss[loss=0.2037, simple_loss=0.2951, pruned_loss=0.05611, over 7208.00 frames.], tot_loss[loss=0.197, simple_loss=0.2807, pruned_loss=0.0566, over 1424171.01 frames.], batch size: 22, lr: 3.91e-04
2022-05-27 16:03:48,318 INFO [train.py:842] (3/4) Epoch 14, batch 4100, loss[loss=0.1945, simple_loss=0.2821, pruned_loss=0.0534, over 7211.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2802, pruned_loss=0.05708, over 1426032.19 frames.], batch size: 22, lr: 3.90e-04
2022-05-27 16:04:27,750 INFO [train.py:842] (3/4) Epoch 14, batch 4150, loss[loss=0.2034, simple_loss=0.2917, pruned_loss=0.05754, over 7317.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2816, pruned_loss=0.05776, over 1421768.56 frames.], batch size: 21, lr: 3.90e-04
2022-05-27 16:05:06,394 INFO [train.py:842] (3/4) Epoch 14, batch 4200, loss[loss=0.1942, simple_loss=0.2696, pruned_loss=0.05936, over 7128.00 frames.], tot_loss[loss=0.199, simple_loss=0.2818, pruned_loss=0.05812, over 1424215.12 frames.], batch size: 17, lr: 3.90e-04
2022-05-27 16:05:45,532 INFO [train.py:842] (3/4) Epoch 14, batch 4250, loss[loss=0.18, simple_loss=0.2677, pruned_loss=0.04615, over 7425.00 frames.], tot_loss[loss=0.1994, simple_loss=0.282, pruned_loss=0.05837, over 1420785.56 frames.], batch size: 20, lr: 3.90e-04
2022-05-27 16:06:24,402 INFO [train.py:842] (3/4) Epoch 14, batch 4300, loss[loss=0.2879, simple_loss=0.3397, pruned_loss=0.118, over 7414.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2835, pruned_loss=0.05964, over 1416372.61 frames.], batch size: 21, lr: 3.90e-04
2022-05-27 16:07:03,468 INFO [train.py:842] (3/4) Epoch 14, batch 4350, loss[loss=0.1768, simple_loss=0.2651, pruned_loss=0.04426, over 7440.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2833, pruned_loss=0.05902, over 1418826.23 frames.], batch size: 20, lr: 3.90e-04
2022-05-27 16:07:42,425 INFO [train.py:842] (3/4) Epoch 14, batch 4400, loss[loss=0.2085, simple_loss=0.2927, pruned_loss=0.06213, over 6792.00 frames.], tot_loss[loss=0.2, simple_loss=0.2831, pruned_loss=0.05851, over 1419151.65 frames.], batch size: 31, lr: 3.90e-04
2022-05-27 16:08:21,619 INFO [train.py:842] (3/4) Epoch 14, batch 4450, loss[loss=0.2385, simple_loss=0.3268, pruned_loss=0.07514, over 7410.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2822, pruned_loss=0.05804, over 1419585.67 frames.], batch size: 21, lr: 3.90e-04
2022-05-27 16:09:00,490 INFO [train.py:842] (3/4) Epoch 14, batch 4500, loss[loss=0.1927, simple_loss=0.2837, pruned_loss=0.05088, over 7219.00 frames.], tot_loss[loss=0.1987, simple_loss=0.282, pruned_loss=0.05774, over 1420645.61 frames.], batch size: 21, lr: 3.90e-04
2022-05-27 16:09:39,610 INFO [train.py:842] (3/4) Epoch 14, batch 4550, loss[loss=0.2031, simple_loss=0.2903, pruned_loss=0.05792, over 7335.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2827, pruned_loss=0.05801, over 1415367.01 frames.], batch size: 22, lr: 3.90e-04
2022-05-27 16:10:18,170 INFO [train.py:842] (3/4) Epoch 14, batch 4600, loss[loss=0.1953, simple_loss=0.2762, pruned_loss=0.05722, over 6625.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2831, pruned_loss=0.05809, over 1415730.90 frames.], batch size: 38, lr: 3.90e-04
2022-05-27 16:10:57,483 INFO [train.py:842] (3/4) Epoch 14, batch 4650, loss[loss=0.2169, simple_loss=0.295, pruned_loss=0.06937, over 7362.00 frames.], tot_loss[loss=0.199, simple_loss=0.2825, pruned_loss=0.0578, over 1415353.94 frames.], batch size: 19, lr: 3.90e-04
2022-05-27 16:11:35,859 INFO [train.py:842] (3/4) Epoch 14, batch 4700, loss[loss=0.1682, simple_loss=0.2563, pruned_loss=0.04004, over 7156.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2828, pruned_loss=0.05799, over 1412853.47 frames.], batch size: 26, lr: 3.90e-04
2022-05-27 16:12:14,911 INFO [train.py:842] (3/4) Epoch 14, batch 4750, loss[loss=0.2627, simple_loss=0.3419, pruned_loss=0.09176, over 7256.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2838, pruned_loss=0.05852, over 1415702.11 frames.], batch size: 19, lr: 3.89e-04
2022-05-27 16:12:53,727 INFO [train.py:842] (3/4) Epoch 14, batch 4800, loss[loss=0.1997, simple_loss=0.2809, pruned_loss=0.05926, over 7424.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2835, pruned_loss=0.05856, over 1417567.81 frames.], batch size: 21, lr: 3.89e-04
2022-05-27 16:13:32,500 INFO [train.py:842] (3/4) Epoch 14, batch 4850, loss[loss=0.2252, simple_loss=0.3134, pruned_loss=0.06851, over 7206.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2842, pruned_loss=0.05855, over 1419170.19 frames.], batch size: 22, lr: 3.89e-04
2022-05-27 16:14:11,419 INFO [train.py:842] (3/4) Epoch 14, batch 4900, loss[loss=0.1874, simple_loss=0.2727, pruned_loss=0.05098, over 6892.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2836, pruned_loss=0.0578, over 1418910.41 frames.], batch size: 31, lr: 3.89e-04
2022-05-27 16:14:50,481 INFO [train.py:842] (3/4) Epoch 14, batch 4950, loss[loss=0.179, simple_loss=0.2712, pruned_loss=0.0434, over 7200.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2823, pruned_loss=0.05712, over 1419111.19 frames.], batch size: 22, lr: 3.89e-04
2022-05-27 16:15:29,230 INFO [train.py:842] (3/4) Epoch 14, batch 5000, loss[loss=0.1673, simple_loss=0.2505, pruned_loss=0.0421, over 7166.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2824, pruned_loss=0.05712, over 1422210.94 frames.], batch size: 18, lr: 3.89e-04
2022-05-27 16:16:08,285 INFO [train.py:842] (3/4) Epoch 14, batch 5050, loss[loss=0.2413, simple_loss=0.2938, pruned_loss=0.09439, over 7012.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2817, pruned_loss=0.05691, over 1418932.97 frames.], batch size: 16, lr: 3.89e-04
2022-05-27 16:16:47,146 INFO [train.py:842] (3/4) Epoch 14, batch 5100, loss[loss=0.1681, simple_loss=0.2514, pruned_loss=0.0424, over 7253.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2815, pruned_loss=0.05702, over 1419108.85 frames.], batch size: 19, lr: 3.89e-04
2022-05-27 16:17:26,328 INFO [train.py:842] (3/4) Epoch 14, batch 5150, loss[loss=0.2406, simple_loss=0.3211, pruned_loss=0.08009, over 7287.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2814, pruned_loss=0.05722, over 1423055.82 frames.], batch size: 24, lr: 3.89e-04
2022-05-27 16:18:04,979 INFO [train.py:842] (3/4) Epoch 14, batch 5200, loss[loss=0.2512, simple_loss=0.3365, pruned_loss=0.08292, over 7408.00 frames.], tot_loss[loss=0.1974, simple_loss=0.281, pruned_loss=0.05697, over 1426280.74 frames.], batch size: 21, lr: 3.89e-04
2022-05-27 16:18:44,083 INFO [train.py:842] (3/4) Epoch 14, batch 5250, loss[loss=0.1987, simple_loss=0.281, pruned_loss=0.05816, over 7389.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2819, pruned_loss=0.05718, over 1428593.27 frames.], batch size: 23, lr: 3.89e-04
2022-05-27 16:19:22,710 INFO [train.py:842] (3/4) Epoch 14, batch 5300, loss[loss=0.2574, simple_loss=0.3222, pruned_loss=0.09636, over 4835.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2834, pruned_loss=0.05796, over 1421583.26 frames.], batch size: 52, lr: 3.89e-04
2022-05-27 16:20:01,792 INFO [train.py:842] (3/4) Epoch 14, batch 5350, loss[loss=0.1966, simple_loss=0.2886, pruned_loss=0.05234, over 7283.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2832, pruned_loss=0.05797, over 1423002.09 frames.], batch size: 24, lr: 3.88e-04
2022-05-27 16:20:40,888 INFO [train.py:842] (3/4) Epoch 14, batch 5400, loss[loss=0.1945, simple_loss=0.2852, pruned_loss=0.05185, over 7333.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2833, pruned_loss=0.05812, over 1426785.10 frames.], batch size: 22, lr: 3.88e-04
2022-05-27 16:21:20,196 INFO [train.py:842] (3/4) Epoch 14, batch 5450, loss[loss=0.1926, simple_loss=0.2804, pruned_loss=0.0524, over 6712.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2833, pruned_loss=0.05797, over 1426932.30 frames.], batch size: 31, lr: 3.88e-04
2022-05-27 16:21:59,186 INFO [train.py:842] (3/4) Epoch 14, batch 5500, loss[loss=0.2105, simple_loss=0.293, pruned_loss=0.064, over 7193.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2827, pruned_loss=0.05761, over 1428299.24 frames.], batch size: 23, lr: 3.88e-04
2022-05-27 16:22:38,738 INFO [train.py:842] (3/4) Epoch 14, batch 5550, loss[loss=0.1854, simple_loss=0.2654, pruned_loss=0.0527, over 7342.00 frames.], tot_loss[loss=0.1984, simple_loss=0.282, pruned_loss=0.05739, over 1430638.34 frames.], batch size: 20, lr: 3.88e-04
2022-05-27 16:23:17,937 INFO [train.py:842] (3/4) Epoch 14, batch 5600, loss[loss=0.166, simple_loss=0.2504, pruned_loss=0.04074, over 7269.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2808, pruned_loss=0.05703, over 1429192.31 frames.], batch size: 17, lr: 3.88e-04
2022-05-27 16:23:57,237 INFO [train.py:842] (3/4) Epoch 14, batch 5650, loss[loss=0.2148, simple_loss=0.3113, pruned_loss=0.0592, over 7295.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2812, pruned_loss=0.05715, over 1429600.43 frames.], batch size: 24, lr: 3.88e-04
2022-05-27 16:24:36,071 INFO [train.py:842] (3/4) Epoch 14, batch 5700, loss[loss=0.1652, simple_loss=0.2582, pruned_loss=0.0361, over 7427.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2807, pruned_loss=0.05723, over 1432210.13 frames.], batch size: 20, lr: 3.88e-04
2022-05-27 16:25:15,159 INFO [train.py:842] (3/4) Epoch 14, batch 5750, loss[loss=0.217, simple_loss=0.2987, pruned_loss=0.06768, over 7298.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2809, pruned_loss=0.05667, over 1430653.79 frames.], batch size: 24, lr: 3.88e-04
2022-05-27 16:25:54,360 INFO [train.py:842] (3/4) Epoch 14, batch 5800, loss[loss=0.2993, simple_loss=0.3616, pruned_loss=0.1185, over 7314.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2808, pruned_loss=0.05695, over 1429825.87 frames.], batch size: 21, lr: 3.88e-04
2022-05-27 16:26:33,789 INFO [train.py:842] (3/4) Epoch 14, batch 5850, loss[loss=0.1727, simple_loss=0.2572, pruned_loss=0.04408, over 7355.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2805, pruned_loss=0.05689, over 1427798.89 frames.], batch size: 19, lr: 3.88e-04
2022-05-27 16:27:12,636 INFO [train.py:842] (3/4) Epoch 14, batch 5900, loss[loss=0.1886, simple_loss=0.2883, pruned_loss=0.0445, over 6690.00 frames.], tot_loss[loss=0.197, simple_loss=0.2803, pruned_loss=0.05681, over 1423246.70 frames.], batch size: 38, lr: 3.88e-04
2022-05-27 16:27:52,043 INFO [train.py:842] (3/4) Epoch 14, batch 5950, loss[loss=0.2068, simple_loss=0.2739, pruned_loss=0.06987, over 7299.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2828, pruned_loss=0.059, over 1425210.09 frames.], batch size: 17, lr: 3.88e-04
2022-05-27 16:28:31,065 INFO [train.py:842] (3/4) Epoch 14, batch 6000, loss[loss=0.187, simple_loss=0.2752, pruned_loss=0.04939, over 6500.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2827, pruned_loss=0.05873, over 1419768.84 frames.], batch size: 38, lr: 3.87e-04
2022-05-27 16:28:31,066 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 16:28:40,676 INFO [train.py:871] (3/4) Epoch 14, validation: loss=0.1701, simple_loss=0.2708, pruned_loss=0.03472, over 868885.00 frames.
2022-05-27 16:29:19,890 INFO [train.py:842] (3/4) Epoch 14, batch 6050, loss[loss=0.2078, simple_loss=0.2851, pruned_loss=0.06522, over 7231.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2814, pruned_loss=0.05786, over 1419571.77 frames.], batch size: 20, lr: 3.87e-04
2022-05-27 16:29:58,686 INFO [train.py:842] (3/4) Epoch 14, batch 6100, loss[loss=0.1767, simple_loss=0.2539, pruned_loss=0.04969, over 7071.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2819, pruned_loss=0.0585, over 1422855.99 frames.], batch size: 18, lr: 3.87e-04
2022-05-27 16:30:38,144 INFO [train.py:842] (3/4) Epoch 14, batch 6150, loss[loss=0.1668, simple_loss=0.2531, pruned_loss=0.04024, over 7231.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2815, pruned_loss=0.05833, over 1422716.16 frames.], batch size: 16, lr: 3.87e-04
2022-05-27 16:31:17,314 INFO [train.py:842] (3/4) Epoch 14, batch 6200, loss[loss=0.1282, simple_loss=0.2106, pruned_loss=0.02287, over 7284.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2811, pruned_loss=0.0578, over 1415549.78 frames.], batch size: 17, lr: 3.87e-04
2022-05-27 16:31:56,500 INFO [train.py:842] (3/4) Epoch 14, batch 6250, loss[loss=0.1828, simple_loss=0.271, pruned_loss=0.04734, over 7191.00 frames.], tot_loss[loss=0.199, simple_loss=0.2817, pruned_loss=0.05811, over 1416321.66 frames.], batch size: 22, lr: 3.87e-04
2022-05-27 16:32:35,097 INFO [train.py:842] (3/4) Epoch 14, batch 6300, loss[loss=0.1593, simple_loss=0.2344, pruned_loss=0.04215, over 7285.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2818, pruned_loss=0.05736, over 1417578.94 frames.], batch size: 17, lr: 3.87e-04
2022-05-27 16:33:14,435 INFO [train.py:842] (3/4) Epoch 14, batch 6350, loss[loss=0.2054, simple_loss=0.2878, pruned_loss=0.06151, over 6179.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2804, pruned_loss=0.05667, over 1416114.16 frames.], batch size: 37, lr: 3.87e-04
2022-05-27 16:33:53,377 INFO [train.py:842] (3/4) Epoch 14, batch 6400, loss[loss=0.1899, simple_loss=0.2836, pruned_loss=0.04812, over 7124.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2794, pruned_loss=0.05601, over 1418636.67 frames.], batch size: 21, lr: 3.87e-04
2022-05-27 16:34:32,591 INFO [train.py:842] (3/4) Epoch 14, batch 6450, loss[loss=0.2079, simple_loss=0.2657, pruned_loss=0.07506, over 7281.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2784, pruned_loss=0.05528, over 1421126.03 frames.], batch size: 17, lr: 3.87e-04
2022-05-27 16:35:11,291 INFO [train.py:842] (3/4) Epoch 14, batch 6500, loss[loss=0.2883, simple_loss=0.3569, pruned_loss=0.1098, over 5033.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2812, pruned_loss=0.05703, over 1415047.87 frames.], batch size: 52, lr: 3.87e-04
2022-05-27 16:35:50,521 INFO [train.py:842] (3/4) Epoch 14, batch 6550, loss[loss=0.197, simple_loss=0.3024, pruned_loss=0.04585, over 7226.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2807, pruned_loss=0.05604, over 1416367.54 frames.], batch size: 21, lr: 3.87e-04
2022-05-27 16:36:29,248 INFO [train.py:842] (3/4) Epoch 14, batch 6600, loss[loss=0.182, simple_loss=0.2799, pruned_loss=0.04201, over 7331.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2807, pruned_loss=0.05595, over 1413844.63 frames.], batch size: 20, lr: 3.87e-04
2022-05-27 16:37:08,442 INFO [train.py:842] (3/4) Epoch 14, batch 6650, loss[loss=0.1835, simple_loss=0.2768, pruned_loss=0.04506, over 7152.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2817, pruned_loss=0.0566, over 1414903.28 frames.], batch size: 20, lr: 3.86e-04
2022-05-27 16:37:47,810 INFO [train.py:842] (3/4) Epoch 14, batch 6700, loss[loss=0.1927, simple_loss=0.2792, pruned_loss=0.05315, over 7334.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2801, pruned_loss=0.05632, over 1419076.38 frames.], batch size: 20, lr: 3.86e-04
2022-05-27 16:38:27,389 INFO [train.py:842] (3/4) Epoch 14, batch 6750, loss[loss=0.2083, simple_loss=0.2804, pruned_loss=0.06804, over 7251.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2797, pruned_loss=0.05609, over 1419793.56 frames.], batch size: 19, lr: 3.86e-04
2022-05-27 16:39:06,433 INFO [train.py:842] (3/4) Epoch 14, batch 6800, loss[loss=0.1826, simple_loss=0.2732, pruned_loss=0.04604, over 7166.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2801, pruned_loss=0.05647, over 1413320.12 frames.], batch size: 19, lr: 3.86e-04
2022-05-27 16:39:45,779 INFO [train.py:842] (3/4) Epoch 14, batch 6850, loss[loss=0.2118, simple_loss=0.2989, pruned_loss=0.06231, over 7206.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2804, pruned_loss=0.05612, over 1413931.77 frames.], batch size: 22, lr: 3.86e-04
2022-05-27 16:40:24,718 INFO [train.py:842] (3/4) Epoch 14, batch 6900, loss[loss=0.187, simple_loss=0.2699, pruned_loss=0.0521, over 7125.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2801, pruned_loss=0.05614, over 1415599.28 frames.], batch size: 17, lr: 3.86e-04
2022-05-27 16:41:03,810 INFO [train.py:842] (3/4) Epoch 14, batch 6950, loss[loss=0.1705, simple_loss=0.2674, pruned_loss=0.03674, over 6560.00 frames.], tot_loss[loss=0.197, simple_loss=0.2809, pruned_loss=0.05652, over 1418417.85 frames.], batch size: 38, lr: 3.86e-04
2022-05-27 16:41:42,274 INFO [train.py:842] (3/4) Epoch 14, batch 7000, loss[loss=0.1653, simple_loss=0.2527, pruned_loss=0.03897, over 7284.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2812, pruned_loss=0.05661, over 1419085.79 frames.], batch size: 18, lr: 3.86e-04
2022-05-27 16:42:21,234 INFO [train.py:842] (3/4) Epoch 14, batch 7050, loss[loss=0.1909, simple_loss=0.2715, pruned_loss=0.05509, over 7067.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2819, pruned_loss=0.05721, over 1418722.26 frames.], batch size: 18, lr: 3.86e-04
2022-05-27 16:43:00,192 INFO [train.py:842] (3/4) Epoch 14, batch 7100, loss[loss=0.2171, simple_loss=0.3041, pruned_loss=0.06507, over 7404.00 frames.], tot_loss[loss=0.199, simple_loss=0.2824, pruned_loss=0.05779, over 1420190.39 frames.], batch size: 18, lr: 3.86e-04
2022-05-27 16:43:39,120 INFO [train.py:842] (3/4) Epoch 14, batch 7150, loss[loss=0.1718, simple_loss=0.2531, pruned_loss=0.04523, over 7052.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2838, pruned_loss=0.05769, over 1420839.04 frames.], batch size: 18, lr: 3.86e-04
2022-05-27 16:44:18,107 INFO [train.py:842] (3/4) Epoch 14, batch 7200, loss[loss=0.2081, simple_loss=0.2947, pruned_loss=0.06076, over 7321.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2832, pruned_loss=0.05729, over 1423236.84 frames.], batch size: 21, lr: 3.86e-04
2022-05-27 16:44:57,222 INFO [train.py:842] (3/4) Epoch 14, batch 7250, loss[loss=0.2089, simple_loss=0.3081, pruned_loss=0.05481, over 7281.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2818, pruned_loss=0.05677, over 1423878.90 frames.], batch size: 25, lr: 3.86e-04
2022-05-27 16:45:35,828 INFO [train.py:842] (3/4) Epoch 14, batch 7300, loss[loss=0.1704, simple_loss=0.2557, pruned_loss=0.04254, over 7057.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2819, pruned_loss=0.0566, over 1426824.32 frames.], batch size: 18, lr: 3.85e-04
2022-05-27 16:46:14,784 INFO [train.py:842] (3/4) Epoch 14, batch 7350, loss[loss=0.209, simple_loss=0.2957, pruned_loss=0.06113, over 7061.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2818, pruned_loss=0.05634, over 1429232.77 frames.], batch size: 28, lr: 3.85e-04
2022-05-27 16:46:53,843 INFO [train.py:842] (3/4) Epoch 14, batch 7400, loss[loss=0.1791, simple_loss=0.2584, pruned_loss=0.04991, over 7295.00 frames.], tot_loss[loss=0.1966, simple_loss=0.281, pruned_loss=0.05614, over 1430580.39 frames.], batch size: 17, lr: 3.85e-04
2022-05-27 16:47:33,355 INFO [train.py:842] (3/4) Epoch 14, batch 7450, loss[loss=0.1846, simple_loss=0.2757, pruned_loss=0.04675, over 7366.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2806, pruned_loss=0.0564, over 1426390.18 frames.], batch size: 23, lr: 3.85e-04
2022-05-27 16:48:12,182 INFO [train.py:842] (3/4) Epoch 14, batch 7500, loss[loss=0.2369, simple_loss=0.3109, pruned_loss=0.08146, over 7146.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2805, pruned_loss=0.05688, over 1422891.56 frames.], batch size: 18, lr: 3.85e-04
2022-05-27 16:48:51,398 INFO [train.py:842] (3/4) Epoch 14, batch 7550, loss[loss=0.1775, simple_loss=0.2547, pruned_loss=0.05009, over 7295.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2806, pruned_loss=0.05677, over 1423166.20 frames.], batch size: 17, lr: 3.85e-04
2022-05-27 16:49:30,451 INFO [train.py:842] (3/4) Epoch 14, batch 7600, loss[loss=0.1989, simple_loss=0.2722, pruned_loss=0.0628, over 6823.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2822, pruned_loss=0.05721, over 1424266.39 frames.], batch size: 15, lr: 3.85e-04
2022-05-27 16:50:09,776 INFO [train.py:842] (3/4) Epoch 14, batch 7650, loss[loss=0.2068, simple_loss=0.3016, pruned_loss=0.05602, over 7142.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2826, pruned_loss=0.0575, over 1426459.20 frames.], batch size: 20, lr: 3.85e-04
2022-05-27 16:50:49,108 INFO [train.py:842] (3/4) Epoch 14, batch 7700, loss[loss=0.1738, simple_loss=0.251, pruned_loss=0.04836, over 7215.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2817, pruned_loss=0.05725, over 1426134.43 frames.], batch size: 16, lr: 3.85e-04
2022-05-27 16:51:28,087 INFO [train.py:842] (3/4) Epoch 14, batch 7750, loss[loss=0.2029, simple_loss=0.2788, pruned_loss=0.06349, over 7272.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2828, pruned_loss=0.05769, over 1420043.55 frames.], batch size: 18, lr: 3.85e-04
2022-05-27 16:52:06,971 INFO [train.py:842] (3/4) Epoch 14, batch 7800, loss[loss=0.1863, simple_loss=0.2566, pruned_loss=0.05798, over 7274.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2833, pruned_loss=0.05789, over 1418341.61 frames.], batch size: 18, lr: 3.85e-04
2022-05-27 16:52:45,713 INFO [train.py:842] (3/4) Epoch 14, batch 7850, loss[loss=0.1633, simple_loss=0.2405, pruned_loss=0.04303, over 7287.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2824, pruned_loss=0.05764, over 1415649.41 frames.], batch size: 18, lr: 3.85e-04
2022-05-27 16:53:24,467 INFO [train.py:842] (3/4) Epoch 14, batch 7900, loss[loss=0.2392, simple_loss=0.3192, pruned_loss=0.07964, over 7169.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2819, pruned_loss=0.05736, over 1416334.42 frames.], batch size: 26, lr: 3.85e-04
2022-05-27 16:54:03,666 INFO [train.py:842] (3/4) Epoch 14, batch 7950, loss[loss=0.2006, simple_loss=0.291, pruned_loss=0.05511, over 7214.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2827, pruned_loss=0.05789, over 1414348.86 frames.], batch size: 21, lr: 3.85e-04
2022-05-27 16:54:42,307 INFO [train.py:842] (3/4) Epoch 14, batch 8000, loss[loss=0.1752, simple_loss=0.2606, pruned_loss=0.04488, over 7143.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2827, pruned_loss=0.05824, over 1410461.27 frames.], batch size: 20, lr: 3.84e-04
2022-05-27 16:55:20,892 INFO [train.py:842] (3/4) Epoch 14, batch 8050, loss[loss=0.1799, simple_loss=0.2798, pruned_loss=0.03997, over 7414.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2846, pruned_loss=0.05945, over 1407908.83 frames.], batch size: 21, lr: 3.84e-04
2022-05-27 16:55:59,559 INFO [train.py:842] (3/4) Epoch 14, batch 8100, loss[loss=0.2067, simple_loss=0.2921, pruned_loss=0.06063, over 7432.00 frames.], tot_loss[loss=0.2, simple_loss=0.2831, pruned_loss=0.05846, over 1413413.80 frames.], batch size: 20, lr: 3.84e-04
2022-05-27 16:56:38,992 INFO [train.py:842] (3/4) Epoch 14, batch 8150, loss[loss=0.218, simple_loss=0.3028, pruned_loss=0.06653, over 7343.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2816, pruned_loss=0.05811, over 1410504.38 frames.], batch size: 22, lr: 3.84e-04
2022-05-27 16:57:17,978 INFO [train.py:842] (3/4) Epoch 14, batch 8200, loss[loss=0.1729, simple_loss=0.2492, pruned_loss=0.04829, over 7282.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2824, pruned_loss=0.05813, over 1415422.03 frames.], batch size: 17, lr: 3.84e-04
2022-05-27 16:57:56,785 INFO [train.py:842] (3/4) Epoch 14, batch 8250, loss[loss=0.2238, simple_loss=0.3092, pruned_loss=0.06917, over 7226.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2823, pruned_loss=0.05753, over 1416966.56 frames.], batch size: 21, lr: 3.84e-04
2022-05-27 16:58:35,712 INFO [train.py:842] (3/4) Epoch 14, batch 8300, loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04908, over 7214.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2807, pruned_loss=0.05671, over 1422131.61 frames.], batch size: 21, lr: 3.84e-04
2022-05-27 16:59:14,915 INFO [train.py:842] (3/4) Epoch 14, batch 8350, loss[loss=0.195, simple_loss=0.29, pruned_loss=0.05005, over 7295.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2808, pruned_loss=0.05652, over 1421034.12 frames.], batch size: 25, lr: 3.84e-04
2022-05-27 16:59:53,729 INFO [train.py:842] (3/4) Epoch 14, batch 8400, loss[loss=0.1904, simple_loss=0.2857, pruned_loss=0.04752, over 7287.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2796, pruned_loss=0.05651, over 1417713.93 frames.], batch size: 24, lr: 3.84e-04
2022-05-27 17:00:32,577 INFO [train.py:842] (3/4) Epoch 14, batch 8450, loss[loss=0.167, simple_loss=0.2617, pruned_loss=0.03617, over 7152.00 frames.], tot_loss[loss=0.1961, simple_loss=0.28, pruned_loss=0.0561, over 1419474.09 frames.], batch size: 20, lr: 3.84e-04
2022-05-27 17:01:11,196 INFO [train.py:842] (3/4) Epoch 14, batch 8500, loss[loss=0.1858, simple_loss=0.2792, pruned_loss=0.04623, over 6814.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2798, pruned_loss=0.05585, over 1420714.04 frames.], batch size: 31, lr: 3.84e-04
2022-05-27 17:01:53,188 INFO [train.py:842] (3/4) Epoch 14, batch 8550, loss[loss=0.1743, simple_loss=0.266, pruned_loss=0.04135, over 6531.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2781, pruned_loss=0.05542, over 1415199.33 frames.], batch size: 38, lr: 3.84e-04
2022-05-27 17:02:32,125 INFO [train.py:842] (3/4) Epoch 14, batch 8600, loss[loss=0.1746, simple_loss=0.2549, pruned_loss=0.04719, over 7425.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2772, pruned_loss=0.05487, over 1418204.15 frames.], batch size: 18, lr: 3.84e-04
2022-05-27 17:03:11,235 INFO [train.py:842] (3/4) Epoch 14, batch 8650, loss[loss=0.2031, simple_loss=0.2718, pruned_loss=0.06721, over 6767.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2768, pruned_loss=0.05499, over 1421085.47 frames.], batch size: 15, lr: 3.83e-04
2022-05-27 17:03:49,929 INFO [train.py:842] (3/4) Epoch 14, batch 8700, loss[loss=0.1944, simple_loss=0.2732, pruned_loss=0.05779, over 7139.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2772, pruned_loss=0.05464, over 1419584.52 frames.], batch size: 19, lr: 3.83e-04
2022-05-27 17:04:29,264 INFO [train.py:842] (3/4) Epoch 14, batch 8750, loss[loss=0.1786, simple_loss=0.2643, pruned_loss=0.04638, over 7223.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2772, pruned_loss=0.05505, over 1417101.04 frames.], batch size: 21, lr: 3.83e-04
2022-05-27 17:05:08,086 INFO [train.py:842] (3/4) Epoch 14, batch 8800, loss[loss=0.221, simple_loss=0.3121, pruned_loss=0.06494, over 7207.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2784, pruned_loss=0.05585, over 1412907.61 frames.], batch size: 21, lr: 3.83e-04
2022-05-27 17:05:47,081 INFO [train.py:842] (3/4) Epoch 14, batch 8850, loss[loss=0.1499, simple_loss=0.2359, pruned_loss=0.03194, over 7074.00 frames.], tot_loss[loss=0.1949, simple_loss=0.278, pruned_loss=0.05595, over 1405143.89 frames.], batch size: 18, lr: 3.83e-04
2022-05-27 17:06:26,082 INFO [train.py:842] (3/4) Epoch 14, batch 8900, loss[loss=0.2392, simple_loss=0.3239, pruned_loss=0.07725, over 6846.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2777, pruned_loss=0.05581, over 1404398.08 frames.], batch size: 31, lr: 3.83e-04
2022-05-27 17:07:05,144 INFO [train.py:842] (3/4) Epoch 14, batch 8950, loss[loss=0.1873, simple_loss=0.2774, pruned_loss=0.04867, over 7262.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2779, pruned_loss=0.05556, over 1406666.29 frames.], batch size: 19, lr: 3.83e-04
2022-05-27 17:07:44,233 INFO [train.py:842] (3/4) Epoch 14, batch 9000, loss[loss=0.2104, simple_loss=0.2997, pruned_loss=0.06058, over 7097.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2766, pruned_loss=0.05476, over 1407986.16 frames.], batch size: 28, lr: 3.83e-04
2022-05-27 17:07:44,234 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 17:07:53,833 INFO [train.py:871] (3/4) Epoch 14, validation: loss=0.1693, simple_loss=0.2692, pruned_loss=0.03464, over 868885.00 frames.
2022-05-27 17:08:33,177 INFO [train.py:842] (3/4) Epoch 14, batch 9050, loss[loss=0.2336, simple_loss=0.3065, pruned_loss=0.08029, over 4988.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2753, pruned_loss=0.05462, over 1398532.51 frames.], batch size: 52, lr: 3.83e-04
2022-05-27 17:09:11,599 INFO [train.py:842] (3/4) Epoch 14, batch 9100, loss[loss=0.2254, simple_loss=0.3028, pruned_loss=0.07402, over 5052.00 frames.], tot_loss[loss=0.195, simple_loss=0.2777, pruned_loss=0.0561, over 1377868.46 frames.], batch size: 52, lr: 3.83e-04
2022-05-27 17:09:49,539 INFO [train.py:842] (3/4) Epoch 14, batch 9150, loss[loss=0.2701, simple_loss=0.344, pruned_loss=0.09813, over 5130.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2831, pruned_loss=0.06034, over 1317683.79 frames.], batch size: 52, lr: 3.83e-04
2022-05-27 17:10:39,680 INFO [train.py:842] (3/4) Epoch 15, batch 0, loss[loss=0.1844, simple_loss=0.279, pruned_loss=0.04489, over 7022.00 frames.], tot_loss[loss=0.1844, simple_loss=0.279, pruned_loss=0.04489, over 7022.00 frames.], batch size: 28, lr: 3.71e-04
2022-05-27 17:11:18,907 INFO [train.py:842] (3/4) Epoch 15, batch 50, loss[loss=0.2931, simple_loss=0.3563, pruned_loss=0.1149, over 4983.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2868, pruned_loss=0.05996, over 321845.64 frames.], batch size: 53, lr: 3.71e-04
2022-05-27 17:11:57,677 INFO [train.py:842] (3/4) Epoch 15, batch 100, loss[loss=0.1594, simple_loss=0.2423, pruned_loss=0.0382, over 7163.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2826, pruned_loss=0.05721, over 568401.78 frames.], batch size: 18, lr: 3.71e-04
2022-05-27 17:12:36,385 INFO [train.py:842] (3/4) Epoch 15, batch 150, loss[loss=0.172, simple_loss=0.2615, pruned_loss=0.0412, over 7113.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2844, pruned_loss=0.05814, over 758933.94 frames.], batch size: 21, lr: 3.71e-04
2022-05-27 17:13:15,168 INFO [train.py:842] (3/4) Epoch 15, batch 200, loss[loss=0.1756, simple_loss=0.2653, pruned_loss=0.04292, over 7338.00 frames.], tot_loss[loss=0.1998, simple_loss=0.284, pruned_loss=0.05783, over 902828.09 frames.], batch size: 20, lr: 3.71e-04
2022-05-27 17:13:54,164 INFO [train.py:842] (3/4) Epoch 15, batch 250, loss[loss=0.2371, simple_loss=0.3221, pruned_loss=0.07611, over 6347.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2843, pruned_loss=0.0578, over 1020395.64 frames.], batch size: 38, lr: 3.71e-04
2022-05-27 17:14:33,347 INFO [train.py:842] (3/4) Epoch 15, batch 300, loss[loss=0.2106, simple_loss=0.2827, pruned_loss=0.06924, over 7142.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2824, pruned_loss=0.05711, over 1110862.75 frames.], batch size: 17, lr: 3.71e-04
2022-05-27 17:15:12,270 INFO [train.py:842] (3/4) Epoch 15, batch 350, loss[loss=0.1635, simple_loss=0.2368, pruned_loss=0.04512, over 7244.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2815, pruned_loss=0.0571, over 1172248.79 frames.], batch size: 16, lr: 3.70e-04
2022-05-27 17:15:51,596 INFO [train.py:842] (3/4) Epoch 15, batch 400, loss[loss=0.2, simple_loss=0.2926, pruned_loss=0.05375, over 7152.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2811, pruned_loss=0.05713, over 1227906.44 frames.], batch size: 20, lr: 3.70e-04
2022-05-27 17:16:30,732 INFO [train.py:842] (3/4) Epoch 15, batch 450, loss[loss=0.1823, simple_loss=0.2632, pruned_loss=0.05068, over 7163.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2804, pruned_loss=0.05636, over 1272456.76 frames.], batch size: 19, lr: 3.70e-04
2022-05-27 17:17:09,299 INFO [train.py:842] (3/4) Epoch 15, batch 500, loss[loss=0.204, simple_loss=0.2984, pruned_loss=0.05476, over 7424.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2813, pruned_loss=0.05686, over 1304482.28 frames.], batch size: 20, lr: 3.70e-04
2022-05-27 17:17:48,651 INFO [train.py:842] (3/4) Epoch 15, batch 550, loss[loss=0.151, simple_loss=0.2421, pruned_loss=0.02997, over 7291.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2811, pruned_loss=0.05732, over 1332920.97 frames.], batch size: 18, lr: 3.70e-04
2022-05-27 17:18:27,559 INFO [train.py:842] (3/4) Epoch 15, batch 600, loss[loss=0.2323, simple_loss=0.3264, pruned_loss=0.06913, over 7236.00 frames.], tot_loss[loss=0.1975, simple_loss=0.281, pruned_loss=0.05704, over 1355768.42 frames.], batch size: 20, lr: 3.70e-04
2022-05-27 17:19:06,359 INFO [train.py:842] (3/4) Epoch 15, batch 650, loss[loss=0.1903, simple_loss=0.2808, pruned_loss=0.04991, over 7341.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2802, pruned_loss=0.05612, over 1370676.14 frames.], batch size: 22, lr: 3.70e-04
2022-05-27 17:19:45,100 INFO [train.py:842] (3/4) Epoch 15, batch 700, loss[loss=0.204, simple_loss=0.2903, pruned_loss=0.05889, over 7329.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2804, pruned_loss=0.05608, over 1383458.22 frames.], batch size: 20, lr: 3.70e-04
2022-05-27 17:20:24,137 INFO [train.py:842] (3/4) Epoch 15, batch 750, loss[loss=0.2347, simple_loss=0.3148, pruned_loss=0.0773, over 7343.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2802, pruned_loss=0.05583, over 1391185.41 frames.], batch size: 22, lr: 3.70e-04
2022-05-27 17:21:03,149 INFO [train.py:842] (3/4) Epoch 15, batch 800, loss[loss=0.2015, simple_loss=0.2879, pruned_loss=0.05755, over 7328.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2795, pruned_loss=0.05582, over 1399895.07 frames.], batch size: 22, lr: 3.70e-04
2022-05-27 17:21:42,302 INFO [train.py:842] (3/4) Epoch 15, batch 850, loss[loss=0.1541, simple_loss=0.2407, pruned_loss=0.03378, over 7133.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2784, pruned_loss=0.05528, over 1403694.71 frames.], batch size: 17, lr: 3.70e-04
2022-05-27 17:22:21,037 INFO [train.py:842] (3/4) Epoch 15, batch 900, loss[loss=0.1377, simple_loss=0.2228, pruned_loss=0.02633, over 7266.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2782, pruned_loss=0.05524, over 1399319.25 frames.], batch size: 19, lr: 3.70e-04
2022-05-27 17:22:59,784 INFO [train.py:842] (3/4) Epoch 15, batch 950, loss[loss=0.2133, simple_loss=0.2977, pruned_loss=0.06439, over 7319.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2804, pruned_loss=0.05626, over 1407391.25 frames.], batch size: 22, lr: 3.70e-04
2022-05-27 17:23:38,678 INFO [train.py:842] (3/4) Epoch 15, batch 1000, loss[loss=0.2024, simple_loss=0.2904, pruned_loss=0.0572, over 7063.00 frames.], tot_loss[loss=0.1967, simple_loss=0.281, pruned_loss=0.05619, over 1408238.33 frames.], batch size: 28, lr: 3.70e-04
2022-05-27 17:24:17,875 INFO [train.py:842] (3/4) Epoch 15, batch 1050, loss[loss=0.1995, simple_loss=0.2874, pruned_loss=0.05583, over 7290.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2805, pruned_loss=0.05594, over 1413947.50 frames.], batch size: 18, lr: 3.70e-04
2022-05-27 17:24:57,076 INFO [train.py:842] (3/4) Epoch 15, batch 1100, loss[loss=0.1769, simple_loss=0.2468, pruned_loss=0.05345, over 7296.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2797, pruned_loss=0.05552, over 1417443.79 frames.], batch size: 17, lr: 3.69e-04
2022-05-27 17:25:36,300 INFO [train.py:842] (3/4) Epoch 15, batch 1150, loss[loss=0.1739, simple_loss=0.2749, pruned_loss=0.03649, over 7412.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2793, pruned_loss=0.0556, over 1421430.51 frames.], batch size: 21, lr: 3.69e-04
2022-05-27 17:26:15,267 INFO [train.py:842] (3/4) Epoch 15, batch 1200, loss[loss=0.155, simple_loss=0.2521, pruned_loss=0.02893, over 7426.00 frames.], tot_loss[loss=0.194, simple_loss=0.2779, pruned_loss=0.05504, over 1423314.06 frames.], batch size: 20, lr: 3.69e-04
2022-05-27 17:26:54,530 INFO [train.py:842] (3/4) Epoch 15, batch 1250, loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.04132, over 7366.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2778, pruned_loss=0.05514, over 1426738.60 frames.], batch size: 19, lr: 3.69e-04
2022-05-27 17:27:33,158 INFO [train.py:842] (3/4) Epoch 15, batch 1300, loss[loss=0.2201, simple_loss=0.3015, pruned_loss=0.06935, over 6354.00 frames.], tot_loss[loss=0.195, simple_loss=0.2784, pruned_loss=0.05577, over 1419334.63 frames.], batch size: 37, lr: 3.69e-04
2022-05-27 17:28:12,414 INFO [train.py:842] (3/4) Epoch 15, batch 1350, loss[loss=0.1655, simple_loss=0.2394, pruned_loss=0.04582, over 7021.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2789, pruned_loss=0.05567, over 1421916.94 frames.], batch size: 16, lr: 3.69e-04
2022-05-27 17:28:51,244 INFO [train.py:842] (3/4) Epoch 15, batch 1400, loss[loss=0.1899, simple_loss=0.2802, pruned_loss=0.04981, over 7295.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2789, pruned_loss=0.05538, over 1420596.09 frames.], batch size: 24, lr: 3.69e-04
2022-05-27 17:29:30,195 INFO [train.py:842] (3/4) Epoch 15, batch 1450, loss[loss=0.2242, simple_loss=0.3133, pruned_loss=0.0675, over 7378.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2798, pruned_loss=0.05583, over 1417135.56 frames.], batch size: 23, lr: 3.69e-04
2022-05-27 17:30:08,831 INFO [train.py:842] (3/4) Epoch 15, batch 1500, loss[loss=0.2105, simple_loss=0.3028, pruned_loss=0.05911, over 7145.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2797, pruned_loss=0.05561, over 1411563.01 frames.], batch size: 20, lr: 3.69e-04
2022-05-27 17:30:48,129 INFO [train.py:842] (3/4) Epoch 15, batch 1550, loss[loss=0.1628, simple_loss=0.2601, pruned_loss=0.03276, over 7117.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2784, pruned_loss=0.05484, over 1416307.11 frames.], batch size: 21, lr: 3.69e-04
2022-05-27 17:31:26,959 INFO [train.py:842] (3/4) Epoch 15, batch 1600, loss[loss=0.2052, simple_loss=0.2861, pruned_loss=0.06219, over 7416.00 frames.], tot_loss[loss=0.194, simple_loss=0.2783, pruned_loss=0.05483, over 1418494.59 frames.], batch size: 21, lr: 3.69e-04
2022-05-27 17:32:05,925 INFO [train.py:842] (3/4) Epoch 15, batch 1650, loss[loss=0.2119, simple_loss=0.298, pruned_loss=0.06289, over 7208.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2766, pruned_loss=0.05363, over 1423580.96 frames.], batch size: 23, lr: 3.69e-04
2022-05-27 17:32:44,951 INFO [train.py:842] (3/4) Epoch 15, batch 1700, loss[loss=0.1974, simple_loss=0.2856, pruned_loss=0.05456, over 7311.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2754, pruned_loss=0.05297, over 1427464.97 frames.], batch size: 25, lr: 3.69e-04
2022-05-27 17:33:24,356 INFO [train.py:842] (3/4) Epoch 15, batch 1750, loss[loss=0.2674, simple_loss=0.3371, pruned_loss=0.09889, over 7226.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2765, pruned_loss=0.0537, over 1431703.26 frames.], batch size: 28, lr: 3.69e-04
2022-05-27 17:34:03,106 INFO [train.py:842] (3/4) Epoch 15, batch 1800, loss[loss=0.1675, simple_loss=0.2448, pruned_loss=0.04515, over 7273.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2769, pruned_loss=0.05415, over 1428791.92 frames.], batch size: 17, lr: 3.68e-04
2022-05-27 17:34:42,363 INFO [train.py:842] (3/4) Epoch 15, batch 1850, loss[loss=0.1494, simple_loss=0.2371, pruned_loss=0.03088, over 7172.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2772, pruned_loss=0.05426, over 1432735.83 frames.], batch size: 18, lr: 3.68e-04
2022-05-27 17:35:21,435 INFO [train.py:842] (3/4) Epoch 15, batch 1900, loss[loss=0.1855, simple_loss=0.2751, pruned_loss=0.04796, over 7120.00 frames.], tot_loss[loss=0.1938, simple_loss=0.278, pruned_loss=0.05479, over 1431501.89 frames.], batch size: 21, lr: 3.68e-04
2022-05-27 17:36:00,639 INFO [train.py:842] (3/4) Epoch 15, batch 1950, loss[loss=0.1701, simple_loss=0.2528, pruned_loss=0.04366, over 7281.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2782, pruned_loss=0.0552, over 1431543.32 frames.], batch size: 18, lr: 3.68e-04
2022-05-27 17:36:39,372 INFO [train.py:842] (3/4) Epoch 15, batch 2000, loss[loss=0.163, simple_loss=0.2529, pruned_loss=0.03658, over 6395.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2779, pruned_loss=0.05545, over 1426889.15 frames.], batch size: 38, lr: 3.68e-04
2022-05-27 17:37:18,711 INFO [train.py:842] (3/4) Epoch 15, batch 2050, loss[loss=0.1961, simple_loss=0.2929, pruned_loss=0.04961, over 7300.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2791, pruned_loss=0.05617, over 1429103.96 frames.], batch size: 25, lr: 3.68e-04
2022-05-27 17:37:57,589 INFO [train.py:842] (3/4) Epoch 15, batch 2100, loss[loss=0.2059, simple_loss=0.2827, pruned_loss=0.06453, over 7393.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2784, pruned_loss=0.05569, over 1423840.51 frames.], batch size: 18, lr: 3.68e-04
2022-05-27 17:38:36,695 INFO [train.py:842] (3/4) Epoch 15, batch 2150, loss[loss=0.2739, simple_loss=0.349, pruned_loss=0.09938, over 7205.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2778, pruned_loss=0.05497, over 1422624.52 frames.], batch size: 22, lr: 3.68e-04
2022-05-27 17:39:15,648 INFO [train.py:842] (3/4) Epoch 15, batch 2200, loss[loss=0.2017, simple_loss=0.2734, pruned_loss=0.06495, over 7434.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2776, pruned_loss=0.0545, over 1421263.27 frames.], batch size: 20, lr: 3.68e-04
2022-05-27 17:39:54,624 INFO [train.py:842] (3/4) Epoch 15, batch 2250, loss[loss=0.1653, simple_loss=0.2585, pruned_loss=0.0361, over 7108.00 frames.], tot_loss[loss=0.193, simple_loss=0.2775, pruned_loss=0.05421, over 1421772.19 frames.], batch size: 28, lr: 3.68e-04
2022-05-27 17:40:33,444 INFO [train.py:842] (3/4) Epoch 15, batch 2300, loss[loss=0.209, simple_loss=0.2747, pruned_loss=0.07162, over 6771.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2788, pruned_loss=0.05537, over 1421636.45 frames.], batch size: 15, lr: 3.68e-04
2022-05-27 17:41:12,445 INFO [train.py:842] (3/4) Epoch 15, batch 2350, loss[loss=0.1971, simple_loss=0.2643, pruned_loss=0.06497, over 7411.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2783, pruned_loss=0.05476, over 1424263.63 frames.], batch size: 18, lr: 3.68e-04
2022-05-27 17:41:51,217 INFO [train.py:842] (3/4) Epoch 15, batch 2400, loss[loss=0.1667, simple_loss=0.2521, pruned_loss=0.04066, over 7415.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2793, pruned_loss=0.05529, over 1421804.49 frames.], batch size: 18, lr: 3.68e-04
2022-05-27 17:42:30,542 INFO [train.py:842] (3/4) Epoch 15, batch 2450, loss[loss=0.1979, simple_loss=0.2969, pruned_loss=0.04941, over 7414.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2797, pruned_loss=0.05581, over 1422513.02 frames.], batch size: 21, lr: 3.68e-04
2022-05-27 17:43:09,566 INFO [train.py:842] (3/4) Epoch 15, batch 2500, loss[loss=0.1615, simple_loss=0.2644, pruned_loss=0.02928, over 7309.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2796, pruned_loss=0.05563, over 1424400.34 frames.], batch size: 21, lr: 3.67e-04
2022-05-27 17:43:48,422 INFO [train.py:842] (3/4) Epoch 15, batch 2550, loss[loss=0.1932, simple_loss=0.2686, pruned_loss=0.05887, over 7157.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2798, pruned_loss=0.05574, over 1427682.23 frames.], batch size: 18, lr: 3.67e-04
2022-05-27 17:44:27,030 INFO [train.py:842] (3/4) Epoch 15, batch 2600, loss[loss=0.1961, simple_loss=0.2853, pruned_loss=0.05338, over 7201.00 frames.], tot_loss[loss=0.1957, simple_loss=0.28, pruned_loss=0.05574, over 1422415.41 frames.], batch size: 23, lr: 3.67e-04
2022-05-27 17:45:06,264 INFO [train.py:842] (3/4) Epoch 15, batch 2650, loss[loss=0.1817, simple_loss=0.2819, pruned_loss=0.04081, over 7298.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2791, pruned_loss=0.05458, over 1422517.83 frames.], batch size: 25, lr: 3.67e-04
2022-05-27 17:45:45,124 INFO [train.py:842] (3/4) Epoch 15, batch 2700, loss[loss=0.191, simple_loss=0.2805, pruned_loss=0.05074, over 7318.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2786, pruned_loss=0.0543, over 1424495.26 frames.], batch size: 21, lr: 3.67e-04
2022-05-27 17:46:24,220 INFO [train.py:842] (3/4) Epoch 15, batch 2750, loss[loss=0.2545, simple_loss=0.3379, pruned_loss=0.08553, over 7279.00 frames.], tot_loss[loss=0.1945, simple_loss=0.279, pruned_loss=0.05495, over 1425484.41 frames.], batch size: 24, lr: 3.67e-04
2022-05-27 17:47:03,182 INFO [train.py:842] (3/4) Epoch 15, batch 2800, loss[loss=0.177, simple_loss=0.2763, pruned_loss=0.03881, over 7146.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2778, pruned_loss=0.05436, over 1428719.15 frames.], batch size: 20, lr: 3.67e-04
2022-05-27 17:47:42,032 INFO [train.py:842] (3/4) Epoch 15, batch 2850, loss[loss=0.2057, simple_loss=0.2749, pruned_loss=0.0683, over 7228.00 frames.], tot_loss[loss=0.1933, simple_loss=0.278, pruned_loss=0.05427, over 1429450.35 frames.], batch size: 16, lr: 3.67e-04
2022-05-27 17:48:20,932 INFO [train.py:842] (3/4) Epoch 15, batch 2900, loss[loss=0.1938, simple_loss=0.2824, pruned_loss=0.05255, over 7374.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2788, pruned_loss=0.055, over 1424162.18 frames.], batch size: 23, lr: 3.67e-04
2022-05-27 17:49:00,336 INFO [train.py:842] (3/4) Epoch 15, batch 2950, loss[loss=0.1638, simple_loss=0.2576, pruned_loss=0.03499, over 7437.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2792, pruned_loss=0.05567, over 1424807.57 frames.], batch size: 20, lr: 3.67e-04
2022-05-27 17:49:39,745 INFO [train.py:842] (3/4) Epoch 15, batch 3000, loss[loss=0.2172, simple_loss=0.2919, pruned_loss=0.07124, over 7164.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2786, pruned_loss=0.05533, over 1422425.79 frames.], batch size: 19, lr: 3.67e-04
2022-05-27 17:49:39,746 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 17:49:49,311 INFO [train.py:871] (3/4) Epoch 15, validation: loss=0.1691, simple_loss=0.2695, pruned_loss=0.03437, over 868885.00 frames.
2022-05-27 17:50:28,473 INFO [train.py:842] (3/4) Epoch 15, batch 3050, loss[loss=0.1612, simple_loss=0.2409, pruned_loss=0.04071, over 7248.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2792, pruned_loss=0.05576, over 1425278.50 frames.], batch size: 16, lr: 3.67e-04
2022-05-27 17:51:07,310 INFO [train.py:842] (3/4) Epoch 15, batch 3100, loss[loss=0.1839, simple_loss=0.2663, pruned_loss=0.05075, over 7324.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2796, pruned_loss=0.05606, over 1421490.94 frames.], batch size: 20, lr: 3.67e-04
2022-05-27 17:51:46,514 INFO [train.py:842] (3/4) Epoch 15, batch 3150, loss[loss=0.1501, simple_loss=0.2347, pruned_loss=0.03272, over 7280.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2781, pruned_loss=0.05555, over 1426666.62 frames.], batch size: 17, lr: 3.67e-04
2022-05-27 17:52:25,460 INFO [train.py:842] (3/4) Epoch 15, batch 3200, loss[loss=0.2042, simple_loss=0.2962, pruned_loss=0.05605, over 7100.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2779, pruned_loss=0.05563, over 1426977.43 frames.], batch size: 28, lr: 3.66e-04
2022-05-27 17:53:04,632 INFO [train.py:842] (3/4) Epoch 15, batch 3250, loss[loss=0.2119, simple_loss=0.2819, pruned_loss=0.07093, over 7069.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2771, pruned_loss=0.05564, over 1427217.81 frames.], batch size: 18, lr: 3.66e-04
2022-05-27 17:53:43,719 INFO [train.py:842] (3/4) Epoch 15, batch 3300, loss[loss=0.1626, simple_loss=0.2462, pruned_loss=0.03944, over 7266.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2766, pruned_loss=0.0554, over 1426697.03 frames.], batch size: 17, lr: 3.66e-04
2022-05-27 17:54:22,787 INFO [train.py:842] (3/4) Epoch 15, batch 3350, loss[loss=0.1778, simple_loss=0.2641, pruned_loss=0.04574, over 7210.00 frames.], tot_loss[loss=0.195, simple_loss=0.2785, pruned_loss=0.05572, over 1426184.88 frames.], batch size: 23, lr: 3.66e-04
2022-05-27 17:55:01,367 INFO [train.py:842] (3/4) Epoch 15, batch 3400, loss[loss=0.2021, simple_loss=0.2987, pruned_loss=0.05272, over 7213.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2794, pruned_loss=0.05559, over 1422670.00 frames.], batch size: 21, lr: 3.66e-04
2022-05-27 17:55:40,242 INFO [train.py:842] (3/4) Epoch 15, batch 3450, loss[loss=0.2169, simple_loss=0.2961, pruned_loss=0.06879, over 7017.00 frames.], tot_loss[loss=0.195, simple_loss=0.2792, pruned_loss=0.05541, over 1421753.66 frames.], batch size: 28, lr: 3.66e-04
2022-05-27 17:56:19,156 INFO [train.py:842] (3/4) Epoch 15, batch 3500, loss[loss=0.1823, simple_loss=0.2743, pruned_loss=0.04509, over 7196.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2787, pruned_loss=0.05507, over 1426303.11 frames.], batch size: 26, lr: 3.66e-04
2022-05-27 17:56:58,066 INFO [train.py:842] (3/4) Epoch 15, batch 3550, loss[loss=0.2111, simple_loss=0.2905, pruned_loss=0.06584, over 7221.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2791, pruned_loss=0.05512, over 1427885.03 frames.], batch size: 20, lr: 3.66e-04
2022-05-27 17:57:36,718 INFO [train.py:842] (3/4) Epoch 15, batch 3600, loss[loss=0.1941, simple_loss=0.284, pruned_loss=0.05211, over 7314.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2801, pruned_loss=0.05603, over 1424360.90 frames.], batch size: 21, lr: 3.66e-04
2022-05-27 17:58:15,802 INFO [train.py:842] (3/4) Epoch 15, batch 3650, loss[loss=0.1754, simple_loss=0.265, pruned_loss=0.04293, over 7267.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2806, pruned_loss=0.0563, over 1424870.11 frames.], batch size: 19, lr: 3.66e-04
2022-05-27 17:58:54,665 INFO [train.py:842] (3/4) Epoch 15, batch 3700, loss[loss=0.2694, simple_loss=0.3313, pruned_loss=0.1037, over 7438.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2799, pruned_loss=0.05563, over 1422748.80 frames.], batch size: 20, lr: 3.66e-04
2022-05-27 17:59:34,174 INFO [train.py:842] (3/4) Epoch 15, batch 3750, loss[loss=0.2563, simple_loss=0.3299, pruned_loss=0.09132, over 4907.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2791, pruned_loss=0.05556, over 1423928.33 frames.], batch size: 52, lr: 3.66e-04
2022-05-27 18:00:12,959 INFO [train.py:842] (3/4) Epoch 15, batch 3800, loss[loss=0.1764, simple_loss=0.2589, pruned_loss=0.04697, over 7065.00 frames.], tot_loss[loss=0.1961, simple_loss=0.28, pruned_loss=0.05606, over 1426293.18 frames.], batch size: 18, lr: 3.66e-04
2022-05-27 18:00:51,719 INFO [train.py:842] (3/4) Epoch 15, batch 3850, loss[loss=0.1971, simple_loss=0.2875, pruned_loss=0.05337, over 7235.00 frames.], tot_loss[loss=0.1968, simple_loss=0.281, pruned_loss=0.05625, over 1428747.99 frames.], batch size: 20, lr: 3.66e-04
2022-05-27 18:01:30,655 INFO [train.py:842] (3/4) Epoch 15, batch 3900, loss[loss=0.1836, simple_loss=0.2697, pruned_loss=0.04874, over 7261.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2799, pruned_loss=0.05601, over 1425702.47 frames.], batch size: 19, lr: 3.66e-04
2022-05-27 18:02:19,748 INFO [train.py:842] (3/4) Epoch 15, batch 3950, loss[loss=0.2282, simple_loss=0.3199, pruned_loss=0.06826, over 7141.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2791, pruned_loss=0.05565, over 1421635.86 frames.], batch size: 20, lr: 3.65e-04
2022-05-27 18:02:58,486 INFO [train.py:842] (3/4) Epoch 15, batch 4000, loss[loss=0.1863, simple_loss=0.2562, pruned_loss=0.05816, over 7146.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2797, pruned_loss=0.0564, over 1421697.79 frames.], batch size: 17, lr: 3.65e-04
2022-05-27 18:03:37,549 INFO [train.py:842] (3/4) Epoch 15, batch 4050, loss[loss=0.1929, simple_loss=0.2818, pruned_loss=0.05198, over 6369.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2804, pruned_loss=0.05635, over 1425340.67 frames.], batch size: 37, lr: 3.65e-04
2022-05-27 18:04:16,197 INFO [train.py:842] (3/4) Epoch 15, batch 4100, loss[loss=0.2078, simple_loss=0.2912, pruned_loss=0.06218, over 7410.00 frames.], tot_loss[loss=0.1959, simple_loss=0.28, pruned_loss=0.05587, over 1421189.79 frames.], batch size: 21, lr: 3.65e-04
2022-05-27 18:04:55,293 INFO [train.py:842] (3/4) Epoch 15, batch 4150, loss[loss=0.1631, simple_loss=0.2399, pruned_loss=0.04312, over 7385.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2794, pruned_loss=0.05522, over 1422526.43 frames.], batch size: 18, lr: 3.65e-04
2022-05-27 18:05:33,945 INFO [train.py:842] (3/4) Epoch 15, batch 4200, loss[loss=0.2005, simple_loss=0.2891, pruned_loss=0.05601, over 7360.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2799, pruned_loss=0.05598, over 1416400.01 frames.], batch size: 23, lr: 3.65e-04
2022-05-27 18:06:13,508 INFO [train.py:842] (3/4) Epoch 15, batch 4250, loss[loss=0.2076, simple_loss=0.3033, pruned_loss=0.05589, over 7284.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2786, pruned_loss=0.05516, over 1417094.61 frames.], batch size: 24, lr: 3.65e-04
2022-05-27 18:06:52,325 INFO [train.py:842] (3/4) Epoch 15, batch 4300, loss[loss=0.1899, simple_loss=0.2851, pruned_loss=0.04732, over 7314.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2775, pruned_loss=0.05496, over 1414668.52 frames.], batch size: 25, lr: 3.65e-04
2022-05-27 18:07:31,767 INFO [train.py:842] (3/4) Epoch 15, batch 4350, loss[loss=0.1607, simple_loss=0.2488, pruned_loss=0.0363, over 7162.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2777, pruned_loss=0.05494, over 1419012.17 frames.], batch size: 18, lr: 3.65e-04
2022-05-27 18:08:10,559 INFO [train.py:842] (3/4) Epoch 15, batch 4400, loss[loss=0.2042, simple_loss=0.2796, pruned_loss=0.06444, over 7273.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2786, pruned_loss=0.05512, over 1418535.64 frames.], batch size: 18, lr: 3.65e-04
2022-05-27 18:08:49,787 INFO [train.py:842] (3/4) Epoch 15, batch 4450, loss[loss=0.1846, simple_loss=0.2824, pruned_loss=0.04338, over 7420.00 frames.], tot_loss[loss=0.1952, simple_loss=0.279, pruned_loss=0.05568, over 1419909.58 frames.], batch size: 21, lr: 3.65e-04
2022-05-27 18:09:28,907 INFO [train.py:842] (3/4) Epoch 15, batch 4500, loss[loss=0.2181, simple_loss=0.3157, pruned_loss=0.06024, over 7287.00 frames.], tot_loss[loss=0.1961, simple_loss=0.28, pruned_loss=0.05609, over 1423034.29 frames.], batch size: 25, lr: 3.65e-04
2022-05-27 18:10:07,903 INFO [train.py:842] (3/4) Epoch 15, batch 4550, loss[loss=0.1591, simple_loss=0.25, pruned_loss=0.03411, over 7320.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2797, pruned_loss=0.05498, over 1425622.91 frames.], batch size: 20, lr: 3.65e-04
2022-05-27 18:10:46,895 INFO [train.py:842] (3/4) Epoch 15, batch 4600, loss[loss=0.2306, simple_loss=0.3118, pruned_loss=0.07474, over 7217.00 frames.], tot_loss[loss=0.1945, simple_loss=0.279, pruned_loss=0.055, over 1426577.75 frames.], batch size: 21, lr: 3.65e-04
2022-05-27 18:11:26,089 INFO [train.py:842] (3/4) Epoch 15, batch 4650, loss[loss=0.1853, simple_loss=0.2692, pruned_loss=0.05073, over 6696.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2797, pruned_loss=0.0556, over 1426005.97 frames.], batch size: 31, lr: 3.64e-04
2022-05-27 18:12:04,843 INFO [train.py:842] (3/4) Epoch 15, batch 4700, loss[loss=0.1611, simple_loss=0.2524, pruned_loss=0.03491, over 7142.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2792, pruned_loss=0.05497, over 1428935.21 frames.], batch size: 20, lr: 3.64e-04
2022-05-27 18:12:44,043 INFO [train.py:842] (3/4) Epoch 15, batch 4750, loss[loss=0.2031, simple_loss=0.2814, pruned_loss=0.06237, over 7277.00 frames.], tot_loss[loss=0.196, simple_loss=0.2804, pruned_loss=0.05574, over 1429258.47 frames.], batch size: 17, lr: 3.64e-04
2022-05-27 18:13:22,839 INFO [train.py:842] (3/4) Epoch 15, batch 4800, loss[loss=0.1764, simple_loss=0.2735, pruned_loss=0.03961, over 6804.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2791, pruned_loss=0.05511, over 1429102.99 frames.], batch size: 31, lr: 3.64e-04
2022-05-27 18:14:02,071 INFO [train.py:842] (3/4) Epoch 15, batch 4850, loss[loss=0.227, simple_loss=0.3088, pruned_loss=0.0726, over 7023.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2784, pruned_loss=0.05531, over 1428102.70 frames.], batch size: 28, lr: 3.64e-04
2022-05-27 18:14:40,911 INFO [train.py:842] (3/4) Epoch 15, batch 4900, loss[loss=0.1994, simple_loss=0.2832, pruned_loss=0.05785, over 7157.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2786, pruned_loss=0.05522, over 1430492.33 frames.], batch size: 19, lr: 3.64e-04
2022-05-27 18:15:20,269 INFO [train.py:842] (3/4) Epoch 15, batch 4950, loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04118, over 7162.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2785, pruned_loss=0.05538, over 1431341.62 frames.], batch size: 19, lr: 3.64e-04
2022-05-27 18:15:58,886 INFO [train.py:842] (3/4) Epoch 15, batch 5000, loss[loss=0.254, simple_loss=0.3293, pruned_loss=0.08933, over 7140.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2784, pruned_loss=0.05507, over 1429624.13 frames.], batch size: 26, lr: 3.64e-04
2022-05-27 18:16:38,076 INFO [train.py:842] (3/4) Epoch 15, batch 5050, loss[loss=0.1869, simple_loss=0.2862, pruned_loss=0.04387, over 7231.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2779, pruned_loss=0.05465, over 1431170.74 frames.], batch size: 20, lr: 3.64e-04
2022-05-27 18:17:17,312 INFO [train.py:842] (3/4) Epoch 15, batch 5100, loss[loss=0.1743, simple_loss=0.2647, pruned_loss=0.04196, over 7435.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2773, pruned_loss=0.05458, over 1429970.38 frames.], batch size: 20, lr: 3.64e-04
2022-05-27 18:17:56,533 INFO [train.py:842] (3/4) Epoch 15, batch 5150, loss[loss=0.187, simple_loss=0.2828, pruned_loss=0.04563, over 7380.00 frames.], tot_loss[loss=0.194, simple_loss=0.2782, pruned_loss=0.05484, over 1426792.56 frames.], batch size: 23, lr: 3.64e-04
2022-05-27 18:18:35,560 INFO [train.py:842] (3/4) Epoch 15, batch 5200, loss[loss=0.2115, simple_loss=0.2947, pruned_loss=0.06414, over 6743.00 frames.], tot_loss[loss=0.194, simple_loss=0.2779, pruned_loss=0.05504, over 1426205.54 frames.], batch size: 31, lr: 3.64e-04
2022-05-27 18:19:14,519 INFO [train.py:842] (3/4) Epoch 15, batch 5250, loss[loss=0.1813, simple_loss=0.2618, pruned_loss=0.05037, over 7155.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2784, pruned_loss=0.05527, over 1425013.47 frames.], batch size: 19, lr: 3.64e-04
2022-05-27 18:19:53,369 INFO [train.py:842] (3/4) Epoch 15, batch 5300, loss[loss=0.1779, simple_loss=0.2637, pruned_loss=0.046, over 7324.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2787, pruned_loss=0.05585, over 1419788.40 frames.], batch size: 20, lr: 3.64e-04
2022-05-27 18:20:32,612 INFO [train.py:842] (3/4) Epoch 15, batch 5350, loss[loss=0.1653, simple_loss=0.2563, pruned_loss=0.03719, over 7256.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2779, pruned_loss=0.05511, over 1420768.37 frames.], batch size: 19, lr: 3.64e-04
2022-05-27 18:21:11,500 INFO [train.py:842] (3/4) Epoch 15, batch 5400, loss[loss=0.1858, simple_loss=0.265, pruned_loss=0.05334, over 7365.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2769, pruned_loss=0.05464, over 1422229.67 frames.], batch size: 19, lr: 3.63e-04
2022-05-27 18:21:50,503 INFO [train.py:842] (3/4) Epoch 15, batch 5450, loss[loss=0.2045, simple_loss=0.289, pruned_loss=0.05997, over 7326.00 frames.], tot_loss[loss=0.1926, simple_loss=0.276, pruned_loss=0.05459, over 1426756.04 frames.], batch size: 22, lr: 3.63e-04
2022-05-27 18:22:29,609 INFO [train.py:842] (3/4) Epoch 15, batch 5500, loss[loss=0.215, simple_loss=0.295, pruned_loss=0.06754, over 7221.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2765, pruned_loss=0.05481, over 1425702.84 frames.], batch size: 22, lr: 3.63e-04
2022-05-27 18:23:08,891 INFO [train.py:842] (3/4) Epoch 15, batch 5550, loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.02831, over 7259.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2765, pruned_loss=0.05444, over 1428497.68 frames.], batch size: 19, lr: 3.63e-04
2022-05-27 18:23:47,682 INFO [train.py:842] (3/4) Epoch 15, batch 5600, loss[loss=0.2132, simple_loss=0.2963, pruned_loss=0.06503, over 7202.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2782, pruned_loss=0.05532, over 1426490.93 frames.], batch size: 22, lr: 3.63e-04
2022-05-27 18:24:26,887 INFO [train.py:842] (3/4) Epoch 15, batch 5650, loss[loss=0.2122, simple_loss=0.2814, pruned_loss=0.07148, over 7160.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2773, pruned_loss=0.05552, over 1424830.58 frames.], batch size: 18, lr: 3.63e-04
2022-05-27 18:25:05,580 INFO [train.py:842] (3/4) Epoch 15, batch 5700, loss[loss=0.1816, simple_loss=0.2687, pruned_loss=0.04724, over 7440.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2782, pruned_loss=0.05544, over 1421577.07 frames.], batch size: 20, lr: 3.63e-04
2022-05-27 18:25:44,765 INFO [train.py:842] (3/4) Epoch 15, batch 5750, loss[loss=0.2094, simple_loss=0.2865, pruned_loss=0.0661, over 7074.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2787, pruned_loss=0.05545, over 1423983.66 frames.], batch size: 28, lr: 3.63e-04
2022-05-27 18:26:23,932 INFO [train.py:842] (3/4) Epoch 15, batch 5800, loss[loss=0.2247, simple_loss=0.2999, pruned_loss=0.07479, over 7327.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2788, pruned_loss=0.05547, over 1426784.78 frames.], batch size: 20, lr: 3.63e-04
2022-05-27 18:27:03,402 INFO [train.py:842] (3/4) Epoch 15, batch 5850, loss[loss=0.19, simple_loss=0.2716, pruned_loss=0.05417, over 7351.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2784, pruned_loss=0.05552, over 1426153.92 frames.], batch size: 19, lr: 3.63e-04
2022-05-27 18:27:42,361 INFO [train.py:842] (3/4) Epoch 15, batch 5900, loss[loss=0.1772, simple_loss=0.2621, pruned_loss=0.0461, over 7142.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2777, pruned_loss=0.05547, over 1425309.84 frames.], batch size: 20, lr: 3.63e-04
2022-05-27 18:28:21,538 INFO [train.py:842] (3/4) Epoch 15, batch 5950, loss[loss=0.174, simple_loss=0.2618, pruned_loss=0.04312, over 7330.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2794, pruned_loss=0.05689, over 1423049.66 frames.], batch size: 20, lr: 3.63e-04
2022-05-27 18:29:00,326 INFO [train.py:842] (3/4) Epoch 15, batch 6000, loss[loss=0.1973, simple_loss=0.2786, pruned_loss=0.05803, over 7276.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2801, pruned_loss=0.05704, over 1419598.49 frames.], batch size: 18, lr: 3.63e-04
2022-05-27 18:29:00,327 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 18:29:10,459 INFO [train.py:871] (3/4) Epoch 15, validation: loss=0.1678, simple_loss=0.2677, pruned_loss=0.03392, over 868885.00 frames.
2022-05-27 18:29:49,709 INFO [train.py:842] (3/4) Epoch 15, batch 6050, loss[loss=0.1803, simple_loss=0.2763, pruned_loss=0.04213, over 7141.00 frames.], tot_loss[loss=0.196, simple_loss=0.2794, pruned_loss=0.05631, over 1423566.85 frames.], batch size: 28, lr: 3.63e-04
2022-05-27 18:30:28,769 INFO [train.py:842] (3/4) Epoch 15, batch 6100, loss[loss=0.2068, simple_loss=0.2856, pruned_loss=0.06402, over 7222.00 frames.], tot_loss[loss=0.196, simple_loss=0.2791, pruned_loss=0.05641, over 1425886.39 frames.], batch size: 21, lr: 3.63e-04
2022-05-27 18:31:08,009 INFO [train.py:842] (3/4) Epoch 15, batch 6150, loss[loss=0.2502, simple_loss=0.3286, pruned_loss=0.08588, over 5177.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2789, pruned_loss=0.0561, over 1426290.24 frames.], batch size: 52, lr: 3.62e-04
2022-05-27 18:31:47,193 INFO [train.py:842] (3/4) Epoch 15, batch 6200, loss[loss=0.1965, simple_loss=0.2794, pruned_loss=0.05684, over 7204.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2784, pruned_loss=0.05569, over 1423714.06 frames.], batch size: 23, lr: 3.62e-04
2022-05-27 18:32:26,321 INFO [train.py:842] (3/4) Epoch 15, batch 6250, loss[loss=0.1757, simple_loss=0.2709, pruned_loss=0.04026, over 7204.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2796, pruned_loss=0.05632, over 1420035.44 frames.], batch size: 22, lr: 3.62e-04
2022-05-27 18:33:04,931 INFO [train.py:842] (3/4) Epoch 15, batch 6300, loss[loss=0.2125, simple_loss=0.2976, pruned_loss=0.06373, over 7208.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2799, pruned_loss=0.05646, over 1419285.85 frames.], batch size: 26, lr: 3.62e-04
2022-05-27 18:33:54,404 INFO [train.py:842] (3/4) Epoch 15, batch 6350, loss[loss=0.1612, simple_loss=0.2373, pruned_loss=0.04256, over 6851.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2804, pruned_loss=0.05651, over 1421088.06 frames.], batch size: 15, lr: 3.62e-04
2022-05-27 18:34:43,523 INFO [train.py:842] (3/4) Epoch 15, batch 6400, loss[loss=0.2076, simple_loss=0.2838, pruned_loss=0.06572, over 7054.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2799, pruned_loss=0.05642, over 1418494.58 frames.], batch size: 18, lr: 3.62e-04
2022-05-27 18:35:22,931 INFO [train.py:842] (3/4) Epoch 15, batch 6450, loss[loss=0.1846, simple_loss=0.2701, pruned_loss=0.04949, over 7118.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2786, pruned_loss=0.05518, over 1422561.84 frames.], batch size: 21, lr: 3.62e-04
2022-05-27 18:36:11,944 INFO [train.py:842] (3/4) Epoch 15, batch 6500, loss[loss=0.2142, simple_loss=0.295, pruned_loss=0.06668, over 6711.00 frames.], tot_loss[loss=0.1946, simple_loss=0.279, pruned_loss=0.05511, over 1418215.55 frames.], batch size: 31, lr: 3.62e-04
2022-05-27 18:36:50,717 INFO [train.py:842] (3/4) Epoch 15, batch 6550, loss[loss=0.2155, simple_loss=0.3001, pruned_loss=0.06541, over 6646.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2812, pruned_loss=0.05658, over 1421434.51 frames.], batch size: 31, lr: 3.62e-04
2022-05-27 18:37:29,208 INFO [train.py:842] (3/4) Epoch 15, batch 6600, loss[loss=0.2005, simple_loss=0.2892, pruned_loss=0.05595, over 7227.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2812, pruned_loss=0.05686, over 1417912.08 frames.], batch size: 20, lr: 3.62e-04
2022-05-27 18:38:08,159 INFO [train.py:842] (3/4) Epoch 15, batch 6650, loss[loss=0.2151, simple_loss=0.3038, pruned_loss=0.06319, over 7293.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2803, pruned_loss=0.0562, over 1420124.11 frames.], batch size: 24, lr: 3.62e-04
2022-05-27 18:38:47,068 INFO [train.py:842] (3/4) Epoch 15, batch 6700, loss[loss=0.1605, simple_loss=0.2426, pruned_loss=0.03923, over 7166.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2792, pruned_loss=0.05528, over 1421373.17 frames.], batch size: 18, lr: 3.62e-04
2022-05-27 18:39:26,022 INFO [train.py:842] (3/4) Epoch 15, batch 6750, loss[loss=0.2116, simple_loss=0.2837, pruned_loss=0.06973, over 7285.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2806, pruned_loss=0.05584, over 1424319.24 frames.], batch size: 18, lr: 3.62e-04
2022-05-27 18:40:05,048 INFO [train.py:842] (3/4) Epoch 15, batch 6800, loss[loss=0.1554, simple_loss=0.2379, pruned_loss=0.03647, over 7286.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2799, pruned_loss=0.05525, over 1426746.83 frames.], batch size: 18, lr: 3.62e-04
2022-05-27 18:40:44,187 INFO [train.py:842] (3/4) Epoch 15, batch 6850, loss[loss=0.2261, simple_loss=0.3097, pruned_loss=0.07131, over 7369.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2792, pruned_loss=0.055, over 1425251.01 frames.], batch size: 23, lr: 3.62e-04
2022-05-27 18:41:23,585 INFO [train.py:842] (3/4) Epoch 15, batch 6900, loss[loss=0.1537, simple_loss=0.2415, pruned_loss=0.03296, over 7136.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2779, pruned_loss=0.05426, over 1428115.07 frames.], batch size: 17, lr: 3.61e-04
2022-05-27 18:42:02,763 INFO [train.py:842] (3/4) Epoch 15, batch 6950, loss[loss=0.1904, simple_loss=0.2864, pruned_loss=0.04726, over 6760.00 frames.], tot_loss[loss=0.1944, simple_loss=0.279, pruned_loss=0.05493, over 1426998.21 frames.], batch size: 31, lr: 3.61e-04
2022-05-27 18:42:41,953 INFO [train.py:842] (3/4) Epoch 15, batch 7000, loss[loss=0.1645, simple_loss=0.2555, pruned_loss=0.03679, over 7231.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2789, pruned_loss=0.05527, over 1428559.66 frames.], batch size: 20, lr: 3.61e-04
2022-05-27 18:43:21,067 INFO [train.py:842] (3/4) Epoch 15, batch 7050, loss[loss=0.1995, simple_loss=0.2838, pruned_loss=0.05761, over 7191.00 frames.], tot_loss[loss=0.1947, simple_loss=0.279, pruned_loss=0.05524, over 1427478.52 frames.], batch size: 22, lr: 3.61e-04
2022-05-27 18:43:59,645 INFO [train.py:842] (3/4) Epoch 15, batch 7100, loss[loss=0.1926, simple_loss=0.2728, pruned_loss=0.05619, over 7373.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2801, pruned_loss=0.05579, over 1429459.15 frames.], batch size: 23, lr: 3.61e-04
2022-05-27 18:44:38,579 INFO [train.py:842] (3/4) Epoch 15, batch 7150, loss[loss=0.168, simple_loss=0.2593, pruned_loss=0.03839, over 7235.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2795, pruned_loss=0.05535, over 1425110.95 frames.], batch size: 20, lr: 3.61e-04
2022-05-27 18:45:17,394 INFO [train.py:842] (3/4) Epoch 15, batch 7200, loss[loss=0.1916, simple_loss=0.2781, pruned_loss=0.05259, over 7362.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2804, pruned_loss=0.05562, over 1426258.19 frames.], batch size: 19, lr: 3.61e-04
2022-05-27 18:45:56,709 INFO [train.py:842] (3/4) Epoch 15, batch 7250, loss[loss=0.2251, simple_loss=0.3076, pruned_loss=0.07131, over 7208.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2798, pruned_loss=0.05553, over 1425233.69 frames.], batch size: 22, lr: 3.61e-04
2022-05-27 18:46:35,259 INFO [train.py:842] (3/4) Epoch 15, batch 7300, loss[loss=0.2258, simple_loss=0.3089, pruned_loss=0.0713, over 7287.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2789, pruned_loss=0.05514, over 1424388.94 frames.], batch size: 24, lr: 3.61e-04
2022-05-27 18:47:17,003 INFO [train.py:842] (3/4) Epoch 15, batch 7350, loss[loss=0.1957, simple_loss=0.2845, pruned_loss=0.05347, over 7375.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2792, pruned_loss=0.05533, over 1425168.60 frames.], batch size: 23, lr: 3.61e-04
2022-05-27 18:47:55,679 INFO [train.py:842] (3/4) Epoch 15, batch 7400, loss[loss=0.2358, simple_loss=0.3257, pruned_loss=0.07295, over 6222.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2799, pruned_loss=0.05567, over 1427020.56 frames.], batch size: 37, lr: 3.61e-04
2022-05-27 18:48:34,728 INFO [train.py:842] (3/4) Epoch 15, batch 7450, loss[loss=0.172, simple_loss=0.2546, pruned_loss=0.04471, over 7328.00 frames.], tot_loss[loss=0.1959, simple_loss=0.28, pruned_loss=0.0559, over 1426808.43 frames.], batch size: 20, lr: 3.61e-04
2022-05-27 18:49:13,771 INFO [train.py:842] (3/4) Epoch 15, batch 7500, loss[loss=0.1723, simple_loss=0.2554, pruned_loss=0.04454, over 7446.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2792, pruned_loss=0.05517, over 1427783.01 frames.], batch size: 19, lr: 3.61e-04
2022-05-27 18:49:52,803 INFO [train.py:842] (3/4) Epoch 15, batch 7550, loss[loss=0.1863, simple_loss=0.2836, pruned_loss=0.04444, over 6799.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2779, pruned_loss=0.05439, over 1424564.64 frames.], batch size: 31, lr: 3.61e-04
2022-05-27 18:50:31,976 INFO [train.py:842] (3/4) Epoch 15, batch 7600, loss[loss=0.1553, simple_loss=0.2452, pruned_loss=0.03271, over 7351.00 frames.], tot_loss[loss=0.1939, simple_loss=0.278, pruned_loss=0.05488, over 1423225.95 frames.], batch size: 19, lr: 3.61e-04
2022-05-27 18:51:10,947 INFO [train.py:842] (3/4) Epoch 15, batch 7650, loss[loss=0.1961, simple_loss=0.2883, pruned_loss=0.05195, over 7086.00 frames.], tot_loss[loss=0.1961, simple_loss=0.28, pruned_loss=0.05609, over 1420708.89 frames.], batch size: 28, lr: 3.60e-04
2022-05-27 18:51:49,847 INFO [train.py:842] (3/4) Epoch 15, batch 7700, loss[loss=0.1752, simple_loss=0.2605, pruned_loss=0.04491, over 7077.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2785, pruned_loss=0.0553, over 1420488.43 frames.], batch size: 28, lr: 3.60e-04
2022-05-27 18:52:29,100 INFO [train.py:842] (3/4) Epoch 15, batch 7750, loss[loss=0.2113, simple_loss=0.2867, pruned_loss=0.06797, over 6673.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2787, pruned_loss=0.05543, over 1424838.49 frames.], batch size: 31, lr: 3.60e-04
2022-05-27 18:53:07,851 INFO [train.py:842] (3/4) Epoch 15, batch 7800, loss[loss=0.1623, simple_loss=0.2305, pruned_loss=0.04706, over 7290.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2781, pruned_loss=0.05538, over 1417919.16 frames.], batch size: 17, lr: 3.60e-04
2022-05-27 18:53:47,094 INFO [train.py:842] (3/4) Epoch 15, batch 7850, loss[loss=0.1929, simple_loss=0.2572, pruned_loss=0.06426, over 7007.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2786, pruned_loss=0.05513, over 1419751.20 frames.], batch size: 16, lr: 3.60e-04
2022-05-27 18:54:25,895 INFO [train.py:842] (3/4) Epoch 15, batch 7900, loss[loss=0.1927, simple_loss=0.2777, pruned_loss=0.05384, over 7394.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2783, pruned_loss=0.0551, over 1422774.35 frames.], batch size: 23, lr: 3.60e-04
2022-05-27 18:55:04,762 INFO [train.py:842] (3/4) Epoch 15, batch 7950, loss[loss=0.1982, simple_loss=0.2975, pruned_loss=0.0495, over 7188.00 frames.], tot_loss[loss=0.1937, simple_loss=0.278, pruned_loss=0.05472, over 1422735.39 frames.], batch size: 23, lr: 3.60e-04
2022-05-27 18:55:44,031 INFO [train.py:842] (3/4) Epoch 15, batch 8000, loss[loss=0.1647, simple_loss=0.2457, pruned_loss=0.04185, over 7207.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2783, pruned_loss=0.05543, over 1422938.55 frames.], batch size: 16, lr: 3.60e-04
2022-05-27 18:56:22,911 INFO [train.py:842] (3/4) Epoch 15, batch 8050, loss[loss=0.2053, simple_loss=0.2912, pruned_loss=0.05973, over 7293.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2777, pruned_loss=0.05471, over 1415864.47 frames.], batch size: 25, lr: 3.60e-04
2022-05-27 18:57:02,140 INFO [train.py:842] (3/4) Epoch 15, batch 8100, loss[loss=0.1663, simple_loss=0.2656, pruned_loss=0.03345, over 7231.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2791, pruned_loss=0.05529, over 1422761.62 frames.], batch size: 20, lr: 3.60e-04
2022-05-27 18:57:41,265 INFO [train.py:842] (3/4) Epoch 15, batch 8150, loss[loss=0.1829, simple_loss=0.2735, pruned_loss=0.04616, over 7327.00 frames.], tot_loss[loss=0.194, simple_loss=0.2783, pruned_loss=0.05491, over 1420537.97 frames.], batch size: 20, lr: 3.60e-04
2022-05-27 18:58:20,254 INFO [train.py:842] (3/4) Epoch 15, batch 8200, loss[loss=0.1824, simple_loss=0.2758, pruned_loss=0.04451, over 7262.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2777, pruned_loss=0.05465, over 1422684.58 frames.], batch size: 19, lr: 3.60e-04
2022-05-27 18:58:59,240 INFO [train.py:842] (3/4) Epoch 15, batch 8250, loss[loss=0.1916, simple_loss=0.2711, pruned_loss=0.05611, over 7254.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2785, pruned_loss=0.05547, over 1421868.77 frames.], batch size: 19, lr: 3.60e-04
2022-05-27 18:59:37,867 INFO [train.py:842] (3/4) Epoch 15, batch 8300, loss[loss=0.1909, simple_loss=0.2728, pruned_loss=0.05449, over 7332.00 frames.], tot_loss[loss=0.1943, simple_loss=0.278, pruned_loss=0.05531, over 1423707.37 frames.], batch size: 20, lr: 3.60e-04
2022-05-27 19:00:17,030 INFO [train.py:842] (3/4) Epoch 15, batch 8350, loss[loss=0.1641, simple_loss=0.246, pruned_loss=0.04108, over 7353.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2771, pruned_loss=0.05487, over 1423834.60 frames.], batch size: 19, lr: 3.60e-04
2022-05-27 19:00:56,007 INFO [train.py:842] (3/4) Epoch 15, batch 8400, loss[loss=0.18, simple_loss=0.2795, pruned_loss=0.04022, over 7195.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2761, pruned_loss=0.05433, over 1424880.51 frames.], batch size: 26, lr: 3.59e-04
2022-05-27 19:01:34,940 INFO [train.py:842] (3/4) Epoch 15, batch 8450, loss[loss=0.2371, simple_loss=0.3198, pruned_loss=0.07717, over 7149.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2783, pruned_loss=0.05561, over 1423575.48 frames.], batch size: 20, lr: 3.59e-04
2022-05-27 19:02:13,505 INFO [train.py:842] (3/4) Epoch 15, batch 8500, loss[loss=0.2009, simple_loss=0.2742, pruned_loss=0.06382, over 7160.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2783, pruned_loss=0.05508, over 1420862.33 frames.], batch size: 18, lr: 3.59e-04
2022-05-27 19:02:52,546 INFO [train.py:842] (3/4) Epoch 15, batch 8550, loss[loss=0.2183, simple_loss=0.2996, pruned_loss=0.0685, over 7116.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2786, pruned_loss=0.055, over 1422458.69 frames.], batch size: 21, lr: 3.59e-04
2022-05-27 19:03:31,280 INFO [train.py:842] (3/4) Epoch 15, batch 8600, loss[loss=0.1888, simple_loss=0.2818, pruned_loss=0.04787, over 7320.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2793, pruned_loss=0.05553, over 1419001.83 frames.], batch size: 21, lr: 3.59e-04
2022-05-27 19:04:10,125 INFO [train.py:842] (3/4) Epoch 15, batch 8650, loss[loss=0.1842, simple_loss=0.2748, pruned_loss=0.04675, over 7331.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2803, pruned_loss=0.05621, over 1417546.95 frames.], batch size: 21, lr: 3.59e-04
2022-05-27 19:04:49,124 INFO [train.py:842] (3/4) Epoch 15, batch 8700, loss[loss=0.1921, simple_loss=0.273, pruned_loss=0.05566, over 7209.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2791, pruned_loss=0.05532, over 1421934.38 frames.], batch size: 22, lr: 3.59e-04
2022-05-27 19:05:28,375 INFO [train.py:842] (3/4) Epoch 15, batch 8750, loss[loss=0.2076, simple_loss=0.29, pruned_loss=0.06262, over 6813.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2776, pruned_loss=0.05491, over 1421326.61 frames.], batch size: 31, lr: 3.59e-04
2022-05-27 19:06:07,395 INFO [train.py:842] (3/4) Epoch 15, batch 8800, loss[loss=0.2374, simple_loss=0.3118, pruned_loss=0.08152, over 7413.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2778, pruned_loss=0.05533, over 1420418.24 frames.], batch size: 21, lr: 3.59e-04
2022-05-27 19:06:46,155 INFO [train.py:842] (3/4) Epoch 15, batch 8850, loss[loss=0.2221, simple_loss=0.3138, pruned_loss=0.06516, over 6798.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2791, pruned_loss=0.05568, over 1417881.90 frames.], batch size: 31, lr: 3.59e-04
2022-05-27 19:07:24,581 INFO [train.py:842] (3/4) Epoch 15, batch 8900, loss[loss=0.2582, simple_loss=0.3362, pruned_loss=0.09006, over 7326.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2794, pruned_loss=0.0562, over 1408440.34 frames.], batch size: 22, lr: 3.59e-04
2022-05-27 19:08:03,440 INFO [train.py:842] (3/4) Epoch 15, batch 8950, loss[loss=0.2163, simple_loss=0.2766, pruned_loss=0.07799, over 7227.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2786, pruned_loss=0.05597, over 1392691.57 frames.], batch size: 16, lr: 3.59e-04
2022-05-27 19:08:41,913 INFO [train.py:842] (3/4) Epoch 15, batch 9000, loss[loss=0.2029, simple_loss=0.2854, pruned_loss=0.06024, over 7195.00 frames.], tot_loss[loss=0.195, simple_loss=0.2779, pruned_loss=0.05606, over 1385789.19 frames.], batch size: 23, lr: 3.59e-04
2022-05-27 19:08:41,914 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 19:08:52,122 INFO [train.py:871] (3/4) Epoch 15, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03401, over 868885.00 frames.
2022-05-27 19:09:30,793 INFO [train.py:842] (3/4) Epoch 15, batch 9050, loss[loss=0.2136, simple_loss=0.3025, pruned_loss=0.06231, over 7208.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2794, pruned_loss=0.05707, over 1368829.75 frames.], batch size: 23, lr: 3.59e-04
2022-05-27 19:10:09,053 INFO [train.py:842] (3/4) Epoch 15, batch 9100, loss[loss=0.2177, simple_loss=0.289, pruned_loss=0.07315, over 5106.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2812, pruned_loss=0.05865, over 1327239.04 frames.], batch size: 52, lr: 3.59e-04
2022-05-27 19:10:46,732 INFO [train.py:842] (3/4) Epoch 15, batch 9150, loss[loss=0.2972, simple_loss=0.3541, pruned_loss=0.1201, over 4910.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2861, pruned_loss=0.06279, over 1257052.25 frames.], batch size: 52, lr: 3.58e-04
2022-05-27 19:11:37,231 INFO [train.py:842] (3/4) Epoch 16, batch 0, loss[loss=0.1944, simple_loss=0.2826, pruned_loss=0.0531, over 7286.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2826, pruned_loss=0.0531, over 7286.00 frames.], batch size: 24, lr: 3.48e-04
2022-05-27 19:12:16,185 INFO [train.py:842] (3/4) Epoch 16, batch 50, loss[loss=0.1867, simple_loss=0.2502, pruned_loss=0.06159, over 7408.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2823, pruned_loss=0.0585, over 320774.64 frames.], batch size: 18, lr: 3.48e-04
2022-05-27 19:12:55,626 INFO [train.py:842] (3/4) Epoch 16, batch 100, loss[loss=0.1695, simple_loss=0.2541, pruned_loss=0.04241, over 7322.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2774, pruned_loss=0.05496, over 564594.76 frames.], batch size: 20, lr: 3.48e-04
2022-05-27 19:13:38,130 INFO [train.py:842] (3/4) Epoch 16, batch 150, loss[loss=0.2137, simple_loss=0.2959, pruned_loss=0.06576, over 7155.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2796, pruned_loss=0.0554, over 754178.66 frames.], batch size: 20, lr: 3.48e-04
2022-05-27 19:14:16,666 INFO [train.py:842] (3/4) Epoch 16, batch 200, loss[loss=0.1956, simple_loss=0.2847, pruned_loss=0.05324, over 7108.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2793, pruned_loss=0.05574, over 897324.99 frames.], batch size: 21, lr: 3.48e-04
2022-05-27 19:14:56,295 INFO [train.py:842] (3/4) Epoch 16, batch 250, loss[loss=0.1957, simple_loss=0.2786, pruned_loss=0.05642, over 7147.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2778, pruned_loss=0.0545, over 1014514.69 frames.], batch size: 19, lr: 3.48e-04
2022-05-27 19:15:36,403 INFO [train.py:842] (3/4) Epoch 16, batch 300, loss[loss=0.2438, simple_loss=0.3193, pruned_loss=0.08413, over 7162.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2778, pruned_loss=0.05447, over 1108264.16 frames.], batch size: 19, lr: 3.48e-04
2022-05-27 19:16:18,288 INFO [train.py:842] (3/4) Epoch 16, batch 350, loss[loss=0.1788, simple_loss=0.2561, pruned_loss=0.05077, over 7290.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2784, pruned_loss=0.05504, over 1179567.68 frames.], batch size: 18, lr: 3.48e-04
2022-05-27 19:16:56,999 INFO [train.py:842] (3/4) Epoch 16, batch 400, loss[loss=0.2123, simple_loss=0.2912, pruned_loss=0.0667, over 7247.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2787, pruned_loss=0.05498, over 1234318.25 frames.], batch size: 19, lr: 3.48e-04
2022-05-27 19:17:36,536 INFO [train.py:842] (3/4) Epoch 16, batch 450, loss[loss=0.2033, simple_loss=0.2853, pruned_loss=0.06064, over 7426.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2789, pruned_loss=0.05521, over 1281182.96 frames.], batch size: 20, lr: 3.47e-04
2022-05-27 19:18:15,372 INFO [train.py:842] (3/4) Epoch 16, batch 500, loss[loss=0.1688, simple_loss=0.266, pruned_loss=0.0358, over 7202.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2792, pruned_loss=0.05532, over 1317893.65 frames.], batch size: 23, lr: 3.47e-04
2022-05-27 19:18:54,567 INFO [train.py:842] (3/4) Epoch 16, batch 550, loss[loss=0.1668, simple_loss=0.2523, pruned_loss=0.04062, over 7283.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2767, pruned_loss=0.05351, over 1345725.56 frames.], batch size: 18, lr: 3.47e-04
2022-05-27 19:19:33,226 INFO [train.py:842] (3/4) Epoch 16, batch 600, loss[loss=0.194, simple_loss=0.2791, pruned_loss=0.05444, over 7159.00 frames.], tot_loss[loss=0.193, simple_loss=0.2778, pruned_loss=0.05408, over 1362082.82 frames.], batch size: 19, lr: 3.47e-04
2022-05-27 19:20:12,225 INFO [train.py:842] (3/4) Epoch 16, batch 650, loss[loss=0.1671, simple_loss=0.2635, pruned_loss=0.03532, over 6491.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2783, pruned_loss=0.0547, over 1374755.96 frames.], batch size: 38, lr: 3.47e-04
2022-05-27 19:20:51,115 INFO [train.py:842] (3/4) Epoch 16, batch 700, loss[loss=0.1841, simple_loss=0.2714, pruned_loss=0.04833, over 7068.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2782, pruned_loss=0.05498, over 1385871.07 frames.], batch size: 28, lr: 3.47e-04
2022-05-27 19:21:33,895 INFO [train.py:842] (3/4) Epoch 16, batch 750, loss[loss=0.1717, simple_loss=0.2621, pruned_loss=0.04067, over 7162.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2779, pruned_loss=0.0548, over 1395038.24 frames.], batch size: 19, lr: 3.47e-04
2022-05-27 19:22:12,446 INFO [train.py:842] (3/4) Epoch 16, batch 800, loss[loss=0.2003, simple_loss=0.283, pruned_loss=0.05887, over 7257.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2778, pruned_loss=0.05444, over 1402581.05 frames.], batch size: 19, lr: 3.47e-04
2022-05-27 19:22:51,512 INFO [train.py:842] (3/4) Epoch 16, batch 850, loss[loss=0.215, simple_loss=0.299, pruned_loss=0.06553, over 7140.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2787, pruned_loss=0.05475, over 1405142.84 frames.], batch size: 20, lr: 3.47e-04
2022-05-27 19:23:30,176 INFO [train.py:842] (3/4) Epoch 16, batch 900, loss[loss=0.153, simple_loss=0.2358, pruned_loss=0.03515, over 7361.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2792, pruned_loss=0.05525, over 1403026.84 frames.], batch size: 19, lr: 3.47e-04
2022-05-27 19:24:09,383 INFO [train.py:842] (3/4) Epoch 16, batch 950, loss[loss=0.2081, simple_loss=0.2889, pruned_loss=0.0637, over 7438.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2787, pruned_loss=0.05523, over 1406407.03 frames.], batch size: 20, lr: 3.47e-04
2022-05-27 19:24:48,101 INFO [train.py:842] (3/4) Epoch 16, batch 1000, loss[loss=0.1902, simple_loss=0.2816, pruned_loss=0.04941, over 7310.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2777, pruned_loss=0.05455, over 1412503.54 frames.], batch size: 25, lr: 3.47e-04
2022-05-27 19:25:27,134 INFO [train.py:842] (3/4) Epoch 16, batch 1050, loss[loss=0.1777, simple_loss=0.2727, pruned_loss=0.04133, over 7319.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2785, pruned_loss=0.05499, over 1417913.53 frames.], batch size: 20, lr: 3.47e-04
2022-05-27 19:26:05,960 INFO [train.py:842] (3/4) Epoch 16, batch 1100, loss[loss=0.1815, simple_loss=0.2565, pruned_loss=0.05327, over 7362.00 frames.], tot_loss[loss=0.194, simple_loss=0.278, pruned_loss=0.055, over 1420140.58 frames.], batch size: 19, lr: 3.47e-04
2022-05-27 19:26:45,449 INFO [train.py:842] (3/4) Epoch 16, batch 1150, loss[loss=0.2505, simple_loss=0.3198, pruned_loss=0.09057, over 4906.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2768, pruned_loss=0.05413, over 1420880.14 frames.], batch size: 54, lr: 3.47e-04
2022-05-27 19:27:24,220 INFO [train.py:842] (3/4) Epoch 16, batch 1200, loss[loss=0.2057, simple_loss=0.2992, pruned_loss=0.05613, over 7119.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2777, pruned_loss=0.05465, over 1417825.33 frames.], batch size: 21, lr: 3.47e-04
2022-05-27 19:28:03,600 INFO [train.py:842] (3/4) Epoch 16, batch 1250, loss[loss=0.2016, simple_loss=0.2796, pruned_loss=0.06174, over 6872.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2778, pruned_loss=0.05483, over 1418395.37 frames.], batch size: 15, lr: 3.46e-04
2022-05-27 19:28:42,346 INFO [train.py:842] (3/4) Epoch 16, batch 1300, loss[loss=0.2256, simple_loss=0.3144, pruned_loss=0.06839, over 7193.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2791, pruned_loss=0.05518, over 1424567.78 frames.], batch size: 22, lr: 3.46e-04
2022-05-27 19:29:21,399 INFO [train.py:842] (3/4) Epoch 16, batch 1350, loss[loss=0.1837, simple_loss=0.2776, pruned_loss=0.04489, over 7163.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2785, pruned_loss=0.05456, over 1417477.36 frames.], batch size: 19, lr: 3.46e-04
2022-05-27 19:30:00,087 INFO [train.py:842] (3/4) Epoch 16, batch 1400, loss[loss=0.1967, simple_loss=0.2877, pruned_loss=0.05282, over 7327.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2776, pruned_loss=0.05394, over 1416300.85 frames.], batch size: 22, lr: 3.46e-04
2022-05-27 19:30:39,309 INFO [train.py:842] (3/4) Epoch 16, batch 1450, loss[loss=0.1804, simple_loss=0.2703, pruned_loss=0.04519, over 7405.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2785, pruned_loss=0.05442, over 1422256.25 frames.], batch size: 21, lr: 3.46e-04
2022-05-27 19:31:18,231 INFO [train.py:842] (3/4) Epoch 16, batch 1500, loss[loss=0.1911, simple_loss=0.2847, pruned_loss=0.04873, over 7218.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2783, pruned_loss=0.05421, over 1422138.76 frames.], batch size: 23, lr: 3.46e-04
2022-05-27 19:31:57,531 INFO [train.py:842] (3/4) Epoch 16, batch 1550, loss[loss=0.1987, simple_loss=0.2603, pruned_loss=0.06859, over 6780.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2778, pruned_loss=0.0542, over 1420153.76 frames.], batch size: 15, lr: 3.46e-04
2022-05-27 19:32:36,433 INFO [train.py:842] (3/4) Epoch 16, batch 1600, loss[loss=0.1775, simple_loss=0.2474, pruned_loss=0.05383, over 6810.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2776, pruned_loss=0.05364, over 1421972.36 frames.], batch size: 15, lr: 3.46e-04
2022-05-27 19:33:15,596 INFO [train.py:842] (3/4) Epoch 16, batch 1650, loss[loss=0.2359, simple_loss=0.3257, pruned_loss=0.07303, over 7142.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2777, pruned_loss=0.05433, over 1423996.18 frames.], batch size: 20, lr: 3.46e-04
2022-05-27 19:33:54,725 INFO [train.py:842] (3/4) Epoch 16, batch 1700, loss[loss=0.1895, simple_loss=0.2749, pruned_loss=0.05206, over 7413.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2777, pruned_loss=0.05478, over 1424715.44 frames.], batch size: 18, lr: 3.46e-04
2022-05-27 19:34:34,165 INFO [train.py:842] (3/4) Epoch 16, batch 1750, loss[loss=0.2085, simple_loss=0.2972, pruned_loss=0.05985, over 7378.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2796, pruned_loss=0.05567, over 1424684.50 frames.], batch size: 23, lr: 3.46e-04
2022-05-27 19:35:13,033 INFO [train.py:842] (3/4) Epoch 16, batch 1800, loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.0328, over 7360.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2805, pruned_loss=0.05612, over 1423419.84 frames.], batch size: 19, lr: 3.46e-04
2022-05-27 19:35:52,253 INFO [train.py:842] (3/4) Epoch 16, batch 1850, loss[loss=0.2302, simple_loss=0.3164, pruned_loss=0.07205, over 7144.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2791, pruned_loss=0.05531, over 1425804.14 frames.], batch size: 20, lr: 3.46e-04
2022-05-27 19:36:31,065 INFO [train.py:842] (3/4) Epoch 16, batch 1900, loss[loss=0.2077, simple_loss=0.289, pruned_loss=0.06321, over 7336.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2776, pruned_loss=0.0548, over 1430095.55 frames.], batch size: 25, lr: 3.46e-04
2022-05-27 19:37:10,359 INFO [train.py:842] (3/4) Epoch 16, batch 1950, loss[loss=0.2002, simple_loss=0.2849, pruned_loss=0.05775, over 7188.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2778, pruned_loss=0.05438, over 1430411.20 frames.], batch size: 23, lr: 3.46e-04
2022-05-27 19:37:48,988 INFO [train.py:842] (3/4) Epoch 16, batch 2000, loss[loss=0.2305, simple_loss=0.2965, pruned_loss=0.08228, over 5098.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2781, pruned_loss=0.05464, over 1425044.39 frames.], batch size: 53, lr: 3.46e-04
2022-05-27 19:38:28,269 INFO [train.py:842] (3/4) Epoch 16, batch 2050, loss[loss=0.2107, simple_loss=0.3007, pruned_loss=0.06038, over 6375.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2789, pruned_loss=0.05536, over 1422696.77 frames.], batch size: 37, lr: 3.45e-04
2022-05-27 19:39:07,368 INFO [train.py:842] (3/4) Epoch 16, batch 2100, loss[loss=0.1935, simple_loss=0.2986, pruned_loss=0.04417, over 7114.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2779, pruned_loss=0.05464, over 1422600.57 frames.], batch size: 21, lr: 3.45e-04
2022-05-27 19:39:46,927 INFO [train.py:842] (3/4) Epoch 16, batch 2150, loss[loss=0.1758, simple_loss=0.2573, pruned_loss=0.04716, over 7253.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2785, pruned_loss=0.05451, over 1417957.82 frames.], batch size: 19, lr: 3.45e-04
2022-05-27 19:40:25,574 INFO [train.py:842] (3/4) Epoch 16, batch 2200, loss[loss=0.2677, simple_loss=0.3432, pruned_loss=0.09608, over 7203.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2788, pruned_loss=0.05446, over 1415090.51 frames.], batch size: 22, lr: 3.45e-04
2022-05-27 19:41:05,254 INFO [train.py:842] (3/4) Epoch 16, batch 2250, loss[loss=0.2266, simple_loss=0.3158, pruned_loss=0.06867, over 7416.00 frames.], tot_loss[loss=0.193, simple_loss=0.2777, pruned_loss=0.0541, over 1417277.13 frames.], batch size: 21, lr: 3.45e-04
2022-05-27 19:41:43,768 INFO [train.py:842] (3/4) Epoch 16, batch 2300, loss[loss=0.19, simple_loss=0.2816, pruned_loss=0.04919, over 7213.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2784, pruned_loss=0.05411, over 1418968.79 frames.], batch size: 23, lr: 3.45e-04
2022-05-27 19:42:23,145 INFO [train.py:842] (3/4) Epoch 16, batch 2350, loss[loss=0.185, simple_loss=0.2817, pruned_loss=0.04415, over 7300.00 frames.], tot_loss[loss=0.193, simple_loss=0.2776, pruned_loss=0.05421, over 1421508.87 frames.], batch size: 25, lr: 3.45e-04
2022-05-27 19:43:02,184 INFO [train.py:842] (3/4) Epoch 16, batch 2400, loss[loss=0.2057, simple_loss=0.2936, pruned_loss=0.05892, over 7292.00 frames.], tot_loss[loss=0.1926, simple_loss=0.277, pruned_loss=0.05407, over 1424902.95 frames.], batch size: 25, lr: 3.45e-04
2022-05-27 19:43:41,274 INFO [train.py:842] (3/4) Epoch 16, batch 2450, loss[loss=0.1808, simple_loss=0.2601, pruned_loss=0.05077, over 6792.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2782, pruned_loss=0.05497, over 1423886.87 frames.], batch size: 31, lr: 3.45e-04
2022-05-27 19:44:20,563 INFO [train.py:842] (3/4) Epoch 16, batch 2500, loss[loss=0.1671, simple_loss=0.2687, pruned_loss=0.03279, over 7216.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2781, pruned_loss=0.05505, over 1427990.71 frames.], batch size: 21, lr: 3.45e-04
2022-05-27 19:44:59,657 INFO [train.py:842] (3/4) Epoch 16, batch 2550, loss[loss=0.1876, simple_loss=0.2719, pruned_loss=0.05159, over 7134.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2774, pruned_loss=0.05475, over 1424198.63 frames.], batch size: 20, lr: 3.45e-04
2022-05-27 19:45:38,435 INFO [train.py:842] (3/4) Epoch 16, batch 2600, loss[loss=0.1589, simple_loss=0.2438, pruned_loss=0.03703, over 7349.00 frames.], tot_loss[loss=0.1929, simple_loss=0.277, pruned_loss=0.05445, over 1423059.85 frames.], batch size: 19, lr: 3.45e-04
2022-05-27 19:46:17,864 INFO [train.py:842] (3/4) Epoch 16, batch 2650, loss[loss=0.2223, simple_loss=0.3067, pruned_loss=0.06893, over 7389.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2765, pruned_loss=0.05444, over 1423732.50 frames.], batch size: 23, lr: 3.45e-04
2022-05-27 19:46:56,744 INFO [train.py:842] (3/4) Epoch 16, batch 2700, loss[loss=0.1744, simple_loss=0.2656, pruned_loss=0.04158, over 7161.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2766, pruned_loss=0.05414, over 1420619.20 frames.], batch size: 26, lr: 3.45e-04
2022-05-27 19:47:35,963 INFO [train.py:842] (3/4) Epoch 16, batch 2750, loss[loss=0.1589, simple_loss=0.2445, pruned_loss=0.03662, over 7289.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2769, pruned_loss=0.05382, over 1424804.73 frames.], batch size: 18, lr: 3.45e-04
2022-05-27 19:48:14,878 INFO [train.py:842] (3/4) Epoch 16, batch 2800, loss[loss=0.1695, simple_loss=0.2584, pruned_loss=0.04025, over 7220.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2765, pruned_loss=0.05363, over 1426185.24 frames.], batch size: 21, lr: 3.45e-04
2022-05-27 19:48:54,107 INFO [train.py:842] (3/4) Epoch 16, batch 2850, loss[loss=0.1719, simple_loss=0.2592, pruned_loss=0.0423, over 7172.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2772, pruned_loss=0.05416, over 1425202.11 frames.], batch size: 18, lr: 3.45e-04
2022-05-27 19:49:32,804 INFO [train.py:842] (3/4) Epoch 16, batch 2900, loss[loss=0.1947, simple_loss=0.2725, pruned_loss=0.05847, over 7154.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2777, pruned_loss=0.0543, over 1427541.65 frames.], batch size: 18, lr: 3.44e-04
2022-05-27 19:50:12,022 INFO [train.py:842] (3/4) Epoch 16, batch 2950, loss[loss=0.167, simple_loss=0.2624, pruned_loss=0.0358, over 7341.00 frames.], tot_loss[loss=0.1927, simple_loss=0.277, pruned_loss=0.05422, over 1423809.28 frames.], batch size: 22, lr: 3.44e-04
2022-05-27 19:50:50,675 INFO [train.py:842] (3/4) Epoch 16, batch 3000, loss[loss=0.2156, simple_loss=0.3052, pruned_loss=0.06302, over 7409.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2777, pruned_loss=0.0543, over 1427658.47 frames.], batch size: 21, lr: 3.44e-04
2022-05-27 19:50:50,675 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 19:51:00,435 INFO [train.py:871] (3/4) Epoch 16, validation: loss=0.1694, simple_loss=0.2694, pruned_loss=0.03473, over 868885.00 frames.
2022-05-27 19:51:39,565 INFO [train.py:842] (3/4) Epoch 16, batch 3050, loss[loss=0.1583, simple_loss=0.2372, pruned_loss=0.03964, over 7408.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2774, pruned_loss=0.0542, over 1426913.14 frames.], batch size: 18, lr: 3.44e-04
2022-05-27 19:52:18,308 INFO [train.py:842] (3/4) Epoch 16, batch 3100, loss[loss=0.1923, simple_loss=0.2829, pruned_loss=0.05084, over 7181.00 frames.], tot_loss[loss=0.1925, simple_loss=0.277, pruned_loss=0.05398, over 1426636.86 frames.], batch size: 23, lr: 3.44e-04
2022-05-27 19:52:57,440 INFO [train.py:842] (3/4) Epoch 16, batch 3150, loss[loss=0.1732, simple_loss=0.2651, pruned_loss=0.04063, over 7169.00 frames.], tot_loss[loss=0.1926, simple_loss=0.277, pruned_loss=0.05405, over 1424227.39 frames.], batch size: 18, lr: 3.44e-04
2022-05-27 19:53:36,245 INFO [train.py:842] (3/4) Epoch 16, batch 3200, loss[loss=0.1912, simple_loss=0.283, pruned_loss=0.04972, over 7273.00 frames.], tot_loss[loss=0.194, simple_loss=0.2782, pruned_loss=0.05492, over 1424370.17 frames.], batch size: 24, lr: 3.44e-04
2022-05-27 19:54:15,781 INFO [train.py:842] (3/4) Epoch 16, batch 3250, loss[loss=0.2023, simple_loss=0.291, pruned_loss=0.05679, over 7328.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2772, pruned_loss=0.05468, over 1426278.17 frames.], batch size: 21, lr: 3.44e-04
2022-05-27 19:54:54,913 INFO [train.py:842] (3/4) Epoch 16, batch 3300, loss[loss=0.232, simple_loss=0.3169, pruned_loss=0.07357, over 7292.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2777, pruned_loss=0.05431, over 1430110.04 frames.], batch size: 25, lr: 3.44e-04
2022-05-27 19:55:34,118 INFO [train.py:842] (3/4) Epoch 16, batch 3350, loss[loss=0.1861, simple_loss=0.2766, pruned_loss=0.04781, over 7227.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2776, pruned_loss=0.05454, over 1431669.29 frames.], batch size: 20, lr: 3.44e-04
2022-05-27 19:56:12,918 INFO [train.py:842] (3/4) Epoch 16, batch 3400, loss[loss=0.2105, simple_loss=0.2932, pruned_loss=0.06385, over 7040.00 frames.], tot_loss[loss=0.193, simple_loss=0.2775, pruned_loss=0.05421, over 1428432.03 frames.], batch size: 28, lr: 3.44e-04
2022-05-27 19:56:52,485 INFO [train.py:842] (3/4) Epoch 16, batch 3450, loss[loss=0.1693, simple_loss=0.2506, pruned_loss=0.04398, over 7344.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2775, pruned_loss=0.05374, over 1429126.42 frames.], batch size: 19, lr: 3.44e-04
2022-05-27 19:57:31,239 INFO [train.py:842] (3/4) Epoch 16, batch 3500, loss[loss=0.1904, simple_loss=0.2792, pruned_loss=0.05079, over 7321.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2776, pruned_loss=0.05404, over 1427929.43 frames.], batch size: 21, lr: 3.44e-04
2022-05-27 19:58:10,272 INFO [train.py:842] (3/4) Epoch 16, batch 3550, loss[loss=0.2183, simple_loss=0.3055, pruned_loss=0.06548, over 7178.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2785, pruned_loss=0.05426, over 1424268.72 frames.], batch size: 26, lr: 3.44e-04
2022-05-27 19:58:48,884 INFO [train.py:842] (3/4) Epoch 16, batch 3600, loss[loss=0.1853, simple_loss=0.2724, pruned_loss=0.04908, over 7300.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2769, pruned_loss=0.05332, over 1425618.27 frames.], batch size: 21, lr: 3.44e-04
2022-05-27 19:59:28,080 INFO [train.py:842] (3/4) Epoch 16, batch 3650, loss[loss=0.1832, simple_loss=0.2621, pruned_loss=0.05217, over 7265.00 frames.], tot_loss[loss=0.191, simple_loss=0.276, pruned_loss=0.05303, over 1425302.26 frames.], batch size: 18, lr: 3.44e-04
2022-05-27 20:00:07,142 INFO [train.py:842] (3/4) Epoch 16, batch 3700, loss[loss=0.1757, simple_loss=0.2605, pruned_loss=0.04544, over 6816.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2769, pruned_loss=0.05369, over 1424196.72 frames.], batch size: 15, lr: 3.43e-04
2022-05-27 20:00:46,297 INFO [train.py:842] (3/4) Epoch 16, batch 3750, loss[loss=0.2068, simple_loss=0.2914, pruned_loss=0.06104, over 7319.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2768, pruned_loss=0.05369, over 1421633.59 frames.], batch size: 25, lr: 3.43e-04
2022-05-27 20:01:24,920 INFO [train.py:842] (3/4) Epoch 16, batch 3800, loss[loss=0.1815, simple_loss=0.2779, pruned_loss=0.04255, over 7215.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2771, pruned_loss=0.05408, over 1424978.13 frames.], batch size: 22, lr: 3.43e-04
2022-05-27 20:02:03,878 INFO [train.py:842] (3/4) Epoch 16, batch 3850, loss[loss=0.1681, simple_loss=0.265, pruned_loss=0.03556, over 7148.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2775, pruned_loss=0.05433, over 1420020.92 frames.], batch size: 20, lr: 3.43e-04
2022-05-27 20:02:42,897 INFO [train.py:842] (3/4) Epoch 16, batch 3900, loss[loss=0.1925, simple_loss=0.2736, pruned_loss=0.0557, over 7291.00 frames.], tot_loss[loss=0.1934, simple_loss=0.278, pruned_loss=0.05436, over 1423005.26 frames.], batch size: 24, lr: 3.43e-04
2022-05-27 20:03:21,499 INFO [train.py:842] (3/4) Epoch 16, batch 3950, loss[loss=0.1911, simple_loss=0.2785, pruned_loss=0.05183, over 7224.00 frames.], tot_loss[loss=0.1934, simple_loss=0.278, pruned_loss=0.05438, over 1420004.92 frames.], batch size: 21, lr: 3.43e-04
2022-05-27 20:04:00,261 INFO [train.py:842] (3/4) Epoch 16, batch 4000, loss[loss=0.1691, simple_loss=0.2614, pruned_loss=0.03835, over 7227.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2778, pruned_loss=0.05394, over 1420756.85 frames.], batch size: 21, lr: 3.43e-04
2022-05-27 20:04:39,441 INFO [train.py:842] (3/4) Epoch 16, batch 4050, loss[loss=0.2812, simple_loss=0.3544, pruned_loss=0.104, over 7226.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2789, pruned_loss=0.05489, over 1422095.45 frames.], batch size: 22, lr: 3.43e-04
2022-05-27 20:05:18,200 INFO [train.py:842] (3/4) Epoch 16, batch 4100, loss[loss=0.2616, simple_loss=0.333, pruned_loss=0.09512, over 7161.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2798, pruned_loss=0.05534, over 1424252.04 frames.], batch size: 18, lr: 3.43e-04
2022-05-27 20:05:57,580 INFO [train.py:842] (3/4) Epoch 16, batch 4150, loss[loss=0.1597, simple_loss=0.2387, pruned_loss=0.04042, over 6998.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2788, pruned_loss=0.05495, over 1425460.95 frames.], batch size: 16, lr: 3.43e-04
2022-05-27 20:06:36,504 INFO [train.py:842] (3/4) Epoch 16, batch 4200, loss[loss=0.1783, simple_loss=0.2735, pruned_loss=0.04152, over 7417.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2781, pruned_loss=0.05433, over 1423221.33 frames.], batch size: 21, lr: 3.43e-04
2022-05-27 20:07:15,435 INFO [train.py:842] (3/4) Epoch 16, batch 4250, loss[loss=0.162, simple_loss=0.257, pruned_loss=0.0335, over 7280.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2774, pruned_loss=0.05365, over 1422122.91 frames.], batch size: 25, lr: 3.43e-04
2022-05-27 20:07:54,450 INFO [train.py:842] (3/4) Epoch 16, batch 4300, loss[loss=0.2542, simple_loss=0.319, pruned_loss=0.09466, over 7229.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2784, pruned_loss=0.05444, over 1422821.99 frames.], batch size: 20, lr: 3.43e-04
2022-05-27 20:08:33,216 INFO [train.py:842] (3/4) Epoch 16, batch 4350, loss[loss=0.2153, simple_loss=0.3046, pruned_loss=0.06296, over 7198.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2781, pruned_loss=0.05375, over 1424890.05 frames.], batch size: 22, lr: 3.43e-04
2022-05-27 20:09:12,174 INFO [train.py:842] (3/4) Epoch 16, batch 4400, loss[loss=0.1783, simple_loss=0.2703, pruned_loss=0.04319, over 7329.00 frames.], tot_loss[loss=0.1922, simple_loss=0.277, pruned_loss=0.05372, over 1420568.20 frames.], batch size: 21, lr: 3.43e-04
2022-05-27 20:09:51,443 INFO [train.py:842] (3/4) Epoch 16, batch 4450, loss[loss=0.1771, simple_loss=0.2576, pruned_loss=0.04831, over 7159.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2777, pruned_loss=0.05368, over 1423755.14 frames.], batch size: 18, lr: 3.43e-04
2022-05-27 20:10:30,388 INFO [train.py:842] (3/4) Epoch 16, batch 4500, loss[loss=0.2459, simple_loss=0.3215, pruned_loss=0.08512, over 7340.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2785, pruned_loss=0.05382, over 1427355.53 frames.], batch size: 22, lr: 3.43e-04
2022-05-27 20:11:09,734 INFO [train.py:842] (3/4) Epoch 16, batch 4550, loss[loss=0.206, simple_loss=0.2847, pruned_loss=0.06365, over 7197.00 frames.], tot_loss[loss=0.192, simple_loss=0.277, pruned_loss=0.05353, over 1428386.13 frames.], batch size: 22, lr: 3.42e-04
2022-05-27 20:11:48,705 INFO [train.py:842] (3/4) Epoch 16, batch 4600, loss[loss=0.1645, simple_loss=0.2465, pruned_loss=0.04127, over 7278.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2763, pruned_loss=0.05347, over 1430024.02 frames.], batch size: 18, lr: 3.42e-04
2022-05-27 20:12:27,776 INFO [train.py:842] (3/4) Epoch 16, batch 4650, loss[loss=0.185, simple_loss=0.2697, pruned_loss=0.05016, over 7242.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2759, pruned_loss=0.0532, over 1430515.29 frames.], batch size: 20, lr: 3.42e-04
2022-05-27 20:13:06,632 INFO [train.py:842] (3/4) Epoch 16, batch 4700, loss[loss=0.1927, simple_loss=0.2724, pruned_loss=0.05647, over 7116.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2766, pruned_loss=0.05341, over 1432444.10 frames.], batch size: 21, lr: 3.42e-04
2022-05-27 20:13:45,942 INFO [train.py:842] (3/4) Epoch 16, batch 4750, loss[loss=0.1413, simple_loss=0.2229, pruned_loss=0.02984, over 6780.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2758, pruned_loss=0.05291, over 1430414.25 frames.], batch size: 15, lr: 3.42e-04
2022-05-27 20:14:24,755 INFO [train.py:842] (3/4) Epoch 16, batch 4800, loss[loss=0.1983, simple_loss=0.281, pruned_loss=0.05783, over 7430.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2773, pruned_loss=0.05363, over 1433384.05 frames.], batch size: 20, lr: 3.42e-04
2022-05-27 20:15:03,940 INFO [train.py:842] (3/4) Epoch 16, batch 4850, loss[loss=0.1738, simple_loss=0.2696, pruned_loss=0.03905, over 7131.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2782, pruned_loss=0.05418, over 1427678.62 frames.], batch size: 20, lr: 3.42e-04
2022-05-27 20:15:43,064 INFO [train.py:842] (3/4) Epoch 16, batch 4900, loss[loss=0.2339, simple_loss=0.3029, pruned_loss=0.08248, over 7325.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2777, pruned_loss=0.05365, over 1426246.81 frames.], batch size: 20, lr: 3.42e-04
2022-05-27 20:16:22,181 INFO [train.py:842] (3/4) Epoch 16, batch 4950, loss[loss=0.1818, simple_loss=0.2809, pruned_loss=0.04138, over 7024.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2777, pruned_loss=0.05407, over 1426948.72 frames.], batch size: 28, lr: 3.42e-04
2022-05-27 20:17:00,912 INFO [train.py:842] (3/4) Epoch 16, batch 5000, loss[loss=0.187, simple_loss=0.2798, pruned_loss=0.04713, over 7199.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2775, pruned_loss=0.05449, over 1423775.66 frames.], batch size: 23, lr: 3.42e-04
2022-05-27 20:17:40,121 INFO [train.py:842] (3/4) Epoch 16, batch 5050, loss[loss=0.1772, simple_loss=0.2589, pruned_loss=0.04772, over 7124.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2768, pruned_loss=0.05397, over 1421635.00 frames.], batch size: 17, lr: 3.42e-04
2022-05-27 20:18:18,509 INFO [train.py:842] (3/4) Epoch 16, batch 5100, loss[loss=0.211, simple_loss=0.295, pruned_loss=0.06352, over 7140.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2785, pruned_loss=0.05437, over 1418872.47 frames.], batch size: 26, lr: 3.42e-04
2022-05-27 20:18:57,665 INFO [train.py:842] (3/4) Epoch 16, batch 5150, loss[loss=0.1851, simple_loss=0.271, pruned_loss=0.04957, over 6651.00 frames.], tot_loss[loss=0.1934, simple_loss=0.278, pruned_loss=0.05439, over 1422729.51 frames.], batch size: 38, lr: 3.42e-04
2022-05-27 20:19:36,701 INFO [train.py:842] (3/4) Epoch 16, batch 5200, loss[loss=0.2115, simple_loss=0.2888, pruned_loss=0.06711, over 7081.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2774, pruned_loss=0.05422, over 1427465.67 frames.], batch size: 18, lr: 3.42e-04
2022-05-27 20:20:15,551 INFO [train.py:842] (3/4) Epoch 16, batch 5250, loss[loss=0.154, simple_loss=0.2343, pruned_loss=0.03686, over 7254.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2782, pruned_loss=0.05435, over 1429204.43 frames.], batch size: 19, lr: 3.42e-04
2022-05-27 20:20:54,297 INFO [train.py:842] (3/4) Epoch 16, batch 5300, loss[loss=0.1904, simple_loss=0.2738, pruned_loss=0.05346, over 7318.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2787, pruned_loss=0.05526, over 1428369.56 frames.], batch size: 21, lr: 3.42e-04
2022-05-27 20:21:33,676 INFO [train.py:842] (3/4) Epoch 16, batch 5350, loss[loss=0.1519, simple_loss=0.2358, pruned_loss=0.03406, over 7282.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2795, pruned_loss=0.05514, over 1430243.68 frames.], batch size: 17, lr: 3.41e-04
2022-05-27 20:22:12,428 INFO [train.py:842] (3/4) Epoch 16, batch 5400, loss[loss=0.167, simple_loss=0.2518, pruned_loss=0.04112, over 7003.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2788, pruned_loss=0.0549, over 1430968.29 frames.], batch size: 16, lr: 3.41e-04
2022-05-27 20:22:51,668 INFO [train.py:842] (3/4) Epoch 16, batch 5450, loss[loss=0.2576, simple_loss=0.3194, pruned_loss=0.0979, over 7265.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2787, pruned_loss=0.05475, over 1431495.65 frames.], batch size: 19, lr: 3.41e-04
2022-05-27 20:23:30,925 INFO [train.py:842] (3/4) Epoch 16, batch 5500, loss[loss=0.2022, simple_loss=0.289, pruned_loss=0.05765, over 7367.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2783, pruned_loss=0.05459, over 1432226.64 frames.], batch size: 23, lr: 3.41e-04
2022-05-27 20:24:09,998 INFO [train.py:842] (3/4) Epoch 16, batch 5550, loss[loss=0.2356, simple_loss=0.308, pruned_loss=0.08161, over 7206.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2791, pruned_loss=0.05505, over 1430930.65 frames.], batch size: 22, lr: 3.41e-04
2022-05-27 20:24:48,783 INFO [train.py:842] (3/4) Epoch 16, batch 5600, loss[loss=0.1844, simple_loss=0.2783, pruned_loss=0.04529, over 6735.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2798, pruned_loss=0.05592, over 1423596.47 frames.], batch size: 31, lr: 3.41e-04
2022-05-27 20:25:28,083 INFO [train.py:842] (3/4) Epoch 16, batch 5650, loss[loss=0.1573, simple_loss=0.2277, pruned_loss=0.04342, over 7276.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2794, pruned_loss=0.05557, over 1419247.71 frames.], batch size: 17, lr: 3.41e-04
2022-05-27 20:26:06,929 INFO [train.py:842] (3/4) Epoch 16, batch 5700, loss[loss=0.2477, simple_loss=0.322, pruned_loss=0.08674, over 6662.00 frames.], tot_loss[loss=0.1948, simple_loss=0.279, pruned_loss=0.05527, over 1418449.59 frames.], batch size: 31, lr: 3.41e-04
2022-05-27 20:26:45,777 INFO [train.py:842] (3/4) Epoch 16, batch 5750, loss[loss=0.1892, simple_loss=0.2805, pruned_loss=0.04891, over 7361.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2782, pruned_loss=0.05466, over 1415077.61 frames.], batch size: 19, lr: 3.41e-04
2022-05-27 20:27:25,122 INFO [train.py:842] (3/4) Epoch 16, batch 5800, loss[loss=0.1707, simple_loss=0.2687, pruned_loss=0.03632, over 7305.00 frames.], tot_loss[loss=0.1925, simple_loss=0.277, pruned_loss=0.054, over 1418141.72 frames.], batch size: 25, lr: 3.41e-04
2022-05-27 20:28:04,514 INFO [train.py:842] (3/4) Epoch 16, batch 5850, loss[loss=0.1726, simple_loss=0.2642, pruned_loss=0.04053, over 7320.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2769, pruned_loss=0.0542, over 1419872.42 frames.], batch size: 21, lr: 3.41e-04
2022-05-27 20:28:43,356 INFO [train.py:842] (3/4) Epoch 16, batch 5900, loss[loss=0.1879, simple_loss=0.2603, pruned_loss=0.05777, over 6830.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2786, pruned_loss=0.05461, over 1423519.53 frames.], batch size: 15, lr: 3.41e-04
2022-05-27 20:29:22,144 INFO [train.py:842] (3/4) Epoch 16, batch 5950, loss[loss=0.1831, simple_loss=0.2605, pruned_loss=0.05285, over 7392.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2782, pruned_loss=0.05453, over 1419815.68 frames.], batch size: 18, lr: 3.41e-04
2022-05-27 20:30:01,020 INFO [train.py:842] (3/4) Epoch 16, batch 6000, loss[loss=0.1773, simple_loss=0.2668, pruned_loss=0.04386, over 7235.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2776, pruned_loss=0.05448, over 1419683.82 frames.], batch size: 20, lr: 3.41e-04
2022-05-27 20:30:01,021 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 20:30:10,685 INFO [train.py:871] (3/4) Epoch 16, validation: loss=0.1676, simple_loss=0.2671, pruned_loss=0.03399, over 868885.00 frames.
2022-05-27 20:30:49,782 INFO [train.py:842] (3/4) Epoch 16, batch 6050, loss[loss=0.1691, simple_loss=0.255, pruned_loss=0.04154, over 7134.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2782, pruned_loss=0.05464, over 1422838.73 frames.], batch size: 17, lr: 3.41e-04
2022-05-27 20:31:28,703 INFO [train.py:842] (3/4) Epoch 16, batch 6100, loss[loss=0.1886, simple_loss=0.2666, pruned_loss=0.05534, over 7423.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2783, pruned_loss=0.05468, over 1423253.02 frames.], batch size: 20, lr: 3.41e-04
2022-05-27 20:32:11,269 INFO [train.py:842] (3/4) Epoch 16, batch 6150, loss[loss=0.1773, simple_loss=0.254, pruned_loss=0.05036, over 7441.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2769, pruned_loss=0.05418, over 1422096.20 frames.], batch size: 20, lr: 3.41e-04
2022-05-27 20:32:50,490 INFO [train.py:842] (3/4) Epoch 16, batch 6200, loss[loss=0.1551, simple_loss=0.2519, pruned_loss=0.02921, over 7316.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2746, pruned_loss=0.05304, over 1427079.33 frames.], batch size: 21, lr: 3.40e-04
2022-05-27 20:33:29,296 INFO [train.py:842] (3/4) Epoch 16, batch 6250, loss[loss=0.1798, simple_loss=0.2547, pruned_loss=0.05244, over 7323.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2754, pruned_loss=0.05352, over 1425918.92 frames.], batch size: 20, lr: 3.40e-04
2022-05-27 20:34:08,323 INFO [train.py:842] (3/4) Epoch 16, batch 6300, loss[loss=0.1893, simple_loss=0.2852, pruned_loss=0.04666, over 7321.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2759, pruned_loss=0.05359, over 1429779.15 frames.], batch size: 22, lr: 3.40e-04
2022-05-27 20:34:47,574 INFO [train.py:842] (3/4) Epoch 16, batch 6350, loss[loss=0.2087, simple_loss=0.2954, pruned_loss=0.06106, over 6481.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2759, pruned_loss=0.05374, over 1425045.95 frames.], batch size: 38, lr: 3.40e-04
2022-05-27 20:35:26,595 INFO [train.py:842] (3/4) Epoch 16, batch 6400, loss[loss=0.1951, simple_loss=0.284, pruned_loss=0.05311, over 7226.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2758, pruned_loss=0.05401, over 1427024.80 frames.], batch size: 21, lr: 3.40e-04
2022-05-27 20:36:05,670 INFO [train.py:842] (3/4) Epoch 16, batch 6450, loss[loss=0.1884, simple_loss=0.2809, pruned_loss=0.04792, over 7316.00 frames.], tot_loss[loss=0.192, simple_loss=0.2757, pruned_loss=0.05412, over 1424465.12 frames.], batch size: 21, lr: 3.40e-04
2022-05-27 20:36:44,217 INFO [train.py:842] (3/4) Epoch 16, batch 6500, loss[loss=0.1611, simple_loss=0.2529, pruned_loss=0.03462, over 7207.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2766, pruned_loss=0.05423, over 1420019.39 frames.], batch size: 21, lr: 3.40e-04
2022-05-27 20:37:23,382 INFO [train.py:842] (3/4) Epoch 16, batch 6550, loss[loss=0.1902, simple_loss=0.276, pruned_loss=0.05219, over 7192.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2766, pruned_loss=0.05426, over 1420517.74 frames.], batch size: 22, lr: 3.40e-04
2022-05-27 20:38:12,092 INFO [train.py:842] (3/4) Epoch 16, batch 6600, loss[loss=0.1592, simple_loss=0.2357, pruned_loss=0.04132, over 7057.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2763, pruned_loss=0.05379, over 1423492.96 frames.], batch size: 18, lr: 3.40e-04
2022-05-27 20:38:51,384 INFO [train.py:842] (3/4) Epoch 16, batch 6650, loss[loss=0.2314, simple_loss=0.3108, pruned_loss=0.07604, over 7064.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2771, pruned_loss=0.05412, over 1423000.67 frames.], batch size: 28, lr: 3.40e-04
2022-05-27 20:39:30,095 INFO [train.py:842] (3/4) Epoch 16, batch 6700, loss[loss=0.1843, simple_loss=0.2684, pruned_loss=0.05006, over 7322.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2781, pruned_loss=0.05436, over 1423826.30 frames.], batch size: 20, lr: 3.40e-04
2022-05-27 20:40:09,435 INFO [train.py:842] (3/4) Epoch 16, batch 6750, loss[loss=0.18, simple_loss=0.2742, pruned_loss=0.0429, over 7327.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2781, pruned_loss=0.05413, over 1425323.08 frames.], batch size: 20, lr: 3.40e-04
2022-05-27 20:40:48,543 INFO [train.py:842] (3/4) Epoch 16, batch 6800, loss[loss=0.1924, simple_loss=0.2775, pruned_loss=0.05366, over 7430.00 frames.], tot_loss[loss=0.193, simple_loss=0.2779, pruned_loss=0.0541, over 1428029.32 frames.], batch size: 20, lr: 3.40e-04
2022-05-27 20:41:27,664 INFO [train.py:842] (3/4) Epoch 16, batch 6850, loss[loss=0.1731, simple_loss=0.2641, pruned_loss=0.04104, over 7259.00 frames.], tot_loss[loss=0.1938, simple_loss=0.278, pruned_loss=0.05481, over 1428400.74 frames.], batch size: 19, lr: 3.40e-04
2022-05-27 20:42:06,265 INFO [train.py:842] (3/4) Epoch 16, batch 6900, loss[loss=0.2338, simple_loss=0.3225, pruned_loss=0.07255, over 7040.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2778, pruned_loss=0.05444, over 1425043.75 frames.], batch size: 28, lr: 3.40e-04
2022-05-27 20:42:45,908 INFO [train.py:842] (3/4) Epoch 16, batch 6950, loss[loss=0.2249, simple_loss=0.3053, pruned_loss=0.07228, over 7275.00 frames.], tot_loss[loss=0.192, simple_loss=0.2766, pruned_loss=0.05372, over 1424965.51 frames.], batch size: 24, lr: 3.40e-04
2022-05-27 20:43:25,273 INFO [train.py:842] (3/4) Epoch 16, batch 7000, loss[loss=0.1939, simple_loss=0.2697, pruned_loss=0.05901, over 6818.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2767, pruned_loss=0.05453, over 1422091.80 frames.], batch size: 15, lr: 3.40e-04
2022-05-27 20:44:04,310 INFO [train.py:842] (3/4) Epoch 16, batch 7050, loss[loss=0.1862, simple_loss=0.2664, pruned_loss=0.05296, over 7144.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2763, pruned_loss=0.05443, over 1424219.79 frames.], batch size: 26, lr: 3.39e-04
2022-05-27 20:44:43,348 INFO [train.py:842] (3/4) Epoch 16, batch 7100, loss[loss=0.218, simple_loss=0.3076, pruned_loss=0.06416, over 7167.00 frames.], tot_loss[loss=0.193, simple_loss=0.2771, pruned_loss=0.05445, over 1428398.13 frames.], batch size: 26, lr: 3.39e-04
2022-05-27 20:45:22,628 INFO [train.py:842] (3/4) Epoch 16, batch 7150, loss[loss=0.2229, simple_loss=0.3011, pruned_loss=0.07237, over 5138.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2775, pruned_loss=0.05458, over 1424627.78 frames.], batch size: 52, lr: 3.39e-04
2022-05-27 20:46:01,392 INFO [train.py:842] (3/4) Epoch 16, batch 7200, loss[loss=0.224, simple_loss=0.3095, pruned_loss=0.06926, over 7384.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2757, pruned_loss=0.05323, over 1427014.49 frames.], batch size: 23, lr: 3.39e-04
2022-05-27 20:46:40,360 INFO [train.py:842] (3/4) Epoch 16, batch 7250, loss[loss=0.2623, simple_loss=0.3225, pruned_loss=0.101, over 7146.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2761, pruned_loss=0.05289, over 1424077.78 frames.], batch size: 19, lr: 3.39e-04
2022-05-27 20:47:19,334 INFO [train.py:842] (3/4) Epoch 16, batch 7300, loss[loss=0.1778, simple_loss=0.2605, pruned_loss=0.04755, over 7059.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2772, pruned_loss=0.05364, over 1419090.02 frames.], batch size: 18, lr: 3.39e-04
2022-05-27 20:47:58,176 INFO [train.py:842] (3/4) Epoch 16, batch 7350, loss[loss=0.1419, simple_loss=0.2239, pruned_loss=0.02993, over 7421.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2773, pruned_loss=0.05379, over 1422102.84 frames.], batch size: 17, lr: 3.39e-04
2022-05-27 20:48:37,018 INFO [train.py:842] (3/4) Epoch 16, batch 7400, loss[loss=0.1466, simple_loss=0.2251, pruned_loss=0.03404, over 7208.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2788, pruned_loss=0.05488, over 1425056.94 frames.], batch size: 16, lr: 3.39e-04
2022-05-27 20:49:15,878 INFO [train.py:842] (3/4) Epoch 16, batch 7450, loss[loss=0.188, simple_loss=0.2605, pruned_loss=0.05779, over 6754.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2784, pruned_loss=0.0552, over 1420681.36 frames.], batch size: 15, lr: 3.39e-04
2022-05-27 20:49:54,828 INFO [train.py:842] (3/4) Epoch 16, batch 7500, loss[loss=0.1958, simple_loss=0.2822, pruned_loss=0.05477, over 7159.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2773, pruned_loss=0.05388, over 1420488.42 frames.], batch size: 18, lr: 3.39e-04
2022-05-27 20:50:33,697 INFO [train.py:842] (3/4) Epoch 16, batch 7550, loss[loss=0.1723, simple_loss=0.2652, pruned_loss=0.03972, over 7415.00 frames.], tot_loss[loss=0.192, simple_loss=0.2768, pruned_loss=0.05355, over 1422155.94 frames.], batch size: 18, lr: 3.39e-04
2022-05-27 20:51:12,606 INFO [train.py:842] (3/4) Epoch 16, batch 7600, loss[loss=0.2058, simple_loss=0.2959, pruned_loss=0.05778, over 6835.00 frames.], tot_loss[loss=0.1928, simple_loss=0.277, pruned_loss=0.05426, over 1421396.09 frames.], batch size: 31, lr: 3.39e-04
2022-05-27 20:51:51,606 INFO [train.py:842] (3/4) Epoch 16, batch 7650, loss[loss=0.169, simple_loss=0.2503, pruned_loss=0.0438, over 7015.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2778, pruned_loss=0.05479, over 1422059.18 frames.], batch size: 16, lr: 3.39e-04
2022-05-27 20:52:30,496 INFO [train.py:842] (3/4) Epoch 16, batch 7700, loss[loss=0.1695, simple_loss=0.261, pruned_loss=0.039, over 7402.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2777, pruned_loss=0.05454, over 1422761.32 frames.], batch size: 21, lr: 3.39e-04
2022-05-27 20:53:09,727 INFO [train.py:842] (3/4) Epoch 16, batch 7750, loss[loss=0.1624, simple_loss=0.249, pruned_loss=0.03793, over 7161.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2777, pruned_loss=0.05432, over 1426160.94 frames.], batch size: 18, lr: 3.39e-04
2022-05-27 20:53:48,651 INFO [train.py:842] (3/4) Epoch 16, batch 7800, loss[loss=0.2023, simple_loss=0.2956, pruned_loss=0.05448, over 6851.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2771, pruned_loss=0.05411, over 1428962.64 frames.], batch size: 31, lr: 3.39e-04
2022-05-27 20:54:27,493 INFO [train.py:842] (3/4) Epoch 16, batch 7850, loss[loss=0.2291, simple_loss=0.2982, pruned_loss=0.07994, over 6821.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2768, pruned_loss=0.05374, over 1429572.02 frames.], batch size: 15, lr: 3.39e-04
2022-05-27 20:55:06,432 INFO [train.py:842] (3/4) Epoch 16, batch 7900, loss[loss=0.1636, simple_loss=0.254, pruned_loss=0.03657, over 7362.00 frames.], tot_loss[loss=0.192, simple_loss=0.2761, pruned_loss=0.05393, over 1427087.55 frames.], batch size: 19, lr: 3.38e-04
2022-05-27 20:55:45,929 INFO [train.py:842] (3/4) Epoch 16, batch 7950, loss[loss=0.1692, simple_loss=0.251, pruned_loss=0.04368, over 7146.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2767, pruned_loss=0.05405, over 1428478.25 frames.], batch size: 17, lr: 3.38e-04
2022-05-27 20:56:24,818 INFO [train.py:842] (3/4) Epoch 16, batch 8000, loss[loss=0.1925, simple_loss=0.2618, pruned_loss=0.06158, over 7275.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2774, pruned_loss=0.05441, over 1429233.22 frames.], batch size: 18, lr: 3.38e-04
2022-05-27 20:57:04,138 INFO [train.py:842] (3/4) Epoch 16, batch 8050, loss[loss=0.1705, simple_loss=0.255, pruned_loss=0.04303, over 6781.00 frames.], tot_loss[loss=0.192, simple_loss=0.2762, pruned_loss=0.05388, over 1427341.73 frames.], batch size: 15, lr: 3.38e-04
2022-05-27 20:57:42,721 INFO [train.py:842] (3/4) Epoch 16, batch 8100, loss[loss=0.176, simple_loss=0.2663, pruned_loss=0.04284, over 7352.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2763, pruned_loss=0.0536, over 1429618.02 frames.], batch size: 19, lr: 3.38e-04
2022-05-27 20:58:21,858 INFO [train.py:842] (3/4) Epoch 16, batch 8150, loss[loss=0.1811, simple_loss=0.2666, pruned_loss=0.0478, over 7199.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2761, pruned_loss=0.05399, over 1429856.97 frames.], batch size: 22, lr: 3.38e-04
2022-05-27 20:59:00,890 INFO [train.py:842] (3/4) Epoch 16, batch 8200, loss[loss=0.1964, simple_loss=0.2496, pruned_loss=0.07155, over 6803.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2762, pruned_loss=0.05422, over 1426177.19 frames.], batch size: 15, lr: 3.38e-04
2022-05-27 20:59:39,540 INFO [train.py:842] (3/4) Epoch 16, batch 8250, loss[loss=0.1905, simple_loss=0.2704, pruned_loss=0.05534, over 7327.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2761, pruned_loss=0.05423, over 1423253.27 frames.], batch size: 25, lr: 3.38e-04
2022-05-27 21:00:18,863 INFO [train.py:842] (3/4) Epoch 16, batch 8300, loss[loss=0.1853, simple_loss=0.2777, pruned_loss=0.0464, over 7325.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2758, pruned_loss=0.05396, over 1422203.55 frames.], batch size: 20, lr: 3.38e-04
2022-05-27 21:00:57,547 INFO [train.py:842] (3/4) Epoch 16, batch 8350, loss[loss=0.178, simple_loss=0.2688, pruned_loss=0.04358, over 7164.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2765, pruned_loss=0.05393, over 1419587.59 frames.], batch size: 26, lr: 3.38e-04
2022-05-27 21:01:36,499 INFO [train.py:842] (3/4) Epoch 16, batch 8400, loss[loss=0.2142, simple_loss=0.2825, pruned_loss=0.07295, over 7217.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2762, pruned_loss=0.05408, over 1416833.54 frames.], batch size: 16, lr: 3.38e-04
2022-05-27 21:02:15,847 INFO [train.py:842] (3/4) Epoch 16, batch 8450, loss[loss=0.1863, simple_loss=0.2663, pruned_loss=0.05311, over 7432.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2768, pruned_loss=0.05434, over 1420884.06 frames.], batch size: 20, lr: 3.38e-04
2022-05-27 21:02:54,715 INFO [train.py:842] (3/4) Epoch 16, batch 8500, loss[loss=0.1832, simple_loss=0.2649, pruned_loss=0.05071, over 7144.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2762, pruned_loss=0.05408, over 1421684.79 frames.], batch size: 19, lr: 3.38e-04
2022-05-27 21:03:33,702 INFO [train.py:842] (3/4) Epoch 16, batch 8550, loss[loss=0.187, simple_loss=0.2642, pruned_loss=0.05493, over 7431.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2761, pruned_loss=0.05424, over 1421125.63 frames.], batch size: 20, lr: 3.38e-04
2022-05-27 21:04:12,822 INFO [train.py:842] (3/4) Epoch 16, batch 8600, loss[loss=0.1562, simple_loss=0.2419, pruned_loss=0.03519, over 7283.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2763, pruned_loss=0.05466, over 1420204.91 frames.], batch size: 18, lr: 3.38e-04
2022-05-27 21:04:52,326 INFO [train.py:842] (3/4) Epoch 16, batch 8650, loss[loss=0.2148, simple_loss=0.2917, pruned_loss=0.06888, over 5167.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2764, pruned_loss=0.05447, over 1415884.36 frames.], batch size: 52, lr: 3.38e-04
2022-05-27 21:05:31,131 INFO [train.py:842] (3/4) Epoch 16, batch 8700, loss[loss=0.1688, simple_loss=0.2676, pruned_loss=0.03503, over 7142.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2751, pruned_loss=0.05352, over 1411895.30 frames.], batch size: 20, lr: 3.38e-04
2022-05-27 21:06:10,268 INFO [train.py:842] (3/4) Epoch 16, batch 8750, loss[loss=0.2081, simple_loss=0.2882, pruned_loss=0.06403, over 7067.00 frames.], tot_loss[loss=0.19, simple_loss=0.2746, pruned_loss=0.05266, over 1413085.11 frames.], batch size: 18, lr: 3.38e-04
2022-05-27 21:06:48,797 INFO [train.py:842] (3/4) Epoch 16, batch 8800, loss[loss=0.2042, simple_loss=0.2883, pruned_loss=0.06006, over 7201.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2755, pruned_loss=0.05335, over 1411864.06 frames.], batch size: 22, lr: 3.37e-04
2022-05-27 21:07:27,902 INFO [train.py:842] (3/4) Epoch 16, batch 8850, loss[loss=0.1601, simple_loss=0.237, pruned_loss=0.04157, over 7068.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2765, pruned_loss=0.05418, over 1410998.25 frames.], batch size: 18, lr: 3.37e-04
2022-05-27 21:08:06,061 INFO [train.py:842] (3/4) Epoch 16, batch 8900, loss[loss=0.2152, simple_loss=0.2923, pruned_loss=0.06912, over 5362.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2779, pruned_loss=0.05523, over 1401791.18 frames.], batch size: 52, lr: 3.37e-04
2022-05-27 21:08:44,714 INFO [train.py:842] (3/4) Epoch 16, batch 8950, loss[loss=0.1844, simple_loss=0.2681, pruned_loss=0.05036, over 7249.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2783, pruned_loss=0.05515, over 1397161.23 frames.], batch size: 19, lr: 3.37e-04
2022-05-27 21:09:22,808 INFO [train.py:842] (3/4) Epoch 16, batch 9000, loss[loss=0.2404, simple_loss=0.3131, pruned_loss=0.08386, over 7119.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2804, pruned_loss=0.05623, over 1382814.32 frames.], batch size: 28, lr: 3.37e-04
2022-05-27 21:09:22,809 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 21:09:32,341 INFO [train.py:871] (3/4) Epoch 16, validation: loss=0.167, simple_loss=0.2669, pruned_loss=0.03357, over 868885.00 frames.
2022-05-27 21:10:10,581 INFO [train.py:842] (3/4) Epoch 16, batch 9050, loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03026, over 7255.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2831, pruned_loss=0.05764, over 1367733.31 frames.], batch size: 19, lr: 3.37e-04
2022-05-27 21:10:58,391 INFO [train.py:842] (3/4) Epoch 16, batch 9100, loss[loss=0.221, simple_loss=0.2982, pruned_loss=0.07187, over 4897.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2856, pruned_loss=0.05972, over 1312327.13 frames.], batch size: 52, lr: 3.37e-04
2022-05-27 21:11:46,310 INFO [train.py:842] (3/4) Epoch 16, batch 9150, loss[loss=0.2466, simple_loss=0.3314, pruned_loss=0.0809, over 5284.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2898, pruned_loss=0.06323, over 1244653.54 frames.], batch size: 53, lr: 3.37e-04
2022-05-27 21:12:47,128 INFO [train.py:842] (3/4) Epoch 17, batch 0, loss[loss=0.2238, simple_loss=0.3186, pruned_loss=0.0645, over 7102.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3186, pruned_loss=0.0645, over 7102.00 frames.], batch size: 21, lr: 3.28e-04
2022-05-27 21:13:26,310 INFO [train.py:842] (3/4) Epoch 17, batch 50, loss[loss=0.1953, simple_loss=0.2933, pruned_loss=0.04867, over 7321.00 frames.], tot_loss[loss=0.194, simple_loss=0.28, pruned_loss=0.05398, over 316912.51 frames.], batch size: 21, lr: 3.28e-04
2022-05-27 21:14:04,923 INFO [train.py:842] (3/4) Epoch 17, batch 100, loss[loss=0.1825, simple_loss=0.2689, pruned_loss=0.04806, over 7158.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2772, pruned_loss=0.05296, over 559495.73 frames.], batch size: 20, lr: 3.28e-04
2022-05-27 21:14:43,845 INFO [train.py:842] (3/4) Epoch 17, batch 150, loss[loss=0.1736, simple_loss=0.2547, pruned_loss=0.04624, over 6984.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2767, pruned_loss=0.05213, over 747469.88 frames.], batch size: 16, lr: 3.28e-04
2022-05-27 21:15:22,358 INFO [train.py:842] (3/4) Epoch 17, batch 200, loss[loss=0.1435, simple_loss=0.2285, pruned_loss=0.02927, over 7126.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2785, pruned_loss=0.05323, over 895920.67 frames.], batch size: 17, lr: 3.27e-04
2022-05-27 21:16:01,202 INFO [train.py:842] (3/4) Epoch 17, batch 250, loss[loss=0.1771, simple_loss=0.2771, pruned_loss=0.03855, over 7260.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2773, pruned_loss=0.05209, over 1015349.56 frames.], batch size: 19, lr: 3.27e-04
2022-05-27 21:16:39,725 INFO [train.py:842] (3/4) Epoch 17, batch 300, loss[loss=0.1791, simple_loss=0.258, pruned_loss=0.05008, over 7067.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2789, pruned_loss=0.05325, over 1101579.64 frames.], batch size: 18, lr: 3.27e-04
2022-05-27 21:17:18,912 INFO [train.py:842] (3/4) Epoch 17, batch 350, loss[loss=0.1769, simple_loss=0.2523, pruned_loss=0.05078, over 7259.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2781, pruned_loss=0.0539, over 1172170.64 frames.], batch size: 16, lr: 3.27e-04
2022-05-27 21:17:57,656 INFO [train.py:842] (3/4) Epoch 17, batch 400, loss[loss=0.2267, simple_loss=0.2984, pruned_loss=0.07752, over 4727.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2792, pruned_loss=0.05407, over 1227889.77 frames.], batch size: 53, lr: 3.27e-04
2022-05-27 21:18:36,677 INFO [train.py:842] (3/4) Epoch 17, batch 450, loss[loss=0.1876, simple_loss=0.2733, pruned_loss=0.05095, over 7363.00 frames.], tot_loss[loss=0.1937, simple_loss=0.279, pruned_loss=0.05422, over 1268866.17 frames.], batch size: 19, lr: 3.27e-04
2022-05-27 21:19:15,523 INFO [train.py:842] (3/4) Epoch 17, batch 500, loss[loss=0.2162, simple_loss=0.29, pruned_loss=0.07115, over 7170.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2765, pruned_loss=0.05294, over 1302570.10 frames.], batch size: 18, lr: 3.27e-04
2022-05-27 21:19:55,025 INFO [train.py:842] (3/4) Epoch 17, batch 550, loss[loss=0.1706, simple_loss=0.242, pruned_loss=0.04955, over 7152.00 frames.], tot_loss[loss=0.193, simple_loss=0.2776, pruned_loss=0.05414, over 1328384.95 frames.], batch size: 17, lr: 3.27e-04
2022-05-27 21:20:33,641 INFO [train.py:842] (3/4) Epoch 17, batch 600, loss[loss=0.2103, simple_loss=0.2993, pruned_loss=0.06061, over 7097.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2776, pruned_loss=0.05407, over 1343337.24 frames.], batch size: 28, lr: 3.27e-04
2022-05-27 21:21:12,984 INFO [train.py:842] (3/4) Epoch 17, batch 650, loss[loss=0.212, simple_loss=0.2973, pruned_loss=0.06329, over 7326.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2783, pruned_loss=0.05412, over 1361890.44 frames.], batch size: 20, lr: 3.27e-04
2022-05-27 21:21:51,616 INFO [train.py:842] (3/4) Epoch 17, batch 700, loss[loss=0.1754, simple_loss=0.2608, pruned_loss=0.04499, over 7268.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2786, pruned_loss=0.05414, over 1370297.96 frames.], batch size: 19, lr: 3.27e-04
2022-05-27 21:22:30,814 INFO [train.py:842] (3/4) Epoch 17, batch 750, loss[loss=0.1689, simple_loss=0.2636, pruned_loss=0.03712, over 7142.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2798, pruned_loss=0.05501, over 1378164.01 frames.], batch size: 20, lr: 3.27e-04
2022-05-27 21:23:09,459 INFO [train.py:842] (3/4) Epoch 17, batch 800, loss[loss=0.268, simple_loss=0.3426, pruned_loss=0.09673, over 7155.00 frames.], tot_loss[loss=0.195, simple_loss=0.2798, pruned_loss=0.05505, over 1388541.98 frames.], batch size: 19, lr: 3.27e-04
2022-05-27 21:23:48,547 INFO [train.py:842] (3/4) Epoch 17, batch 850, loss[loss=0.2117, simple_loss=0.2925, pruned_loss=0.06542, over 6345.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2791, pruned_loss=0.05472, over 1396891.64 frames.], batch size: 37, lr: 3.27e-04
2022-05-27 21:24:27,499 INFO [train.py:842] (3/4) Epoch 17, batch 900, loss[loss=0.2012, simple_loss=0.2951, pruned_loss=0.05361, over 7329.00 frames.], tot_loss[loss=0.1939, simple_loss=0.279, pruned_loss=0.05439, over 1408602.29 frames.], batch size: 20, lr: 3.27e-04
2022-05-27 21:25:06,299 INFO [train.py:842] (3/4) Epoch 17, batch 950, loss[loss=0.1471, simple_loss=0.2321, pruned_loss=0.03101, over 7126.00 frames.], tot_loss[loss=0.193, simple_loss=0.2784, pruned_loss=0.05383, over 1412965.36 frames.], batch size: 17, lr: 3.27e-04
2022-05-27 21:25:44,922 INFO [train.py:842] (3/4) Epoch 17, batch 1000, loss[loss=0.1993, simple_loss=0.2896, pruned_loss=0.05454, over 7445.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2779, pruned_loss=0.05378, over 1417420.48 frames.], batch size: 22, lr: 3.27e-04
2022-05-27 21:26:24,314 INFO [train.py:842] (3/4) Epoch 17, batch 1050, loss[loss=0.1911, simple_loss=0.2853, pruned_loss=0.04846, over 7331.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2767, pruned_loss=0.05335, over 1421479.27 frames.], batch size: 22, lr: 3.27e-04
2022-05-27 21:27:03,148 INFO [train.py:842] (3/4) Epoch 17, batch 1100, loss[loss=0.2099, simple_loss=0.3018, pruned_loss=0.05904, over 7278.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2776, pruned_loss=0.05366, over 1422254.46 frames.], batch size: 24, lr: 3.26e-04
2022-05-27 21:27:42,208 INFO [train.py:842] (3/4) Epoch 17, batch 1150, loss[loss=0.2101, simple_loss=0.2913, pruned_loss=0.06443, over 7302.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2793, pruned_loss=0.05481, over 1423463.94 frames.], batch size: 24, lr: 3.26e-04
2022-05-27 21:28:20,866 INFO [train.py:842] (3/4) Epoch 17, batch 1200, loss[loss=0.2148, simple_loss=0.2956, pruned_loss=0.06697, over 7296.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2784, pruned_loss=0.05446, over 1420545.81 frames.], batch size: 25, lr: 3.26e-04
2022-05-27 21:28:59,949 INFO [train.py:842] (3/4) Epoch 17, batch 1250, loss[loss=0.1648, simple_loss=0.2493, pruned_loss=0.04016, over 7277.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2784, pruned_loss=0.05433, over 1415854.03 frames.], batch size: 18, lr: 3.26e-04
2022-05-27 21:29:38,957 INFO [train.py:842] (3/4) Epoch 17, batch 1300, loss[loss=0.1966, simple_loss=0.3014, pruned_loss=0.04589, over 7335.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2771, pruned_loss=0.0536, over 1414073.42 frames.], batch size: 22, lr: 3.26e-04
2022-05-27 21:30:18,044 INFO [train.py:842] (3/4) Epoch 17, batch 1350, loss[loss=0.1654, simple_loss=0.2461, pruned_loss=0.04237, over 7005.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2775, pruned_loss=0.05339, over 1419406.63 frames.], batch size: 16, lr: 3.26e-04
2022-05-27 21:30:56,923 INFO [train.py:842] (3/4) Epoch 17, batch 1400, loss[loss=0.193, simple_loss=0.291, pruned_loss=0.04745, over 7146.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2769, pruned_loss=0.05338, over 1420725.08 frames.], batch size: 20, lr: 3.26e-04
2022-05-27 21:31:36,145 INFO [train.py:842] (3/4) Epoch 17, batch 1450, loss[loss=0.192, simple_loss=0.2819, pruned_loss=0.05109, over 7347.00 frames.], tot_loss[loss=0.1917, simple_loss=0.277, pruned_loss=0.05324, over 1419833.56 frames.], batch size: 22, lr: 3.26e-04
2022-05-27 21:32:15,400 INFO [train.py:842] (3/4) Epoch 17, batch 1500, loss[loss=0.1719, simple_loss=0.254, pruned_loss=0.04492, over 7249.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2763, pruned_loss=0.05338, over 1425758.62 frames.], batch size: 19, lr: 3.26e-04
2022-05-27 21:32:54,710 INFO [train.py:842] (3/4) Epoch 17, batch 1550, loss[loss=0.1825, simple_loss=0.2706, pruned_loss=0.04714, over 7227.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2766, pruned_loss=0.05352, over 1422814.17 frames.], batch size: 21, lr: 3.26e-04
2022-05-27 21:33:33,701 INFO [train.py:842] (3/4) Epoch 17, batch 1600, loss[loss=0.1773, simple_loss=0.2736, pruned_loss=0.04048, over 7428.00 frames.], tot_loss[loss=0.19, simple_loss=0.2753, pruned_loss=0.05236, over 1427182.67 frames.], batch size: 20, lr: 3.26e-04
2022-05-27 21:34:12,941 INFO [train.py:842] (3/4) Epoch 17, batch 1650, loss[loss=0.187, simple_loss=0.2674, pruned_loss=0.05331, over 7416.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2774, pruned_loss=0.05337, over 1428911.06 frames.], batch size: 21, lr: 3.26e-04
2022-05-27 21:34:51,648 INFO [train.py:842] (3/4) Epoch 17, batch 1700, loss[loss=0.2446, simple_loss=0.3265, pruned_loss=0.08135, over 5066.00 frames.], tot_loss[loss=0.193, simple_loss=0.278, pruned_loss=0.05403, over 1423187.93 frames.], batch size: 52, lr: 3.26e-04
2022-05-27 21:35:30,468 INFO [train.py:842] (3/4) Epoch 17, batch 1750, loss[loss=0.2078, simple_loss=0.2944, pruned_loss=0.06063, over 7385.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2781, pruned_loss=0.05417, over 1414028.74 frames.], batch size: 23, lr: 3.26e-04
2022-05-27 21:36:09,010 INFO [train.py:842] (3/4) Epoch 17, batch 1800, loss[loss=0.1911, simple_loss=0.286, pruned_loss=0.04806, over 7202.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2793, pruned_loss=0.05488, over 1415445.56 frames.], batch size: 23, lr: 3.26e-04
2022-05-27 21:36:48,046 INFO [train.py:842] (3/4) Epoch 17, batch 1850, loss[loss=0.1691, simple_loss=0.2717, pruned_loss=0.03323, over 6363.00 frames.], tot_loss[loss=0.1944, simple_loss=0.279, pruned_loss=0.05489, over 1416386.82 frames.], batch size: 38, lr: 3.26e-04
2022-05-27 21:37:26,830 INFO [train.py:842] (3/4) Epoch 17, batch 1900, loss[loss=0.1574, simple_loss=0.2507, pruned_loss=0.03206, over 7426.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2787, pruned_loss=0.05482, over 1420869.99 frames.], batch size: 20, lr: 3.26e-04
2022-05-27 21:38:05,896 INFO [train.py:842] (3/4) Epoch 17, batch 1950, loss[loss=0.1935, simple_loss=0.2836, pruned_loss=0.05168, over 7323.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2791, pruned_loss=0.05513, over 1423160.05 frames.], batch size: 21, lr: 3.26e-04
2022-05-27 21:38:44,434 INFO [train.py:842] (3/4) Epoch 17, batch 2000, loss[loss=0.1604, simple_loss=0.2499, pruned_loss=0.0354, over 7266.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2784, pruned_loss=0.05461, over 1424687.94 frames.], batch size: 19, lr: 3.25e-04
2022-05-27 21:39:23,663 INFO [train.py:842] (3/4) Epoch 17, batch 2050, loss[loss=0.1607, simple_loss=0.2456, pruned_loss=0.03792, over 7421.00 frames.], tot_loss[loss=0.193, simple_loss=0.2775, pruned_loss=0.0543, over 1428035.41 frames.], batch size: 18, lr: 3.25e-04
2022-05-27 21:40:02,214 INFO [train.py:842] (3/4) Epoch 17, batch 2100, loss[loss=0.1917, simple_loss=0.2839, pruned_loss=0.04973, over 7404.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2773, pruned_loss=0.0539, over 1429192.86 frames.], batch size: 21, lr: 3.25e-04
2022-05-27 21:40:41,307 INFO [train.py:842] (3/4) Epoch 17, batch 2150, loss[loss=0.191, simple_loss=0.2742, pruned_loss=0.05393, over 7356.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2769, pruned_loss=0.05371, over 1425776.50 frames.], batch size: 19, lr: 3.25e-04
2022-05-27 21:41:20,100 INFO [train.py:842] (3/4) Epoch 17, batch 2200, loss[loss=0.19, simple_loss=0.2948, pruned_loss=0.04259, over 7327.00 frames.], tot_loss[loss=0.192, simple_loss=0.277, pruned_loss=0.05347, over 1422010.61 frames.], batch size: 22, lr: 3.25e-04
2022-05-27 21:41:59,494 INFO [train.py:842] (3/4) Epoch 17, batch 2250, loss[loss=0.177, simple_loss=0.2671, pruned_loss=0.04346, over 7421.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2777, pruned_loss=0.05407, over 1424034.22 frames.], batch size: 21, lr: 3.25e-04
2022-05-27 21:42:38,197 INFO [train.py:842] (3/4) Epoch 17, batch 2300, loss[loss=0.2125, simple_loss=0.2877, pruned_loss=0.06861, over 7305.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2772, pruned_loss=0.05405, over 1423459.26 frames.], batch size: 24, lr: 3.25e-04
2022-05-27 21:43:17,613 INFO [train.py:842] (3/4) Epoch 17, batch 2350, loss[loss=0.2153, simple_loss=0.2966, pruned_loss=0.067, over 7367.00 frames.], tot_loss[loss=0.1911, simple_loss=0.276, pruned_loss=0.05309, over 1427114.76 frames.], batch size: 23, lr: 3.25e-04
2022-05-27 21:43:56,283 INFO [train.py:842] (3/4) Epoch 17, batch 2400, loss[loss=0.2364, simple_loss=0.3015, pruned_loss=0.08568, over 6992.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2758, pruned_loss=0.053, over 1424764.62 frames.], batch size: 16, lr: 3.25e-04
2022-05-27 21:44:35,708 INFO [train.py:842] (3/4) Epoch 17, batch 2450, loss[loss=0.1884, simple_loss=0.2761, pruned_loss=0.05031, over 7345.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2745, pruned_loss=0.05237, over 1424271.13 frames.], batch size: 22, lr: 3.25e-04
2022-05-27 21:45:14,369 INFO [train.py:842] (3/4) Epoch 17, batch 2500, loss[loss=0.1582, simple_loss=0.2557, pruned_loss=0.03035, over 7225.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2736, pruned_loss=0.05177, over 1424394.11 frames.], batch size: 21, lr: 3.25e-04
2022-05-27 21:45:53,525 INFO [train.py:842] (3/4) Epoch 17, batch 2550, loss[loss=0.1902, simple_loss=0.2813, pruned_loss=0.04958, over 7223.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2733, pruned_loss=0.05187, over 1420616.68 frames.], batch size: 21, lr: 3.25e-04
2022-05-27 21:46:32,091 INFO [train.py:842] (3/4) Epoch 17, batch 2600, loss[loss=0.2192, simple_loss=0.309, pruned_loss=0.06472, over 6972.00 frames.], tot_loss[loss=0.1896, simple_loss=0.275, pruned_loss=0.05206, over 1422264.73 frames.], batch size: 28, lr: 3.25e-04
2022-05-27 21:47:11,547 INFO [train.py:842] (3/4) Epoch 17, batch 2650, loss[loss=0.2256, simple_loss=0.2865, pruned_loss=0.08234, over 7351.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2763, pruned_loss=0.05305, over 1420310.95 frames.], batch size: 19, lr: 3.25e-04
2022-05-27 21:47:50,587 INFO [train.py:842] (3/4) Epoch 17, batch 2700, loss[loss=0.1742, simple_loss=0.2773, pruned_loss=0.03549, over 7342.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2751, pruned_loss=0.05279, over 1423345.30 frames.], batch size: 22, lr: 3.25e-04
2022-05-27 21:48:29,826 INFO [train.py:842] (3/4) Epoch 17, batch 2750, loss[loss=0.1968, simple_loss=0.2775, pruned_loss=0.05804, over 7165.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2736, pruned_loss=0.05232, over 1422508.94 frames.], batch size: 19, lr: 3.25e-04
2022-05-27 21:49:09,022 INFO [train.py:842] (3/4) Epoch 17, batch 2800, loss[loss=0.2585, simple_loss=0.3338, pruned_loss=0.09154, over 4967.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2744, pruned_loss=0.05331, over 1421702.26 frames.], batch size: 52, lr: 3.25e-04
2022-05-27 21:49:47,937 INFO [train.py:842] (3/4) Epoch 17, batch 2850, loss[loss=0.2234, simple_loss=0.3067, pruned_loss=0.07008, over 7329.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2756, pruned_loss=0.05351, over 1421692.03 frames.], batch size: 21, lr: 3.25e-04
2022-05-27 21:50:27,042 INFO [train.py:842] (3/4) Epoch 17, batch 2900, loss[loss=0.209, simple_loss=0.2963, pruned_loss=0.06086, over 7238.00 frames.], tot_loss[loss=0.192, simple_loss=0.2763, pruned_loss=0.0539, over 1417475.86 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 21:51:06,320 INFO [train.py:842] (3/4) Epoch 17, batch 2950, loss[loss=0.1616, simple_loss=0.2447, pruned_loss=0.0392, over 7267.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2762, pruned_loss=0.05344, over 1418230.72 frames.], batch size: 18, lr: 3.24e-04
2022-05-27 21:51:45,531 INFO [train.py:842] (3/4) Epoch 17, batch 3000, loss[loss=0.1702, simple_loss=0.2588, pruned_loss=0.04084, over 7151.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2755, pruned_loss=0.05269, over 1423730.99 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 21:51:45,531 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 21:51:55,147 INFO [train.py:871] (3/4) Epoch 17, validation: loss=0.1666, simple_loss=0.2663, pruned_loss=0.03343, over 868885.00 frames.
2022-05-27 21:52:34,187 INFO [train.py:842] (3/4) Epoch 17, batch 3050, loss[loss=0.1899, simple_loss=0.2802, pruned_loss=0.04979, over 6307.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2749, pruned_loss=0.05242, over 1423631.53 frames.], batch size: 38, lr: 3.24e-04
2022-05-27 21:53:12,921 INFO [train.py:842] (3/4) Epoch 17, batch 3100, loss[loss=0.262, simple_loss=0.3482, pruned_loss=0.08794, over 7294.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2751, pruned_loss=0.05228, over 1420610.02 frames.], batch size: 25, lr: 3.24e-04
2022-05-27 21:53:52,117 INFO [train.py:842] (3/4) Epoch 17, batch 3150, loss[loss=0.208, simple_loss=0.2796, pruned_loss=0.0682, over 7324.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2755, pruned_loss=0.05283, over 1419889.02 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 21:54:30,925 INFO [train.py:842] (3/4) Epoch 17, batch 3200, loss[loss=0.1686, simple_loss=0.2556, pruned_loss=0.04082, over 7368.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2764, pruned_loss=0.05358, over 1419759.26 frames.], batch size: 19, lr: 3.24e-04
2022-05-27 21:55:10,327 INFO [train.py:842] (3/4) Epoch 17, batch 3250, loss[loss=0.1473, simple_loss=0.2326, pruned_loss=0.03096, over 7064.00 frames.], tot_loss[loss=0.191, simple_loss=0.2759, pruned_loss=0.05301, over 1424940.73 frames.], batch size: 18, lr: 3.24e-04
2022-05-27 21:55:49,267 INFO [train.py:842] (3/4) Epoch 17, batch 3300, loss[loss=0.2615, simple_loss=0.3262, pruned_loss=0.09842, over 7161.00 frames.], tot_loss[loss=0.193, simple_loss=0.278, pruned_loss=0.05396, over 1425578.06 frames.], batch size: 19, lr: 3.24e-04
2022-05-27 21:56:28,702 INFO [train.py:842] (3/4) Epoch 17, batch 3350, loss[loss=0.2078, simple_loss=0.2961, pruned_loss=0.05979, over 7314.00 frames.], tot_loss[loss=0.1917, simple_loss=0.277, pruned_loss=0.05319, over 1426848.48 frames.], batch size: 22, lr: 3.24e-04
2022-05-27 21:57:07,354 INFO [train.py:842] (3/4) Epoch 17, batch 3400, loss[loss=0.1841, simple_loss=0.2859, pruned_loss=0.04116, over 7144.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2777, pruned_loss=0.05359, over 1423788.61 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 21:57:46,435 INFO [train.py:842] (3/4) Epoch 17, batch 3450, loss[loss=0.1402, simple_loss=0.2299, pruned_loss=0.02522, over 7335.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2751, pruned_loss=0.05271, over 1424600.45 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 21:58:25,551 INFO [train.py:842] (3/4) Epoch 17, batch 3500, loss[loss=0.2228, simple_loss=0.3001, pruned_loss=0.07275, over 7211.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2754, pruned_loss=0.05337, over 1424113.25 frames.], batch size: 22, lr: 3.24e-04
2022-05-27 21:59:04,653 INFO [train.py:842] (3/4) Epoch 17, batch 3550, loss[loss=0.1699, simple_loss=0.2574, pruned_loss=0.04126, over 7116.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2756, pruned_loss=0.05289, over 1426472.96 frames.], batch size: 21, lr: 3.24e-04
2022-05-27 21:59:43,840 INFO [train.py:842] (3/4) Epoch 17, batch 3600, loss[loss=0.1739, simple_loss=0.256, pruned_loss=0.04588, over 7271.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2767, pruned_loss=0.05329, over 1427129.82 frames.], batch size: 18, lr: 3.24e-04
2022-05-27 22:00:23,014 INFO [train.py:842] (3/4) Epoch 17, batch 3650, loss[loss=0.1742, simple_loss=0.252, pruned_loss=0.04819, over 7323.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2759, pruned_loss=0.05317, over 1430270.95 frames.], batch size: 21, lr: 3.24e-04
2022-05-27 22:01:02,004 INFO [train.py:842] (3/4) Epoch 17, batch 3700, loss[loss=0.1899, simple_loss=0.2703, pruned_loss=0.05474, over 7157.00 frames.], tot_loss[loss=0.191, simple_loss=0.2756, pruned_loss=0.05319, over 1429596.46 frames.], batch size: 20, lr: 3.24e-04
2022-05-27 22:01:41,177 INFO [train.py:842] (3/4) Epoch 17, batch 3750, loss[loss=0.168, simple_loss=0.262, pruned_loss=0.03695, over 6395.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2755, pruned_loss=0.05286, over 1427077.39 frames.], batch size: 38, lr: 3.24e-04
2022-05-27 22:02:19,660 INFO [train.py:842] (3/4) Epoch 17, batch 3800, loss[loss=0.1917, simple_loss=0.281, pruned_loss=0.05123, over 6428.00 frames.], tot_loss[loss=0.1909, simple_loss=0.276, pruned_loss=0.05286, over 1425862.85 frames.], batch size: 38, lr: 3.24e-04
2022-05-27 22:02:58,466 INFO [train.py:842] (3/4) Epoch 17, batch 3850, loss[loss=0.1904, simple_loss=0.2647, pruned_loss=0.05802, over 7014.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2764, pruned_loss=0.05286, over 1425560.75 frames.], batch size: 16, lr: 3.23e-04
2022-05-27 22:03:37,693 INFO [train.py:842] (3/4) Epoch 17, batch 3900, loss[loss=0.2428, simple_loss=0.3219, pruned_loss=0.08184, over 7218.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2764, pruned_loss=0.05316, over 1428085.13 frames.], batch size: 22, lr: 3.23e-04
2022-05-27 22:04:16,900 INFO [train.py:842] (3/4) Epoch 17, batch 3950, loss[loss=0.2017, simple_loss=0.2888, pruned_loss=0.05728, over 7181.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2763, pruned_loss=0.05293, over 1427041.68 frames.], batch size: 23, lr: 3.23e-04
2022-05-27 22:04:55,782 INFO [train.py:842] (3/4) Epoch 17, batch 4000, loss[loss=0.1761, simple_loss=0.2592, pruned_loss=0.04653, over 7278.00 frames.], tot_loss[loss=0.191, simple_loss=0.2758, pruned_loss=0.05312, over 1427529.53 frames.], batch size: 18, lr: 3.23e-04
2022-05-27 22:05:35,082 INFO [train.py:842] (3/4) Epoch 17, batch 4050, loss[loss=0.1866, simple_loss=0.2842, pruned_loss=0.04455, over 6802.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2749, pruned_loss=0.05283, over 1424013.91 frames.], batch size: 31, lr: 3.23e-04
2022-05-27 22:06:13,936 INFO [train.py:842] (3/4) Epoch 17, batch 4100, loss[loss=0.2697, simple_loss=0.344, pruned_loss=0.09769, over 6402.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2774, pruned_loss=0.05392, over 1423202.81 frames.], batch size: 38, lr: 3.23e-04
2022-05-27 22:06:52,835 INFO [train.py:842] (3/4) Epoch 17, batch 4150, loss[loss=0.1741, simple_loss=0.2616, pruned_loss=0.04332, over 7352.00 frames.], tot_loss[loss=0.1912, simple_loss=0.276, pruned_loss=0.05324, over 1422788.67 frames.], batch size: 22, lr: 3.23e-04
2022-05-27 22:07:31,507 INFO [train.py:842] (3/4) Epoch 17, batch 4200, loss[loss=0.1623, simple_loss=0.2596, pruned_loss=0.03246, over 7167.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2752, pruned_loss=0.05257, over 1422473.96 frames.], batch size: 19, lr: 3.23e-04
2022-05-27 22:08:10,864 INFO [train.py:842] (3/4) Epoch 17, batch 4250, loss[loss=0.1854, simple_loss=0.2671, pruned_loss=0.05188, over 7137.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2746, pruned_loss=0.0523, over 1425146.47 frames.], batch size: 17, lr: 3.23e-04
2022-05-27 22:08:49,637 INFO [train.py:842] (3/4) Epoch 17, batch 4300, loss[loss=0.227, simple_loss=0.3169, pruned_loss=0.06857, over 7312.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2756, pruned_loss=0.05284, over 1422489.32 frames.], batch size: 21, lr: 3.23e-04
2022-05-27 22:09:29,071 INFO [train.py:842] (3/4) Epoch 17, batch 4350, loss[loss=0.2161, simple_loss=0.2947, pruned_loss=0.06872, over 6769.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2748, pruned_loss=0.05242, over 1420987.03 frames.], batch size: 31, lr: 3.23e-04
2022-05-27 22:10:08,022 INFO [train.py:842] (3/4) Epoch 17, batch 4400, loss[loss=0.1512, simple_loss=0.2355, pruned_loss=0.03344, over 7257.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2729, pruned_loss=0.05143, over 1423310.67 frames.], batch size: 19, lr: 3.23e-04
2022-05-27 22:10:47,307 INFO [train.py:842] (3/4) Epoch 17, batch 4450, loss[loss=0.1808, simple_loss=0.2575, pruned_loss=0.05207, over 7067.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2729, pruned_loss=0.05189, over 1426502.86 frames.], batch size: 18, lr: 3.23e-04
2022-05-27 22:11:26,016 INFO [train.py:842] (3/4) Epoch 17, batch 4500, loss[loss=0.2298, simple_loss=0.3105, pruned_loss=0.07456, over 6555.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2739, pruned_loss=0.05231, over 1423402.80 frames.], batch size: 38, lr: 3.23e-04
2022-05-27 22:12:04,908 INFO [train.py:842] (3/4) Epoch 17, batch 4550, loss[loss=0.1898, simple_loss=0.2849, pruned_loss=0.04734, over 7331.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2756, pruned_loss=0.05286, over 1422397.83 frames.], batch size: 22, lr: 3.23e-04
2022-05-27 22:12:43,483 INFO [train.py:842] (3/4) Epoch 17, batch 4600, loss[loss=0.2243, simple_loss=0.3111, pruned_loss=0.06878, over 7203.00 frames.], tot_loss[loss=0.1897, simple_loss=0.275, pruned_loss=0.05217, over 1424586.60 frames.], batch size: 22, lr: 3.23e-04
2022-05-27 22:13:22,541 INFO [train.py:842] (3/4) Epoch 17, batch 4650, loss[loss=0.2165, simple_loss=0.3054, pruned_loss=0.06382, over 7324.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2738, pruned_loss=0.05148, over 1427237.02 frames.], batch size: 22, lr: 3.23e-04
2022-05-27 22:14:01,628 INFO [train.py:842] (3/4) Epoch 17, batch 4700, loss[loss=0.2079, simple_loss=0.2942, pruned_loss=0.06078, over 7213.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2747, pruned_loss=0.05205, over 1421913.90 frames.], batch size: 21, lr: 3.23e-04
2022-05-27 22:14:40,347 INFO [train.py:842] (3/4) Epoch 17, batch 4750, loss[loss=0.1639, simple_loss=0.2556, pruned_loss=0.03606, over 7069.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2756, pruned_loss=0.05212, over 1423372.78 frames.], batch size: 18, lr: 3.23e-04
2022-05-27 22:15:19,267 INFO [train.py:842] (3/4) Epoch 17, batch 4800, loss[loss=0.1889, simple_loss=0.2664, pruned_loss=0.05565, over 7305.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2746, pruned_loss=0.0515, over 1423361.97 frames.], batch size: 17, lr: 3.22e-04
2022-05-27 22:15:58,814 INFO [train.py:842] (3/4) Epoch 17, batch 4850, loss[loss=0.1989, simple_loss=0.2767, pruned_loss=0.06057, over 7066.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2754, pruned_loss=0.05218, over 1422018.32 frames.], batch size: 18, lr: 3.22e-04
2022-05-27 22:16:37,948 INFO [train.py:842] (3/4) Epoch 17, batch 4900, loss[loss=0.1946, simple_loss=0.283, pruned_loss=0.0531, over 7211.00 frames.], tot_loss[loss=0.1901, simple_loss=0.275, pruned_loss=0.05261, over 1423096.14 frames.], batch size: 26, lr: 3.22e-04
2022-05-27 22:17:20,304 INFO [train.py:842] (3/4) Epoch 17, batch 4950, loss[loss=0.1695, simple_loss=0.2401, pruned_loss=0.04942, over 6792.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2725, pruned_loss=0.05169, over 1425068.38 frames.], batch size: 15, lr: 3.22e-04
2022-05-27 22:17:59,075 INFO [train.py:842] (3/4) Epoch 17, batch 5000, loss[loss=0.1313, simple_loss=0.2204, pruned_loss=0.02109, over 7426.00 frames.], tot_loss[loss=0.188, simple_loss=0.2729, pruned_loss=0.05157, over 1422629.24 frames.], batch size: 17, lr: 3.22e-04
2022-05-27 22:18:38,083 INFO [train.py:842] (3/4) Epoch 17, batch 5050, loss[loss=0.1823, simple_loss=0.259, pruned_loss=0.05277, over 7286.00 frames.], tot_loss[loss=0.187, simple_loss=0.2723, pruned_loss=0.05083, over 1423476.30 frames.], batch size: 18, lr: 3.22e-04
2022-05-27 22:19:17,096 INFO [train.py:842] (3/4) Epoch 17, batch 5100, loss[loss=0.1798, simple_loss=0.2654, pruned_loss=0.04708, over 7004.00 frames.], tot_loss[loss=0.188, simple_loss=0.2733, pruned_loss=0.0513, over 1422464.40 frames.], batch size: 16, lr: 3.22e-04
2022-05-27 22:19:56,243 INFO [train.py:842] (3/4) Epoch 17, batch 5150, loss[loss=0.2013, simple_loss=0.2809, pruned_loss=0.06089, over 7236.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2742, pruned_loss=0.05229, over 1419920.97 frames.], batch size: 20, lr: 3.22e-04
2022-05-27 22:20:35,418 INFO [train.py:842] (3/4) Epoch 17, batch 5200, loss[loss=0.1592, simple_loss=0.2555, pruned_loss=0.03143, over 7155.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2732, pruned_loss=0.05152, over 1424334.10 frames.], batch size: 20, lr: 3.22e-04
2022-05-27 22:21:14,396 INFO [train.py:842] (3/4) Epoch 17, batch 5250, loss[loss=0.2399, simple_loss=0.3153, pruned_loss=0.0822, over 7104.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2733, pruned_loss=0.05178, over 1423575.10 frames.], batch size: 21, lr: 3.22e-04
2022-05-27 22:21:53,442 INFO [train.py:842] (3/4) Epoch 17, batch 5300, loss[loss=0.2097, simple_loss=0.2899, pruned_loss=0.06468, over 6810.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2736, pruned_loss=0.05205, over 1422252.97 frames.], batch size: 15, lr: 3.22e-04
2022-05-27 22:22:32,641 INFO [train.py:842] (3/4) Epoch 17, batch 5350, loss[loss=0.1349, simple_loss=0.2188, pruned_loss=0.02552, over 6771.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2752, pruned_loss=0.05319, over 1423035.01 frames.], batch size: 15, lr: 3.22e-04
2022-05-27 22:23:11,623 INFO [train.py:842] (3/4) Epoch 17, batch 5400, loss[loss=0.2116, simple_loss=0.3054, pruned_loss=0.05885, over 7237.00 frames.], tot_loss[loss=0.191, simple_loss=0.2755, pruned_loss=0.0532, over 1423248.36 frames.], batch size: 20, lr: 3.22e-04
2022-05-27 22:23:51,031 INFO [train.py:842] (3/4) Epoch 17, batch 5450, loss[loss=0.1961, simple_loss=0.2842, pruned_loss=0.05402, over 7172.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2759, pruned_loss=0.05313, over 1426301.33 frames.], batch size: 19, lr: 3.22e-04
2022-05-27 22:24:29,924 INFO [train.py:842] (3/4) Epoch 17, batch 5500, loss[loss=0.1993, simple_loss=0.2787, pruned_loss=0.05997, over 7270.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2765, pruned_loss=0.05361, over 1426828.51 frames.], batch size: 24, lr: 3.22e-04
2022-05-27 22:25:09,380 INFO [train.py:842] (3/4) Epoch 17, batch 5550, loss[loss=0.1791, simple_loss=0.2716, pruned_loss=0.04335, over 7245.00 frames.], tot_loss[loss=0.192, simple_loss=0.2767, pruned_loss=0.05361, over 1428337.72 frames.], batch size: 20, lr: 3.22e-04
2022-05-27 22:25:48,417 INFO [train.py:842] (3/4) Epoch 17, batch 5600, loss[loss=0.1905, simple_loss=0.2707, pruned_loss=0.05515, over 7326.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2756, pruned_loss=0.05331, over 1432009.41 frames.], batch size: 20, lr: 3.22e-04
2022-05-27 22:26:27,336 INFO [train.py:842] (3/4) Epoch 17, batch 5650, loss[loss=0.2046, simple_loss=0.3038, pruned_loss=0.05271, over 7310.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2776, pruned_loss=0.05402, over 1430038.56 frames.], batch size: 24, lr: 3.22e-04
2022-05-27 22:27:05,752 INFO [train.py:842] (3/4) Epoch 17, batch 5700, loss[loss=0.1533, simple_loss=0.237, pruned_loss=0.03485, over 7403.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2776, pruned_loss=0.05376, over 1428648.93 frames.], batch size: 18, lr: 3.22e-04
2022-05-27 22:27:45,006 INFO [train.py:842] (3/4) Epoch 17, batch 5750, loss[loss=0.2096, simple_loss=0.2943, pruned_loss=0.06246, over 6384.00 frames.], tot_loss[loss=0.192, simple_loss=0.2767, pruned_loss=0.05362, over 1421110.57 frames.], batch size: 38, lr: 3.21e-04
2022-05-27 22:28:23,798 INFO [train.py:842] (3/4) Epoch 17, batch 5800, loss[loss=0.1867, simple_loss=0.2787, pruned_loss=0.04738, over 7322.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2761, pruned_loss=0.05324, over 1421425.53 frames.], batch size: 20, lr: 3.21e-04
2022-05-27 22:29:02,981 INFO [train.py:842] (3/4) Epoch 17, batch 5850, loss[loss=0.1579, simple_loss=0.2515, pruned_loss=0.0322, over 7279.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2761, pruned_loss=0.05271, over 1425335.89 frames.], batch size: 18, lr: 3.21e-04
2022-05-27 22:29:41,701 INFO [train.py:842] (3/4) Epoch 17, batch 5900, loss[loss=0.1769, simple_loss=0.2651, pruned_loss=0.04438, over 7367.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2759, pruned_loss=0.05276, over 1425067.15 frames.], batch size: 23, lr: 3.21e-04
2022-05-27 22:30:20,740 INFO [train.py:842] (3/4) Epoch 17, batch 5950, loss[loss=0.2587, simple_loss=0.3323, pruned_loss=0.09256, over 7158.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2768, pruned_loss=0.05363, over 1419547.57 frames.], batch size: 26, lr: 3.21e-04
2022-05-27 22:30:59,324 INFO [train.py:842] (3/4) Epoch 17, batch 6000, loss[loss=0.2161, simple_loss=0.3123, pruned_loss=0.05997, over 7328.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2775, pruned_loss=0.05387, over 1419669.28 frames.], batch size: 20, lr: 3.21e-04
2022-05-27 22:30:59,325 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 22:31:09,110 INFO [train.py:871] (3/4) Epoch 17, validation: loss=0.1659, simple_loss=0.2656, pruned_loss=0.03306, over 868885.00 frames.
2022-05-27 22:31:48,630 INFO [train.py:842] (3/4) Epoch 17, batch 6050, loss[loss=0.1737, simple_loss=0.2642, pruned_loss=0.04162, over 7336.00 frames.], tot_loss[loss=0.1932, simple_loss=0.278, pruned_loss=0.05419, over 1423019.95 frames.], batch size: 21, lr: 3.21e-04
2022-05-27 22:32:27,139 INFO [train.py:842] (3/4) Epoch 17, batch 6100, loss[loss=0.1989, simple_loss=0.2941, pruned_loss=0.05187, over 7203.00 frames.], tot_loss[loss=0.193, simple_loss=0.2778, pruned_loss=0.05406, over 1424954.99 frames.], batch size: 23, lr: 3.21e-04
2022-05-27 22:33:05,948 INFO [train.py:842] (3/4) Epoch 17, batch 6150, loss[loss=0.1538, simple_loss=0.2353, pruned_loss=0.03614, over 6802.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2772, pruned_loss=0.05359, over 1419852.96 frames.], batch size: 15, lr: 3.21e-04
2022-05-27 22:33:44,753 INFO [train.py:842] (3/4) Epoch 17, batch 6200, loss[loss=0.1828, simple_loss=0.2688, pruned_loss=0.04847, over 7408.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2772, pruned_loss=0.05369, over 1420934.62 frames.], batch size: 21, lr: 3.21e-04
2022-05-27 22:34:23,867 INFO [train.py:842] (3/4) Epoch 17, batch 6250, loss[loss=0.1655, simple_loss=0.2632, pruned_loss=0.03388, over 6766.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2781, pruned_loss=0.05449, over 1420000.00 frames.], batch size: 31, lr: 3.21e-04
2022-05-27 22:35:02,519 INFO [train.py:842] (3/4) Epoch 17, batch 6300, loss[loss=0.1983, simple_loss=0.288, pruned_loss=0.05437, over 7409.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2771, pruned_loss=0.05386, over 1419757.02 frames.], batch size: 21, lr: 3.21e-04
2022-05-27 22:35:41,908 INFO [train.py:842] (3/4) Epoch 17, batch 6350, loss[loss=0.1628, simple_loss=0.2367, pruned_loss=0.04449, over 7282.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2765, pruned_loss=0.05393, over 1424037.36 frames.], batch size: 17, lr: 3.21e-04
2022-05-27 22:36:20,831 INFO [train.py:842] (3/4) Epoch 17, batch 6400, loss[loss=0.1968, simple_loss=0.2807, pruned_loss=0.05646, over 7234.00 frames.], tot_loss[loss=0.191, simple_loss=0.2757, pruned_loss=0.05317, over 1428947.29 frames.], batch size: 20, lr: 3.21e-04
2022-05-27 22:36:59,896 INFO [train.py:842] (3/4) Epoch 17, batch 6450, loss[loss=0.1655, simple_loss=0.2531, pruned_loss=0.03893, over 7361.00 frames.], tot_loss[loss=0.19, simple_loss=0.2749, pruned_loss=0.05256, over 1427931.71 frames.], batch size: 19, lr: 3.21e-04
2022-05-27 22:37:38,909 INFO [train.py:842] (3/4) Epoch 17, batch 6500, loss[loss=0.1675, simple_loss=0.249, pruned_loss=0.04298, over 7406.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2756, pruned_loss=0.05292, over 1428999.62 frames.], batch size: 18, lr: 3.21e-04
2022-05-27 22:38:18,079 INFO [train.py:842] (3/4) Epoch 17, batch 6550, loss[loss=0.2113, simple_loss=0.2866, pruned_loss=0.06797, over 7217.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2754, pruned_loss=0.05305, over 1426724.75 frames.], batch size: 23, lr: 3.21e-04
2022-05-27 22:38:57,338 INFO [train.py:842] (3/4) Epoch 17, batch 6600, loss[loss=0.2289, simple_loss=0.2981, pruned_loss=0.07984, over 4378.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2773, pruned_loss=0.05404, over 1425440.08 frames.], batch size: 52, lr: 3.21e-04
2022-05-27 22:39:36,222 INFO [train.py:842] (3/4) Epoch 17, batch 6650, loss[loss=0.1613, simple_loss=0.2369, pruned_loss=0.04279, over 7015.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2798, pruned_loss=0.05632, over 1422617.16 frames.], batch size: 16, lr: 3.21e-04
2022-05-27 22:40:14,952 INFO [train.py:842] (3/4) Epoch 17, batch 6700, loss[loss=0.2218, simple_loss=0.3045, pruned_loss=0.06958, over 7192.00 frames.], tot_loss[loss=0.1963, simple_loss=0.28, pruned_loss=0.05634, over 1419133.32 frames.], batch size: 22, lr: 3.20e-04
2022-05-27 22:40:54,204 INFO [train.py:842] (3/4) Epoch 17, batch 6750, loss[loss=0.1896, simple_loss=0.2708, pruned_loss=0.05418, over 7193.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2795, pruned_loss=0.05588, over 1415399.39 frames.], batch size: 22, lr: 3.20e-04
2022-05-27 22:41:33,195 INFO [train.py:842] (3/4) Epoch 17, batch 6800, loss[loss=0.1952, simple_loss=0.2737, pruned_loss=0.05836, over 7401.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2771, pruned_loss=0.05434, over 1419488.02 frames.], batch size: 18, lr: 3.20e-04
2022-05-27 22:42:12,529 INFO [train.py:842] (3/4) Epoch 17, batch 6850, loss[loss=0.1783, simple_loss=0.2624, pruned_loss=0.04716, over 7068.00 frames.], tot_loss[loss=0.1918, simple_loss=0.276, pruned_loss=0.05381, over 1421638.98 frames.], batch size: 18, lr: 3.20e-04
2022-05-27 22:42:51,375 INFO [train.py:842] (3/4) Epoch 17, batch 6900, loss[loss=0.1798, simple_loss=0.2742, pruned_loss=0.04266, over 7223.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2756, pruned_loss=0.05382, over 1422739.27 frames.], batch size: 21, lr: 3.20e-04
2022-05-27 22:43:30,336 INFO [train.py:842] (3/4) Epoch 17, batch 6950, loss[loss=0.1715, simple_loss=0.2562, pruned_loss=0.04339, over 7416.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2757, pruned_loss=0.05389, over 1423643.66 frames.], batch size: 21, lr: 3.20e-04
2022-05-27 22:44:09,762 INFO [train.py:842] (3/4) Epoch 17, batch 7000, loss[loss=0.1737, simple_loss=0.2573, pruned_loss=0.04509, over 7378.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2755, pruned_loss=0.0538, over 1424306.58 frames.], batch size: 23, lr: 3.20e-04
2022-05-27 22:44:49,097 INFO [train.py:842] (3/4) Epoch 17, batch 7050, loss[loss=0.1952, simple_loss=0.2851, pruned_loss=0.05263, over 7211.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2756, pruned_loss=0.05376, over 1422094.66 frames.], batch size: 23, lr: 3.20e-04
2022-05-27 22:45:28,485 INFO [train.py:842] (3/4) Epoch 17, batch 7100, loss[loss=0.1847, simple_loss=0.2721, pruned_loss=0.04869, over 7318.00 frames.], tot_loss[loss=0.1916, simple_loss=0.276, pruned_loss=0.05359, over 1424960.21 frames.], batch size: 21, lr: 3.20e-04
2022-05-27 22:46:07,824 INFO [train.py:842] (3/4) Epoch 17, batch 7150, loss[loss=0.1741, simple_loss=0.2743, pruned_loss=0.03697, over 7281.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2749, pruned_loss=0.05334, over 1427485.48 frames.], batch size: 24, lr: 3.20e-04
2022-05-27 22:46:46,815 INFO [train.py:842] (3/4) Epoch 17, batch 7200, loss[loss=0.1838, simple_loss=0.2802, pruned_loss=0.04374, over 7221.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2745, pruned_loss=0.05289, over 1427059.90 frames.], batch size: 23, lr: 3.20e-04
2022-05-27 22:47:26,424 INFO [train.py:842] (3/4) Epoch 17, batch 7250, loss[loss=0.213, simple_loss=0.2998, pruned_loss=0.06316, over 7332.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2757, pruned_loss=0.05361, over 1430210.34 frames.], batch size: 21, lr: 3.20e-04
2022-05-27 22:48:05,629 INFO [train.py:842] (3/4) Epoch 17, batch 7300, loss[loss=0.1437, simple_loss=0.2361, pruned_loss=0.02564, over 7270.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2754, pruned_loss=0.05312, over 1432178.44 frames.], batch size: 17, lr: 3.20e-04
2022-05-27 22:48:44,790 INFO [train.py:842] (3/4) Epoch 17, batch 7350, loss[loss=0.1696, simple_loss=0.2639, pruned_loss=0.0377, over 7306.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2762, pruned_loss=0.05351, over 1432905.94 frames.], batch size: 21, lr: 3.20e-04
2022-05-27 22:49:23,634 INFO [train.py:842] (3/4) Epoch 17, batch 7400, loss[loss=0.2292, simple_loss=0.3035, pruned_loss=0.07741, over 5143.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2766, pruned_loss=0.05403, over 1424858.83 frames.], batch size: 52, lr: 3.20e-04
2022-05-27 22:50:02,541 INFO [train.py:842] (3/4) Epoch 17, batch 7450, loss[loss=0.1546, simple_loss=0.2354, pruned_loss=0.03689, over 7280.00 frames.], tot_loss[loss=0.1925, simple_loss=0.277, pruned_loss=0.05401, over 1428478.56 frames.], batch size: 17, lr: 3.20e-04
2022-05-27 22:50:41,670 INFO [train.py:842] (3/4) Epoch 17, batch 7500, loss[loss=0.2071, simple_loss=0.2891, pruned_loss=0.06257, over 7068.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2762, pruned_loss=0.05381, over 1429236.82 frames.], batch size: 18, lr: 3.20e-04
2022-05-27 22:51:20,636 INFO [train.py:842] (3/4) Epoch 17, batch 7550, loss[loss=0.2462, simple_loss=0.3325, pruned_loss=0.0799, over 7201.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2762, pruned_loss=0.05341, over 1427941.74 frames.], batch size: 23, lr: 3.20e-04
2022-05-27 22:51:59,832 INFO [train.py:842] (3/4) Epoch 17, batch 7600, loss[loss=0.1945, simple_loss=0.2765, pruned_loss=0.05621, over 7275.00 frames.], tot_loss[loss=0.19, simple_loss=0.2747, pruned_loss=0.05268, over 1430500.78 frames.], batch size: 18, lr: 3.20e-04
2022-05-27 22:52:38,864 INFO [train.py:842] (3/4) Epoch 17, batch 7650, loss[loss=0.1694, simple_loss=0.2512, pruned_loss=0.04382, over 6813.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2755, pruned_loss=0.05344, over 1428657.14 frames.], batch size: 15, lr: 3.19e-04
2022-05-27 22:53:17,424 INFO [train.py:842] (3/4) Epoch 17, batch 7700, loss[loss=0.1903, simple_loss=0.2821, pruned_loss=0.04922, over 7334.00 frames.], tot_loss[loss=0.1922, simple_loss=0.277, pruned_loss=0.05371, over 1428898.15 frames.], batch size: 22, lr: 3.19e-04
2022-05-27 22:53:56,294 INFO [train.py:842] (3/4) Epoch 17, batch 7750, loss[loss=0.1805, simple_loss=0.2677, pruned_loss=0.04664, over 7222.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2764, pruned_loss=0.05365, over 1429098.11 frames.], batch size: 22, lr: 3.19e-04
2022-05-27 22:54:34,892 INFO [train.py:842] (3/4) Epoch 17, batch 7800, loss[loss=0.1551, simple_loss=0.2371, pruned_loss=0.03655, over 6995.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2779, pruned_loss=0.0546, over 1424391.67 frames.], batch size: 16, lr: 3.19e-04
2022-05-27 22:55:13,934 INFO [train.py:842] (3/4) Epoch 17, batch 7850, loss[loss=0.1529, simple_loss=0.2381, pruned_loss=0.03384, over 7126.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2785, pruned_loss=0.05492, over 1423921.73 frames.], batch size: 17, lr: 3.19e-04
2022-05-27 22:55:52,910 INFO [train.py:842] (3/4) Epoch 17, batch 7900, loss[loss=0.1784, simple_loss=0.2667, pruned_loss=0.04501, over 7274.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2786, pruned_loss=0.05508, over 1425076.54 frames.], batch size: 19, lr: 3.19e-04
2022-05-27 22:56:32,278 INFO [train.py:842] (3/4) Epoch 17, batch 7950, loss[loss=0.1578, simple_loss=0.242, pruned_loss=0.03675, over 7063.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2775, pruned_loss=0.05448, over 1423613.83 frames.], batch size: 18, lr: 3.19e-04
2022-05-27 22:57:10,830 INFO [train.py:842] (3/4) Epoch 17, batch 8000, loss[loss=0.1729, simple_loss=0.2604, pruned_loss=0.04272, over 7330.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2765, pruned_loss=0.05385, over 1418645.76 frames.], batch size: 20, lr: 3.19e-04
2022-05-27 22:57:50,119 INFO [train.py:842] (3/4) Epoch 17, batch 8050, loss[loss=0.1953, simple_loss=0.2779, pruned_loss=0.05632, over 7157.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2761, pruned_loss=0.05424, over 1413029.62 frames.], batch size: 19, lr: 3.19e-04
2022-05-27 22:58:28,868 INFO [train.py:842] (3/4) Epoch 17, batch 8100, loss[loss=0.1987, simple_loss=0.2797, pruned_loss=0.05881, over 6411.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2758, pruned_loss=0.05403, over 1413177.32 frames.], batch size: 37, lr: 3.19e-04
2022-05-27 22:59:08,307 INFO [train.py:842] (3/4) Epoch 17, batch 8150, loss[loss=0.2103, simple_loss=0.2952, pruned_loss=0.06271, over 7200.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2748, pruned_loss=0.05319, over 1412107.01 frames.], batch size: 22, lr: 3.19e-04
2022-05-27 22:59:46,879 INFO [train.py:842] (3/4) Epoch 17, batch 8200, loss[loss=0.1644, simple_loss=0.2504, pruned_loss=0.03916, over 7440.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2762, pruned_loss=0.05369, over 1409155.33 frames.], batch size: 20, lr: 3.19e-04
2022-05-27 23:00:26,386 INFO [train.py:842] (3/4) Epoch 17, batch 8250, loss[loss=0.1818, simple_loss=0.2773, pruned_loss=0.0431, over 7314.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2762, pruned_loss=0.05329, over 1415862.95 frames.], batch size: 21, lr: 3.19e-04
2022-05-27 23:01:04,938 INFO [train.py:842] (3/4) Epoch 17, batch 8300, loss[loss=0.1518, simple_loss=0.2399, pruned_loss=0.03182, over 7119.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2772, pruned_loss=0.0537, over 1415031.98 frames.], batch size: 21, lr: 3.19e-04
2022-05-27 23:01:43,884 INFO [train.py:842] (3/4) Epoch 17, batch 8350, loss[loss=0.1852, simple_loss=0.2695, pruned_loss=0.05042, over 7295.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2762, pruned_loss=0.05366, over 1419343.23 frames.], batch size: 25, lr: 3.19e-04
2022-05-27 23:02:22,698 INFO [train.py:842] (3/4) Epoch 17, batch 8400, loss[loss=0.1921, simple_loss=0.2937, pruned_loss=0.04522, over 6975.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2762, pruned_loss=0.05334, over 1421478.76 frames.], batch size: 28, lr: 3.19e-04
2022-05-27 23:03:01,599 INFO [train.py:842] (3/4) Epoch 17, batch 8450, loss[loss=0.1656, simple_loss=0.2608, pruned_loss=0.03522, over 6215.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2759, pruned_loss=0.05329, over 1419792.72 frames.], batch size: 37, lr: 3.19e-04
2022-05-27 23:03:40,260 INFO [train.py:842] (3/4) Epoch 17, batch 8500, loss[loss=0.1946, simple_loss=0.2855, pruned_loss=0.05178, over 7170.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2754, pruned_loss=0.05301, over 1412458.53 frames.], batch size: 26, lr: 3.19e-04
2022-05-27 23:04:19,023 INFO [train.py:842] (3/4) Epoch 17, batch 8550, loss[loss=0.1829, simple_loss=0.2721, pruned_loss=0.04691, over 6341.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2759, pruned_loss=0.05282, over 1411429.76 frames.], batch size: 38, lr: 3.19e-04
2022-05-27 23:04:57,784 INFO [train.py:842] (3/4) Epoch 17, batch 8600, loss[loss=0.1935, simple_loss=0.2827, pruned_loss=0.05216, over 7338.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2763, pruned_loss=0.05306, over 1417059.33 frames.], batch size: 22, lr: 3.19e-04
2022-05-27 23:05:36,637 INFO [train.py:842] (3/4) Epoch 17, batch 8650, loss[loss=0.1682, simple_loss=0.238, pruned_loss=0.04918, over 7265.00 frames.], tot_loss[loss=0.191, simple_loss=0.2763, pruned_loss=0.05286, over 1418586.20 frames.], batch size: 18, lr: 3.18e-04
2022-05-27 23:06:15,468 INFO [train.py:842] (3/4) Epoch 17, batch 8700, loss[loss=0.2545, simple_loss=0.3343, pruned_loss=0.08734, over 7297.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2772, pruned_loss=0.05328, over 1422812.74 frames.], batch size: 25, lr: 3.18e-04
2022-05-27 23:06:54,777 INFO [train.py:842] (3/4) Epoch 17, batch 8750, loss[loss=0.1786, simple_loss=0.26, pruned_loss=0.04859, over 7067.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2765, pruned_loss=0.05269, over 1422720.58 frames.], batch size: 18, lr: 3.18e-04
2022-05-27 23:07:33,420 INFO [train.py:842] (3/4) Epoch 17, batch 8800, loss[loss=0.161, simple_loss=0.251, pruned_loss=0.0355, over 7081.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2773, pruned_loss=0.05302, over 1418066.97 frames.], batch size: 18, lr: 3.18e-04
2022-05-27 23:08:12,280 INFO [train.py:842] (3/4) Epoch 17, batch 8850, loss[loss=0.2171, simple_loss=0.2982, pruned_loss=0.068, over 5264.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2773, pruned_loss=0.053, over 1416183.99 frames.], batch size: 52, lr: 3.18e-04
2022-05-27 23:08:51,339 INFO [train.py:842] (3/4) Epoch 17, batch 8900, loss[loss=0.2035, simple_loss=0.2902, pruned_loss=0.05837, over 7137.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2759, pruned_loss=0.05258, over 1415959.34 frames.], batch size: 20, lr: 3.18e-04
2022-05-27 23:09:30,579 INFO [train.py:842] (3/4) Epoch 17, batch 8950, loss[loss=0.184, simple_loss=0.2669, pruned_loss=0.05054, over 7287.00 frames.], tot_loss[loss=0.1909, simple_loss=0.276, pruned_loss=0.05285, over 1407398.39 frames.], batch size: 18, lr: 3.18e-04
2022-05-27 23:10:09,460 INFO [train.py:842] (3/4) Epoch 17, batch 9000, loss[loss=0.2314, simple_loss=0.3255, pruned_loss=0.06859, over 7148.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2767, pruned_loss=0.05324, over 1399699.92 frames.], batch size: 20, lr: 3.18e-04
2022-05-27 23:10:09,461 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 23:10:18,901 INFO [train.py:871] (3/4) Epoch 17, validation: loss=0.1657, simple_loss=0.2652, pruned_loss=0.03308, over 868885.00 frames.
2022-05-27 23:10:57,894 INFO [train.py:842] (3/4) Epoch 17, batch 9050, loss[loss=0.2078, simple_loss=0.3007, pruned_loss=0.05742, over 7325.00 frames.], tot_loss[loss=0.192, simple_loss=0.2774, pruned_loss=0.0533, over 1393973.16 frames.], batch size: 20, lr: 3.18e-04
2022-05-27 23:11:46,173 INFO [train.py:842] (3/4) Epoch 17, batch 9100, loss[loss=0.2939, simple_loss=0.356, pruned_loss=0.1159, over 5489.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2799, pruned_loss=0.05565, over 1345403.92 frames.], batch size: 53, lr: 3.18e-04
2022-05-27 23:12:24,166 INFO [train.py:842] (3/4) Epoch 17, batch 9150, loss[loss=0.2016, simple_loss=0.2896, pruned_loss=0.05682, over 4867.00 frames.], tot_loss[loss=0.2012, simple_loss=0.284, pruned_loss=0.05921, over 1270840.56 frames.], batch size: 54, lr: 3.18e-04
2022-05-27 23:13:16,683 INFO [train.py:842] (3/4) Epoch 18, batch 0, loss[loss=0.2195, simple_loss=0.2921, pruned_loss=0.07341, over 7238.00 frames.], tot_loss[loss=0.2195, simple_loss=0.2921, pruned_loss=0.07341, over 7238.00 frames.], batch size: 20, lr: 3.10e-04
2022-05-27 23:13:56,081 INFO [train.py:842] (3/4) Epoch 18, batch 50, loss[loss=0.1563, simple_loss=0.2364, pruned_loss=0.03806, over 6997.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2732, pruned_loss=0.05272, over 323623.60 frames.], batch size: 16, lr: 3.09e-04
2022-05-27 23:14:34,699 INFO [train.py:842] (3/4) Epoch 18, batch 100, loss[loss=0.17, simple_loss=0.2551, pruned_loss=0.04251, over 7161.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2727, pruned_loss=0.05121, over 565303.51 frames.], batch size: 18, lr: 3.09e-04
2022-05-27 23:15:14,080 INFO [train.py:842] (3/4) Epoch 18, batch 150, loss[loss=0.2148, simple_loss=0.3113, pruned_loss=0.05917, over 7148.00 frames.], tot_loss[loss=0.19, simple_loss=0.2758, pruned_loss=0.05208, over 752592.26 frames.], batch size: 20, lr: 3.09e-04
2022-05-27 23:15:53,009 INFO [train.py:842] (3/4) Epoch 18, batch 200, loss[loss=0.207, simple_loss=0.275, pruned_loss=0.06949, over 7157.00 frames.], tot_loss[loss=0.1912, simple_loss=0.277, pruned_loss=0.05274, over 903775.57 frames.], batch size: 18, lr: 3.09e-04
2022-05-27 23:16:31,864 INFO [train.py:842] (3/4) Epoch 18, batch 250, loss[loss=0.2559, simple_loss=0.3252, pruned_loss=0.09327, over 6823.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2776, pruned_loss=0.05249, over 1021088.63 frames.], batch size: 31, lr: 3.09e-04
2022-05-27 23:17:10,694 INFO [train.py:842] (3/4) Epoch 18, batch 300, loss[loss=0.1853, simple_loss=0.2721, pruned_loss=0.04926, over 7074.00 frames.], tot_loss[loss=0.191, simple_loss=0.2772, pruned_loss=0.0524, over 1105136.57 frames.], batch size: 28, lr: 3.09e-04
2022-05-27 23:17:49,738 INFO [train.py:842] (3/4) Epoch 18, batch 350, loss[loss=0.1871, simple_loss=0.2704, pruned_loss=0.05185, over 7336.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2764, pruned_loss=0.05269, over 1173177.89 frames.], batch size: 22, lr: 3.09e-04
2022-05-27 23:18:28,726 INFO [train.py:842] (3/4) Epoch 18, batch 400, loss[loss=0.1268, simple_loss=0.2147, pruned_loss=0.01946, over 6844.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2759, pruned_loss=0.05236, over 1233314.88 frames.], batch size: 15, lr: 3.09e-04
2022-05-27 23:19:07,686 INFO [train.py:842] (3/4) Epoch 18, batch 450, loss[loss=0.28, simple_loss=0.3466, pruned_loss=0.1068, over 7207.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2768, pruned_loss=0.05285, over 1276545.10 frames.], batch size: 22, lr: 3.09e-04
2022-05-27 23:19:46,708 INFO [train.py:842] (3/4) Epoch 18, batch 500, loss[loss=0.1914, simple_loss=0.2884, pruned_loss=0.04718, over 7330.00 frames.], tot_loss[loss=0.1892, simple_loss=0.275, pruned_loss=0.05165, over 1313211.73 frames.], batch size: 22, lr: 3.09e-04
2022-05-27 23:20:26,028 INFO [train.py:842] (3/4) Epoch 18, batch 550, loss[loss=0.1627, simple_loss=0.2447, pruned_loss=0.04036, over 7139.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2749, pruned_loss=0.05166, over 1339660.00 frames.], batch size: 17, lr: 3.09e-04
2022-05-27 23:21:04,758 INFO [train.py:842] (3/4) Epoch 18, batch 600, loss[loss=0.2525, simple_loss=0.3354, pruned_loss=0.08478, over 6361.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2754, pruned_loss=0.05189, over 1357064.25 frames.], batch size: 37, lr: 3.09e-04
2022-05-27 23:21:43,507 INFO [train.py:842] (3/4) Epoch 18, batch 650, loss[loss=0.2262, simple_loss=0.2981, pruned_loss=0.07718, over 5041.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2761, pruned_loss=0.05211, over 1369717.23 frames.], batch size: 54, lr: 3.09e-04
2022-05-27 23:22:22,381 INFO [train.py:842] (3/4) Epoch 18, batch 700, loss[loss=0.2293, simple_loss=0.3086, pruned_loss=0.07502, over 7322.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2765, pruned_loss=0.05234, over 1380966.08 frames.], batch size: 21, lr: 3.09e-04
2022-05-27 23:23:01,864 INFO [train.py:842] (3/4) Epoch 18, batch 750, loss[loss=0.1709, simple_loss=0.2547, pruned_loss=0.04353, over 7422.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2744, pruned_loss=0.05137, over 1391776.03 frames.], batch size: 18, lr: 3.09e-04
2022-05-27 23:23:41,047 INFO [train.py:842] (3/4) Epoch 18, batch 800, loss[loss=0.2051, simple_loss=0.2897, pruned_loss=0.06024, over 7319.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2738, pruned_loss=0.05068, over 1403680.25 frames.], batch size: 21, lr: 3.09e-04
2022-05-27 23:24:20,299 INFO [train.py:842] (3/4) Epoch 18, batch 850, loss[loss=0.1761, simple_loss=0.2624, pruned_loss=0.0449, over 7403.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2736, pruned_loss=0.05088, over 1406958.05 frames.], batch size: 21, lr: 3.09e-04
2022-05-27 23:24:58,894 INFO [train.py:842] (3/4) Epoch 18, batch 900, loss[loss=0.1951, simple_loss=0.2873, pruned_loss=0.05142, over 7200.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2746, pruned_loss=0.05139, over 1406868.87 frames.], batch size: 22, lr: 3.09e-04
2022-05-27 23:25:37,806 INFO [train.py:842] (3/4) Epoch 18, batch 950, loss[loss=0.2103, simple_loss=0.2859, pruned_loss=0.06741, over 7263.00 frames.], tot_loss[loss=0.188, simple_loss=0.2741, pruned_loss=0.05091, over 1409251.18 frames.], batch size: 19, lr: 3.09e-04
2022-05-27 23:26:16,538 INFO [train.py:842] (3/4) Epoch 18, batch 1000, loss[loss=0.2236, simple_loss=0.306, pruned_loss=0.07055, over 7305.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2732, pruned_loss=0.05023, over 1414050.06 frames.], batch size: 24, lr: 3.09e-04
2022-05-27 23:26:55,813 INFO [train.py:842] (3/4) Epoch 18, batch 1050, loss[loss=0.1642, simple_loss=0.235, pruned_loss=0.0467, over 7273.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2729, pruned_loss=0.05011, over 1416880.53 frames.], batch size: 17, lr: 3.08e-04
2022-05-27 23:27:34,967 INFO [train.py:842] (3/4) Epoch 18, batch 1100, loss[loss=0.1871, simple_loss=0.2766, pruned_loss=0.04878, over 7301.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2742, pruned_loss=0.05108, over 1419943.46 frames.], batch size: 25, lr: 3.08e-04
2022-05-27 23:28:14,183 INFO [train.py:842] (3/4) Epoch 18, batch 1150, loss[loss=0.1922, simple_loss=0.273, pruned_loss=0.05574, over 7378.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2726, pruned_loss=0.05044, over 1417975.70 frames.], batch size: 23, lr: 3.08e-04
2022-05-27 23:28:53,127 INFO [train.py:842] (3/4) Epoch 18, batch 1200, loss[loss=0.165, simple_loss=0.253, pruned_loss=0.03851, over 7289.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2725, pruned_loss=0.0503, over 1416137.06 frames.], batch size: 18, lr: 3.08e-04
2022-05-27 23:29:32,559 INFO [train.py:842] (3/4) Epoch 18, batch 1250, loss[loss=0.2114, simple_loss=0.2978, pruned_loss=0.06256, over 7404.00 frames.], tot_loss[loss=0.1873, simple_loss=0.273, pruned_loss=0.05086, over 1417546.44 frames.], batch size: 21, lr: 3.08e-04
2022-05-27 23:30:11,878 INFO [train.py:842] (3/4) Epoch 18, batch 1300, loss[loss=0.1998, simple_loss=0.2874, pruned_loss=0.05608, over 7159.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2741, pruned_loss=0.0518, over 1418567.97 frames.], batch size: 26, lr: 3.08e-04
2022-05-27 23:30:51,068 INFO [train.py:842] (3/4) Epoch 18, batch 1350, loss[loss=0.155, simple_loss=0.2321, pruned_loss=0.03892, over 7002.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2734, pruned_loss=0.05111, over 1422132.33 frames.], batch size: 16, lr: 3.08e-04
2022-05-27 23:31:29,681 INFO [train.py:842] (3/4) Epoch 18, batch 1400, loss[loss=0.1657, simple_loss=0.2566, pruned_loss=0.03739, over 7114.00 frames.], tot_loss[loss=0.189, simple_loss=0.2746, pruned_loss=0.05172, over 1423473.88 frames.], batch size: 21, lr: 3.08e-04
2022-05-27 23:32:08,773 INFO [train.py:842] (3/4) Epoch 18, batch 1450, loss[loss=0.1846, simple_loss=0.2797, pruned_loss=0.0447, over 7147.00 frames.], tot_loss[loss=0.19, simple_loss=0.2756, pruned_loss=0.05218, over 1421317.62 frames.], batch size: 20, lr: 3.08e-04
2022-05-27 23:32:47,812 INFO [train.py:842] (3/4) Epoch 18, batch 1500, loss[loss=0.159, simple_loss=0.2584, pruned_loss=0.02986, over 7280.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2758, pruned_loss=0.05267, over 1413358.94 frames.], batch size: 25, lr: 3.08e-04
2022-05-27 23:33:26,856 INFO [train.py:842] (3/4) Epoch 18, batch 1550, loss[loss=0.1841, simple_loss=0.2597, pruned_loss=0.0542, over 7156.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2763, pruned_loss=0.05312, over 1420581.41 frames.], batch size: 19, lr: 3.08e-04
2022-05-27 23:34:05,617 INFO [train.py:842] (3/4) Epoch 18, batch 1600, loss[loss=0.1799, simple_loss=0.2657, pruned_loss=0.04708, over 7431.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2756, pruned_loss=0.05295, over 1422028.26 frames.], batch size: 20, lr: 3.08e-04
2022-05-27 23:34:44,628 INFO [train.py:842] (3/4) Epoch 18, batch 1650, loss[loss=0.1601, simple_loss=0.2374, pruned_loss=0.04145, over 7284.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2752, pruned_loss=0.05251, over 1422150.67 frames.], batch size: 17, lr: 3.08e-04
2022-05-27 23:35:23,701 INFO [train.py:842] (3/4) Epoch 18, batch 1700, loss[loss=0.2403, simple_loss=0.3, pruned_loss=0.09035, over 7362.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2757, pruned_loss=0.05281, over 1424839.00 frames.], batch size: 19, lr: 3.08e-04
2022-05-27 23:36:03,306 INFO [train.py:842] (3/4) Epoch 18, batch 1750, loss[loss=0.1724, simple_loss=0.2688, pruned_loss=0.03797, over 7320.00 frames.], tot_loss[loss=0.1901, simple_loss=0.275, pruned_loss=0.0526, over 1425842.57 frames.], batch size: 21, lr: 3.08e-04
2022-05-27 23:36:42,507 INFO [train.py:842] (3/4) Epoch 18, batch 1800, loss[loss=0.2045, simple_loss=0.2975, pruned_loss=0.05576, over 7234.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2754, pruned_loss=0.05284, over 1429515.89 frames.], batch size: 20, lr: 3.08e-04
2022-05-27 23:37:22,125 INFO [train.py:842] (3/4) Epoch 18, batch 1850, loss[loss=0.2135, simple_loss=0.2957, pruned_loss=0.06569, over 5058.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2751, pruned_loss=0.05296, over 1427833.87 frames.], batch size: 52, lr: 3.08e-04
2022-05-27 23:38:00,794 INFO [train.py:842] (3/4) Epoch 18, batch 1900, loss[loss=0.1943, simple_loss=0.2782, pruned_loss=0.05519, over 7318.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2762, pruned_loss=0.05334, over 1427780.88 frames.], batch size: 21, lr: 3.08e-04
2022-05-27 23:38:39,670 INFO [train.py:842] (3/4) Epoch 18, batch 1950, loss[loss=0.2152, simple_loss=0.3004, pruned_loss=0.065, over 7327.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2769, pruned_loss=0.05328, over 1423810.72 frames.], batch size: 21, lr: 3.08e-04
2022-05-27 23:39:18,750 INFO [train.py:842] (3/4) Epoch 18, batch 2000, loss[loss=0.2325, simple_loss=0.3182, pruned_loss=0.07336, over 5085.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2754, pruned_loss=0.05255, over 1424808.27 frames.], batch size: 52, lr: 3.08e-04
2022-05-27 23:39:57,974 INFO [train.py:842] (3/4) Epoch 18, batch 2050, loss[loss=0.1801, simple_loss=0.2741, pruned_loss=0.04302, over 7123.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2754, pruned_loss=0.05312, over 1420161.61 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:40:36,532 INFO [train.py:842] (3/4) Epoch 18, batch 2100, loss[loss=0.1953, simple_loss=0.2785, pruned_loss=0.05598, over 6751.00 frames.], tot_loss[loss=0.1903, simple_loss=0.275, pruned_loss=0.05273, over 1416846.00 frames.], batch size: 31, lr: 3.07e-04
2022-05-27 23:41:15,748 INFO [train.py:842] (3/4) Epoch 18, batch 2150, loss[loss=0.1798, simple_loss=0.272, pruned_loss=0.04375, over 7217.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2746, pruned_loss=0.0523, over 1418856.43 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:41:54,580 INFO [train.py:842] (3/4) Epoch 18, batch 2200, loss[loss=0.2035, simple_loss=0.2795, pruned_loss=0.06377, over 6779.00 frames.], tot_loss[loss=0.1899, simple_loss=0.275, pruned_loss=0.0524, over 1420608.31 frames.], batch size: 15, lr: 3.07e-04
2022-05-27 23:42:33,987 INFO [train.py:842] (3/4) Epoch 18, batch 2250, loss[loss=0.1624, simple_loss=0.2335, pruned_loss=0.04562, over 7012.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2753, pruned_loss=0.05289, over 1424361.01 frames.], batch size: 16, lr: 3.07e-04
2022-05-27 23:43:12,904 INFO [train.py:842] (3/4) Epoch 18, batch 2300, loss[loss=0.1803, simple_loss=0.2716, pruned_loss=0.04452, over 7150.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2753, pruned_loss=0.05257, over 1426424.12 frames.], batch size: 20, lr: 3.07e-04
2022-05-27 23:43:52,057 INFO [train.py:842] (3/4) Epoch 18, batch 2350, loss[loss=0.2025, simple_loss=0.2862, pruned_loss=0.05941, over 7198.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2751, pruned_loss=0.05268, over 1426073.01 frames.], batch size: 26, lr: 3.07e-04
2022-05-27 23:44:31,171 INFO [train.py:842] (3/4) Epoch 18, batch 2400, loss[loss=0.2246, simple_loss=0.3117, pruned_loss=0.06875, over 6504.00 frames.], tot_loss[loss=0.191, simple_loss=0.2759, pruned_loss=0.053, over 1424665.47 frames.], batch size: 38, lr: 3.07e-04
2022-05-27 23:45:10,102 INFO [train.py:842] (3/4) Epoch 18, batch 2450, loss[loss=0.2314, simple_loss=0.312, pruned_loss=0.07543, over 7155.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2748, pruned_loss=0.05235, over 1425622.24 frames.], batch size: 19, lr: 3.07e-04
2022-05-27 23:45:58,785 INFO [train.py:842] (3/4) Epoch 18, batch 2500, loss[loss=0.1691, simple_loss=0.2586, pruned_loss=0.03974, over 7117.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2753, pruned_loss=0.05227, over 1418072.43 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:46:37,750 INFO [train.py:842] (3/4) Epoch 18, batch 2550, loss[loss=0.2041, simple_loss=0.2946, pruned_loss=0.05679, over 7320.00 frames.], tot_loss[loss=0.19, simple_loss=0.2751, pruned_loss=0.0524, over 1419472.73 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:47:16,441 INFO [train.py:842] (3/4) Epoch 18, batch 2600, loss[loss=0.1619, simple_loss=0.2419, pruned_loss=0.04095, over 7183.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2751, pruned_loss=0.05193, over 1419290.62 frames.], batch size: 16, lr: 3.07e-04
2022-05-27 23:48:05,833 INFO [train.py:842] (3/4) Epoch 18, batch 2650, loss[loss=0.1774, simple_loss=0.2743, pruned_loss=0.04024, over 7354.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2739, pruned_loss=0.05178, over 1420213.35 frames.], batch size: 19, lr: 3.07e-04
2022-05-27 23:48:44,821 INFO [train.py:842] (3/4) Epoch 18, batch 2700, loss[loss=0.1613, simple_loss=0.2373, pruned_loss=0.04268, over 7277.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2729, pruned_loss=0.05129, over 1419668.51 frames.], batch size: 18, lr: 3.07e-04
2022-05-27 23:49:23,612 INFO [train.py:842] (3/4) Epoch 18, batch 2750, loss[loss=0.1751, simple_loss=0.2678, pruned_loss=0.04123, over 7138.00 frames.], tot_loss[loss=0.1876, simple_loss=0.273, pruned_loss=0.05107, over 1417329.16 frames.], batch size: 20, lr: 3.07e-04
2022-05-27 23:50:12,208 INFO [train.py:842] (3/4) Epoch 18, batch 2800, loss[loss=0.2317, simple_loss=0.3224, pruned_loss=0.07047, over 7326.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2735, pruned_loss=0.0514, over 1417086.27 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:50:50,924 INFO [train.py:842] (3/4) Epoch 18, batch 2850, loss[loss=0.1981, simple_loss=0.2882, pruned_loss=0.05402, over 7299.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2736, pruned_loss=0.0511, over 1419926.11 frames.], batch size: 25, lr: 3.07e-04
2022-05-27 23:51:29,801 INFO [train.py:842] (3/4) Epoch 18, batch 2900, loss[loss=0.2026, simple_loss=0.2913, pruned_loss=0.05693, over 7182.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2757, pruned_loss=0.05291, over 1422480.17 frames.], batch size: 22, lr: 3.07e-04
2022-05-27 23:52:08,760 INFO [train.py:842] (3/4) Epoch 18, batch 2950, loss[loss=0.2395, simple_loss=0.3215, pruned_loss=0.07875, over 6467.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2759, pruned_loss=0.05255, over 1419390.63 frames.], batch size: 38, lr: 3.07e-04
2022-05-27 23:52:47,344 INFO [train.py:842] (3/4) Epoch 18, batch 3000, loss[loss=0.257, simple_loss=0.3316, pruned_loss=0.09121, over 7285.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2763, pruned_loss=0.05266, over 1418454.39 frames.], batch size: 25, lr: 3.07e-04
2022-05-27 23:52:47,345 INFO [train.py:862] (3/4) Computing validation loss
2022-05-27 23:52:57,054 INFO [train.py:871] (3/4) Epoch 18, validation: loss=0.1661, simple_loss=0.2662, pruned_loss=0.03302, over 868885.00 frames.
2022-05-27 23:53:35,991 INFO [train.py:842] (3/4) Epoch 18, batch 3050, loss[loss=0.1581, simple_loss=0.2551, pruned_loss=0.03052, over 7117.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2756, pruned_loss=0.05254, over 1417340.95 frames.], batch size: 21, lr: 3.07e-04
2022-05-27 23:54:14,584 INFO [train.py:842] (3/4) Epoch 18, batch 3100, loss[loss=0.1917, simple_loss=0.2864, pruned_loss=0.0485, over 7238.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2752, pruned_loss=0.05207, over 1417755.30 frames.], batch size: 20, lr: 3.06e-04
2022-05-27 23:54:53,756 INFO [train.py:842] (3/4) Epoch 18, batch 3150, loss[loss=0.1627, simple_loss=0.2513, pruned_loss=0.03702, over 7252.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2747, pruned_loss=0.05174, over 1420288.22 frames.], batch size: 19, lr: 3.06e-04
2022-05-27 23:55:32,583 INFO [train.py:842] (3/4) Epoch 18, batch 3200, loss[loss=0.1945, simple_loss=0.2894, pruned_loss=0.04977, over 6707.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2742, pruned_loss=0.05139, over 1418513.35 frames.], batch size: 31, lr: 3.06e-04
2022-05-27 23:56:11,871 INFO [train.py:842] (3/4) Epoch 18, batch 3250, loss[loss=0.187, simple_loss=0.2724, pruned_loss=0.05085, over 7382.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2744, pruned_loss=0.05167, over 1422159.62 frames.], batch size: 23, lr: 3.06e-04
2022-05-27 23:56:51,379 INFO [train.py:842] (3/4) Epoch 18, batch 3300, loss[loss=0.1531, simple_loss=0.2426, pruned_loss=0.03178, over 7164.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2737, pruned_loss=0.05161, over 1426787.66 frames.], batch size: 18, lr: 3.06e-04
2022-05-27 23:57:30,314 INFO [train.py:842] (3/4) Epoch 18, batch 3350, loss[loss=0.1558, simple_loss=0.2343, pruned_loss=0.03869, over 7414.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2737, pruned_loss=0.05183, over 1426332.24 frames.], batch size: 18, lr: 3.06e-04
2022-05-27 23:58:09,211 INFO [train.py:842] (3/4) Epoch 18, batch 3400, loss[loss=0.1874, simple_loss=0.2619, pruned_loss=0.05646, over 7387.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2729, pruned_loss=0.05138, over 1429857.62 frames.], batch size: 23, lr: 3.06e-04
2022-05-27 23:58:48,441 INFO [train.py:842] (3/4) Epoch 18, batch 3450, loss[loss=0.2409, simple_loss=0.306, pruned_loss=0.08794, over 7419.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2744, pruned_loss=0.05172, over 1430758.75 frames.], batch size: 18, lr: 3.06e-04
2022-05-27 23:59:27,883 INFO [train.py:842] (3/4) Epoch 18, batch 3500, loss[loss=0.1821, simple_loss=0.2758, pruned_loss=0.04426, over 6333.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2747, pruned_loss=0.05225, over 1433199.81 frames.], batch size: 37, lr: 3.06e-04
2022-05-28 00:00:07,002 INFO [train.py:842] (3/4) Epoch 18, batch 3550, loss[loss=0.1752, simple_loss=0.2841, pruned_loss=0.03313, over 7208.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2758, pruned_loss=0.05275, over 1431024.96 frames.], batch size: 23, lr: 3.06e-04
2022-05-28 00:00:45,914 INFO [train.py:842] (3/4) Epoch 18, batch 3600, loss[loss=0.1749, simple_loss=0.2693, pruned_loss=0.04025, over 7222.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2742, pruned_loss=0.05183, over 1431393.90 frames.], batch size: 21, lr: 3.06e-04
2022-05-28 00:01:24,919 INFO [train.py:842] (3/4) Epoch 18, batch 3650, loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03486, over 7337.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2732, pruned_loss=0.05148, over 1423323.64 frames.], batch size: 22, lr: 3.06e-04
2022-05-28 00:02:03,662 INFO [train.py:842] (3/4) Epoch 18, batch 3700, loss[loss=0.1622, simple_loss=0.2414, pruned_loss=0.04148, over 7017.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2733, pruned_loss=0.05098, over 1424538.58 frames.], batch size: 16, lr: 3.06e-04
2022-05-28 00:02:45,148 INFO [train.py:842] (3/4) Epoch 18, batch 3750, loss[loss=0.2073, simple_loss=0.2955, pruned_loss=0.05957, over 7303.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2754, pruned_loss=0.05179, over 1427073.91 frames.], batch size: 25, lr: 3.06e-04
2022-05-28 00:03:23,946 INFO [train.py:842] (3/4) Epoch 18, batch 3800, loss[loss=0.2293, simple_loss=0.3047, pruned_loss=0.07695, over 7355.00 frames.], tot_loss[loss=0.1878, simple_loss=0.274, pruned_loss=0.05084, over 1426405.98 frames.], batch size: 19, lr: 3.06e-04
2022-05-28 00:04:03,232 INFO [train.py:842] (3/4) Epoch 18, batch 3850, loss[loss=0.1585, simple_loss=0.2377, pruned_loss=0.03966, over 7424.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2738, pruned_loss=0.05061, over 1425441.92 frames.], batch size: 18, lr: 3.06e-04
2022-05-28 00:04:42,000 INFO [train.py:842] (3/4) Epoch 18, batch 3900, loss[loss=0.2081, simple_loss=0.2991, pruned_loss=0.05849, over 7122.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2749, pruned_loss=0.05196, over 1421447.65 frames.], batch size: 21, lr: 3.06e-04
2022-05-28 00:05:21,348 INFO [train.py:842] (3/4) Epoch 18, batch 3950, loss[loss=0.1936, simple_loss=0.2798, pruned_loss=0.05368, over 7330.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2746, pruned_loss=0.05201, over 1423995.03 frames.], batch size: 20, lr: 3.06e-04
2022-05-28 00:06:00,210 INFO [train.py:842] (3/4) Epoch 18, batch 4000, loss[loss=0.285, simple_loss=0.3348, pruned_loss=0.1176, over 7368.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2767, pruned_loss=0.05329, over 1425296.68 frames.], batch size: 23, lr: 3.06e-04
2022-05-28 00:06:39,279 INFO [train.py:842] (3/4) Epoch 18, batch 4050, loss[loss=0.1483, simple_loss=0.2191, pruned_loss=0.03879, over 7415.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2762, pruned_loss=0.05301, over 1429451.01 frames.], batch size: 18, lr: 3.06e-04
2022-05-28 00:07:18,091 INFO [train.py:842] (3/4) Epoch 18, batch 4100, loss[loss=0.2305, simple_loss=0.3152, pruned_loss=0.07291, over 7065.00 frames.], tot_loss[loss=0.1915, simple_loss=0.277, pruned_loss=0.05299, over 1428282.19 frames.], batch size: 18, lr: 3.06e-04
2022-05-28 00:07:57,213 INFO [train.py:842] (3/4) Epoch 18, batch 4150, loss[loss=0.1859, simple_loss=0.269, pruned_loss=0.05137, over 7218.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2759, pruned_loss=0.05261, over 1426182.74 frames.], batch size: 23, lr: 3.05e-04
2022-05-28 00:08:36,168 INFO [train.py:842] (3/4) Epoch 18, batch 4200, loss[loss=0.2225, simple_loss=0.3032, pruned_loss=0.07092, over 7345.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2759, pruned_loss=0.05322, over 1425612.95 frames.], batch size: 22, lr: 3.05e-04
2022-05-28 00:09:15,383 INFO [train.py:842] (3/4) Epoch 18, batch 4250, loss[loss=0.1738, simple_loss=0.2717, pruned_loss=0.03791, over 7282.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2756, pruned_loss=0.05302, over 1423447.00 frames.], batch size: 24, lr: 3.05e-04
2022-05-28 00:09:54,216 INFO [train.py:842] (3/4) Epoch 18, batch 4300, loss[loss=0.2273, simple_loss=0.3128, pruned_loss=0.07094, over 6350.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2768, pruned_loss=0.05328, over 1424950.90 frames.], batch size: 37, lr: 3.05e-04
2022-05-28 00:10:33,492 INFO [train.py:842] (3/4) Epoch 18, batch 4350, loss[loss=0.1535, simple_loss=0.2394, pruned_loss=0.03378, over 7413.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2758, pruned_loss=0.05294, over 1425855.51 frames.], batch size: 18, lr: 3.05e-04
2022-05-28 00:11:12,563 INFO [train.py:842] (3/4) Epoch 18, batch 4400, loss[loss=0.2047, simple_loss=0.28, pruned_loss=0.06467, over 7073.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2735, pruned_loss=0.05202, over 1424797.22 frames.], batch size: 28, lr: 3.05e-04
2022-05-28 00:11:51,897 INFO [train.py:842] (3/4) Epoch 18, batch 4450, loss[loss=0.169, simple_loss=0.2698, pruned_loss=0.03407, over 7267.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2746, pruned_loss=0.0523, over 1423976.75 frames.], batch size: 24, lr: 3.05e-04
2022-05-28 00:12:30,697 INFO [train.py:842] (3/4) Epoch 18, batch 4500, loss[loss=0.1722, simple_loss=0.2497, pruned_loss=0.04734, over 7261.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2747, pruned_loss=0.05221, over 1424433.75 frames.], batch size: 19, lr: 3.05e-04
2022-05-28 00:13:09,713 INFO [train.py:842] (3/4) Epoch 18, batch 4550, loss[loss=0.2118, simple_loss=0.2915, pruned_loss=0.0661, over 7107.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2746, pruned_loss=0.05212, over 1423574.86 frames.], batch size: 28, lr: 3.05e-04
2022-05-28 00:13:48,428 INFO [train.py:842] (3/4) Epoch 18, batch 4600, loss[loss=0.173, simple_loss=0.2692, pruned_loss=0.03844, over 7215.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2749, pruned_loss=0.0522, over 1422113.43 frames.], batch size: 21, lr: 3.05e-04
2022-05-28 00:14:27,483 INFO [train.py:842] (3/4) Epoch 18, batch 4650, loss[loss=0.1929, simple_loss=0.2828, pruned_loss=0.05148, over 7199.00 frames.], tot_loss[loss=0.19, simple_loss=0.275, pruned_loss=0.05246, over 1416884.41 frames.], batch size: 22, lr: 3.05e-04
2022-05-28 00:15:06,715 INFO [train.py:842] (3/4) Epoch 18, batch 4700, loss[loss=0.1839, simple_loss=0.2631, pruned_loss=0.05232, over 7070.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2749, pruned_loss=0.05248, over 1419988.68 frames.], batch size: 18, lr: 3.05e-04
2022-05-28 00:15:46,211 INFO [train.py:842] (3/4) Epoch 18, batch 4750, loss[loss=0.174, simple_loss=0.2571, pruned_loss=0.04543, over 7353.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2746, pruned_loss=0.05255, over 1420354.05 frames.], batch size: 19, lr: 3.05e-04
2022-05-28 00:16:25,216 INFO [train.py:842] (3/4) Epoch 18, batch 4800, loss[loss=0.1497, simple_loss=0.2334, pruned_loss=0.03305, over 7244.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2752, pruned_loss=0.05254, over 1422059.62 frames.], batch size: 19, lr: 3.05e-04
2022-05-28 00:17:04,352 INFO [train.py:842] (3/4) Epoch 18, batch 4850, loss[loss=0.2249, simple_loss=0.3055, pruned_loss=0.0721, over 7070.00 frames.], tot_loss[loss=0.1893, simple_loss=0.275, pruned_loss=0.05176, over 1425681.44 frames.], batch size: 28, lr: 3.05e-04
2022-05-28 00:17:43,322 INFO [train.py:842] (3/4) Epoch 18, batch 4900, loss[loss=0.1763, simple_loss=0.2716, pruned_loss=0.04047, over 7142.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2754, pruned_loss=0.05174, over 1429368.62 frames.], batch size: 20, lr: 3.05e-04
2022-05-28 00:18:22,519 INFO [train.py:842] (3/4) Epoch 18, batch 4950, loss[loss=0.1573, simple_loss=0.2477, pruned_loss=0.03345, over 7259.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2744, pruned_loss=0.05136, over 1428752.96 frames.], batch size: 19, lr: 3.05e-04
2022-05-28 00:19:01,633 INFO [train.py:842] (3/4) Epoch 18, batch 5000, loss[loss=0.1974, simple_loss=0.2825, pruned_loss=0.05617, over 7197.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2741, pruned_loss=0.05142, over 1428651.32 frames.], batch size: 23, lr: 3.05e-04
2022-05-28 00:19:40,956 INFO [train.py:842] (3/4) Epoch 18, batch 5050, loss[loss=0.2358, simple_loss=0.3099, pruned_loss=0.08087, over 7144.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2756, pruned_loss=0.05206, over 1431267.08 frames.], batch size: 18, lr: 3.05e-04
2022-05-28 00:20:19,759 INFO [train.py:842] (3/4) Epoch 18, batch 5100, loss[loss=0.2202, simple_loss=0.3117, pruned_loss=0.06432, over 7198.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2761, pruned_loss=0.05231, over 1428862.57 frames.], batch size: 23, lr: 3.05e-04
2022-05-28 00:20:58,758 INFO [train.py:842] (3/4) Epoch 18, batch 5150, loss[loss=0.1491, simple_loss=0.2352, pruned_loss=0.03153, over 7391.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2741, pruned_loss=0.05147, over 1431291.29 frames.], batch size: 18, lr: 3.05e-04
2022-05-28 00:21:37,380 INFO [train.py:842] (3/4) Epoch 18, batch 5200, loss[loss=0.2114, simple_loss=0.3047, pruned_loss=0.05907, over 7053.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2746, pruned_loss=0.05186, over 1432405.94 frames.], batch size: 28, lr: 3.04e-04
2022-05-28 00:22:17,195 INFO [train.py:842] (3/4) Epoch 18, batch 5250, loss[loss=0.1919, simple_loss=0.2722, pruned_loss=0.05576, over 6938.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2732, pruned_loss=0.05075, over 1434476.85 frames.], batch size: 32, lr: 3.04e-04
2022-05-28 00:22:55,889 INFO [train.py:842] (3/4) Epoch 18, batch 5300, loss[loss=0.1852, simple_loss=0.282, pruned_loss=0.04423, over 7309.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2735, pruned_loss=0.05066, over 1432111.83 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:23:35,048 INFO [train.py:842] (3/4) Epoch 18, batch 5350, loss[loss=0.1603, simple_loss=0.2446, pruned_loss=0.03804, over 7399.00 frames.], tot_loss[loss=0.187, simple_loss=0.2733, pruned_loss=0.05031, over 1433473.56 frames.], batch size: 18, lr: 3.04e-04
2022-05-28 00:24:13,948 INFO [train.py:842] (3/4) Epoch 18, batch 5400, loss[loss=0.1946, simple_loss=0.2912, pruned_loss=0.04897, over 7118.00 frames.], tot_loss[loss=0.1882, simple_loss=0.274, pruned_loss=0.0512, over 1429882.30 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:24:53,098 INFO [train.py:842] (3/4) Epoch 18, batch 5450, loss[loss=0.2101, simple_loss=0.2853, pruned_loss=0.0675, over 7363.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2747, pruned_loss=0.05149, over 1431240.14 frames.], batch size: 19, lr: 3.04e-04
2022-05-28 00:25:32,205 INFO [train.py:842] (3/4) Epoch 18, batch 5500, loss[loss=0.1805, simple_loss=0.2714, pruned_loss=0.0448, over 7177.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2749, pruned_loss=0.05184, over 1432592.68 frames.], batch size: 26, lr: 3.04e-04
2022-05-28 00:26:11,402 INFO [train.py:842] (3/4) Epoch 18, batch 5550, loss[loss=0.1929, simple_loss=0.2773, pruned_loss=0.05425, over 7200.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2744, pruned_loss=0.05152, over 1433818.65 frames.], batch size: 22, lr: 3.04e-04
2022-05-28 00:26:50,027 INFO [train.py:842] (3/4) Epoch 18, batch 5600, loss[loss=0.1941, simple_loss=0.2731, pruned_loss=0.05759, over 7288.00 frames.], tot_loss[loss=0.189, simple_loss=0.2748, pruned_loss=0.05159, over 1432809.17 frames.], batch size: 24, lr: 3.04e-04
2022-05-28 00:27:28,971 INFO [train.py:842] (3/4) Epoch 18, batch 5650, loss[loss=0.1699, simple_loss=0.2598, pruned_loss=0.04, over 7059.00 frames.], tot_loss[loss=0.188, simple_loss=0.2742, pruned_loss=0.05092, over 1429797.36 frames.], batch size: 18, lr: 3.04e-04
2022-05-28 00:28:08,033 INFO [train.py:842] (3/4) Epoch 18, batch 5700, loss[loss=0.2192, simple_loss=0.3071, pruned_loss=0.06563, over 7384.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2748, pruned_loss=0.05113, over 1428983.75 frames.], batch size: 23, lr: 3.04e-04
2022-05-28 00:28:47,272 INFO [train.py:842] (3/4) Epoch 18, batch 5750, loss[loss=0.2555, simple_loss=0.3365, pruned_loss=0.08721, over 7123.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2751, pruned_loss=0.05102, over 1428165.25 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:29:26,203 INFO [train.py:842] (3/4) Epoch 18, batch 5800, loss[loss=0.2011, simple_loss=0.2933, pruned_loss=0.05448, over 7347.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2736, pruned_loss=0.05039, over 1429336.28 frames.], batch size: 25, lr: 3.04e-04
2022-05-28 00:30:05,310 INFO [train.py:842] (3/4) Epoch 18, batch 5850, loss[loss=0.212, simple_loss=0.3123, pruned_loss=0.05582, over 7197.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2731, pruned_loss=0.05058, over 1424190.45 frames.], batch size: 23, lr: 3.04e-04
2022-05-28 00:30:44,185 INFO [train.py:842] (3/4) Epoch 18, batch 5900, loss[loss=0.1743, simple_loss=0.2554, pruned_loss=0.04658, over 7061.00 frames.], tot_loss[loss=0.1873, simple_loss=0.273, pruned_loss=0.05076, over 1424167.90 frames.], batch size: 18, lr: 3.04e-04
2022-05-28 00:31:22,990 INFO [train.py:842] (3/4) Epoch 18, batch 5950, loss[loss=0.1526, simple_loss=0.2409, pruned_loss=0.03218, over 7254.00 frames.], tot_loss[loss=0.1886, simple_loss=0.274, pruned_loss=0.05162, over 1423500.32 frames.], batch size: 19, lr: 3.04e-04
2022-05-28 00:32:01,719 INFO [train.py:842] (3/4) Epoch 18, batch 6000, loss[loss=0.1869, simple_loss=0.2729, pruned_loss=0.05042, over 7305.00 frames.], tot_loss[loss=0.189, simple_loss=0.2747, pruned_loss=0.05163, over 1427664.99 frames.], batch size: 25, lr: 3.04e-04
2022-05-28 00:32:01,720 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 00:32:11,164 INFO [train.py:871] (3/4) Epoch 18, validation: loss=0.1679, simple_loss=0.2675, pruned_loss=0.03415, over 868885.00 frames.
2022-05-28 00:32:50,451 INFO [train.py:842] (3/4) Epoch 18, batch 6050, loss[loss=0.184, simple_loss=0.2842, pruned_loss=0.04189, over 7413.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2733, pruned_loss=0.05083, over 1426988.36 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:33:29,272 INFO [train.py:842] (3/4) Epoch 18, batch 6100, loss[loss=0.1877, simple_loss=0.2694, pruned_loss=0.05294, over 7423.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2733, pruned_loss=0.0505, over 1428855.07 frames.], batch size: 20, lr: 3.04e-04
2022-05-28 00:34:08,678 INFO [train.py:842] (3/4) Epoch 18, batch 6150, loss[loss=0.206, simple_loss=0.2901, pruned_loss=0.06094, over 7113.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2733, pruned_loss=0.05095, over 1430844.90 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:34:47,573 INFO [train.py:842] (3/4) Epoch 18, batch 6200, loss[loss=0.1648, simple_loss=0.259, pruned_loss=0.03531, over 7123.00 frames.], tot_loss[loss=0.186, simple_loss=0.2718, pruned_loss=0.05012, over 1425072.95 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:35:26,857 INFO [train.py:842] (3/4) Epoch 18, batch 6250, loss[loss=0.1674, simple_loss=0.2595, pruned_loss=0.03762, over 7221.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2717, pruned_loss=0.05042, over 1423981.03 frames.], batch size: 21, lr: 3.04e-04
2022-05-28 00:36:05,693 INFO [train.py:842] (3/4) Epoch 18, batch 6300, loss[loss=0.2549, simple_loss=0.3383, pruned_loss=0.08571, over 7143.00 frames.], tot_loss[loss=0.188, simple_loss=0.2731, pruned_loss=0.05144, over 1421748.83 frames.], batch size: 20, lr: 3.03e-04
2022-05-28 00:36:45,099 INFO [train.py:842] (3/4) Epoch 18, batch 6350, loss[loss=0.1985, simple_loss=0.2941, pruned_loss=0.05144, over 7220.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2717, pruned_loss=0.05042, over 1425088.70 frames.], batch size: 21, lr: 3.03e-04
2022-05-28 00:37:23,951 INFO [train.py:842] (3/4) Epoch 18, batch 6400, loss[loss=0.1981, simple_loss=0.2701, pruned_loss=0.06309, over 7404.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2727, pruned_loss=0.05092, over 1424537.13 frames.], batch size: 18, lr: 3.03e-04
2022-05-28 00:38:03,171 INFO [train.py:842] (3/4) Epoch 18, batch 6450, loss[loss=0.1655, simple_loss=0.2499, pruned_loss=0.04058, over 7360.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2729, pruned_loss=0.05108, over 1425011.34 frames.], batch size: 19, lr: 3.03e-04
2022-05-28 00:38:41,964 INFO [train.py:842] (3/4) Epoch 18, batch 6500, loss[loss=0.1655, simple_loss=0.2462, pruned_loss=0.04237, over 7156.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2741, pruned_loss=0.05181, over 1423518.86 frames.], batch size: 17, lr: 3.03e-04
2022-05-28 00:39:21,189 INFO [train.py:842] (3/4) Epoch 18, batch 6550, loss[loss=0.204, simple_loss=0.2842, pruned_loss=0.06184, over 7332.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2723, pruned_loss=0.05112, over 1426422.54 frames.], batch size: 20, lr: 3.03e-04
2022-05-28 00:40:00,117 INFO [train.py:842] (3/4) Epoch 18, batch 6600, loss[loss=0.2097, simple_loss=0.2881, pruned_loss=0.06566, over 7216.00 frames.], tot_loss[loss=0.187, simple_loss=0.2718, pruned_loss=0.05106, over 1426487.16 frames.], batch size: 22, lr: 3.03e-04
2022-05-28 00:40:38,950 INFO [train.py:842] (3/4) Epoch 18, batch 6650, loss[loss=0.1874, simple_loss=0.2786, pruned_loss=0.04809, over 7332.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2744, pruned_loss=0.05219, over 1418747.83 frames.], batch size: 22, lr: 3.03e-04
2022-05-28 00:41:17,450 INFO [train.py:842] (3/4) Epoch 18, batch 6700, loss[loss=0.2201, simple_loss=0.312, pruned_loss=0.0641, over 7318.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2753, pruned_loss=0.05218, over 1415665.24 frames.], batch size: 25, lr: 3.03e-04
2022-05-28 00:41:56,432 INFO [train.py:842] (3/4) Epoch 18, batch 6750, loss[loss=0.1921, simple_loss=0.2768, pruned_loss=0.05369, over 7198.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2741, pruned_loss=0.05176, over 1414951.26 frames.], batch size: 22, lr: 3.03e-04
2022-05-28 00:42:35,484 INFO [train.py:842] (3/4) Epoch 18, batch 6800, loss[loss=0.1987, simple_loss=0.2717, pruned_loss=0.06284, over 7281.00 frames.], tot_loss[loss=0.1888, simple_loss=0.274, pruned_loss=0.0518, over 1416628.49 frames.], batch size: 18, lr: 3.03e-04
2022-05-28 00:43:14,486 INFO [train.py:842] (3/4) Epoch 18, batch 6850, loss[loss=0.2058, simple_loss=0.2829, pruned_loss=0.06438, over 7380.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2758, pruned_loss=0.05249, over 1419942.42 frames.], batch size: 23, lr: 3.03e-04
2022-05-28 00:43:53,158 INFO [train.py:842] (3/4) Epoch 18, batch 6900, loss[loss=0.1517, simple_loss=0.2486, pruned_loss=0.02734, over 7148.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2751, pruned_loss=0.05194, over 1421012.13 frames.], batch size: 20, lr: 3.03e-04
2022-05-28 00:44:31,886 INFO [train.py:842] (3/4) Epoch 18, batch 6950, loss[loss=0.1955, simple_loss=0.273, pruned_loss=0.05899, over 7276.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2767, pruned_loss=0.0527, over 1421308.52 frames.], batch size: 24, lr: 3.03e-04
2022-05-28 00:45:09,752 INFO [train.py:842] (3/4) Epoch 18, batch 7000, loss[loss=0.2009, simple_loss=0.2795, pruned_loss=0.06118, over 4958.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2754, pruned_loss=0.05179, over 1421783.49 frames.], batch size: 54, lr: 3.03e-04
2022-05-28 00:45:48,078 INFO [train.py:842] (3/4) Epoch 18, batch 7050, loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.0325, over 7160.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2743, pruned_loss=0.05173, over 1422998.14 frames.], batch size: 19, lr: 3.03e-04
2022-05-28 00:46:26,166 INFO [train.py:842] (3/4) Epoch 18, batch 7100, loss[loss=0.1818, simple_loss=0.2797, pruned_loss=0.042, over 7210.00 frames.], tot_loss[loss=0.189, simple_loss=0.2743, pruned_loss=0.0519, over 1423234.57 frames.], batch size: 21, lr: 3.03e-04
2022-05-28 00:47:04,380 INFO [train.py:842] (3/4) Epoch 18, batch 7150, loss[loss=0.1549, simple_loss=0.2384, pruned_loss=0.03572, over 7260.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2732, pruned_loss=0.05087, over 1426014.15 frames.], batch size: 19, lr: 3.03e-04
2022-05-28 00:47:42,508 INFO [train.py:842] (3/4) Epoch 18, batch 7200, loss[loss=0.1879, simple_loss=0.2728, pruned_loss=0.05155, over 7151.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2728, pruned_loss=0.05039, over 1427601.08 frames.], batch size: 19, lr: 3.03e-04
2022-05-28 00:48:20,749 INFO [train.py:842] (3/4) Epoch 18, batch 7250, loss[loss=0.2256, simple_loss=0.3132, pruned_loss=0.06903, over 7205.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2735, pruned_loss=0.05069, over 1426461.07 frames.], batch size: 23, lr: 3.03e-04
2022-05-28 00:48:58,656 INFO [train.py:842] (3/4) Epoch 18, batch 7300, loss[loss=0.1679, simple_loss=0.2535, pruned_loss=0.04121, over 7237.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2743, pruned_loss=0.05144, over 1423888.57 frames.], batch size: 20, lr: 3.03e-04
2022-05-28 00:49:37,081 INFO [train.py:842] (3/4) Epoch 18, batch 7350, loss[loss=0.1892, simple_loss=0.2604, pruned_loss=0.05903, over 7142.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2738, pruned_loss=0.05163, over 1427103.58 frames.], batch size: 17, lr: 3.02e-04
2022-05-28 00:50:15,184 INFO [train.py:842] (3/4) Epoch 18, batch 7400, loss[loss=0.1536, simple_loss=0.2496, pruned_loss=0.02879, over 7326.00 frames.], tot_loss[loss=0.188, simple_loss=0.2731, pruned_loss=0.05149, over 1423732.41 frames.], batch size: 21, lr: 3.02e-04
2022-05-28 00:50:53,599 INFO [train.py:842] (3/4) Epoch 18, batch 7450, loss[loss=0.2172, simple_loss=0.3044, pruned_loss=0.065, over 7407.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2736, pruned_loss=0.05173, over 1422629.83 frames.], batch size: 21, lr: 3.02e-04
2022-05-28 00:51:31,511 INFO [train.py:842] (3/4) Epoch 18, batch 7500, loss[loss=0.1733, simple_loss=0.2591, pruned_loss=0.04375, over 7225.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2736, pruned_loss=0.05187, over 1421436.46 frames.], batch size: 20, lr: 3.02e-04
2022-05-28 00:52:09,623 INFO [train.py:842] (3/4) Epoch 18, batch 7550, loss[loss=0.2297, simple_loss=0.3054, pruned_loss=0.07701, over 5149.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2735, pruned_loss=0.05161, over 1421203.01 frames.], batch size: 52, lr: 3.02e-04
2022-05-28 00:52:47,707 INFO [train.py:842] (3/4) Epoch 18, batch 7600, loss[loss=0.2188, simple_loss=0.299, pruned_loss=0.06928, over 7163.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2729, pruned_loss=0.05103, over 1425534.31 frames.], batch size: 26, lr: 3.02e-04
2022-05-28 00:53:25,838 INFO [train.py:842] (3/4) Epoch 18, batch 7650, loss[loss=0.1815, simple_loss=0.2478, pruned_loss=0.05756, over 7425.00 frames.], tot_loss[loss=0.1876, simple_loss=0.273, pruned_loss=0.05109, over 1423208.51 frames.], batch size: 18, lr: 3.02e-04
2022-05-28 00:54:03,769 INFO [train.py:842] (3/4) Epoch 18, batch 7700, loss[loss=0.2022, simple_loss=0.2863, pruned_loss=0.05906, over 6731.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2743, pruned_loss=0.05124, over 1424324.43 frames.], batch size: 31, lr: 3.02e-04
2022-05-28 00:54:42,126 INFO [train.py:842] (3/4) Epoch 18, batch 7750, loss[loss=0.1499, simple_loss=0.2298, pruned_loss=0.03499, over 7275.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2745, pruned_loss=0.05158, over 1424997.18 frames.], batch size: 17, lr: 3.02e-04
2022-05-28 00:55:20,299 INFO [train.py:842] (3/4) Epoch 18, batch 7800, loss[loss=0.1848, simple_loss=0.2704, pruned_loss=0.0496, over 7181.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2735, pruned_loss=0.05114, over 1427932.37 frames.], batch size: 18, lr: 3.02e-04
2022-05-28 00:55:58,697 INFO [train.py:842] (3/4) Epoch 18, batch 7850, loss[loss=0.1676, simple_loss=0.2486, pruned_loss=0.0433, over 7365.00 frames.], tot_loss[loss=0.188, simple_loss=0.2735, pruned_loss=0.05125, over 1429546.81 frames.], batch size: 19, lr: 3.02e-04
2022-05-28 00:56:36,711 INFO [train.py:842] (3/4) Epoch 18, batch 7900, loss[loss=0.2327, simple_loss=0.3198, pruned_loss=0.07277, over 7283.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2731, pruned_loss=0.0509, over 1432495.02 frames.], batch size: 24, lr: 3.02e-04
2022-05-28 00:57:14,991 INFO [train.py:842] (3/4) Epoch 18, batch 7950, loss[loss=0.2981, simple_loss=0.3577, pruned_loss=0.1193, over 4942.00 frames.], tot_loss[loss=0.188, simple_loss=0.2736, pruned_loss=0.05118, over 1431878.24 frames.], batch size: 52, lr: 3.02e-04
2022-05-28 00:57:52,953 INFO [train.py:842] (3/4) Epoch 18, batch 8000, loss[loss=0.1732, simple_loss=0.2792, pruned_loss=0.03363, over 7216.00 frames.], tot_loss[loss=0.188, simple_loss=0.2737, pruned_loss=0.05115, over 1433090.59 frames.], batch size: 21, lr: 3.02e-04
2022-05-28 00:58:31,221 INFO [train.py:842] (3/4) Epoch 18, batch 8050, loss[loss=0.1879, simple_loss=0.2829, pruned_loss=0.04645, over 7031.00 frames.], tot_loss[loss=0.1887, simple_loss=0.274, pruned_loss=0.05166, over 1428605.74 frames.], batch size: 28, lr: 3.02e-04
2022-05-28 00:59:09,181 INFO [train.py:842] (3/4) Epoch 18, batch 8100, loss[loss=0.1727, simple_loss=0.2576, pruned_loss=0.04388, over 6817.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2749, pruned_loss=0.05208, over 1425222.79 frames.], batch size: 15, lr: 3.02e-04
2022-05-28 00:59:47,556 INFO [train.py:842] (3/4) Epoch 18, batch 8150, loss[loss=0.1981, simple_loss=0.2785, pruned_loss=0.05884, over 7097.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2736, pruned_loss=0.05131, over 1427674.69 frames.], batch size: 28, lr: 3.02e-04
2022-05-28 01:00:25,312 INFO [train.py:842] (3/4) Epoch 18, batch 8200, loss[loss=0.1647, simple_loss=0.2511, pruned_loss=0.03915, over 7141.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2736, pruned_loss=0.05141, over 1426427.15 frames.], batch size: 17, lr: 3.02e-04
2022-05-28 01:01:03,710 INFO [train.py:842] (3/4) Epoch 18, batch 8250, loss[loss=0.204, simple_loss=0.2888, pruned_loss=0.05965, over 7217.00 frames.], tot_loss[loss=0.188, simple_loss=0.2733, pruned_loss=0.05134, over 1426842.39 frames.], batch size: 22, lr: 3.02e-04
2022-05-28 01:01:41,871 INFO [train.py:842] (3/4) Epoch 18, batch 8300, loss[loss=0.1428, simple_loss=0.2276, pruned_loss=0.02901, over 7155.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2723, pruned_loss=0.05091, over 1426971.59 frames.], batch size: 17, lr: 3.02e-04
2022-05-28 01:02:20,129 INFO [train.py:842] (3/4) Epoch 18, batch 8350, loss[loss=0.179, simple_loss=0.2826, pruned_loss=0.03771, over 7124.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2732, pruned_loss=0.05131, over 1426155.44 frames.], batch size: 21, lr: 3.02e-04
2022-05-28 01:02:58,020 INFO [train.py:842] (3/4) Epoch 18, batch 8400, loss[loss=0.1828, simple_loss=0.2654, pruned_loss=0.0501, over 7420.00 frames.], tot_loss[loss=0.1886, simple_loss=0.274, pruned_loss=0.05165, over 1422582.10 frames.], batch size: 21, lr: 3.02e-04
2022-05-28 01:03:36,357 INFO [train.py:842] (3/4) Epoch 18, batch 8450, loss[loss=0.2105, simple_loss=0.3047, pruned_loss=0.05816, over 7225.00 frames.], tot_loss[loss=0.188, simple_loss=0.2737, pruned_loss=0.0512, over 1423930.55 frames.], batch size: 26, lr: 3.01e-04
2022-05-28 01:04:14,378 INFO [train.py:842] (3/4) Epoch 18, batch 8500, loss[loss=0.166, simple_loss=0.2491, pruned_loss=0.04138, over 7080.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2736, pruned_loss=0.05141, over 1424566.60 frames.], batch size: 18, lr: 3.01e-04
2022-05-28 01:04:52,549 INFO [train.py:842] (3/4) Epoch 18, batch 8550, loss[loss=0.1791, simple_loss=0.2617, pruned_loss=0.04829, over 7410.00 frames.], tot_loss[loss=0.1898, simple_loss=0.275, pruned_loss=0.05236, over 1427132.45 frames.], batch size: 21, lr: 3.01e-04
2022-05-28 01:05:30,280 INFO [train.py:842] (3/4) Epoch 18, batch 8600, loss[loss=0.1868, simple_loss=0.2542, pruned_loss=0.05971, over 7285.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2759, pruned_loss=0.05294, over 1424735.09 frames.], batch size: 17, lr: 3.01e-04
2022-05-28 01:06:08,308 INFO [train.py:842] (3/4) Epoch 18, batch 8650, loss[loss=0.1683, simple_loss=0.2556, pruned_loss=0.04051, over 7265.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2771, pruned_loss=0.05352, over 1419111.60 frames.], batch size: 19, lr: 3.01e-04
2022-05-28 01:06:46,198 INFO [train.py:842] (3/4) Epoch 18, batch 8700, loss[loss=0.2636, simple_loss=0.3395, pruned_loss=0.09382, over 7303.00 frames.], tot_loss[loss=0.1907, simple_loss=0.276, pruned_loss=0.05273, over 1419325.18 frames.], batch size: 25, lr: 3.01e-04
2022-05-28 01:07:24,559 INFO [train.py:842] (3/4) Epoch 18, batch 8750, loss[loss=0.1793, simple_loss=0.275, pruned_loss=0.0418, over 7204.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2743, pruned_loss=0.05195, over 1419832.92 frames.], batch size: 23, lr: 3.01e-04
2022-05-28 01:08:02,255 INFO [train.py:842] (3/4) Epoch 18, batch 8800, loss[loss=0.2136, simple_loss=0.2757, pruned_loss=0.07575, over 7129.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2761, pruned_loss=0.05346, over 1410609.46 frames.], batch size: 17, lr: 3.01e-04
2022-05-28 01:08:40,264 INFO [train.py:842] (3/4) Epoch 18, batch 8850, loss[loss=0.1881, simple_loss=0.275, pruned_loss=0.05063, over 6422.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2762, pruned_loss=0.05369, over 1405439.61 frames.], batch size: 37, lr: 3.01e-04
2022-05-28 01:09:17,568 INFO [train.py:842] (3/4) Epoch 18, batch 8900, loss[loss=0.1997, simple_loss=0.2706, pruned_loss=0.06446, over 6985.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2767, pruned_loss=0.05415, over 1397700.72 frames.], batch size: 16, lr: 3.01e-04
2022-05-28 01:09:55,317 INFO [train.py:842] (3/4) Epoch 18, batch 8950, loss[loss=0.2227, simple_loss=0.2943, pruned_loss=0.07553, over 4798.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2757, pruned_loss=0.05332, over 1385969.79 frames.], batch size: 53, lr: 3.01e-04
2022-05-28 01:10:32,667 INFO [train.py:842] (3/4) Epoch 18, batch 9000, loss[loss=0.2061, simple_loss=0.297, pruned_loss=0.05759, over 6719.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2765, pruned_loss=0.05344, over 1382695.84 frames.], batch size: 31, lr: 3.01e-04
2022-05-28 01:10:32,668 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 01:10:41,756 INFO [train.py:871] (3/4) Epoch 18, validation: loss=0.1664, simple_loss=0.2661, pruned_loss=0.03336, over 868885.00 frames.
2022-05-28 01:11:19,010 INFO [train.py:842] (3/4) Epoch 18, batch 9050, loss[loss=0.1754, simple_loss=0.2642, pruned_loss=0.04329, over 6730.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2772, pruned_loss=0.05393, over 1366933.81 frames.], batch size: 31, lr: 3.01e-04
2022-05-28 01:11:55,788 INFO [train.py:842] (3/4) Epoch 18, batch 9100, loss[loss=0.2469, simple_loss=0.3308, pruned_loss=0.0815, over 4732.00 frames.], tot_loss[loss=0.199, simple_loss=0.2822, pruned_loss=0.05795, over 1295763.34 frames.], batch size: 52, lr: 3.01e-04
2022-05-28 01:12:32,915 INFO [train.py:842] (3/4) Epoch 18, batch 9150, loss[loss=0.2281, simple_loss=0.3083, pruned_loss=0.07401, over 5122.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2867, pruned_loss=0.06154, over 1233956.11 frames.], batch size: 52, lr: 3.01e-04
2022-05-28 01:13:18,591 INFO [train.py:842] (3/4) Epoch 19, batch 0, loss[loss=0.216, simple_loss=0.3052, pruned_loss=0.06336, over 7285.00 frames.], tot_loss[loss=0.216, simple_loss=0.3052, pruned_loss=0.06336, over 7285.00 frames.], batch size: 25, lr: 2.93e-04
2022-05-28 01:13:57,230 INFO [train.py:842] (3/4) Epoch 19, batch 50, loss[loss=0.1728, simple_loss=0.2767, pruned_loss=0.03448, over 7336.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2785, pruned_loss=0.05405, over 325440.14 frames.], batch size: 22, lr: 2.93e-04
2022-05-28 01:14:35,416 INFO [train.py:842] (3/4) Epoch 19, batch 100, loss[loss=0.235, simple_loss=0.3122, pruned_loss=0.07892, over 7334.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2744, pruned_loss=0.05028, over 575441.81 frames.], batch size: 22, lr: 2.93e-04
2022-05-28 01:15:13,710 INFO [train.py:842] (3/4) Epoch 19, batch 150, loss[loss=0.196, simple_loss=0.2979, pruned_loss=0.04703, over 7215.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2729, pruned_loss=0.05047, over 764526.95 frames.], batch size: 21, lr: 2.93e-04
2022-05-28 01:15:51,851 INFO [train.py:842] (3/4) Epoch 19, batch 200, loss[loss=0.1794, simple_loss=0.2654, pruned_loss=0.04669, over 7289.00 frames.], tot_loss[loss=0.1861, simple_loss=0.272, pruned_loss=0.05011, over 909707.24 frames.], batch size: 17, lr: 2.93e-04
2022-05-28 01:16:30,158 INFO [train.py:842] (3/4) Epoch 19, batch 250, loss[loss=0.1928, simple_loss=0.2843, pruned_loss=0.05072, over 6766.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2734, pruned_loss=0.05069, over 1025288.57 frames.], batch size: 31, lr: 2.93e-04
2022-05-28 01:17:08,203 INFO [train.py:842] (3/4) Epoch 19, batch 300, loss[loss=0.1803, simple_loss=0.2739, pruned_loss=0.0433, over 7233.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2721, pruned_loss=0.04982, over 1116028.27 frames.], batch size: 20, lr: 2.93e-04
2022-05-28 01:17:46,571 INFO [train.py:842] (3/4) Epoch 19, batch 350, loss[loss=0.2168, simple_loss=0.2959, pruned_loss=0.0688, over 6796.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2735, pruned_loss=0.05137, over 1182930.33 frames.], batch size: 31, lr: 2.93e-04
2022-05-28 01:18:24,407 INFO [train.py:842] (3/4) Epoch 19, batch 400, loss[loss=0.1678, simple_loss=0.2533, pruned_loss=0.04117, over 7059.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2742, pruned_loss=0.05154, over 1233911.96 frames.], batch size: 18, lr: 2.93e-04
2022-05-28 01:19:02,590 INFO [train.py:842] (3/4) Epoch 19, batch 450, loss[loss=0.1997, simple_loss=0.286, pruned_loss=0.05672, over 7321.00 frames.], tot_loss[loss=0.1884, simple_loss=0.274, pruned_loss=0.0514, over 1275471.22 frames.], batch size: 22, lr: 2.93e-04
2022-05-28 01:19:40,381 INFO [train.py:842] (3/4) Epoch 19, batch 500, loss[loss=0.1725, simple_loss=0.2531, pruned_loss=0.046, over 7143.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2744, pruned_loss=0.05185, over 1305999.34 frames.], batch size: 17, lr: 2.93e-04
2022-05-28 01:20:18,790 INFO [train.py:842] (3/4) Epoch 19, batch 550, loss[loss=0.1572, simple_loss=0.2354, pruned_loss=0.03945, over 7274.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2733, pruned_loss=0.05111, over 1335610.73 frames.], batch size: 17, lr: 2.93e-04
2022-05-28 01:20:56,851 INFO [train.py:842] (3/4) Epoch 19, batch 600, loss[loss=0.1947, simple_loss=0.2752, pruned_loss=0.05711, over 7278.00 frames.], tot_loss[loss=0.1879, simple_loss=0.273, pruned_loss=0.05143, over 1356302.63 frames.], batch size: 18, lr: 2.93e-04
2022-05-28 01:21:35,376 INFO [train.py:842] (3/4) Epoch 19, batch 650, loss[loss=0.1761, simple_loss=0.2649, pruned_loss=0.04359, over 7111.00 frames.], tot_loss[loss=0.187, simple_loss=0.2718, pruned_loss=0.05112, over 1375010.53 frames.], batch size: 21, lr: 2.93e-04
2022-05-28 01:22:13,261 INFO [train.py:842] (3/4) Epoch 19, batch 700, loss[loss=0.2244, simple_loss=0.3003, pruned_loss=0.07419, over 5251.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2734, pruned_loss=0.05187, over 1385955.19 frames.], batch size: 52, lr: 2.93e-04
2022-05-28 01:22:51,654 INFO [train.py:842] (3/4) Epoch 19, batch 750, loss[loss=0.1885, simple_loss=0.2669, pruned_loss=0.05503, over 7161.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2722, pruned_loss=0.05099, over 1395292.43 frames.], batch size: 19, lr: 2.93e-04
2022-05-28 01:23:29,312 INFO [train.py:842] (3/4) Epoch 19, batch 800, loss[loss=0.2144, simple_loss=0.2994, pruned_loss=0.06467, over 6714.00 frames.], tot_loss[loss=0.188, simple_loss=0.2734, pruned_loss=0.0513, over 1397762.58 frames.], batch size: 31, lr: 2.92e-04
2022-05-28 01:24:07,578 INFO [train.py:842] (3/4) Epoch 19, batch 850, loss[loss=0.1861, simple_loss=0.2763, pruned_loss=0.04796, over 7059.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2738, pruned_loss=0.05127, over 1405353.20 frames.], batch size: 18, lr: 2.92e-04
2022-05-28 01:24:45,433 INFO [train.py:842] (3/4) Epoch 19, batch 900, loss[loss=0.1842, simple_loss=0.2551, pruned_loss=0.05665, over 7221.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2744, pruned_loss=0.05105, over 1411147.17 frames.], batch size: 16, lr: 2.92e-04
2022-05-28 01:25:23,701 INFO [train.py:842] (3/4) Epoch 19, batch 950, loss[loss=0.2018, simple_loss=0.2895, pruned_loss=0.05703, over 7395.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2736, pruned_loss=0.05098, over 1414295.94 frames.], batch size: 23, lr: 2.92e-04
2022-05-28 01:26:01,661 INFO [train.py:842] (3/4) Epoch 19, batch 1000, loss[loss=0.1899, simple_loss=0.288, pruned_loss=0.04588, over 7138.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2748, pruned_loss=0.05187, over 1420502.68 frames.], batch size: 20, lr: 2.92e-04
2022-05-28 01:26:39,860 INFO [train.py:842] (3/4) Epoch 19, batch 1050, loss[loss=0.1747, simple_loss=0.2649, pruned_loss=0.04221, over 7310.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2743, pruned_loss=0.05195, over 1418782.10 frames.], batch size: 25, lr: 2.92e-04
2022-05-28 01:27:17,945 INFO [train.py:842] (3/4) Epoch 19, batch 1100, loss[loss=0.2041, simple_loss=0.2853, pruned_loss=0.06141, over 7335.00 frames.], tot_loss[loss=0.1899, simple_loss=0.275, pruned_loss=0.05241, over 1419580.55 frames.], batch size: 20, lr: 2.92e-04
2022-05-28 01:27:56,175 INFO [train.py:842] (3/4) Epoch 19, batch 1150, loss[loss=0.242, simple_loss=0.3176, pruned_loss=0.08321, over 7278.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2753, pruned_loss=0.05249, over 1419774.74 frames.], batch size: 24, lr: 2.92e-04
2022-05-28 01:28:34,217 INFO [train.py:842] (3/4) Epoch 19, batch 1200, loss[loss=0.27, simple_loss=0.3339, pruned_loss=0.1031, over 4755.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2753, pruned_loss=0.05292, over 1414723.41 frames.], batch size: 52, lr: 2.92e-04
2022-05-28 01:29:12,407 INFO [train.py:842] (3/4) Epoch 19, batch 1250, loss[loss=0.1892, simple_loss=0.2906, pruned_loss=0.04391, over 7117.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2746, pruned_loss=0.05225, over 1415641.23 frames.], batch size: 21, lr: 2.92e-04
2022-05-28 01:29:50,149 INFO [train.py:842] (3/4) Epoch 19, batch 1300, loss[loss=0.1645, simple_loss=0.2517, pruned_loss=0.03865, over 7146.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2741, pruned_loss=0.05163, over 1415134.23 frames.], batch size: 19, lr: 2.92e-04
2022-05-28 01:30:28,063 INFO [train.py:842] (3/4) Epoch 19, batch 1350, loss[loss=0.1732, simple_loss=0.267, pruned_loss=0.03969, over 7047.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2749, pruned_loss=0.05223, over 1413283.84 frames.], batch size: 28, lr: 2.92e-04
2022-05-28 01:31:06,131 INFO [train.py:842] (3/4) Epoch 19, batch 1400, loss[loss=0.2023, simple_loss=0.2793, pruned_loss=0.06263, over 7075.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2753, pruned_loss=0.05318, over 1411351.18 frames.], batch size: 18, lr: 2.92e-04
2022-05-28 01:31:44,483 INFO [train.py:842] (3/4) Epoch 19, batch 1450, loss[loss=0.1751, simple_loss=0.2607, pruned_loss=0.04481, over 7319.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2746, pruned_loss=0.05256, over 1417886.58 frames.], batch size: 21, lr: 2.92e-04
2022-05-28 01:32:22,424 INFO [train.py:842] (3/4) Epoch 19, batch 1500, loss[loss=0.1699, simple_loss=0.2599, pruned_loss=0.03991, over 7255.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2751, pruned_loss=0.0522, over 1421741.14 frames.], batch size: 19, lr: 2.92e-04
2022-05-28 01:33:00,829 INFO [train.py:842] (3/4) Epoch 19, batch 1550, loss[loss=0.1856, simple_loss=0.286, pruned_loss=0.04257, over 7419.00 frames.], tot_loss[loss=0.189, simple_loss=0.2744, pruned_loss=0.05184, over 1425179.07 frames.], batch size: 21, lr: 2.92e-04
2022-05-28 01:33:38,793 INFO [train.py:842] (3/4) Epoch 19, batch 1600, loss[loss=0.1842, simple_loss=0.2721, pruned_loss=0.04819, over 7221.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2731, pruned_loss=0.05108, over 1423863.23 frames.], batch size: 22, lr: 2.92e-04
2022-05-28 01:34:17,156 INFO [train.py:842] (3/4) Epoch 19, batch 1650, loss[loss=0.1519, simple_loss=0.2325, pruned_loss=0.03561, over 7167.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2732, pruned_loss=0.05175, over 1423296.93 frames.], batch size: 18, lr: 2.92e-04
2022-05-28 01:34:55,117 INFO [train.py:842] (3/4) Epoch 19, batch 1700, loss[loss=0.1836, simple_loss=0.2647, pruned_loss=0.05123, over 7164.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2736, pruned_loss=0.05141, over 1423221.87 frames.], batch size: 18, lr: 2.92e-04
2022-05-28 01:35:32,927 INFO [train.py:842] (3/4) Epoch 19, batch 1750, loss[loss=0.2182, simple_loss=0.2988, pruned_loss=0.06882, over 7150.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2742, pruned_loss=0.05125, over 1416339.02 frames.], batch size: 20, lr: 2.92e-04
2022-05-28 01:36:10,619 INFO [train.py:842] (3/4) Epoch 19, batch 1800, loss[loss=0.172, simple_loss=0.2587, pruned_loss=0.04263, over 7266.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2744, pruned_loss=0.05086, over 1417443.61 frames.], batch size: 19, lr: 2.92e-04
2022-05-28 01:36:48,925 INFO [train.py:842] (3/4) Epoch 19, batch 1850, loss[loss=0.1851, simple_loss=0.2641, pruned_loss=0.05304, over 7287.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2746, pruned_loss=0.0509, over 1423396.87 frames.], batch size: 24, lr: 2.92e-04
2022-05-28 01:37:26,740 INFO [train.py:842] (3/4) Epoch 19, batch 1900, loss[loss=0.1683, simple_loss=0.2583, pruned_loss=0.03909, over 7109.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2744, pruned_loss=0.05109, over 1419834.47 frames.], batch size: 28, lr: 2.92e-04
2022-05-28 01:38:05,000 INFO [train.py:842] (3/4) Epoch 19, batch 1950, loss[loss=0.151, simple_loss=0.2305, pruned_loss=0.03572, over 6990.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2734, pruned_loss=0.05042, over 1420510.86 frames.], batch size: 16, lr: 2.91e-04
2022-05-28 01:38:43,031 INFO [train.py:842] (3/4) Epoch 19, batch 2000, loss[loss=0.1846, simple_loss=0.2776, pruned_loss=0.04579, over 7146.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2725, pruned_loss=0.05004, over 1424189.89 frames.], batch size: 20, lr: 2.91e-04
2022-05-28 01:39:21,324 INFO [train.py:842] (3/4) Epoch 19, batch 2050, loss[loss=0.2187, simple_loss=0.2917, pruned_loss=0.07285, over 7310.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2732, pruned_loss=0.05102, over 1424089.58 frames.], batch size: 25, lr: 2.91e-04
2022-05-28 01:39:59,174 INFO [train.py:842] (3/4) Epoch 19, batch 2100, loss[loss=0.1757, simple_loss=0.2639, pruned_loss=0.04371, over 7160.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2731, pruned_loss=0.05091, over 1424386.64 frames.], batch size: 19, lr: 2.91e-04
2022-05-28 01:40:37,560 INFO [train.py:842] (3/4) Epoch 19, batch 2150, loss[loss=0.2031, simple_loss=0.2913, pruned_loss=0.05746, over 7227.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2726, pruned_loss=0.05084, over 1421200.27 frames.], batch size: 21, lr: 2.91e-04
2022-05-28 01:41:15,629 INFO [train.py:842] (3/4) Epoch 19, batch 2200, loss[loss=0.1826, simple_loss=0.2649, pruned_loss=0.05013, over 7125.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2727, pruned_loss=0.0508, over 1425725.30 frames.], batch size: 21, lr: 2.91e-04
2022-05-28 01:41:53,811 INFO [train.py:842] (3/4) Epoch 19, batch 2250, loss[loss=0.1666, simple_loss=0.249, pruned_loss=0.04216, over 6437.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2734, pruned_loss=0.05077, over 1424487.66 frames.], batch size: 38, lr: 2.91e-04
2022-05-28 01:42:31,843 INFO [train.py:842] (3/4) Epoch 19, batch 2300, loss[loss=0.2019, simple_loss=0.2885, pruned_loss=0.05761, over 7383.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2743, pruned_loss=0.05152, over 1425929.91 frames.], batch size: 23, lr: 2.91e-04
2022-05-28 01:43:09,941 INFO [train.py:842] (3/4) Epoch 19, batch 2350, loss[loss=0.193, simple_loss=0.2606, pruned_loss=0.06277, over 7294.00 frames.], tot_loss[loss=0.1896, simple_loss=0.275, pruned_loss=0.0521, over 1423128.13 frames.], batch size: 17, lr: 2.91e-04
2022-05-28 01:43:57,332 INFO [train.py:842] (3/4) Epoch 19, batch 2400, loss[loss=0.1996, simple_loss=0.2929, pruned_loss=0.05311, over 7144.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2746, pruned_loss=0.05188, over 1419124.60 frames.], batch size: 20, lr: 2.91e-04
2022-05-28 01:44:35,691 INFO [train.py:842] (3/4) Epoch 19, batch 2450, loss[loss=0.2301, simple_loss=0.3153, pruned_loss=0.07244, over 7140.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2754, pruned_loss=0.05238, over 1421475.94 frames.], batch size: 20, lr: 2.91e-04
2022-05-28 01:45:13,672 INFO [train.py:842] (3/4) Epoch 19, batch 2500, loss[loss=0.1917, simple_loss=0.2724, pruned_loss=0.05551, over 7180.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2747, pruned_loss=0.05237, over 1420558.13 frames.], batch size: 26, lr: 2.91e-04
2022-05-28 01:45:54,642 INFO [train.py:842] (3/4) Epoch 19, batch 2550, loss[loss=0.2084, simple_loss=0.2932, pruned_loss=0.06175, over 7270.00 frames.], tot_loss[loss=0.19, simple_loss=0.2748, pruned_loss=0.05262, over 1420644.21 frames.], batch size: 24, lr: 2.91e-04
2022-05-28 01:46:32,542 INFO [train.py:842] (3/4) Epoch 19, batch 2600, loss[loss=0.1724, simple_loss=0.2585, pruned_loss=0.04312, over 6989.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2747, pruned_loss=0.05181, over 1424901.19 frames.], batch size: 16, lr: 2.91e-04
2022-05-28 01:47:10,857 INFO [train.py:842] (3/4) Epoch 19, batch 2650, loss[loss=0.2748, simple_loss=0.3429, pruned_loss=0.1033, over 7254.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2749, pruned_loss=0.05223, over 1426975.42 frames.], batch size: 24, lr: 2.91e-04
2022-05-28 01:47:49,151 INFO [train.py:842] (3/4) Epoch 19, batch 2700, loss[loss=0.2176, simple_loss=0.3096, pruned_loss=0.06286, over 7307.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2748, pruned_loss=0.05189, over 1431121.12 frames.], batch size: 25, lr: 2.91e-04
2022-05-28 01:48:27,308 INFO [train.py:842] (3/4) Epoch 19, batch 2750, loss[loss=0.1996, simple_loss=0.2898, pruned_loss=0.05472, over 7407.00 frames.], tot_loss[loss=0.1904, simple_loss=0.276, pruned_loss=0.05245, over 1430585.17 frames.], batch size: 21, lr: 2.91e-04
2022-05-28 01:49:05,393 INFO [train.py:842] (3/4) Epoch 19, batch 2800, loss[loss=0.1621, simple_loss=0.2486, pruned_loss=0.03777, over 7075.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2758, pruned_loss=0.0526, over 1431290.86 frames.], batch size: 18, lr: 2.91e-04
2022-05-28 01:49:43,512 INFO [train.py:842] (3/4) Epoch 19, batch 2850, loss[loss=0.1803, simple_loss=0.2727, pruned_loss=0.04397, over 7155.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2752, pruned_loss=0.05201, over 1427883.11 frames.], batch size: 19, lr: 2.91e-04
2022-05-28 01:50:21,401 INFO [train.py:842] (3/4) Epoch 19, batch 2900, loss[loss=0.1968, simple_loss=0.2877, pruned_loss=0.05294, over 7132.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2739, pruned_loss=0.05139, over 1426221.14 frames.], batch size: 26, lr: 2.91e-04
2022-05-28 01:50:59,794 INFO [train.py:842] (3/4) Epoch 19, batch 2950, loss[loss=0.1882, simple_loss=0.274, pruned_loss=0.05117, over 7273.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2737, pruned_loss=0.05125, over 1431513.32 frames.], batch size: 17, lr: 2.91e-04
2022-05-28 01:51:37,815 INFO [train.py:842] (3/4) Epoch 19, batch 3000, loss[loss=0.211, simple_loss=0.2958, pruned_loss=0.06307, over 4831.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2727, pruned_loss=0.05081, over 1430786.77 frames.], batch size: 52, lr: 2.91e-04
2022-05-28 01:51:37,816 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 01:51:46,796 INFO [train.py:871] (3/4) Epoch 19, validation: loss=0.1654, simple_loss=0.2649, pruned_loss=0.03297, over 868885.00 frames.
2022-05-28 01:52:25,074 INFO [train.py:842] (3/4) Epoch 19, batch 3050, loss[loss=0.2558, simple_loss=0.3482, pruned_loss=0.0817, over 7204.00 frames.], tot_loss[loss=0.188, simple_loss=0.2735, pruned_loss=0.05127, over 1431878.70 frames.], batch size: 23, lr: 2.91e-04
2022-05-28 01:53:03,103 INFO [train.py:842] (3/4) Epoch 19, batch 3100, loss[loss=0.1932, simple_loss=0.2837, pruned_loss=0.05137, over 6233.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2739, pruned_loss=0.05154, over 1432232.22 frames.], batch size: 37, lr: 2.90e-04
2022-05-28 01:53:41,182 INFO [train.py:842] (3/4) Epoch 19, batch 3150, loss[loss=0.1898, simple_loss=0.2587, pruned_loss=0.0604, over 7271.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2744, pruned_loss=0.0519, over 1429064.28 frames.], batch size: 18, lr: 2.90e-04
2022-05-28 01:54:19,126 INFO [train.py:842] (3/4) Epoch 19, batch 3200, loss[loss=0.205, simple_loss=0.2855, pruned_loss=0.06225, over 7156.00 frames.], tot_loss[loss=0.189, simple_loss=0.2744, pruned_loss=0.05183, over 1427527.95 frames.], batch size: 19, lr: 2.90e-04
2022-05-28 01:54:57,220 INFO [train.py:842] (3/4) Epoch 19, batch 3250, loss[loss=0.2181, simple_loss=0.2916, pruned_loss=0.07235, over 7358.00 frames.], tot_loss[loss=0.189, simple_loss=0.2747, pruned_loss=0.05163, over 1424457.40 frames.], batch size: 19, lr: 2.90e-04
2022-05-28 01:55:35,150 INFO [train.py:842] (3/4) Epoch 19, batch 3300, loss[loss=0.1597, simple_loss=0.2533, pruned_loss=0.03303, over 6347.00 frames.], tot_loss[loss=0.1892, simple_loss=0.275, pruned_loss=0.05163, over 1424911.23 frames.], batch size: 38, lr: 2.90e-04
2022-05-28 01:56:13,612 INFO [train.py:842] (3/4) Epoch 19, batch 3350, loss[loss=0.1716, simple_loss=0.2493, pruned_loss=0.04693, over 7122.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2747, pruned_loss=0.05129, over 1424408.96 frames.], batch size: 21, lr: 2.90e-04
2022-05-28 01:56:51,562 INFO [train.py:842] (3/4) Epoch 19, batch 3400, loss[loss=0.18, simple_loss=0.2604, pruned_loss=0.04983, over 7292.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2755, pruned_loss=0.05203, over 1425199.02 frames.], batch size: 18, lr: 2.90e-04
2022-05-28 01:57:29,947 INFO [train.py:842] (3/4) Epoch 19, batch 3450, loss[loss=0.1501, simple_loss=0.237, pruned_loss=0.03156, over 7362.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2741, pruned_loss=0.05121, over 1421143.11 frames.], batch size: 19, lr: 2.90e-04
2022-05-28 01:58:07,910 INFO [train.py:842] (3/4) Epoch 19, batch 3500, loss[loss=0.216, simple_loss=0.2861, pruned_loss=0.07288, over 7278.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2745, pruned_loss=0.05164, over 1423570.38 frames.], batch size: 18, lr: 2.90e-04
2022-05-28 01:58:46,252 INFO [train.py:842] (3/4) Epoch 19, batch 3550, loss[loss=0.2041, simple_loss=0.2846, pruned_loss=0.0618, over 7122.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2746, pruned_loss=0.05161, over 1422573.61 frames.], batch size: 17, lr: 2.90e-04
2022-05-28 01:59:24,116 INFO [train.py:842] (3/4) Epoch 19, batch 3600, loss[loss=0.1814, simple_loss=0.27, pruned_loss=0.04634, over 7216.00 frames.], tot_loss[loss=0.19, simple_loss=0.2756, pruned_loss=0.05218, over 1420415.93 frames.], batch size: 23, lr: 2.90e-04
2022-05-28 02:00:02,227 INFO [train.py:842] (3/4) Epoch 19, batch 3650, loss[loss=0.1877, simple_loss=0.2811, pruned_loss=0.04711, over 7329.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2768, pruned_loss=0.0525, over 1414663.39 frames.], batch size: 20, lr: 2.90e-04
2022-05-28 02:00:40,213 INFO [train.py:842] (3/4) Epoch 19, batch 3700, loss[loss=0.1841, simple_loss=0.2558, pruned_loss=0.05623, over 7269.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2758, pruned_loss=0.05196, over 1417092.82 frames.], batch size: 17, lr: 2.90e-04
2022-05-28 02:01:18,454 INFO [train.py:842] (3/4) Epoch 19, batch 3750, loss[loss=0.2211, simple_loss=0.3103, pruned_loss=0.06596, over 7328.00 frames.], tot_loss[loss=0.1891, simple_loss=0.275, pruned_loss=0.05159, over 1413049.83 frames.], batch size: 22, lr: 2.90e-04
2022-05-28 02:01:56,353 INFO [train.py:842] (3/4) Epoch 19, batch 3800, loss[loss=0.1428, simple_loss=0.2362, pruned_loss=0.02471, over 6987.00 frames.], tot_loss[loss=0.1886, simple_loss=0.275, pruned_loss=0.05117, over 1417644.50 frames.], batch size: 16, lr: 2.90e-04
2022-05-28 02:02:34,517 INFO [train.py:842] (3/4) Epoch 19, batch 3850, loss[loss=0.2648, simple_loss=0.3305, pruned_loss=0.09961, over 5148.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2755, pruned_loss=0.05184, over 1415510.94 frames.], batch size: 53, lr: 2.90e-04
2022-05-28 02:03:12,474 INFO [train.py:842] (3/4) Epoch 19, batch 3900, loss[loss=0.1971, simple_loss=0.2865, pruned_loss=0.05385, over 7202.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2754, pruned_loss=0.05201, over 1415553.39 frames.], batch size: 26, lr: 2.90e-04
2022-05-28 02:03:50,756 INFO [train.py:842] (3/4) Epoch 19, batch 3950, loss[loss=0.1763, simple_loss=0.2706, pruned_loss=0.04097, over 7239.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2751, pruned_loss=0.0522, over 1417778.99 frames.], batch size: 20, lr: 2.90e-04
2022-05-28 02:04:28,773 INFO [train.py:842] (3/4) Epoch 19, batch 4000, loss[loss=0.1901, simple_loss=0.2809, pruned_loss=0.04965, over 7106.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2735, pruned_loss=0.0514, over 1420276.16 frames.], batch size: 21, lr: 2.90e-04
2022-05-28 02:05:07,119 INFO [train.py:842] (3/4) Epoch 19, batch 4050, loss[loss=0.1557, simple_loss=0.2461, pruned_loss=0.03264, over 7355.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2732, pruned_loss=0.05068, over 1419831.69 frames.], batch size: 19, lr: 2.90e-04
2022-05-28 02:05:45,240 INFO [train.py:842] (3/4) Epoch 19, batch 4100, loss[loss=0.171, simple_loss=0.2623, pruned_loss=0.03989, over 7147.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2726, pruned_loss=0.05074, over 1417436.69 frames.], batch size: 20, lr: 2.90e-04
2022-05-28 02:06:23,175 INFO [train.py:842] (3/4) Epoch 19, batch 4150, loss[loss=0.2362, simple_loss=0.3258, pruned_loss=0.07331, over 7197.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2751, pruned_loss=0.05169, over 1416172.56 frames.], batch size: 22, lr: 2.90e-04
2022-05-28 02:07:01,162 INFO [train.py:842] (3/4) Epoch 19, batch 4200, loss[loss=0.208, simple_loss=0.2974, pruned_loss=0.05933, over 7322.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2751, pruned_loss=0.05128, over 1423559.03 frames.], batch size: 22, lr: 2.90e-04
2022-05-28 02:07:39,416 INFO [train.py:842] (3/4) Epoch 19, batch 4250, loss[loss=0.1964, simple_loss=0.2824, pruned_loss=0.05521, over 7319.00 frames.], tot_loss[loss=0.189, simple_loss=0.2751, pruned_loss=0.05144, over 1422319.22 frames.], batch size: 20, lr: 2.90e-04
2022-05-28 02:08:17,286 INFO [train.py:842] (3/4) Epoch 19, batch 4300, loss[loss=0.1903, simple_loss=0.2726, pruned_loss=0.05399, over 7172.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2757, pruned_loss=0.05228, over 1421272.04 frames.], batch size: 23, lr: 2.89e-04
2022-05-28 02:08:55,445 INFO [train.py:842] (3/4) Epoch 19, batch 4350, loss[loss=0.1633, simple_loss=0.2584, pruned_loss=0.03411, over 6862.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2762, pruned_loss=0.05214, over 1421669.43 frames.], batch size: 31, lr: 2.89e-04
2022-05-28 02:09:33,407 INFO [train.py:842] (3/4) Epoch 19, batch 4400, loss[loss=0.1665, simple_loss=0.2646, pruned_loss=0.03421, over 7227.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2755, pruned_loss=0.05156, over 1423593.97 frames.], batch size: 20, lr: 2.89e-04
2022-05-28 02:10:11,533 INFO [train.py:842] (3/4) Epoch 19, batch 4450, loss[loss=0.188, simple_loss=0.2766, pruned_loss=0.04972, over 7113.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2768, pruned_loss=0.0522, over 1420612.24 frames.], batch size: 21, lr: 2.89e-04
2022-05-28 02:10:49,585 INFO [train.py:842] (3/4) Epoch 19, batch 4500, loss[loss=0.2061, simple_loss=0.2909, pruned_loss=0.06065, over 7283.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2763, pruned_loss=0.05213, over 1420754.91 frames.], batch size: 24, lr: 2.89e-04
2022-05-28 02:11:28,105 INFO [train.py:842] (3/4) Epoch 19, batch 4550, loss[loss=0.1822, simple_loss=0.2653, pruned_loss=0.04955, over 7391.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2738, pruned_loss=0.05096, over 1425054.05 frames.], batch size: 23, lr: 2.89e-04
2022-05-28 02:12:06,117 INFO [train.py:842] (3/4) Epoch 19, batch 4600, loss[loss=0.2082, simple_loss=0.2903, pruned_loss=0.06309, over 7415.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2729, pruned_loss=0.05065, over 1424014.80 frames.], batch size: 21, lr: 2.89e-04
2022-05-28 02:12:44,401 INFO [train.py:842] (3/4) Epoch 19, batch 4650, loss[loss=0.187, simple_loss=0.2736, pruned_loss=0.05016, over 7353.00 frames.], tot_loss[loss=0.1875, simple_loss=0.273, pruned_loss=0.05103, over 1420381.71 frames.], batch size: 19, lr: 2.89e-04
2022-05-28 02:13:22,321 INFO [train.py:842] (3/4) Epoch 19, batch 4700, loss[loss=0.1513, simple_loss=0.2377, pruned_loss=0.03238, over 7276.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2732, pruned_loss=0.05077, over 1421169.67 frames.], batch size: 17, lr: 2.89e-04
2022-05-28 02:14:00,475 INFO [train.py:842] (3/4) Epoch 19, batch 4750, loss[loss=0.1385, simple_loss=0.2219, pruned_loss=0.0276, over 7284.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2728, pruned_loss=0.05039, over 1423800.75 frames.], batch size: 17, lr: 2.89e-04
2022-05-28 02:14:38,601 INFO [train.py:842] (3/4) Epoch 19, batch 4800, loss[loss=0.1773, simple_loss=0.2624, pruned_loss=0.04606, over 7262.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2732, pruned_loss=0.05064, over 1418777.27 frames.], batch size: 19, lr: 2.89e-04
2022-05-28 02:15:16,767 INFO [train.py:842] (3/4) Epoch 19, batch 4850, loss[loss=0.1502, simple_loss=0.2291, pruned_loss=0.03566, over 6771.00 frames.], tot_loss[loss=0.1879, simple_loss=0.274, pruned_loss=0.0509, over 1419246.02 frames.], batch size: 15, lr: 2.89e-04
2022-05-28 02:15:54,799 INFO [train.py:842] (3/4) Epoch 19, batch 4900, loss[loss=0.1842, simple_loss=0.2748, pruned_loss=0.04677, over 7230.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2718, pruned_loss=0.0497, over 1421161.86 frames.], batch size: 21, lr: 2.89e-04
2022-05-28 02:16:32,991 INFO [train.py:842] (3/4) Epoch 19, batch 4950, loss[loss=0.2042, simple_loss=0.2961, pruned_loss=0.05616, over 5080.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2727, pruned_loss=0.0501, over 1419069.30 frames.], batch size: 52, lr: 2.89e-04
2022-05-28 02:17:10,626 INFO [train.py:842] (3/4) Epoch 19, batch 5000, loss[loss=0.1611, simple_loss=0.2577, pruned_loss=0.03223, over 6768.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2748, pruned_loss=0.05069, over 1421572.31 frames.], batch size: 31, lr: 2.89e-04
2022-05-28 02:17:48,869 INFO [train.py:842] (3/4) Epoch 19, batch 5050, loss[loss=0.1654, simple_loss=0.2344, pruned_loss=0.04824, over 7002.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2761, pruned_loss=0.05209, over 1421888.00 frames.], batch size: 16, lr: 2.89e-04
2022-05-28 02:18:26,635 INFO [train.py:842] (3/4) Epoch 19, batch 5100, loss[loss=0.2047, simple_loss=0.2879, pruned_loss=0.06072, over 4904.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2755, pruned_loss=0.05154, over 1420342.52 frames.], batch size: 52, lr: 2.89e-04
2022-05-28 02:19:05,006 INFO [train.py:842] (3/4) Epoch 19, batch 5150, loss[loss=0.2081, simple_loss=0.3102, pruned_loss=0.053, over 7166.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2748, pruned_loss=0.05099, over 1422363.48 frames.], batch size: 19, lr: 2.89e-04
2022-05-28 02:19:43,069 INFO [train.py:842] (3/4) Epoch 19, batch 5200, loss[loss=0.215, simple_loss=0.2965, pruned_loss=0.06669, over 6787.00 frames.], tot_loss[loss=0.1879, simple_loss=0.274, pruned_loss=0.05089, over 1425415.28 frames.], batch size: 31, lr: 2.89e-04
2022-05-28 02:20:21,233 INFO [train.py:842] (3/4) Epoch 19, batch 5250, loss[loss=0.2003, simple_loss=0.2682, pruned_loss=0.06617, over 7295.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2745, pruned_loss=0.05119, over 1418528.53 frames.], batch size: 17, lr: 2.89e-04
2022-05-28 02:21:08,637 INFO [train.py:842] (3/4) Epoch 19, batch 5300, loss[loss=0.1324, simple_loss=0.2182, pruned_loss=0.02331, over 7285.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2735, pruned_loss=0.05104, over 1422214.69 frames.], batch size: 18, lr: 2.89e-04
2022-05-28 02:21:47,033 INFO [train.py:842] (3/4) Epoch 19, batch 5350, loss[loss=0.1832, simple_loss=0.2703, pruned_loss=0.04808, over 7217.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2722, pruned_loss=0.05043, over 1420667.46 frames.], batch size: 21, lr: 2.89e-04
2022-05-28 02:22:24,939 INFO [train.py:842] (3/4) Epoch 19, batch 5400, loss[loss=0.2522, simple_loss=0.3094, pruned_loss=0.09749, over 7436.00 frames.], tot_loss[loss=0.1877, simple_loss=0.273, pruned_loss=0.05121, over 1420720.40 frames.], batch size: 20, lr: 2.89e-04
2022-05-28 02:23:12,407 INFO [train.py:842] (3/4) Epoch 19, batch 5450, loss[loss=0.1832, simple_loss=0.2658, pruned_loss=0.05035, over 6729.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2738, pruned_loss=0.05152, over 1420280.92 frames.], batch size: 31, lr: 2.88e-04
2022-05-28 02:23:50,555 INFO [train.py:842] (3/4) Epoch 19, batch 5500, loss[loss=0.1835, simple_loss=0.2602, pruned_loss=0.05346, over 6999.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2729, pruned_loss=0.05133, over 1418997.72 frames.], batch size: 16, lr: 2.88e-04
2022-05-28 02:24:28,425 INFO [train.py:842] (3/4) Epoch 19, batch 5550, loss[loss=0.342, simple_loss=0.3934, pruned_loss=0.1453, over 5259.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2745, pruned_loss=0.05195, over 1418985.09 frames.], batch size: 52, lr: 2.88e-04
2022-05-28 02:25:06,228 INFO [train.py:842] (3/4) Epoch 19, batch 5600, loss[loss=0.1578, simple_loss=0.2395, pruned_loss=0.03805, over 7164.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2748, pruned_loss=0.05168, over 1420845.77 frames.], batch size: 18, lr: 2.88e-04
2022-05-28 02:25:44,625 INFO [train.py:842] (3/4) Epoch 19, batch 5650, loss[loss=0.2048, simple_loss=0.3054, pruned_loss=0.05209, over 7329.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2744, pruned_loss=0.05144, over 1422737.78 frames.], batch size: 22, lr: 2.88e-04
2022-05-28 02:26:31,927 INFO [train.py:842] (3/4) Epoch 19, batch 5700, loss[loss=0.2407, simple_loss=0.3177, pruned_loss=0.08182, over 7014.00 frames.], tot_loss[loss=0.1884, simple_loss=0.274, pruned_loss=0.0514, over 1423624.84 frames.], batch size: 28, lr: 2.88e-04
2022-05-28 02:27:10,281 INFO [train.py:842] (3/4) Epoch 19, batch 5750, loss[loss=0.1602, simple_loss=0.248, pruned_loss=0.03622, over 7135.00 frames.], tot_loss[loss=0.1882, simple_loss=0.274, pruned_loss=0.05118, over 1429542.31 frames.], batch size: 17, lr: 2.88e-04
2022-05-28 02:27:48,267 INFO [train.py:842] (3/4) Epoch 19, batch 5800, loss[loss=0.2506, simple_loss=0.3306, pruned_loss=0.08532, over 7320.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2743, pruned_loss=0.05217, over 1428524.46 frames.], batch size: 20, lr: 2.88e-04
2022-05-28 02:28:26,603 INFO [train.py:842] (3/4) Epoch 19, batch 5850, loss[loss=0.243, simple_loss=0.3178, pruned_loss=0.08405, over 4971.00 frames.], tot_loss[loss=0.1892, simple_loss=0.274, pruned_loss=0.05222, over 1426498.38 frames.], batch size: 52, lr: 2.88e-04
2022-05-28 02:29:04,697 INFO [train.py:842] (3/4) Epoch 19, batch 5900, loss[loss=0.1853, simple_loss=0.265, pruned_loss=0.05278, over 7328.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2711, pruned_loss=0.05034, over 1422979.70 frames.], batch size: 20, lr: 2.88e-04
2022-05-28 02:29:43,072 INFO [train.py:842] (3/4) Epoch 19, batch 5950, loss[loss=0.1574, simple_loss=0.2517, pruned_loss=0.03156, over 7315.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2719, pruned_loss=0.05046, over 1427170.21 frames.], batch size: 21, lr: 2.88e-04
2022-05-28 02:30:20,903 INFO [train.py:842] (3/4) Epoch 19, batch 6000, loss[loss=0.2482, simple_loss=0.3315, pruned_loss=0.08252, over 6864.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2732, pruned_loss=0.0513, over 1424470.34 frames.], batch size: 31, lr: 2.88e-04
2022-05-28 02:30:20,904 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 02:30:29,955 INFO [train.py:871] (3/4) Epoch 19, validation: loss=0.1648, simple_loss=0.2646, pruned_loss=0.03256, over 868885.00 frames.
2022-05-28 02:31:08,294 INFO [train.py:842] (3/4) Epoch 19, batch 6050, loss[loss=0.2182, simple_loss=0.3049, pruned_loss=0.06579, over 7415.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2725, pruned_loss=0.05111, over 1426090.42 frames.], batch size: 21, lr: 2.88e-04
2022-05-28 02:31:45,888 INFO [train.py:842] (3/4) Epoch 19, batch 6100, loss[loss=0.1943, simple_loss=0.2803, pruned_loss=0.05418, over 6698.00 frames.], tot_loss[loss=0.1886, simple_loss=0.274, pruned_loss=0.05156, over 1423699.41 frames.], batch size: 31, lr: 2.88e-04
2022-05-28 02:32:24,070 INFO [train.py:842] (3/4) Epoch 19, batch 6150, loss[loss=0.202, simple_loss=0.2903, pruned_loss=0.05689, over 7154.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2735, pruned_loss=0.05079, over 1428026.81 frames.], batch size: 20, lr: 2.88e-04
2022-05-28 02:33:02,034 INFO [train.py:842] (3/4) Epoch 19, batch 6200, loss[loss=0.2253, simple_loss=0.3099, pruned_loss=0.07038, over 7263.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2743, pruned_loss=0.05136, over 1424695.85 frames.], batch size: 19, lr: 2.88e-04
2022-05-28 02:33:40,516 INFO [train.py:842] (3/4) Epoch 19, batch 6250, loss[loss=0.1635, simple_loss=0.2438, pruned_loss=0.04161, over 7389.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2732, pruned_loss=0.05102, over 1429281.43 frames.], batch size: 18, lr: 2.88e-04
2022-05-28 02:34:18,351 INFO [train.py:842] (3/4) Epoch 19, batch 6300, loss[loss=0.1937, simple_loss=0.2768, pruned_loss=0.0553, over 7304.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2736, pruned_loss=0.05116, over 1424978.87 frames.], batch size: 25, lr: 2.88e-04
2022-05-28 02:34:56,852 INFO [train.py:842] (3/4) Epoch 19, batch 6350, loss[loss=0.1638, simple_loss=0.2434, pruned_loss=0.04207, over 7162.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2734, pruned_loss=0.05144, over 1427223.30 frames.], batch size: 18, lr: 2.88e-04
2022-05-28 02:35:34,603 INFO [train.py:842] (3/4) Epoch 19, batch 6400, loss[loss=0.1913, simple_loss=0.2893, pruned_loss=0.04663, over 7106.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2738, pruned_loss=0.05136, over 1426184.23 frames.], batch size: 28, lr: 2.88e-04
2022-05-28 02:36:12,803 INFO [train.py:842] (3/4) Epoch 19, batch 6450, loss[loss=0.1503, simple_loss=0.2393, pruned_loss=0.03061, over 7058.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2745, pruned_loss=0.0522, over 1423850.22 frames.], batch size: 18, lr: 2.88e-04
2022-05-28 02:36:50,732 INFO [train.py:842] (3/4) Epoch 19, batch 6500, loss[loss=0.1719, simple_loss=0.2661, pruned_loss=0.03891, over 6449.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2747, pruned_loss=0.05237, over 1424165.02 frames.], batch size: 38, lr: 2.88e-04
2022-05-28 02:37:28,657 INFO [train.py:842] (3/4) Epoch 19, batch 6550, loss[loss=0.1698, simple_loss=0.2642, pruned_loss=0.03766, over 7105.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2758, pruned_loss=0.05239, over 1421552.73 frames.], batch size: 21, lr: 2.88e-04
2022-05-28 02:38:06,631 INFO [train.py:842] (3/4) Epoch 19, batch 6600, loss[loss=0.1891, simple_loss=0.2704, pruned_loss=0.05394, over 7222.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2749, pruned_loss=0.05184, over 1424707.10 frames.], batch size: 20, lr: 2.88e-04
2022-05-28 02:38:44,833 INFO [train.py:842] (3/4) Epoch 19, batch 6650, loss[loss=0.1658, simple_loss=0.2569, pruned_loss=0.03739, over 7328.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2747, pruned_loss=0.05198, over 1419028.06 frames.], batch size: 20, lr: 2.87e-04
2022-05-28 02:39:22,756 INFO [train.py:842] (3/4) Epoch 19, batch 6700, loss[loss=0.2091, simple_loss=0.3028, pruned_loss=0.05769, over 7340.00 frames.], tot_loss[loss=0.1881, simple_loss=0.274, pruned_loss=0.05111, over 1420483.68 frames.], batch size: 22, lr: 2.87e-04
2022-05-28 02:40:00,839 INFO [train.py:842] (3/4) Epoch 19, batch 6750, loss[loss=0.1777, simple_loss=0.2699, pruned_loss=0.04275, over 7116.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2738, pruned_loss=0.05097, over 1419740.55 frames.], batch size: 21, lr: 2.87e-04
2022-05-28 02:40:39,058 INFO [train.py:842] (3/4) Epoch 19, batch 6800, loss[loss=0.1931, simple_loss=0.2812, pruned_loss=0.05247, over 7314.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2735, pruned_loss=0.05073, over 1425820.28 frames.], batch size: 25, lr: 2.87e-04
2022-05-28 02:41:17,211 INFO [train.py:842] (3/4) Epoch 19, batch 6850, loss[loss=0.1936, simple_loss=0.2847, pruned_loss=0.05127, over 7204.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2733, pruned_loss=0.05009, over 1427208.85 frames.], batch size: 23, lr: 2.87e-04
2022-05-28 02:41:55,501 INFO [train.py:842] (3/4) Epoch 19, batch 6900, loss[loss=0.1912, simple_loss=0.2876, pruned_loss=0.04736, over 7411.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2725, pruned_loss=0.05006, over 1428663.76 frames.], batch size: 21, lr: 2.87e-04
2022-05-28 02:42:33,710 INFO [train.py:842] (3/4) Epoch 19, batch 6950, loss[loss=0.2141, simple_loss=0.2999, pruned_loss=0.06414, over 7148.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2739, pruned_loss=0.05083, over 1426384.70 frames.], batch size: 20, lr: 2.87e-04
2022-05-28 02:43:11,788 INFO [train.py:842] (3/4) Epoch 19, batch 7000, loss[loss=0.1799, simple_loss=0.2594, pruned_loss=0.05024, over 7132.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2728, pruned_loss=0.04999, over 1423568.55 frames.], batch size: 17, lr: 2.87e-04
2022-05-28 02:43:50,065 INFO [train.py:842] (3/4) Epoch 19, batch 7050, loss[loss=0.262, simple_loss=0.3349, pruned_loss=0.09455, over 6861.00 frames.], tot_loss[loss=0.186, simple_loss=0.2722, pruned_loss=0.04987, over 1423897.52 frames.], batch size: 31, lr: 2.87e-04
2022-05-28 02:44:27,967 INFO [train.py:842] (3/4) Epoch 19, batch 7100, loss[loss=0.1667, simple_loss=0.2571, pruned_loss=0.03816, over 7209.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2733, pruned_loss=0.0501, over 1425161.16 frames.], batch size: 22, lr: 2.87e-04
2022-05-28 02:45:06,039 INFO [train.py:842] (3/4) Epoch 19, batch 7150, loss[loss=0.1626, simple_loss=0.2334, pruned_loss=0.0459, over 7288.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2741, pruned_loss=0.0506, over 1424761.03 frames.], batch size: 17, lr: 2.87e-04
2022-05-28 02:45:44,154 INFO [train.py:842] (3/4) Epoch 19, batch 7200, loss[loss=0.1657, simple_loss=0.2485, pruned_loss=0.04151, over 7287.00 frames.], tot_loss[loss=0.187, simple_loss=0.2728, pruned_loss=0.05058, over 1425389.05 frames.], batch size: 18, lr: 2.87e-04
2022-05-28 02:46:22,503 INFO [train.py:842] (3/4) Epoch 19, batch 7250, loss[loss=0.1939, simple_loss=0.2749, pruned_loss=0.05643, over 7190.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2732, pruned_loss=0.05122, over 1424121.57 frames.], batch size: 23, lr: 2.87e-04
2022-05-28 02:47:00,633 INFO [train.py:842] (3/4) Epoch 19, batch 7300, loss[loss=0.2024, simple_loss=0.2935, pruned_loss=0.0557, over 7329.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2728, pruned_loss=0.05121, over 1423021.50 frames.], batch size: 20, lr: 2.87e-04
2022-05-28 02:47:38,838 INFO [train.py:842] (3/4) Epoch 19, batch 7350, loss[loss=0.1362, simple_loss=0.2172, pruned_loss=0.0276, over 7149.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2736, pruned_loss=0.05176, over 1422045.20 frames.], batch size: 17, lr: 2.87e-04
2022-05-28 02:48:16,557 INFO [train.py:842] (3/4) Epoch 19, batch 7400, loss[loss=0.1514, simple_loss=0.2389, pruned_loss=0.03199, over 7344.00 frames.], tot_loss[loss=0.1888, simple_loss=0.274, pruned_loss=0.05183, over 1419258.30 frames.], batch size: 19, lr: 2.87e-04
2022-05-28 02:48:54,939 INFO [train.py:842] (3/4) Epoch 19, batch 7450, loss[loss=0.191, simple_loss=0.2843, pruned_loss=0.04891, over 7156.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2738, pruned_loss=0.05168, over 1418772.94 frames.], batch size: 19, lr: 2.87e-04
2022-05-28 02:49:33,068 INFO [train.py:842] (3/4) Epoch 19, batch 7500, loss[loss=0.1555, simple_loss=0.2483, pruned_loss=0.03133, over 7282.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2732, pruned_loss=0.05128, over 1423851.88 frames.], batch size: 17, lr: 2.87e-04
2022-05-28 02:50:11,372 INFO [train.py:842] (3/4) Epoch 19, batch 7550, loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.04408, over 7400.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2737, pruned_loss=0.05157, over 1426647.60 frames.], batch size: 21, lr: 2.87e-04
2022-05-28 02:50:49,182 INFO [train.py:842] (3/4) Epoch 19, batch 7600, loss[loss=0.1947, simple_loss=0.282, pruned_loss=0.05365, over 7103.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2751, pruned_loss=0.05174, over 1426810.86 frames.], batch size: 28, lr: 2.87e-04
2022-05-28 02:51:27,613 INFO [train.py:842] (3/4) Epoch 19, batch 7650, loss[loss=0.1742, simple_loss=0.2755, pruned_loss=0.0365, over 7013.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2739, pruned_loss=0.05144, over 1427192.90 frames.], batch size: 28, lr: 2.87e-04
2022-05-28 02:52:05,424 INFO [train.py:842] (3/4) Epoch 19, batch 7700, loss[loss=0.1928, simple_loss=0.2787, pruned_loss=0.05344, over 7315.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2741, pruned_loss=0.05164, over 1424042.97 frames.], batch size: 24, lr: 2.87e-04
2022-05-28 02:52:43,760 INFO [train.py:842] (3/4) Epoch 19, batch 7750, loss[loss=0.1532, simple_loss=0.2421, pruned_loss=0.03213, over 7162.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2744, pruned_loss=0.05198, over 1424580.17 frames.], batch size: 18, lr: 2.87e-04
2022-05-28 02:53:21,939 INFO [train.py:842] (3/4) Epoch 19, batch 7800, loss[loss=0.1454, simple_loss=0.2398, pruned_loss=0.02552, over 7426.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2731, pruned_loss=0.05136, over 1425438.99 frames.], batch size: 20, lr: 2.87e-04
2022-05-28 02:53:59,976 INFO [train.py:842] (3/4) Epoch 19, batch 7850, loss[loss=0.2138, simple_loss=0.2967, pruned_loss=0.06546, over 7302.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2721, pruned_loss=0.05068, over 1417887.09 frames.], batch size: 25, lr: 2.86e-04
2022-05-28 02:54:37,950 INFO [train.py:842] (3/4) Epoch 19, batch 7900, loss[loss=0.2236, simple_loss=0.3124, pruned_loss=0.06741, over 7338.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2729, pruned_loss=0.051, over 1419271.84 frames.], batch size: 22, lr: 2.86e-04
2022-05-28 02:55:16,100 INFO [train.py:842] (3/4) Epoch 19, batch 7950, loss[loss=0.1865, simple_loss=0.2686, pruned_loss=0.0522, over 7363.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2741, pruned_loss=0.05178, over 1421105.05 frames.], batch size: 19, lr: 2.86e-04
2022-05-28 02:55:54,126 INFO [train.py:842] (3/4) Epoch 19, batch 8000, loss[loss=0.1683, simple_loss=0.2513, pruned_loss=0.04263, over 7430.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2728, pruned_loss=0.05105, over 1420773.29 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 02:56:32,338 INFO [train.py:842] (3/4) Epoch 19, batch 8050, loss[loss=0.192, simple_loss=0.2829, pruned_loss=0.05054, over 7321.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2737, pruned_loss=0.05099, over 1425067.63 frames.], batch size: 21, lr: 2.86e-04
2022-05-28 02:57:10,370 INFO [train.py:842] (3/4) Epoch 19, batch 8100, loss[loss=0.2269, simple_loss=0.3134, pruned_loss=0.07018, over 7224.00 frames.], tot_loss[loss=0.187, simple_loss=0.2724, pruned_loss=0.05082, over 1425739.27 frames.], batch size: 21, lr: 2.86e-04
2022-05-28 02:57:48,670 INFO [train.py:842] (3/4) Epoch 19, batch 8150, loss[loss=0.1823, simple_loss=0.2638, pruned_loss=0.05042, over 7429.00 frames.], tot_loss[loss=0.1869, simple_loss=0.272, pruned_loss=0.05088, over 1422371.22 frames.], batch size: 20, lr: 2.86e-04
2022-05-28 02:58:26,744 INFO [train.py:842] (3/4) Epoch 19, batch 8200, loss[loss=0.1834, simple_loss=0.2694, pruned_loss=0.04867, over 7370.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2724, pruned_loss=0.05112, over 1425366.47 frames.], batch size: 19, lr: 2.86e-04
2022-05-28 02:59:05,086 INFO [train.py:842] (3/4) Epoch 19, batch 8250, loss[loss=0.1799, simple_loss=0.2601, pruned_loss=0.04983, over 7155.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2719, pruned_loss=0.0506, over 1428422.80 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 02:59:42,820 INFO [train.py:842] (3/4) Epoch 19, batch 8300, loss[loss=0.1937, simple_loss=0.2697, pruned_loss=0.05886, over 7443.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2728, pruned_loss=0.05018, over 1427746.14 frames.], batch size: 19, lr: 2.86e-04
2022-05-28 03:00:21,235 INFO [train.py:842] (3/4) Epoch 19, batch 8350, loss[loss=0.1855, simple_loss=0.2609, pruned_loss=0.05507, over 6991.00 frames.], tot_loss[loss=0.1882, simple_loss=0.274, pruned_loss=0.05118, over 1428953.34 frames.], batch size: 16, lr: 2.86e-04
2022-05-28 03:00:59,130 INFO [train.py:842] (3/4) Epoch 19, batch 8400, loss[loss=0.282, simple_loss=0.3486, pruned_loss=0.1077, over 7311.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2753, pruned_loss=0.05214, over 1423916.26 frames.], batch size: 21, lr: 2.86e-04
2022-05-28 03:01:37,407 INFO [train.py:842] (3/4) Epoch 19, batch 8450, loss[loss=0.2064, simple_loss=0.2738, pruned_loss=0.0695, over 7289.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2734, pruned_loss=0.05161, over 1422645.54 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 03:02:15,567 INFO [train.py:842] (3/4) Epoch 19, batch 8500, loss[loss=0.1563, simple_loss=0.2535, pruned_loss=0.02959, over 7435.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2717, pruned_loss=0.05043, over 1422089.91 frames.], batch size: 20, lr: 2.86e-04
2022-05-28 03:02:53,779 INFO [train.py:842] (3/4) Epoch 19, batch 8550, loss[loss=0.1813, simple_loss=0.275, pruned_loss=0.0438, over 7286.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2723, pruned_loss=0.05031, over 1424346.40 frames.], batch size: 24, lr: 2.86e-04
2022-05-28 03:03:31,639 INFO [train.py:842] (3/4) Epoch 19, batch 8600, loss[loss=0.2006, simple_loss=0.2871, pruned_loss=0.05706, over 5156.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2728, pruned_loss=0.05047, over 1421007.01 frames.], batch size: 52, lr: 2.86e-04
2022-05-28 03:04:09,688 INFO [train.py:842] (3/4) Epoch 19, batch 8650, loss[loss=0.1585, simple_loss=0.2516, pruned_loss=0.03271, over 7169.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2742, pruned_loss=0.05105, over 1420431.74 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 03:04:47,381 INFO [train.py:842] (3/4) Epoch 19, batch 8700, loss[loss=0.1962, simple_loss=0.2796, pruned_loss=0.05637, over 7367.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2737, pruned_loss=0.05099, over 1417230.48 frames.], batch size: 19, lr: 2.86e-04
2022-05-28 03:05:25,588 INFO [train.py:842] (3/4) Epoch 19, batch 8750, loss[loss=0.1924, simple_loss=0.2773, pruned_loss=0.05371, over 7225.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2735, pruned_loss=0.05078, over 1417403.47 frames.], batch size: 16, lr: 2.86e-04
2022-05-28 03:06:03,568 INFO [train.py:842] (3/4) Epoch 19, batch 8800, loss[loss=0.2205, simple_loss=0.3019, pruned_loss=0.06957, over 7268.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2737, pruned_loss=0.0511, over 1417538.41 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 03:06:41,771 INFO [train.py:842] (3/4) Epoch 19, batch 8850, loss[loss=0.2166, simple_loss=0.2997, pruned_loss=0.06674, over 7197.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2739, pruned_loss=0.05127, over 1414807.33 frames.], batch size: 23, lr: 2.86e-04
2022-05-28 03:07:19,683 INFO [train.py:842] (3/4) Epoch 19, batch 8900, loss[loss=0.163, simple_loss=0.2469, pruned_loss=0.03957, over 7257.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2733, pruned_loss=0.05121, over 1410146.15 frames.], batch size: 19, lr: 2.86e-04
2022-05-28 03:07:57,663 INFO [train.py:842] (3/4) Epoch 19, batch 8950, loss[loss=0.1695, simple_loss=0.2461, pruned_loss=0.04643, over 7289.00 frames.], tot_loss[loss=0.189, simple_loss=0.2739, pruned_loss=0.05202, over 1403448.22 frames.], batch size: 18, lr: 2.86e-04
2022-05-28 03:08:35,133 INFO [train.py:842] (3/4) Epoch 19, batch 9000, loss[loss=0.2033, simple_loss=0.2966, pruned_loss=0.05506, over 7223.00 frames.], tot_loss[loss=0.1897, simple_loss=0.275, pruned_loss=0.05224, over 1400971.36 frames.], batch size: 23, lr: 2.86e-04
2022-05-28 03:08:35,133 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 03:08:44,267 INFO [train.py:871] (3/4) Epoch 19, validation: loss=0.1647, simple_loss=0.2641, pruned_loss=0.03266, over 868885.00 frames.
2022-05-28 03:09:22,103 INFO [train.py:842] (3/4) Epoch 19, batch 9050, loss[loss=0.249, simple_loss=0.3235, pruned_loss=0.08724, over 5071.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2752, pruned_loss=0.05343, over 1381616.10 frames.], batch size: 52, lr: 2.86e-04
2022-05-28 03:09:59,170 INFO [train.py:842] (3/4) Epoch 19, batch 9100, loss[loss=0.2122, simple_loss=0.2834, pruned_loss=0.07048, over 5102.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2775, pruned_loss=0.05505, over 1333625.17 frames.], batch size: 52, lr: 2.85e-04
2022-05-28 03:10:36,169 INFO [train.py:842] (3/4) Epoch 19, batch 9150, loss[loss=0.2452, simple_loss=0.317, pruned_loss=0.08668, over 5046.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2822, pruned_loss=0.05859, over 1260048.37 frames.], batch size: 52, lr: 2.85e-04
2022-05-28 03:11:25,263 INFO [train.py:842] (3/4) Epoch 20, batch 0, loss[loss=0.1725, simple_loss=0.263, pruned_loss=0.04106, over 7365.00 frames.], tot_loss[loss=0.1725, simple_loss=0.263, pruned_loss=0.04106, over 7365.00 frames.], batch size: 19, lr: 2.78e-04
2022-05-28 03:12:03,125 INFO [train.py:842] (3/4) Epoch 20, batch 50, loss[loss=0.2066, simple_loss=0.2856, pruned_loss=0.06382, over 7306.00 frames.], tot_loss[loss=0.19, simple_loss=0.2782, pruned_loss=0.05093, over 320038.92 frames.], batch size: 18, lr: 2.78e-04
2022-05-28 03:12:41,516 INFO [train.py:842] (3/4) Epoch 20, batch 100, loss[loss=0.1895, simple_loss=0.2657, pruned_loss=0.05669, over 5067.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2764, pruned_loss=0.05132, over 565480.92 frames.], batch size: 54, lr: 2.78e-04
2022-05-28 03:13:19,284 INFO [train.py:842] (3/4) Epoch 20, batch 150, loss[loss=0.1794, simple_loss=0.2779, pruned_loss=0.04045, over 7319.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2784, pruned_loss=0.05223, over 755954.80 frames.], batch size: 21, lr: 2.78e-04
2022-05-28 03:13:57,454 INFO [train.py:842] (3/4) Epoch 20, batch 200, loss[loss=0.2031, simple_loss=0.2906, pruned_loss=0.05779, over 7333.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2779, pruned_loss=0.05238, over 903328.30 frames.], batch size: 22, lr: 2.78e-04
2022-05-28 03:14:35,706 INFO [train.py:842] (3/4) Epoch 20, batch 250, loss[loss=0.223, simple_loss=0.322, pruned_loss=0.06204, over 7344.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2755, pruned_loss=0.05097, over 1022477.89 frames.], batch size: 22, lr: 2.78e-04
2022-05-28 03:15:13,686 INFO [train.py:842] (3/4) Epoch 20, batch 300, loss[loss=0.2015, simple_loss=0.2897, pruned_loss=0.05665, over 7194.00 frames.], tot_loss[loss=0.1891, simple_loss=0.276, pruned_loss=0.0511, over 1111634.19 frames.], batch size: 23, lr: 2.78e-04
2022-05-28 03:15:51,623 INFO [train.py:842] (3/4) Epoch 20, batch 350, loss[loss=0.1786, simple_loss=0.2758, pruned_loss=0.04073, over 7149.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2756, pruned_loss=0.05091, over 1184074.98 frames.], batch size: 20, lr: 2.78e-04
2022-05-28 03:16:29,697 INFO [train.py:842] (3/4) Epoch 20, batch 400, loss[loss=0.1928, simple_loss=0.2837, pruned_loss=0.05099, over 7153.00 frames.], tot_loss[loss=0.1889, simple_loss=0.276, pruned_loss=0.05096, over 1237648.28 frames.], batch size: 20, lr: 2.78e-04
2022-05-28 03:17:07,422 INFO [train.py:842] (3/4) Epoch 20, batch 450, loss[loss=0.1738, simple_loss=0.2557, pruned_loss=0.04593, over 7387.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2758, pruned_loss=0.05085, over 1274521.04 frames.], batch size: 23, lr: 2.78e-04
2022-05-28 03:17:45,573 INFO [train.py:842] (3/4) Epoch 20, batch 500, loss[loss=0.1701, simple_loss=0.2636, pruned_loss=0.03826, over 7210.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2768, pruned_loss=0.05151, over 1306511.01 frames.], batch size: 21, lr: 2.78e-04
2022-05-28 03:18:23,489 INFO [train.py:842] (3/4) Epoch 20, batch 550, loss[loss=0.165, simple_loss=0.2606, pruned_loss=0.03467, over 6681.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2764, pruned_loss=0.0514, over 1333073.44 frames.], batch size: 31, lr: 2.78e-04
2022-05-28 03:19:02,118 INFO [train.py:842] (3/4) Epoch 20, batch 600, loss[loss=0.1894, simple_loss=0.2698, pruned_loss=0.05456, over 7150.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2748, pruned_loss=0.05096, over 1354649.22 frames.], batch size: 18, lr: 2.78e-04
2022-05-28 03:19:40,169 INFO [train.py:842] (3/4) Epoch 20, batch 650, loss[loss=0.1842, simple_loss=0.2678, pruned_loss=0.05034, over 7163.00 frames.], tot_loss[loss=0.188, simple_loss=0.2746, pruned_loss=0.05065, over 1369759.83 frames.], batch size: 18, lr: 2.78e-04
2022-05-28 03:20:18,368 INFO [train.py:842] (3/4) Epoch 20, batch 700, loss[loss=0.1855, simple_loss=0.2801, pruned_loss=0.04548, over 7239.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2738, pruned_loss=0.04992, over 1383952.64 frames.], batch size: 20, lr: 2.78e-04
2022-05-28 03:20:56,449 INFO [train.py:842] (3/4) Epoch 20, batch 750, loss[loss=0.2107, simple_loss=0.3027, pruned_loss=0.05938, over 7317.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2728, pruned_loss=0.04986, over 1394757.81 frames.], batch size: 25, lr: 2.78e-04
2022-05-28 03:21:34,817 INFO [train.py:842] (3/4) Epoch 20, batch 800, loss[loss=0.1403, simple_loss=0.2236, pruned_loss=0.02853, over 7424.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2715, pruned_loss=0.04913, over 1403508.00 frames.], batch size: 18, lr: 2.78e-04
2022-05-28 03:22:12,811 INFO [train.py:842] (3/4) Epoch 20, batch 850, loss[loss=0.2102, simple_loss=0.2954, pruned_loss=0.06253, over 7006.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2716, pruned_loss=0.04909, over 1411651.71 frames.], batch size: 28, lr: 2.78e-04
2022-05-28 03:22:51,273 INFO [train.py:842] (3/4) Epoch 20, batch 900, loss[loss=0.194, simple_loss=0.2784, pruned_loss=0.05475, over 7350.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2708, pruned_loss=0.04887, over 1416515.57 frames.], batch size: 19, lr: 2.78e-04
2022-05-28 03:23:29,312 INFO [train.py:842] (3/4) Epoch 20, batch 950, loss[loss=0.1803, simple_loss=0.2736, pruned_loss=0.04347, over 7246.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2721, pruned_loss=0.04923, over 1419509.02 frames.], batch size: 20, lr: 2.78e-04
2022-05-28 03:24:07,522 INFO [train.py:842] (3/4) Epoch 20, batch 1000, loss[loss=0.2733, simple_loss=0.3356, pruned_loss=0.1055, over 7298.00 frames.], tot_loss[loss=0.1861, simple_loss=0.273, pruned_loss=0.04961, over 1420417.30 frames.], batch size: 24, lr: 2.78e-04
2022-05-28 03:24:45,375 INFO [train.py:842] (3/4) Epoch 20, batch 1050, loss[loss=0.1651, simple_loss=0.249, pruned_loss=0.04054, over 7207.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2732, pruned_loss=0.04955, over 1420008.36 frames.], batch size: 22, lr: 2.78e-04
2022-05-28 03:25:23,607 INFO [train.py:842] (3/4) Epoch 20, batch 1100, loss[loss=0.2131, simple_loss=0.3005, pruned_loss=0.06284, over 7192.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2725, pruned_loss=0.04954, over 1415771.62 frames.], batch size: 22, lr: 2.78e-04
2022-05-28 03:26:01,388 INFO [train.py:842] (3/4) Epoch 20, batch 1150, loss[loss=0.2788, simple_loss=0.3493, pruned_loss=0.1041, over 7300.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2737, pruned_loss=0.04981, over 1419691.36 frames.], batch size: 24, lr: 2.78e-04
2022-05-28 03:26:39,931 INFO [train.py:842] (3/4) Epoch 20, batch 1200, loss[loss=0.1966, simple_loss=0.2897, pruned_loss=0.05176, over 7336.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2733, pruned_loss=0.05008, over 1424270.95 frames.], batch size: 22, lr: 2.78e-04
2022-05-28 03:27:17,887 INFO [train.py:842] (3/4) Epoch 20, batch 1250, loss[loss=0.1481, simple_loss=0.2287, pruned_loss=0.03369, over 7146.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2724, pruned_loss=0.0496, over 1425204.49 frames.], batch size: 17, lr: 2.78e-04
2022-05-28 03:27:56,128 INFO [train.py:842] (3/4) Epoch 20, batch 1300, loss[loss=0.1844, simple_loss=0.2806, pruned_loss=0.04407, over 7113.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2719, pruned_loss=0.04918, over 1427267.83 frames.], batch size: 21, lr: 2.77e-04
2022-05-28 03:28:34,018 INFO [train.py:842] (3/4) Epoch 20, batch 1350, loss[loss=0.1786, simple_loss=0.2684, pruned_loss=0.04442, over 7202.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2726, pruned_loss=0.04931, over 1429251.28 frames.], batch size: 22, lr: 2.77e-04
2022-05-28 03:29:15,152 INFO [train.py:842] (3/4) Epoch 20, batch 1400, loss[loss=0.2108, simple_loss=0.2883, pruned_loss=0.06666, over 7160.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2725, pruned_loss=0.04967, over 1431110.68 frames.], batch size: 26, lr: 2.77e-04
2022-05-28 03:29:53,003 INFO [train.py:842] (3/4) Epoch 20, batch 1450, loss[loss=0.2145, simple_loss=0.3028, pruned_loss=0.06316, over 7183.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2734, pruned_loss=0.04999, over 1429373.19 frames.], batch size: 26, lr: 2.77e-04
2022-05-28 03:30:31,249 INFO [train.py:842] (3/4) Epoch 20, batch 1500, loss[loss=0.1955, simple_loss=0.2825, pruned_loss=0.05419, over 7365.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2744, pruned_loss=0.0503, over 1427786.69 frames.], batch size: 23, lr: 2.77e-04
2022-05-28 03:31:09,385 INFO [train.py:842] (3/4) Epoch 20, batch 1550, loss[loss=0.1878, simple_loss=0.2767, pruned_loss=0.04939, over 7440.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2725, pruned_loss=0.0495, over 1429592.73 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:31:47,538 INFO [train.py:842] (3/4) Epoch 20, batch 1600, loss[loss=0.201, simple_loss=0.294, pruned_loss=0.05401, over 7333.00 frames.], tot_loss[loss=0.186, simple_loss=0.2723, pruned_loss=0.04987, over 1425177.63 frames.], batch size: 22, lr: 2.77e-04
2022-05-28 03:32:25,381 INFO [train.py:842] (3/4) Epoch 20, batch 1650, loss[loss=0.2309, simple_loss=0.3126, pruned_loss=0.07462, over 7195.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2731, pruned_loss=0.04999, over 1422351.31 frames.], batch size: 23, lr: 2.77e-04
2022-05-28 03:33:03,580 INFO [train.py:842] (3/4) Epoch 20, batch 1700, loss[loss=0.1735, simple_loss=0.2647, pruned_loss=0.04113, over 7156.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2724, pruned_loss=0.04969, over 1420746.24 frames.], batch size: 19, lr: 2.77e-04
2022-05-28 03:33:41,622 INFO [train.py:842] (3/4) Epoch 20, batch 1750, loss[loss=0.2088, simple_loss=0.3011, pruned_loss=0.05827, over 7346.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2735, pruned_loss=0.05016, over 1426590.36 frames.], batch size: 22, lr: 2.77e-04
2022-05-28 03:34:19,916 INFO [train.py:842] (3/4) Epoch 20, batch 1800, loss[loss=0.1909, simple_loss=0.282, pruned_loss=0.04995, over 7274.00 frames.], tot_loss[loss=0.187, simple_loss=0.2737, pruned_loss=0.05018, over 1426206.93 frames.], batch size: 25, lr: 2.77e-04
2022-05-28 03:34:58,003 INFO [train.py:842] (3/4) Epoch 20, batch 1850, loss[loss=0.169, simple_loss=0.2573, pruned_loss=0.04033, over 7056.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2729, pruned_loss=0.04998, over 1428786.55 frames.], batch size: 18, lr: 2.77e-04
2022-05-28 03:35:36,128 INFO [train.py:842] (3/4) Epoch 20, batch 1900, loss[loss=0.1673, simple_loss=0.2585, pruned_loss=0.03805, over 7231.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2736, pruned_loss=0.0498, over 1429291.77 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:36:14,214 INFO [train.py:842] (3/4) Epoch 20, batch 1950, loss[loss=0.2037, simple_loss=0.2948, pruned_loss=0.05634, over 6359.00 frames.], tot_loss[loss=0.1861, simple_loss=0.273, pruned_loss=0.04957, over 1429472.75 frames.], batch size: 37, lr: 2.77e-04
2022-05-28 03:36:52,623 INFO [train.py:842] (3/4) Epoch 20, batch 2000, loss[loss=0.2067, simple_loss=0.3065, pruned_loss=0.05349, over 7229.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2738, pruned_loss=0.0506, over 1430063.10 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:37:30,761 INFO [train.py:842] (3/4) Epoch 20, batch 2050, loss[loss=0.2003, simple_loss=0.2974, pruned_loss=0.05159, over 7210.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2731, pruned_loss=0.05027, over 1429323.09 frames.], batch size: 21, lr: 2.77e-04
2022-05-28 03:38:09,221 INFO [train.py:842] (3/4) Epoch 20, batch 2100, loss[loss=0.1825, simple_loss=0.2698, pruned_loss=0.04763, over 7444.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2712, pruned_loss=0.0493, over 1432455.84 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:38:47,119 INFO [train.py:842] (3/4) Epoch 20, batch 2150, loss[loss=0.203, simple_loss=0.29, pruned_loss=0.05805, over 7208.00 frames.], tot_loss[loss=0.186, simple_loss=0.2722, pruned_loss=0.04988, over 1425899.64 frames.], batch size: 22, lr: 2.77e-04
2022-05-28 03:39:25,453 INFO [train.py:842] (3/4) Epoch 20, batch 2200, loss[loss=0.1609, simple_loss=0.2378, pruned_loss=0.042, over 6810.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2714, pruned_loss=0.04991, over 1420772.44 frames.], batch size: 15, lr: 2.77e-04
2022-05-28 03:40:03,673 INFO [train.py:842] (3/4) Epoch 20, batch 2250, loss[loss=0.1994, simple_loss=0.2786, pruned_loss=0.06012, over 7156.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2722, pruned_loss=0.05021, over 1423706.75 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:40:41,877 INFO [train.py:842] (3/4) Epoch 20, batch 2300, loss[loss=0.2197, simple_loss=0.3041, pruned_loss=0.06766, over 7393.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2711, pruned_loss=0.0496, over 1424279.07 frames.], batch size: 23, lr: 2.77e-04
2022-05-28 03:41:19,755 INFO [train.py:842] (3/4) Epoch 20, batch 2350, loss[loss=0.2095, simple_loss=0.2981, pruned_loss=0.06047, over 7315.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2709, pruned_loss=0.04917, over 1423254.42 frames.], batch size: 21, lr: 2.77e-04
2022-05-28 03:41:58,029 INFO [train.py:842] (3/4) Epoch 20, batch 2400, loss[loss=0.1754, simple_loss=0.268, pruned_loss=0.04137, over 7432.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2708, pruned_loss=0.04906, over 1424530.30 frames.], batch size: 20, lr: 2.77e-04
2022-05-28 03:42:36,050 INFO [train.py:842] (3/4) Epoch 20, batch 2450, loss[loss=0.2139, simple_loss=0.3082, pruned_loss=0.05979, over 7105.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2715, pruned_loss=0.04963, over 1427742.87 frames.], batch size: 28, lr: 2.77e-04
2022-05-28 03:43:14,466 INFO [train.py:842] (3/4) Epoch 20, batch 2500, loss[loss=0.1782, simple_loss=0.2674, pruned_loss=0.04452, over 7174.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2708, pruned_loss=0.04923, over 1426018.21 frames.], batch size: 26, lr: 2.77e-04
2022-05-28 03:43:52,366 INFO [train.py:842] (3/4) Epoch 20, batch 2550, loss[loss=0.1804, simple_loss=0.2706, pruned_loss=0.04513, over 7332.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2714, pruned_loss=0.04991, over 1426042.30 frames.], batch size: 20, lr: 2.76e-04
2022-05-28 03:44:30,389 INFO [train.py:842] (3/4) Epoch 20, batch 2600, loss[loss=0.1849, simple_loss=0.2842, pruned_loss=0.04281, over 6783.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2734, pruned_loss=0.05072, over 1427086.67 frames.], batch size: 31, lr: 2.76e-04
2022-05-28 03:45:08,536 INFO [train.py:842] (3/4) Epoch 20, batch 2650, loss[loss=0.1704, simple_loss=0.2504, pruned_loss=0.04521, over 7009.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2731, pruned_loss=0.051, over 1428523.87 frames.], batch size: 16, lr: 2.76e-04
2022-05-28 03:45:46,861 INFO [train.py:842] (3/4) Epoch 20, batch 2700, loss[loss=0.1628, simple_loss=0.2545, pruned_loss=0.03553, over 7385.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2717, pruned_loss=0.05024, over 1429064.60 frames.], batch size: 23, lr: 2.76e-04
2022-05-28 03:46:24,699 INFO [train.py:842] (3/4) Epoch 20, batch 2750, loss[loss=0.2136, simple_loss=0.3095, pruned_loss=0.05879, over 7188.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2718, pruned_loss=0.0497, over 1427254.82 frames.], batch size: 23, lr: 2.76e-04
2022-05-28 03:47:03,029 INFO [train.py:842] (3/4) Epoch 20, batch 2800, loss[loss=0.1956, simple_loss=0.2704, pruned_loss=0.06034, over 7168.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2716, pruned_loss=0.04968, over 1430545.85 frames.], batch size: 18, lr: 2.76e-04
2022-05-28 03:47:41,139 INFO [train.py:842] (3/4) Epoch 20, batch 2850, loss[loss=0.1755, simple_loss=0.2682, pruned_loss=0.04135, over 7409.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2708, pruned_loss=0.04941, over 1432064.20 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:48:19,362 INFO [train.py:842] (3/4) Epoch 20, batch 2900, loss[loss=0.2355, simple_loss=0.3187, pruned_loss=0.07615, over 7130.00 frames.], tot_loss[loss=0.185, simple_loss=0.2708, pruned_loss=0.04962, over 1427735.64 frames.], batch size: 26, lr: 2.76e-04
2022-05-28 03:48:57,425 INFO [train.py:842] (3/4) Epoch 20, batch 2950, loss[loss=0.1891, simple_loss=0.2841, pruned_loss=0.04702, over 7240.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2721, pruned_loss=0.04984, over 1432537.15 frames.], batch size: 20, lr: 2.76e-04
2022-05-28 03:49:35,444 INFO [train.py:842] (3/4) Epoch 20, batch 3000, loss[loss=0.2331, simple_loss=0.3169, pruned_loss=0.07468, over 7384.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2731, pruned_loss=0.05029, over 1431351.53 frames.], batch size: 23, lr: 2.76e-04
2022-05-28 03:49:35,444 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 03:49:44,759 INFO [train.py:871] (3/4) Epoch 20, validation: loss=0.1666, simple_loss=0.2655, pruned_loss=0.0338, over 868885.00 frames.
2022-05-28 03:50:22,740 INFO [train.py:842] (3/4) Epoch 20, batch 3050, loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04235, over 7147.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2736, pruned_loss=0.05059, over 1432626.13 frames.], batch size: 19, lr: 2.76e-04
2022-05-28 03:51:00,933 INFO [train.py:842] (3/4) Epoch 20, batch 3100, loss[loss=0.1893, simple_loss=0.2801, pruned_loss=0.04921, over 7124.00 frames.], tot_loss[loss=0.1878, simple_loss=0.274, pruned_loss=0.05079, over 1431513.38 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:51:38,897 INFO [train.py:842] (3/4) Epoch 20, batch 3150, loss[loss=0.2015, simple_loss=0.277, pruned_loss=0.06296, over 7289.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2737, pruned_loss=0.05059, over 1432025.83 frames.], batch size: 18, lr: 2.76e-04
2022-05-28 03:52:17,383 INFO [train.py:842] (3/4) Epoch 20, batch 3200, loss[loss=0.1789, simple_loss=0.2709, pruned_loss=0.04346, over 6950.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2726, pruned_loss=0.05019, over 1431606.06 frames.], batch size: 32, lr: 2.76e-04
2022-05-28 03:52:55,238 INFO [train.py:842] (3/4) Epoch 20, batch 3250, loss[loss=0.1651, simple_loss=0.2503, pruned_loss=0.03994, over 7061.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2734, pruned_loss=0.05045, over 1428350.36 frames.], batch size: 18, lr: 2.76e-04
2022-05-28 03:53:33,562 INFO [train.py:842] (3/4) Epoch 20, batch 3300, loss[loss=0.1921, simple_loss=0.2644, pruned_loss=0.05995, over 7127.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2734, pruned_loss=0.05074, over 1428007.27 frames.], batch size: 17, lr: 2.76e-04
2022-05-28 03:54:11,571 INFO [train.py:842] (3/4) Epoch 20, batch 3350, loss[loss=0.1753, simple_loss=0.2644, pruned_loss=0.04304, over 7147.00 frames.], tot_loss[loss=0.187, simple_loss=0.273, pruned_loss=0.05049, over 1427450.12 frames.], batch size: 20, lr: 2.76e-04
2022-05-28 03:54:49,734 INFO [train.py:842] (3/4) Epoch 20, batch 3400, loss[loss=0.1738, simple_loss=0.2586, pruned_loss=0.04448, over 7274.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2734, pruned_loss=0.05075, over 1426356.94 frames.], batch size: 17, lr: 2.76e-04
2022-05-28 03:55:27,655 INFO [train.py:842] (3/4) Epoch 20, batch 3450, loss[loss=0.1814, simple_loss=0.2746, pruned_loss=0.0441, over 7243.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2726, pruned_loss=0.0501, over 1425343.37 frames.], batch size: 20, lr: 2.76e-04
2022-05-28 03:56:05,952 INFO [train.py:842] (3/4) Epoch 20, batch 3500, loss[loss=0.1757, simple_loss=0.2576, pruned_loss=0.04693, over 7258.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2725, pruned_loss=0.05022, over 1423678.97 frames.], batch size: 19, lr: 2.76e-04
2022-05-28 03:56:43,798 INFO [train.py:842] (3/4) Epoch 20, batch 3550, loss[loss=0.188, simple_loss=0.2776, pruned_loss=0.04918, over 7120.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2734, pruned_loss=0.05075, over 1426829.62 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:57:22,223 INFO [train.py:842] (3/4) Epoch 20, batch 3600, loss[loss=0.217, simple_loss=0.2969, pruned_loss=0.06853, over 7434.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2739, pruned_loss=0.05095, over 1431312.50 frames.], batch size: 20, lr: 2.76e-04
2022-05-28 03:58:00,181 INFO [train.py:842] (3/4) Epoch 20, batch 3650, loss[loss=0.1541, simple_loss=0.2478, pruned_loss=0.03026, over 7421.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2726, pruned_loss=0.05014, over 1431686.74 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:58:38,389 INFO [train.py:842] (3/4) Epoch 20, batch 3700, loss[loss=0.1653, simple_loss=0.2575, pruned_loss=0.03651, over 7225.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2725, pruned_loss=0.04995, over 1432913.93 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:59:16,265 INFO [train.py:842] (3/4) Epoch 20, batch 3750, loss[loss=0.1588, simple_loss=0.2606, pruned_loss=0.02851, over 7316.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2729, pruned_loss=0.05033, over 1428325.07 frames.], batch size: 21, lr: 2.76e-04
2022-05-28 03:59:54,694 INFO [train.py:842] (3/4) Epoch 20, batch 3800, loss[loss=0.162, simple_loss=0.2348, pruned_loss=0.04458, over 7280.00 frames.], tot_loss[loss=0.1873, simple_loss=0.273, pruned_loss=0.05081, over 1428234.85 frames.], batch size: 17, lr: 2.76e-04
2022-05-28 04:00:32,649 INFO [train.py:842] (3/4) Epoch 20, batch 3850, loss[loss=0.1727, simple_loss=0.2613, pruned_loss=0.04206, over 7359.00 frames.], tot_loss[loss=0.187, simple_loss=0.2729, pruned_loss=0.05057, over 1424023.88 frames.], batch size: 19, lr: 2.75e-04
2022-05-28 04:01:10,458 INFO [train.py:842] (3/4) Epoch 20, batch 3900, loss[loss=0.1892, simple_loss=0.2799, pruned_loss=0.04929, over 7282.00 frames.], tot_loss[loss=0.1875, simple_loss=0.274, pruned_loss=0.05052, over 1420675.40 frames.], batch size: 25, lr: 2.75e-04
2022-05-28 04:01:48,154 INFO [train.py:842] (3/4) Epoch 20, batch 3950, loss[loss=0.1743, simple_loss=0.2624, pruned_loss=0.0431, over 7407.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2737, pruned_loss=0.05043, over 1418120.36 frames.], batch size: 21, lr: 2.75e-04
2022-05-28 04:02:26,113 INFO [train.py:842] (3/4) Epoch 20, batch 4000, loss[loss=0.1774, simple_loss=0.2707, pruned_loss=0.04202, over 7222.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2739, pruned_loss=0.05046, over 1410097.30 frames.], batch size: 21, lr: 2.75e-04
2022-05-28 04:03:04,021 INFO [train.py:842] (3/4) Epoch 20, batch 4050, loss[loss=0.1509, simple_loss=0.2492, pruned_loss=0.02629, over 7222.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2742, pruned_loss=0.0504, over 1412286.90 frames.], batch size: 21, lr: 2.75e-04
2022-05-28 04:03:42,441 INFO [train.py:842] (3/4) Epoch 20, batch 4100, loss[loss=0.1983, simple_loss=0.2944, pruned_loss=0.0511, over 7189.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2741, pruned_loss=0.0502, over 1411203.89 frames.], batch size: 26, lr: 2.75e-04
2022-05-28 04:04:20,460 INFO [train.py:842] (3/4) Epoch 20, batch 4150, loss[loss=0.2333, simple_loss=0.3175, pruned_loss=0.07457, over 7341.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2731, pruned_loss=0.04976, over 1415903.89 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:04:58,994 INFO [train.py:842] (3/4) Epoch 20, batch 4200, loss[loss=0.1834, simple_loss=0.2752, pruned_loss=0.04582, over 7365.00 frames.], tot_loss[loss=0.185, simple_loss=0.2716, pruned_loss=0.0492, over 1419651.33 frames.], batch size: 19, lr: 2.75e-04
2022-05-28 04:05:36,681 INFO [train.py:842] (3/4) Epoch 20, batch 4250, loss[loss=0.201, simple_loss=0.2947, pruned_loss=0.05362, over 7154.00 frames.], tot_loss[loss=0.187, simple_loss=0.2732, pruned_loss=0.0504, over 1416821.59 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:06:14,975 INFO [train.py:842] (3/4) Epoch 20, batch 4300, loss[loss=0.1654, simple_loss=0.2615, pruned_loss=0.03463, over 7162.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2721, pruned_loss=0.05024, over 1415428.32 frames.], batch size: 26, lr: 2.75e-04
2022-05-28 04:06:53,174 INFO [train.py:842] (3/4) Epoch 20, batch 4350, loss[loss=0.177, simple_loss=0.2539, pruned_loss=0.05001, over 7398.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2702, pruned_loss=0.04912, over 1417693.56 frames.], batch size: 18, lr: 2.75e-04
2022-05-28 04:07:31,390 INFO [train.py:842] (3/4) Epoch 20, batch 4400, loss[loss=0.1978, simple_loss=0.2785, pruned_loss=0.05855, over 7270.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2712, pruned_loss=0.04984, over 1420562.07 frames.], batch size: 25, lr: 2.75e-04
2022-05-28 04:08:09,374 INFO [train.py:842] (3/4) Epoch 20, batch 4450, loss[loss=0.1871, simple_loss=0.2771, pruned_loss=0.04849, over 7412.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04952, over 1415050.67 frames.], batch size: 21, lr: 2.75e-04
2022-05-28 04:08:47,646 INFO [train.py:842] (3/4) Epoch 20, batch 4500, loss[loss=0.1657, simple_loss=0.2541, pruned_loss=0.0387, over 7171.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2701, pruned_loss=0.04932, over 1419874.91 frames.], batch size: 26, lr: 2.75e-04
2022-05-28 04:09:25,678 INFO [train.py:842] (3/4) Epoch 20, batch 4550, loss[loss=0.1914, simple_loss=0.27, pruned_loss=0.05637, over 7359.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2694, pruned_loss=0.04867, over 1425306.11 frames.], batch size: 19, lr: 2.75e-04
2022-05-28 04:10:04,101 INFO [train.py:842] (3/4) Epoch 20, batch 4600, loss[loss=0.1888, simple_loss=0.2845, pruned_loss=0.04653, over 7325.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2695, pruned_loss=0.04903, over 1423186.66 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:10:42,091 INFO [train.py:842] (3/4) Epoch 20, batch 4650, loss[loss=0.1975, simple_loss=0.2868, pruned_loss=0.05406, over 7143.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2704, pruned_loss=0.04957, over 1426289.58 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:11:20,095 INFO [train.py:842] (3/4) Epoch 20, batch 4700, loss[loss=0.2209, simple_loss=0.3046, pruned_loss=0.06866, over 7219.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2701, pruned_loss=0.04915, over 1422470.04 frames.], batch size: 21, lr: 2.75e-04
2022-05-28 04:11:57,880 INFO [train.py:842] (3/4) Epoch 20, batch 4750, loss[loss=0.1794, simple_loss=0.2735, pruned_loss=0.04266, over 6287.00 frames.], tot_loss[loss=0.1849, simple_loss=0.271, pruned_loss=0.04939, over 1421228.30 frames.], batch size: 37, lr: 2.75e-04
2022-05-28 04:12:36,335 INFO [train.py:842] (3/4) Epoch 20, batch 4800, loss[loss=0.2011, simple_loss=0.2751, pruned_loss=0.06356, over 4640.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2708, pruned_loss=0.04939, over 1421947.39 frames.], batch size: 52, lr: 2.75e-04
2022-05-28 04:13:14,132 INFO [train.py:842] (3/4) Epoch 20, batch 4850, loss[loss=0.2047, simple_loss=0.3017, pruned_loss=0.0538, over 7152.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2705, pruned_loss=0.04923, over 1418195.86 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:13:52,320 INFO [train.py:842] (3/4) Epoch 20, batch 4900, loss[loss=0.2204, simple_loss=0.299, pruned_loss=0.07085, over 4807.00 frames.], tot_loss[loss=0.186, simple_loss=0.2723, pruned_loss=0.04984, over 1420191.57 frames.], batch size: 52, lr: 2.75e-04
2022-05-28 04:14:30,429 INFO [train.py:842] (3/4) Epoch 20, batch 4950, loss[loss=0.267, simple_loss=0.3432, pruned_loss=0.09545, over 7152.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2726, pruned_loss=0.05042, over 1422981.65 frames.], batch size: 20, lr: 2.75e-04
2022-05-28 04:15:18,014 INFO [train.py:842] (3/4) Epoch 20, batch 5000, loss[loss=0.1876, simple_loss=0.2816, pruned_loss=0.04683, over 7191.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2726, pruned_loss=0.05033, over 1428007.80 frames.], batch size: 26, lr: 2.75e-04
2022-05-28 04:15:55,724 INFO [train.py:842] (3/4) Epoch 20, batch 5050, loss[loss=0.1878, simple_loss=0.2644, pruned_loss=0.0556, over 6800.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2722, pruned_loss=0.05032, over 1419743.61 frames.], batch size: 15, lr: 2.75e-04
2022-05-28 04:16:33,971 INFO [train.py:842] (3/4) Epoch 20, batch 5100, loss[loss=0.1751, simple_loss=0.2582, pruned_loss=0.04604, over 7353.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2714, pruned_loss=0.0494, over 1424719.80 frames.], batch size: 19, lr: 2.75e-04
2022-05-28 04:17:11,885 INFO [train.py:842] (3/4) Epoch 20, batch 5150, loss[loss=0.1412, simple_loss=0.2258, pruned_loss=0.0283, over 7273.00 frames.], tot_loss[loss=0.186, simple_loss=0.2724, pruned_loss=0.04985, over 1425470.98 frames.], batch size: 17, lr: 2.74e-04
2022-05-28 04:17:50,065 INFO [train.py:842] (3/4) Epoch 20, batch 5200, loss[loss=0.176, simple_loss=0.274, pruned_loss=0.03905, over 7229.00 frames.], tot_loss[loss=0.186, simple_loss=0.2728, pruned_loss=0.04961, over 1427489.94 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:18:27,919 INFO [train.py:842] (3/4) Epoch 20, batch 5250, loss[loss=0.2153, simple_loss=0.3019, pruned_loss=0.06436, over 7347.00 frames.], tot_loss[loss=0.187, simple_loss=0.2734, pruned_loss=0.05035, over 1421290.23 frames.], batch size: 22, lr: 2.74e-04
2022-05-28 04:19:06,165 INFO [train.py:842] (3/4) Epoch 20, batch 5300, loss[loss=0.2081, simple_loss=0.3024, pruned_loss=0.05695, over 7384.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2734, pruned_loss=0.05064, over 1418394.27 frames.], batch size: 23, lr: 2.74e-04
2022-05-28 04:19:43,984 INFO [train.py:842] (3/4) Epoch 20, batch 5350, loss[loss=0.2512, simple_loss=0.3247, pruned_loss=0.08888, over 7283.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2744, pruned_loss=0.05108, over 1420065.88 frames.], batch size: 24, lr: 2.74e-04
2022-05-28 04:20:22,326 INFO [train.py:842] (3/4) Epoch 20, batch 5400, loss[loss=0.173, simple_loss=0.274, pruned_loss=0.03597, over 7236.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2737, pruned_loss=0.05036, over 1419658.94 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:21:00,426 INFO [train.py:842] (3/4) Epoch 20, batch 5450, loss[loss=0.1399, simple_loss=0.2294, pruned_loss=0.02526, over 7429.00 frames.], tot_loss[loss=0.186, simple_loss=0.2727, pruned_loss=0.0497, over 1419915.59 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:21:38,512 INFO [train.py:842] (3/4) Epoch 20, batch 5500, loss[loss=0.1693, simple_loss=0.2565, pruned_loss=0.04103, over 7314.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2719, pruned_loss=0.04915, over 1418592.53 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:22:16,448 INFO [train.py:842] (3/4) Epoch 20, batch 5550, loss[loss=0.1751, simple_loss=0.2648, pruned_loss=0.04266, over 7420.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2725, pruned_loss=0.04928, over 1422200.69 frames.], batch size: 21, lr: 2.74e-04
2022-05-28 04:22:54,450 INFO [train.py:842] (3/4) Epoch 20, batch 5600, loss[loss=0.1821, simple_loss=0.2659, pruned_loss=0.04914, over 7287.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2724, pruned_loss=0.04944, over 1422554.27 frames.], batch size: 25, lr: 2.74e-04
2022-05-28 04:23:32,213 INFO [train.py:842] (3/4) Epoch 20, batch 5650, loss[loss=0.2482, simple_loss=0.3382, pruned_loss=0.07912, over 7206.00 frames.], tot_loss[loss=0.187, simple_loss=0.2736, pruned_loss=0.05016, over 1419692.23 frames.], batch size: 22, lr: 2.74e-04
2022-05-28 04:24:10,415 INFO [train.py:842] (3/4) Epoch 20, batch 5700, loss[loss=0.1234, simple_loss=0.2106, pruned_loss=0.01815, over 6803.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2732, pruned_loss=0.04967, over 1420029.03 frames.], batch size: 15, lr: 2.74e-04
2022-05-28 04:24:48,366 INFO [train.py:842] (3/4) Epoch 20, batch 5750, loss[loss=0.1976, simple_loss=0.2887, pruned_loss=0.05323, over 7198.00 frames.], tot_loss[loss=0.1862, simple_loss=0.273, pruned_loss=0.04969, over 1418392.69 frames.], batch size: 23, lr: 2.74e-04
2022-05-28 04:25:26,846 INFO [train.py:842] (3/4) Epoch 20, batch 5800, loss[loss=0.1753, simple_loss=0.2732, pruned_loss=0.03869, over 7146.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2709, pruned_loss=0.04864, over 1422002.02 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:26:04,824 INFO [train.py:842] (3/4) Epoch 20, batch 5850, loss[loss=0.2378, simple_loss=0.3179, pruned_loss=0.07884, over 6710.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2722, pruned_loss=0.04961, over 1425984.59 frames.], batch size: 31, lr: 2.74e-04
2022-05-28 04:26:42,989 INFO [train.py:842] (3/4) Epoch 20, batch 5900, loss[loss=0.1835, simple_loss=0.2633, pruned_loss=0.05182, over 7328.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2717, pruned_loss=0.04961, over 1420016.70 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:27:20,899 INFO [train.py:842] (3/4) Epoch 20, batch 5950, loss[loss=0.1811, simple_loss=0.2728, pruned_loss=0.04469, over 7326.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2723, pruned_loss=0.05029, over 1417920.32 frames.], batch size: 22, lr: 2.74e-04
2022-05-28 04:27:59,351 INFO [train.py:842] (3/4) Epoch 20, batch 6000, loss[loss=0.2474, simple_loss=0.3122, pruned_loss=0.09129, over 7343.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2714, pruned_loss=0.04993, over 1421458.83 frames.], batch size: 22, lr: 2.74e-04
2022-05-28 04:27:59,351 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 04:28:08,359 INFO [train.py:871] (3/4) Epoch 20, validation: loss=0.1665, simple_loss=0.2662, pruned_loss=0.03341, over 868885.00 frames.
2022-05-28 04:28:46,229 INFO [train.py:842] (3/4) Epoch 20, batch 6050, loss[loss=0.1932, simple_loss=0.284, pruned_loss=0.05119, over 7072.00 frames.], tot_loss[loss=0.185, simple_loss=0.2712, pruned_loss=0.04947, over 1420557.93 frames.], batch size: 18, lr: 2.74e-04
2022-05-28 04:29:24,663 INFO [train.py:842] (3/4) Epoch 20, batch 6100, loss[loss=0.1656, simple_loss=0.2587, pruned_loss=0.03622, over 7438.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2711, pruned_loss=0.04964, over 1421444.32 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:30:02,605 INFO [train.py:842] (3/4) Epoch 20, batch 6150, loss[loss=0.2027, simple_loss=0.2901, pruned_loss=0.05769, over 7062.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2711, pruned_loss=0.04977, over 1423485.06 frames.], batch size: 18, lr: 2.74e-04
2022-05-28 04:30:41,022 INFO [train.py:842] (3/4) Epoch 20, batch 6200, loss[loss=0.1736, simple_loss=0.2593, pruned_loss=0.04399, over 7434.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2717, pruned_loss=0.05055, over 1423768.08 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:31:18,809 INFO [train.py:842] (3/4) Epoch 20, batch 6250, loss[loss=0.1967, simple_loss=0.2748, pruned_loss=0.05924, over 7360.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2718, pruned_loss=0.05043, over 1421793.60 frames.], batch size: 19, lr: 2.74e-04
2022-05-28 04:31:56,961 INFO [train.py:842] (3/4) Epoch 20, batch 6300, loss[loss=0.2142, simple_loss=0.2995, pruned_loss=0.06446, over 7288.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2726, pruned_loss=0.0504, over 1421367.86 frames.], batch size: 25, lr: 2.74e-04
2022-05-28 04:32:34,975 INFO [train.py:842] (3/4) Epoch 20, batch 6350, loss[loss=0.1927, simple_loss=0.2792, pruned_loss=0.05305, over 7311.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2718, pruned_loss=0.04973, over 1424269.99 frames.], batch size: 21, lr: 2.74e-04
2022-05-28 04:33:13,294 INFO [train.py:842] (3/4) Epoch 20, batch 6400, loss[loss=0.1521, simple_loss=0.2465, pruned_loss=0.02882, over 7333.00 frames.], tot_loss[loss=0.1848, simple_loss=0.271, pruned_loss=0.04927, over 1423871.72 frames.], batch size: 20, lr: 2.74e-04
2022-05-28 04:33:50,982 INFO [train.py:842] (3/4) Epoch 20, batch 6450, loss[loss=0.1642, simple_loss=0.2548, pruned_loss=0.03683, over 7332.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2723, pruned_loss=0.04978, over 1421488.18 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:34:29,321 INFO [train.py:842] (3/4) Epoch 20, batch 6500, loss[loss=0.1713, simple_loss=0.2517, pruned_loss=0.0455, over 7062.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2718, pruned_loss=0.04946, over 1424938.06 frames.], batch size: 18, lr: 2.73e-04
2022-05-28 04:35:07,342 INFO [train.py:842] (3/4) Epoch 20, batch 6550, loss[loss=0.1839, simple_loss=0.2684, pruned_loss=0.0497, over 7162.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2718, pruned_loss=0.04956, over 1424025.22 frames.], batch size: 19, lr: 2.73e-04
2022-05-28 04:35:45,537 INFO [train.py:842] (3/4) Epoch 20, batch 6600, loss[loss=0.1696, simple_loss=0.2567, pruned_loss=0.04128, over 6747.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2722, pruned_loss=0.0498, over 1426341.80 frames.], batch size: 15, lr: 2.73e-04
2022-05-28 04:36:23,636 INFO [train.py:842] (3/4) Epoch 20, batch 6650, loss[loss=0.1989, simple_loss=0.2854, pruned_loss=0.05619, over 7235.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2711, pruned_loss=0.04897, over 1426102.99 frames.], batch size: 20, lr: 2.73e-04
2022-05-28 04:37:02,180 INFO [train.py:842] (3/4) Epoch 20, batch 6700, loss[loss=0.1522, simple_loss=0.2293, pruned_loss=0.03753, over 7129.00 frames.], tot_loss[loss=0.185, simple_loss=0.2711, pruned_loss=0.04947, over 1425037.16 frames.], batch size: 17, lr: 2.73e-04
2022-05-28 04:37:40,092 INFO [train.py:842] (3/4) Epoch 20, batch 6750, loss[loss=0.2504, simple_loss=0.3054, pruned_loss=0.09764, over 7168.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2716, pruned_loss=0.04974, over 1429498.35 frames.], batch size: 18, lr: 2.73e-04
2022-05-28 04:38:18,251 INFO [train.py:842] (3/4) Epoch 20, batch 6800, loss[loss=0.1627, simple_loss=0.2513, pruned_loss=0.03708, over 7282.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2712, pruned_loss=0.04915, over 1428113.60 frames.], batch size: 17, lr: 2.73e-04
2022-05-28 04:38:56,162 INFO [train.py:842] (3/4) Epoch 20, batch 6850, loss[loss=0.135, simple_loss=0.2174, pruned_loss=0.02632, over 7001.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2708, pruned_loss=0.04875, over 1428238.79 frames.], batch size: 16, lr: 2.73e-04
2022-05-28 04:39:34,138 INFO [train.py:842] (3/4) Epoch 20, batch 6900, loss[loss=0.1891, simple_loss=0.282, pruned_loss=0.04808, over 7318.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2712, pruned_loss=0.04905, over 1425156.31 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:40:11,940 INFO [train.py:842] (3/4) Epoch 20, batch 6950, loss[loss=0.2047, simple_loss=0.2874, pruned_loss=0.06099, over 7204.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2719, pruned_loss=0.04956, over 1426109.64 frames.], batch size: 22, lr: 2.73e-04
2022-05-28 04:40:50,229 INFO [train.py:842] (3/4) Epoch 20, batch 7000, loss[loss=0.1768, simple_loss=0.2577, pruned_loss=0.04798, over 7228.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2727, pruned_loss=0.05021, over 1427519.72 frames.], batch size: 16, lr: 2.73e-04
2022-05-28 04:41:28,306 INFO [train.py:842] (3/4) Epoch 20, batch 7050, loss[loss=0.1974, simple_loss=0.2812, pruned_loss=0.05683, over 7097.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2719, pruned_loss=0.04985, over 1430769.51 frames.], batch size: 28, lr: 2.73e-04
2022-05-28 04:42:06,612 INFO [train.py:842] (3/4) Epoch 20, batch 7100, loss[loss=0.1952, simple_loss=0.2859, pruned_loss=0.05229, over 7155.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2728, pruned_loss=0.05019, over 1431705.60 frames.], batch size: 19, lr: 2.73e-04
2022-05-28 04:42:44,641 INFO [train.py:842] (3/4) Epoch 20, batch 7150, loss[loss=0.1771, simple_loss=0.2744, pruned_loss=0.03989, over 7233.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2727, pruned_loss=0.05019, over 1432875.85 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:43:22,722 INFO [train.py:842] (3/4) Epoch 20, batch 7200, loss[loss=0.1847, simple_loss=0.2751, pruned_loss=0.04716, over 7110.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2721, pruned_loss=0.04949, over 1426050.24 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:44:00,678 INFO [train.py:842] (3/4) Epoch 20, batch 7250, loss[loss=0.1775, simple_loss=0.2691, pruned_loss=0.04293, over 7335.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2715, pruned_loss=0.04946, over 1424589.54 frames.], batch size: 22, lr: 2.73e-04
2022-05-28 04:44:38,834 INFO [train.py:842] (3/4) Epoch 20, batch 7300, loss[loss=0.2053, simple_loss=0.2841, pruned_loss=0.06319, over 4685.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2723, pruned_loss=0.04975, over 1420887.75 frames.], batch size: 52, lr: 2.73e-04
2022-05-28 04:45:16,996 INFO [train.py:842] (3/4) Epoch 20, batch 7350, loss[loss=0.1612, simple_loss=0.2374, pruned_loss=0.04255, over 7157.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2718, pruned_loss=0.04977, over 1423896.80 frames.], batch size: 18, lr: 2.73e-04
2022-05-28 04:45:55,205 INFO [train.py:842] (3/4) Epoch 20, batch 7400, loss[loss=0.1597, simple_loss=0.2412, pruned_loss=0.03907, over 7131.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2712, pruned_loss=0.04959, over 1426096.66 frames.], batch size: 17, lr: 2.73e-04
2022-05-28 04:46:32,950 INFO [train.py:842] (3/4) Epoch 20, batch 7450, loss[loss=0.1814, simple_loss=0.2679, pruned_loss=0.04746, over 7323.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2725, pruned_loss=0.04999, over 1426571.41 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:47:11,139 INFO [train.py:842] (3/4) Epoch 20, batch 7500, loss[loss=0.2019, simple_loss=0.3057, pruned_loss=0.04906, over 7226.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2735, pruned_loss=0.05029, over 1429265.95 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:47:48,922 INFO [train.py:842] (3/4) Epoch 20, batch 7550, loss[loss=0.1629, simple_loss=0.2476, pruned_loss=0.03905, over 7283.00 frames.], tot_loss[loss=0.187, simple_loss=0.2732, pruned_loss=0.05044, over 1424223.31 frames.], batch size: 18, lr: 2.73e-04
2022-05-28 04:48:27,070 INFO [train.py:842] (3/4) Epoch 20, batch 7600, loss[loss=0.1735, simple_loss=0.2609, pruned_loss=0.043, over 7067.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2741, pruned_loss=0.0505, over 1423304.16 frames.], batch size: 18, lr: 2.73e-04
2022-05-28 04:49:05,143 INFO [train.py:842] (3/4) Epoch 20, batch 7650, loss[loss=0.2037, simple_loss=0.2947, pruned_loss=0.05638, over 7215.00 frames.], tot_loss[loss=0.1862, simple_loss=0.273, pruned_loss=0.0497, over 1423994.10 frames.], batch size: 21, lr: 2.73e-04
2022-05-28 04:49:43,401 INFO [train.py:842] (3/4) Epoch 20, batch 7700, loss[loss=0.155, simple_loss=0.2335, pruned_loss=0.03823, over 7258.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2721, pruned_loss=0.04961, over 1426281.07 frames.], batch size: 19, lr: 2.73e-04
2022-05-28 04:50:21,415 INFO [train.py:842] (3/4) Epoch 20, batch 7750, loss[loss=0.1826, simple_loss=0.2783, pruned_loss=0.04341, over 7145.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2723, pruned_loss=0.04995, over 1426517.54 frames.], batch size: 20, lr: 2.73e-04
2022-05-28 04:50:59,587 INFO [train.py:842] (3/4) Epoch 20, batch 7800, loss[loss=0.1612, simple_loss=0.2508, pruned_loss=0.03586, over 7163.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2714, pruned_loss=0.04906, over 1426425.55 frames.], batch size: 18, lr: 2.72e-04
2022-05-28 04:51:37,540 INFO [train.py:842] (3/4) Epoch 20, batch 7850, loss[loss=0.1497, simple_loss=0.2484, pruned_loss=0.02548, over 7154.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2711, pruned_loss=0.04855, over 1425683.49 frames.], batch size: 20, lr: 2.72e-04
2022-05-28 04:52:15,878 INFO [train.py:842] (3/4) Epoch 20, batch 7900, loss[loss=0.2085, simple_loss=0.2969, pruned_loss=0.06003, over 7118.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2704, pruned_loss=0.04844, over 1427390.72 frames.], batch size: 21, lr: 2.72e-04
2022-05-28 04:52:53,900 INFO [train.py:842] (3/4) Epoch 20, batch 7950, loss[loss=0.1962, simple_loss=0.2907, pruned_loss=0.05082, over 7309.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2704, pruned_loss=0.04841, over 1429130.83 frames.], batch size: 25, lr: 2.72e-04
2022-05-28 04:53:32,242 INFO [train.py:842] (3/4) Epoch 20, batch 8000, loss[loss=0.1626, simple_loss=0.2378, pruned_loss=0.04374, over 7348.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2703, pruned_loss=0.04807, over 1430832.51 frames.], batch size: 19, lr: 2.72e-04
2022-05-28 04:54:10,495 INFO [train.py:842] (3/4) Epoch 20, batch 8050, loss[loss=0.1652, simple_loss=0.2563, pruned_loss=0.0371, over 7216.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2695, pruned_loss=0.048, over 1428432.37 frames.], batch size: 21, lr: 2.72e-04
2022-05-28 04:54:48,892 INFO [train.py:842] (3/4) Epoch 20, batch 8100, loss[loss=0.2066, simple_loss=0.2927, pruned_loss=0.0603, over 7428.00 frames.], tot_loss[loss=0.1826, simple_loss=0.269, pruned_loss=0.04813, over 1431531.50 frames.], batch size: 20, lr: 2.72e-04
2022-05-28 04:55:36,036 INFO [train.py:842] (3/4) Epoch 20, batch 8150, loss[loss=0.1572, simple_loss=0.2421, pruned_loss=0.03614, over 7150.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2691, pruned_loss=0.04856, over 1425616.12 frames.], batch size: 17, lr: 2.72e-04
2022-05-28 04:56:14,322 INFO [train.py:842] (3/4) Epoch 20, batch 8200, loss[loss=0.1861, simple_loss=0.2719, pruned_loss=0.05014, over 7414.00 frames.], tot_loss[loss=0.183, simple_loss=0.2694, pruned_loss=0.04831, over 1426726.61 frames.], batch size: 18, lr: 2.72e-04
2022-05-28 04:56:52,104 INFO [train.py:842] (3/4) Epoch 20, batch 8250, loss[loss=0.1711, simple_loss=0.2597, pruned_loss=0.04125, over 7280.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2714, pruned_loss=0.04938, over 1425918.32 frames.], batch size: 18, lr: 2.72e-04
2022-05-28 04:57:30,463 INFO [train.py:842] (3/4) Epoch 20, batch 8300, loss[loss=0.2091, simple_loss=0.2928, pruned_loss=0.06271, over 7323.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2709, pruned_loss=0.04934, over 1426291.20 frames.], batch size: 21, lr: 2.72e-04
2022-05-28 04:58:17,707 INFO [train.py:842] (3/4) Epoch 20, batch 8350, loss[loss=0.2008, simple_loss=0.2863, pruned_loss=0.05764, over 7197.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2719, pruned_loss=0.04923, over 1421658.63 frames.], batch size: 23, lr: 2.72e-04
2022-05-28 04:58:55,805 INFO [train.py:842] (3/4) Epoch 20, batch 8400, loss[loss=0.1727, simple_loss=0.2559, pruned_loss=0.04475, over 7320.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2721, pruned_loss=0.04931, over 1421121.40 frames.], batch size: 20, lr: 2.72e-04
2022-05-28 04:59:33,819 INFO [train.py:842] (3/4) Epoch 20, batch 8450, loss[loss=0.1404, simple_loss=0.2145, pruned_loss=0.03315, over 7403.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2715, pruned_loss=0.04895, over 1423437.92 frames.], batch size: 18, lr: 2.72e-04
2022-05-28 05:00:21,176 INFO [train.py:842] (3/4) Epoch 20, batch 8500, loss[loss=0.2002, simple_loss=0.2885, pruned_loss=0.05592, over 7311.00 frames.], tot_loss[loss=0.1858, simple_loss=0.272, pruned_loss=0.04982, over 1417183.95 frames.], batch size: 24, lr: 2.72e-04
2022-05-28 05:00:59,189 INFO [train.py:842] (3/4) Epoch 20, batch 8550, loss[loss=0.1862, simple_loss=0.2762, pruned_loss=0.04812, over 7251.00 frames.], tot_loss[loss=0.1861, simple_loss=0.272, pruned_loss=0.05012, over 1421334.52 frames.], batch size: 19, lr: 2.72e-04
2022-05-28 05:01:37,335 INFO [train.py:842] (3/4) Epoch 20, batch 8600, loss[loss=0.1854, simple_loss=0.2767, pruned_loss=0.04708, over 7313.00 frames.], tot_loss[loss=0.186, simple_loss=0.2716, pruned_loss=0.05019, over 1423073.09 frames.], batch size: 21, lr: 2.72e-04
2022-05-28 05:02:15,321 INFO [train.py:842] (3/4) Epoch 20, batch 8650, loss[loss=0.1681, simple_loss=0.2589, pruned_loss=0.03868, over 7229.00 frames.], tot_loss[loss=0.1846, simple_loss=0.27, pruned_loss=0.04956, over 1421296.88 frames.], batch size: 20, lr: 2.72e-04
2022-05-28 05:02:53,357 INFO [train.py:842] (3/4) Epoch 20, batch 8700, loss[loss=0.1777, simple_loss=0.2617, pruned_loss=0.04678, over 7282.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2693, pruned_loss=0.04876, over 1413736.66 frames.], batch size: 18, lr: 2.72e-04
2022-05-28 05:03:31,390 INFO [train.py:842] (3/4) Epoch 20, batch 8750, loss[loss=0.2006, simple_loss=0.2859, pruned_loss=0.0576, over 7202.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2693, pruned_loss=0.0487, over 1415562.07 frames.], batch size: 23, lr: 2.72e-04
2022-05-28 05:04:09,705 INFO [train.py:842] (3/4) Epoch 20, batch 8800, loss[loss=0.1822, simple_loss=0.2743, pruned_loss=0.04509, over 7166.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2686, pruned_loss=0.04835, over 1416381.90 frames.], batch size: 19, lr: 2.72e-04
2022-05-28 05:04:47,748 INFO [train.py:842] (3/4) Epoch 20, batch 8850, loss[loss=0.1553, simple_loss=0.2399, pruned_loss=0.03537, over 7431.00 frames.], tot_loss[loss=0.182, simple_loss=0.2677, pruned_loss=0.04822, over 1409039.18 frames.], batch size: 17, lr: 2.72e-04
2022-05-28 05:05:25,745 INFO [train.py:842] (3/4) Epoch 20, batch 8900, loss[loss=0.196, simple_loss=0.2733, pruned_loss=0.05938, over 7255.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2684, pruned_loss=0.04868, over 1399188.36 frames.], batch size: 19, lr: 2.72e-04
2022-05-28 05:06:03,649 INFO [train.py:842] (3/4) Epoch 20, batch 8950, loss[loss=0.2311, simple_loss=0.3225, pruned_loss=0.0698, over 7217.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2676, pruned_loss=0.04845, over 1390269.62 frames.], batch size: 21, lr: 2.72e-04
2022-05-28 05:06:42,112 INFO [train.py:842] (3/4) Epoch 20, batch 9000, loss[loss=0.3061, simple_loss=0.3756, pruned_loss=0.1183, over 6514.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2663, pruned_loss=0.04871, over 1368587.04 frames.], batch size: 38, lr: 2.72e-04
2022-05-28 05:06:42,113 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 05:06:51,176 INFO [train.py:871] (3/4) Epoch 20, validation: loss=0.164, simple_loss=0.2628, pruned_loss=0.03265, over 868885.00 frames.
2022-05-28 05:07:28,680 INFO [train.py:842] (3/4) Epoch 20, batch 9050, loss[loss=0.2642, simple_loss=0.332, pruned_loss=0.09819, over 5066.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2688, pruned_loss=0.05099, over 1334121.47 frames.], batch size: 53, lr: 2.72e-04
2022-05-28 05:08:05,301 INFO [train.py:842] (3/4) Epoch 20, batch 9100, loss[loss=0.1987, simple_loss=0.2974, pruned_loss=0.04997, over 6428.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2731, pruned_loss=0.05303, over 1293375.01 frames.], batch size: 37, lr: 2.72e-04
2022-05-28 05:08:41,905 INFO [train.py:842] (3/4) Epoch 20, batch 9150, loss[loss=0.2198, simple_loss=0.3072, pruned_loss=0.06622, over 5431.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2782, pruned_loss=0.05628, over 1242598.02 frames.], batch size: 52, lr: 2.71e-04
2022-05-28 05:09:33,861 INFO [train.py:842] (3/4) Epoch 21, batch 0, loss[loss=0.1632, simple_loss=0.2514, pruned_loss=0.03744, over 7010.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2514, pruned_loss=0.03744, over 7010.00 frames.], batch size: 16, lr: 2.65e-04
2022-05-28 05:10:12,040 INFO [train.py:842] (3/4) Epoch 21, batch 50, loss[loss=0.1684, simple_loss=0.261, pruned_loss=0.03795, over 6287.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2762, pruned_loss=0.05217, over 322742.14 frames.], batch size: 37, lr: 2.65e-04
2022-05-28 05:10:50,328 INFO [train.py:842] (3/4) Epoch 21, batch 100, loss[loss=0.1892, simple_loss=0.2607, pruned_loss=0.05888, over 6805.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2758, pruned_loss=0.05175, over 566446.24 frames.], batch size: 15, lr: 2.65e-04
2022-05-28 05:11:28,271 INFO [train.py:842] (3/4) Epoch 21, batch 150, loss[loss=0.1603, simple_loss=0.2436, pruned_loss=0.03846, over 7168.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2732, pruned_loss=0.05018, over 755400.32 frames.], batch size: 18, lr: 2.65e-04
2022-05-28 05:12:09,313 INFO [train.py:842] (3/4) Epoch 21, batch 200, loss[loss=0.1966, simple_loss=0.2949, pruned_loss=0.04917, over 6720.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2735, pruned_loss=0.04979, over 900734.81 frames.], batch size: 31, lr: 2.65e-04
2022-05-28 05:12:47,242 INFO [train.py:842] (3/4) Epoch 21, batch 250, loss[loss=0.1609, simple_loss=0.2496, pruned_loss=0.03615, over 7163.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2731, pruned_loss=0.04986, over 1012137.45 frames.], batch size: 19, lr: 2.65e-04
2022-05-28 05:13:25,539 INFO [train.py:842] (3/4) Epoch 21, batch 300, loss[loss=0.1835, simple_loss=0.2653, pruned_loss=0.05088, over 7280.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2722, pruned_loss=0.04975, over 1101178.74 frames.], batch size: 18, lr: 2.65e-04
2022-05-28 05:14:03,309 INFO [train.py:842] (3/4) Epoch 21, batch 350, loss[loss=0.1662, simple_loss=0.2492, pruned_loss=0.04163, over 7261.00 frames.], tot_loss[loss=0.1857, simple_loss=0.272, pruned_loss=0.04968, over 1168971.27 frames.], batch size: 19, lr: 2.65e-04
2022-05-28 05:14:41,729 INFO [train.py:842] (3/4) Epoch 21, batch 400, loss[loss=0.2031, simple_loss=0.2789, pruned_loss=0.06364, over 7068.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2723, pruned_loss=0.05013, over 1228270.61 frames.], batch size: 18, lr: 2.65e-04
2022-05-28 05:15:19,620 INFO [train.py:842] (3/4) Epoch 21, batch 450, loss[loss=0.1502, simple_loss=0.2396, pruned_loss=0.03044, over 7064.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2721, pruned_loss=0.05006, over 1270889.36 frames.], batch size: 18, lr: 2.65e-04
2022-05-28 05:15:57,951 INFO [train.py:842] (3/4) Epoch 21, batch 500, loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03544, over 6988.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2715, pruned_loss=0.04954, over 1309834.51 frames.], batch size: 28, lr: 2.65e-04
2022-05-28 05:16:36,042 INFO [train.py:842] (3/4) Epoch 21, batch 550, loss[loss=0.2047, simple_loss=0.2717, pruned_loss=0.0689, over 6763.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2693, pruned_loss=0.04803, over 1336416.09 frames.], batch size: 15, lr: 2.65e-04
2022-05-28 05:17:14,244 INFO [train.py:842] (3/4) Epoch 21, batch 600, loss[loss=0.201, simple_loss=0.2879, pruned_loss=0.05702, over 7214.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2707, pruned_loss=0.04892, over 1354454.83 frames.], batch size: 22, lr: 2.65e-04
2022-05-28 05:17:52,434 INFO [train.py:842] (3/4) Epoch 21, batch 650, loss[loss=0.2263, simple_loss=0.2855, pruned_loss=0.08361, over 7140.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2695, pruned_loss=0.04881, over 1369068.04 frames.], batch size: 17, lr: 2.65e-04
2022-05-28 05:18:30,496 INFO [train.py:842] (3/4) Epoch 21, batch 700, loss[loss=0.1724, simple_loss=0.2537, pruned_loss=0.04555, over 7237.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2691, pruned_loss=0.04837, over 1378448.82 frames.], batch size: 20, lr: 2.65e-04
2022-05-28 05:19:08,402 INFO [train.py:842] (3/4) Epoch 21, batch 750, loss[loss=0.178, simple_loss=0.2618, pruned_loss=0.04711, over 7405.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2708, pruned_loss=0.04919, over 1384570.75 frames.], batch size: 18, lr: 2.65e-04
2022-05-28 05:19:46,510 INFO [train.py:842] (3/4) Epoch 21, batch 800, loss[loss=0.2316, simple_loss=0.2972, pruned_loss=0.08297, over 7227.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2711, pruned_loss=0.04953, over 1383643.72 frames.], batch size: 20, lr: 2.65e-04
2022-05-28 05:20:24,491 INFO [train.py:842] (3/4) Epoch 21, batch 850, loss[loss=0.2084, simple_loss=0.2931, pruned_loss=0.0619, over 7259.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2701, pruned_loss=0.04925, over 1389423.08 frames.], batch size: 25, lr: 2.65e-04
2022-05-28 05:21:02,930 INFO [train.py:842] (3/4) Epoch 21, batch 900, loss[loss=0.1527, simple_loss=0.2465, pruned_loss=0.0295, over 7230.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2686, pruned_loss=0.04807, over 1398892.72 frames.], batch size: 20, lr: 2.65e-04
2022-05-28 05:21:40,830 INFO [train.py:842] (3/4) Epoch 21, batch 950, loss[loss=0.2092, simple_loss=0.3007, pruned_loss=0.05883, over 7342.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2695, pruned_loss=0.04866, over 1405141.89 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:22:18,912 INFO [train.py:842] (3/4) Epoch 21, batch 1000, loss[loss=0.2096, simple_loss=0.3029, pruned_loss=0.05812, over 7218.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2708, pruned_loss=0.04912, over 1404947.26 frames.], batch size: 23, lr: 2.64e-04
2022-05-28 05:22:56,519 INFO [train.py:842] (3/4) Epoch 21, batch 1050, loss[loss=0.2112, simple_loss=0.2945, pruned_loss=0.06391, over 7413.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2727, pruned_loss=0.04994, over 1405647.47 frames.], batch size: 21, lr: 2.64e-04
2022-05-28 05:23:34,913 INFO [train.py:842] (3/4) Epoch 21, batch 1100, loss[loss=0.16, simple_loss=0.2374, pruned_loss=0.04126, over 7200.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2705, pruned_loss=0.04897, over 1407570.12 frames.], batch size: 16, lr: 2.64e-04
2022-05-28 05:24:12,847 INFO [train.py:842] (3/4) Epoch 21, batch 1150, loss[loss=0.2051, simple_loss=0.2948, pruned_loss=0.0577, over 7283.00 frames.], tot_loss[loss=0.184, simple_loss=0.2704, pruned_loss=0.04881, over 1412707.74 frames.], batch size: 24, lr: 2.64e-04
2022-05-28 05:24:50,889 INFO [train.py:842] (3/4) Epoch 21, batch 1200, loss[loss=0.1636, simple_loss=0.252, pruned_loss=0.0376, over 7286.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2713, pruned_loss=0.04892, over 1415805.18 frames.], batch size: 18, lr: 2.64e-04
2022-05-28 05:25:28,914 INFO [train.py:842] (3/4) Epoch 21, batch 1250, loss[loss=0.2061, simple_loss=0.2907, pruned_loss=0.06079, over 7301.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2712, pruned_loss=0.04919, over 1418066.48 frames.], batch size: 24, lr: 2.64e-04
2022-05-28 05:26:07,277 INFO [train.py:842] (3/4) Epoch 21, batch 1300, loss[loss=0.1821, simple_loss=0.2691, pruned_loss=0.04761, over 7461.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2698, pruned_loss=0.04831, over 1417788.13 frames.], batch size: 19, lr: 2.64e-04
2022-05-28 05:26:45,554 INFO [train.py:842] (3/4) Epoch 21, batch 1350, loss[loss=0.1788, simple_loss=0.2717, pruned_loss=0.04288, over 7324.00 frames.], tot_loss[loss=0.183, simple_loss=0.2696, pruned_loss=0.04816, over 1424402.67 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:27:23,888 INFO [train.py:842] (3/4) Epoch 21, batch 1400, loss[loss=0.2139, simple_loss=0.3108, pruned_loss=0.05853, over 7370.00 frames.], tot_loss[loss=0.1835, simple_loss=0.27, pruned_loss=0.04854, over 1427537.05 frames.], batch size: 23, lr: 2.64e-04
2022-05-28 05:28:01,810 INFO [train.py:842] (3/4) Epoch 21, batch 1450, loss[loss=0.2636, simple_loss=0.3308, pruned_loss=0.0982, over 4668.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2707, pruned_loss=0.04928, over 1421411.74 frames.], batch size: 52, lr: 2.64e-04
2022-05-28 05:28:39,864 INFO [train.py:842] (3/4) Epoch 21, batch 1500, loss[loss=0.2112, simple_loss=0.2986, pruned_loss=0.06197, over 7346.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2707, pruned_loss=0.04871, over 1418728.62 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:29:17,835 INFO [train.py:842] (3/4) Epoch 21, batch 1550, loss[loss=0.2076, simple_loss=0.2921, pruned_loss=0.06154, over 6773.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2708, pruned_loss=0.0485, over 1420727.57 frames.], batch size: 31, lr: 2.64e-04
2022-05-28 05:29:56,070 INFO [train.py:842] (3/4) Epoch 21, batch 1600, loss[loss=0.1984, simple_loss=0.2839, pruned_loss=0.05646, over 7339.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2715, pruned_loss=0.04875, over 1421404.02 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:30:33,974 INFO [train.py:842] (3/4) Epoch 21, batch 1650, loss[loss=0.1828, simple_loss=0.2655, pruned_loss=0.05005, over 7328.00 frames.], tot_loss[loss=0.184, simple_loss=0.2709, pruned_loss=0.04852, over 1422571.90 frames.], batch size: 20, lr: 2.64e-04
2022-05-28 05:31:12,225 INFO [train.py:842] (3/4) Epoch 21, batch 1700, loss[loss=0.3369, simple_loss=0.3776, pruned_loss=0.1481, over 7338.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2711, pruned_loss=0.04876, over 1422244.60 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:31:50,201 INFO [train.py:842] (3/4) Epoch 21, batch 1750, loss[loss=0.1911, simple_loss=0.2659, pruned_loss=0.05813, over 7428.00 frames.], tot_loss[loss=0.185, simple_loss=0.2717, pruned_loss=0.04919, over 1423261.84 frames.], batch size: 18, lr: 2.64e-04
2022-05-28 05:32:28,369 INFO [train.py:842] (3/4) Epoch 21, batch 1800, loss[loss=0.1824, simple_loss=0.2674, pruned_loss=0.04865, over 7176.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2713, pruned_loss=0.04951, over 1424686.07 frames.], batch size: 23, lr: 2.64e-04
2022-05-28 05:33:06,420 INFO [train.py:842] (3/4) Epoch 21, batch 1850, loss[loss=0.1744, simple_loss=0.26, pruned_loss=0.04442, over 7412.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2717, pruned_loss=0.04998, over 1423322.79 frames.], batch size: 18, lr: 2.64e-04
2022-05-28 05:33:44,681 INFO [train.py:842] (3/4) Epoch 21, batch 1900, loss[loss=0.1945, simple_loss=0.2916, pruned_loss=0.04874, over 7152.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2724, pruned_loss=0.05056, over 1424284.13 frames.], batch size: 19, lr: 2.64e-04
2022-05-28 05:34:22,661 INFO [train.py:842] (3/4) Epoch 21, batch 1950, loss[loss=0.154, simple_loss=0.2426, pruned_loss=0.03267, over 7260.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2716, pruned_loss=0.04986, over 1427689.03 frames.], batch size: 19, lr: 2.64e-04
2022-05-28 05:35:00,912 INFO [train.py:842] (3/4) Epoch 21, batch 2000, loss[loss=0.1632, simple_loss=0.2503, pruned_loss=0.03811, over 6809.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2713, pruned_loss=0.04982, over 1424361.12 frames.], batch size: 31, lr: 2.64e-04
2022-05-28 05:35:38,837 INFO [train.py:842] (3/4) Epoch 21, batch 2050, loss[loss=0.1652, simple_loss=0.2594, pruned_loss=0.03552, over 7218.00 frames.], tot_loss[loss=0.186, simple_loss=0.2716, pruned_loss=0.05024, over 1423867.55 frames.], batch size: 21, lr: 2.64e-04
2022-05-28 05:36:17,024 INFO [train.py:842] (3/4) Epoch 21, batch 2100, loss[loss=0.216, simple_loss=0.2891, pruned_loss=0.07146, over 7074.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2718, pruned_loss=0.05032, over 1423091.67 frames.], batch size: 18, lr: 2.64e-04
2022-05-28 05:36:54,839 INFO [train.py:842] (3/4) Epoch 21, batch 2150, loss[loss=0.1685, simple_loss=0.2456, pruned_loss=0.04573, over 6795.00 frames.], tot_loss[loss=0.1849, simple_loss=0.271, pruned_loss=0.04943, over 1421531.95 frames.], batch size: 15, lr: 2.64e-04
2022-05-28 05:37:33,251 INFO [train.py:842] (3/4) Epoch 21, batch 2200, loss[loss=0.2146, simple_loss=0.3015, pruned_loss=0.06388, over 7202.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2706, pruned_loss=0.04956, over 1423325.60 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:38:11,128 INFO [train.py:842] (3/4) Epoch 21, batch 2250, loss[loss=0.2151, simple_loss=0.3076, pruned_loss=0.06129, over 7192.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2715, pruned_loss=0.04967, over 1423879.94 frames.], batch size: 22, lr: 2.64e-04
2022-05-28 05:38:49,552 INFO [train.py:842] (3/4) Epoch 21, batch 2300, loss[loss=0.2303, simple_loss=0.3044, pruned_loss=0.07805, over 5127.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2702, pruned_loss=0.04907, over 1421271.72 frames.], batch size: 53, lr: 2.64e-04
2022-05-28 05:39:27,159 INFO [train.py:842] (3/4) Epoch 21, batch 2350, loss[loss=0.2128, simple_loss=0.2989, pruned_loss=0.06334, over 7315.00 frames.], tot_loss[loss=0.1855, simple_loss=0.272, pruned_loss=0.04954, over 1416035.31 frames.], batch size: 24, lr: 2.63e-04
2022-05-28 05:40:05,579 INFO [train.py:842] (3/4) Epoch 21, batch 2400, loss[loss=0.173, simple_loss=0.2611, pruned_loss=0.04243, over 7215.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2703, pruned_loss=0.0485, over 1420057.89 frames.], batch size: 23, lr: 2.63e-04
2022-05-28 05:40:43,637 INFO [train.py:842] (3/4) Epoch 21, batch 2450, loss[loss=0.1778, simple_loss=0.2683, pruned_loss=0.04362, over 7143.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2701, pruned_loss=0.04842, over 1421605.95 frames.], batch size: 19, lr: 2.63e-04
2022-05-28 05:41:21,979 INFO [train.py:842] (3/4) Epoch 21, batch 2500, loss[loss=0.1734, simple_loss=0.264, pruned_loss=0.04142, over 7412.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2703, pruned_loss=0.04879, over 1423644.92 frames.], batch size: 21, lr: 2.63e-04
2022-05-28 05:41:59,717 INFO [train.py:842] (3/4) Epoch 21, batch 2550, loss[loss=0.2048, simple_loss=0.2791, pruned_loss=0.06528, over 5107.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2711, pruned_loss=0.049, over 1421416.32 frames.], batch size: 52, lr: 2.63e-04
2022-05-28 05:42:37,956 INFO [train.py:842] (3/4) Epoch 21, batch 2600, loss[loss=0.1512, simple_loss=0.2441, pruned_loss=0.02918, over 7443.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2719, pruned_loss=0.04976, over 1422271.34 frames.], batch size: 19, lr: 2.63e-04
2022-05-28 05:43:15,793 INFO [train.py:842] (3/4) Epoch 21, batch 2650, loss[loss=0.1851, simple_loss=0.2764, pruned_loss=0.04694, over 7327.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2733, pruned_loss=0.05081, over 1416899.68 frames.], batch size: 20, lr: 2.63e-04
2022-05-28 05:43:53,883 INFO [train.py:842] (3/4) Epoch 21, batch 2700, loss[loss=0.1648, simple_loss=0.2488, pruned_loss=0.04037, over 7415.00 frames.], tot_loss[loss=0.1871, simple_loss=0.273, pruned_loss=0.05062, over 1420400.21 frames.], batch size: 18, lr: 2.63e-04
2022-05-28 05:44:31,853 INFO [train.py:842] (3/4) Epoch 21, batch 2750, loss[loss=0.1836, simple_loss=0.2735, pruned_loss=0.04679, over 7154.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2726, pruned_loss=0.05022, over 1422102.59 frames.], batch size: 18, lr: 2.63e-04
2022-05-28 05:45:10,232 INFO [train.py:842] (3/4) Epoch 21, batch 2800, loss[loss=0.1855, simple_loss=0.2737, pruned_loss=0.04866, over 7393.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2724, pruned_loss=0.05043, over 1425304.39 frames.], batch size: 23, lr: 2.63e-04
2022-05-28 05:45:48,227 INFO [train.py:842] (3/4) Epoch 21, batch 2850, loss[loss=0.1733, simple_loss=0.2755, pruned_loss=0.03551, over 7201.00 frames.], tot_loss[loss=0.187, simple_loss=0.2726, pruned_loss=0.05073, over 1419980.58 frames.], batch size: 23, lr: 2.63e-04
2022-05-28 05:46:26,350 INFO [train.py:842] (3/4) Epoch 21, batch 2900, loss[loss=0.2169, simple_loss=0.2997, pruned_loss=0.06708, over 6978.00 frames.], tot_loss[loss=0.1862, simple_loss=0.272, pruned_loss=0.05018, over 1414836.51 frames.], batch size: 28, lr: 2.63e-04
2022-05-28 05:47:04,351 INFO [train.py:842] (3/4) Epoch 21, batch 2950, loss[loss=0.1979, simple_loss=0.2792, pruned_loss=0.05829, over 7362.00 frames.], tot_loss[loss=0.187, simple_loss=0.2728, pruned_loss=0.05058, over 1414962.32 frames.], batch size: 19, lr: 2.63e-04
2022-05-28 05:47:42,624 INFO [train.py:842] (3/4) Epoch 21, batch 3000, loss[loss=0.1834, simple_loss=0.2808, pruned_loss=0.04306, over 6770.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2735, pruned_loss=0.05103, over 1414532.23 frames.], batch size: 31, lr: 2.63e-04
2022-05-28 05:47:42,625 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 05:47:51,726 INFO [train.py:871] (3/4) Epoch 21, validation: loss=0.1652, simple_loss=0.2649, pruned_loss=0.0328, over 868885.00 frames.
2022-05-28 05:48:29,681 INFO [train.py:842] (3/4) Epoch 21, batch 3050, loss[loss=0.149, simple_loss=0.2351, pruned_loss=0.03144, over 7289.00 frames.], tot_loss[loss=0.188, simple_loss=0.2738, pruned_loss=0.05112, over 1415272.48 frames.], batch size: 18, lr: 2.63e-04
2022-05-28 05:49:07,879 INFO [train.py:842] (3/4) Epoch 21, batch 3100, loss[loss=0.2062, simple_loss=0.2984, pruned_loss=0.05705, over 7391.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2735, pruned_loss=0.05089, over 1413834.01 frames.], batch size: 23, lr: 2.63e-04
2022-05-28 05:49:46,063 INFO [train.py:842] (3/4) Epoch 21, batch 3150, loss[loss=0.1727, simple_loss=0.2728, pruned_loss=0.03631, over 7303.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2723, pruned_loss=0.05026, over 1418364.52 frames.], batch size: 24, lr: 2.63e-04
2022-05-28 05:50:24,126 INFO [train.py:842] (3/4) Epoch 21, batch 3200, loss[loss=0.2157, simple_loss=0.3065, pruned_loss=0.0624, over 7320.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2727, pruned_loss=0.04977, over 1422519.59 frames.], batch size: 21, lr: 2.63e-04
2022-05-28 05:51:01,978 INFO [train.py:842] (3/4) Epoch 21, batch 3250, loss[loss=0.1439, simple_loss=0.229, pruned_loss=0.02944, over 7064.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2718, pruned_loss=0.04894, over 1421971.40 frames.], batch size: 18, lr: 2.63e-04
2022-05-28 05:51:40,405 INFO [train.py:842] (3/4) Epoch 21, batch 3300, loss[loss=0.138, simple_loss=0.2226, pruned_loss=0.02669, over 7145.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2712, pruned_loss=0.04901, over 1423917.94 frames.], batch size: 17, lr: 2.63e-04
2022-05-28 05:52:18,328 INFO [train.py:842] (3/4) Epoch 21, batch 3350, loss[loss=0.2115, simple_loss=0.2988, pruned_loss=0.06209, over 7241.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2719, pruned_loss=0.0494, over 1419868.64 frames.], batch size: 20, lr: 2.63e-04
2022-05-28 05:52:56,398 INFO [train.py:842] (3/4) Epoch 21, batch 3400, loss[loss=0.2011, simple_loss=0.2921, pruned_loss=0.05504, over 6350.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2723, pruned_loss=0.04951, over 1415557.62 frames.], batch size: 38, lr: 2.63e-04
2022-05-28 05:53:34,255 INFO [train.py:842] (3/4) Epoch 21, batch 3450, loss[loss=0.1859, simple_loss=0.2887, pruned_loss=0.04156, over 7324.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2718, pruned_loss=0.04901, over 1414336.15 frames.], batch size: 21, lr: 2.63e-04
2022-05-28 05:54:12,337 INFO [train.py:842] (3/4) Epoch 21, batch 3500, loss[loss=0.1966, simple_loss=0.2874, pruned_loss=0.05294, over 7151.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2732, pruned_loss=0.05006, over 1410365.99 frames.], batch size: 28, lr: 2.63e-04
2022-05-28 05:54:50,563 INFO [train.py:842] (3/4) Epoch 21, batch 3550, loss[loss=0.152, simple_loss=0.2299, pruned_loss=0.03703, over 7289.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2722, pruned_loss=0.04953, over 1414009.65 frames.], batch size: 17, lr: 2.63e-04
2022-05-28 05:55:28,705 INFO [train.py:842] (3/4) Epoch 21, batch 3600, loss[loss=0.2032, simple_loss=0.2898, pruned_loss=0.05836, over 7394.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2727, pruned_loss=0.04987, over 1411664.66 frames.], batch size: 23, lr: 2.63e-04
2022-05-28 05:56:06,587 INFO [train.py:842] (3/4) Epoch 21, batch 3650, loss[loss=0.1952, simple_loss=0.2915, pruned_loss=0.04944, over 7186.00 frames.], tot_loss[loss=0.186, simple_loss=0.2722, pruned_loss=0.04989, over 1413246.19 frames.], batch size: 26, lr: 2.63e-04
2022-05-28 05:56:44,828 INFO [train.py:842] (3/4) Epoch 21, batch 3700, loss[loss=0.2368, simple_loss=0.3258, pruned_loss=0.07385, over 7318.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2719, pruned_loss=0.04969, over 1413186.13 frames.], batch size: 21, lr: 2.63e-04
2022-05-28 05:57:22,926 INFO [train.py:842] (3/4) Epoch 21, batch 3750, loss[loss=0.1659, simple_loss=0.251, pruned_loss=0.04035, over 7319.00 frames.], tot_loss[loss=0.1847, simple_loss=0.271, pruned_loss=0.04926, over 1416800.29 frames.], batch size: 25, lr: 2.62e-04
2022-05-28 05:58:01,036 INFO [train.py:842] (3/4) Epoch 21, batch 3800, loss[loss=0.2027, simple_loss=0.2915, pruned_loss=0.05697, over 7196.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2711, pruned_loss=0.04935, over 1417214.20 frames.], batch size: 26, lr: 2.62e-04
2022-05-28 05:58:38,984 INFO [train.py:842] (3/4) Epoch 21, batch 3850, loss[loss=0.1715, simple_loss=0.2623, pruned_loss=0.04036, over 7333.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2716, pruned_loss=0.04949, over 1418371.35 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 05:59:17,316 INFO [train.py:842] (3/4) Epoch 21, batch 3900, loss[loss=0.1759, simple_loss=0.2532, pruned_loss=0.04929, over 7262.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2723, pruned_loss=0.05004, over 1422097.03 frames.], batch size: 19, lr: 2.62e-04
2022-05-28 05:59:54,992 INFO [train.py:842] (3/4) Epoch 21, batch 3950, loss[loss=0.1525, simple_loss=0.2467, pruned_loss=0.02911, over 7404.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2723, pruned_loss=0.04976, over 1417468.49 frames.], batch size: 18, lr: 2.62e-04
2022-05-28 06:00:33,130 INFO [train.py:842] (3/4) Epoch 21, batch 4000, loss[loss=0.17, simple_loss=0.2533, pruned_loss=0.04334, over 7355.00 frames.], tot_loss[loss=0.185, simple_loss=0.2714, pruned_loss=0.04931, over 1421504.10 frames.], batch size: 19, lr: 2.62e-04
2022-05-28 06:01:11,320 INFO [train.py:842] (3/4) Epoch 21, batch 4050, loss[loss=0.1679, simple_loss=0.2571, pruned_loss=0.03934, over 7434.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2701, pruned_loss=0.04863, over 1422796.54 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:01:49,094 INFO [train.py:842] (3/4) Epoch 21, batch 4100, loss[loss=0.1471, simple_loss=0.2287, pruned_loss=0.03279, over 7132.00 frames.], tot_loss[loss=0.185, simple_loss=0.2717, pruned_loss=0.04911, over 1412916.73 frames.], batch size: 17, lr: 2.62e-04
2022-05-28 06:02:26,900 INFO [train.py:842] (3/4) Epoch 21, batch 4150, loss[loss=0.1887, simple_loss=0.2808, pruned_loss=0.04835, over 7216.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2723, pruned_loss=0.04934, over 1411676.31 frames.], batch size: 23, lr: 2.62e-04
2022-05-28 06:03:05,087 INFO [train.py:842] (3/4) Epoch 21, batch 4200, loss[loss=0.2014, simple_loss=0.2819, pruned_loss=0.06044, over 5205.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2726, pruned_loss=0.0495, over 1416211.07 frames.], batch size: 52, lr: 2.62e-04
2022-05-28 06:03:42,989 INFO [train.py:842] (3/4) Epoch 21, batch 4250, loss[loss=0.168, simple_loss=0.2596, pruned_loss=0.03817, over 7214.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2733, pruned_loss=0.04992, over 1416660.49 frames.], batch size: 21, lr: 2.62e-04
2022-05-28 06:04:21,422 INFO [train.py:842] (3/4) Epoch 21, batch 4300, loss[loss=0.2297, simple_loss=0.3047, pruned_loss=0.07733, over 7008.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2724, pruned_loss=0.04974, over 1419791.71 frames.], batch size: 16, lr: 2.62e-04
2022-05-28 06:04:59,218 INFO [train.py:842] (3/4) Epoch 21, batch 4350, loss[loss=0.1922, simple_loss=0.2726, pruned_loss=0.05595, over 7283.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2727, pruned_loss=0.04959, over 1419527.48 frames.], batch size: 24, lr: 2.62e-04
2022-05-28 06:05:37,560 INFO [train.py:842] (3/4) Epoch 21, batch 4400, loss[loss=0.1581, simple_loss=0.2568, pruned_loss=0.02974, over 6541.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2712, pruned_loss=0.04854, over 1421282.82 frames.], batch size: 38, lr: 2.62e-04
2022-05-28 06:06:15,537 INFO [train.py:842] (3/4) Epoch 21, batch 4450, loss[loss=0.19, simple_loss=0.2762, pruned_loss=0.0519, over 7214.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2711, pruned_loss=0.04868, over 1422903.43 frames.], batch size: 21, lr: 2.62e-04
2022-05-28 06:06:53,888 INFO [train.py:842] (3/4) Epoch 21, batch 4500, loss[loss=0.1959, simple_loss=0.2816, pruned_loss=0.0551, over 7232.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2712, pruned_loss=0.04889, over 1425248.90 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:07:31,874 INFO [train.py:842] (3/4) Epoch 21, batch 4550, loss[loss=0.2191, simple_loss=0.311, pruned_loss=0.06365, over 7081.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2715, pruned_loss=0.04868, over 1426204.68 frames.], batch size: 28, lr: 2.62e-04
2022-05-28 06:08:10,252 INFO [train.py:842] (3/4) Epoch 21, batch 4600, loss[loss=0.1773, simple_loss=0.2582, pruned_loss=0.04818, over 7160.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2719, pruned_loss=0.04933, over 1424296.37 frames.], batch size: 18, lr: 2.62e-04
2022-05-28 06:08:48,137 INFO [train.py:842] (3/4) Epoch 21, batch 4650, loss[loss=0.1811, simple_loss=0.2751, pruned_loss=0.0435, over 7228.00 frames.], tot_loss[loss=0.185, simple_loss=0.2714, pruned_loss=0.04932, over 1423963.76 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:09:26,160 INFO [train.py:842] (3/4) Epoch 21, batch 4700, loss[loss=0.1522, simple_loss=0.2496, pruned_loss=0.02743, over 7151.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2715, pruned_loss=0.04909, over 1425728.90 frames.], batch size: 19, lr: 2.62e-04
2022-05-28 06:10:04,167 INFO [train.py:842] (3/4) Epoch 21, batch 4750, loss[loss=0.2031, simple_loss=0.2978, pruned_loss=0.05415, over 7113.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2715, pruned_loss=0.04936, over 1424967.04 frames.], batch size: 28, lr: 2.62e-04
2022-05-28 06:10:42,359 INFO [train.py:842] (3/4) Epoch 21, batch 4800, loss[loss=0.2247, simple_loss=0.3013, pruned_loss=0.07406, over 7284.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2726, pruned_loss=0.04993, over 1422566.05 frames.], batch size: 24, lr: 2.62e-04
2022-05-28 06:11:20,373 INFO [train.py:842] (3/4) Epoch 21, batch 4850, loss[loss=0.1904, simple_loss=0.2752, pruned_loss=0.05286, over 7328.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2719, pruned_loss=0.04972, over 1419582.30 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:11:58,844 INFO [train.py:842] (3/4) Epoch 21, batch 4900, loss[loss=0.1672, simple_loss=0.2548, pruned_loss=0.03981, over 7309.00 frames.], tot_loss[loss=0.185, simple_loss=0.2711, pruned_loss=0.04943, over 1422941.28 frames.], batch size: 24, lr: 2.62e-04
2022-05-28 06:12:36,425 INFO [train.py:842] (3/4) Epoch 21, batch 4950, loss[loss=0.1886, simple_loss=0.2762, pruned_loss=0.05053, over 7147.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2725, pruned_loss=0.0496, over 1414630.28 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:13:14,609 INFO [train.py:842] (3/4) Epoch 21, batch 5000, loss[loss=0.1875, simple_loss=0.2637, pruned_loss=0.05561, over 7430.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2726, pruned_loss=0.04955, over 1418188.70 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:13:52,560 INFO [train.py:842] (3/4) Epoch 21, batch 5050, loss[loss=0.1637, simple_loss=0.2551, pruned_loss=0.03612, over 7429.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2728, pruned_loss=0.04994, over 1419108.97 frames.], batch size: 20, lr: 2.62e-04
2022-05-28 06:14:30,645 INFO [train.py:842] (3/4) Epoch 21, batch 5100, loss[loss=0.14, simple_loss=0.2285, pruned_loss=0.02575, over 7163.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2725, pruned_loss=0.04964, over 1420255.08 frames.], batch size: 18, lr: 2.62e-04
2022-05-28 06:15:08,578 INFO [train.py:842] (3/4) Epoch 21, batch 5150, loss[loss=0.2888, simple_loss=0.3605, pruned_loss=0.1086, over 5107.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2726, pruned_loss=0.04985, over 1415035.27 frames.], batch size: 52, lr: 2.62e-04
2022-05-28 06:15:46,843 INFO [train.py:842] (3/4) Epoch 21, batch 5200, loss[loss=0.1815, simple_loss=0.2647, pruned_loss=0.04921, over 6753.00 frames.], tot_loss[loss=0.186, simple_loss=0.2726, pruned_loss=0.04968, over 1419134.56 frames.], batch size: 31, lr: 2.61e-04
2022-05-28 06:16:24,695 INFO [train.py:842] (3/4) Epoch 21, batch 5250, loss[loss=0.1885, simple_loss=0.2871, pruned_loss=0.04494, over 6275.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2726, pruned_loss=0.04958, over 1420078.66 frames.], batch size: 37, lr: 2.61e-04
2022-05-28 06:17:02,977 INFO [train.py:842] (3/4) Epoch 21, batch 5300, loss[loss=0.1632, simple_loss=0.2443, pruned_loss=0.04103, over 7162.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2715, pruned_loss=0.04883, over 1423305.17 frames.], batch size: 18, lr: 2.61e-04
2022-05-28 06:17:40,972 INFO [train.py:842] (3/4) Epoch 21, batch 5350, loss[loss=0.1924, simple_loss=0.2804, pruned_loss=0.05218, over 7284.00 frames.], tot_loss[loss=0.1852, simple_loss=0.272, pruned_loss=0.04921, over 1424724.91 frames.], batch size: 25, lr: 2.61e-04
2022-05-28 06:18:19,351 INFO [train.py:842] (3/4) Epoch 21, batch 5400, loss[loss=0.158, simple_loss=0.2447, pruned_loss=0.03572, over 7276.00 frames.], tot_loss[loss=0.1863, simple_loss=0.273, pruned_loss=0.04979, over 1420477.53 frames.], batch size: 18, lr: 2.61e-04
2022-05-28 06:18:57,186 INFO [train.py:842] (3/4) Epoch 21, batch 5450, loss[loss=0.1983, simple_loss=0.2895, pruned_loss=0.05356, over 7190.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2735, pruned_loss=0.04996, over 1423064.48 frames.], batch size: 23, lr: 2.61e-04
2022-05-28 06:19:35,462 INFO [train.py:842] (3/4) Epoch 21, batch 5500, loss[loss=0.1998, simple_loss=0.2866, pruned_loss=0.05654, over 7371.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2737, pruned_loss=0.05001, over 1422006.20 frames.], batch size: 23, lr: 2.61e-04
2022-05-28 06:20:13,588 INFO [train.py:842] (3/4) Epoch 21, batch 5550, loss[loss=0.1817, simple_loss=0.2693, pruned_loss=0.0471, over 7335.00 frames.], tot_loss[loss=0.1867, simple_loss=0.273, pruned_loss=0.05016, over 1418738.81 frames.], batch size: 22, lr: 2.61e-04
2022-05-28 06:20:51,847 INFO [train.py:842] (3/4) Epoch 21, batch 5600, loss[loss=0.2231, simple_loss=0.291, pruned_loss=0.07764, over 7011.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2722, pruned_loss=0.04997, over 1417346.06 frames.], batch size: 16, lr: 2.61e-04
2022-05-28 06:21:29,935 INFO [train.py:842] (3/4) Epoch 21, batch 5650, loss[loss=0.2184, simple_loss=0.3012, pruned_loss=0.06787, over 7314.00 frames.], tot_loss[loss=0.1863, simple_loss=0.272, pruned_loss=0.05029, over 1420503.30 frames.], batch size: 21, lr: 2.61e-04
2022-05-28 06:22:08,300 INFO [train.py:842] (3/4) Epoch 21, batch 5700, loss[loss=0.2044, simple_loss=0.2927, pruned_loss=0.05801, over 7040.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2727, pruned_loss=0.05086, over 1423153.62 frames.], batch size: 28, lr: 2.61e-04
2022-05-28 06:22:46,375 INFO [train.py:842] (3/4) Epoch 21, batch 5750, loss[loss=0.1866, simple_loss=0.2937, pruned_loss=0.03971, over 7332.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2719, pruned_loss=0.05012, over 1427011.51 frames.], batch size: 22, lr: 2.61e-04
2022-05-28 06:23:24,682 INFO [train.py:842] (3/4) Epoch 21, batch 5800, loss[loss=0.1966, simple_loss=0.2789, pruned_loss=0.05714, over 7276.00 frames.], tot_loss[loss=0.186, simple_loss=0.2717, pruned_loss=0.05017, over 1429631.46 frames.], batch size: 25, lr: 2.61e-04
2022-05-28 06:24:02,714 INFO [train.py:842] (3/4) Epoch 21, batch 5850, loss[loss=0.1499, simple_loss=0.2355, pruned_loss=0.03221, over 7437.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2717, pruned_loss=0.05035, over 1423130.19 frames.], batch size: 20, lr: 2.61e-04
2022-05-28 06:24:40,940 INFO [train.py:842] (3/4) Epoch 21, batch 5900, loss[loss=0.2185, simple_loss=0.309, pruned_loss=0.06399, over 7287.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2716, pruned_loss=0.04989, over 1422876.93 frames.], batch size: 24, lr: 2.61e-04
2022-05-28 06:25:18,663 INFO [train.py:842] (3/4) Epoch 21, batch 5950, loss[loss=0.2117, simple_loss=0.2922, pruned_loss=0.06556, over 6799.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2728, pruned_loss=0.05026, over 1416034.70 frames.], batch size: 31, lr: 2.61e-04
2022-05-28 06:25:56,959 INFO [train.py:842] (3/4) Epoch 21, batch 6000, loss[loss=0.1529, simple_loss=0.2353, pruned_loss=0.03519, over 6852.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2729, pruned_loss=0.05002, over 1419475.14 frames.], batch size: 15, lr: 2.61e-04
2022-05-28 06:25:56,960 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 06:26:05,956 INFO [train.py:871] (3/4) Epoch 21, validation: loss=0.1654, simple_loss=0.2646, pruned_loss=0.03309, over 868885.00 frames.
2022-05-28 06:26:43,748 INFO [train.py:842] (3/4) Epoch 21, batch 6050, loss[loss=0.1797, simple_loss=0.2794, pruned_loss=0.03997, over 6547.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2733, pruned_loss=0.04976, over 1416337.15 frames.], batch size: 38, lr: 2.61e-04
2022-05-28 06:27:22,092 INFO [train.py:842] (3/4) Epoch 21, batch 6100, loss[loss=0.1698, simple_loss=0.2462, pruned_loss=0.04672, over 7141.00 frames.], tot_loss[loss=0.1856, simple_loss=0.272, pruned_loss=0.04959, over 1418290.78 frames.], batch size: 17, lr: 2.61e-04
2022-05-28 06:27:59,910 INFO [train.py:842] (3/4) Epoch 21, batch 6150, loss[loss=0.1783, simple_loss=0.2765, pruned_loss=0.0401, over 7336.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2721, pruned_loss=0.04909, over 1419028.66 frames.], batch size: 22, lr: 2.61e-04
2022-05-28 06:28:38,156 INFO [train.py:842] (3/4) Epoch 21, batch 6200, loss[loss=0.1875, simple_loss=0.2801, pruned_loss=0.04741, over 7193.00 frames.], tot_loss[loss=0.185, simple_loss=0.2723, pruned_loss=0.04883, over 1422748.52 frames.], batch size: 26, lr: 2.61e-04
2022-05-28 06:29:16,121 INFO [train.py:842] (3/4) Epoch 21, batch 6250, loss[loss=0.1979, simple_loss=0.2811, pruned_loss=0.05737, over 7302.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2726, pruned_loss=0.04945, over 1422188.22 frames.], batch size: 24, lr: 2.61e-04
2022-05-28 06:29:54,361 INFO [train.py:842] (3/4) Epoch 21, batch 6300, loss[loss=0.2403, simple_loss=0.3143, pruned_loss=0.08316, over 7345.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2734, pruned_loss=0.04992, over 1425524.84 frames.], batch size: 22, lr: 2.61e-04
2022-05-28 06:30:32,473 INFO [train.py:842] (3/4) Epoch 21, batch 6350, loss[loss=0.1451, simple_loss=0.2379, pruned_loss=0.02613, over 7315.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2723, pruned_loss=0.04963, over 1428511.78 frames.], batch size: 20, lr: 2.61e-04
2022-05-28 06:31:10,715 INFO [train.py:842] (3/4) Epoch 21, batch 6400, loss[loss=0.2489, simple_loss=0.3235, pruned_loss=0.08721, over 5229.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2717, pruned_loss=0.04964, over 1425805.73 frames.], batch size: 52, lr: 2.61e-04
2022-05-28 06:31:48,572 INFO [train.py:842] (3/4) Epoch 21, batch 6450, loss[loss=0.1556, simple_loss=0.2413, pruned_loss=0.03495, over 7439.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2715, pruned_loss=0.04958, over 1423694.74 frames.], batch size: 20, lr: 2.61e-04
2022-05-28 06:32:26,774 INFO [train.py:842] (3/4) Epoch 21, batch 6500, loss[loss=0.1823, simple_loss=0.2609, pruned_loss=0.05182, over 7061.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2719, pruned_loss=0.0495, over 1425896.54 frames.], batch size: 18, lr: 2.61e-04
2022-05-28 06:33:04,416 INFO [train.py:842] (3/4) Epoch 21, batch 6550, loss[loss=0.1868, simple_loss=0.2719, pruned_loss=0.05079, over 7432.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2723, pruned_loss=0.04948, over 1423019.09 frames.], batch size: 20, lr: 2.61e-04
2022-05-28 06:33:42,758 INFO [train.py:842] (3/4) Epoch 21, batch 6600, loss[loss=0.1953, simple_loss=0.289, pruned_loss=0.05082, over 7335.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2723, pruned_loss=0.04919, over 1422465.46 frames.], batch size: 22, lr: 2.61e-04
2022-05-28 06:34:20,562 INFO [train.py:842] (3/4) Epoch 21, batch 6650, loss[loss=0.174, simple_loss=0.2488, pruned_loss=0.04961, over 7419.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2719, pruned_loss=0.0493, over 1417895.25 frames.], batch size: 18, lr: 2.60e-04
2022-05-28 06:34:59,053 INFO [train.py:842] (3/4) Epoch 21, batch 6700, loss[loss=0.1962, simple_loss=0.285, pruned_loss=0.05374, over 7383.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2717, pruned_loss=0.04888, over 1423175.02 frames.], batch size: 23, lr: 2.60e-04
2022-05-28 06:35:36,972 INFO [train.py:842] (3/4) Epoch 21, batch 6750, loss[loss=0.1477, simple_loss=0.2341, pruned_loss=0.03066, over 7001.00 frames.], tot_loss[loss=0.1842, simple_loss=0.271, pruned_loss=0.04868, over 1425639.74 frames.], batch size: 16, lr: 2.60e-04
2022-05-28 06:36:14,940 INFO [train.py:842] (3/4) Epoch 21, batch 6800, loss[loss=0.1881, simple_loss=0.2763, pruned_loss=0.04992, over 7408.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2713, pruned_loss=0.04891, over 1423762.64 frames.], batch size: 21, lr: 2.60e-04
2022-05-28 06:36:52,975 INFO [train.py:842] (3/4) Epoch 21, batch 6850, loss[loss=0.1856, simple_loss=0.2683, pruned_loss=0.05146, over 7441.00 frames.], tot_loss[loss=0.1841, simple_loss=0.271, pruned_loss=0.04862, over 1426804.37 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:37:31,260 INFO [train.py:842] (3/4) Epoch 21, batch 6900, loss[loss=0.177, simple_loss=0.2597, pruned_loss=0.04711, over 7163.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2717, pruned_loss=0.04898, over 1428372.50 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:38:09,067 INFO [train.py:842] (3/4) Epoch 21, batch 6950, loss[loss=0.1687, simple_loss=0.2637, pruned_loss=0.03684, over 7203.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2722, pruned_loss=0.04938, over 1427707.99 frames.], batch size: 23, lr: 2.60e-04
2022-05-28 06:38:47,244 INFO [train.py:842] (3/4) Epoch 21, batch 7000, loss[loss=0.1832, simple_loss=0.2657, pruned_loss=0.05028, over 7449.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2723, pruned_loss=0.04908, over 1427572.92 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:39:25,169 INFO [train.py:842] (3/4) Epoch 21, batch 7050, loss[loss=0.1949, simple_loss=0.2776, pruned_loss=0.05605, over 7209.00 frames.], tot_loss[loss=0.184, simple_loss=0.2709, pruned_loss=0.04853, over 1428435.12 frames.], batch size: 22, lr: 2.60e-04
2022-05-28 06:40:03,304 INFO [train.py:842] (3/4) Epoch 21, batch 7100, loss[loss=0.1532, simple_loss=0.2475, pruned_loss=0.02945, over 7067.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2708, pruned_loss=0.0484, over 1425423.46 frames.], batch size: 18, lr: 2.60e-04
2022-05-28 06:40:41,329 INFO [train.py:842] (3/4) Epoch 21, batch 7150, loss[loss=0.1567, simple_loss=0.247, pruned_loss=0.03319, over 7152.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2696, pruned_loss=0.04759, over 1429212.00 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:41:19,797 INFO [train.py:842] (3/4) Epoch 21, batch 7200, loss[loss=0.187, simple_loss=0.27, pruned_loss=0.05203, over 7326.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2693, pruned_loss=0.04747, over 1431760.64 frames.], batch size: 20, lr: 2.60e-04
2022-05-28 06:41:57,870 INFO [train.py:842] (3/4) Epoch 21, batch 7250, loss[loss=0.1723, simple_loss=0.2652, pruned_loss=0.03975, over 7430.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2687, pruned_loss=0.04723, over 1427841.00 frames.], batch size: 20, lr: 2.60e-04
2022-05-28 06:42:36,003 INFO [train.py:842] (3/4) Epoch 21, batch 7300, loss[loss=0.1893, simple_loss=0.2614, pruned_loss=0.05862, over 7135.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2691, pruned_loss=0.04726, over 1428625.55 frames.], batch size: 17, lr: 2.60e-04
2022-05-28 06:43:13,741 INFO [train.py:842] (3/4) Epoch 21, batch 7350, loss[loss=0.2277, simple_loss=0.3123, pruned_loss=0.07156, over 7278.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2707, pruned_loss=0.04809, over 1426976.22 frames.], batch size: 24, lr: 2.60e-04
2022-05-28 06:43:51,817 INFO [train.py:842] (3/4) Epoch 21, batch 7400, loss[loss=0.1915, simple_loss=0.2933, pruned_loss=0.04482, over 7326.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2719, pruned_loss=0.04871, over 1426283.38 frames.], batch size: 20, lr: 2.60e-04
2022-05-28 06:44:29,677 INFO [train.py:842] (3/4) Epoch 21, batch 7450, loss[loss=0.1793, simple_loss=0.2682, pruned_loss=0.04522, over 7261.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2727, pruned_loss=0.04935, over 1425024.61 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:45:08,006 INFO [train.py:842] (3/4) Epoch 21, batch 7500, loss[loss=0.2206, simple_loss=0.3184, pruned_loss=0.06138, over 7256.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2728, pruned_loss=0.04974, over 1422975.46 frames.], batch size: 19, lr: 2.60e-04
2022-05-28 06:45:46,000 INFO [train.py:842] (3/4) Epoch 21, batch 7550, loss[loss=0.1894, simple_loss=0.28, pruned_loss=0.04941, over 7072.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2717, pruned_loss=0.04893, over 1423776.24 frames.], batch size: 28, lr: 2.60e-04
2022-05-28 06:46:33,472 INFO [train.py:842] (3/4) Epoch 21, batch 7600, loss[loss=0.1759, simple_loss=0.2713, pruned_loss=0.04026, over 7206.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2725, pruned_loss=0.04969, over 1417312.17 frames.], batch size: 22, lr: 2.60e-04
2022-05-28 06:47:11,540 INFO [train.py:842] (3/4) Epoch 21, batch 7650, loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06016, over 7277.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2715, pruned_loss=0.04932, over 1418633.13 frames.], batch size: 17, lr: 2.60e-04
2022-05-28 06:47:49,877 INFO [train.py:842] (3/4) Epoch 21, batch 7700, loss[loss=0.1602, simple_loss=0.252, pruned_loss=0.03417, over 7341.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2714, pruned_loss=0.04967, over 1419195.92 frames.], batch size: 22, lr: 2.60e-04
2022-05-28 06:48:27,635 INFO [train.py:842] (3/4) Epoch 21, batch 7750, loss[loss=0.1713, simple_loss=0.2597, pruned_loss=0.04141, over 7157.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2722, pruned_loss=0.04999, over 1417809.75 frames.], batch size: 18, lr: 2.60e-04
2022-05-28 06:49:05,972 INFO [train.py:842] (3/4) Epoch 21, batch 7800, loss[loss=0.1831, simple_loss=0.2648, pruned_loss=0.05068, over 7408.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2724, pruned_loss=0.05042, over 1422323.28 frames.], batch size: 18, lr: 2.60e-04
2022-05-28 06:49:44,033 INFO [train.py:842] (3/4) Epoch 21, batch 7850, loss[loss=0.145, simple_loss=0.2511, pruned_loss=0.0195, over 7227.00 frames.], tot_loss[loss=0.1853, simple_loss=0.271, pruned_loss=0.04979, over 1422040.58 frames.], batch size: 21, lr: 2.60e-04
2022-05-28 06:50:22,202 INFO [train.py:842] (3/4) Epoch 21, batch 7900, loss[loss=0.1928, simple_loss=0.2964, pruned_loss=0.0446, over 7330.00 frames.], tot_loss[loss=0.186, simple_loss=0.2721, pruned_loss=0.04992, over 1423697.16 frames.], batch size: 21, lr: 2.60e-04
2022-05-28 06:51:00,112 INFO [train.py:842] (3/4) Epoch 21, batch 7950, loss[loss=0.1999, simple_loss=0.269, pruned_loss=0.06543, over 7000.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2709, pruned_loss=0.04947, over 1424941.80 frames.], batch size: 16, lr: 2.60e-04
2022-05-28 06:51:38,310 INFO [train.py:842] (3/4) Epoch 21, batch 8000, loss[loss=0.1859, simple_loss=0.2747, pruned_loss=0.04853, over 7307.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2715, pruned_loss=0.04991, over 1425194.54 frames.], batch size: 25, lr: 2.60e-04
2022-05-28 06:52:16,324 INFO [train.py:842] (3/4) Epoch 21, batch 8050, loss[loss=0.1886, simple_loss=0.2632, pruned_loss=0.05699, over 7389.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2706, pruned_loss=0.04879, over 1427574.20 frames.], batch size: 23, lr: 2.60e-04
2022-05-28 06:52:54,476 INFO [train.py:842] (3/4) Epoch 21, batch 8100, loss[loss=0.2001, simple_loss=0.2877, pruned_loss=0.05618, over 7287.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2716, pruned_loss=0.04962, over 1426540.50 frames.], batch size: 24, lr: 2.60e-04
2022-05-28 06:53:32,528 INFO [train.py:842] (3/4) Epoch 21, batch 8150, loss[loss=0.1718, simple_loss=0.2576, pruned_loss=0.04303, over 7325.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2719, pruned_loss=0.04948, over 1426290.08 frames.], batch size: 20, lr: 2.59e-04
2022-05-28 06:54:13,540 INFO [train.py:842] (3/4) Epoch 21, batch 8200, loss[loss=0.1591, simple_loss=0.2441, pruned_loss=0.03708, over 7059.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2715, pruned_loss=0.04917, over 1429401.77 frames.], batch size: 18, lr: 2.59e-04
2022-05-28 06:54:51,653 INFO [train.py:842] (3/4) Epoch 21, batch 8250, loss[loss=0.2678, simple_loss=0.3562, pruned_loss=0.08974, over 4965.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2714, pruned_loss=0.04915, over 1429056.66 frames.], batch size: 52, lr: 2.59e-04
2022-05-28 06:55:30,097 INFO [train.py:842] (3/4) Epoch 21, batch 8300, loss[loss=0.1867, simple_loss=0.2841, pruned_loss=0.04465, over 7292.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2695, pruned_loss=0.04834, over 1428232.68 frames.], batch size: 25, lr: 2.59e-04
2022-05-28 06:56:07,853 INFO [train.py:842] (3/4) Epoch 21, batch 8350, loss[loss=0.2448, simple_loss=0.333, pruned_loss=0.07828, over 7416.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2712, pruned_loss=0.04935, over 1427470.98 frames.], batch size: 21, lr: 2.59e-04
2022-05-28 06:56:46,229 INFO [train.py:842] (3/4) Epoch 21, batch 8400, loss[loss=0.1724, simple_loss=0.2642, pruned_loss=0.0403, over 7189.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2709, pruned_loss=0.04988, over 1430756.78 frames.], batch size: 26, lr: 2.59e-04
2022-05-28 06:57:24,203 INFO [train.py:842] (3/4) Epoch 21, batch 8450, loss[loss=0.1557, simple_loss=0.2574, pruned_loss=0.02702, over 7140.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2704, pruned_loss=0.04947, over 1426374.66 frames.], batch size: 20, lr: 2.59e-04
2022-05-28 06:58:02,579 INFO [train.py:842] (3/4) Epoch 21, batch 8500, loss[loss=0.188, simple_loss=0.2762, pruned_loss=0.0499, over 7424.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2702, pruned_loss=0.04943, over 1424215.10 frames.], batch size: 20, lr: 2.59e-04
2022-05-28 06:58:40,505 INFO [train.py:842] (3/4) Epoch 21, batch 8550, loss[loss=0.1331, simple_loss=0.214, pruned_loss=0.02614, over 7294.00 frames.], tot_loss[loss=0.1827, simple_loss=0.269, pruned_loss=0.04824, over 1424750.25 frames.], batch size: 17, lr: 2.59e-04
2022-05-28 06:59:18,643 INFO [train.py:842] (3/4) Epoch 21, batch 8600, loss[loss=0.1712, simple_loss=0.2652, pruned_loss=0.03861, over 7293.00 frames.], tot_loss[loss=0.1823, simple_loss=0.269, pruned_loss=0.04778, over 1421267.12 frames.], batch size: 25, lr: 2.59e-04
2022-05-28 06:59:56,664 INFO [train.py:842] (3/4) Epoch 21, batch 8650, loss[loss=0.172, simple_loss=0.251, pruned_loss=0.04647, over 7165.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2694, pruned_loss=0.048, over 1418956.72 frames.], batch size: 18, lr: 2.59e-04
2022-05-28 07:00:35,015 INFO [train.py:842] (3/4) Epoch 21, batch 8700, loss[loss=0.1923, simple_loss=0.2823, pruned_loss=0.05109, over 7116.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2686, pruned_loss=0.04787, over 1416463.09 frames.], batch size: 21, lr: 2.59e-04
2022-05-28 07:01:12,972 INFO [train.py:842] (3/4) Epoch 21, batch 8750, loss[loss=0.1793, simple_loss=0.2723, pruned_loss=0.04313, over 6810.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2696, pruned_loss=0.04846, over 1418508.46 frames.], batch size: 31, lr: 2.59e-04
2022-05-28 07:01:51,338 INFO [train.py:842] (3/4) Epoch 21, batch 8800, loss[loss=0.1822, simple_loss=0.2472, pruned_loss=0.0586, over 7283.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2685, pruned_loss=0.04797, over 1421776.03 frames.], batch size: 17, lr: 2.59e-04
2022-05-28 07:02:29,290 INFO [train.py:842] (3/4) Epoch 21, batch 8850, loss[loss=0.1759, simple_loss=0.2633, pruned_loss=0.04422, over 6339.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2692, pruned_loss=0.04848, over 1419172.25 frames.], batch size: 38, lr: 2.59e-04
2022-05-28 07:03:07,726 INFO [train.py:842] (3/4) Epoch 21, batch 8900, loss[loss=0.1874, simple_loss=0.273, pruned_loss=0.05088, over 7121.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2687, pruned_loss=0.0484, over 1420239.34 frames.], batch size: 21, lr: 2.59e-04
2022-05-28 07:03:45,617 INFO [train.py:842] (3/4) Epoch 21, batch 8950, loss[loss=0.1899, simple_loss=0.2785, pruned_loss=0.05067, over 7143.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2703, pruned_loss=0.04923, over 1411258.60 frames.], batch size: 20, lr: 2.59e-04
2022-05-28 07:04:23,627 INFO [train.py:842] (3/4) Epoch 21, batch 9000, loss[loss=0.1825, simple_loss=0.2764, pruned_loss=0.04427, over 6535.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2715, pruned_loss=0.05013, over 1397363.72 frames.], batch size: 38, lr: 2.59e-04
2022-05-28 07:04:23,628 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 07:04:32,660 INFO [train.py:871] (3/4) Epoch 21, validation: loss=0.1634, simple_loss=0.2627, pruned_loss=0.03203, over 868885.00 frames.
2022-05-28 07:05:10,706 INFO [train.py:842] (3/4) Epoch 21, batch 9050, loss[loss=0.1625, simple_loss=0.243, pruned_loss=0.04098, over 6765.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2711, pruned_loss=0.0506, over 1385846.87 frames.], batch size: 15, lr: 2.59e-04
2022-05-28 07:05:48,359 INFO [train.py:842] (3/4) Epoch 21, batch 9100, loss[loss=0.1927, simple_loss=0.2762, pruned_loss=0.05463, over 5188.00 frames.], tot_loss[loss=0.1869, simple_loss=0.272, pruned_loss=0.05093, over 1357840.32 frames.], batch size: 52, lr: 2.59e-04
2022-05-28 07:06:25,193 INFO [train.py:842] (3/4) Epoch 21, batch 9150, loss[loss=0.2007, simple_loss=0.2858, pruned_loss=0.05779, over 7118.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2756, pruned_loss=0.05231, over 1323521.92 frames.], batch size: 21, lr: 2.59e-04
2022-05-28 07:07:15,921 INFO [train.py:842] (3/4) Epoch 22, batch 0, loss[loss=0.1843, simple_loss=0.2871, pruned_loss=0.04069, over 7284.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2871, pruned_loss=0.04069, over 7284.00 frames.], batch size: 25, lr: 2.53e-04
2022-05-28 07:07:54,000 INFO [train.py:842] (3/4) Epoch 22, batch 50, loss[loss=0.1427, simple_loss=0.2298, pruned_loss=0.02783, over 7163.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2745, pruned_loss=0.05027, over 317725.51 frames.], batch size: 18, lr: 2.53e-04
2022-05-28 07:08:32,416 INFO [train.py:842] (3/4) Epoch 22, batch 100, loss[loss=0.1624, simple_loss=0.261, pruned_loss=0.03194, over 7120.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2705, pruned_loss=0.04827, over 563571.44 frames.], batch size: 21, lr: 2.53e-04
2022-05-28 07:09:10,280 INFO [train.py:842] (3/4) Epoch 22, batch 150, loss[loss=0.1709, simple_loss=0.2563, pruned_loss=0.04278, over 7313.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2714, pruned_loss=0.04894, over 752952.74 frames.], batch size: 21, lr: 2.53e-04
2022-05-28 07:09:48,507 INFO [train.py:842] (3/4) Epoch 22, batch 200, loss[loss=0.1976, simple_loss=0.2991, pruned_loss=0.0481, over 7351.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2698, pruned_loss=0.04819, over 900936.74 frames.], batch size: 22, lr: 2.53e-04
2022-05-28 07:10:26,529 INFO [train.py:842] (3/4) Epoch 22, batch 250, loss[loss=0.1876, simple_loss=0.2692, pruned_loss=0.05298, over 7260.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2694, pruned_loss=0.04807, over 1014290.05 frames.], batch size: 19, lr: 2.53e-04
2022-05-28 07:11:04,691 INFO [train.py:842] (3/4) Epoch 22, batch 300, loss[loss=0.2034, simple_loss=0.2881, pruned_loss=0.05941, over 7236.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2701, pruned_loss=0.04873, over 1106481.08 frames.], batch size: 20, lr: 2.53e-04
2022-05-28 07:11:42,636 INFO [train.py:842] (3/4) Epoch 22, batch 350, loss[loss=0.139, simple_loss=0.2311, pruned_loss=0.02349, over 7153.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2698, pruned_loss=0.04838, over 1177099.15 frames.], batch size: 19, lr: 2.53e-04
2022-05-28 07:12:20,796 INFO [train.py:842] (3/4) Epoch 22, batch 400, loss[loss=0.1847, simple_loss=0.2788, pruned_loss=0.04526, over 7218.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2693, pruned_loss=0.04772, over 1229362.39 frames.], batch size: 21, lr: 2.53e-04
2022-05-28 07:12:58,844 INFO [train.py:842] (3/4) Epoch 22, batch 450, loss[loss=0.2263, simple_loss=0.3048, pruned_loss=0.07389, over 4982.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2687, pruned_loss=0.04729, over 1273128.82 frames.], batch size: 52, lr: 2.53e-04
2022-05-28 07:13:36,985 INFO [train.py:842] (3/4) Epoch 22, batch 500, loss[loss=0.1799, simple_loss=0.2742, pruned_loss=0.04282, over 7332.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2705, pruned_loss=0.0474, over 1309103.24 frames.], batch size: 25, lr: 2.53e-04
2022-05-28 07:14:14,816 INFO [train.py:842] (3/4) Epoch 22, batch 550, loss[loss=0.1618, simple_loss=0.2558, pruned_loss=0.03397, over 7429.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2722, pruned_loss=0.04884, over 1332286.93 frames.], batch size: 20, lr: 2.53e-04
2022-05-28 07:14:53,174 INFO [train.py:842] (3/4) Epoch 22, batch 600, loss[loss=0.1852, simple_loss=0.2778, pruned_loss=0.04623, over 7337.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2706, pruned_loss=0.04832, over 1353652.86 frames.], batch size: 22, lr: 2.53e-04
2022-05-28 07:15:30,886 INFO [train.py:842] (3/4) Epoch 22, batch 650, loss[loss=0.1761, simple_loss=0.2732, pruned_loss=0.03944, over 7342.00 frames.], tot_loss[loss=0.1836, simple_loss=0.271, pruned_loss=0.04809, over 1368541.27 frames.], batch size: 22, lr: 2.53e-04
2022-05-28 07:16:09,254 INFO [train.py:842] (3/4) Epoch 22, batch 700, loss[loss=0.1802, simple_loss=0.2806, pruned_loss=0.0399, over 7305.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2704, pruned_loss=0.04823, over 1376824.13 frames.], batch size: 25, lr: 2.53e-04
2022-05-28 07:16:47,348 INFO [train.py:842] (3/4) Epoch 22, batch 750, loss[loss=0.1883, simple_loss=0.2665, pruned_loss=0.0551, over 7163.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2704, pruned_loss=0.04894, over 1385196.51 frames.], batch size: 18, lr: 2.53e-04
2022-05-28 07:17:25,599 INFO [train.py:842] (3/4) Epoch 22, batch 800, loss[loss=0.1924, simple_loss=0.2827, pruned_loss=0.05108, over 7303.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2706, pruned_loss=0.04884, over 1398429.60 frames.], batch size: 25, lr: 2.53e-04
2022-05-28 07:18:03,633 INFO [train.py:842] (3/4) Epoch 22, batch 850, loss[loss=0.1676, simple_loss=0.2458, pruned_loss=0.04471, over 7411.00 frames.], tot_loss[loss=0.1843, simple_loss=0.271, pruned_loss=0.04879, over 1403702.40 frames.], batch size: 18, lr: 2.52e-04
2022-05-28 07:18:41,829 INFO [train.py:842] (3/4) Epoch 22, batch 900, loss[loss=0.1844, simple_loss=0.2808, pruned_loss=0.04395, over 6387.00 frames.], tot_loss[loss=0.184, simple_loss=0.2706, pruned_loss=0.04873, over 1407602.26 frames.], batch size: 38, lr: 2.52e-04
2022-05-28 07:19:19,856 INFO [train.py:842] (3/4) Epoch 22, batch 950, loss[loss=0.2424, simple_loss=0.3174, pruned_loss=0.0837, over 7265.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2706, pruned_loss=0.04911, over 1409352.07 frames.], batch size: 18, lr: 2.52e-04
2022-05-28 07:19:57,846 INFO [train.py:842] (3/4) Epoch 22, batch 1000, loss[loss=0.1894, simple_loss=0.2696, pruned_loss=0.05461, over 7155.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2726, pruned_loss=0.05019, over 1410126.30 frames.], batch size: 19, lr: 2.52e-04
2022-05-28 07:20:36,026 INFO [train.py:842] (3/4) Epoch 22, batch 1050, loss[loss=0.2025, simple_loss=0.3025, pruned_loss=0.05121, over 7352.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2706, pruned_loss=0.0489, over 1414309.74 frames.], batch size: 22, lr: 2.52e-04
2022-05-28 07:21:14,306 INFO [train.py:842] (3/4) Epoch 22, batch 1100, loss[loss=0.1997, simple_loss=0.2851, pruned_loss=0.0572, over 6349.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2717, pruned_loss=0.04976, over 1418289.53 frames.], batch size: 37, lr: 2.52e-04
2022-05-28 07:21:52,341 INFO [train.py:842] (3/4) Epoch 22, batch 1150, loss[loss=0.1837, simple_loss=0.2533, pruned_loss=0.05707, over 7250.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2712, pruned_loss=0.04952, over 1419963.28 frames.], batch size: 19, lr: 2.52e-04
2022-05-28 07:22:30,720 INFO [train.py:842] (3/4) Epoch 22, batch 1200, loss[loss=0.2189, simple_loss=0.3045, pruned_loss=0.06669, over 7311.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2705, pruned_loss=0.04945, over 1420562.85 frames.], batch size: 25, lr: 2.52e-04
2022-05-28 07:23:08,673 INFO [train.py:842] (3/4) Epoch 22, batch 1250, loss[loss=0.1421, simple_loss=0.2276, pruned_loss=0.02827, over 7006.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2706, pruned_loss=0.04922, over 1419519.09 frames.], batch size: 16, lr: 2.52e-04
2022-05-28 07:23:46,950 INFO [train.py:842] (3/4) Epoch 22, batch 1300, loss[loss=0.206, simple_loss=0.2904, pruned_loss=0.06074, over 7157.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2706, pruned_loss=0.04916, over 1418231.52 frames.], batch size: 19, lr: 2.52e-04
2022-05-28 07:24:25,115 INFO [train.py:842] (3/4) Epoch 22, batch 1350, loss[loss=0.1975, simple_loss=0.2811, pruned_loss=0.05691, over 7417.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2704, pruned_loss=0.04907, over 1422805.68 frames.], batch size: 21, lr: 2.52e-04
2022-05-28 07:25:03,519 INFO [train.py:842] (3/4) Epoch 22, batch 1400, loss[loss=0.1984, simple_loss=0.2937, pruned_loss=0.05159, over 7183.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2697, pruned_loss=0.04827, over 1420436.40 frames.], batch size: 22, lr: 2.52e-04
2022-05-28 07:25:41,559 INFO [train.py:842] (3/4) Epoch 22, batch 1450, loss[loss=0.1617, simple_loss=0.2602, pruned_loss=0.03159, over 7431.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2703, pruned_loss=0.04842, over 1425274.52 frames.], batch size: 20, lr: 2.52e-04
2022-05-28 07:26:19,934 INFO [train.py:842] (3/4) Epoch 22, batch 1500, loss[loss=0.1693, simple_loss=0.2554, pruned_loss=0.0416, over 7223.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2699, pruned_loss=0.04824, over 1427228.22 frames.], batch size: 20, lr: 2.52e-04
2022-05-28 07:26:58,149 INFO [train.py:842] (3/4) Epoch 22, batch 1550, loss[loss=0.1541, simple_loss=0.2499, pruned_loss=0.02912, over 7228.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2701, pruned_loss=0.04855, over 1429002.33 frames.], batch size: 20, lr: 2.52e-04
2022-05-28 07:27:45,579 INFO [train.py:842] (3/4) Epoch 22, batch 1600, loss[loss=0.1735, simple_loss=0.2522, pruned_loss=0.04745, over 6763.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2712, pruned_loss=0.0488, over 1429825.76 frames.], batch size: 15, lr: 2.52e-04
2022-05-28 07:28:23,585 INFO [train.py:842] (3/4) Epoch 22, batch 1650, loss[loss=0.1996, simple_loss=0.2892, pruned_loss=0.05504, over 6750.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2708, pruned_loss=0.04838, over 1431427.21 frames.], batch size: 31, lr: 2.52e-04
2022-05-28 07:29:02,075 INFO [train.py:842] (3/4) Epoch 22, batch 1700, loss[loss=0.1649, simple_loss=0.2566, pruned_loss=0.03655, over 7335.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2698, pruned_loss=0.04768, over 1433183.28 frames.], batch size: 22, lr: 2.52e-04
2022-05-28 07:29:40,026 INFO [train.py:842] (3/4) Epoch 22, batch 1750, loss[loss=0.1845, simple_loss=0.2792, pruned_loss=0.04489, over 7240.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2694, pruned_loss=0.04736, over 1432539.49 frames.], batch size: 20, lr: 2.52e-04
2022-05-28 07:30:27,702 INFO [train.py:842] (3/4) Epoch 22, batch 1800, loss[loss=0.1721, simple_loss=0.2471, pruned_loss=0.04857, over 7281.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2694, pruned_loss=0.04783, over 1430090.80 frames.], batch size: 17, lr: 2.52e-04
2022-05-28 07:31:05,561 INFO [train.py:842] (3/4) Epoch 22, batch 1850, loss[loss=0.1973, simple_loss=0.2894, pruned_loss=0.05262, over 6160.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2691, pruned_loss=0.04758, over 1425505.94 frames.], batch size: 37, lr: 2.52e-04
2022-05-28 07:31:53,097 INFO [train.py:842] (3/4) Epoch 22, batch 1900, loss[loss=0.2444, simple_loss=0.3273, pruned_loss=0.08076, over 5400.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2695, pruned_loss=0.04796, over 1424276.89 frames.], batch size: 54, lr: 2.52e-04
2022-05-28 07:32:31,075 INFO [train.py:842] (3/4) Epoch 22, batch 1950, loss[loss=0.1756, simple_loss=0.2446, pruned_loss=0.05331, over 7279.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2686, pruned_loss=0.0476, over 1426263.59 frames.], batch size: 17, lr: 2.52e-04
2022-05-28 07:33:09,372 INFO [train.py:842] (3/4) Epoch 22, batch 2000, loss[loss=0.1672, simple_loss=0.2499, pruned_loss=0.04229, over 7323.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2696, pruned_loss=0.04842, over 1428507.94 frames.], batch size: 20, lr: 2.52e-04
2022-05-28 07:33:47,299 INFO [train.py:842] (3/4) Epoch 22, batch 2050, loss[loss=0.2071, simple_loss=0.277, pruned_loss=0.06858, over 7274.00 frames.], tot_loss[loss=0.184, simple_loss=0.2708, pruned_loss=0.04861, over 1429279.41 frames.], batch size: 17, lr: 2.52e-04
2022-05-28 07:34:25,516 INFO [train.py:842] (3/4) Epoch 22, batch 2100, loss[loss=0.1897, simple_loss=0.2647, pruned_loss=0.05737, over 7411.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2708, pruned_loss=0.04842, over 1428096.28 frames.], batch size: 18, lr: 2.52e-04
2022-05-28 07:35:03,406 INFO [train.py:842] (3/4) Epoch 22, batch 2150, loss[loss=0.148, simple_loss=0.2327, pruned_loss=0.03165, over 7165.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2716, pruned_loss=0.049, over 1424129.54 frames.], batch size: 18, lr: 2.52e-04
2022-05-28 07:35:41,682 INFO [train.py:842] (3/4) Epoch 22, batch 2200, loss[loss=0.2006, simple_loss=0.2929, pruned_loss=0.05412, over 7119.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2701, pruned_loss=0.04804, over 1426686.32 frames.], batch size: 21, lr: 2.52e-04
2022-05-28 07:36:19,635 INFO [train.py:842] (3/4) Epoch 22, batch 2250, loss[loss=0.1657, simple_loss=0.2418, pruned_loss=0.04479, over 7241.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2697, pruned_loss=0.04769, over 1424370.14 frames.], batch size: 16, lr: 2.52e-04
2022-05-28 07:36:57,806 INFO [train.py:842] (3/4) Epoch 22, batch 2300, loss[loss=0.2415, simple_loss=0.3204, pruned_loss=0.08133, over 5423.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2704, pruned_loss=0.04843, over 1425976.56 frames.], batch size: 52, lr: 2.52e-04
2022-05-28 07:37:35,873 INFO [train.py:842] (3/4) Epoch 22, batch 2350, loss[loss=0.1857, simple_loss=0.2819, pruned_loss=0.04482, over 6543.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2694, pruned_loss=0.04767, over 1427633.35 frames.], batch size: 38, lr: 2.52e-04
2022-05-28 07:38:14,399 INFO [train.py:842] (3/4) Epoch 22, batch 2400, loss[loss=0.1956, simple_loss=0.2711, pruned_loss=0.06006, over 7142.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2678, pruned_loss=0.04738, over 1426544.63 frames.], batch size: 17, lr: 2.51e-04
2022-05-28 07:38:52,298 INFO [train.py:842] (3/4) Epoch 22, batch 2450, loss[loss=0.1585, simple_loss=0.2407, pruned_loss=0.03812, over 7254.00 frames.], tot_loss[loss=0.182, simple_loss=0.2684, pruned_loss=0.04782, over 1424532.43 frames.], batch size: 17, lr: 2.51e-04
2022-05-28 07:39:30,631 INFO [train.py:842] (3/4) Epoch 22, batch 2500, loss[loss=0.1678, simple_loss=0.2588, pruned_loss=0.03843, over 7393.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2677, pruned_loss=0.04747, over 1421524.63 frames.], batch size: 21, lr: 2.51e-04
2022-05-28 07:40:08,490 INFO [train.py:842] (3/4) Epoch 22, batch 2550, loss[loss=0.1375, simple_loss=0.2231, pruned_loss=0.02593, over 7065.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2682, pruned_loss=0.04802, over 1420859.51 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:40:46,518 INFO [train.py:842] (3/4) Epoch 22, batch 2600, loss[loss=0.1734, simple_loss=0.2585, pruned_loss=0.04415, over 7146.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2703, pruned_loss=0.04855, over 1417409.84 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:41:24,754 INFO [train.py:842] (3/4) Epoch 22, batch 2650, loss[loss=0.1814, simple_loss=0.2628, pruned_loss=0.04999, over 7253.00 frames.], tot_loss[loss=0.1836, simple_loss=0.27, pruned_loss=0.04867, over 1421535.33 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:42:02,992 INFO [train.py:842] (3/4) Epoch 22, batch 2700, loss[loss=0.2099, simple_loss=0.2962, pruned_loss=0.06174, over 7161.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2699, pruned_loss=0.0486, over 1420334.57 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:42:40,718 INFO [train.py:842] (3/4) Epoch 22, batch 2750, loss[loss=0.1641, simple_loss=0.2561, pruned_loss=0.03606, over 7066.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2694, pruned_loss=0.04814, over 1420299.86 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:43:18,879 INFO [train.py:842] (3/4) Epoch 22, batch 2800, loss[loss=0.15, simple_loss=0.2308, pruned_loss=0.03457, over 7281.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2689, pruned_loss=0.04742, over 1420496.75 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:43:56,995 INFO [train.py:842] (3/4) Epoch 22, batch 2850, loss[loss=0.1804, simple_loss=0.2641, pruned_loss=0.04838, over 7160.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2694, pruned_loss=0.04794, over 1419776.73 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:44:35,188 INFO [train.py:842] (3/4) Epoch 22, batch 2900, loss[loss=0.1886, simple_loss=0.2715, pruned_loss=0.0529, over 7161.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2695, pruned_loss=0.048, over 1422863.28 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:45:13,317 INFO [train.py:842] (3/4) Epoch 22, batch 2950, loss[loss=0.1783, simple_loss=0.2721, pruned_loss=0.04223, over 7419.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2706, pruned_loss=0.04891, over 1422438.83 frames.], batch size: 21, lr: 2.51e-04
2022-05-28 07:45:51,554 INFO [train.py:842] (3/4) Epoch 22, batch 3000, loss[loss=0.1456, simple_loss=0.2405, pruned_loss=0.0253, over 7160.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2689, pruned_loss=0.04764, over 1425799.22 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:45:51,555 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 07:46:00,591 INFO [train.py:871] (3/4) Epoch 22, validation: loss=0.1649, simple_loss=0.2645, pruned_loss=0.03269, over 868885.00 frames.
2022-05-28 07:46:38,624 INFO [train.py:842] (3/4) Epoch 22, batch 3050, loss[loss=0.2113, simple_loss=0.2976, pruned_loss=0.06253, over 7020.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2689, pruned_loss=0.04749, over 1427825.93 frames.], batch size: 28, lr: 2.51e-04
2022-05-28 07:47:17,294 INFO [train.py:842] (3/4) Epoch 22, batch 3100, loss[loss=0.1864, simple_loss=0.2684, pruned_loss=0.05223, over 5079.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2683, pruned_loss=0.04766, over 1428309.58 frames.], batch size: 52, lr: 2.51e-04
2022-05-28 07:47:55,463 INFO [train.py:842] (3/4) Epoch 22, batch 3150, loss[loss=0.1809, simple_loss=0.2791, pruned_loss=0.04132, over 7408.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2685, pruned_loss=0.04764, over 1425821.44 frames.], batch size: 21, lr: 2.51e-04
2022-05-28 07:48:33,865 INFO [train.py:842] (3/4) Epoch 22, batch 3200, loss[loss=0.16, simple_loss=0.2363, pruned_loss=0.04184, over 7066.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2688, pruned_loss=0.0478, over 1427344.83 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:49:11,743 INFO [train.py:842] (3/4) Epoch 22, batch 3250, loss[loss=0.162, simple_loss=0.239, pruned_loss=0.04248, over 6996.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2697, pruned_loss=0.04834, over 1428286.26 frames.], batch size: 16, lr: 2.51e-04
2022-05-28 07:49:49,923 INFO [train.py:842] (3/4) Epoch 22, batch 3300, loss[loss=0.1642, simple_loss=0.257, pruned_loss=0.03573, over 7430.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2705, pruned_loss=0.04835, over 1430446.06 frames.], batch size: 20, lr: 2.51e-04
2022-05-28 07:50:27,870 INFO [train.py:842] (3/4) Epoch 22, batch 3350, loss[loss=0.1611, simple_loss=0.2458, pruned_loss=0.03816, over 7356.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2713, pruned_loss=0.0488, over 1428646.36 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:51:05,911 INFO [train.py:842] (3/4) Epoch 22, batch 3400, loss[loss=0.1764, simple_loss=0.2519, pruned_loss=0.05044, over 7144.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2705, pruned_loss=0.04843, over 1424914.07 frames.], batch size: 17, lr: 2.51e-04
2022-05-28 07:51:43,857 INFO [train.py:842] (3/4) Epoch 22, batch 3450, loss[loss=0.1932, simple_loss=0.2896, pruned_loss=0.04835, over 7337.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2704, pruned_loss=0.04861, over 1426327.70 frames.], batch size: 22, lr: 2.51e-04
2022-05-28 07:52:22,337 INFO [train.py:842] (3/4) Epoch 22, batch 3500, loss[loss=0.1856, simple_loss=0.2792, pruned_loss=0.04598, over 7324.00 frames.], tot_loss[loss=0.1835, simple_loss=0.27, pruned_loss=0.04844, over 1429332.75 frames.], batch size: 22, lr: 2.51e-04
2022-05-28 07:53:00,184 INFO [train.py:842] (3/4) Epoch 22, batch 3550, loss[loss=0.1799, simple_loss=0.2801, pruned_loss=0.03983, over 6794.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2688, pruned_loss=0.04721, over 1426975.39 frames.], batch size: 31, lr: 2.51e-04
2022-05-28 07:53:38,514 INFO [train.py:842] (3/4) Epoch 22, batch 3600, loss[loss=0.1615, simple_loss=0.2454, pruned_loss=0.03878, over 7249.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2684, pruned_loss=0.04761, over 1420980.61 frames.], batch size: 17, lr: 2.51e-04
2022-05-28 07:54:16,519 INFO [train.py:842] (3/4) Epoch 22, batch 3650, loss[loss=0.1645, simple_loss=0.2534, pruned_loss=0.03779, over 7265.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2681, pruned_loss=0.04751, over 1424249.92 frames.], batch size: 19, lr: 2.51e-04
2022-05-28 07:54:54,680 INFO [train.py:842] (3/4) Epoch 22, batch 3700, loss[loss=0.1789, simple_loss=0.2675, pruned_loss=0.04521, over 7137.00 frames.], tot_loss[loss=0.1812, simple_loss=0.268, pruned_loss=0.04726, over 1425365.17 frames.], batch size: 20, lr: 2.51e-04
2022-05-28 07:55:32,502 INFO [train.py:842] (3/4) Epoch 22, batch 3750, loss[loss=0.1547, simple_loss=0.2499, pruned_loss=0.02974, over 7317.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2682, pruned_loss=0.04745, over 1427876.58 frames.], batch size: 24, lr: 2.51e-04
2022-05-28 07:56:11,028 INFO [train.py:842] (3/4) Epoch 22, batch 3800, loss[loss=0.2327, simple_loss=0.3048, pruned_loss=0.08035, over 5000.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2672, pruned_loss=0.0473, over 1425346.12 frames.], batch size: 53, lr: 2.51e-04
2022-05-28 07:56:49,082 INFO [train.py:842] (3/4) Epoch 22, batch 3850, loss[loss=0.222, simple_loss=0.2946, pruned_loss=0.07472, over 7276.00 frames.], tot_loss[loss=0.182, simple_loss=0.2682, pruned_loss=0.04792, over 1426419.36 frames.], batch size: 18, lr: 2.51e-04
2022-05-28 07:57:27,546 INFO [train.py:842] (3/4) Epoch 22, batch 3900, loss[loss=0.2264, simple_loss=0.3065, pruned_loss=0.0732, over 7323.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2685, pruned_loss=0.04799, over 1428833.13 frames.], batch size: 20, lr: 2.51e-04
2022-05-28 07:58:05,561 INFO [train.py:842] (3/4) Epoch 22, batch 3950, loss[loss=0.1986, simple_loss=0.2911, pruned_loss=0.05306, over 7419.00 frames.], tot_loss[loss=0.182, simple_loss=0.268, pruned_loss=0.04802, over 1428186.99 frames.], batch size: 21, lr: 2.50e-04
2022-05-28 07:58:43,890 INFO [train.py:842] (3/4) Epoch 22, batch 4000, loss[loss=0.1756, simple_loss=0.2628, pruned_loss=0.04416, over 6798.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2668, pruned_loss=0.04725, over 1428777.82 frames.], batch size: 31, lr: 2.50e-04
2022-05-28 07:59:21,793 INFO [train.py:842] (3/4) Epoch 22, batch 4050, loss[loss=0.2211, simple_loss=0.3081, pruned_loss=0.06705, over 7411.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2684, pruned_loss=0.04812, over 1426631.44 frames.], batch size: 21, lr: 2.50e-04
2022-05-28 08:00:00,263 INFO [train.py:842] (3/4) Epoch 22, batch 4100, loss[loss=0.1983, simple_loss=0.2955, pruned_loss=0.05059, over 7341.00 frames.], tot_loss[loss=0.1818, simple_loss=0.268, pruned_loss=0.04784, over 1425765.97 frames.], batch size: 22, lr: 2.50e-04
2022-05-28 08:00:38,150 INFO [train.py:842] (3/4) Epoch 22, batch 4150, loss[loss=0.1815, simple_loss=0.2695, pruned_loss=0.04671, over 7334.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2687, pruned_loss=0.04789, over 1427989.76 frames.], batch size: 22, lr: 2.50e-04
2022-05-28 08:01:16,335 INFO [train.py:842] (3/4) Epoch 22, batch 4200, loss[loss=0.2392, simple_loss=0.3213, pruned_loss=0.07853, over 4995.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2688, pruned_loss=0.04817, over 1419791.96 frames.], batch size: 52, lr: 2.50e-04
2022-05-28 08:01:54,114 INFO [train.py:842] (3/4) Epoch 22, batch 4250, loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.05481, over 4752.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2696, pruned_loss=0.04806, over 1415517.75 frames.], batch size: 52, lr: 2.50e-04
2022-05-28 08:02:32,402 INFO [train.py:842] (3/4) Epoch 22, batch 4300, loss[loss=0.1737, simple_loss=0.2464, pruned_loss=0.05046, over 7404.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2694, pruned_loss=0.04779, over 1418119.83 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:03:10,576 INFO [train.py:842] (3/4) Epoch 22, batch 4350, loss[loss=0.1444, simple_loss=0.2284, pruned_loss=0.0302, over 7285.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2683, pruned_loss=0.04739, over 1419160.96 frames.], batch size: 17, lr: 2.50e-04
2022-05-28 08:03:48,879 INFO [train.py:842] (3/4) Epoch 22, batch 4400, loss[loss=0.1842, simple_loss=0.2725, pruned_loss=0.04798, over 7327.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2692, pruned_loss=0.04764, over 1420295.92 frames.], batch size: 21, lr: 2.50e-04
2022-05-28 08:04:26,822 INFO [train.py:842] (3/4) Epoch 22, batch 4450, loss[loss=0.2014, simple_loss=0.2884, pruned_loss=0.05722, over 7279.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2697, pruned_loss=0.0478, over 1416820.55 frames.], batch size: 24, lr: 2.50e-04
2022-05-28 08:05:05,057 INFO [train.py:842] (3/4) Epoch 22, batch 4500, loss[loss=0.1998, simple_loss=0.285, pruned_loss=0.05734, over 7398.00 frames.], tot_loss[loss=0.184, simple_loss=0.2708, pruned_loss=0.04863, over 1419344.42 frames.], batch size: 23, lr: 2.50e-04
2022-05-28 08:05:43,127 INFO [train.py:842] (3/4) Epoch 22, batch 4550, loss[loss=0.1798, simple_loss=0.2581, pruned_loss=0.05078, over 7158.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2708, pruned_loss=0.04867, over 1420185.37 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:06:21,015 INFO [train.py:842] (3/4) Epoch 22, batch 4600, loss[loss=0.1769, simple_loss=0.2698, pruned_loss=0.04202, over 7232.00 frames.], tot_loss[loss=0.185, simple_loss=0.272, pruned_loss=0.04896, over 1420088.71 frames.], batch size: 20, lr: 2.50e-04
2022-05-28 08:06:58,737 INFO [train.py:842] (3/4) Epoch 22, batch 4650, loss[loss=0.1659, simple_loss=0.2446, pruned_loss=0.04363, over 7063.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2712, pruned_loss=0.04848, over 1417121.33 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:07:37,057 INFO [train.py:842] (3/4) Epoch 22, batch 4700, loss[loss=0.1732, simple_loss=0.2583, pruned_loss=0.04407, over 7353.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2705, pruned_loss=0.04793, over 1418250.42 frames.], batch size: 19, lr: 2.50e-04
2022-05-28 08:08:15,476 INFO [train.py:842] (3/4) Epoch 22, batch 4750, loss[loss=0.1818, simple_loss=0.2629, pruned_loss=0.05035, over 7273.00 frames.], tot_loss[loss=0.182, simple_loss=0.2685, pruned_loss=0.04772, over 1423267.77 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:08:53,587 INFO [train.py:842] (3/4) Epoch 22, batch 4800, loss[loss=0.2062, simple_loss=0.2836, pruned_loss=0.06438, over 4995.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2705, pruned_loss=0.04889, over 1418113.78 frames.], batch size: 52, lr: 2.50e-04
2022-05-28 08:09:31,589 INFO [train.py:842] (3/4) Epoch 22, batch 4850, loss[loss=0.202, simple_loss=0.2993, pruned_loss=0.05236, over 7128.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2706, pruned_loss=0.04903, over 1420783.17 frames.], batch size: 21, lr: 2.50e-04
2022-05-28 08:10:09,781 INFO [train.py:842] (3/4) Epoch 22, batch 4900, loss[loss=0.2197, simple_loss=0.303, pruned_loss=0.06814, over 7220.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2717, pruned_loss=0.0493, over 1419288.79 frames.], batch size: 23, lr: 2.50e-04
2022-05-28 08:10:47,874 INFO [train.py:842] (3/4) Epoch 22, batch 4950, loss[loss=0.1534, simple_loss=0.2484, pruned_loss=0.02919, over 7252.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2697, pruned_loss=0.0483, over 1415237.60 frames.], batch size: 19, lr: 2.50e-04
2022-05-28 08:11:25,840 INFO [train.py:842] (3/4) Epoch 22, batch 5000, loss[loss=0.1848, simple_loss=0.2764, pruned_loss=0.04655, over 6408.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2699, pruned_loss=0.04823, over 1412762.99 frames.], batch size: 38, lr: 2.50e-04
2022-05-28 08:12:03,913 INFO [train.py:842] (3/4) Epoch 22, batch 5050, loss[loss=0.178, simple_loss=0.2575, pruned_loss=0.04928, over 7410.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2706, pruned_loss=0.04834, over 1415853.92 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:12:42,395 INFO [train.py:842] (3/4) Epoch 22, batch 5100, loss[loss=0.1937, simple_loss=0.295, pruned_loss=0.04618, over 7319.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2703, pruned_loss=0.04841, over 1419897.54 frames.], batch size: 21, lr: 2.50e-04
2022-05-28 08:13:20,360 INFO [train.py:842] (3/4) Epoch 22, batch 5150, loss[loss=0.1931, simple_loss=0.2807, pruned_loss=0.05272, over 7331.00 frames.], tot_loss[loss=0.184, simple_loss=0.2711, pruned_loss=0.04843, over 1425836.08 frames.], batch size: 22, lr: 2.50e-04
2022-05-28 08:13:58,907 INFO [train.py:842] (3/4) Epoch 22, batch 5200, loss[loss=0.1779, simple_loss=0.2704, pruned_loss=0.04275, over 7322.00 frames.], tot_loss[loss=0.1835, simple_loss=0.27, pruned_loss=0.04851, over 1424475.85 frames.], batch size: 20, lr: 2.50e-04
2022-05-28 08:14:36,960 INFO [train.py:842] (3/4) Epoch 22, batch 5250, loss[loss=0.1787, simple_loss=0.279, pruned_loss=0.03916, over 7090.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2694, pruned_loss=0.0484, over 1420660.48 frames.], batch size: 28, lr: 2.50e-04
2022-05-28 08:15:14,911 INFO [train.py:842] (3/4) Epoch 22, batch 5300, loss[loss=0.2056, simple_loss=0.297, pruned_loss=0.05712, over 7330.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2713, pruned_loss=0.04901, over 1421280.84 frames.], batch size: 22, lr: 2.50e-04
2022-05-28 08:15:52,748 INFO [train.py:842] (3/4) Epoch 22, batch 5350, loss[loss=0.2048, simple_loss=0.2938, pruned_loss=0.05786, over 6757.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2712, pruned_loss=0.04881, over 1422930.86 frames.], batch size: 31, lr: 2.50e-04
2022-05-28 08:16:30,993 INFO [train.py:842] (3/4) Epoch 22, batch 5400, loss[loss=0.1611, simple_loss=0.2399, pruned_loss=0.04114, over 7066.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2711, pruned_loss=0.04872, over 1423929.06 frames.], batch size: 18, lr: 2.50e-04
2022-05-28 08:17:09,164 INFO [train.py:842] (3/4) Epoch 22, batch 5450, loss[loss=0.1803, simple_loss=0.2499, pruned_loss=0.05529, over 7430.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2715, pruned_loss=0.04877, over 1425005.31 frames.], batch size: 20, lr: 2.50e-04
2022-05-28 08:17:47,423 INFO [train.py:842] (3/4) Epoch 22, batch 5500, loss[loss=0.175, simple_loss=0.2726, pruned_loss=0.03867, over 7413.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2715, pruned_loss=0.04868, over 1423058.00 frames.], batch size: 21, lr: 2.49e-04
2022-05-28 08:18:25,320 INFO [train.py:842] (3/4) Epoch 22, batch 5550, loss[loss=0.1885, simple_loss=0.2701, pruned_loss=0.05344, over 7150.00 frames.], tot_loss[loss=0.1841, simple_loss=0.271, pruned_loss=0.04863, over 1420542.35 frames.], batch size: 18, lr: 2.49e-04
2022-05-28 08:19:03,353 INFO [train.py:842] (3/4) Epoch 22, batch 5600, loss[loss=0.2041, simple_loss=0.2863, pruned_loss=0.06093, over 7158.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2718, pruned_loss=0.04901, over 1421131.09 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:19:41,118 INFO [train.py:842] (3/4) Epoch 22, batch 5650, loss[loss=0.182, simple_loss=0.2718, pruned_loss=0.04606, over 7353.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2715, pruned_loss=0.04908, over 1419631.15 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:20:19,524 INFO [train.py:842] (3/4) Epoch 22, batch 5700, loss[loss=0.1728, simple_loss=0.267, pruned_loss=0.0393, over 7342.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2699, pruned_loss=0.04818, over 1425219.97 frames.], batch size: 22, lr: 2.49e-04
2022-05-28 08:20:57,467 INFO [train.py:842] (3/4) Epoch 22, batch 5750, loss[loss=0.1949, simple_loss=0.2747, pruned_loss=0.05755, over 7408.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2706, pruned_loss=0.04842, over 1427243.16 frames.], batch size: 18, lr: 2.49e-04
2022-05-28 08:21:35,779 INFO [train.py:842] (3/4) Epoch 22, batch 5800, loss[loss=0.1533, simple_loss=0.24, pruned_loss=0.03335, over 7115.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2696, pruned_loss=0.04836, over 1428023.97 frames.], batch size: 17, lr: 2.49e-04
2022-05-28 08:22:13,665 INFO [train.py:842] (3/4) Epoch 22, batch 5850, loss[loss=0.2043, simple_loss=0.2984, pruned_loss=0.05515, over 7284.00 frames.], tot_loss[loss=0.184, simple_loss=0.2708, pruned_loss=0.04861, over 1429835.92 frames.], batch size: 24, lr: 2.49e-04
2022-05-28 08:22:52,083 INFO [train.py:842] (3/4) Epoch 22, batch 5900, loss[loss=0.1674, simple_loss=0.25, pruned_loss=0.04237, over 7200.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2695, pruned_loss=0.04801, over 1432669.85 frames.], batch size: 23, lr: 2.49e-04
2022-05-28 08:23:29,857 INFO [train.py:842] (3/4) Epoch 22, batch 5950, loss[loss=0.1753, simple_loss=0.2603, pruned_loss=0.04515, over 7332.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2699, pruned_loss=0.0479, over 1426658.23 frames.], batch size: 22, lr: 2.49e-04
2022-05-28 08:24:08,111 INFO [train.py:842] (3/4) Epoch 22, batch 6000, loss[loss=0.1463, simple_loss=0.2367, pruned_loss=0.02795, over 7425.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2689, pruned_loss=0.04728, over 1428888.43 frames.], batch size: 18, lr: 2.49e-04
2022-05-28 08:24:08,111 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 08:24:17,058 INFO [train.py:871] (3/4) Epoch 22, validation: loss=0.1664, simple_loss=0.2658, pruned_loss=0.03347, over 868885.00 frames.
2022-05-28 08:24:55,057 INFO [train.py:842] (3/4) Epoch 22, batch 6050, loss[loss=0.1783, simple_loss=0.2523, pruned_loss=0.05218, over 7276.00 frames.], tot_loss[loss=0.1821, simple_loss=0.269, pruned_loss=0.04763, over 1425681.51 frames.], batch size: 17, lr: 2.49e-04
2022-05-28 08:25:33,545 INFO [train.py:842] (3/4) Epoch 22, batch 6100, loss[loss=0.1732, simple_loss=0.2556, pruned_loss=0.04539, over 7153.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2681, pruned_loss=0.04708, over 1426685.73 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:26:11,606 INFO [train.py:842] (3/4) Epoch 22, batch 6150, loss[loss=0.1728, simple_loss=0.2629, pruned_loss=0.04137, over 7072.00 frames.], tot_loss[loss=0.1812, simple_loss=0.268, pruned_loss=0.0472, over 1422436.56 frames.], batch size: 18, lr: 2.49e-04
2022-05-28 08:26:49,991 INFO [train.py:842] (3/4) Epoch 22, batch 6200, loss[loss=0.1852, simple_loss=0.2766, pruned_loss=0.04689, over 7417.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2681, pruned_loss=0.04746, over 1425910.00 frames.], batch size: 21, lr: 2.49e-04
2022-05-28 08:27:27,699 INFO [train.py:842] (3/4) Epoch 22, batch 6250, loss[loss=0.1876, simple_loss=0.2771, pruned_loss=0.049, over 6864.00 frames.], tot_loss[loss=0.1814, simple_loss=0.268, pruned_loss=0.04742, over 1421349.97 frames.], batch size: 31, lr: 2.49e-04
2022-05-28 08:28:05,775 INFO [train.py:842] (3/4) Epoch 22, batch 6300, loss[loss=0.156, simple_loss=0.2595, pruned_loss=0.02625, over 7329.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2688, pruned_loss=0.04744, over 1421101.75 frames.], batch size: 22, lr: 2.49e-04
2022-05-28 08:28:43,779 INFO [train.py:842] (3/4) Epoch 22, batch 6350, loss[loss=0.2453, simple_loss=0.3036, pruned_loss=0.09348, over 4813.00 frames.], tot_loss[loss=0.1819, simple_loss=0.269, pruned_loss=0.04742, over 1422603.77 frames.], batch size: 53, lr: 2.49e-04
2022-05-28 08:29:22,120 INFO [train.py:842] (3/4) Epoch 22, batch 6400, loss[loss=0.1856, simple_loss=0.2675, pruned_loss=0.05185, over 7162.00 frames.], tot_loss[loss=0.183, simple_loss=0.2699, pruned_loss=0.04807, over 1424316.56 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:30:00,142 INFO [train.py:842] (3/4) Epoch 22, batch 6450, loss[loss=0.1528, simple_loss=0.2405, pruned_loss=0.03257, over 7251.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2699, pruned_loss=0.04834, over 1423296.04 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:30:38,599 INFO [train.py:842] (3/4) Epoch 22, batch 6500, loss[loss=0.1369, simple_loss=0.2204, pruned_loss=0.02668, over 7008.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2698, pruned_loss=0.04881, over 1425139.02 frames.], batch size: 16, lr: 2.49e-04
2022-05-28 08:31:16,546 INFO [train.py:842] (3/4) Epoch 22, batch 6550, loss[loss=0.1873, simple_loss=0.2698, pruned_loss=0.05243, over 7062.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2695, pruned_loss=0.04832, over 1421806.06 frames.], batch size: 18, lr: 2.49e-04
2022-05-28 08:31:54,818 INFO [train.py:842] (3/4) Epoch 22, batch 6600, loss[loss=0.2576, simple_loss=0.3251, pruned_loss=0.09506, over 7269.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2698, pruned_loss=0.04862, over 1418420.26 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:32:32,835 INFO [train.py:842] (3/4) Epoch 22, batch 6650, loss[loss=0.1553, simple_loss=0.2493, pruned_loss=0.03062, over 7330.00 frames.], tot_loss[loss=0.182, simple_loss=0.2687, pruned_loss=0.04767, over 1421995.97 frames.], batch size: 22, lr: 2.49e-04
2022-05-28 08:33:11,312 INFO [train.py:842] (3/4) Epoch 22, batch 6700, loss[loss=0.139, simple_loss=0.2375, pruned_loss=0.02024, over 7258.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2684, pruned_loss=0.04768, over 1425793.94 frames.], batch size: 19, lr: 2.49e-04
2022-05-28 08:33:49,378 INFO [train.py:842] (3/4) Epoch 22, batch 6750, loss[loss=0.1798, simple_loss=0.2608, pruned_loss=0.04935, over 7234.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2682, pruned_loss=0.04762, over 1424770.31 frames.], batch size: 20, lr: 2.49e-04
2022-05-28 08:34:27,419 INFO [train.py:842] (3/4) Epoch 22, batch 6800, loss[loss=0.1785, simple_loss=0.2678, pruned_loss=0.04458, over 6409.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2693, pruned_loss=0.04799, over 1422108.72 frames.], batch size: 38, lr: 2.49e-04
2022-05-28 08:35:05,260 INFO [train.py:842] (3/4) Epoch 22, batch 6850, loss[loss=0.1831, simple_loss=0.27, pruned_loss=0.04809, over 7290.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2696, pruned_loss=0.04776, over 1420271.28 frames.], batch size: 24, lr: 2.49e-04
2022-05-28 08:35:43,337 INFO [train.py:842] (3/4) Epoch 22, batch 6900, loss[loss=0.1651, simple_loss=0.2568, pruned_loss=0.03672, over 7213.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2702, pruned_loss=0.04834, over 1416566.34 frames.], batch size: 21, lr: 2.49e-04
2022-05-28 08:36:21,225 INFO [train.py:842] (3/4) Epoch 22, batch 6950, loss[loss=0.1812, simple_loss=0.2619, pruned_loss=0.05028, over 7433.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2706, pruned_loss=0.04896, over 1413745.41 frames.], batch size: 20, lr: 2.49e-04
2022-05-28 08:37:02,026 INFO [train.py:842] (3/4) Epoch 22, batch 7000, loss[loss=0.1656, simple_loss=0.2585, pruned_loss=0.03639, over 7320.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2709, pruned_loss=0.04927, over 1416011.97 frames.], batch size: 21, lr: 2.49e-04
2022-05-28 08:37:39,802 INFO [train.py:842] (3/4) Epoch 22, batch 7050, loss[loss=0.2257, simple_loss=0.3102, pruned_loss=0.07065, over 7299.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2711, pruned_loss=0.04916, over 1417651.71 frames.], batch size: 24, lr: 2.49e-04
2022-05-28 08:38:17,977 INFO [train.py:842] (3/4) Epoch 22, batch 7100, loss[loss=0.166, simple_loss=0.2404, pruned_loss=0.04577, over 6970.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2711, pruned_loss=0.04911, over 1418955.82 frames.], batch size: 16, lr: 2.49e-04
2022-05-28 08:38:55,915 INFO [train.py:842] (3/4) Epoch 22, batch 7150, loss[loss=0.1562, simple_loss=0.2397, pruned_loss=0.03639, over 7415.00 frames.], tot_loss[loss=0.184, simple_loss=0.271, pruned_loss=0.04855, over 1417960.26 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:39:34,207 INFO [train.py:842] (3/4) Epoch 22, batch 7200, loss[loss=0.1746, simple_loss=0.2708, pruned_loss=0.03919, over 7229.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2711, pruned_loss=0.04853, over 1411160.94 frames.], batch size: 20, lr: 2.48e-04
2022-05-28 08:40:12,378 INFO [train.py:842] (3/4) Epoch 22, batch 7250, loss[loss=0.2198, simple_loss=0.3119, pruned_loss=0.06388, over 7215.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2707, pruned_loss=0.04846, over 1415635.85 frames.], batch size: 23, lr: 2.48e-04
2022-05-28 08:40:50,464 INFO [train.py:842] (3/4) Epoch 22, batch 7300, loss[loss=0.1593, simple_loss=0.2389, pruned_loss=0.03989, over 7290.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2696, pruned_loss=0.04759, over 1413287.88 frames.], batch size: 17, lr: 2.48e-04
2022-05-28 08:41:28,167 INFO [train.py:842] (3/4) Epoch 22, batch 7350, loss[loss=0.2049, simple_loss=0.301, pruned_loss=0.05437, over 7149.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2719, pruned_loss=0.04855, over 1416267.74 frames.], batch size: 20, lr: 2.48e-04
2022-05-28 08:42:06,484 INFO [train.py:842] (3/4) Epoch 22, batch 7400, loss[loss=0.1843, simple_loss=0.2854, pruned_loss=0.04159, over 7273.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2724, pruned_loss=0.04886, over 1418342.39 frames.], batch size: 25, lr: 2.48e-04
2022-05-28 08:42:44,752 INFO [train.py:842] (3/4) Epoch 22, batch 7450, loss[loss=0.1795, simple_loss=0.2612, pruned_loss=0.04892, over 7143.00 frames.], tot_loss[loss=0.185, simple_loss=0.2715, pruned_loss=0.04922, over 1418005.96 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:43:22,942 INFO [train.py:842] (3/4) Epoch 22, batch 7500, loss[loss=0.1576, simple_loss=0.2529, pruned_loss=0.03116, over 7406.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2714, pruned_loss=0.04911, over 1419557.53 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:44:01,053 INFO [train.py:842] (3/4) Epoch 22, batch 7550, loss[loss=0.2235, simple_loss=0.3088, pruned_loss=0.06912, over 7207.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2696, pruned_loss=0.04861, over 1417686.74 frames.], batch size: 23, lr: 2.48e-04
2022-05-28 08:44:39,280 INFO [train.py:842] (3/4) Epoch 22, batch 7600, loss[loss=0.2094, simple_loss=0.3023, pruned_loss=0.05828, over 7203.00 frames.], tot_loss[loss=0.183, simple_loss=0.2691, pruned_loss=0.04843, over 1418553.43 frames.], batch size: 22, lr: 2.48e-04
2022-05-28 08:45:17,063 INFO [train.py:842] (3/4) Epoch 22, batch 7650, loss[loss=0.2092, simple_loss=0.306, pruned_loss=0.05621, over 7329.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2701, pruned_loss=0.04835, over 1419805.82 frames.], batch size: 20, lr: 2.48e-04
2022-05-28 08:45:55,437 INFO [train.py:842] (3/4) Epoch 22, batch 7700, loss[loss=0.1781, simple_loss=0.2743, pruned_loss=0.0409, over 7225.00 frames.], tot_loss[loss=0.183, simple_loss=0.2697, pruned_loss=0.04817, over 1420959.54 frames.], batch size: 21, lr: 2.48e-04
2022-05-28 08:46:33,284 INFO [train.py:842] (3/4) Epoch 22, batch 7750, loss[loss=0.1866, simple_loss=0.2895, pruned_loss=0.04191, over 7150.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2707, pruned_loss=0.04873, over 1423814.46 frames.], batch size: 20, lr: 2.48e-04
2022-05-28 08:47:11,747 INFO [train.py:842] (3/4) Epoch 22, batch 7800, loss[loss=0.2029, simple_loss=0.2943, pruned_loss=0.05577, over 7271.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2703, pruned_loss=0.04861, over 1420259.22 frames.], batch size: 25, lr: 2.48e-04
2022-05-28 08:47:49,720 INFO [train.py:842] (3/4) Epoch 22, batch 7850, loss[loss=0.2154, simple_loss=0.2991, pruned_loss=0.0658, over 7276.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2702, pruned_loss=0.04875, over 1419626.03 frames.], batch size: 25, lr: 2.48e-04
2022-05-28 08:48:27,745 INFO [train.py:842] (3/4) Epoch 22, batch 7900, loss[loss=0.1563, simple_loss=0.2481, pruned_loss=0.03225, over 7058.00 frames.], tot_loss[loss=0.1846, simple_loss=0.271, pruned_loss=0.04913, over 1413889.82 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:49:05,729 INFO [train.py:842] (3/4) Epoch 22, batch 7950, loss[loss=0.1872, simple_loss=0.2757, pruned_loss=0.04932, over 7310.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2704, pruned_loss=0.04876, over 1412541.66 frames.], batch size: 25, lr: 2.48e-04
2022-05-28 08:49:43,862 INFO [train.py:842] (3/4) Epoch 22, batch 8000, loss[loss=0.2122, simple_loss=0.2967, pruned_loss=0.06384, over 7053.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2722, pruned_loss=0.04967, over 1413579.36 frames.], batch size: 28, lr: 2.48e-04
2022-05-28 08:50:21,591 INFO [train.py:842] (3/4) Epoch 22, batch 8050, loss[loss=0.1539, simple_loss=0.236, pruned_loss=0.03586, over 7000.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2732, pruned_loss=0.05019, over 1410365.28 frames.], batch size: 16, lr: 2.48e-04
2022-05-28 08:50:59,778 INFO [train.py:842] (3/4) Epoch 22, batch 8100, loss[loss=0.2726, simple_loss=0.338, pruned_loss=0.1036, over 7067.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2736, pruned_loss=0.051, over 1406892.15 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:51:37,740 INFO [train.py:842] (3/4) Epoch 22, batch 8150, loss[loss=0.1376, simple_loss=0.2206, pruned_loss=0.02729, over 7298.00 frames.], tot_loss[loss=0.187, simple_loss=0.2732, pruned_loss=0.05039, over 1412123.61 frames.], batch size: 17, lr: 2.48e-04
2022-05-28 08:52:15,704 INFO [train.py:842] (3/4) Epoch 22, batch 8200, loss[loss=0.1872, simple_loss=0.2861, pruned_loss=0.04411, over 6662.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2731, pruned_loss=0.04967, over 1416167.13 frames.], batch size: 38, lr: 2.48e-04
2022-05-28 08:52:53,589 INFO [train.py:842] (3/4) Epoch 22, batch 8250, loss[loss=0.1659, simple_loss=0.2622, pruned_loss=0.0348, over 7068.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2732, pruned_loss=0.04998, over 1416798.93 frames.], batch size: 28, lr: 2.48e-04
2022-05-28 08:53:31,683 INFO [train.py:842] (3/4) Epoch 22, batch 8300, loss[loss=0.2074, simple_loss=0.2994, pruned_loss=0.05768, over 7299.00 frames.], tot_loss[loss=0.185, simple_loss=0.2721, pruned_loss=0.04897, over 1417992.20 frames.], batch size: 24, lr: 2.48e-04
2022-05-28 08:54:09,573 INFO [train.py:842] (3/4) Epoch 22, batch 8350, loss[loss=0.1995, simple_loss=0.2842, pruned_loss=0.05737, over 7224.00 frames.], tot_loss[loss=0.187, simple_loss=0.2737, pruned_loss=0.05014, over 1419983.89 frames.], batch size: 21, lr: 2.48e-04
2022-05-28 08:54:47,768 INFO [train.py:842] (3/4) Epoch 22, batch 8400, loss[loss=0.1885, simple_loss=0.2864, pruned_loss=0.04532, over 7223.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2735, pruned_loss=0.04975, over 1421520.55 frames.], batch size: 21, lr: 2.48e-04
2022-05-28 08:55:25,643 INFO [train.py:842] (3/4) Epoch 22, batch 8450, loss[loss=0.2269, simple_loss=0.3058, pruned_loss=0.07398, over 7320.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2727, pruned_loss=0.04955, over 1417617.24 frames.], batch size: 20, lr: 2.48e-04
2022-05-28 08:56:03,904 INFO [train.py:842] (3/4) Epoch 22, batch 8500, loss[loss=0.1446, simple_loss=0.2295, pruned_loss=0.0299, over 7004.00 frames.], tot_loss[loss=0.1851, simple_loss=0.272, pruned_loss=0.04913, over 1419725.56 frames.], batch size: 16, lr: 2.48e-04
2022-05-28 08:56:41,571 INFO [train.py:842] (3/4) Epoch 22, batch 8550, loss[loss=0.2602, simple_loss=0.3354, pruned_loss=0.0925, over 7302.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2732, pruned_loss=0.04922, over 1415684.43 frames.], batch size: 25, lr: 2.48e-04
2022-05-28 08:57:19,539 INFO [train.py:842] (3/4) Epoch 22, batch 8600, loss[loss=0.2536, simple_loss=0.3388, pruned_loss=0.08418, over 7275.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2734, pruned_loss=0.04899, over 1417932.65 frames.], batch size: 24, lr: 2.48e-04
2022-05-28 08:57:57,120 INFO [train.py:842] (3/4) Epoch 22, batch 8650, loss[loss=0.1793, simple_loss=0.2687, pruned_loss=0.04488, over 7153.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2743, pruned_loss=0.05, over 1410534.14 frames.], batch size: 18, lr: 2.48e-04
2022-05-28 08:58:35,191 INFO [train.py:842] (3/4) Epoch 22, batch 8700, loss[loss=0.2072, simple_loss=0.2873, pruned_loss=0.06349, over 7361.00 frames.], tot_loss[loss=0.187, simple_loss=0.2742, pruned_loss=0.04991, over 1410418.34 frames.], batch size: 19, lr: 2.48e-04
2022-05-28 08:59:13,001 INFO [train.py:842] (3/4) Epoch 22, batch 8750, loss[loss=0.2063, simple_loss=0.3068, pruned_loss=0.05287, over 7341.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2731, pruned_loss=0.04922, over 1413348.58 frames.], batch size: 22, lr: 2.47e-04
2022-05-28 08:59:50,900 INFO [train.py:842] (3/4) Epoch 22, batch 8800, loss[loss=0.1587, simple_loss=0.2491, pruned_loss=0.03414, over 7165.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2733, pruned_loss=0.04895, over 1411089.91 frames.], batch size: 18, lr: 2.47e-04
2022-05-28 09:00:28,604 INFO [train.py:842] (3/4) Epoch 22, batch 8850, loss[loss=0.1667, simple_loss=0.2533, pruned_loss=0.04007, over 7426.00 frames.], tot_loss[loss=0.186, simple_loss=0.2735, pruned_loss=0.04926, over 1409134.15 frames.], batch size: 20, lr: 2.47e-04
2022-05-28 09:01:06,629 INFO [train.py:842] (3/4) Epoch 22, batch 8900, loss[loss=0.1938, simple_loss=0.2804, pruned_loss=0.05362, over 7233.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2726, pruned_loss=0.04875, over 1411516.74 frames.], batch size: 20, lr: 2.47e-04
2022-05-28 09:01:44,254 INFO [train.py:842] (3/4) Epoch 22, batch 8950, loss[loss=0.1733, simple_loss=0.272, pruned_loss=0.03733, over 7311.00 frames.], tot_loss[loss=0.1856, simple_loss=0.273, pruned_loss=0.04915, over 1406064.72 frames.], batch size: 25, lr: 2.47e-04
2022-05-28 09:02:22,236 INFO [train.py:842] (3/4) Epoch 22, batch 9000, loss[loss=0.1743, simple_loss=0.2433, pruned_loss=0.05262, over 6994.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2728, pruned_loss=0.0492, over 1400287.39 frames.], batch size: 16, lr: 2.47e-04
2022-05-28 09:02:22,236 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 09:02:31,315 INFO [train.py:871] (3/4) Epoch 22, validation: loss=0.1647, simple_loss=0.2634, pruned_loss=0.03302, over 868885.00 frames.
2022-05-28 09:03:08,933 INFO [train.py:842] (3/4) Epoch 22, batch 9050, loss[loss=0.2178, simple_loss=0.2907, pruned_loss=0.07242, over 5045.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2724, pruned_loss=0.04958, over 1393435.17 frames.], batch size: 52, lr: 2.47e-04
2022-05-28 09:03:46,327 INFO [train.py:842] (3/4) Epoch 22, batch 9100, loss[loss=0.255, simple_loss=0.3316, pruned_loss=0.08923, over 5015.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2733, pruned_loss=0.05005, over 1368518.42 frames.], batch size: 52, lr: 2.47e-04
2022-05-28 09:04:23,086 INFO [train.py:842] (3/4) Epoch 22, batch 9150, loss[loss=0.2378, simple_loss=0.3145, pruned_loss=0.08052, over 5114.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2773, pruned_loss=0.05329, over 1287802.86 frames.], batch size: 52, lr: 2.47e-04
2022-05-28 09:05:08,936 INFO [train.py:842] (3/4) Epoch 23, batch 0, loss[loss=0.152, simple_loss=0.2413, pruned_loss=0.03133, over 7229.00 frames.], tot_loss[loss=0.152, simple_loss=0.2413, pruned_loss=0.03133, over 7229.00 frames.], batch size: 16, lr: 2.42e-04
2022-05-28 09:05:47,167 INFO [train.py:842] (3/4) Epoch 23, batch 50, loss[loss=0.2563, simple_loss=0.338, pruned_loss=0.08725, over 7161.00 frames.], tot_loss[loss=0.181, simple_loss=0.2689, pruned_loss=0.04654, over 318706.86 frames.], batch size: 19, lr: 2.42e-04
2022-05-28 09:06:25,605 INFO [train.py:842] (3/4) Epoch 23, batch 100, loss[loss=0.1815, simple_loss=0.2602, pruned_loss=0.05137, over 7277.00 frames.], tot_loss[loss=0.18, simple_loss=0.2674, pruned_loss=0.04636, over 565444.09 frames.], batch size: 18, lr: 2.42e-04
2022-05-28 09:07:03,396 INFO [train.py:842] (3/4) Epoch 23, batch 150, loss[loss=0.2201, simple_loss=0.3111, pruned_loss=0.06454, over 7319.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2708, pruned_loss=0.04786, over 752077.37 frames.], batch size: 24, lr: 2.42e-04
2022-05-28 09:07:41,561 INFO [train.py:842] (3/4) Epoch 23, batch 200, loss[loss=0.2343, simple_loss=0.305, pruned_loss=0.08183, over 6374.00 frames.], tot_loss[loss=0.1825, simple_loss=0.27, pruned_loss=0.04745, over 900573.92 frames.], batch size: 38, lr: 2.42e-04
2022-05-28 09:08:19,374 INFO [train.py:842] (3/4) Epoch 23, batch 250, loss[loss=0.2092, simple_loss=0.307, pruned_loss=0.05572, over 7192.00 frames.], tot_loss[loss=0.1833, simple_loss=0.271, pruned_loss=0.04781, over 1016726.77 frames.], batch size: 23, lr: 2.42e-04
2022-05-28 09:08:57,670 INFO [train.py:842] (3/4) Epoch 23, batch 300, loss[loss=0.2043, simple_loss=0.282, pruned_loss=0.06324, over 7155.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2706, pruned_loss=0.04785, over 1102381.87 frames.], batch size: 19, lr: 2.42e-04
2022-05-28 09:09:35,675 INFO [train.py:842] (3/4) Epoch 23, batch 350, loss[loss=0.1586, simple_loss=0.2605, pruned_loss=0.02831, over 7335.00 frames.], tot_loss[loss=0.1808, simple_loss=0.268, pruned_loss=0.04676, over 1177644.79 frames.], batch size: 22, lr: 2.42e-04
2022-05-28 09:10:13,904 INFO [train.py:842] (3/4) Epoch 23, batch 400, loss[loss=0.1916, simple_loss=0.2815, pruned_loss=0.05081, over 7185.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2685, pruned_loss=0.04704, over 1231178.73 frames.], batch size: 23, lr: 2.42e-04
2022-05-28 09:10:51,795 INFO [train.py:842] (3/4) Epoch 23, batch 450, loss[loss=0.1973, simple_loss=0.2966, pruned_loss=0.04903, over 7302.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2696, pruned_loss=0.04761, over 1271394.39 frames.], batch size: 24, lr: 2.42e-04
2022-05-28 09:11:30,074 INFO [train.py:842] (3/4) Epoch 23, batch 500, loss[loss=0.1467, simple_loss=0.22, pruned_loss=0.03665, over 6780.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2691, pruned_loss=0.04692, over 1306582.28 frames.], batch size: 15, lr: 2.42e-04
2022-05-28 09:12:08,365 INFO [train.py:842] (3/4) Epoch 23, batch 550, loss[loss=0.2023, simple_loss=0.292, pruned_loss=0.0563, over 7277.00 frames.], tot_loss[loss=0.1814, simple_loss=0.269, pruned_loss=0.04689, over 1336193.53 frames.], batch size: 24, lr: 2.42e-04
2022-05-28 09:12:46,595 INFO [train.py:842] (3/4) Epoch 23, batch 600, loss[loss=0.1802, simple_loss=0.2696, pruned_loss=0.04544, over 7135.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2704, pruned_loss=0.04807, over 1359246.51 frames.], batch size: 21, lr: 2.42e-04
2022-05-28 09:13:24,496 INFO [train.py:842] (3/4) Epoch 23, batch 650, loss[loss=0.1873, simple_loss=0.2716, pruned_loss=0.05151, over 6878.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2705, pruned_loss=0.04826, over 1374132.62 frames.], batch size: 32, lr: 2.42e-04
2022-05-28 09:14:02,712 INFO [train.py:842] (3/4) Epoch 23, batch 700, loss[loss=0.1753, simple_loss=0.2619, pruned_loss=0.04433, over 4626.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2709, pruned_loss=0.04806, over 1379729.23 frames.], batch size: 52, lr: 2.42e-04
2022-05-28 09:14:40,551 INFO [train.py:842] (3/4) Epoch 23, batch 750, loss[loss=0.2242, simple_loss=0.2984, pruned_loss=0.07496, over 7184.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2714, pruned_loss=0.0484, over 1390476.36 frames.], batch size: 23, lr: 2.41e-04
2022-05-28 09:15:18,802 INFO [train.py:842] (3/4) Epoch 23, batch 800, loss[loss=0.1745, simple_loss=0.2622, pruned_loss=0.04336, over 7363.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2699, pruned_loss=0.04742, over 1395507.21 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:16:05,932 INFO [train.py:842] (3/4) Epoch 23, batch 850, loss[loss=0.1766, simple_loss=0.2668, pruned_loss=0.04322, over 7434.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2698, pruned_loss=0.04745, over 1403489.26 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:16:44,112 INFO [train.py:842] (3/4) Epoch 23, batch 900, loss[loss=0.2031, simple_loss=0.2841, pruned_loss=0.06104, over 7157.00 frames.], tot_loss[loss=0.1824, simple_loss=0.27, pruned_loss=0.04739, over 1407883.45 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:17:21,905 INFO [train.py:842] (3/4) Epoch 23, batch 950, loss[loss=0.2813, simple_loss=0.349, pruned_loss=0.1068, over 6987.00 frames.], tot_loss[loss=0.183, simple_loss=0.2706, pruned_loss=0.04768, over 1410308.56 frames.], batch size: 28, lr: 2.41e-04
2022-05-28 09:18:00,188 INFO [train.py:842] (3/4) Epoch 23, batch 1000, loss[loss=0.1551, simple_loss=0.2397, pruned_loss=0.03523, over 7349.00 frames.], tot_loss[loss=0.1836, simple_loss=0.271, pruned_loss=0.04805, over 1417248.95 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:18:38,356 INFO [train.py:842] (3/4) Epoch 23, batch 1050, loss[loss=0.2123, simple_loss=0.2908, pruned_loss=0.06691, over 5096.00 frames.], tot_loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04802, over 1418238.38 frames.], batch size: 52, lr: 2.41e-04
2022-05-28 09:19:16,284 INFO [train.py:842] (3/4) Epoch 23, batch 1100, loss[loss=0.1332, simple_loss=0.222, pruned_loss=0.02221, over 7276.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2701, pruned_loss=0.048, over 1418350.17 frames.], batch size: 17, lr: 2.41e-04
2022-05-28 09:19:54,205 INFO [train.py:842] (3/4) Epoch 23, batch 1150, loss[loss=0.1623, simple_loss=0.2514, pruned_loss=0.03662, over 7436.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2708, pruned_loss=0.04805, over 1422228.79 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:20:32,494 INFO [train.py:842] (3/4) Epoch 23, batch 1200, loss[loss=0.2372, simple_loss=0.2923, pruned_loss=0.09109, over 7266.00 frames.], tot_loss[loss=0.184, simple_loss=0.2712, pruned_loss=0.0484, over 1421302.91 frames.], batch size: 18, lr: 2.41e-04
2022-05-28 09:21:10,632 INFO [train.py:842] (3/4) Epoch 23, batch 1250, loss[loss=0.2019, simple_loss=0.2772, pruned_loss=0.06325, over 6778.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2704, pruned_loss=0.04817, over 1424424.52 frames.], batch size: 15, lr: 2.41e-04
2022-05-28 09:21:48,977 INFO [train.py:842] (3/4) Epoch 23, batch 1300, loss[loss=0.1864, simple_loss=0.2779, pruned_loss=0.04749, over 7212.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2707, pruned_loss=0.04825, over 1427818.77 frames.], batch size: 23, lr: 2.41e-04
2022-05-28 09:22:27,070 INFO [train.py:842] (3/4) Epoch 23, batch 1350, loss[loss=0.1573, simple_loss=0.2375, pruned_loss=0.03852, over 7288.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2695, pruned_loss=0.04809, over 1428384.58 frames.], batch size: 18, lr: 2.41e-04
2022-05-28 09:23:05,257 INFO [train.py:842] (3/4) Epoch 23, batch 1400, loss[loss=0.1605, simple_loss=0.2526, pruned_loss=0.0342, over 7114.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2701, pruned_loss=0.04789, over 1428177.21 frames.], batch size: 21, lr: 2.41e-04
2022-05-28 09:23:43,278 INFO [train.py:842] (3/4) Epoch 23, batch 1450, loss[loss=0.172, simple_loss=0.2489, pruned_loss=0.04761, over 7409.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2696, pruned_loss=0.04768, over 1422162.82 frames.], batch size: 18, lr: 2.41e-04
2022-05-28 09:24:21,888 INFO [train.py:842] (3/4) Epoch 23, batch 1500, loss[loss=0.1772, simple_loss=0.2713, pruned_loss=0.04154, over 7036.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2671, pruned_loss=0.04659, over 1422913.58 frames.], batch size: 28, lr: 2.41e-04
2022-05-28 09:24:59,679 INFO [train.py:842] (3/4) Epoch 23, batch 1550, loss[loss=0.1664, simple_loss=0.2605, pruned_loss=0.03613, over 7363.00 frames.], tot_loss[loss=0.181, simple_loss=0.2678, pruned_loss=0.04708, over 1413803.40 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:25:37,908 INFO [train.py:842] (3/4) Epoch 23, batch 1600, loss[loss=0.2054, simple_loss=0.3002, pruned_loss=0.05531, over 7206.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2693, pruned_loss=0.04748, over 1412213.30 frames.], batch size: 21, lr: 2.41e-04
2022-05-28 09:26:16,019 INFO [train.py:842] (3/4) Epoch 23, batch 1650, loss[loss=0.1997, simple_loss=0.2793, pruned_loss=0.06003, over 7381.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2695, pruned_loss=0.04805, over 1414877.51 frames.], batch size: 23, lr: 2.41e-04
2022-05-28 09:26:54,170 INFO [train.py:842] (3/4) Epoch 23, batch 1700, loss[loss=0.183, simple_loss=0.2606, pruned_loss=0.05273, over 7389.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2691, pruned_loss=0.04755, over 1416315.34 frames.], batch size: 18, lr: 2.41e-04
2022-05-28 09:27:31,885 INFO [train.py:842] (3/4) Epoch 23, batch 1750, loss[loss=0.1823, simple_loss=0.2704, pruned_loss=0.04712, over 7158.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2701, pruned_loss=0.04763, over 1414592.82 frames.], batch size: 26, lr: 2.41e-04
2022-05-28 09:28:10,172 INFO [train.py:842] (3/4) Epoch 23, batch 1800, loss[loss=0.2197, simple_loss=0.2983, pruned_loss=0.07051, over 5071.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2704, pruned_loss=0.04772, over 1411678.81 frames.], batch size: 52, lr: 2.41e-04
2022-05-28 09:28:48,261 INFO [train.py:842] (3/4) Epoch 23, batch 1850, loss[loss=0.1759, simple_loss=0.265, pruned_loss=0.04342, over 7431.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2693, pruned_loss=0.04723, over 1416455.05 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:29:26,613 INFO [train.py:842] (3/4) Epoch 23, batch 1900, loss[loss=0.2236, simple_loss=0.3028, pruned_loss=0.07217, over 7144.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2697, pruned_loss=0.04756, over 1419890.29 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:30:04,587 INFO [train.py:842] (3/4) Epoch 23, batch 1950, loss[loss=0.1672, simple_loss=0.2669, pruned_loss=0.03374, over 7137.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2696, pruned_loss=0.04772, over 1417608.27 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:30:42,758 INFO [train.py:842] (3/4) Epoch 23, batch 2000, loss[loss=0.1832, simple_loss=0.2684, pruned_loss=0.04895, over 7255.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2707, pruned_loss=0.04804, over 1420517.37 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:31:20,838 INFO [train.py:842] (3/4) Epoch 23, batch 2050, loss[loss=0.1632, simple_loss=0.2514, pruned_loss=0.03752, over 7232.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2702, pruned_loss=0.04736, over 1425283.04 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:31:59,070 INFO [train.py:842] (3/4) Epoch 23, batch 2100, loss[loss=0.1978, simple_loss=0.2946, pruned_loss=0.05046, over 7207.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2699, pruned_loss=0.04729, over 1419857.16 frames.], batch size: 23, lr: 2.41e-04
2022-05-28 09:32:37,119 INFO [train.py:842] (3/4) Epoch 23, batch 2150, loss[loss=0.1662, simple_loss=0.2521, pruned_loss=0.04013, over 7159.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2692, pruned_loss=0.04669, over 1420925.81 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:33:15,372 INFO [train.py:842] (3/4) Epoch 23, batch 2200, loss[loss=0.1652, simple_loss=0.255, pruned_loss=0.03772, over 7147.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2697, pruned_loss=0.04691, over 1415478.10 frames.], batch size: 20, lr: 2.41e-04
2022-05-28 09:33:53,113 INFO [train.py:842] (3/4) Epoch 23, batch 2250, loss[loss=0.1719, simple_loss=0.2644, pruned_loss=0.03965, over 7156.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2692, pruned_loss=0.04692, over 1410918.53 frames.], batch size: 19, lr: 2.41e-04
2022-05-28 09:34:31,498 INFO [train.py:842] (3/4) Epoch 23, batch 2300, loss[loss=0.1724, simple_loss=0.2732, pruned_loss=0.03579, over 7329.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2684, pruned_loss=0.0466, over 1412533.93 frames.], batch size: 21, lr: 2.41e-04
2022-05-28 09:35:09,545 INFO [train.py:842] (3/4) Epoch 23, batch 2350, loss[loss=0.1677, simple_loss=0.2549, pruned_loss=0.04023, over 7336.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2686, pruned_loss=0.04684, over 1414991.86 frames.], batch size: 22, lr: 2.41e-04
2022-05-28 09:35:47,650 INFO [train.py:842] (3/4) Epoch 23, batch 2400, loss[loss=0.1818, simple_loss=0.2799, pruned_loss=0.04189, over 7285.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2704, pruned_loss=0.04724, over 1417872.04 frames.], batch size: 24, lr: 2.41e-04
2022-05-28 09:36:25,394 INFO [train.py:842] (3/4) Epoch 23, batch 2450, loss[loss=0.1863, simple_loss=0.2659, pruned_loss=0.05335, over 7204.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2714, pruned_loss=0.04785, over 1421951.64 frames.], batch size: 22, lr: 2.40e-04
2022-05-28 09:37:03,850 INFO [train.py:842] (3/4) Epoch 23, batch 2500, loss[loss=0.1838, simple_loss=0.2809, pruned_loss=0.04332, over 6391.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2696, pruned_loss=0.04767, over 1419899.66 frames.], batch size: 38, lr: 2.40e-04
2022-05-28 09:37:41,691 INFO [train.py:842] (3/4) Epoch 23, batch 2550, loss[loss=0.1944, simple_loss=0.2801, pruned_loss=0.0544, over 7380.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2697, pruned_loss=0.04765, over 1420504.87 frames.], batch size: 23, lr: 2.40e-04
2022-05-28 09:38:20,092 INFO [train.py:842] (3/4) Epoch 23, batch 2600, loss[loss=0.1712, simple_loss=0.2676, pruned_loss=0.03739, over 7345.00 frames.], tot_loss[loss=0.182, simple_loss=0.2694, pruned_loss=0.04732, over 1424862.08 frames.], batch size: 22, lr: 2.40e-04
2022-05-28 09:38:58,233 INFO [train.py:842] (3/4) Epoch 23, batch 2650, loss[loss=0.1921, simple_loss=0.2832, pruned_loss=0.05048, over 7322.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2681, pruned_loss=0.04689, over 1422509.38 frames.], batch size: 25, lr: 2.40e-04
2022-05-28 09:39:36,481 INFO [train.py:842] (3/4) Epoch 23, batch 2700, loss[loss=0.173, simple_loss=0.2657, pruned_loss=0.04014, over 7153.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2685, pruned_loss=0.04708, over 1422466.86 frames.], batch size: 19, lr: 2.40e-04
2022-05-28 09:40:14,502 INFO [train.py:842] (3/4) Epoch 23, batch 2750, loss[loss=0.1637, simple_loss=0.258, pruned_loss=0.03469, over 7165.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2675, pruned_loss=0.04707, over 1420887.71 frames.], batch size: 18, lr: 2.40e-04
2022-05-28 09:40:52,723 INFO [train.py:842] (3/4) Epoch 23, batch 2800, loss[loss=0.1587, simple_loss=0.2559, pruned_loss=0.03072, over 7171.00 frames.], tot_loss[loss=0.181, simple_loss=0.2677, pruned_loss=0.04708, over 1419526.03 frames.], batch size: 18, lr: 2.40e-04
2022-05-28 09:41:30,793 INFO [train.py:842] (3/4) Epoch 23, batch 2850, loss[loss=0.2151, simple_loss=0.2981, pruned_loss=0.06603, over 7054.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2676, pruned_loss=0.04664, over 1420908.53 frames.], batch size: 28, lr: 2.40e-04
2022-05-28 09:42:08,986 INFO [train.py:842] (3/4) Epoch 23, batch 2900, loss[loss=0.1764, simple_loss=0.2751, pruned_loss=0.03891, over 7329.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2673, pruned_loss=0.04604, over 1423407.86 frames.], batch size: 25, lr: 2.40e-04
2022-05-28 09:42:46,958 INFO [train.py:842] (3/4) Epoch 23, batch 2950, loss[loss=0.2417, simple_loss=0.3198, pruned_loss=0.08177, over 7208.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2688, pruned_loss=0.04719, over 1423944.16 frames.], batch size: 22, lr: 2.40e-04
2022-05-28 09:43:25,058 INFO [train.py:842] (3/4) Epoch 23, batch 3000, loss[loss=0.1284, simple_loss=0.2131, pruned_loss=0.02184, over 6990.00 frames.], tot_loss[loss=0.182, simple_loss=0.2693, pruned_loss=0.04738, over 1423055.89 frames.], batch size: 16, lr: 2.40e-04
2022-05-28 09:43:25,059 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 09:43:34,050 INFO [train.py:871] (3/4) Epoch 23, validation: loss=0.1673, simple_loss=0.2658, pruned_loss=0.03441, over 868885.00 frames.
2022-05-28 09:44:12,034 INFO [train.py:842] (3/4) Epoch 23, batch 3050, loss[loss=0.1582, simple_loss=0.2433, pruned_loss=0.03654, over 7161.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2691, pruned_loss=0.04735, over 1425506.59 frames.], batch size: 19, lr: 2.40e-04
2022-05-28 09:44:50,433 INFO [train.py:842] (3/4) Epoch 23, batch 3100, loss[loss=0.1819, simple_loss=0.2623, pruned_loss=0.05069, over 7233.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2686, pruned_loss=0.04702, over 1424652.82 frames.], batch size: 20, lr: 2.40e-04
2022-05-28 09:45:28,474 INFO [train.py:842] (3/4) Epoch 23, batch 3150, loss[loss=0.1721, simple_loss=0.2558, pruned_loss=0.04421, over 7329.00 frames.], tot_loss[loss=0.1812, simple_loss=0.268, pruned_loss=0.04714, over 1425985.73 frames.], batch size: 20, lr: 2.40e-04
2022-05-28 09:46:06,791 INFO [train.py:842] (3/4) Epoch 23, batch 3200, loss[loss=0.2008, simple_loss=0.302, pruned_loss=0.04981, over 7108.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2674, pruned_loss=0.04656, over 1427566.39 frames.], batch size: 21, lr: 2.40e-04
2022-05-28 09:46:44,587 INFO [train.py:842] (3/4) Epoch 23, batch 3250, loss[loss=0.1813, simple_loss=0.274, pruned_loss=0.04433, over 6291.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2685, pruned_loss=0.0472, over 1422576.24 frames.], batch size: 37, lr: 2.40e-04
2022-05-28 09:47:22,771 INFO [train.py:842] (3/4) Epoch 23, batch 3300, loss[loss=0.1755, simple_loss=0.2594, pruned_loss=0.0458, over 7279.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2683, pruned_loss=0.04731, over 1423633.69 frames.], batch size: 24, lr: 2.40e-04
2022-05-28 09:48:00,970 INFO [train.py:842] (3/4) Epoch 23, batch 3350, loss[loss=0.1625, simple_loss=0.2641, pruned_loss=0.03045, over 7157.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2677, pruned_loss=0.04695, over 1427967.07 frames.], batch size: 26, lr: 2.40e-04
2022-05-28 09:48:39,181 INFO [train.py:842] (3/4) Epoch 23, batch 3400, loss[loss=0.133, simple_loss=0.2209, pruned_loss=0.0225, over 7149.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2687, pruned_loss=0.04716, over 1428818.66 frames.], batch size: 19, lr: 2.40e-04
2022-05-28 09:49:17,342 INFO [train.py:842] (3/4) Epoch 23, batch 3450, loss[loss=0.1626, simple_loss=0.2435, pruned_loss=0.04089, over 6802.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2684, pruned_loss=0.04715, over 1430699.32 frames.], batch size: 15, lr: 2.40e-04
2022-05-28 09:49:55,694 INFO [train.py:842] (3/4) Epoch 23, batch 3500, loss[loss=0.1783, simple_loss=0.2599, pruned_loss=0.04831, over 6787.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2685, pruned_loss=0.04739, over 1431359.82 frames.], batch size: 15, lr: 2.40e-04
2022-05-28 09:50:33,628 INFO [train.py:842] (3/4) Epoch 23, batch 3550, loss[loss=0.1614, simple_loss=0.2405, pruned_loss=0.04113, over 7422.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2679, pruned_loss=0.04698, over 1431001.40 frames.], batch size: 18, lr: 2.40e-04
2022-05-28 09:51:11,856 INFO [train.py:842] (3/4) Epoch 23, batch 3600, loss[loss=0.157, simple_loss=0.237, pruned_loss=0.03849, over 7291.00 frames.], tot_loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04798, over 1431982.42 frames.], batch size: 17, lr: 2.40e-04
2022-05-28 09:51:49,920 INFO [train.py:842] (3/4) Epoch 23, batch 3650, loss[loss=0.1886, simple_loss=0.2809, pruned_loss=0.04811, over 6514.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2709, pruned_loss=0.04818, over 1432169.60 frames.], batch size: 38, lr: 2.40e-04
2022-05-28 09:52:28,072 INFO [train.py:842] (3/4) Epoch 23, batch 3700, loss[loss=0.1872, simple_loss=0.2736, pruned_loss=0.05036, over 7157.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2709, pruned_loss=0.04823, over 1430547.90 frames.], batch size: 19, lr: 2.40e-04
2022-05-28 09:53:05,874 INFO [train.py:842] (3/4) Epoch 23, batch 3750, loss[loss=0.2094, simple_loss=0.2828, pruned_loss=0.06801, over 7277.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2716, pruned_loss=0.04912, over 1428217.07 frames.], batch size: 17, lr: 2.40e-04
2022-05-28 09:53:44,127 INFO [train.py:842] (3/4) Epoch 23, batch 3800, loss[loss=0.1779, simple_loss=0.2715, pruned_loss=0.0421, over 7378.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2718, pruned_loss=0.04928, over 1430018.07 frames.], batch size: 23, lr: 2.40e-04
2022-05-28 09:54:22,219 INFO [train.py:842] (3/4) Epoch 23, batch 3850, loss[loss=0.2532, simple_loss=0.3373, pruned_loss=0.08459, over 7076.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2714, pruned_loss=0.04865, over 1430898.21 frames.], batch size: 28, lr: 2.40e-04
2022-05-28 09:55:00,588 INFO [train.py:842] (3/4) Epoch 23, batch 3900, loss[loss=0.1763, simple_loss=0.2767, pruned_loss=0.038, over 7120.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2713, pruned_loss=0.04889, over 1430754.52 frames.], batch size: 21, lr: 2.40e-04
2022-05-28 09:55:38,448 INFO [train.py:842] (3/4) Epoch 23, batch 3950, loss[loss=0.1963, simple_loss=0.2871, pruned_loss=0.05269, over 7156.00 frames.], tot_loss[loss=0.1835, simple_loss=0.271, pruned_loss=0.04801, over 1430290.31 frames.], batch size: 19, lr: 2.40e-04
2022-05-28 09:56:16,616 INFO [train.py:842] (3/4) Epoch 23, batch 4000, loss[loss=0.1632, simple_loss=0.2501, pruned_loss=0.03808, over 7273.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2714, pruned_loss=0.0481, over 1427066.49 frames.], batch size: 17, lr: 2.40e-04
2022-05-28 09:56:54,388 INFO [train.py:842] (3/4) Epoch 23, batch 4050, loss[loss=0.1469, simple_loss=0.2304, pruned_loss=0.03167, over 6755.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2722, pruned_loss=0.04841, over 1422309.76 frames.], batch size: 15, lr: 2.40e-04
2022-05-28 09:57:32,632 INFO [train.py:842] (3/4) Epoch 23, batch 4100, loss[loss=0.1712, simple_loss=0.2614, pruned_loss=0.04052, over 7145.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2708, pruned_loss=0.04784, over 1420083.45 frames.], batch size: 20, lr: 2.40e-04
2022-05-28 09:58:10,729 INFO [train.py:842] (3/4) Epoch 23, batch 4150, loss[loss=0.1702, simple_loss=0.2582, pruned_loss=0.04109, over 7070.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2691, pruned_loss=0.04696, over 1419798.29 frames.], batch size: 18, lr: 2.39e-04
2022-05-28 09:58:48,827 INFO [train.py:842] (3/4) Epoch 23, batch 4200, loss[loss=0.1473, simple_loss=0.2418, pruned_loss=0.02643, over 7440.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2691, pruned_loss=0.04694, over 1423117.75 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 09:59:26,833 INFO [train.py:842] (3/4) Epoch 23, batch 4250, loss[loss=0.1742, simple_loss=0.2479, pruned_loss=0.05026, over 7286.00 frames.], tot_loss[loss=0.1816, simple_loss=0.269, pruned_loss=0.04715, over 1427004.90 frames.], batch size: 17, lr: 2.39e-04
2022-05-28 10:00:04,964 INFO [train.py:842] (3/4) Epoch 23, batch 4300, loss[loss=0.1622, simple_loss=0.2499, pruned_loss=0.03726, over 6682.00 frames.], tot_loss[loss=0.182, simple_loss=0.2694, pruned_loss=0.04724, over 1427735.21 frames.], batch size: 31, lr: 2.39e-04
2022-05-28 10:00:42,801 INFO [train.py:842] (3/4) Epoch 23, batch 4350, loss[loss=0.1784, simple_loss=0.2656, pruned_loss=0.04565, over 7420.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2697, pruned_loss=0.04726, over 1426509.61 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:01:30,393 INFO [train.py:842] (3/4) Epoch 23, batch 4400, loss[loss=0.2014, simple_loss=0.2876, pruned_loss=0.05764, over 6860.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2693, pruned_loss=0.04742, over 1428359.24 frames.], batch size: 31, lr: 2.39e-04
2022-05-28 10:02:08,609 INFO [train.py:842] (3/4) Epoch 23, batch 4450, loss[loss=0.1745, simple_loss=0.2419, pruned_loss=0.05357, over 7137.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2684, pruned_loss=0.04717, over 1429016.54 frames.], batch size: 17, lr: 2.39e-04
2022-05-28 10:02:46,916 INFO [train.py:842] (3/4) Epoch 23, batch 4500, loss[loss=0.1737, simple_loss=0.2642, pruned_loss=0.04166, over 7400.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2697, pruned_loss=0.04761, over 1427350.18 frames.], batch size: 18, lr: 2.39e-04
2022-05-28 10:03:24,945 INFO [train.py:842] (3/4) Epoch 23, batch 4550, loss[loss=0.1777, simple_loss=0.2796, pruned_loss=0.03791, over 7199.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2693, pruned_loss=0.04725, over 1430722.12 frames.], batch size: 22, lr: 2.39e-04
2022-05-28 10:04:12,784 INFO [train.py:842] (3/4) Epoch 23, batch 4600, loss[loss=0.1789, simple_loss=0.2694, pruned_loss=0.04423, over 7386.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2697, pruned_loss=0.04759, over 1425645.81 frames.], batch size: 23, lr: 2.39e-04
2022-05-28 10:04:50,911 INFO [train.py:842] (3/4) Epoch 23, batch 4650, loss[loss=0.2046, simple_loss=0.2698, pruned_loss=0.06969, over 7436.00 frames.], tot_loss[loss=0.182, simple_loss=0.2689, pruned_loss=0.04755, over 1429597.66 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:05:38,565 INFO [train.py:842] (3/4) Epoch 23, batch 4700, loss[loss=0.1835, simple_loss=0.2819, pruned_loss=0.04258, over 7395.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2687, pruned_loss=0.04723, over 1430668.69 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:06:16,323 INFO [train.py:842] (3/4) Epoch 23, batch 4750, loss[loss=0.1936, simple_loss=0.2793, pruned_loss=0.0539, over 7153.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2703, pruned_loss=0.04832, over 1423392.03 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:06:54,365 INFO [train.py:842] (3/4) Epoch 23, batch 4800, loss[loss=0.1573, simple_loss=0.2393, pruned_loss=0.03764, over 7448.00 frames.], tot_loss[loss=0.184, simple_loss=0.2709, pruned_loss=0.04855, over 1420253.64 frames.], batch size: 19, lr: 2.39e-04
2022-05-28 10:07:32,381 INFO [train.py:842] (3/4) Epoch 23, batch 4850, loss[loss=0.1584, simple_loss=0.2406, pruned_loss=0.03811, over 7414.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2696, pruned_loss=0.04799, over 1418959.25 frames.], batch size: 18, lr: 2.39e-04
2022-05-28 10:08:10,716 INFO [train.py:842] (3/4) Epoch 23, batch 4900, loss[loss=0.2284, simple_loss=0.3192, pruned_loss=0.06883, over 7213.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2703, pruned_loss=0.04834, over 1422294.81 frames.], batch size: 22, lr: 2.39e-04
2022-05-28 10:08:48,737 INFO [train.py:842] (3/4) Epoch 23, batch 4950, loss[loss=0.2085, simple_loss=0.2987, pruned_loss=0.05917, over 7420.00 frames.], tot_loss[loss=0.183, simple_loss=0.2696, pruned_loss=0.04823, over 1423344.91 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:09:27,012 INFO [train.py:842] (3/4) Epoch 23, batch 5000, loss[loss=0.1834, simple_loss=0.2734, pruned_loss=0.04669, over 7431.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2692, pruned_loss=0.04816, over 1422835.07 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:10:05,042 INFO [train.py:842] (3/4) Epoch 23, batch 5050, loss[loss=0.1758, simple_loss=0.2609, pruned_loss=0.04541, over 7159.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2671, pruned_loss=0.04718, over 1420500.05 frames.], batch size: 19, lr: 2.39e-04
2022-05-28 10:10:43,288 INFO [train.py:842] (3/4) Epoch 23, batch 5100, loss[loss=0.2415, simple_loss=0.3116, pruned_loss=0.08569, over 7288.00 frames.], tot_loss[loss=0.181, simple_loss=0.2674, pruned_loss=0.04734, over 1422088.35 frames.], batch size: 24, lr: 2.39e-04
2022-05-28 10:11:21,306 INFO [train.py:842] (3/4) Epoch 23, batch 5150, loss[loss=0.1819, simple_loss=0.2751, pruned_loss=0.04435, over 7416.00 frames.], tot_loss[loss=0.1803, simple_loss=0.267, pruned_loss=0.04677, over 1426129.39 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:11:59,868 INFO [train.py:842] (3/4) Epoch 23, batch 5200, loss[loss=0.1725, simple_loss=0.2594, pruned_loss=0.04286, over 7394.00 frames.], tot_loss[loss=0.1794, simple_loss=0.266, pruned_loss=0.04638, over 1428773.45 frames.], batch size: 23, lr: 2.39e-04
2022-05-28 10:12:37,838 INFO [train.py:842] (3/4) Epoch 23, batch 5250, loss[loss=0.1944, simple_loss=0.2931, pruned_loss=0.04786, over 7316.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2673, pruned_loss=0.04657, over 1430710.74 frames.], batch size: 22, lr: 2.39e-04
2022-05-28 10:13:16,076 INFO [train.py:842] (3/4) Epoch 23, batch 5300, loss[loss=0.2315, simple_loss=0.3219, pruned_loss=0.07053, over 6397.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2677, pruned_loss=0.04652, over 1429334.79 frames.], batch size: 38, lr: 2.39e-04
2022-05-28 10:13:54,140 INFO [train.py:842] (3/4) Epoch 23, batch 5350, loss[loss=0.1984, simple_loss=0.2942, pruned_loss=0.05132, over 7115.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2677, pruned_loss=0.04692, over 1425599.11 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:14:32,596 INFO [train.py:842] (3/4) Epoch 23, batch 5400, loss[loss=0.1649, simple_loss=0.2554, pruned_loss=0.03714, over 7338.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2683, pruned_loss=0.04745, over 1430186.16 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:15:10,497 INFO [train.py:842] (3/4) Epoch 23, batch 5450, loss[loss=0.2145, simple_loss=0.2943, pruned_loss=0.0674, over 7014.00 frames.], tot_loss[loss=0.1821, simple_loss=0.269, pruned_loss=0.04761, over 1431468.53 frames.], batch size: 28, lr: 2.39e-04
2022-05-28 10:15:48,471 INFO [train.py:842] (3/4) Epoch 23, batch 5500, loss[loss=0.1902, simple_loss=0.2735, pruned_loss=0.05341, over 7165.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2703, pruned_loss=0.04822, over 1425360.52 frames.], batch size: 26, lr: 2.39e-04
2022-05-28 10:16:26,512 INFO [train.py:842] (3/4) Epoch 23, batch 5550, loss[loss=0.2016, simple_loss=0.2877, pruned_loss=0.05779, over 7185.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2695, pruned_loss=0.04761, over 1427722.54 frames.], batch size: 22, lr: 2.39e-04
2022-05-28 10:17:04,854 INFO [train.py:842] (3/4) Epoch 23, batch 5600, loss[loss=0.1934, simple_loss=0.2761, pruned_loss=0.05536, over 7224.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2697, pruned_loss=0.04753, over 1428293.18 frames.], batch size: 16, lr: 2.39e-04
2022-05-28 10:17:43,163 INFO [train.py:842] (3/4) Epoch 23, batch 5650, loss[loss=0.1723, simple_loss=0.2726, pruned_loss=0.03602, over 7435.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2689, pruned_loss=0.04706, over 1431194.38 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:18:21,422 INFO [train.py:842] (3/4) Epoch 23, batch 5700, loss[loss=0.1746, simple_loss=0.2614, pruned_loss=0.04394, over 7156.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2689, pruned_loss=0.04732, over 1426454.70 frames.], batch size: 20, lr: 2.39e-04
2022-05-28 10:18:59,382 INFO [train.py:842] (3/4) Epoch 23, batch 5750, loss[loss=0.1479, simple_loss=0.2293, pruned_loss=0.03326, over 7130.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2685, pruned_loss=0.04746, over 1423500.65 frames.], batch size: 17, lr: 2.39e-04
2022-05-28 10:19:40,415 INFO [train.py:842] (3/4) Epoch 23, batch 5800, loss[loss=0.1418, simple_loss=0.2287, pruned_loss=0.02748, over 7454.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2663, pruned_loss=0.04613, over 1426094.54 frames.], batch size: 19, lr: 2.39e-04
2022-05-28 10:20:18,499 INFO [train.py:842] (3/4) Epoch 23, batch 5850, loss[loss=0.179, simple_loss=0.2708, pruned_loss=0.04358, over 7322.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2664, pruned_loss=0.04598, over 1428416.38 frames.], batch size: 21, lr: 2.39e-04
2022-05-28 10:20:56,750 INFO [train.py:842] (3/4) Epoch 23, batch 5900, loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02938, over 7424.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2675, pruned_loss=0.04637, over 1424503.23 frames.], batch size: 20, lr: 2.38e-04
2022-05-28 10:21:34,796 INFO [train.py:842] (3/4) Epoch 23, batch 5950, loss[loss=0.1624, simple_loss=0.2417, pruned_loss=0.04156, over 6981.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2679, pruned_loss=0.04675, over 1419350.56 frames.], batch size: 16, lr: 2.38e-04
2022-05-28 10:22:13,048 INFO [train.py:842] (3/4) Epoch 23, batch 6000, loss[loss=0.1817, simple_loss=0.2637, pruned_loss=0.04984, over 6754.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2681, pruned_loss=0.0473, over 1419926.97 frames.], batch size: 31, lr: 2.38e-04
2022-05-28 10:22:13,049 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 10:22:22,048 INFO [train.py:871] (3/4) Epoch 23, validation: loss=0.1637, simple_loss=0.2625, pruned_loss=0.03241, over 868885.00 frames.
2022-05-28 10:22:59,815 INFO [train.py:842] (3/4) Epoch 23, batch 6050, loss[loss=0.1542, simple_loss=0.2348, pruned_loss=0.03677, over 7411.00 frames.], tot_loss[loss=0.1818, simple_loss=0.269, pruned_loss=0.04734, over 1419189.71 frames.], batch size: 18, lr: 2.38e-04
2022-05-28 10:23:37,974 INFO [train.py:842] (3/4) Epoch 23, batch 6100, loss[loss=0.1528, simple_loss=0.2479, pruned_loss=0.02887, over 6786.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2694, pruned_loss=0.04755, over 1420730.42 frames.], batch size: 31, lr: 2.38e-04
2022-05-28 10:24:16,060 INFO [train.py:842] (3/4) Epoch 23, batch 6150, loss[loss=0.1902, simple_loss=0.2814, pruned_loss=0.04945, over 7299.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2696, pruned_loss=0.04756, over 1420872.30 frames.], batch size: 24, lr: 2.38e-04
2022-05-28 10:24:54,371 INFO [train.py:842] (3/4) Epoch 23, batch 6200, loss[loss=0.2147, simple_loss=0.3037, pruned_loss=0.06279, over 7120.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2703, pruned_loss=0.04799, over 1423228.55 frames.], batch size: 26, lr: 2.38e-04
2022-05-28 10:25:32,203 INFO [train.py:842] (3/4) Epoch 23, batch 6250, loss[loss=0.1934, simple_loss=0.2749, pruned_loss=0.05596, over 6748.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2694, pruned_loss=0.04786, over 1420877.83 frames.], batch size: 31, lr: 2.38e-04
2022-05-28 10:26:10,653 INFO [train.py:842] (3/4) Epoch 23, batch 6300, loss[loss=0.2006, simple_loss=0.2862, pruned_loss=0.05753, over 7310.00 frames.], tot_loss[loss=0.1809, simple_loss=0.268, pruned_loss=0.04684, over 1421912.80 frames.], batch size: 25, lr: 2.38e-04
2022-05-28 10:26:48,652 INFO [train.py:842] (3/4) Epoch 23, batch 6350, loss[loss=0.1861, simple_loss=0.2737, pruned_loss=0.04928, over 7161.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2682, pruned_loss=0.04702, over 1420725.24 frames.], batch size: 26, lr: 2.38e-04
2022-05-28 10:27:27,051 INFO [train.py:842] (3/4) Epoch 23, batch 6400, loss[loss=0.182, simple_loss=0.2807, pruned_loss=0.04163, over 7065.00 frames.], tot_loss[loss=0.1798, simple_loss=0.267, pruned_loss=0.04629, over 1423615.07 frames.], batch size: 28, lr: 2.38e-04
2022-05-28 10:28:05,061 INFO [train.py:842] (3/4) Epoch 23, batch 6450, loss[loss=0.1734, simple_loss=0.2609, pruned_loss=0.04298, over 7335.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2672, pruned_loss=0.04629, over 1421077.92 frames.], batch size: 20, lr: 2.38e-04
2022-05-28 10:28:43,396 INFO [train.py:842] (3/4) Epoch 23, batch 6500, loss[loss=0.1786, simple_loss=0.2553, pruned_loss=0.05095, over 7163.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2664, pruned_loss=0.04595, over 1421623.37 frames.], batch size: 18, lr: 2.38e-04
2022-05-28 10:29:21,295 INFO [train.py:842] (3/4) Epoch 23, batch 6550, loss[loss=0.1753, simple_loss=0.2673, pruned_loss=0.04166, over 7259.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2678, pruned_loss=0.04631, over 1422487.72 frames.], batch size: 19, lr: 2.38e-04
2022-05-28 10:29:59,627 INFO [train.py:842] (3/4) Epoch 23, batch 6600, loss[loss=0.1693, simple_loss=0.2656, pruned_loss=0.03654, over 6797.00 frames.], tot_loss[loss=0.181, simple_loss=0.2685, pruned_loss=0.04675, over 1426813.42 frames.], batch size: 31, lr: 2.38e-04
2022-05-28 10:30:37,537 INFO [train.py:842] (3/4) Epoch 23, batch 6650, loss[loss=0.225, simple_loss=0.3106, pruned_loss=0.06966, over 7315.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2684, pruned_loss=0.04668, over 1428601.18 frames.], batch size: 21, lr: 2.38e-04
2022-05-28 10:31:15,863 INFO [train.py:842] (3/4) Epoch 23, batch 6700, loss[loss=0.1791, simple_loss=0.2688, pruned_loss=0.04472, over 7364.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2684, pruned_loss=0.04696, over 1428369.89 frames.], batch size: 19, lr: 2.38e-04
2022-05-28 10:31:54,045 INFO [train.py:842] (3/4) Epoch 23, batch 6750, loss[loss=0.1724, simple_loss=0.269, pruned_loss=0.03788, over 7420.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2678, pruned_loss=0.04721, over 1429897.14 frames.], batch size: 21, lr: 2.38e-04
2022-05-28 10:32:32,273 INFO [train.py:842] (3/4) Epoch 23, batch 6800, loss[loss=0.1685, simple_loss=0.2492, pruned_loss=0.04393, over 7363.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2674, pruned_loss=0.04639, over 1431954.39 frames.], batch size: 19, lr: 2.38e-04
2022-05-28 10:33:10,274 INFO [train.py:842] (3/4) Epoch 23, batch 6850, loss[loss=0.1452, simple_loss=0.2329, pruned_loss=0.02877, over 7272.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2673, pruned_loss=0.04626, over 1427162.73 frames.], batch size: 18, lr: 2.38e-04
2022-05-28 10:33:48,540 INFO [train.py:842] (3/4) Epoch 23, batch 6900, loss[loss=0.1917, simple_loss=0.2711, pruned_loss=0.05618, over 7409.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2694, pruned_loss=0.04766, over 1426208.55 frames.], batch size: 21, lr: 2.38e-04
2022-05-28 10:34:26,516 INFO [train.py:842] (3/4) Epoch 23, batch 6950, loss[loss=0.1384, simple_loss=0.2137, pruned_loss=0.03158, over 7404.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2694, pruned_loss=0.04755, over 1428656.77 frames.], batch size: 17, lr: 2.38e-04
2022-05-28 10:35:04,770 INFO [train.py:842] (3/4) Epoch 23, batch 7000, loss[loss=0.2991, simple_loss=0.362, pruned_loss=0.1182, over 4852.00 frames.], tot_loss[loss=0.1829, simple_loss=0.27, pruned_loss=0.04788, over 1427570.23 frames.], batch size: 52, lr: 2.38e-04
2022-05-28 10:35:42,817 INFO [train.py:842] (3/4) Epoch 23, batch 7050, loss[loss=0.1787, simple_loss=0.2689, pruned_loss=0.04424, over 7236.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2699, pruned_loss=0.04811, over 1427412.16 frames.], batch size: 20, lr: 2.38e-04
2022-05-28 10:36:21,013 INFO [train.py:842] (3/4) Epoch 23, batch 7100, loss[loss=0.2505, simple_loss=0.3241, pruned_loss=0.0884, over 7293.00 frames.], tot_loss[loss=0.183, simple_loss=0.27, pruned_loss=0.04799, over 1423414.08 frames.], batch size: 24, lr: 2.38e-04
2022-05-28 10:36:58,905 INFO [train.py:842] (3/4) Epoch 23, batch 7150, loss[loss=0.1741, simple_loss=0.264, pruned_loss=0.04206, over 7311.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2699, pruned_loss=0.04789, over 1425736.67 frames.], batch size: 25, lr: 2.38e-04
2022-05-28 10:37:37,092 INFO [train.py:842] (3/4) Epoch 23, batch 7200, loss[loss=0.184, simple_loss=0.2701, pruned_loss=0.04899, over 7321.00 frames.], tot_loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04797, over 1420546.02 frames.], batch size: 20, lr: 2.38e-04
2022-05-28 10:38:15,060 INFO [train.py:842] (3/4) Epoch 23, batch 7250, loss[loss=0.1597, simple_loss=0.2581, pruned_loss=0.03062, over 7148.00 frames.], tot_loss[loss=0.185, simple_loss=0.272, pruned_loss=0.04903, over 1418348.97 frames.], batch size: 19, lr: 2.38e-04
2022-05-28 10:38:53,290 INFO [train.py:842] (3/4) Epoch 23, batch 7300, loss[loss=0.2028, simple_loss=0.2904, pruned_loss=0.05758, over 7181.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2705, pruned_loss=0.04848, over 1418000.44 frames.], batch size: 26, lr: 2.38e-04
2022-05-28 10:39:31,506 INFO [train.py:842] (3/4) Epoch 23, batch 7350, loss[loss=0.2035, simple_loss=0.2825, pruned_loss=0.06223, over 4971.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2704, pruned_loss=0.0489, over 1420489.62 frames.], batch size: 52, lr: 2.38e-04
2022-05-28 10:40:09,512 INFO [train.py:842] (3/4) Epoch 23, batch 7400, loss[loss=0.1975, simple_loss=0.281, pruned_loss=0.05705, over 7155.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2703, pruned_loss=0.0482, over 1421819.15 frames.], batch size: 20, lr: 2.38e-04
2022-05-28 10:40:47,423 INFO [train.py:842] (3/4) Epoch 23, batch 7450, loss[loss=0.1768, simple_loss=0.2667, pruned_loss=0.04351, over 7168.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2707, pruned_loss=0.04832, over 1423811.98 frames.], batch size: 19, lr: 2.38e-04
2022-05-28 10:41:25,547 INFO [train.py:842] (3/4) Epoch 23, batch 7500, loss[loss=0.2593, simple_loss=0.3486, pruned_loss=0.08501, over 7220.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2714, pruned_loss=0.04833, over 1416726.79 frames.], batch size: 22, lr: 2.38e-04
2022-05-28 10:42:03,565 INFO [train.py:842] (3/4) Epoch 23, batch 7550, loss[loss=0.1846, simple_loss=0.2717, pruned_loss=0.04873, over 7413.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2707, pruned_loss=0.04793, over 1420540.23 frames.], batch size: 21, lr: 2.38e-04
2022-05-28 10:42:41,664 INFO [train.py:842] (3/4) Epoch 23, batch 7600, loss[loss=0.2353, simple_loss=0.3143, pruned_loss=0.07819, over 5288.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2702, pruned_loss=0.0478, over 1417642.06 frames.], batch size: 53, lr: 2.38e-04
2022-05-28 10:43:19,669 INFO [train.py:842] (3/4) Epoch 23, batch 7650, loss[loss=0.2032, simple_loss=0.2916, pruned_loss=0.05745, over 6735.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2693, pruned_loss=0.04764, over 1415621.10 frames.], batch size: 31, lr: 2.37e-04
2022-05-28 10:43:57,926 INFO [train.py:842] (3/4) Epoch 23, batch 7700, loss[loss=0.1849, simple_loss=0.2802, pruned_loss=0.04476, over 7140.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2695, pruned_loss=0.04744, over 1415320.66 frames.], batch size: 20, lr: 2.37e-04
2022-05-28 10:44:35,750 INFO [train.py:842] (3/4) Epoch 23, batch 7750, loss[loss=0.1768, simple_loss=0.2706, pruned_loss=0.04147, over 7412.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2695, pruned_loss=0.04739, over 1418696.61 frames.], batch size: 21, lr: 2.37e-04
2022-05-28 10:45:14,283 INFO [train.py:842] (3/4) Epoch 23, batch 7800, loss[loss=0.2345, simple_loss=0.3218, pruned_loss=0.07364, over 7174.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2687, pruned_loss=0.04705, over 1423164.46 frames.], batch size: 26, lr: 2.37e-04
2022-05-28 10:45:52,176 INFO [train.py:842] (3/4) Epoch 23, batch 7850, loss[loss=0.2489, simple_loss=0.3115, pruned_loss=0.09316, over 5004.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2684, pruned_loss=0.04723, over 1418691.37 frames.], batch size: 55, lr: 2.37e-04
2022-05-28 10:46:30,465 INFO [train.py:842] (3/4) Epoch 23, batch 7900, loss[loss=0.1895, simple_loss=0.2757, pruned_loss=0.05172, over 5232.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2682, pruned_loss=0.0472, over 1419083.95 frames.], batch size: 52, lr: 2.37e-04
2022-05-28 10:47:08,312 INFO [train.py:842] (3/4) Epoch 23, batch 7950, loss[loss=0.1578, simple_loss=0.2408, pruned_loss=0.03742, over 7159.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2676, pruned_loss=0.04685, over 1420317.99 frames.], batch size: 17, lr: 2.37e-04
2022-05-28 10:47:46,451 INFO [train.py:842] (3/4) Epoch 23, batch 8000, loss[loss=0.1546, simple_loss=0.2553, pruned_loss=0.02697, over 7147.00 frames.], tot_loss[loss=0.181, simple_loss=0.2684, pruned_loss=0.04677, over 1423983.71 frames.], batch size: 26, lr: 2.37e-04
2022-05-28 10:48:24,468 INFO [train.py:842] (3/4) Epoch 23, batch 8050, loss[loss=0.1865, simple_loss=0.2669, pruned_loss=0.05304, over 7155.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2675, pruned_loss=0.0465, over 1422421.98 frames.], batch size: 18, lr: 2.37e-04
2022-05-28 10:49:02,723 INFO [train.py:842] (3/4) Epoch 23, batch 8100, loss[loss=0.1711, simple_loss=0.2523, pruned_loss=0.04495, over 7282.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2675, pruned_loss=0.04678, over 1424055.05 frames.], batch size: 17, lr: 2.37e-04
2022-05-28 10:49:40,304 INFO [train.py:842] (3/4) Epoch 23, batch 8150, loss[loss=0.1945, simple_loss=0.2853, pruned_loss=0.05183, over 7220.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2688, pruned_loss=0.04728, over 1419658.95 frames.], batch size: 21, lr: 2.37e-04
2022-05-28 10:50:18,858 INFO [train.py:842] (3/4) Epoch 23, batch 8200, loss[loss=0.1642, simple_loss=0.2623, pruned_loss=0.03305, over 7284.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2673, pruned_loss=0.04663, over 1420487.76 frames.], batch size: 25, lr: 2.37e-04
2022-05-28 10:50:56,569 INFO [train.py:842] (3/4) Epoch 23, batch 8250, loss[loss=0.1773, simple_loss=0.2676, pruned_loss=0.04346, over 7191.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2678, pruned_loss=0.04654, over 1420336.18 frames.], batch size: 22, lr: 2.37e-04
2022-05-28 10:51:34,715 INFO [train.py:842] (3/4) Epoch 23, batch 8300, loss[loss=0.1739, simple_loss=0.2615, pruned_loss=0.04313, over 7077.00 frames.], tot_loss[loss=0.181, simple_loss=0.2682, pruned_loss=0.04689, over 1414851.65 frames.], batch size: 18, lr: 2.37e-04
2022-05-28 10:52:12,737 INFO [train.py:842] (3/4) Epoch 23, batch 8350, loss[loss=0.1755, simple_loss=0.2761, pruned_loss=0.03748, over 6601.00 frames.], tot_loss[loss=0.1811, simple_loss=0.268, pruned_loss=0.04706, over 1413594.36 frames.], batch size: 38, lr: 2.37e-04
2022-05-28 10:52:50,731 INFO [train.py:842] (3/4) Epoch 23, batch 8400, loss[loss=0.1705, simple_loss=0.2687, pruned_loss=0.03618, over 7070.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2693, pruned_loss=0.04756, over 1409177.65 frames.], batch size: 18, lr: 2.37e-04
2022-05-28 10:53:28,676 INFO [train.py:842] (3/4) Epoch 23, batch 8450, loss[loss=0.1419, simple_loss=0.225, pruned_loss=0.0294, over 7016.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2682, pruned_loss=0.04747, over 1408649.44 frames.], batch size: 16, lr: 2.37e-04
2022-05-28 10:54:06,871 INFO [train.py:842] (3/4) Epoch 23, batch 8500, loss[loss=0.1775, simple_loss=0.2544, pruned_loss=0.05028, over 6859.00 frames.], tot_loss[loss=0.182, simple_loss=0.2688, pruned_loss=0.04765, over 1409199.59 frames.], batch size: 15, lr: 2.37e-04
2022-05-28 10:54:44,745 INFO [train.py:842] (3/4) Epoch 23, batch 8550, loss[loss=0.162, simple_loss=0.2528, pruned_loss=0.03563, over 7216.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2698, pruned_loss=0.04833, over 1411372.54 frames.], batch size: 21, lr: 2.37e-04
2022-05-28 10:55:22,740 INFO [train.py:842] (3/4) Epoch 23, batch 8600, loss[loss=0.1718, simple_loss=0.2576, pruned_loss=0.04299, over 7387.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2703, pruned_loss=0.04823, over 1411554.04 frames.], batch size: 23, lr: 2.37e-04
2022-05-28 10:56:00,907 INFO [train.py:842] (3/4) Epoch 23, batch 8650, loss[loss=0.1501, simple_loss=0.2299, pruned_loss=0.03517, over 7291.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2686, pruned_loss=0.04766, over 1415881.91 frames.], batch size: 17, lr: 2.37e-04
2022-05-28 10:56:39,175 INFO [train.py:842] (3/4) Epoch 23, batch 8700, loss[loss=0.1431, simple_loss=0.2243, pruned_loss=0.03096, over 7005.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2674, pruned_loss=0.0476, over 1415230.98 frames.], batch size: 16, lr: 2.37e-04
2022-05-28 10:57:17,041 INFO [train.py:842] (3/4) Epoch 23, batch 8750, loss[loss=0.1898, simple_loss=0.2581, pruned_loss=0.06073, over 7141.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2676, pruned_loss=0.04743, over 1412968.50 frames.], batch size: 17, lr: 2.37e-04
2022-05-28 10:57:55,229 INFO [train.py:842] (3/4) Epoch 23, batch 8800, loss[loss=0.1758, simple_loss=0.2646, pruned_loss=0.0435, over 7292.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2691, pruned_loss=0.04828, over 1408904.90 frames.], batch size: 24, lr: 2.37e-04
2022-05-28 10:58:33,260 INFO [train.py:842] (3/4) Epoch 23, batch 8850, loss[loss=0.1877, simple_loss=0.2824, pruned_loss=0.04651, over 7115.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2685, pruned_loss=0.04752, over 1410597.01 frames.], batch size: 21, lr: 2.37e-04
2022-05-28 10:59:11,044 INFO [train.py:842] (3/4) Epoch 23, batch 8900, loss[loss=0.1917, simple_loss=0.2899, pruned_loss=0.04677, over 7159.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2688, pruned_loss=0.04744, over 1401020.72 frames.], batch size: 26, lr: 2.37e-04
2022-05-28 10:59:48,807 INFO [train.py:842] (3/4) Epoch 23, batch 8950, loss[loss=0.2136, simple_loss=0.3026, pruned_loss=0.06231, over 6513.00 frames.], tot_loss[loss=0.1831, simple_loss=0.27, pruned_loss=0.04808, over 1395095.42 frames.], batch size: 38, lr: 2.37e-04
2022-05-28 11:00:26,427 INFO [train.py:842] (3/4) Epoch 23, batch 9000, loss[loss=0.1894, simple_loss=0.2722, pruned_loss=0.05333, over 5139.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2723, pruned_loss=0.04868, over 1392018.52 frames.], batch size: 53, lr: 2.37e-04
2022-05-28 11:00:26,428 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 11:00:35,435 INFO [train.py:871] (3/4) Epoch 23, validation: loss=0.1641, simple_loss=0.2627, pruned_loss=0.03273, over 868885.00 frames.
2022-05-28 11:01:12,467 INFO [train.py:842] (3/4) Epoch 23, batch 9050, loss[loss=0.1861, simple_loss=0.2758, pruned_loss=0.04824, over 6724.00 frames.], tot_loss[loss=0.1861, simple_loss=0.274, pruned_loss=0.04908, over 1380041.58 frames.], batch size: 31, lr: 2.37e-04
2022-05-28 11:01:49,743 INFO [train.py:842] (3/4) Epoch 23, batch 9100, loss[loss=0.1611, simple_loss=0.2523, pruned_loss=0.03496, over 7167.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2764, pruned_loss=0.05087, over 1346567.74 frames.], batch size: 26, lr: 2.37e-04
2022-05-28 11:02:26,565 INFO [train.py:842] (3/4) Epoch 23, batch 9150, loss[loss=0.1922, simple_loss=0.2765, pruned_loss=0.05395, over 4983.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2791, pruned_loss=0.05333, over 1282447.26 frames.], batch size: 52, lr: 2.37e-04
2022-05-28 11:03:11,882 INFO [train.py:842] (3/4) Epoch 24, batch 0, loss[loss=0.1758, simple_loss=0.2469, pruned_loss=0.05236, over 6844.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2469, pruned_loss=0.05236, over 6844.00 frames.], batch size: 15, lr: 2.32e-04
2022-05-28 11:03:49,770 INFO [train.py:842] (3/4) Epoch 24, batch 50, loss[loss=0.1312, simple_loss=0.2238, pruned_loss=0.01929, over 7272.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2628, pruned_loss=0.04222, over 316294.90 frames.], batch size: 17, lr: 2.32e-04
2022-05-28 11:04:28,177 INFO [train.py:842] (3/4) Epoch 24, batch 100, loss[loss=0.1859, simple_loss=0.2681, pruned_loss=0.05189, over 7335.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2675, pruned_loss=0.04536, over 566892.22 frames.], batch size: 20, lr: 2.32e-04
2022-05-28 11:05:05,930 INFO [train.py:842] (3/4) Epoch 24, batch 150, loss[loss=0.2393, simple_loss=0.3131, pruned_loss=0.08278, over 7379.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2717, pruned_loss=0.04853, over 753257.74 frames.], batch size: 23, lr: 2.32e-04
2022-05-28 11:05:44,214 INFO [train.py:842] (3/4) Epoch 24, batch 200, loss[loss=0.2278, simple_loss=0.3208, pruned_loss=0.06743, over 7213.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2699, pruned_loss=0.0478, over 904507.30 frames.], batch size: 22, lr: 2.32e-04
2022-05-28 11:06:22,176 INFO [train.py:842] (3/4) Epoch 24, batch 250, loss[loss=0.153, simple_loss=0.2462, pruned_loss=0.02987, over 7405.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2674, pruned_loss=0.04646, over 1017338.03 frames.], batch size: 21, lr: 2.32e-04
2022-05-28 11:07:00,471 INFO [train.py:842] (3/4) Epoch 24, batch 300, loss[loss=0.1707, simple_loss=0.2665, pruned_loss=0.03742, over 7149.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2669, pruned_loss=0.04615, over 1108415.93 frames.], batch size: 20, lr: 2.32e-04
2022-05-28 11:07:38,466 INFO [train.py:842] (3/4) Epoch 24, batch 350, loss[loss=0.1953, simple_loss=0.2923, pruned_loss=0.04913, over 7308.00 frames.], tot_loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04588, over 1179551.60 frames.], batch size: 25, lr: 2.32e-04
2022-05-28 11:08:16,632 INFO [train.py:842] (3/4) Epoch 24, batch 400, loss[loss=0.1731, simple_loss=0.2608, pruned_loss=0.04273, over 7298.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2664, pruned_loss=0.04567, over 1230027.20 frames.], batch size: 24, lr: 2.32e-04
2022-05-28 11:08:54,682 INFO [train.py:842] (3/4) Epoch 24, batch 450, loss[loss=0.2033, simple_loss=0.2933, pruned_loss=0.0566, over 7145.00 frames.], tot_loss[loss=0.179, simple_loss=0.2666, pruned_loss=0.04568, over 1275751.79 frames.], batch size: 20, lr: 2.32e-04
2022-05-28 11:09:32,938 INFO [train.py:842] (3/4) Epoch 24, batch 500, loss[loss=0.1984, simple_loss=0.2875, pruned_loss=0.05467, over 7363.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2671, pruned_loss=0.0462, over 1307691.51 frames.], batch size: 19, lr: 2.31e-04
2022-05-28 11:10:11,042 INFO [train.py:842] (3/4) Epoch 24, batch 550, loss[loss=0.1839, simple_loss=0.2711, pruned_loss=0.04835, over 7200.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2674, pruned_loss=0.04637, over 1336404.82 frames.], batch size: 22, lr: 2.31e-04
2022-05-28 11:10:49,414 INFO [train.py:842] (3/4) Epoch 24, batch 600, loss[loss=0.1674, simple_loss=0.25, pruned_loss=0.04237, over 7344.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2656, pruned_loss=0.04584, over 1353659.65 frames.], batch size: 19, lr: 2.31e-04
2022-05-28 11:11:27,464 INFO [train.py:842] (3/4) Epoch 24, batch 650, loss[loss=0.1626, simple_loss=0.2465, pruned_loss=0.03941, over 7344.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2661, pruned_loss=0.04648, over 1363239.74 frames.], batch size: 19, lr: 2.31e-04
2022-05-28 11:12:06,142 INFO [train.py:842] (3/4) Epoch 24, batch 700, loss[loss=0.187, simple_loss=0.2808, pruned_loss=0.04665, over 7195.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2652, pruned_loss=0.04605, over 1380386.29 frames.], batch size: 26, lr: 2.31e-04
2022-05-28 11:12:44,045 INFO [train.py:842] (3/4) Epoch 24, batch 750, loss[loss=0.1732, simple_loss=0.2394, pruned_loss=0.05347, over 6993.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2667, pruned_loss=0.04648, over 1391728.11 frames.], batch size: 16, lr: 2.31e-04
2022-05-28 11:13:22,549 INFO [train.py:842] (3/4) Epoch 24, batch 800, loss[loss=0.141, simple_loss=0.2365, pruned_loss=0.02271, over 7270.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2658, pruned_loss=0.04576, over 1398438.17 frames.], batch size: 19, lr: 2.31e-04
2022-05-28 11:14:00,602 INFO [train.py:842] (3/4) Epoch 24, batch 850, loss[loss=0.1981, simple_loss=0.2892, pruned_loss=0.05349, over 6674.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2652, pruned_loss=0.04535, over 1404301.88 frames.], batch size: 31, lr: 2.31e-04
2022-05-28 11:14:38,796 INFO [train.py:842] (3/4) Epoch 24, batch 900, loss[loss=0.1847, simple_loss=0.2736, pruned_loss=0.04789, over 7442.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2661, pruned_loss=0.04588, over 1410037.68 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:15:16,797 INFO [train.py:842] (3/4) Epoch 24, batch 950, loss[loss=0.1811, simple_loss=0.279, pruned_loss=0.04159, over 6511.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2666, pruned_loss=0.04623, over 1415216.31 frames.], batch size: 38, lr: 2.31e-04
2022-05-28 11:15:55,343 INFO [train.py:842] (3/4) Epoch 24, batch 1000, loss[loss=0.2042, simple_loss=0.294, pruned_loss=0.0572, over 7318.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2669, pruned_loss=0.0464, over 1417026.80 frames.], batch size: 21, lr: 2.31e-04
2022-05-28 11:16:33,153 INFO [train.py:842] (3/4) Epoch 24, batch 1050, loss[loss=0.1875, simple_loss=0.2759, pruned_loss=0.04954, over 7250.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2683, pruned_loss=0.0472, over 1411566.15 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:17:11,287 INFO [train.py:842] (3/4) Epoch 24, batch 1100, loss[loss=0.1691, simple_loss=0.2585, pruned_loss=0.03985, over 7131.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2688, pruned_loss=0.04768, over 1411740.39 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:17:49,527 INFO [train.py:842] (3/4) Epoch 24, batch 1150, loss[loss=0.1968, simple_loss=0.2769, pruned_loss=0.05833, over 6337.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2687, pruned_loss=0.04794, over 1415191.39 frames.], batch size: 38, lr: 2.31e-04
2022-05-28 11:18:27,589 INFO [train.py:842] (3/4) Epoch 24, batch 1200, loss[loss=0.1865, simple_loss=0.2737, pruned_loss=0.04963, over 7174.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2687, pruned_loss=0.0471, over 1417288.03 frames.], batch size: 18, lr: 2.31e-04
2022-05-28 11:19:05,769 INFO [train.py:842] (3/4) Epoch 24, batch 1250, loss[loss=0.2239, simple_loss=0.3003, pruned_loss=0.07376, over 7327.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2679, pruned_loss=0.04658, over 1419182.27 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:19:44,011 INFO [train.py:842] (3/4) Epoch 24, batch 1300, loss[loss=0.1882, simple_loss=0.2732, pruned_loss=0.05157, over 6887.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2683, pruned_loss=0.04655, over 1420275.14 frames.], batch size: 31, lr: 2.31e-04
2022-05-28 11:20:21,962 INFO [train.py:842] (3/4) Epoch 24, batch 1350, loss[loss=0.1722, simple_loss=0.2541, pruned_loss=0.04512, over 7406.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2684, pruned_loss=0.04627, over 1425876.54 frames.], batch size: 18, lr: 2.31e-04
2022-05-28 11:21:00,278 INFO [train.py:842] (3/4) Epoch 24, batch 1400, loss[loss=0.1879, simple_loss=0.2766, pruned_loss=0.04959, over 7128.00 frames.], tot_loss[loss=0.1815, simple_loss=0.269, pruned_loss=0.047, over 1424165.77 frames.], batch size: 26, lr: 2.31e-04
2022-05-28 11:21:38,261 INFO [train.py:842] (3/4) Epoch 24, batch 1450, loss[loss=0.1771, simple_loss=0.2736, pruned_loss=0.04028, over 7153.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2687, pruned_loss=0.04701, over 1422794.40 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:22:16,543 INFO [train.py:842] (3/4) Epoch 24, batch 1500, loss[loss=0.1566, simple_loss=0.2445, pruned_loss=0.03433, over 7155.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2674, pruned_loss=0.04645, over 1421170.16 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:22:54,642 INFO [train.py:842] (3/4) Epoch 24, batch 1550, loss[loss=0.2079, simple_loss=0.3025, pruned_loss=0.05671, over 6679.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2682, pruned_loss=0.04676, over 1420704.50 frames.], batch size: 31, lr: 2.31e-04
2022-05-28 11:23:32,827 INFO [train.py:842] (3/4) Epoch 24, batch 1600, loss[loss=0.1636, simple_loss=0.2511, pruned_loss=0.03807, over 7316.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2689, pruned_loss=0.04693, over 1422264.27 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:24:10,609 INFO [train.py:842] (3/4) Epoch 24, batch 1650, loss[loss=0.1548, simple_loss=0.2285, pruned_loss=0.0406, over 6748.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2696, pruned_loss=0.04711, over 1415284.33 frames.], batch size: 15, lr: 2.31e-04
2022-05-28 11:24:48,824 INFO [train.py:842] (3/4) Epoch 24, batch 1700, loss[loss=0.1561, simple_loss=0.2515, pruned_loss=0.0304, over 7319.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2689, pruned_loss=0.04673, over 1418477.38 frames.], batch size: 21, lr: 2.31e-04
2022-05-28 11:25:26,714 INFO [train.py:842] (3/4) Epoch 24, batch 1750, loss[loss=0.1856, simple_loss=0.2614, pruned_loss=0.05497, over 7059.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2687, pruned_loss=0.04675, over 1419985.27 frames.], batch size: 18, lr: 2.31e-04
2022-05-28 11:26:05,009 INFO [train.py:842] (3/4) Epoch 24, batch 1800, loss[loss=0.1984, simple_loss=0.2844, pruned_loss=0.05621, over 7339.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2685, pruned_loss=0.04679, over 1420736.51 frames.], batch size: 22, lr: 2.31e-04
2022-05-28 11:26:42,920 INFO [train.py:842] (3/4) Epoch 24, batch 1850, loss[loss=0.2493, simple_loss=0.3272, pruned_loss=0.08565, over 7264.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2682, pruned_loss=0.04679, over 1424085.52 frames.], batch size: 24, lr: 2.31e-04
2022-05-28 11:27:21,189 INFO [train.py:842] (3/4) Epoch 24, batch 1900, loss[loss=0.1788, simple_loss=0.2751, pruned_loss=0.0413, over 7002.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2685, pruned_loss=0.04704, over 1422020.95 frames.], batch size: 28, lr: 2.31e-04
2022-05-28 11:27:59,208 INFO [train.py:842] (3/4) Epoch 24, batch 1950, loss[loss=0.1785, simple_loss=0.2787, pruned_loss=0.03917, over 7112.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2684, pruned_loss=0.04638, over 1423133.90 frames.], batch size: 21, lr: 2.31e-04
2022-05-28 11:28:37,371 INFO [train.py:842] (3/4) Epoch 24, batch 2000, loss[loss=0.1841, simple_loss=0.2545, pruned_loss=0.05684, over 4560.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2691, pruned_loss=0.04676, over 1420926.89 frames.], batch size: 53, lr: 2.31e-04
2022-05-28 11:29:15,375 INFO [train.py:842] (3/4) Epoch 24, batch 2050, loss[loss=0.1856, simple_loss=0.2688, pruned_loss=0.0512, over 7431.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2691, pruned_loss=0.04672, over 1421519.25 frames.], batch size: 20, lr: 2.31e-04
2022-05-28 11:29:53,653 INFO [train.py:842] (3/4) Epoch 24, batch 2100, loss[loss=0.139, simple_loss=0.2304, pruned_loss=0.02384, over 7004.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2677, pruned_loss=0.04604, over 1422335.56 frames.], batch size: 16, lr: 2.31e-04
2022-05-28 11:30:31,681 INFO [train.py:842] (3/4) Epoch 24, batch 2150, loss[loss=0.2008, simple_loss=0.2939, pruned_loss=0.05385, over 5062.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2668, pruned_loss=0.04588, over 1421394.20 frames.], batch size: 52, lr: 2.31e-04
2022-05-28 11:31:10,143 INFO [train.py:842] (3/4) Epoch 24, batch 2200, loss[loss=0.1541, simple_loss=0.2361, pruned_loss=0.03605, over 7145.00 frames.], tot_loss[loss=0.1791, simple_loss=0.267, pruned_loss=0.04567, over 1420124.15 frames.], batch size: 17, lr: 2.31e-04
2022-05-28 11:31:47,817 INFO [train.py:842] (3/4) Epoch 24, batch 2250, loss[loss=0.2151, simple_loss=0.3053, pruned_loss=0.06249, over 7319.00 frames.], tot_loss[loss=0.181, simple_loss=0.2687, pruned_loss=0.04664, over 1409129.54 frames.], batch size: 25, lr: 2.31e-04
2022-05-28 11:32:26,192 INFO [train.py:842] (3/4) Epoch 24, batch 2300, loss[loss=0.1732, simple_loss=0.256, pruned_loss=0.0452, over 7291.00 frames.], tot_loss[loss=0.1805, simple_loss=0.268, pruned_loss=0.04649, over 1416434.17 frames.], batch size: 17, lr: 2.31e-04
2022-05-28 11:33:04,229 INFO [train.py:842] (3/4) Epoch 24, batch 2350, loss[loss=0.1743, simple_loss=0.2697, pruned_loss=0.03943, over 7345.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2675, pruned_loss=0.04589, over 1418083.32 frames.], batch size: 22, lr: 2.30e-04
2022-05-28 11:33:42,613 INFO [train.py:842] (3/4) Epoch 24, batch 2400, loss[loss=0.1976, simple_loss=0.26, pruned_loss=0.06756, over 6832.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2687, pruned_loss=0.04635, over 1420759.15 frames.], batch size: 15, lr: 2.30e-04
2022-05-28 11:34:20,481 INFO [train.py:842] (3/4) Epoch 24, batch 2450, loss[loss=0.1497, simple_loss=0.2495, pruned_loss=0.0249, over 7233.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2681, pruned_loss=0.04645, over 1416778.54 frames.], batch size: 20, lr: 2.30e-04
2022-05-28 11:34:58,783 INFO [train.py:842] (3/4) Epoch 24, batch 2500, loss[loss=0.1758, simple_loss=0.2779, pruned_loss=0.03689, over 7317.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2678, pruned_loss=0.04647, over 1417766.46 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:35:36,695 INFO [train.py:842] (3/4) Epoch 24, batch 2550, loss[loss=0.2043, simple_loss=0.2879, pruned_loss=0.06036, over 4940.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2678, pruned_loss=0.0468, over 1413477.63 frames.], batch size: 52, lr: 2.30e-04
2022-05-28 11:36:14,962 INFO [train.py:842] (3/4) Epoch 24, batch 2600, loss[loss=0.1685, simple_loss=0.2423, pruned_loss=0.04738, over 7293.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2685, pruned_loss=0.04711, over 1416802.67 frames.], batch size: 18, lr: 2.30e-04
2022-05-28 11:36:52,935 INFO [train.py:842] (3/4) Epoch 24, batch 2650, loss[loss=0.169, simple_loss=0.2638, pruned_loss=0.03713, over 7322.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2686, pruned_loss=0.04715, over 1416848.84 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:37:31,152 INFO [train.py:842] (3/4) Epoch 24, batch 2700, loss[loss=0.153, simple_loss=0.2499, pruned_loss=0.02808, over 7342.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2685, pruned_loss=0.04714, over 1421956.10 frames.], batch size: 22, lr: 2.30e-04
2022-05-28 11:38:09,222 INFO [train.py:842] (3/4) Epoch 24, batch 2750, loss[loss=0.171, simple_loss=0.2618, pruned_loss=0.0401, over 7409.00 frames.], tot_loss[loss=0.181, simple_loss=0.2682, pruned_loss=0.04691, over 1425218.15 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:38:47,222 INFO [train.py:842] (3/4) Epoch 24, batch 2800, loss[loss=0.1632, simple_loss=0.2613, pruned_loss=0.03251, over 7232.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2697, pruned_loss=0.04735, over 1421699.37 frames.], batch size: 20, lr: 2.30e-04
2022-05-28 11:39:25,102 INFO [train.py:842] (3/4) Epoch 24, batch 2850, loss[loss=0.1845, simple_loss=0.2762, pruned_loss=0.04643, over 7346.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2698, pruned_loss=0.04721, over 1423073.38 frames.], batch size: 19, lr: 2.30e-04
2022-05-28 11:40:03,395 INFO [train.py:842] (3/4) Epoch 24, batch 2900, loss[loss=0.1959, simple_loss=0.2815, pruned_loss=0.05516, over 7298.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2693, pruned_loss=0.04679, over 1422037.15 frames.], batch size: 25, lr: 2.30e-04
2022-05-28 11:40:41,510 INFO [train.py:842] (3/4) Epoch 24, batch 2950, loss[loss=0.1464, simple_loss=0.2175, pruned_loss=0.03761, over 7269.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2687, pruned_loss=0.04682, over 1426182.77 frames.], batch size: 17, lr: 2.30e-04
2022-05-28 11:41:19,741 INFO [train.py:842] (3/4) Epoch 24, batch 3000, loss[loss=0.1828, simple_loss=0.2802, pruned_loss=0.04271, over 7111.00 frames.], tot_loss[loss=0.1825, simple_loss=0.27, pruned_loss=0.04753, over 1421525.34 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:41:19,741 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 11:41:28,713 INFO [train.py:871] (3/4) Epoch 24, validation: loss=0.1662, simple_loss=0.2647, pruned_loss=0.03391, over 868885.00 frames.
2022-05-28 11:42:06,681 INFO [train.py:842] (3/4) Epoch 24, batch 3050, loss[loss=0.1729, simple_loss=0.2616, pruned_loss=0.04213, over 7272.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2706, pruned_loss=0.04852, over 1416659.46 frames.], batch size: 18, lr: 2.30e-04
2022-05-28 11:42:45,181 INFO [train.py:842] (3/4) Epoch 24, batch 3100, loss[loss=0.1932, simple_loss=0.2764, pruned_loss=0.05503, over 6798.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2691, pruned_loss=0.04784, over 1420674.41 frames.], batch size: 31, lr: 2.30e-04
2022-05-28 11:43:23,179 INFO [train.py:842] (3/4) Epoch 24, batch 3150, loss[loss=0.1814, simple_loss=0.2634, pruned_loss=0.04965, over 6977.00 frames.], tot_loss[loss=0.183, simple_loss=0.2696, pruned_loss=0.04817, over 1421711.94 frames.], batch size: 16, lr: 2.30e-04
2022-05-28 11:44:01,735 INFO [train.py:842] (3/4) Epoch 24, batch 3200, loss[loss=0.2247, simple_loss=0.3181, pruned_loss=0.06562, over 7317.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2697, pruned_loss=0.04785, over 1426209.11 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:44:39,937 INFO [train.py:842] (3/4) Epoch 24, batch 3250, loss[loss=0.1381, simple_loss=0.2226, pruned_loss=0.02681, over 7177.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2697, pruned_loss=0.04796, over 1428351.66 frames.], batch size: 18, lr: 2.30e-04
2022-05-28 11:45:18,240 INFO [train.py:842] (3/4) Epoch 24, batch 3300, loss[loss=0.2062, simple_loss=0.2983, pruned_loss=0.05706, over 7298.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2689, pruned_loss=0.04731, over 1428060.35 frames.], batch size: 24, lr: 2.30e-04
2022-05-28 11:45:56,720 INFO [train.py:842] (3/4) Epoch 24, batch 3350, loss[loss=0.2014, simple_loss=0.285, pruned_loss=0.05887, over 7317.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2699, pruned_loss=0.04796, over 1423666.20 frames.], batch size: 24, lr: 2.30e-04
2022-05-28 11:46:35,165 INFO [train.py:842] (3/4) Epoch 24, batch 3400, loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.0332, over 7358.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2691, pruned_loss=0.04761, over 1427360.52 frames.], batch size: 19, lr: 2.30e-04
2022-05-28 11:47:13,097 INFO [train.py:842] (3/4) Epoch 24, batch 3450, loss[loss=0.1809, simple_loss=0.267, pruned_loss=0.04741, over 7346.00 frames.], tot_loss[loss=0.1816, simple_loss=0.269, pruned_loss=0.04711, over 1422589.11 frames.], batch size: 22, lr: 2.30e-04
2022-05-28 11:47:51,623 INFO [train.py:842] (3/4) Epoch 24, batch 3500, loss[loss=0.1419, simple_loss=0.2219, pruned_loss=0.03092, over 6794.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2664, pruned_loss=0.04603, over 1422534.03 frames.], batch size: 15, lr: 2.30e-04
2022-05-28 11:48:29,733 INFO [train.py:842] (3/4) Epoch 24, batch 3550, loss[loss=0.1768, simple_loss=0.2699, pruned_loss=0.04183, over 7123.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2658, pruned_loss=0.04543, over 1424992.21 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:49:17,342 INFO [train.py:842] (3/4) Epoch 24, batch 3600, loss[loss=0.1556, simple_loss=0.2508, pruned_loss=0.03019, over 7062.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2668, pruned_loss=0.04544, over 1423541.45 frames.], batch size: 18, lr: 2.30e-04
2022-05-28 11:49:55,165 INFO [train.py:842] (3/4) Epoch 24, batch 3650, loss[loss=0.1607, simple_loss=0.245, pruned_loss=0.03822, over 7348.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2663, pruned_loss=0.04528, over 1424066.08 frames.], batch size: 19, lr: 2.30e-04
2022-05-28 11:50:33,274 INFO [train.py:842] (3/4) Epoch 24, batch 3700, loss[loss=0.1904, simple_loss=0.2792, pruned_loss=0.05076, over 6493.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2668, pruned_loss=0.04567, over 1420632.90 frames.], batch size: 38, lr: 2.30e-04
2022-05-28 11:51:11,253 INFO [train.py:842] (3/4) Epoch 24, batch 3750, loss[loss=0.1579, simple_loss=0.2407, pruned_loss=0.03753, over 7268.00 frames.], tot_loss[loss=0.1805, simple_loss=0.268, pruned_loss=0.04645, over 1422481.64 frames.], batch size: 18, lr: 2.30e-04
2022-05-28 11:51:49,645 INFO [train.py:842] (3/4) Epoch 24, batch 3800, loss[loss=0.145, simple_loss=0.2384, pruned_loss=0.02578, over 7429.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2681, pruned_loss=0.04648, over 1424442.52 frames.], batch size: 20, lr: 2.30e-04
2022-05-28 11:52:27,532 INFO [train.py:842] (3/4) Epoch 24, batch 3850, loss[loss=0.2805, simple_loss=0.356, pruned_loss=0.1025, over 4604.00 frames.], tot_loss[loss=0.181, simple_loss=0.2684, pruned_loss=0.04683, over 1419847.81 frames.], batch size: 52, lr: 2.30e-04
2022-05-28 11:53:05,686 INFO [train.py:842] (3/4) Epoch 24, batch 3900, loss[loss=0.169, simple_loss=0.2618, pruned_loss=0.03811, over 6854.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2686, pruned_loss=0.0472, over 1416618.72 frames.], batch size: 31, lr: 2.30e-04
2022-05-28 11:53:43,325 INFO [train.py:842] (3/4) Epoch 24, batch 3950, loss[loss=0.2136, simple_loss=0.3056, pruned_loss=0.06076, over 7316.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2694, pruned_loss=0.04743, over 1417082.09 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:54:21,407 INFO [train.py:842] (3/4) Epoch 24, batch 4000, loss[loss=0.177, simple_loss=0.2626, pruned_loss=0.0457, over 7163.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2693, pruned_loss=0.04729, over 1417928.18 frames.], batch size: 19, lr: 2.30e-04
2022-05-28 11:54:59,375 INFO [train.py:842] (3/4) Epoch 24, batch 4050, loss[loss=0.1738, simple_loss=0.2665, pruned_loss=0.04057, over 7417.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2688, pruned_loss=0.04669, over 1421916.83 frames.], batch size: 21, lr: 2.30e-04
2022-05-28 11:55:37,624 INFO [train.py:842] (3/4) Epoch 24, batch 4100, loss[loss=0.2388, simple_loss=0.3201, pruned_loss=0.07869, over 7320.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2686, pruned_loss=0.04658, over 1420750.18 frames.], batch size: 24, lr: 2.30e-04
2022-05-28 11:56:15,705 INFO [train.py:842] (3/4) Epoch 24, batch 4150, loss[loss=0.1695, simple_loss=0.2491, pruned_loss=0.04492, over 7261.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2702, pruned_loss=0.04759, over 1425712.28 frames.], batch size: 19, lr: 2.30e-04
2022-05-28 11:56:54,004 INFO [train.py:842] (3/4) Epoch 24, batch 4200, loss[loss=0.1906, simple_loss=0.2676, pruned_loss=0.05678, over 4848.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2685, pruned_loss=0.04689, over 1423220.29 frames.], batch size: 53, lr: 2.29e-04
2022-05-28 11:57:31,912 INFO [train.py:842] (3/4) Epoch 24, batch 4250, loss[loss=0.1359, simple_loss=0.2165, pruned_loss=0.02766, over 7120.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2679, pruned_loss=0.04714, over 1427233.90 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 11:58:10,160 INFO [train.py:842] (3/4) Epoch 24, batch 4300, loss[loss=0.2051, simple_loss=0.2947, pruned_loss=0.05777, over 7218.00 frames.], tot_loss[loss=0.182, simple_loss=0.2686, pruned_loss=0.04774, over 1423485.69 frames.], batch size: 21, lr: 2.29e-04
2022-05-28 11:58:48,032 INFO [train.py:842] (3/4) Epoch 24, batch 4350, loss[loss=0.194, simple_loss=0.2901, pruned_loss=0.04893, over 7330.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2686, pruned_loss=0.04748, over 1422169.14 frames.], batch size: 20, lr: 2.29e-04
2022-05-28 11:59:26,290 INFO [train.py:842] (3/4) Epoch 24, batch 4400, loss[loss=0.18, simple_loss=0.2774, pruned_loss=0.04128, over 7422.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2682, pruned_loss=0.04658, over 1422897.71 frames.], batch size: 21, lr: 2.29e-04
2022-05-28 12:00:04,054 INFO [train.py:842] (3/4) Epoch 24, batch 4450, loss[loss=0.1645, simple_loss=0.2487, pruned_loss=0.04014, over 7140.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2686, pruned_loss=0.04658, over 1421036.58 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:00:42,354 INFO [train.py:842] (3/4) Epoch 24, batch 4500, loss[loss=0.168, simple_loss=0.2416, pruned_loss=0.04717, over 7135.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2686, pruned_loss=0.04674, over 1422682.01 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:01:20,181 INFO [train.py:842] (3/4) Epoch 24, batch 4550, loss[loss=0.1587, simple_loss=0.2389, pruned_loss=0.03927, over 7352.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2685, pruned_loss=0.04663, over 1422135.09 frames.], batch size: 19, lr: 2.29e-04
2022-05-28 12:02:01,227 INFO [train.py:842] (3/4) Epoch 24, batch 4600, loss[loss=0.125, simple_loss=0.2043, pruned_loss=0.02286, over 7288.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2671, pruned_loss=0.04624, over 1427262.12 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:02:38,970 INFO [train.py:842] (3/4) Epoch 24, batch 4650, loss[loss=0.1754, simple_loss=0.2701, pruned_loss=0.04035, over 6804.00 frames.], tot_loss[loss=0.1806, simple_loss=0.268, pruned_loss=0.04654, over 1425267.23 frames.], batch size: 31, lr: 2.29e-04
2022-05-28 12:03:17,227 INFO [train.py:842] (3/4) Epoch 24, batch 4700, loss[loss=0.1506, simple_loss=0.2382, pruned_loss=0.03144, over 7133.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2677, pruned_loss=0.04641, over 1424033.25 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:03:55,145 INFO [train.py:842] (3/4) Epoch 24, batch 4750, loss[loss=0.1557, simple_loss=0.2476, pruned_loss=0.03189, over 7159.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2672, pruned_loss=0.04602, over 1423881.33 frames.], batch size: 18, lr: 2.29e-04
2022-05-28 12:04:33,317 INFO [train.py:842] (3/4) Epoch 24, batch 4800, loss[loss=0.1805, simple_loss=0.2748, pruned_loss=0.04314, over 7018.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2679, pruned_loss=0.04641, over 1425428.09 frames.], batch size: 28, lr: 2.29e-04
2022-05-28 12:05:10,969 INFO [train.py:842] (3/4) Epoch 24, batch 4850, loss[loss=0.1641, simple_loss=0.2618, pruned_loss=0.0332, over 6374.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2686, pruned_loss=0.04684, over 1419840.79 frames.], batch size: 38, lr: 2.29e-04
2022-05-28 12:05:49,024 INFO [train.py:842] (3/4) Epoch 24, batch 4900, loss[loss=0.1775, simple_loss=0.2574, pruned_loss=0.04877, over 7417.00 frames.], tot_loss[loss=0.181, simple_loss=0.2684, pruned_loss=0.0468, over 1418749.00 frames.], batch size: 18, lr: 2.29e-04
2022-05-28 12:06:27,197 INFO [train.py:842] (3/4) Epoch 24, batch 4950, loss[loss=0.1708, simple_loss=0.2488, pruned_loss=0.04647, over 7271.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2679, pruned_loss=0.04712, over 1418580.99 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:07:05,416 INFO [train.py:842] (3/4) Epoch 24, batch 5000, loss[loss=0.1858, simple_loss=0.277, pruned_loss=0.0473, over 7215.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2678, pruned_loss=0.04729, over 1417697.57 frames.], batch size: 22, lr: 2.29e-04
2022-05-28 12:07:43,335 INFO [train.py:842] (3/4) Epoch 24, batch 5050, loss[loss=0.2015, simple_loss=0.2784, pruned_loss=0.0623, over 6830.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2677, pruned_loss=0.04749, over 1418963.90 frames.], batch size: 15, lr: 2.29e-04
2022-05-28 12:08:21,587 INFO [train.py:842] (3/4) Epoch 24, batch 5100, loss[loss=0.208, simple_loss=0.2825, pruned_loss=0.06677, over 5004.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2681, pruned_loss=0.04749, over 1419127.74 frames.], batch size: 53, lr: 2.29e-04
2022-05-28 12:08:59,668 INFO [train.py:842] (3/4) Epoch 24, batch 5150, loss[loss=0.1605, simple_loss=0.2494, pruned_loss=0.03579, over 7346.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2678, pruned_loss=0.04692, over 1423735.67 frames.], batch size: 19, lr: 2.29e-04
2022-05-28 12:09:37,932 INFO [train.py:842] (3/4) Epoch 24, batch 5200, loss[loss=0.1677, simple_loss=0.2555, pruned_loss=0.03997, over 7356.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2682, pruned_loss=0.0465, over 1426778.25 frames.], batch size: 19, lr: 2.29e-04
2022-05-28 12:10:16,001 INFO [train.py:842] (3/4) Epoch 24, batch 5250, loss[loss=0.1785, simple_loss=0.2739, pruned_loss=0.0416, over 7378.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2671, pruned_loss=0.04621, over 1428695.58 frames.], batch size: 23, lr: 2.29e-04
2022-05-28 12:10:54,308 INFO [train.py:842] (3/4) Epoch 24, batch 5300, loss[loss=0.1935, simple_loss=0.2865, pruned_loss=0.05027, over 7183.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2678, pruned_loss=0.04607, over 1430730.63 frames.], batch size: 26, lr: 2.29e-04
2022-05-28 12:11:32,306 INFO [train.py:842] (3/4) Epoch 24, batch 5350, loss[loss=0.1899, simple_loss=0.2853, pruned_loss=0.04721, over 7411.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2675, pruned_loss=0.04583, over 1428530.87 frames.], batch size: 21, lr: 2.29e-04
2022-05-28 12:12:10,623 INFO [train.py:842] (3/4) Epoch 24, batch 5400, loss[loss=0.1896, simple_loss=0.278, pruned_loss=0.05065, over 4928.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2672, pruned_loss=0.04575, over 1429414.86 frames.], batch size: 52, lr: 2.29e-04
2022-05-28 12:12:48,588 INFO [train.py:842] (3/4) Epoch 24, batch 5450, loss[loss=0.1974, simple_loss=0.2943, pruned_loss=0.0503, over 7209.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2673, pruned_loss=0.04615, over 1432327.41 frames.], batch size: 23, lr: 2.29e-04
2022-05-28 12:13:26,958 INFO [train.py:842] (3/4) Epoch 24, batch 5500, loss[loss=0.2246, simple_loss=0.2998, pruned_loss=0.07467, over 7123.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2682, pruned_loss=0.04631, over 1426259.08 frames.], batch size: 26, lr: 2.29e-04
2022-05-28 12:14:04,959 INFO [train.py:842] (3/4) Epoch 24, batch 5550, loss[loss=0.2009, simple_loss=0.2907, pruned_loss=0.0556, over 7262.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2682, pruned_loss=0.04633, over 1425432.00 frames.], batch size: 25, lr: 2.29e-04
2022-05-28 12:14:43,530 INFO [train.py:842] (3/4) Epoch 24, batch 5600, loss[loss=0.1667, simple_loss=0.2438, pruned_loss=0.04477, over 7442.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2667, pruned_loss=0.04578, over 1423867.56 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:15:21,849 INFO [train.py:842] (3/4) Epoch 24, batch 5650, loss[loss=0.1732, simple_loss=0.2593, pruned_loss=0.04353, over 7146.00 frames.], tot_loss[loss=0.1792, simple_loss=0.267, pruned_loss=0.04569, over 1423297.10 frames.], batch size: 20, lr: 2.29e-04
2022-05-28 12:16:00,305 INFO [train.py:842] (3/4) Epoch 24, batch 5700, loss[loss=0.1761, simple_loss=0.2635, pruned_loss=0.04438, over 7322.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2679, pruned_loss=0.04643, over 1424079.46 frames.], batch size: 25, lr: 2.29e-04
2022-05-28 12:16:38,567 INFO [train.py:842] (3/4) Epoch 24, batch 5750, loss[loss=0.1777, simple_loss=0.2544, pruned_loss=0.05051, over 7316.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2689, pruned_loss=0.04691, over 1421582.84 frames.], batch size: 17, lr: 2.29e-04
2022-05-28 12:17:17,300 INFO [train.py:842] (3/4) Epoch 24, batch 5800, loss[loss=0.1848, simple_loss=0.2823, pruned_loss=0.04361, over 7214.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2695, pruned_loss=0.04742, over 1421849.43 frames.], batch size: 22, lr: 2.29e-04
2022-05-28 12:17:55,621 INFO [train.py:842] (3/4) Epoch 24, batch 5850, loss[loss=0.1831, simple_loss=0.2721, pruned_loss=0.04704, over 7198.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2695, pruned_loss=0.04817, over 1419934.55 frames.], batch size: 23, lr: 2.29e-04
2022-05-28 12:18:34,454 INFO [train.py:842] (3/4) Epoch 24, batch 5900, loss[loss=0.1506, simple_loss=0.2176, pruned_loss=0.04177, over 6824.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2682, pruned_loss=0.04742, over 1419353.20 frames.], batch size: 15, lr: 2.29e-04
2022-05-28 12:19:12,859 INFO [train.py:842] (3/4) Epoch 24, batch 5950, loss[loss=0.1786, simple_loss=0.2686, pruned_loss=0.04433, over 7159.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2676, pruned_loss=0.04687, over 1420585.25 frames.], batch size: 26, lr: 2.29e-04
2022-05-28 12:19:51,442 INFO [train.py:842] (3/4) Epoch 24, batch 6000, loss[loss=0.2052, simple_loss=0.2784, pruned_loss=0.06598, over 5125.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2665, pruned_loss=0.04637, over 1419247.46 frames.], batch size: 54, lr: 2.29e-04
2022-05-28 12:19:51,443 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 12:20:00,718 INFO [train.py:871] (3/4) Epoch 24, validation: loss=0.166, simple_loss=0.2648, pruned_loss=0.03361, over 868885.00 frames.
2022-05-28 12:20:38,962 INFO [train.py:842] (3/4) Epoch 24, batch 6050, loss[loss=0.1881, simple_loss=0.2877, pruned_loss=0.04426, over 6842.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2665, pruned_loss=0.04627, over 1421393.18 frames.], batch size: 31, lr: 2.29e-04
2022-05-28 12:21:17,786 INFO [train.py:842] (3/4) Epoch 24, batch 6100, loss[loss=0.2176, simple_loss=0.3055, pruned_loss=0.06487, over 7382.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2655, pruned_loss=0.04587, over 1423193.98 frames.], batch size: 23, lr: 2.28e-04
2022-05-28 12:21:56,411 INFO [train.py:842] (3/4) Epoch 24, batch 6150, loss[loss=0.17, simple_loss=0.257, pruned_loss=0.04147, over 7428.00 frames.], tot_loss[loss=0.178, simple_loss=0.2649, pruned_loss=0.04557, over 1423965.22 frames.], batch size: 20, lr: 2.28e-04
2022-05-28 12:22:35,163 INFO [train.py:842] (3/4) Epoch 24, batch 6200, loss[loss=0.1968, simple_loss=0.2777, pruned_loss=0.05794, over 7301.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2664, pruned_loss=0.04626, over 1424251.80 frames.], batch size: 25, lr: 2.28e-04
2022-05-28 12:23:13,729 INFO [train.py:842] (3/4) Epoch 24, batch 6250, loss[loss=0.1718, simple_loss=0.2605, pruned_loss=0.04156, over 7074.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2654, pruned_loss=0.04573, over 1425715.13 frames.], batch size: 28, lr: 2.28e-04
2022-05-28 12:23:52,511 INFO [train.py:842] (3/4) Epoch 24, batch 6300, loss[loss=0.2046, simple_loss=0.288, pruned_loss=0.06064, over 7404.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2665, pruned_loss=0.04649, over 1423620.69 frames.], batch size: 21, lr: 2.28e-04
2022-05-28 12:24:30,647 INFO [train.py:842] (3/4) Epoch 24, batch 6350, loss[loss=0.2216, simple_loss=0.3076, pruned_loss=0.06778, over 6752.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2674, pruned_loss=0.04661, over 1420215.69 frames.], batch size: 31, lr: 2.28e-04
2022-05-28 12:25:09,317 INFO [train.py:842] (3/4) Epoch 24, batch 6400, loss[loss=0.1522, simple_loss=0.2323, pruned_loss=0.03608, over 6997.00 frames.], tot_loss[loss=0.179, simple_loss=0.2662, pruned_loss=0.04591, over 1421094.65 frames.], batch size: 16, lr: 2.28e-04
2022-05-28 12:25:47,751 INFO [train.py:842] (3/4) Epoch 24, batch 6450, loss[loss=0.1918, simple_loss=0.2719, pruned_loss=0.05582, over 6683.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2667, pruned_loss=0.04617, over 1420680.21 frames.], batch size: 31, lr: 2.28e-04
2022-05-28 12:26:26,357 INFO [train.py:842] (3/4) Epoch 24, batch 6500, loss[loss=0.1515, simple_loss=0.2314, pruned_loss=0.03578, over 7002.00 frames.], tot_loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04586, over 1421092.94 frames.], batch size: 16, lr: 2.28e-04
2022-05-28 12:27:04,744 INFO [train.py:842] (3/4) Epoch 24, batch 6550, loss[loss=0.21, simple_loss=0.2959, pruned_loss=0.06203, over 7268.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2669, pruned_loss=0.04594, over 1423785.29 frames.], batch size: 24, lr: 2.28e-04
2022-05-28 12:27:43,576 INFO [train.py:842] (3/4) Epoch 24, batch 6600, loss[loss=0.1905, simple_loss=0.2823, pruned_loss=0.04931, over 7084.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2671, pruned_loss=0.04579, over 1425560.83 frames.], batch size: 28, lr: 2.28e-04
2022-05-28 12:28:22,112 INFO [train.py:842] (3/4) Epoch 24, batch 6650, loss[loss=0.1808, simple_loss=0.2794, pruned_loss=0.04107, over 7328.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2677, pruned_loss=0.04596, over 1427364.79 frames.], batch size: 24, lr: 2.28e-04
2022-05-28 12:29:00,913 INFO [train.py:842] (3/4) Epoch 24, batch 6700, loss[loss=0.1318, simple_loss=0.2217, pruned_loss=0.02098, over 7291.00 frames.], tot_loss[loss=0.179, simple_loss=0.2664, pruned_loss=0.04583, over 1429763.66 frames.], batch size: 17, lr: 2.28e-04
2022-05-28 12:29:39,683 INFO [train.py:842] (3/4) Epoch 24, batch 6750, loss[loss=0.1631, simple_loss=0.2496, pruned_loss=0.03828, over 7154.00 frames.], tot_loss[loss=0.18, simple_loss=0.2669, pruned_loss=0.04659, over 1429344.91 frames.], batch size: 19, lr: 2.28e-04
2022-05-28 12:30:18,214 INFO [train.py:842] (3/4) Epoch 24, batch 6800, loss[loss=0.1588, simple_loss=0.2583, pruned_loss=0.02971, over 7154.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2691, pruned_loss=0.04766, over 1426692.83 frames.], batch size: 20, lr: 2.28e-04
2022-05-28 12:30:56,684 INFO [train.py:842] (3/4) Epoch 24, batch 6850, loss[loss=0.1996, simple_loss=0.2957, pruned_loss=0.05174, over 6270.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2691, pruned_loss=0.04758, over 1426417.91 frames.], batch size: 37, lr: 2.28e-04
2022-05-28 12:31:35,026 INFO [train.py:842] (3/4) Epoch 24, batch 6900, loss[loss=0.1829, simple_loss=0.2698, pruned_loss=0.04797, over 7199.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2699, pruned_loss=0.04772, over 1426808.93 frames.], batch size: 23, lr: 2.28e-04
2022-05-28 12:32:13,554 INFO [train.py:842] (3/4) Epoch 24, batch 6950, loss[loss=0.2014, simple_loss=0.2876, pruned_loss=0.05759, over 7309.00 frames.], tot_loss[loss=0.1831, simple_loss=0.27, pruned_loss=0.04808, over 1428507.83 frames.], batch size: 16, lr: 2.28e-04
2022-05-28 12:32:52,271 INFO [train.py:842] (3/4) Epoch 24, batch 7000, loss[loss=0.1599, simple_loss=0.241, pruned_loss=0.03942, over 7232.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2706, pruned_loss=0.04813, over 1427959.97 frames.], batch size: 16, lr: 2.28e-04
2022-05-28 12:33:30,589 INFO [train.py:842] (3/4) Epoch 24, batch 7050, loss[loss=0.208, simple_loss=0.2975, pruned_loss=0.05922, over 7195.00 frames.], tot_loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04797, over 1428531.33 frames.], batch size: 26, lr: 2.28e-04
2022-05-28 12:34:09,122 INFO [train.py:842] (3/4) Epoch 24, batch 7100, loss[loss=0.1763, simple_loss=0.2641, pruned_loss=0.04428, over 7086.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2688, pruned_loss=0.04717, over 1427741.16 frames.], batch size: 28, lr: 2.28e-04
2022-05-28 12:34:47,728 INFO [train.py:842] (3/4) Epoch 24, batch 7150, loss[loss=0.1679, simple_loss=0.2566, pruned_loss=0.03965, over 7153.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2676, pruned_loss=0.04666, over 1427645.54 frames.], batch size: 19, lr: 2.28e-04
2022-05-28 12:35:36,400 INFO [train.py:842] (3/4) Epoch 24, batch 7200, loss[loss=0.2004, simple_loss=0.2889, pruned_loss=0.05597, over 7114.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2686, pruned_loss=0.04697, over 1427782.16 frames.], batch size: 21, lr: 2.28e-04
2022-05-28 12:36:14,997 INFO [train.py:842] (3/4) Epoch 24, batch 7250, loss[loss=0.2296, simple_loss=0.3145, pruned_loss=0.07235, over 7350.00 frames.], tot_loss[loss=0.1808, simple_loss=0.268, pruned_loss=0.04677, over 1432264.35 frames.], batch size: 22, lr: 2.28e-04
2022-05-28 12:36:53,721 INFO [train.py:842] (3/4) Epoch 24, batch 7300, loss[loss=0.1712, simple_loss=0.262, pruned_loss=0.0402, over 7072.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2661, pruned_loss=0.04578, over 1431678.73 frames.], batch size: 18, lr: 2.28e-04
2022-05-28 12:37:32,034 INFO [train.py:842] (3/4) Epoch 24, batch 7350, loss[loss=0.169, simple_loss=0.254, pruned_loss=0.04199, over 6987.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2672, pruned_loss=0.04612, over 1433652.48 frames.], batch size: 16, lr: 2.28e-04
2022-05-28 12:38:10,697 INFO [train.py:842] (3/4) Epoch 24, batch 7400, loss[loss=0.2383, simple_loss=0.3308, pruned_loss=0.07293, over 7240.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2683, pruned_loss=0.04665, over 1432099.18 frames.], batch size: 20, lr: 2.28e-04
2022-05-28 12:38:59,113 INFO [train.py:842] (3/4) Epoch 24, batch 7450, loss[loss=0.1767, simple_loss=0.2638, pruned_loss=0.04473, over 7420.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2677, pruned_loss=0.04624, over 1430406.15 frames.], batch size: 20, lr: 2.28e-04
2022-05-28 12:39:37,724 INFO [train.py:842] (3/4) Epoch 24, batch 7500, loss[loss=0.1648, simple_loss=0.2595, pruned_loss=0.03508, over 7247.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2679, pruned_loss=0.04624, over 1428837.07 frames.], batch size: 19, lr: 2.28e-04
2022-05-28 12:40:26,163 INFO [train.py:842] (3/4) Epoch 24, batch 7550, loss[loss=0.1569, simple_loss=0.2454, pruned_loss=0.03418, over 7349.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2688, pruned_loss=0.04674, over 1428206.41 frames.], batch size: 19, lr: 2.28e-04
2022-05-28 12:41:04,830 INFO [train.py:842] (3/4) Epoch 24, batch 7600, loss[loss=0.2052, simple_loss=0.2888, pruned_loss=0.0608, over 7192.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2694, pruned_loss=0.04693, over 1429208.91 frames.], batch size: 26, lr: 2.28e-04
2022-05-28 12:41:43,345 INFO [train.py:842] (3/4) Epoch 24, batch 7650, loss[loss=0.1906, simple_loss=0.2966, pruned_loss=0.04225, over 7243.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2696, pruned_loss=0.04713, over 1431904.41 frames.], batch size: 25, lr: 2.28e-04
2022-05-28 12:42:22,067 INFO [train.py:842] (3/4) Epoch 24, batch 7700, loss[loss=0.1874, simple_loss=0.279, pruned_loss=0.04788, over 7042.00 frames.], tot_loss[loss=0.1818, simple_loss=0.269, pruned_loss=0.04729, over 1430688.32 frames.], batch size: 28, lr: 2.28e-04
2022-05-28 12:43:00,408 INFO [train.py:842] (3/4) Epoch 24, batch 7750, loss[loss=0.1619, simple_loss=0.2479, pruned_loss=0.03797, over 7358.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2702, pruned_loss=0.04802, over 1430865.20 frames.], batch size: 19, lr: 2.28e-04
2022-05-28 12:43:39,169 INFO [train.py:842] (3/4) Epoch 24, batch 7800, loss[loss=0.2582, simple_loss=0.3229, pruned_loss=0.0968, over 7380.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2708, pruned_loss=0.04853, over 1431833.38 frames.], batch size: 23, lr: 2.28e-04
2022-05-28 12:44:17,737 INFO [train.py:842] (3/4) Epoch 24, batch 7850, loss[loss=0.2159, simple_loss=0.287, pruned_loss=0.07237, over 4879.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2697, pruned_loss=0.04791, over 1428887.05 frames.], batch size: 52, lr: 2.28e-04
2022-05-28 12:44:56,196 INFO [train.py:842] (3/4) Epoch 24, batch 7900, loss[loss=0.2264, simple_loss=0.3033, pruned_loss=0.07476, over 7397.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2713, pruned_loss=0.0488, over 1425288.55 frames.], batch size: 18, lr: 2.28e-04
2022-05-28 12:45:34,551 INFO [train.py:842] (3/4) Epoch 24, batch 7950, loss[loss=0.2264, simple_loss=0.3099, pruned_loss=0.07146, over 6322.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2712, pruned_loss=0.04858, over 1427109.21 frames.], batch size: 37, lr: 2.28e-04
2022-05-28 12:46:13,257 INFO [train.py:842] (3/4) Epoch 24, batch 8000, loss[loss=0.2265, simple_loss=0.3075, pruned_loss=0.07279, over 7275.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2712, pruned_loss=0.04868, over 1419521.19 frames.], batch size: 24, lr: 2.27e-04
2022-05-28 12:46:51,901 INFO [train.py:842] (3/4) Epoch 24, batch 8050, loss[loss=0.165, simple_loss=0.2587, pruned_loss=0.03564, over 6747.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2694, pruned_loss=0.04804, over 1418488.90 frames.], batch size: 31, lr: 2.27e-04
2022-05-28 12:47:30,411 INFO [train.py:842] (3/4) Epoch 24, batch 8100, loss[loss=0.2018, simple_loss=0.2869, pruned_loss=0.05834, over 7291.00 frames.], tot_loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04793, over 1417099.83 frames.], batch size: 24, lr: 2.27e-04
2022-05-28 12:48:08,872 INFO [train.py:842] (3/4) Epoch 24, batch 8150, loss[loss=0.213, simple_loss=0.2942, pruned_loss=0.06589, over 7062.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2691, pruned_loss=0.04737, over 1415058.12 frames.], batch size: 18, lr: 2.27e-04
2022-05-28 12:48:47,294 INFO [train.py:842] (3/4) Epoch 24, batch 8200, loss[loss=0.1733, simple_loss=0.2676, pruned_loss=0.03947, over 7158.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2693, pruned_loss=0.04723, over 1418997.52 frames.], batch size: 19, lr: 2.27e-04
2022-05-28 12:49:25,445 INFO [train.py:842] (3/4) Epoch 24, batch 8250, loss[loss=0.2069, simple_loss=0.2914, pruned_loss=0.06126, over 6496.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2696, pruned_loss=0.04798, over 1420318.82 frames.], batch size: 38, lr: 2.27e-04
2022-05-28 12:50:04,145 INFO [train.py:842] (3/4) Epoch 24, batch 8300, loss[loss=0.1716, simple_loss=0.2562, pruned_loss=0.04353, over 7309.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2697, pruned_loss=0.04782, over 1423272.95 frames.], batch size: 21, lr: 2.27e-04
2022-05-28 12:50:42,590 INFO [train.py:842] (3/4) Epoch 24, batch 8350, loss[loss=0.1879, simple_loss=0.272, pruned_loss=0.05187, over 6939.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2693, pruned_loss=0.04748, over 1421257.37 frames.], batch size: 28, lr: 2.27e-04
2022-05-28 12:51:21,500 INFO [train.py:842] (3/4) Epoch 24, batch 8400, loss[loss=0.1975, simple_loss=0.2672, pruned_loss=0.06383, over 7428.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2686, pruned_loss=0.04709, over 1425787.87 frames.], batch size: 18, lr: 2.27e-04
2022-05-28 12:51:59,862 INFO [train.py:842] (3/4) Epoch 24, batch 8450, loss[loss=0.2298, simple_loss=0.3051, pruned_loss=0.07728, over 6427.00 frames.], tot_loss[loss=0.182, simple_loss=0.2688, pruned_loss=0.04763, over 1425765.46 frames.], batch size: 38, lr: 2.27e-04
2022-05-28 12:52:39,120 INFO [train.py:842] (3/4) Epoch 24, batch 8500, loss[loss=0.1777, simple_loss=0.2629, pruned_loss=0.04626, over 7185.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2688, pruned_loss=0.04773, over 1427744.20 frames.], batch size: 22, lr: 2.27e-04
2022-05-28 12:53:18,124 INFO [train.py:842] (3/4) Epoch 24, batch 8550, loss[loss=0.1931, simple_loss=0.2865, pruned_loss=0.04987, over 7182.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2667, pruned_loss=0.047, over 1427935.03 frames.], batch size: 26, lr: 2.27e-04
2022-05-28 12:53:57,155 INFO [train.py:842] (3/4) Epoch 24, batch 8600, loss[loss=0.1696, simple_loss=0.254, pruned_loss=0.04258, over 7171.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2675, pruned_loss=0.04699, over 1430068.23 frames.], batch size: 18, lr: 2.27e-04
2022-05-28 12:54:35,701 INFO [train.py:842] (3/4) Epoch 24, batch 8650, loss[loss=0.1621, simple_loss=0.2565, pruned_loss=0.03384, over 7240.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2689, pruned_loss=0.04722, over 1424312.84 frames.], batch size: 20, lr: 2.27e-04
2022-05-28 12:55:14,321 INFO [train.py:842] (3/4) Epoch 24, batch 8700, loss[loss=0.1733, simple_loss=0.2537, pruned_loss=0.0464, over 7162.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2691, pruned_loss=0.04707, over 1418608.69 frames.], batch size: 18, lr: 2.27e-04
2022-05-28 12:55:52,916 INFO [train.py:842] (3/4) Epoch 24, batch 8750, loss[loss=0.2497, simple_loss=0.3222, pruned_loss=0.08862, over 7218.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2685, pruned_loss=0.04684, over 1420330.02 frames.], batch size: 23, lr: 2.27e-04
2022-05-28 12:56:31,828 INFO [train.py:842] (3/4) Epoch 24, batch 8800, loss[loss=0.1706, simple_loss=0.2622, pruned_loss=0.03947, over 7215.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2686, pruned_loss=0.04718, over 1420045.27 frames.], batch size: 21, lr: 2.27e-04
2022-05-28 12:57:10,124 INFO [train.py:842] (3/4) Epoch 24, batch 8850, loss[loss=0.1768, simple_loss=0.2626, pruned_loss=0.04555, over 6421.00 frames.], tot_loss[loss=0.182, simple_loss=0.2686, pruned_loss=0.04769, over 1411595.36 frames.], batch size: 38, lr: 2.27e-04
2022-05-28 12:57:48,736 INFO [train.py:842] (3/4) Epoch 24, batch 8900, loss[loss=0.1991, simple_loss=0.2796, pruned_loss=0.0593, over 7197.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2686, pruned_loss=0.04759, over 1400989.18 frames.], batch size: 22, lr: 2.27e-04
2022-05-28 12:58:27,164 INFO [train.py:842] (3/4) Epoch 24, batch 8950, loss[loss=0.2521, simple_loss=0.3183, pruned_loss=0.09293, over 5016.00 frames.], tot_loss[loss=0.181, simple_loss=0.2678, pruned_loss=0.04713, over 1397796.03 frames.], batch size: 52, lr: 2.27e-04
2022-05-28 12:59:05,934 INFO [train.py:842] (3/4) Epoch 24, batch 9000, loss[loss=0.1544, simple_loss=0.2326, pruned_loss=0.03813, over 7176.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2693, pruned_loss=0.04822, over 1392568.60 frames.], batch size: 16, lr: 2.27e-04
2022-05-28 12:59:05,935 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 12:59:15,343 INFO [train.py:871] (3/4) Epoch 24, validation: loss=0.1628, simple_loss=0.2615, pruned_loss=0.03209, over 868885.00 frames.
2022-05-28 12:59:53,643 INFO [train.py:842] (3/4) Epoch 24, batch 9050, loss[loss=0.1779, simple_loss=0.2743, pruned_loss=0.0408, over 7358.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2712, pruned_loss=0.0489, over 1381303.23 frames.], batch size: 23, lr: 2.27e-04
2022-05-28 13:00:31,864 INFO [train.py:842] (3/4) Epoch 24, batch 9100, loss[loss=0.2024, simple_loss=0.2904, pruned_loss=0.05718, over 5380.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2751, pruned_loss=0.05112, over 1334453.38 frames.], batch size: 53, lr: 2.27e-04
2022-05-28 13:01:09,345 INFO [train.py:842] (3/4) Epoch 24, batch 9150, loss[loss=0.206, simple_loss=0.2914, pruned_loss=0.06025, over 5169.00 frames.], tot_loss[loss=0.193, simple_loss=0.2784, pruned_loss=0.05377, over 1258316.17 frames.], batch size: 54, lr: 2.27e-04
2022-05-28 13:02:00,937 INFO [train.py:842] (3/4) Epoch 25, batch 0, loss[loss=0.2148, simple_loss=0.2954, pruned_loss=0.06708, over 7059.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2954, pruned_loss=0.06708, over 7059.00 frames.], batch size: 18, lr: 2.22e-04
2022-05-28 13:02:39,747 INFO [train.py:842] (3/4) Epoch 25, batch 50, loss[loss=0.1852, simple_loss=0.2734, pruned_loss=0.04853, over 7249.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2673, pruned_loss=0.04651, over 322058.80 frames.], batch size: 19, lr: 2.22e-04
2022-05-28 13:03:18,849 INFO [train.py:842] (3/4) Epoch 25, batch 100, loss[loss=0.1847, simple_loss=0.267, pruned_loss=0.05123, over 7326.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2683, pruned_loss=0.04697, over 569948.38 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:03:57,396 INFO [train.py:842] (3/4) Epoch 25, batch 150, loss[loss=0.1667, simple_loss=0.2618, pruned_loss=0.0358, over 7326.00 frames.], tot_loss[loss=0.18, simple_loss=0.2679, pruned_loss=0.04603, over 761082.02 frames.], batch size: 21, lr: 2.22e-04
2022-05-28 13:04:36,573 INFO [train.py:842] (3/4) Epoch 25, batch 200, loss[loss=0.1431, simple_loss=0.2338, pruned_loss=0.0262, over 7212.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2658, pruned_loss=0.04527, over 906597.01 frames.], batch size: 16, lr: 2.22e-04
2022-05-28 13:05:14,877 INFO [train.py:842] (3/4) Epoch 25, batch 250, loss[loss=0.2032, simple_loss=0.29, pruned_loss=0.05821, over 7229.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2668, pruned_loss=0.04579, over 1018964.75 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:05:53,577 INFO [train.py:842] (3/4) Epoch 25, batch 300, loss[loss=0.136, simple_loss=0.2317, pruned_loss=0.02014, over 7165.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2676, pruned_loss=0.04626, over 1112225.26 frames.], batch size: 19, lr: 2.22e-04
2022-05-28 13:06:31,938 INFO [train.py:842] (3/4) Epoch 25, batch 350, loss[loss=0.193, simple_loss=0.2728, pruned_loss=0.05657, over 7194.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2671, pruned_loss=0.04608, over 1181159.52 frames.], batch size: 23, lr: 2.22e-04
2022-05-28 13:07:10,738 INFO [train.py:842] (3/4) Epoch 25, batch 400, loss[loss=0.1617, simple_loss=0.254, pruned_loss=0.03472, over 7229.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2666, pruned_loss=0.04593, over 1235841.27 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:07:49,150 INFO [train.py:842] (3/4) Epoch 25, batch 450, loss[loss=0.1718, simple_loss=0.2639, pruned_loss=0.0399, over 7065.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2657, pruned_loss=0.04557, over 1276869.77 frames.], batch size: 28, lr: 2.22e-04
2022-05-28 13:08:27,861 INFO [train.py:842] (3/4) Epoch 25, batch 500, loss[loss=0.1453, simple_loss=0.228, pruned_loss=0.03127, over 7162.00 frames.], tot_loss[loss=0.1786, simple_loss=0.266, pruned_loss=0.04566, over 1312331.66 frames.], batch size: 18, lr: 2.22e-04
2022-05-28 13:09:06,206 INFO [train.py:842] (3/4) Epoch 25, batch 550, loss[loss=0.1482, simple_loss=0.2361, pruned_loss=0.03015, over 7159.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2658, pruned_loss=0.04538, over 1338905.55 frames.], batch size: 18, lr: 2.22e-04
2022-05-28 13:09:45,032 INFO [train.py:842] (3/4) Epoch 25, batch 600, loss[loss=0.2517, simple_loss=0.333, pruned_loss=0.0852, over 7168.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2674, pruned_loss=0.04658, over 1357864.02 frames.], batch size: 23, lr: 2.22e-04
2022-05-28 13:10:23,513 INFO [train.py:842] (3/4) Epoch 25, batch 650, loss[loss=0.1461, simple_loss=0.2258, pruned_loss=0.03315, over 7273.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2663, pruned_loss=0.0461, over 1370041.10 frames.], batch size: 17, lr: 2.22e-04
2022-05-28 13:11:02,302 INFO [train.py:842] (3/4) Epoch 25, batch 700, loss[loss=0.1449, simple_loss=0.2276, pruned_loss=0.03108, over 6819.00 frames.], tot_loss[loss=0.1784, simple_loss=0.266, pruned_loss=0.04543, over 1386019.49 frames.], batch size: 15, lr: 2.22e-04
2022-05-28 13:11:40,752 INFO [train.py:842] (3/4) Epoch 25, batch 750, loss[loss=0.1728, simple_loss=0.2638, pruned_loss=0.04085, over 7244.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2662, pruned_loss=0.04553, over 1396903.68 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:12:19,438 INFO [train.py:842] (3/4) Epoch 25, batch 800, loss[loss=0.2065, simple_loss=0.2956, pruned_loss=0.0587, over 7409.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2675, pruned_loss=0.04589, over 1404835.91 frames.], batch size: 21, lr: 2.22e-04
2022-05-28 13:12:57,618 INFO [train.py:842] (3/4) Epoch 25, batch 850, loss[loss=0.1774, simple_loss=0.2748, pruned_loss=0.04004, over 7317.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2671, pruned_loss=0.04602, over 1407396.56 frames.], batch size: 21, lr: 2.22e-04
2022-05-28 13:13:36,195 INFO [train.py:842] (3/4) Epoch 25, batch 900, loss[loss=0.1734, simple_loss=0.2761, pruned_loss=0.03534, over 7290.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2682, pruned_loss=0.04636, over 1409966.59 frames.], batch size: 25, lr: 2.22e-04
2022-05-28 13:14:14,473 INFO [train.py:842] (3/4) Epoch 25, batch 950, loss[loss=0.2092, simple_loss=0.2793, pruned_loss=0.0696, over 5188.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2689, pruned_loss=0.04694, over 1404537.22 frames.], batch size: 53, lr: 2.22e-04
2022-05-28 13:14:53,228 INFO [train.py:842] (3/4) Epoch 25, batch 1000, loss[loss=0.1775, simple_loss=0.2649, pruned_loss=0.04503, over 7419.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2696, pruned_loss=0.04701, over 1410792.22 frames.], batch size: 21, lr: 2.22e-04
2022-05-28 13:15:31,617 INFO [train.py:842] (3/4) Epoch 25, batch 1050, loss[loss=0.1629, simple_loss=0.2559, pruned_loss=0.03501, over 7315.00 frames.], tot_loss[loss=0.1832, simple_loss=0.271, pruned_loss=0.04774, over 1417739.23 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:16:10,346 INFO [train.py:842] (3/4) Epoch 25, batch 1100, loss[loss=0.1646, simple_loss=0.2665, pruned_loss=0.03133, over 7347.00 frames.], tot_loss[loss=0.182, simple_loss=0.2696, pruned_loss=0.04724, over 1420714.88 frames.], batch size: 22, lr: 2.22e-04
2022-05-28 13:16:48,961 INFO [train.py:842] (3/4) Epoch 25, batch 1150, loss[loss=0.1778, simple_loss=0.2666, pruned_loss=0.04446, over 7203.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2689, pruned_loss=0.04678, over 1423403.13 frames.], batch size: 23, lr: 2.22e-04
2022-05-28 13:17:27,822 INFO [train.py:842] (3/4) Epoch 25, batch 1200, loss[loss=0.1757, simple_loss=0.2694, pruned_loss=0.04095, over 7387.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2686, pruned_loss=0.04748, over 1422757.57 frames.], batch size: 23, lr: 2.22e-04
2022-05-28 13:18:06,186 INFO [train.py:842] (3/4) Epoch 25, batch 1250, loss[loss=0.1633, simple_loss=0.259, pruned_loss=0.0338, over 7144.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2677, pruned_loss=0.04688, over 1421844.40 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:18:44,996 INFO [train.py:842] (3/4) Epoch 25, batch 1300, loss[loss=0.2772, simple_loss=0.3159, pruned_loss=0.1193, over 7240.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2679, pruned_loss=0.0472, over 1421557.85 frames.], batch size: 16, lr: 2.22e-04
2022-05-28 13:19:23,290 INFO [train.py:842] (3/4) Epoch 25, batch 1350, loss[loss=0.2385, simple_loss=0.3165, pruned_loss=0.08025, over 6325.00 frames.], tot_loss[loss=0.1814, simple_loss=0.268, pruned_loss=0.04738, over 1421289.68 frames.], batch size: 37, lr: 2.22e-04
2022-05-28 13:20:01,956 INFO [train.py:842] (3/4) Epoch 25, batch 1400, loss[loss=0.1615, simple_loss=0.2406, pruned_loss=0.04114, over 7280.00 frames.], tot_loss[loss=0.181, simple_loss=0.2682, pruned_loss=0.04691, over 1426417.96 frames.], batch size: 17, lr: 2.22e-04
2022-05-28 13:20:40,269 INFO [train.py:842] (3/4) Epoch 25, batch 1450, loss[loss=0.174, simple_loss=0.2683, pruned_loss=0.03986, over 7150.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2676, pruned_loss=0.04654, over 1422470.19 frames.], batch size: 20, lr: 2.22e-04
2022-05-28 13:21:18,927 INFO [train.py:842] (3/4) Epoch 25, batch 1500, loss[loss=0.175, simple_loss=0.2695, pruned_loss=0.04028, over 6783.00 frames.], tot_loss[loss=0.1796, simple_loss=0.267, pruned_loss=0.04613, over 1421378.65 frames.], batch size: 31, lr: 2.22e-04
2022-05-28 13:21:57,246 INFO [train.py:842] (3/4) Epoch 25, batch 1550, loss[loss=0.1793, simple_loss=0.2707, pruned_loss=0.04396, over 7283.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2678, pruned_loss=0.04594, over 1422459.03 frames.], batch size: 18, lr: 2.22e-04
2022-05-28 13:22:36,329 INFO [train.py:842] (3/4) Epoch 25, batch 1600, loss[loss=0.1462, simple_loss=0.2296, pruned_loss=0.03141, over 7258.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2679, pruned_loss=0.046, over 1421944.41 frames.], batch size: 16, lr: 2.22e-04
2022-05-28 13:23:14,839 INFO [train.py:842] (3/4) Epoch 25, batch 1650, loss[loss=0.2107, simple_loss=0.2985, pruned_loss=0.06144, over 7226.00 frames.], tot_loss[loss=0.1802, simple_loss=0.268, pruned_loss=0.04615, over 1423246.72 frames.], batch size: 21, lr: 2.22e-04
2022-05-28 13:23:53,572 INFO [train.py:842] (3/4) Epoch 25, batch 1700, loss[loss=0.1857, simple_loss=0.2762, pruned_loss=0.04763, over 7373.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2678, pruned_loss=0.04599, over 1422157.99 frames.], batch size: 23, lr: 2.22e-04
2022-05-28 13:24:31,719 INFO [train.py:842] (3/4) Epoch 25, batch 1750, loss[loss=0.2203, simple_loss=0.2836, pruned_loss=0.07849, over 7140.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2683, pruned_loss=0.04662, over 1424260.85 frames.], batch size: 17, lr: 2.22e-04
2022-05-28 13:25:10,180 INFO [train.py:842] (3/4) Epoch 25, batch 1800, loss[loss=0.1624, simple_loss=0.2421, pruned_loss=0.04131, over 6979.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2697, pruned_loss=0.04707, over 1423869.68 frames.], batch size: 16, lr: 2.21e-04
2022-05-28 13:25:48,935 INFO [train.py:842] (3/4) Epoch 25, batch 1850, loss[loss=0.1627, simple_loss=0.2407, pruned_loss=0.04232, over 7208.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2683, pruned_loss=0.04658, over 1421117.98 frames.], batch size: 16, lr: 2.21e-04
2022-05-28 13:26:27,667 INFO [train.py:842] (3/4) Epoch 25, batch 1900, loss[loss=0.2313, simple_loss=0.3155, pruned_loss=0.07359, over 7255.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2676, pruned_loss=0.04634, over 1423132.58 frames.], batch size: 25, lr: 2.21e-04
2022-05-28 13:27:06,030 INFO [train.py:842] (3/4) Epoch 25, batch 1950, loss[loss=0.1713, simple_loss=0.2609, pruned_loss=0.04081, over 7265.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2667, pruned_loss=0.04588, over 1425247.91 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:27:44,823 INFO [train.py:842] (3/4) Epoch 25, batch 2000, loss[loss=0.1711, simple_loss=0.2471, pruned_loss=0.04757, over 7154.00 frames.], tot_loss[loss=0.179, simple_loss=0.2661, pruned_loss=0.04593, over 1425325.77 frames.], batch size: 18, lr: 2.21e-04
2022-05-28 13:28:23,563 INFO [train.py:842] (3/4) Epoch 25, batch 2050, loss[loss=0.1561, simple_loss=0.2495, pruned_loss=0.03141, over 7322.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2658, pruned_loss=0.04599, over 1428030.18 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:29:02,063 INFO [train.py:842] (3/4) Epoch 25, batch 2100, loss[loss=0.2002, simple_loss=0.2795, pruned_loss=0.06046, over 7275.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2658, pruned_loss=0.04597, over 1424517.71 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:29:40,348 INFO [train.py:842] (3/4) Epoch 25, batch 2150, loss[loss=0.1782, simple_loss=0.2665, pruned_loss=0.04491, over 7415.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2671, pruned_loss=0.04657, over 1423410.86 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:30:19,182 INFO [train.py:842] (3/4) Epoch 25, batch 2200, loss[loss=0.2013, simple_loss=0.2784, pruned_loss=0.06206, over 6854.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2677, pruned_loss=0.04703, over 1421289.96 frames.], batch size: 15, lr: 2.21e-04
2022-05-28 13:30:57,864 INFO [train.py:842] (3/4) Epoch 25, batch 2250, loss[loss=0.1469, simple_loss=0.2329, pruned_loss=0.03046, over 7066.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2677, pruned_loss=0.0474, over 1417104.57 frames.], batch size: 18, lr: 2.21e-04
2022-05-28 13:31:36,586 INFO [train.py:842] (3/4) Epoch 25, batch 2300, loss[loss=0.178, simple_loss=0.257, pruned_loss=0.04952, over 6773.00 frames.], tot_loss[loss=0.1803, simple_loss=0.267, pruned_loss=0.04678, over 1418088.62 frames.], batch size: 15, lr: 2.21e-04
2022-05-28 13:32:14,943 INFO [train.py:842] (3/4) Epoch 25, batch 2350, loss[loss=0.2108, simple_loss=0.3019, pruned_loss=0.05991, over 7316.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2663, pruned_loss=0.04637, over 1418357.52 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:32:53,610 INFO [train.py:842] (3/4) Epoch 25, batch 2400, loss[loss=0.1817, simple_loss=0.2635, pruned_loss=0.04991, over 7364.00 frames.], tot_loss[loss=0.1796, simple_loss=0.267, pruned_loss=0.04612, over 1423360.79 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:33:32,118 INFO [train.py:842] (3/4) Epoch 25, batch 2450, loss[loss=0.139, simple_loss=0.2305, pruned_loss=0.02375, over 7152.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2668, pruned_loss=0.04596, over 1423313.82 frames.], batch size: 17, lr: 2.21e-04
2022-05-28 13:34:10,900 INFO [train.py:842] (3/4) Epoch 25, batch 2500, loss[loss=0.191, simple_loss=0.2831, pruned_loss=0.04942, over 7412.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2673, pruned_loss=0.04608, over 1424472.27 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:34:49,188 INFO [train.py:842] (3/4) Epoch 25, batch 2550, loss[loss=0.1472, simple_loss=0.2419, pruned_loss=0.02629, over 7433.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2671, pruned_loss=0.04569, over 1425490.18 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:35:27,896 INFO [train.py:842] (3/4) Epoch 25, batch 2600, loss[loss=0.1416, simple_loss=0.2251, pruned_loss=0.02903, over 7130.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2666, pruned_loss=0.04561, over 1422236.98 frames.], batch size: 17, lr: 2.21e-04
2022-05-28 13:36:06,377 INFO [train.py:842] (3/4) Epoch 25, batch 2650, loss[loss=0.2498, simple_loss=0.3217, pruned_loss=0.0889, over 7200.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2668, pruned_loss=0.04542, over 1423801.38 frames.], batch size: 22, lr: 2.21e-04
2022-05-28 13:36:45,200 INFO [train.py:842] (3/4) Epoch 25, batch 2700, loss[loss=0.1669, simple_loss=0.2494, pruned_loss=0.04216, over 7062.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2665, pruned_loss=0.04535, over 1425807.82 frames.], batch size: 18, lr: 2.21e-04
2022-05-28 13:37:23,660 INFO [train.py:842] (3/4) Epoch 25, batch 2750, loss[loss=0.1689, simple_loss=0.2634, pruned_loss=0.0372, over 7138.00 frames.], tot_loss[loss=0.1784, simple_loss=0.266, pruned_loss=0.04543, over 1421044.47 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:38:02,447 INFO [train.py:842] (3/4) Epoch 25, batch 2800, loss[loss=0.1355, simple_loss=0.2302, pruned_loss=0.02037, over 7242.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2661, pruned_loss=0.0457, over 1421849.01 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:38:40,762 INFO [train.py:842] (3/4) Epoch 25, batch 2850, loss[loss=0.2201, simple_loss=0.3048, pruned_loss=0.06763, over 7432.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2651, pruned_loss=0.04469, over 1420036.48 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:39:19,318 INFO [train.py:842] (3/4) Epoch 25, batch 2900, loss[loss=0.1801, simple_loss=0.2721, pruned_loss=0.044, over 7182.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2657, pruned_loss=0.04495, over 1421178.50 frames.], batch size: 23, lr: 2.21e-04
2022-05-28 13:39:57,703 INFO [train.py:842] (3/4) Epoch 25, batch 2950, loss[loss=0.1688, simple_loss=0.2535, pruned_loss=0.04201, over 7113.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2661, pruned_loss=0.04456, over 1426458.90 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:40:36,697 INFO [train.py:842] (3/4) Epoch 25, batch 3000, loss[loss=0.1531, simple_loss=0.2569, pruned_loss=0.02462, over 6804.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2646, pruned_loss=0.04426, over 1429568.27 frames.], batch size: 31, lr: 2.21e-04
2022-05-28 13:40:36,699 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 13:40:46,045 INFO [train.py:871] (3/4) Epoch 25, validation: loss=0.1651, simple_loss=0.2634, pruned_loss=0.03341, over 868885.00 frames.
2022-05-28 13:41:24,586 INFO [train.py:842] (3/4) Epoch 25, batch 3050, loss[loss=0.208, simple_loss=0.3029, pruned_loss=0.05658, over 7119.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2658, pruned_loss=0.04523, over 1430187.93 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:42:03,501 INFO [train.py:842] (3/4) Epoch 25, batch 3100, loss[loss=0.178, simple_loss=0.2595, pruned_loss=0.04827, over 7252.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2648, pruned_loss=0.04507, over 1429765.74 frames.], batch size: 16, lr: 2.21e-04
2022-05-28 13:42:41,831 INFO [train.py:842] (3/4) Epoch 25, batch 3150, loss[loss=0.1644, simple_loss=0.2507, pruned_loss=0.03911, over 7255.00 frames.], tot_loss[loss=0.1775, simple_loss=0.265, pruned_loss=0.04502, over 1430217.20 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:43:20,553 INFO [train.py:842] (3/4) Epoch 25, batch 3200, loss[loss=0.2129, simple_loss=0.2962, pruned_loss=0.06483, over 5237.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2659, pruned_loss=0.04584, over 1429337.22 frames.], batch size: 52, lr: 2.21e-04
2022-05-28 13:43:59,062 INFO [train.py:842] (3/4) Epoch 25, batch 3250, loss[loss=0.2298, simple_loss=0.3141, pruned_loss=0.07271, over 7239.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2676, pruned_loss=0.04669, over 1427495.81 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:44:37,664 INFO [train.py:842] (3/4) Epoch 25, batch 3300, loss[loss=0.1678, simple_loss=0.2699, pruned_loss=0.03288, over 7171.00 frames.], tot_loss[loss=0.18, simple_loss=0.2672, pruned_loss=0.04642, over 1426766.84 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:45:16,124 INFO [train.py:842] (3/4) Epoch 25, batch 3350, loss[loss=0.1888, simple_loss=0.2659, pruned_loss=0.05587, over 7265.00 frames.], tot_loss[loss=0.181, simple_loss=0.2681, pruned_loss=0.04695, over 1423838.37 frames.], batch size: 19, lr: 2.21e-04
2022-05-28 13:45:57,679 INFO [train.py:842] (3/4) Epoch 25, batch 3400, loss[loss=0.1394, simple_loss=0.2213, pruned_loss=0.02877, over 7282.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2682, pruned_loss=0.04736, over 1425145.98 frames.], batch size: 17, lr: 2.21e-04
2022-05-28 13:46:36,043 INFO [train.py:842] (3/4) Epoch 25, batch 3450, loss[loss=0.1869, simple_loss=0.2771, pruned_loss=0.04835, over 7225.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2694, pruned_loss=0.04818, over 1421457.03 frames.], batch size: 21, lr: 2.21e-04
2022-05-28 13:47:14,712 INFO [train.py:842] (3/4) Epoch 25, batch 3500, loss[loss=0.1645, simple_loss=0.2499, pruned_loss=0.03954, over 7135.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2704, pruned_loss=0.04841, over 1422989.65 frames.], batch size: 17, lr: 2.21e-04
2022-05-28 13:47:52,983 INFO [train.py:842] (3/4) Epoch 25, batch 3550, loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.0377, over 7334.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2704, pruned_loss=0.04804, over 1423795.05 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:48:31,620 INFO [train.py:842] (3/4) Epoch 25, batch 3600, loss[loss=0.2485, simple_loss=0.3187, pruned_loss=0.08914, over 7192.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2706, pruned_loss=0.04802, over 1422059.52 frames.], batch size: 23, lr: 2.21e-04
2022-05-28 13:49:09,898 INFO [train.py:842] (3/4) Epoch 25, batch 3650, loss[loss=0.1813, simple_loss=0.2723, pruned_loss=0.0451, over 6471.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2707, pruned_loss=0.04814, over 1418641.79 frames.], batch size: 38, lr: 2.21e-04
2022-05-28 13:49:48,744 INFO [train.py:842] (3/4) Epoch 25, batch 3700, loss[loss=0.1725, simple_loss=0.2692, pruned_loss=0.03793, over 7429.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2697, pruned_loss=0.048, over 1421316.71 frames.], batch size: 20, lr: 2.21e-04
2022-05-28 13:50:27,340 INFO [train.py:842] (3/4) Epoch 25, batch 3750, loss[loss=0.202, simple_loss=0.2915, pruned_loss=0.05625, over 7371.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2686, pruned_loss=0.04755, over 1423804.46 frames.], batch size: 23, lr: 2.21e-04
2022-05-28 13:51:06,210 INFO [train.py:842] (3/4) Epoch 25, batch 3800, loss[loss=0.238, simple_loss=0.3163, pruned_loss=0.07982, over 4919.00 frames.], tot_loss[loss=0.181, simple_loss=0.268, pruned_loss=0.04703, over 1421585.17 frames.], batch size: 52, lr: 2.21e-04
2022-05-28 13:51:44,472 INFO [train.py:842] (3/4) Epoch 25, batch 3850, loss[loss=0.1415, simple_loss=0.2337, pruned_loss=0.02466, over 7283.00 frames.], tot_loss[loss=0.1808, simple_loss=0.268, pruned_loss=0.04683, over 1421089.66 frames.], batch size: 18, lr: 2.20e-04
2022-05-28 13:52:23,078 INFO [train.py:842] (3/4) Epoch 25, batch 3900, loss[loss=0.1819, simple_loss=0.2735, pruned_loss=0.04518, over 7257.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2685, pruned_loss=0.04705, over 1421431.11 frames.], batch size: 19, lr: 2.20e-04
2022-05-28 13:53:01,454 INFO [train.py:842] (3/4) Epoch 25, batch 3950, loss[loss=0.1451, simple_loss=0.2279, pruned_loss=0.03116, over 7398.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2678, pruned_loss=0.04662, over 1423420.63 frames.], batch size: 18, lr: 2.20e-04
2022-05-28 13:53:40,185 INFO [train.py:842] (3/4) Epoch 25, batch 4000, loss[loss=0.1709, simple_loss=0.2643, pruned_loss=0.03877, over 7408.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2678, pruned_loss=0.04628, over 1424798.89 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 13:54:18,687 INFO [train.py:842] (3/4) Epoch 25, batch 4050, loss[loss=0.1861, simple_loss=0.2576, pruned_loss=0.05732, over 7133.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2671, pruned_loss=0.04593, over 1424126.77 frames.], batch size: 17, lr: 2.20e-04
2022-05-28 13:54:57,374 INFO [train.py:842] (3/4) Epoch 25, batch 4100, loss[loss=0.1662, simple_loss=0.257, pruned_loss=0.03772, over 7322.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2673, pruned_loss=0.04589, over 1427657.28 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 13:55:35,869 INFO [train.py:842] (3/4) Epoch 25, batch 4150, loss[loss=0.1616, simple_loss=0.2587, pruned_loss=0.03222, over 7421.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2675, pruned_loss=0.04631, over 1423801.37 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 13:56:14,592 INFO [train.py:842] (3/4) Epoch 25, batch 4200, loss[loss=0.1836, simple_loss=0.2801, pruned_loss=0.04357, over 7222.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2684, pruned_loss=0.04687, over 1420971.61 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 13:56:52,845 INFO [train.py:842] (3/4) Epoch 25, batch 4250, loss[loss=0.1975, simple_loss=0.2949, pruned_loss=0.05003, over 7379.00 frames.], tot_loss[loss=0.182, simple_loss=0.2697, pruned_loss=0.04721, over 1423417.35 frames.], batch size: 23, lr: 2.20e-04
2022-05-28 13:57:31,632 INFO [train.py:842] (3/4) Epoch 25, batch 4300, loss[loss=0.1687, simple_loss=0.268, pruned_loss=0.03474, over 6990.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2694, pruned_loss=0.04709, over 1424902.14 frames.], batch size: 28, lr: 2.20e-04
2022-05-28 13:58:10,174 INFO [train.py:842] (3/4) Epoch 25, batch 4350, loss[loss=0.1619, simple_loss=0.2505, pruned_loss=0.03664, over 7409.00 frames.], tot_loss[loss=0.181, simple_loss=0.2683, pruned_loss=0.04688, over 1425523.29 frames.], batch size: 18, lr: 2.20e-04
2022-05-28 13:58:48,819 INFO [train.py:842] (3/4) Epoch 25, batch 4400, loss[loss=0.209, simple_loss=0.3065, pruned_loss=0.05578, over 7228.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2685, pruned_loss=0.04689, over 1424195.53 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 13:59:27,186 INFO [train.py:842] (3/4) Epoch 25, batch 4450, loss[loss=0.2271, simple_loss=0.3066, pruned_loss=0.0738, over 7288.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2681, pruned_loss=0.04661, over 1422398.52 frames.], batch size: 24, lr: 2.20e-04
2022-05-28 14:00:05,960 INFO [train.py:842] (3/4) Epoch 25, batch 4500, loss[loss=0.1672, simple_loss=0.2607, pruned_loss=0.03685, over 7144.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2671, pruned_loss=0.04614, over 1424170.00 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 14:00:44,418 INFO [train.py:842] (3/4) Epoch 25, batch 4550, loss[loss=0.1659, simple_loss=0.2594, pruned_loss=0.03622, over 6495.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2667, pruned_loss=0.04554, over 1424558.08 frames.], batch size: 38, lr: 2.20e-04
2022-05-28 14:01:23,184 INFO [train.py:842] (3/4) Epoch 25, batch 4600, loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03119, over 6777.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04501, over 1423228.35 frames.], batch size: 31, lr: 2.20e-04
2022-05-28 14:02:01,597 INFO [train.py:842] (3/4) Epoch 25, batch 4650, loss[loss=0.2528, simple_loss=0.3278, pruned_loss=0.0889, over 7107.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2659, pruned_loss=0.04532, over 1422192.43 frames.], batch size: 26, lr: 2.20e-04
2022-05-28 14:02:40,413 INFO [train.py:842] (3/4) Epoch 25, batch 4700, loss[loss=0.1647, simple_loss=0.2368, pruned_loss=0.0463, over 6983.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2662, pruned_loss=0.04559, over 1418413.96 frames.], batch size: 16, lr: 2.20e-04
2022-05-28 14:03:18,776 INFO [train.py:842] (3/4) Epoch 25, batch 4750, loss[loss=0.2312, simple_loss=0.3116, pruned_loss=0.0754, over 7276.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2662, pruned_loss=0.04583, over 1420631.69 frames.], batch size: 24, lr: 2.20e-04
2022-05-28 14:03:57,596 INFO [train.py:842] (3/4) Epoch 25, batch 4800, loss[loss=0.199, simple_loss=0.2983, pruned_loss=0.04988, over 7200.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2666, pruned_loss=0.04603, over 1423476.10 frames.], batch size: 22, lr: 2.20e-04
2022-05-28 14:04:36,164 INFO [train.py:842] (3/4) Epoch 25, batch 4850, loss[loss=0.1769, simple_loss=0.264, pruned_loss=0.04492, over 7314.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2667, pruned_loss=0.04601, over 1429184.66 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 14:05:14,796 INFO [train.py:842] (3/4) Epoch 25, batch 4900, loss[loss=0.2142, simple_loss=0.3057, pruned_loss=0.06131, over 7396.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2665, pruned_loss=0.04619, over 1422498.52 frames.], batch size: 23, lr: 2.20e-04
2022-05-28 14:05:53,363 INFO [train.py:842] (3/4) Epoch 25, batch 4950, loss[loss=0.2514, simple_loss=0.3268, pruned_loss=0.08801, over 4703.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2673, pruned_loss=0.04608, over 1420504.73 frames.], batch size: 52, lr: 2.20e-04
2022-05-28 14:06:31,865 INFO [train.py:842] (3/4) Epoch 25, batch 5000, loss[loss=0.1816, simple_loss=0.2689, pruned_loss=0.04715, over 7433.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2677, pruned_loss=0.04639, over 1417436.27 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 14:07:10,248 INFO [train.py:842] (3/4) Epoch 25, batch 5050, loss[loss=0.1734, simple_loss=0.2716, pruned_loss=0.0376, over 7316.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2682, pruned_loss=0.04627, over 1423857.07 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 14:07:49,143 INFO [train.py:842] (3/4) Epoch 25, batch 5100, loss[loss=0.1653, simple_loss=0.2623, pruned_loss=0.03414, over 7152.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2669, pruned_loss=0.0459, over 1425375.91 frames.], batch size: 19, lr: 2.20e-04
2022-05-28 14:08:27,764 INFO [train.py:842] (3/4) Epoch 25, batch 5150, loss[loss=0.1747, simple_loss=0.2686, pruned_loss=0.04038, over 7126.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2674, pruned_loss=0.04647, over 1426307.06 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 14:09:06,407 INFO [train.py:842] (3/4) Epoch 25, batch 5200, loss[loss=0.1937, simple_loss=0.2894, pruned_loss=0.04903, over 7171.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2694, pruned_loss=0.04685, over 1427605.64 frames.], batch size: 26, lr: 2.20e-04
2022-05-28 14:09:44,927 INFO [train.py:842] (3/4) Epoch 25, batch 5250, loss[loss=0.2044, simple_loss=0.2758, pruned_loss=0.06651, over 7346.00 frames.], tot_loss[loss=0.1807, simple_loss=0.268, pruned_loss=0.04666, over 1425139.50 frames.], batch size: 19, lr: 2.20e-04
2022-05-28 14:10:23,859 INFO [train.py:842] (3/4) Epoch 25, batch 5300, loss[loss=0.1931, simple_loss=0.2821, pruned_loss=0.05211, over 7325.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2684, pruned_loss=0.04716, over 1422630.30 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 14:11:02,330 INFO [train.py:842] (3/4) Epoch 25, batch 5350, loss[loss=0.1665, simple_loss=0.2512, pruned_loss=0.04084, over 7357.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2685, pruned_loss=0.04729, over 1417475.91 frames.], batch size: 19, lr: 2.20e-04
2022-05-28 14:11:41,188 INFO [train.py:842] (3/4) Epoch 25, batch 5400, loss[loss=0.1823, simple_loss=0.26, pruned_loss=0.05231, over 7059.00 frames.], tot_loss[loss=0.1799, simple_loss=0.267, pruned_loss=0.04637, over 1423195.75 frames.], batch size: 18, lr: 2.20e-04
2022-05-28 14:12:19,668 INFO [train.py:842] (3/4) Epoch 25, batch 5450, loss[loss=0.1739, simple_loss=0.2549, pruned_loss=0.04645, over 7430.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2669, pruned_loss=0.04635, over 1420480.81 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 14:12:58,326 INFO [train.py:842] (3/4) Epoch 25, batch 5500, loss[loss=0.1679, simple_loss=0.2586, pruned_loss=0.0386, over 6441.00 frames.], tot_loss[loss=0.179, simple_loss=0.266, pruned_loss=0.04601, over 1420431.23 frames.], batch size: 38, lr: 2.20e-04
2022-05-28 14:13:36,713 INFO [train.py:842] (3/4) Epoch 25, batch 5550, loss[loss=0.182, simple_loss=0.268, pruned_loss=0.04804, over 7416.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2647, pruned_loss=0.04554, over 1424668.53 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 14:14:15,460 INFO [train.py:842] (3/4) Epoch 25, batch 5600, loss[loss=0.2052, simple_loss=0.2968, pruned_loss=0.05681, over 7215.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2648, pruned_loss=0.0458, over 1427761.24 frames.], batch size: 21, lr: 2.20e-04
2022-05-28 14:14:53,936 INFO [train.py:842] (3/4) Epoch 25, batch 5650, loss[loss=0.1842, simple_loss=0.2767, pruned_loss=0.04581, over 7043.00 frames.], tot_loss[loss=0.178, simple_loss=0.265, pruned_loss=0.04545, over 1430922.46 frames.], batch size: 28, lr: 2.20e-04
2022-05-28 14:15:32,489 INFO [train.py:842] (3/4) Epoch 25, batch 5700, loss[loss=0.1715, simple_loss=0.2682, pruned_loss=0.03738, over 7341.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2649, pruned_loss=0.04476, over 1426732.31 frames.], batch size: 22, lr: 2.20e-04
2022-05-28 14:16:11,070 INFO [train.py:842] (3/4) Epoch 25, batch 5750, loss[loss=0.1613, simple_loss=0.2367, pruned_loss=0.04293, over 7140.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2645, pruned_loss=0.04451, over 1428869.70 frames.], batch size: 17, lr: 2.20e-04
2022-05-28 14:16:49,548 INFO [train.py:842] (3/4) Epoch 25, batch 5800, loss[loss=0.2025, simple_loss=0.3033, pruned_loss=0.05082, over 7150.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2651, pruned_loss=0.04432, over 1430618.30 frames.], batch size: 20, lr: 2.20e-04
2022-05-28 14:17:27,563 INFO [train.py:842] (3/4) Epoch 25, batch 5850, loss[loss=0.1932, simple_loss=0.2956, pruned_loss=0.04537, over 6290.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2671, pruned_loss=0.04503, over 1423956.96 frames.], batch size: 37, lr: 2.20e-04
2022-05-28 14:18:06,221 INFO [train.py:842] (3/4) Epoch 25, batch 5900, loss[loss=0.1529, simple_loss=0.2419, pruned_loss=0.03201, over 7329.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2665, pruned_loss=0.04503, over 1424640.78 frames.], batch size: 22, lr: 2.19e-04
2022-05-28 14:18:44,338 INFO [train.py:842] (3/4) Epoch 25, batch 5950, loss[loss=0.1414, simple_loss=0.2393, pruned_loss=0.02179, over 7426.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2672, pruned_loss=0.04494, over 1422641.13 frames.], batch size: 20, lr: 2.19e-04
2022-05-28 14:19:23,244 INFO [train.py:842] (3/4) Epoch 25, batch 6000, loss[loss=0.1728, simple_loss=0.2663, pruned_loss=0.03969, over 7352.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2669, pruned_loss=0.0452, over 1424219.33 frames.], batch size: 22, lr: 2.19e-04
2022-05-28 14:19:23,245 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 14:19:32,870 INFO [train.py:871] (3/4) Epoch 25, validation: loss=0.1658, simple_loss=0.2641, pruned_loss=0.03372, over 868885.00 frames.
2022-05-28 14:20:11,404 INFO [train.py:842] (3/4) Epoch 25, batch 6050, loss[loss=0.1916, simple_loss=0.2748, pruned_loss=0.05426, over 7193.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2663, pruned_loss=0.04548, over 1425167.14 frames.], batch size: 23, lr: 2.19e-04
2022-05-28 14:20:50,174 INFO [train.py:842] (3/4) Epoch 25, batch 6100, loss[loss=0.1818, simple_loss=0.2491, pruned_loss=0.05722, over 7007.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2668, pruned_loss=0.0453, over 1427084.06 frames.], batch size: 16, lr: 2.19e-04
2022-05-28 14:21:28,816 INFO [train.py:842] (3/4) Epoch 25, batch 6150, loss[loss=0.1821, simple_loss=0.2823, pruned_loss=0.04091, over 7099.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2669, pruned_loss=0.04573, over 1425042.04 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:22:07,511 INFO [train.py:842] (3/4) Epoch 25, batch 6200, loss[loss=0.1534, simple_loss=0.2418, pruned_loss=0.03246, over 7326.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2679, pruned_loss=0.04652, over 1421973.53 frames.], batch size: 20, lr: 2.19e-04
2022-05-28 14:22:45,948 INFO [train.py:842] (3/4) Epoch 25, batch 6250, loss[loss=0.1781, simple_loss=0.2785, pruned_loss=0.03887, over 7225.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2679, pruned_loss=0.04657, over 1418596.75 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:23:34,554 INFO [train.py:842] (3/4) Epoch 25, batch 6300, loss[loss=0.1571, simple_loss=0.2549, pruned_loss=0.02969, over 7334.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2688, pruned_loss=0.04644, over 1418300.81 frames.], batch size: 22, lr: 2.19e-04
2022-05-28 14:24:12,969 INFO [train.py:842] (3/4) Epoch 25, batch 6350, loss[loss=0.1944, simple_loss=0.2954, pruned_loss=0.04664, over 7409.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2693, pruned_loss=0.04681, over 1418031.05 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:24:51,931 INFO [train.py:842] (3/4) Epoch 25, batch 6400, loss[loss=0.1545, simple_loss=0.2468, pruned_loss=0.03109, over 7248.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2694, pruned_loss=0.04694, over 1419366.71 frames.], batch size: 19, lr: 2.19e-04
2022-05-28 14:25:30,512 INFO [train.py:842] (3/4) Epoch 25, batch 6450, loss[loss=0.171, simple_loss=0.2476, pruned_loss=0.04722, over 6995.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2692, pruned_loss=0.04697, over 1423554.87 frames.], batch size: 16, lr: 2.19e-04
2022-05-28 14:26:09,244 INFO [train.py:842] (3/4) Epoch 25, batch 6500, loss[loss=0.1844, simple_loss=0.2763, pruned_loss=0.0463, over 6627.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2694, pruned_loss=0.0472, over 1422960.49 frames.], batch size: 38, lr: 2.19e-04
2022-05-28 14:26:47,618 INFO [train.py:842] (3/4) Epoch 25, batch 6550, loss[loss=0.1636, simple_loss=0.2477, pruned_loss=0.03978, over 7159.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2686, pruned_loss=0.04708, over 1421034.23 frames.], batch size: 19, lr: 2.19e-04
2022-05-28 14:27:26,218 INFO [train.py:842] (3/4) Epoch 25, batch 6600, loss[loss=0.2232, simple_loss=0.3028, pruned_loss=0.07181, over 7240.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2686, pruned_loss=0.04687, over 1423202.20 frames.], batch size: 20, lr: 2.19e-04
2022-05-28 14:28:04,726 INFO [train.py:842] (3/4) Epoch 25, batch 6650, loss[loss=0.1912, simple_loss=0.2783, pruned_loss=0.05201, over 6663.00 frames.], tot_loss[loss=0.181, simple_loss=0.2682, pruned_loss=0.04694, over 1424181.03 frames.], batch size: 31, lr: 2.19e-04
2022-05-28 14:28:43,453 INFO [train.py:842] (3/4) Epoch 25, batch 6700, loss[loss=0.1596, simple_loss=0.2482, pruned_loss=0.03554, over 7157.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2679, pruned_loss=0.04649, over 1425218.38 frames.], batch size: 19, lr: 2.19e-04
2022-05-28 14:29:22,079 INFO [train.py:842] (3/4) Epoch 25, batch 6750, loss[loss=0.1901, simple_loss=0.2814, pruned_loss=0.0494, over 7143.00 frames.], tot_loss[loss=0.181, simple_loss=0.2684, pruned_loss=0.04674, over 1426015.82 frames.], batch size: 20, lr: 2.19e-04
2022-05-28 14:30:00,932 INFO [train.py:842] (3/4) Epoch 25, batch 6800, loss[loss=0.2384, simple_loss=0.3068, pruned_loss=0.08507, over 4917.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2679, pruned_loss=0.04666, over 1423025.04 frames.], batch size: 53, lr: 2.19e-04
2022-05-28 14:30:39,289 INFO [train.py:842] (3/4) Epoch 25, batch 6850, loss[loss=0.1848, simple_loss=0.2809, pruned_loss=0.04432, over 7423.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2685, pruned_loss=0.04667, over 1426673.90 frames.], batch size: 20, lr: 2.19e-04
2022-05-28 14:31:18,203 INFO [train.py:842] (3/4) Epoch 25, batch 6900, loss[loss=0.156, simple_loss=0.234, pruned_loss=0.03902, over 7150.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2678, pruned_loss=0.04638, over 1429731.41 frames.], batch size: 17, lr: 2.19e-04
2022-05-28 14:31:56,685 INFO [train.py:842] (3/4) Epoch 25, batch 6950, loss[loss=0.1521, simple_loss=0.2433, pruned_loss=0.03046, over 7321.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2677, pruned_loss=0.04653, over 1430917.13 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:32:35,585 INFO [train.py:842] (3/4) Epoch 25, batch 7000, loss[loss=0.1507, simple_loss=0.2437, pruned_loss=0.02883, over 7271.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2662, pruned_loss=0.04544, over 1433519.58 frames.], batch size: 18, lr: 2.19e-04
2022-05-28 14:33:13,744 INFO [train.py:842] (3/4) Epoch 25, batch 7050, loss[loss=0.1526, simple_loss=0.2425, pruned_loss=0.03142, over 7250.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2666, pruned_loss=0.04575, over 1429211.06 frames.], batch size: 19, lr: 2.19e-04
2022-05-28 14:33:52,546 INFO [train.py:842] (3/4) Epoch 25, batch 7100, loss[loss=0.1784, simple_loss=0.275, pruned_loss=0.04088, over 7313.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2664, pruned_loss=0.04608, over 1429283.22 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:34:31,050 INFO [train.py:842] (3/4) Epoch 25, batch 7150, loss[loss=0.1486, simple_loss=0.2357, pruned_loss=0.03077, over 7264.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2658, pruned_loss=0.04547, over 1428078.48 frames.], batch size: 17, lr: 2.19e-04
2022-05-28 14:35:09,894 INFO [train.py:842] (3/4) Epoch 25, batch 7200, loss[loss=0.1672, simple_loss=0.2648, pruned_loss=0.03486, over 7313.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2663, pruned_loss=0.04546, over 1428243.82 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:35:48,516 INFO [train.py:842] (3/4) Epoch 25, batch 7250, loss[loss=0.1789, simple_loss=0.2728, pruned_loss=0.04245, over 7190.00 frames.], tot_loss[loss=0.1773, simple_loss=0.265, pruned_loss=0.04479, over 1429279.83 frames.], batch size: 26, lr: 2.19e-04
2022-05-28 14:36:26,929 INFO [train.py:842] (3/4) Epoch 25, batch 7300, loss[loss=0.1909, simple_loss=0.2828, pruned_loss=0.0495, over 7320.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2672, pruned_loss=0.04549, over 1425282.70 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:37:05,552 INFO [train.py:842] (3/4) Epoch 25, batch 7350, loss[loss=0.1909, simple_loss=0.2778, pruned_loss=0.05198, over 7191.00 frames.], tot_loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04584, over 1427543.87 frames.], batch size: 22, lr: 2.19e-04
2022-05-28 14:37:44,467 INFO [train.py:842] (3/4) Epoch 25, batch 7400, loss[loss=0.1686, simple_loss=0.251, pruned_loss=0.04309, over 7068.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2672, pruned_loss=0.04619, over 1425376.11 frames.], batch size: 18, lr: 2.19e-04
2022-05-28 14:38:22,841 INFO [train.py:842] (3/4) Epoch 25, batch 7450, loss[loss=0.2021, simple_loss=0.2877, pruned_loss=0.05829, over 7292.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2673, pruned_loss=0.0463, over 1426619.75 frames.], batch size: 24, lr: 2.19e-04
2022-05-28 14:39:01,272 INFO [train.py:842] (3/4) Epoch 25, batch 7500, loss[loss=0.1805, simple_loss=0.2661, pruned_loss=0.0475, over 7061.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2683, pruned_loss=0.0468, over 1424750.70 frames.], batch size: 18, lr: 2.19e-04
2022-05-28 14:39:39,760 INFO [train.py:842] (3/4) Epoch 25, batch 7550, loss[loss=0.1998, simple_loss=0.2931, pruned_loss=0.05319, over 7309.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2681, pruned_loss=0.04631, over 1428426.16 frames.], batch size: 25, lr: 2.19e-04
2022-05-28 14:40:18,795 INFO [train.py:842] (3/4) Epoch 25, batch 7600, loss[loss=0.1854, simple_loss=0.2754, pruned_loss=0.04771, over 7388.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2674, pruned_loss=0.04557, over 1432733.51 frames.], batch size: 23, lr: 2.19e-04
2022-05-28 14:40:57,021 INFO [train.py:842] (3/4) Epoch 25, batch 7650, loss[loss=0.1828, simple_loss=0.2777, pruned_loss=0.04394, over 7106.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2683, pruned_loss=0.046, over 1432927.61 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:41:35,622 INFO [train.py:842] (3/4) Epoch 25, batch 7700, loss[loss=0.2001, simple_loss=0.2839, pruned_loss=0.05821, over 7060.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2682, pruned_loss=0.04609, over 1431905.08 frames.], batch size: 18, lr: 2.19e-04
2022-05-28 14:42:14,011 INFO [train.py:842] (3/4) Epoch 25, batch 7750, loss[loss=0.1969, simple_loss=0.2831, pruned_loss=0.05538, over 5118.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2675, pruned_loss=0.04588, over 1431283.36 frames.], batch size: 52, lr: 2.19e-04
2022-05-28 14:42:52,794 INFO [train.py:842] (3/4) Epoch 25, batch 7800, loss[loss=0.2028, simple_loss=0.2951, pruned_loss=0.05519, over 6736.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2662, pruned_loss=0.04561, over 1427807.93 frames.], batch size: 31, lr: 2.19e-04
2022-05-28 14:43:31,082 INFO [train.py:842] (3/4) Epoch 25, batch 7850, loss[loss=0.1625, simple_loss=0.2573, pruned_loss=0.03384, over 7326.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2669, pruned_loss=0.0462, over 1426859.36 frames.], batch size: 21, lr: 2.19e-04
2022-05-28 14:44:10,158 INFO [train.py:842] (3/4) Epoch 25, batch 7900, loss[loss=0.1507, simple_loss=0.2347, pruned_loss=0.03331, over 7265.00 frames.], tot_loss[loss=0.1801, simple_loss=0.267, pruned_loss=0.04663, over 1427887.12 frames.], batch size: 18, lr: 2.19e-04
2022-05-28 14:44:48,432 INFO [train.py:842] (3/4) Epoch 25, batch 7950, loss[loss=0.1384, simple_loss=0.2234, pruned_loss=0.02667, over 6999.00 frames.], tot_loss[loss=0.18, simple_loss=0.2675, pruned_loss=0.04622, over 1426595.59 frames.], batch size: 16, lr: 2.18e-04
2022-05-28 14:45:27,125 INFO [train.py:842] (3/4) Epoch 25, batch 8000, loss[loss=0.2123, simple_loss=0.3026, pruned_loss=0.06098, over 7339.00 frames.], tot_loss[loss=0.1831, simple_loss=0.27, pruned_loss=0.04808, over 1423150.88 frames.], batch size: 20, lr: 2.18e-04
2022-05-28 14:46:05,221 INFO [train.py:842] (3/4) Epoch 25, batch 8050, loss[loss=0.1624, simple_loss=0.2478, pruned_loss=0.03853, over 7294.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2701, pruned_loss=0.04791, over 1420509.51 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:46:43,912 INFO [train.py:842] (3/4) Epoch 25, batch 8100, loss[loss=0.1777, simple_loss=0.2734, pruned_loss=0.041, over 7207.00 frames.], tot_loss[loss=0.181, simple_loss=0.2687, pruned_loss=0.04666, over 1423017.54 frames.], batch size: 22, lr: 2.18e-04
2022-05-28 14:47:22,090 INFO [train.py:842] (3/4) Epoch 25, batch 8150, loss[loss=0.1846, simple_loss=0.2775, pruned_loss=0.04583, over 7233.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2692, pruned_loss=0.04682, over 1417982.84 frames.], batch size: 20, lr: 2.18e-04
2022-05-28 14:48:00,741 INFO [train.py:842] (3/4) Epoch 25, batch 8200, loss[loss=0.163, simple_loss=0.2418, pruned_loss=0.04209, over 7288.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2682, pruned_loss=0.0467, over 1414223.13 frames.], batch size: 17, lr: 2.18e-04
2022-05-28 14:48:39,279 INFO [train.py:842] (3/4) Epoch 25, batch 8250, loss[loss=0.2249, simple_loss=0.3059, pruned_loss=0.07197, over 7172.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2675, pruned_loss=0.04612, over 1419160.60 frames.], batch size: 19, lr: 2.18e-04
2022-05-28 14:49:18,057 INFO [train.py:842] (3/4) Epoch 25, batch 8300, loss[loss=0.1594, simple_loss=0.2484, pruned_loss=0.03516, over 7072.00 frames.], tot_loss[loss=0.1799, simple_loss=0.268, pruned_loss=0.04591, over 1420931.91 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:49:56,275 INFO [train.py:842] (3/4) Epoch 25, batch 8350, loss[loss=0.1505, simple_loss=0.2387, pruned_loss=0.0312, over 7295.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2666, pruned_loss=0.04527, over 1416659.69 frames.], batch size: 17, lr: 2.18e-04
2022-05-28 14:50:35,126 INFO [train.py:842] (3/4) Epoch 25, batch 8400, loss[loss=0.1738, simple_loss=0.2774, pruned_loss=0.03511, over 7225.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04494, over 1415133.51 frames.], batch size: 21, lr: 2.18e-04
2022-05-28 14:51:13,377 INFO [train.py:842] (3/4) Epoch 25, batch 8450, loss[loss=0.1997, simple_loss=0.2988, pruned_loss=0.05035, over 7169.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2682, pruned_loss=0.04575, over 1416029.93 frames.], batch size: 26, lr: 2.18e-04
2022-05-28 14:51:51,818 INFO [train.py:842] (3/4) Epoch 25, batch 8500, loss[loss=0.1983, simple_loss=0.287, pruned_loss=0.05477, over 7069.00 frames.], tot_loss[loss=0.181, simple_loss=0.2689, pruned_loss=0.04651, over 1416191.36 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:52:29,806 INFO [train.py:842] (3/4) Epoch 25, batch 8550, loss[loss=0.1374, simple_loss=0.2227, pruned_loss=0.02599, over 7407.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2687, pruned_loss=0.04649, over 1413683.31 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:53:08,332 INFO [train.py:842] (3/4) Epoch 25, batch 8600, loss[loss=0.1757, simple_loss=0.2639, pruned_loss=0.04372, over 7113.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2689, pruned_loss=0.04694, over 1414341.32 frames.], batch size: 21, lr: 2.18e-04
2022-05-28 14:53:46,556 INFO [train.py:842] (3/4) Epoch 25, batch 8650, loss[loss=0.1799, simple_loss=0.272, pruned_loss=0.04388, over 7297.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2689, pruned_loss=0.04679, over 1418650.82 frames.], batch size: 24, lr: 2.18e-04
2022-05-28 14:54:25,090 INFO [train.py:842] (3/4) Epoch 25, batch 8700, loss[loss=0.1795, simple_loss=0.2598, pruned_loss=0.04958, over 7279.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2682, pruned_loss=0.04614, over 1420168.33 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:55:03,386 INFO [train.py:842] (3/4) Epoch 25, batch 8750, loss[loss=0.2048, simple_loss=0.2961, pruned_loss=0.05678, over 7209.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2688, pruned_loss=0.04648, over 1423498.10 frames.], batch size: 23, lr: 2.18e-04
2022-05-28 14:55:42,045 INFO [train.py:842] (3/4) Epoch 25, batch 8800, loss[loss=0.1599, simple_loss=0.2427, pruned_loss=0.03857, over 7060.00 frames.], tot_loss[loss=0.181, simple_loss=0.2689, pruned_loss=0.04653, over 1421424.19 frames.], batch size: 18, lr: 2.18e-04
2022-05-28 14:56:20,246 INFO [train.py:842] (3/4) Epoch 25, batch 8850, loss[loss=0.153, simple_loss=0.2523, pruned_loss=0.02682, over 7219.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2691, pruned_loss=0.04639, over 1421044.15 frames.], batch size: 21, lr: 2.18e-04
2022-05-28 14:56:58,675 INFO [train.py:842] (3/4) Epoch 25, batch 8900, loss[loss=0.1802, simple_loss=0.2687, pruned_loss=0.04581, over 7172.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2695, pruned_loss=0.04701, over 1406776.94 frames.], batch size: 28, lr: 2.18e-04
2022-05-28 14:57:36,572 INFO [train.py:842] (3/4) Epoch 25, batch 8950, loss[loss=0.2015, simple_loss=0.2807, pruned_loss=0.06109, over 5183.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2711, pruned_loss=0.04736, over 1400141.22 frames.], batch size: 52, lr: 2.18e-04
2022-05-28 14:58:14,362 INFO [train.py:842] (3/4) Epoch 25, batch 9000, loss[loss=0.215, simple_loss=0.3018, pruned_loss=0.06407, over 6270.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2715, pruned_loss=0.04735, over 1385355.11 frames.], batch size: 37, lr: 2.18e-04
2022-05-28 14:58:14,362 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 14:58:23,547 INFO [train.py:871] (3/4) Epoch 25, validation: loss=0.1658, simple_loss=0.265, pruned_loss=0.03327, over 868885.00 frames.
2022-05-28 14:59:00,506 INFO [train.py:842] (3/4) Epoch 25, batch 9050, loss[loss=0.1724, simple_loss=0.2676, pruned_loss=0.03861, over 6304.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2733, pruned_loss=0.04839, over 1348228.24 frames.], batch size: 37, lr: 2.18e-04
2022-05-28 14:59:37,689 INFO [train.py:842] (3/4) Epoch 25, batch 9100, loss[loss=0.2335, simple_loss=0.3076, pruned_loss=0.07965, over 5161.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2774, pruned_loss=0.05114, over 1300582.07 frames.], batch size: 53, lr: 2.18e-04
2022-05-28 15:00:14,857 INFO [train.py:842] (3/4) Epoch 25, batch 9150, loss[loss=0.1821, simple_loss=0.2633, pruned_loss=0.05039, over 5075.00 frames.], tot_loss[loss=0.194, simple_loss=0.2805, pruned_loss=0.05375, over 1244722.95 frames.], batch size: 53, lr: 2.18e-04
2022-05-28 15:01:00,944 INFO [train.py:842] (3/4) Epoch 26, batch 0, loss[loss=0.184, simple_loss=0.2784, pruned_loss=0.04479, over 7217.00 frames.], tot_loss[loss=0.184, simple_loss=0.2784, pruned_loss=0.04479, over 7217.00 frames.], batch size: 21, lr: 2.14e-04
2022-05-28 15:01:39,904 INFO [train.py:842] (3/4) Epoch 26, batch 50, loss[loss=0.1805, simple_loss=0.2735, pruned_loss=0.04371, over 7329.00 frames.], tot_loss[loss=0.171, simple_loss=0.2593, pruned_loss=0.04135, over 322425.46 frames.], batch size: 21, lr: 2.14e-04
2022-05-28 15:02:18,136 INFO [train.py:842] (3/4) Epoch 26, batch 100, loss[loss=0.2371, simple_loss=0.3201, pruned_loss=0.07706, over 4757.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04493, over 566083.41 frames.], batch size: 52, lr: 2.14e-04
2022-05-28 15:02:56,780 INFO [train.py:842] (3/4) Epoch 26, batch 150, loss[loss=0.1689, simple_loss=0.2532, pruned_loss=0.0423, over 7272.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2658, pruned_loss=0.04526, over 759810.50 frames.], batch size: 17, lr: 2.14e-04
2022-05-28 15:03:35,211 INFO [train.py:842] (3/4) Epoch 26, batch 200, loss[loss=0.1805, simple_loss=0.27, pruned_loss=0.0455, over 7375.00 frames.], tot_loss[loss=0.178, simple_loss=0.2658, pruned_loss=0.04512, over 906801.14 frames.], batch size: 23, lr: 2.14e-04
2022-05-28 15:04:13,810 INFO [train.py:842] (3/4) Epoch 26, batch 250, loss[loss=0.192, simple_loss=0.2711, pruned_loss=0.05642, over 7217.00 frames.], tot_loss[loss=0.179, simple_loss=0.2667, pruned_loss=0.04567, over 1019167.79 frames.], batch size: 22, lr: 2.14e-04
2022-05-28 15:04:51,895 INFO [train.py:842] (3/4) Epoch 26, batch 300, loss[loss=0.1748, simple_loss=0.2611, pruned_loss=0.04428, over 7324.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2669, pruned_loss=0.04572, over 1105137.81 frames.], batch size: 20, lr: 2.14e-04
2022-05-28 15:05:30,454 INFO [train.py:842] (3/4) Epoch 26, batch 350, loss[loss=0.1565, simple_loss=0.2445, pruned_loss=0.03426, over 7163.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2668, pruned_loss=0.04601, over 1175499.09 frames.], batch size: 18, lr: 2.14e-04
2022-05-28 15:06:08,854 INFO [train.py:842] (3/4) Epoch 26, batch 400, loss[loss=0.1576, simple_loss=0.2494, pruned_loss=0.03293, over 7413.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2665, pruned_loss=0.04549, over 1233916.78 frames.], batch size: 18, lr: 2.14e-04
2022-05-28 15:06:47,618 INFO [train.py:842] (3/4) Epoch 26, batch 450, loss[loss=0.179, simple_loss=0.2734, pruned_loss=0.0423, over 7405.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2658, pruned_loss=0.04474, over 1274859.80 frames.], batch size: 21, lr: 2.14e-04
2022-05-28 15:07:25,851 INFO [train.py:842] (3/4) Epoch 26, batch 500, loss[loss=0.2103, simple_loss=0.2882, pruned_loss=0.06614, over 7392.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2665, pruned_loss=0.04519, over 1302367.35 frames.], batch size: 23, lr: 2.14e-04
2022-05-28 15:08:04,634 INFO [train.py:842] (3/4) Epoch 26, batch 550, loss[loss=0.1953, simple_loss=0.2829, pruned_loss=0.05386, over 7234.00 frames.], tot_loss[loss=0.178, simple_loss=0.2659, pruned_loss=0.04508, over 1329121.50 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:08:43,130 INFO [train.py:842] (3/4) Epoch 26, batch 600, loss[loss=0.1768, simple_loss=0.2752, pruned_loss=0.03915, over 7045.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2661, pruned_loss=0.04526, over 1347324.18 frames.], batch size: 28, lr: 2.13e-04
2022-05-28 15:09:22,114 INFO [train.py:842] (3/4) Epoch 26, batch 650, loss[loss=0.1465, simple_loss=0.2413, pruned_loss=0.0258, over 7323.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2653, pruned_loss=0.04524, over 1361484.05 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:10:10,863 INFO [train.py:842] (3/4) Epoch 26, batch 700, loss[loss=0.1914, simple_loss=0.2732, pruned_loss=0.0548, over 7156.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2648, pruned_loss=0.04485, over 1374484.39 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:10:49,687 INFO [train.py:842] (3/4) Epoch 26, batch 750, loss[loss=0.1546, simple_loss=0.2494, pruned_loss=0.0299, over 7444.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.0443, over 1389723.44 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:11:27,864 INFO [train.py:842] (3/4) Epoch 26, batch 800, loss[loss=0.1812, simple_loss=0.2735, pruned_loss=0.04444, over 6761.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2647, pruned_loss=0.04455, over 1396280.66 frames.], batch size: 31, lr: 2.13e-04
2022-05-28 15:12:06,496 INFO [train.py:842] (3/4) Epoch 26, batch 850, loss[loss=0.2035, simple_loss=0.2889, pruned_loss=0.05906, over 7114.00 frames.], tot_loss[loss=0.178, simple_loss=0.2665, pruned_loss=0.04481, over 1407044.89 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:12:54,997 INFO [train.py:842] (3/4) Epoch 26, batch 900, loss[loss=0.2098, simple_loss=0.273, pruned_loss=0.07326, over 7222.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2665, pruned_loss=0.04497, over 1406679.26 frames.], batch size: 16, lr: 2.13e-04
2022-05-28 15:13:43,627 INFO [train.py:842] (3/4) Epoch 26, batch 950, loss[loss=0.1414, simple_loss=0.2259, pruned_loss=0.02848, over 7279.00 frames.], tot_loss[loss=0.1776, simple_loss=0.266, pruned_loss=0.04462, over 1413000.73 frames.], batch size: 17, lr: 2.13e-04
2022-05-28 15:14:21,988 INFO [train.py:842] (3/4) Epoch 26, batch 1000, loss[loss=0.2272, simple_loss=0.3122, pruned_loss=0.07111, over 7108.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2674, pruned_loss=0.04572, over 1412646.71 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:15:00,540 INFO [train.py:842] (3/4) Epoch 26, batch 1050, loss[loss=0.2193, simple_loss=0.2945, pruned_loss=0.07206, over 5039.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2667, pruned_loss=0.04531, over 1412465.86 frames.], batch size: 52, lr: 2.13e-04
2022-05-28 15:15:38,922 INFO [train.py:842] (3/4) Epoch 26, batch 1100, loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.03769, over 7112.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2673, pruned_loss=0.04557, over 1413414.35 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:16:17,632 INFO [train.py:842] (3/4) Epoch 26, batch 1150, loss[loss=0.2135, simple_loss=0.2951, pruned_loss=0.06595, over 7372.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2684, pruned_loss=0.04628, over 1416980.47 frames.], batch size: 23, lr: 2.13e-04
2022-05-28 15:16:56,067 INFO [train.py:842] (3/4) Epoch 26, batch 1200, loss[loss=0.1725, simple_loss=0.2559, pruned_loss=0.04449, over 7115.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2675, pruned_loss=0.04602, over 1421521.26 frames.], batch size: 17, lr: 2.13e-04
2022-05-28 15:17:34,837 INFO [train.py:842] (3/4) Epoch 26, batch 1250, loss[loss=0.2304, simple_loss=0.3214, pruned_loss=0.06965, over 7317.00 frames.], tot_loss[loss=0.181, simple_loss=0.2689, pruned_loss=0.04653, over 1423771.88 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:18:13,314 INFO [train.py:842] (3/4) Epoch 26, batch 1300, loss[loss=0.1887, simple_loss=0.2758, pruned_loss=0.05086, over 7419.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2681, pruned_loss=0.04567, over 1427299.93 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:18:51,822 INFO [train.py:842] (3/4) Epoch 26, batch 1350, loss[loss=0.1687, simple_loss=0.2558, pruned_loss=0.04079, over 7322.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2683, pruned_loss=0.04604, over 1427641.90 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:19:30,190 INFO [train.py:842] (3/4) Epoch 26, batch 1400, loss[loss=0.1557, simple_loss=0.2454, pruned_loss=0.03297, over 7340.00 frames.], tot_loss[loss=0.18, simple_loss=0.2683, pruned_loss=0.04587, over 1427588.16 frames.], batch size: 22, lr: 2.13e-04
2022-05-28 15:20:08,710 INFO [train.py:842] (3/4) Epoch 26, batch 1450, loss[loss=0.1372, simple_loss=0.2206, pruned_loss=0.02693, over 7007.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2679, pruned_loss=0.04557, over 1429189.39 frames.], batch size: 16, lr: 2.13e-04
2022-05-28 15:20:47,191 INFO [train.py:842] (3/4) Epoch 26, batch 1500, loss[loss=0.1864, simple_loss=0.268, pruned_loss=0.05245, over 7220.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2667, pruned_loss=0.04537, over 1428275.37 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:21:25,998 INFO [train.py:842] (3/4) Epoch 26, batch 1550, loss[loss=0.1549, simple_loss=0.2368, pruned_loss=0.03646, over 7122.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2671, pruned_loss=0.04631, over 1427405.65 frames.], batch size: 17, lr: 2.13e-04
2022-05-28 15:22:03,994 INFO [train.py:842] (3/4) Epoch 26, batch 1600, loss[loss=0.1808, simple_loss=0.2769, pruned_loss=0.04231, over 7145.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2688, pruned_loss=0.04682, over 1424249.87 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:22:43,195 INFO [train.py:842] (3/4) Epoch 26, batch 1650, loss[loss=0.1697, simple_loss=0.2605, pruned_loss=0.03948, over 7100.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2665, pruned_loss=0.04525, over 1425598.64 frames.], batch size: 28, lr: 2.13e-04
2022-05-28 15:23:21,400 INFO [train.py:842] (3/4) Epoch 26, batch 1700, loss[loss=0.1891, simple_loss=0.2925, pruned_loss=0.04283, over 7323.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2661, pruned_loss=0.04469, over 1425549.10 frames.], batch size: 21, lr: 2.13e-04
2022-05-28 15:24:00,058 INFO [train.py:842] (3/4) Epoch 26, batch 1750, loss[loss=0.1594, simple_loss=0.242, pruned_loss=0.03843, over 7123.00 frames.], tot_loss[loss=0.177, simple_loss=0.2656, pruned_loss=0.04424, over 1425495.25 frames.], batch size: 17, lr: 2.13e-04
2022-05-28 15:24:38,396 INFO [train.py:842] (3/4) Epoch 26, batch 1800, loss[loss=0.1607, simple_loss=0.252, pruned_loss=0.03472, over 7153.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2649, pruned_loss=0.044, over 1421872.09 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:25:17,121 INFO [train.py:842] (3/4) Epoch 26, batch 1850, loss[loss=0.1725, simple_loss=0.2624, pruned_loss=0.0413, over 7431.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2655, pruned_loss=0.04467, over 1423007.31 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:25:55,284 INFO [train.py:842] (3/4) Epoch 26, batch 1900, loss[loss=0.1604, simple_loss=0.2383, pruned_loss=0.04125, over 7132.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2659, pruned_loss=0.04465, over 1423521.46 frames.], batch size: 17, lr: 2.13e-04
2022-05-28 15:26:33,988 INFO [train.py:842] (3/4) Epoch 26, batch 1950, loss[loss=0.1845, simple_loss=0.274, pruned_loss=0.04746, over 5148.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2662, pruned_loss=0.04526, over 1420734.65 frames.], batch size: 52, lr: 2.13e-04
2022-05-28 15:27:12,183 INFO [train.py:842] (3/4) Epoch 26, batch 2000, loss[loss=0.1623, simple_loss=0.2572, pruned_loss=0.03369, over 7151.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2658, pruned_loss=0.04497, over 1416175.84 frames.], batch size: 19, lr: 2.13e-04
2022-05-28 15:27:51,026 INFO [train.py:842] (3/4) Epoch 26, batch 2050, loss[loss=0.1739, simple_loss=0.2597, pruned_loss=0.04409, over 7340.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2668, pruned_loss=0.04577, over 1418048.91 frames.], batch size: 20, lr: 2.13e-04
2022-05-28 15:28:29,357 INFO [train.py:842] (3/4) Epoch 26, batch 2100, loss[loss=0.1717, simple_loss=0.2653, pruned_loss=0.039, over 7220.00 frames.], tot_loss[loss=0.18, simple_loss=0.2679, pruned_loss=0.0461, over 1417197.80 frames.], batch size: 22, lr: 2.13e-04
2022-05-28 15:29:07,773 INFO [train.py:842] (3/4) Epoch 26, batch 2150, loss[loss=0.1505, simple_loss=0.2297, pruned_loss=0.03572, over 7157.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2679, pruned_loss=0.04573, over 1419741.96 frames.], batch size: 18, lr: 2.13e-04
2022-05-28 15:29:46,156 INFO [train.py:842] (3/4) Epoch 26, batch 2200, loss[loss=0.1605, simple_loss=0.2539, pruned_loss=0.03358, over 7098.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2669, pruned_loss=0.04546, over 1422182.38 frames.], batch size: 28, lr: 2.13e-04
2022-05-28 15:30:27,808 INFO [train.py:842] (3/4) Epoch 26, batch 2250, loss[loss=0.1815, simple_loss=0.2742, pruned_loss=0.04436, over 7384.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2651, pruned_loss=0.04436, over 1425000.02 frames.], batch size: 23, lr: 2.13e-04
2022-05-28 15:31:06,150 INFO [train.py:842] (3/4) Epoch 26, batch 2300, loss[loss=0.1703, simple_loss=0.2521, pruned_loss=0.04424, over 7079.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2651, pruned_loss=0.04406, over 1425200.21 frames.], batch size: 18, lr: 2.13e-04
2022-05-28 15:31:45,079 INFO [train.py:842] (3/4) Epoch 26, batch 2350, loss[loss=0.1771, simple_loss=0.2611, pruned_loss=0.04657, over 7270.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2649, pruned_loss=0.04475, over 1425200.07 frames.], batch size: 19, lr: 2.13e-04
2022-05-28 15:32:23,720 INFO [train.py:842] (3/4) Epoch 26, batch 2400, loss[loss=0.2137, simple_loss=0.29, pruned_loss=0.06872, over 7358.00 frames.], tot_loss[loss=0.178, simple_loss=0.2655, pruned_loss=0.04524, over 1423014.97 frames.], batch size: 23, lr: 2.13e-04
2022-05-28 15:33:02,378 INFO [train.py:842] (3/4) Epoch 26, batch 2450, loss[loss=0.1782, simple_loss=0.275, pruned_loss=0.04069, over 6780.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2652, pruned_loss=0.04523, over 1421778.66 frames.], batch size: 31, lr: 2.13e-04
2022-05-28 15:33:40,957 INFO [train.py:842] (3/4) Epoch 26, batch 2500, loss[loss=0.149, simple_loss=0.2383, pruned_loss=0.02981, over 7362.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2652, pruned_loss=0.04464, over 1423252.64 frames.], batch size: 19, lr: 2.13e-04
2022-05-28 15:34:19,836 INFO [train.py:842] (3/4) Epoch 26, batch 2550, loss[loss=0.1332, simple_loss=0.2117, pruned_loss=0.0274, over 7413.00 frames.], tot_loss[loss=0.178, simple_loss=0.2657, pruned_loss=0.04509, over 1426281.05 frames.], batch size: 18, lr: 2.13e-04
2022-05-28 15:34:58,261 INFO [train.py:842] (3/4) Epoch 26, batch 2600, loss[loss=0.1804, simple_loss=0.2717, pruned_loss=0.04454, over 7160.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2668, pruned_loss=0.04595, over 1423911.61 frames.], batch size: 19, lr: 2.13e-04
2022-05-28 15:35:36,583 INFO [train.py:842] (3/4) Epoch 26, batch 2650, loss[loss=0.2165, simple_loss=0.3009, pruned_loss=0.06606, over 7142.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2662, pruned_loss=0.04501, over 1419823.72 frames.], batch size: 28, lr: 2.13e-04
2022-05-28 15:36:14,919 INFO [train.py:842] (3/4) Epoch 26, batch 2700, loss[loss=0.1843, simple_loss=0.2817, pruned_loss=0.04347, over 7259.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2661, pruned_loss=0.04488, over 1420502.39 frames.], batch size: 19, lr: 2.13e-04
2022-05-28 15:36:53,432 INFO [train.py:842] (3/4) Epoch 26, batch 2750, loss[loss=0.2035, simple_loss=0.2908, pruned_loss=0.05809, over 7317.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2681, pruned_loss=0.0461, over 1413633.76 frames.], batch size: 25, lr: 2.12e-04
2022-05-28 15:37:32,277 INFO [train.py:842] (3/4) Epoch 26, batch 2800, loss[loss=0.1678, simple_loss=0.2531, pruned_loss=0.04125, over 7294.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2678, pruned_loss=0.04599, over 1416679.01 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 15:38:11,412 INFO [train.py:842] (3/4) Epoch 26, batch 2850, loss[loss=0.2023, simple_loss=0.3034, pruned_loss=0.05061, over 7410.00 frames.], tot_loss[loss=0.179, simple_loss=0.2669, pruned_loss=0.04548, over 1411531.43 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:38:50,414 INFO [train.py:842] (3/4) Epoch 26, batch 2900, loss[loss=0.1591, simple_loss=0.254, pruned_loss=0.03212, over 7148.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2673, pruned_loss=0.04581, over 1417370.74 frames.], batch size: 20, lr: 2.12e-04
2022-05-28 15:39:29,982 INFO [train.py:842] (3/4) Epoch 26, batch 2950, loss[loss=0.1634, simple_loss=0.2589, pruned_loss=0.03392, over 7329.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2681, pruned_loss=0.04611, over 1417596.17 frames.], batch size: 20, lr: 2.12e-04
2022-05-28 15:40:09,217 INFO [train.py:842] (3/4) Epoch 26, batch 3000, loss[loss=0.172, simple_loss=0.2685, pruned_loss=0.03778, over 6454.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2672, pruned_loss=0.04549, over 1422374.18 frames.], batch size: 37, lr: 2.12e-04
2022-05-28 15:40:09,218 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 15:40:19,618 INFO [train.py:871] (3/4) Epoch 26, validation: loss=0.166, simple_loss=0.2639, pruned_loss=0.0341, over 868885.00 frames.
2022-05-28 15:40:59,133 INFO [train.py:842] (3/4) Epoch 26, batch 3050, loss[loss=0.1617, simple_loss=0.2552, pruned_loss=0.03409, over 7332.00 frames.], tot_loss[loss=0.178, simple_loss=0.2667, pruned_loss=0.04469, over 1421805.70 frames.], batch size: 22, lr: 2.12e-04
2022-05-28 15:41:38,584 INFO [train.py:842] (3/4) Epoch 26, batch 3100, loss[loss=0.1684, simple_loss=0.2534, pruned_loss=0.04167, over 7264.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2661, pruned_loss=0.0447, over 1419568.65 frames.], batch size: 19, lr: 2.12e-04
2022-05-28 15:42:18,123 INFO [train.py:842] (3/4) Epoch 26, batch 3150, loss[loss=0.1807, simple_loss=0.2544, pruned_loss=0.05352, over 7147.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2656, pruned_loss=0.04433, over 1418092.76 frames.], batch size: 17, lr: 2.12e-04
2022-05-28 15:42:57,581 INFO [train.py:842] (3/4) Epoch 26, batch 3200, loss[loss=0.1878, simple_loss=0.2773, pruned_loss=0.04919, over 7153.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2659, pruned_loss=0.04466, over 1421099.73 frames.], batch size: 19, lr: 2.12e-04
2022-05-28 15:43:37,416 INFO [train.py:842] (3/4) Epoch 26, batch 3250, loss[loss=0.1431, simple_loss=0.2359, pruned_loss=0.02512, over 7275.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2654, pruned_loss=0.04496, over 1424210.12 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 15:44:16,462 INFO [train.py:842] (3/4) Epoch 26, batch 3300, loss[loss=0.2257, simple_loss=0.3127, pruned_loss=0.0694, over 7178.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2667, pruned_loss=0.04573, over 1417182.17 frames.], batch size: 26, lr: 2.12e-04
2022-05-28 15:44:55,920 INFO [train.py:842] (3/4) Epoch 26, batch 3350, loss[loss=0.1926, simple_loss=0.282, pruned_loss=0.05162, over 7325.00 frames.], tot_loss[loss=0.1793, simple_loss=0.267, pruned_loss=0.04587, over 1413625.76 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:45:35,705 INFO [train.py:842] (3/4) Epoch 26, batch 3400, loss[loss=0.1796, simple_loss=0.2738, pruned_loss=0.04268, over 6593.00 frames.], tot_loss[loss=0.1797, simple_loss=0.267, pruned_loss=0.04626, over 1418974.18 frames.], batch size: 38, lr: 2.12e-04
2022-05-28 15:46:15,391 INFO [train.py:842] (3/4) Epoch 26, batch 3450, loss[loss=0.1654, simple_loss=0.2587, pruned_loss=0.03599, over 7166.00 frames.], tot_loss[loss=0.18, simple_loss=0.2675, pruned_loss=0.04627, over 1420374.16 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 15:46:54,511 INFO [train.py:842] (3/4) Epoch 26, batch 3500, loss[loss=0.194, simple_loss=0.2835, pruned_loss=0.05228, over 7401.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2682, pruned_loss=0.04652, over 1419542.65 frames.], batch size: 23, lr: 2.12e-04
2022-05-28 15:47:33,974 INFO [train.py:842] (3/4) Epoch 26, batch 3550, loss[loss=0.1788, simple_loss=0.2716, pruned_loss=0.04299, over 7412.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2669, pruned_loss=0.04536, over 1421888.57 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:48:13,511 INFO [train.py:842] (3/4) Epoch 26, batch 3600, loss[loss=0.1792, simple_loss=0.2714, pruned_loss=0.04346, over 7221.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2658, pruned_loss=0.04544, over 1426153.09 frames.], batch size: 23, lr: 2.12e-04
2022-05-28 15:48:53,120 INFO [train.py:842] (3/4) Epoch 26, batch 3650, loss[loss=0.1558, simple_loss=0.2519, pruned_loss=0.02984, over 7260.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2647, pruned_loss=0.04494, over 1427288.62 frames.], batch size: 19, lr: 2.12e-04
2022-05-28 15:49:32,409 INFO [train.py:842] (3/4) Epoch 26, batch 3700, loss[loss=0.1744, simple_loss=0.2637, pruned_loss=0.04257, over 7077.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2643, pruned_loss=0.04445, over 1424306.11 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 15:50:12,029 INFO [train.py:842] (3/4) Epoch 26, batch 3750, loss[loss=0.1532, simple_loss=0.243, pruned_loss=0.03166, over 7165.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2653, pruned_loss=0.04445, over 1422059.82 frames.], batch size: 19, lr: 2.12e-04
2022-05-28 15:50:51,106 INFO [train.py:842] (3/4) Epoch 26, batch 3800, loss[loss=0.1608, simple_loss=0.2589, pruned_loss=0.03129, over 6376.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.0442, over 1420363.99 frames.], batch size: 37, lr: 2.12e-04
2022-05-28 15:51:30,412 INFO [train.py:842] (3/4) Epoch 26, batch 3850, loss[loss=0.2114, simple_loss=0.3066, pruned_loss=0.0581, over 7147.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2645, pruned_loss=0.04435, over 1419089.34 frames.], batch size: 20, lr: 2.12e-04
2022-05-28 15:52:09,603 INFO [train.py:842] (3/4) Epoch 26, batch 3900, loss[loss=0.1966, simple_loss=0.2854, pruned_loss=0.05387, over 7243.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2665, pruned_loss=0.04551, over 1420333.43 frames.], batch size: 20, lr: 2.12e-04
2022-05-28 15:52:49,322 INFO [train.py:842] (3/4) Epoch 26, batch 3950, loss[loss=0.1898, simple_loss=0.284, pruned_loss=0.0478, over 6724.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2658, pruned_loss=0.04495, over 1425196.66 frames.], batch size: 31, lr: 2.12e-04
2022-05-28 15:53:28,766 INFO [train.py:842] (3/4) Epoch 26, batch 4000, loss[loss=0.1691, simple_loss=0.2614, pruned_loss=0.03837, over 7118.00 frames.], tot_loss[loss=0.177, simple_loss=0.2645, pruned_loss=0.04471, over 1418071.94 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:54:08,332 INFO [train.py:842] (3/4) Epoch 26, batch 4050, loss[loss=0.1919, simple_loss=0.2845, pruned_loss=0.04959, over 6333.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2646, pruned_loss=0.04432, over 1419640.45 frames.], batch size: 38, lr: 2.12e-04
2022-05-28 15:54:48,042 INFO [train.py:842] (3/4) Epoch 26, batch 4100, loss[loss=0.1455, simple_loss=0.2259, pruned_loss=0.03253, over 7271.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2656, pruned_loss=0.04542, over 1418432.02 frames.], batch size: 17, lr: 2.12e-04
2022-05-28 15:55:28,401 INFO [train.py:842] (3/4) Epoch 26, batch 4150, loss[loss=0.2, simple_loss=0.2785, pruned_loss=0.06075, over 7052.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2649, pruned_loss=0.04524, over 1422193.19 frames.], batch size: 28, lr: 2.12e-04
2022-05-28 15:56:07,750 INFO [train.py:842] (3/4) Epoch 26, batch 4200, loss[loss=0.1755, simple_loss=0.2507, pruned_loss=0.05015, over 7298.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2649, pruned_loss=0.04508, over 1421932.48 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 15:56:47,372 INFO [train.py:842] (3/4) Epoch 26, batch 4250, loss[loss=0.2095, simple_loss=0.2976, pruned_loss=0.06069, over 7226.00 frames.], tot_loss[loss=0.177, simple_loss=0.2643, pruned_loss=0.04489, over 1424230.33 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:57:26,576 INFO [train.py:842] (3/4) Epoch 26, batch 4300, loss[loss=0.1986, simple_loss=0.2788, pruned_loss=0.05921, over 7442.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2647, pruned_loss=0.04494, over 1423403.45 frames.], batch size: 20, lr: 2.12e-04
2022-05-28 15:58:06,190 INFO [train.py:842] (3/4) Epoch 26, batch 4350, loss[loss=0.2066, simple_loss=0.2928, pruned_loss=0.06014, over 7372.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2646, pruned_loss=0.04527, over 1424332.60 frames.], batch size: 23, lr: 2.12e-04
2022-05-28 15:58:45,538 INFO [train.py:842] (3/4) Epoch 26, batch 4400, loss[loss=0.1816, simple_loss=0.2806, pruned_loss=0.04132, over 7217.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2646, pruned_loss=0.04556, over 1423791.78 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 15:59:24,728 INFO [train.py:842] (3/4) Epoch 26, batch 4450, loss[loss=0.1638, simple_loss=0.2456, pruned_loss=0.041, over 7281.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04589, over 1416318.91 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 16:00:03,670 INFO [train.py:842] (3/4) Epoch 26, batch 4500, loss[loss=0.1709, simple_loss=0.264, pruned_loss=0.03885, over 6266.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2666, pruned_loss=0.04589, over 1416118.23 frames.], batch size: 38, lr: 2.12e-04
2022-05-28 16:00:44,589 INFO [train.py:842] (3/4) Epoch 26, batch 4550, loss[loss=0.1658, simple_loss=0.2684, pruned_loss=0.0316, over 7117.00 frames.], tot_loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04586, over 1415067.16 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 16:01:23,784 INFO [train.py:842] (3/4) Epoch 26, batch 4600, loss[loss=0.1571, simple_loss=0.243, pruned_loss=0.03557, over 7068.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2668, pruned_loss=0.04592, over 1418521.00 frames.], batch size: 18, lr: 2.12e-04
2022-05-28 16:02:03,272 INFO [train.py:842] (3/4) Epoch 26, batch 4650, loss[loss=0.1739, simple_loss=0.2701, pruned_loss=0.03886, over 6295.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2677, pruned_loss=0.04669, over 1412620.24 frames.], batch size: 37, lr: 2.12e-04
2022-05-28 16:02:42,695 INFO [train.py:842] (3/4) Epoch 26, batch 4700, loss[loss=0.2122, simple_loss=0.2915, pruned_loss=0.06651, over 7205.00 frames.], tot_loss[loss=0.1798, simple_loss=0.267, pruned_loss=0.04626, over 1415813.00 frames.], batch size: 22, lr: 2.12e-04
2022-05-28 16:03:22,513 INFO [train.py:842] (3/4) Epoch 26, batch 4750, loss[loss=0.1937, simple_loss=0.2821, pruned_loss=0.05266, over 7379.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2665, pruned_loss=0.0464, over 1416388.70 frames.], batch size: 23, lr: 2.12e-04
2022-05-28 16:04:03,168 INFO [train.py:842] (3/4) Epoch 26, batch 4800, loss[loss=0.1682, simple_loss=0.2631, pruned_loss=0.03665, over 7321.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2665, pruned_loss=0.04611, over 1419769.43 frames.], batch size: 21, lr: 2.12e-04
2022-05-28 16:04:43,155 INFO [train.py:842] (3/4) Epoch 26, batch 4850, loss[loss=0.1621, simple_loss=0.2585, pruned_loss=0.03288, over 7327.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2658, pruned_loss=0.04576, over 1422818.06 frames.], batch size: 22, lr: 2.12e-04
2022-05-28 16:05:22,332 INFO [train.py:842] (3/4) Epoch 26, batch 4900, loss[loss=0.1396, simple_loss=0.2275, pruned_loss=0.02585, over 7158.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2667, pruned_loss=0.04616, over 1420100.93 frames.], batch size: 19, lr: 2.12e-04
2022-05-28 16:06:02,523 INFO [train.py:842] (3/4) Epoch 26, batch 4950, loss[loss=0.179, simple_loss=0.2596, pruned_loss=0.04915, over 7082.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2659, pruned_loss=0.04555, over 1418157.58 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:06:42,114 INFO [train.py:842] (3/4) Epoch 26, batch 5000, loss[loss=0.1671, simple_loss=0.26, pruned_loss=0.03707, over 7125.00 frames.], tot_loss[loss=0.178, simple_loss=0.2659, pruned_loss=0.0451, over 1420499.93 frames.], batch size: 21, lr: 2.11e-04
2022-05-28 16:07:21,665 INFO [train.py:842] (3/4) Epoch 26, batch 5050, loss[loss=0.1607, simple_loss=0.2461, pruned_loss=0.03766, over 6789.00 frames.], tot_loss[loss=0.1795, simple_loss=0.267, pruned_loss=0.04601, over 1419647.39 frames.], batch size: 15, lr: 2.11e-04
2022-05-28 16:08:00,696 INFO [train.py:842] (3/4) Epoch 26, batch 5100, loss[loss=0.1807, simple_loss=0.2618, pruned_loss=0.04974, over 5444.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2654, pruned_loss=0.04543, over 1418938.84 frames.], batch size: 52, lr: 2.11e-04
2022-05-28 16:08:40,347 INFO [train.py:842] (3/4) Epoch 26, batch 5150, loss[loss=0.1866, simple_loss=0.2827, pruned_loss=0.0452, over 7326.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2663, pruned_loss=0.04603, over 1419939.54 frames.], batch size: 22, lr: 2.11e-04
2022-05-28 16:09:19,800 INFO [train.py:842] (3/4) Epoch 26, batch 5200, loss[loss=0.172, simple_loss=0.2667, pruned_loss=0.03868, over 6352.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2659, pruned_loss=0.04615, over 1420526.59 frames.], batch size: 38, lr: 2.11e-04
2022-05-28 16:09:59,258 INFO [train.py:842] (3/4) Epoch 26, batch 5250, loss[loss=0.1919, simple_loss=0.2721, pruned_loss=0.05587, over 7238.00 frames.], tot_loss[loss=0.179, simple_loss=0.266, pruned_loss=0.04599, over 1421291.21 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:10:38,553 INFO [train.py:842] (3/4) Epoch 26, batch 5300, loss[loss=0.1565, simple_loss=0.2477, pruned_loss=0.03265, over 7263.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2666, pruned_loss=0.04617, over 1421734.27 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:11:17,705 INFO [train.py:842] (3/4) Epoch 26, batch 5350, loss[loss=0.1632, simple_loss=0.2417, pruned_loss=0.04235, over 7154.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2665, pruned_loss=0.04584, over 1418984.57 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:11:56,905 INFO [train.py:842] (3/4) Epoch 26, batch 5400, loss[loss=0.1825, simple_loss=0.263, pruned_loss=0.05097, over 7155.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2671, pruned_loss=0.04574, over 1416840.60 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:12:36,484 INFO [train.py:842] (3/4) Epoch 26, batch 5450, loss[loss=0.1417, simple_loss=0.2336, pruned_loss=0.02495, over 7170.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2661, pruned_loss=0.04518, over 1418274.96 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:13:15,646 INFO [train.py:842] (3/4) Epoch 26, batch 5500, loss[loss=0.1688, simple_loss=0.2501, pruned_loss=0.04382, over 7002.00 frames.], tot_loss[loss=0.1784, simple_loss=0.266, pruned_loss=0.04535, over 1412783.79 frames.], batch size: 16, lr: 2.11e-04
2022-05-28 16:13:54,877 INFO [train.py:842] (3/4) Epoch 26, batch 5550, loss[loss=0.1656, simple_loss=0.2613, pruned_loss=0.03496, over 7225.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2659, pruned_loss=0.04535, over 1415623.64 frames.], batch size: 21, lr: 2.11e-04
2022-05-28 16:14:34,118 INFO [train.py:842] (3/4) Epoch 26, batch 5600, loss[loss=0.1754, simple_loss=0.2675, pruned_loss=0.04169, over 7215.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2666, pruned_loss=0.04536, over 1417130.15 frames.], batch size: 22, lr: 2.11e-04
2022-05-28 16:15:15,705 INFO [train.py:842] (3/4) Epoch 26, batch 5650, loss[loss=0.2024, simple_loss=0.2943, pruned_loss=0.05528, over 7192.00 frames.], tot_loss[loss=0.18, simple_loss=0.2679, pruned_loss=0.04602, over 1418383.66 frames.], batch size: 23, lr: 2.11e-04
2022-05-28 16:15:55,739 INFO [train.py:842] (3/4) Epoch 26, batch 5700, loss[loss=0.1762, simple_loss=0.2718, pruned_loss=0.04035, over 7178.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2674, pruned_loss=0.04559, over 1420757.58 frames.], batch size: 26, lr: 2.11e-04
2022-05-28 16:16:35,373 INFO [train.py:842] (3/4) Epoch 26, batch 5750, loss[loss=0.1474, simple_loss=0.2388, pruned_loss=0.028, over 7154.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2663, pruned_loss=0.04536, over 1420950.92 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:17:14,691 INFO [train.py:842] (3/4) Epoch 26, batch 5800, loss[loss=0.2041, simple_loss=0.293, pruned_loss=0.05765, over 7244.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2672, pruned_loss=0.04575, over 1422686.21 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:17:54,296 INFO [train.py:842] (3/4) Epoch 26, batch 5850, loss[loss=0.1663, simple_loss=0.2452, pruned_loss=0.04363, over 7266.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2677, pruned_loss=0.04628, over 1421385.92 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:18:34,352 INFO [train.py:842] (3/4) Epoch 26, batch 5900, loss[loss=0.2061, simple_loss=0.2888, pruned_loss=0.06171, over 7290.00 frames.], tot_loss[loss=0.18, simple_loss=0.2676, pruned_loss=0.04621, over 1423352.18 frames.], batch size: 17, lr: 2.11e-04
2022-05-28 16:19:16,469 INFO [train.py:842] (3/4) Epoch 26, batch 5950, loss[loss=0.1861, simple_loss=0.2801, pruned_loss=0.04609, over 7224.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2662, pruned_loss=0.04548, over 1424359.71 frames.], batch size: 21, lr: 2.11e-04
2022-05-28 16:19:56,740 INFO [train.py:842] (3/4) Epoch 26, batch 6000, loss[loss=0.1623, simple_loss=0.257, pruned_loss=0.03378, over 6896.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2667, pruned_loss=0.04547, over 1422010.16 frames.], batch size: 31, lr: 2.11e-04
2022-05-28 16:19:56,741 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 16:20:06,474 INFO [train.py:871] (3/4) Epoch 26, validation: loss=0.164, simple_loss=0.2621, pruned_loss=0.03292, over 868885.00 frames.
2022-05-28 16:20:46,080 INFO [train.py:842] (3/4) Epoch 26, batch 6050, loss[loss=0.2486, simple_loss=0.3275, pruned_loss=0.08488, over 7142.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2672, pruned_loss=0.0457, over 1422687.62 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:21:25,162 INFO [train.py:842] (3/4) Epoch 26, batch 6100, loss[loss=0.1433, simple_loss=0.236, pruned_loss=0.02526, over 7147.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2666, pruned_loss=0.04552, over 1422906.51 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:22:05,082 INFO [train.py:842] (3/4) Epoch 26, batch 6150, loss[loss=0.1867, simple_loss=0.2778, pruned_loss=0.04777, over 7303.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2661, pruned_loss=0.04477, over 1426613.58 frames.], batch size: 24, lr: 2.11e-04
2022-05-28 16:22:44,676 INFO [train.py:842] (3/4) Epoch 26, batch 6200, loss[loss=0.16, simple_loss=0.2522, pruned_loss=0.03396, over 7161.00 frames.], tot_loss[loss=0.1773, simple_loss=0.265, pruned_loss=0.04478, over 1427614.95 frames.], batch size: 26, lr: 2.11e-04
2022-05-28 16:23:24,238 INFO [train.py:842] (3/4) Epoch 26, batch 6250, loss[loss=0.1757, simple_loss=0.2676, pruned_loss=0.04194, over 7401.00 frames.], tot_loss[loss=0.178, simple_loss=0.2658, pruned_loss=0.04512, over 1430638.69 frames.], batch size: 23, lr: 2.11e-04
2022-05-28 16:24:03,362 INFO [train.py:842] (3/4) Epoch 26, batch 6300, loss[loss=0.175, simple_loss=0.2681, pruned_loss=0.04095, over 7281.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2664, pruned_loss=0.04555, over 1425658.12 frames.], batch size: 25, lr: 2.11e-04
2022-05-28 16:24:42,799 INFO [train.py:842] (3/4) Epoch 26, batch 6350, loss[loss=0.1853, simple_loss=0.26, pruned_loss=0.05526, over 7134.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2674, pruned_loss=0.04594, over 1422933.85 frames.], batch size: 17, lr: 2.11e-04
2022-05-28 16:25:22,051 INFO [train.py:842] (3/4) Epoch 26, batch 6400, loss[loss=0.197, simple_loss=0.2756, pruned_loss=0.05923, over 7433.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2671, pruned_loss=0.0458, over 1425699.60 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:26:01,607 INFO [train.py:842] (3/4) Epoch 26, batch 6450, loss[loss=0.1835, simple_loss=0.2739, pruned_loss=0.0465, over 7248.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2669, pruned_loss=0.04615, over 1420301.32 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:26:41,195 INFO [train.py:842] (3/4) Epoch 26, batch 6500, loss[loss=0.1424, simple_loss=0.2344, pruned_loss=0.02525, over 7066.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2664, pruned_loss=0.04565, over 1423922.25 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:27:20,711 INFO [train.py:842] (3/4) Epoch 26, batch 6550, loss[loss=0.1836, simple_loss=0.2729, pruned_loss=0.04715, over 7426.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2668, pruned_loss=0.04543, over 1419172.76 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:28:00,090 INFO [train.py:842] (3/4) Epoch 26, batch 6600, loss[loss=0.2004, simple_loss=0.292, pruned_loss=0.05443, over 7203.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2661, pruned_loss=0.04508, over 1422669.23 frames.], batch size: 22, lr: 2.11e-04
2022-05-28 16:28:39,884 INFO [train.py:842] (3/4) Epoch 26, batch 6650, loss[loss=0.2138, simple_loss=0.2962, pruned_loss=0.06564, over 7367.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2659, pruned_loss=0.04521, over 1425869.57 frames.], batch size: 23, lr: 2.11e-04
2022-05-28 16:29:19,236 INFO [train.py:842] (3/4) Epoch 26, batch 6700, loss[loss=0.1395, simple_loss=0.2232, pruned_loss=0.02791, over 7273.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2659, pruned_loss=0.04499, over 1428043.31 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:29:59,171 INFO [train.py:842] (3/4) Epoch 26, batch 6750, loss[loss=0.1579, simple_loss=0.2576, pruned_loss=0.02908, over 7068.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2645, pruned_loss=0.04459, over 1429570.05 frames.], batch size: 18, lr: 2.11e-04
2022-05-28 16:30:38,531 INFO [train.py:842] (3/4) Epoch 26, batch 6800, loss[loss=0.1413, simple_loss=0.235, pruned_loss=0.02377, over 7326.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.04407, over 1431285.54 frames.], batch size: 20, lr: 2.11e-04
2022-05-28 16:31:18,202 INFO [train.py:842] (3/4) Epoch 26, batch 6850, loss[loss=0.1767, simple_loss=0.2658, pruned_loss=0.04383, over 7355.00 frames.], tot_loss[loss=0.176, simple_loss=0.2642, pruned_loss=0.04395, over 1430826.69 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:31:57,855 INFO [train.py:842] (3/4) Epoch 26, batch 6900, loss[loss=0.1507, simple_loss=0.2401, pruned_loss=0.03063, over 7263.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2639, pruned_loss=0.04425, over 1430265.35 frames.], batch size: 19, lr: 2.11e-04
2022-05-28 16:32:37,587 INFO [train.py:842] (3/4) Epoch 26, batch 6950, loss[loss=0.1695, simple_loss=0.2502, pruned_loss=0.04443, over 7137.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2643, pruned_loss=0.04478, over 1426071.02 frames.], batch size: 17, lr: 2.11e-04
2022-05-28 16:33:16,704 INFO [train.py:842] (3/4) Epoch 26, batch 7000, loss[loss=0.1591, simple_loss=0.2471, pruned_loss=0.0356, over 7294.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2658, pruned_loss=0.04544, over 1427865.36 frames.], batch size: 17, lr: 2.11e-04
2022-05-28 16:33:56,306 INFO [train.py:842] (3/4) Epoch 26, batch 7050, loss[loss=0.1993, simple_loss=0.2828, pruned_loss=0.05791, over 5397.00 frames.], tot_loss[loss=0.1771, simple_loss=0.265, pruned_loss=0.04463, over 1425288.24 frames.], batch size: 52, lr: 2.11e-04
2022-05-28 16:34:35,499 INFO [train.py:842] (3/4) Epoch 26, batch 7100, loss[loss=0.1861, simple_loss=0.2802, pruned_loss=0.04602, over 7100.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2652, pruned_loss=0.04489, over 1420484.86 frames.], batch size: 28, lr: 2.11e-04
2022-05-28 16:35:15,069 INFO [train.py:842] (3/4) Epoch 26, batch 7150, loss[loss=0.2121, simple_loss=0.2925, pruned_loss=0.06587, over 7302.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2667, pruned_loss=0.04587, over 1422575.45 frames.], batch size: 25, lr: 2.11e-04
2022-05-28 16:35:54,052 INFO [train.py:842] (3/4) Epoch 26, batch 7200, loss[loss=0.202, simple_loss=0.2943, pruned_loss=0.05491, over 7400.00 frames.], tot_loss[loss=0.1796, simple_loss=0.267, pruned_loss=0.04609, over 1423002.42 frames.], batch size: 21, lr: 2.10e-04
2022-05-28 16:36:33,705 INFO [train.py:842] (3/4) Epoch 26, batch 7250, loss[loss=0.2066, simple_loss=0.2925, pruned_loss=0.06041, over 7296.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2661, pruned_loss=0.04567, over 1424892.27 frames.], batch size: 24, lr: 2.10e-04
2022-05-28 16:37:12,939 INFO [train.py:842] (3/4) Epoch 26, batch 7300, loss[loss=0.1625, simple_loss=0.2445, pruned_loss=0.04027, over 7279.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2669, pruned_loss=0.04615, over 1423475.19 frames.], batch size: 17, lr: 2.10e-04
2022-05-28 16:37:52,158 INFO [train.py:842] (3/4) Epoch 26, batch 7350, loss[loss=0.161, simple_loss=0.2462, pruned_loss=0.03792, over 7057.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2664, pruned_loss=0.04543, over 1423625.13 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:38:31,857 INFO [train.py:842] (3/4) Epoch 26, batch 7400, loss[loss=0.1456, simple_loss=0.2187, pruned_loss=0.03622, over 7283.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2669, pruned_loss=0.04544, over 1427005.54 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:39:11,481 INFO [train.py:842] (3/4) Epoch 26, batch 7450, loss[loss=0.196, simple_loss=0.2814, pruned_loss=0.05527, over 7351.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2673, pruned_loss=0.04529, over 1426002.97 frames.], batch size: 19, lr: 2.10e-04
2022-05-28 16:39:50,860 INFO [train.py:842] (3/4) Epoch 26, batch 7500, loss[loss=0.2081, simple_loss=0.2954, pruned_loss=0.06041, over 7126.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2673, pruned_loss=0.04555, over 1430479.95 frames.], batch size: 26, lr: 2.10e-04
2022-05-28 16:40:30,590 INFO [train.py:842] (3/4) Epoch 26, batch 7550, loss[loss=0.169, simple_loss=0.2595, pruned_loss=0.03921, over 7170.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2671, pruned_loss=0.04561, over 1424141.09 frames.], batch size: 19, lr: 2.10e-04
2022-05-28 16:41:09,944 INFO [train.py:842] (3/4) Epoch 26, batch 7600, loss[loss=0.1879, simple_loss=0.2771, pruned_loss=0.04931, over 7142.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2665, pruned_loss=0.04526, over 1426066.67 frames.], batch size: 20, lr: 2.10e-04
2022-05-28 16:41:49,272 INFO [train.py:842] (3/4) Epoch 26, batch 7650, loss[loss=0.1791, simple_loss=0.2724, pruned_loss=0.04294, over 7208.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2671, pruned_loss=0.04556, over 1426889.16 frames.], batch size: 23, lr: 2.10e-04
2022-05-28 16:42:28,499 INFO [train.py:842] (3/4) Epoch 26, batch 7700, loss[loss=0.152, simple_loss=0.241, pruned_loss=0.03154, over 7430.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2667, pruned_loss=0.04523, over 1428050.59 frames.], batch size: 20, lr: 2.10e-04
2022-05-28 16:43:08,333 INFO [train.py:842] (3/4) Epoch 26, batch 7750, loss[loss=0.1368, simple_loss=0.2272, pruned_loss=0.02318, over 7160.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2661, pruned_loss=0.04521, over 1430439.91 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:43:47,837 INFO [train.py:842] (3/4) Epoch 26, batch 7800, loss[loss=0.191, simple_loss=0.2638, pruned_loss=0.05914, over 6987.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2653, pruned_loss=0.04495, over 1428192.43 frames.], batch size: 16, lr: 2.10e-04
2022-05-28 16:44:27,484 INFO [train.py:842] (3/4) Epoch 26, batch 7850, loss[loss=0.2023, simple_loss=0.302, pruned_loss=0.05127, over 6498.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04448, over 1424340.14 frames.], batch size: 38, lr: 2.10e-04
2022-05-28 16:45:06,411 INFO [train.py:842] (3/4) Epoch 26, batch 7900, loss[loss=0.1726, simple_loss=0.2525, pruned_loss=0.04636, over 6752.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2649, pruned_loss=0.04513, over 1421319.38 frames.], batch size: 15, lr: 2.10e-04
2022-05-28 16:45:46,033 INFO [train.py:842] (3/4) Epoch 26, batch 7950, loss[loss=0.1445, simple_loss=0.2324, pruned_loss=0.02831, over 7157.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2645, pruned_loss=0.04529, over 1419901.33 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:46:25,439 INFO [train.py:842] (3/4) Epoch 26, batch 8000, loss[loss=0.1757, simple_loss=0.2624, pruned_loss=0.04448, over 7167.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2634, pruned_loss=0.04447, over 1425492.93 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:47:04,830 INFO [train.py:842] (3/4) Epoch 26, batch 8050, loss[loss=0.1713, simple_loss=0.2505, pruned_loss=0.04599, over 6783.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2643, pruned_loss=0.04471, over 1427349.63 frames.], batch size: 15, lr: 2.10e-04
2022-05-28 16:47:43,851 INFO [train.py:842] (3/4) Epoch 26, batch 8100, loss[loss=0.1573, simple_loss=0.2476, pruned_loss=0.03349, over 7432.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2652, pruned_loss=0.04497, over 1429422.44 frames.], batch size: 20, lr: 2.10e-04
2022-05-28 16:48:23,583 INFO [train.py:842] (3/4) Epoch 26, batch 8150, loss[loss=0.1776, simple_loss=0.2724, pruned_loss=0.0414, over 7317.00 frames.], tot_loss[loss=0.1774, simple_loss=0.265, pruned_loss=0.04492, over 1431743.74 frames.], batch size: 21, lr: 2.10e-04
2022-05-28 16:49:02,896 INFO [train.py:842] (3/4) Epoch 26, batch 8200, loss[loss=0.1719, simple_loss=0.2544, pruned_loss=0.0447, over 7269.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2653, pruned_loss=0.04487, over 1431399.40 frames.], batch size: 19, lr: 2.10e-04
2022-05-28 16:49:42,448 INFO [train.py:842] (3/4) Epoch 26, batch 8250, loss[loss=0.162, simple_loss=0.2482, pruned_loss=0.03791, over 7419.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2654, pruned_loss=0.04492, over 1430838.83 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:50:21,811 INFO [train.py:842] (3/4) Epoch 26, batch 8300, loss[loss=0.1826, simple_loss=0.2788, pruned_loss=0.04319, over 7347.00 frames.], tot_loss[loss=0.177, simple_loss=0.2647, pruned_loss=0.04463, over 1432767.37 frames.], batch size: 25, lr: 2.10e-04
2022-05-28 16:51:01,224 INFO [train.py:842] (3/4) Epoch 26, batch 8350, loss[loss=0.172, simple_loss=0.2532, pruned_loss=0.04536, over 7360.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2659, pruned_loss=0.04547, over 1423532.87 frames.], batch size: 19, lr: 2.10e-04
2022-05-28 16:51:40,163 INFO [train.py:842] (3/4) Epoch 26, batch 8400, loss[loss=0.1897, simple_loss=0.2736, pruned_loss=0.05287, over 7163.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2664, pruned_loss=0.0454, over 1420381.60 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:52:19,775 INFO [train.py:842] (3/4) Epoch 26, batch 8450, loss[loss=0.1876, simple_loss=0.2693, pruned_loss=0.05292, over 5189.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2662, pruned_loss=0.0456, over 1421258.18 frames.], batch size: 52, lr: 2.10e-04
2022-05-28 16:52:58,978 INFO [train.py:842] (3/4) Epoch 26, batch 8500, loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.04103, over 7256.00 frames.], tot_loss[loss=0.1797, simple_loss=0.267, pruned_loss=0.04617, over 1419569.52 frames.], batch size: 19, lr: 2.10e-04
2022-05-28 16:53:38,744 INFO [train.py:842] (3/4) Epoch 26, batch 8550, loss[loss=0.1795, simple_loss=0.2746, pruned_loss=0.04225, over 7024.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2669, pruned_loss=0.04596, over 1421024.36 frames.], batch size: 28, lr: 2.10e-04
2022-05-28 16:54:18,378 INFO [train.py:842] (3/4) Epoch 26, batch 8600, loss[loss=0.1603, simple_loss=0.2451, pruned_loss=0.03775, over 7132.00 frames.], tot_loss[loss=0.1795, simple_loss=0.267, pruned_loss=0.04599, over 1425030.37 frames.], batch size: 17, lr: 2.10e-04
2022-05-28 16:54:58,073 INFO [train.py:842] (3/4) Epoch 26, batch 8650, loss[loss=0.1451, simple_loss=0.234, pruned_loss=0.0281, over 7145.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2658, pruned_loss=0.04533, over 1419819.31 frames.], batch size: 17, lr: 2.10e-04
2022-05-28 16:55:37,258 INFO [train.py:842] (3/4) Epoch 26, batch 8700, loss[loss=0.1623, simple_loss=0.2581, pruned_loss=0.0333, over 7337.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2659, pruned_loss=0.04525, over 1415362.10 frames.], batch size: 20, lr: 2.10e-04
2022-05-28 16:56:16,928 INFO [train.py:842] (3/4) Epoch 26, batch 8750, loss[loss=0.1885, simple_loss=0.2898, pruned_loss=0.04353, over 7165.00 frames.], tot_loss[loss=0.178, simple_loss=0.266, pruned_loss=0.04498, over 1419734.26 frames.], batch size: 26, lr: 2.10e-04
2022-05-28 16:56:56,114 INFO [train.py:842] (3/4) Epoch 26, batch 8800, loss[loss=0.2718, simple_loss=0.34, pruned_loss=0.1018, over 7278.00 frames.], tot_loss[loss=0.179, simple_loss=0.2669, pruned_loss=0.04551, over 1420992.69 frames.], batch size: 24, lr: 2.10e-04
2022-05-28 16:57:35,786 INFO [train.py:842] (3/4) Epoch 26, batch 8850, loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.04099, over 7067.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2678, pruned_loss=0.04619, over 1419063.03 frames.], batch size: 18, lr: 2.10e-04
2022-05-28 16:58:14,948 INFO [train.py:842] (3/4) Epoch 26, batch 8900, loss[loss=0.1675, simple_loss=0.2534, pruned_loss=0.04082, over 7150.00 frames.], tot_loss[loss=0.181, simple_loss=0.2688, pruned_loss=0.04655, over 1420172.63 frames.], batch size: 20, lr: 2.10e-04
2022-05-28 16:59:04,939 INFO [train.py:842] (3/4) Epoch 26, batch 8950, loss[loss=0.1966, simple_loss=0.2902, pruned_loss=0.05152, over 7140.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2691, pruned_loss=0.04619, over 1417721.79 frames.], batch size: 26, lr: 2.10e-04
2022-05-28 16:59:43,834 INFO [train.py:842] (3/4) Epoch 26, batch 9000, loss[loss=0.2175, simple_loss=0.2952, pruned_loss=0.06994, over 5089.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2695, pruned_loss=0.04641, over 1413362.84 frames.], batch size: 54, lr: 2.10e-04
2022-05-28 16:59:43,835 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 16:59:53,410 INFO [train.py:871] (3/4) Epoch 26, validation: loss=0.1634, simple_loss=0.2612, pruned_loss=0.03281, over 868885.00 frames.
2022-05-28 17:00:32,367 INFO [train.py:842] (3/4) Epoch 26, batch 9050, loss[loss=0.1813, simple_loss=0.265, pruned_loss=0.04873, over 4761.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2705, pruned_loss=0.04721, over 1388738.81 frames.], batch size: 52, lr: 2.10e-04
2022-05-28 17:01:10,221 INFO [train.py:842] (3/4) Epoch 26, batch 9100, loss[loss=0.2291, simple_loss=0.3163, pruned_loss=0.07094, over 4857.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2731, pruned_loss=0.04871, over 1341953.02 frames.], batch size: 52, lr: 2.10e-04
2022-05-28 17:01:48,413 INFO [train.py:842] (3/4) Epoch 26, batch 9150, loss[loss=0.2678, simple_loss=0.3498, pruned_loss=0.09289, over 4897.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2776, pruned_loss=0.05207, over 1275180.10 frames.], batch size: 53, lr: 2.10e-04
2022-05-28 17:02:39,069 INFO [train.py:842] (3/4) Epoch 27, batch 0, loss[loss=0.1729, simple_loss=0.2529, pruned_loss=0.04641, over 7164.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2529, pruned_loss=0.04641, over 7164.00 frames.], batch size: 18, lr: 2.06e-04
2022-05-28 17:03:18,930 INFO [train.py:842] (3/4) Epoch 27, batch 50, loss[loss=0.1398, simple_loss=0.2158, pruned_loss=0.03191, over 7269.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2657, pruned_loss=0.04573, over 318278.64 frames.], batch size: 17, lr: 2.06e-04
2022-05-28 17:03:58,064 INFO [train.py:842] (3/4) Epoch 27, batch 100, loss[loss=0.1679, simple_loss=0.244, pruned_loss=0.04587, over 7281.00 frames.], tot_loss[loss=0.18, simple_loss=0.2681, pruned_loss=0.04598, over 562080.78 frames.], batch size: 17, lr: 2.06e-04
2022-05-28 17:04:37,588 INFO [train.py:842] (3/4) Epoch 27, batch 150, loss[loss=0.1869, simple_loss=0.277, pruned_loss=0.04845, over 6272.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2668, pruned_loss=0.04543, over 751109.46 frames.], batch size: 37, lr: 2.06e-04
2022-05-28 17:05:16,840 INFO [train.py:842] (3/4) Epoch 27, batch 200, loss[loss=0.172, simple_loss=0.2681, pruned_loss=0.038, over 7179.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2668, pruned_loss=0.04591, over 893727.64 frames.], batch size: 26, lr: 2.06e-04
2022-05-28 17:05:56,180 INFO [train.py:842] (3/4) Epoch 27, batch 250, loss[loss=0.1459, simple_loss=0.2375, pruned_loss=0.0272, over 6196.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2674, pruned_loss=0.04583, over 1006162.54 frames.], batch size: 37, lr: 2.06e-04
2022-05-28 17:06:35,394 INFO [train.py:842] (3/4) Epoch 27, batch 300, loss[loss=0.1757, simple_loss=0.2719, pruned_loss=0.03976, over 6219.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2659, pruned_loss=0.04456, over 1099805.05 frames.], batch size: 37, lr: 2.06e-04
2022-05-28 17:07:15,024 INFO [train.py:842] (3/4) Epoch 27, batch 350, loss[loss=0.1886, simple_loss=0.2851, pruned_loss=0.04602, over 6720.00 frames.], tot_loss[loss=0.176, simple_loss=0.2647, pruned_loss=0.04363, over 1167670.06 frames.], batch size: 31, lr: 2.06e-04
2022-05-28 17:07:54,297 INFO [train.py:842] (3/4) Epoch 27, batch 400, loss[loss=0.1559, simple_loss=0.2523, pruned_loss=0.02974, over 7144.00 frames.], tot_loss[loss=0.176, simple_loss=0.2651, pruned_loss=0.04348, over 1227822.19 frames.], batch size: 20, lr: 2.06e-04
2022-05-28 17:08:33,818 INFO [train.py:842] (3/4) Epoch 27, batch 450, loss[loss=0.211, simple_loss=0.3002, pruned_loss=0.06088, over 7229.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2643, pruned_loss=0.04327, over 1275509.73 frames.], batch size: 20, lr: 2.06e-04
2022-05-28 17:09:13,073 INFO [train.py:842] (3/4) Epoch 27, batch 500, loss[loss=0.2075, simple_loss=0.2975, pruned_loss=0.05869, over 5481.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2638, pruned_loss=0.0433, over 1307351.98 frames.], batch size: 56, lr: 2.06e-04
2022-05-28 17:09:52,599 INFO [train.py:842] (3/4) Epoch 27, batch 550, loss[loss=0.1688, simple_loss=0.2567, pruned_loss=0.04044, over 7201.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2643, pruned_loss=0.04371, over 1332625.54 frames.], batch size: 22, lr: 2.06e-04
2022-05-28 17:10:31,944 INFO [train.py:842] (3/4) Epoch 27, batch 600, loss[loss=0.1707, simple_loss=0.2497, pruned_loss=0.04581, over 7262.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.04424, over 1355383.98 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:11:11,821 INFO [train.py:842] (3/4) Epoch 27, batch 650, loss[loss=0.14, simple_loss=0.2285, pruned_loss=0.02574, over 7267.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2638, pruned_loss=0.04417, over 1373002.19 frames.], batch size: 18, lr: 2.05e-04
2022-05-28 17:11:50,950 INFO [train.py:842] (3/4) Epoch 27, batch 700, loss[loss=0.1511, simple_loss=0.2448, pruned_loss=0.02873, over 7120.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2641, pruned_loss=0.04384, over 1382451.13 frames.], batch size: 21, lr: 2.05e-04
2022-05-28 17:12:30,585 INFO [train.py:842] (3/4) Epoch 27, batch 750, loss[loss=0.1732, simple_loss=0.2701, pruned_loss=0.0381, over 7141.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2647, pruned_loss=0.04383, over 1390225.93 frames.], batch size: 20, lr: 2.05e-04
2022-05-28 17:13:09,841 INFO [train.py:842] (3/4) Epoch 27, batch 800, loss[loss=0.1765, simple_loss=0.2633, pruned_loss=0.04479, over 7245.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2647, pruned_loss=0.044, over 1396093.40 frames.], batch size: 20, lr: 2.05e-04
2022-05-28 17:13:49,299 INFO [train.py:842] (3/4) Epoch 27, batch 850, loss[loss=0.1831, simple_loss=0.2663, pruned_loss=0.04991, over 5495.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2657, pruned_loss=0.04441, over 1399333.80 frames.], batch size: 52, lr: 2.05e-04
2022-05-28 17:14:28,646 INFO [train.py:842] (3/4) Epoch 27, batch 900, loss[loss=0.1686, simple_loss=0.2497, pruned_loss=0.0438, over 7412.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2649, pruned_loss=0.04396, over 1408668.68 frames.], batch size: 18, lr: 2.05e-04
2022-05-28 17:15:08,264 INFO [train.py:842] (3/4) Epoch 27, batch 950, loss[loss=0.1768, simple_loss=0.257, pruned_loss=0.04833, over 6767.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2661, pruned_loss=0.04469, over 1409618.17 frames.], batch size: 15, lr: 2.05e-04
2022-05-28 17:15:47,437 INFO [train.py:842] (3/4) Epoch 27, batch 1000, loss[loss=0.1818, simple_loss=0.2685, pruned_loss=0.04752, over 7299.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2656, pruned_loss=0.04448, over 1413188.10 frames.], batch size: 24, lr: 2.05e-04
2022-05-28 17:16:29,684 INFO [train.py:842] (3/4) Epoch 27, batch 1050, loss[loss=0.1691, simple_loss=0.2613, pruned_loss=0.03844, over 7181.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2658, pruned_loss=0.04494, over 1417940.02 frames.], batch size: 23, lr: 2.05e-04
2022-05-28 17:17:09,247 INFO [train.py:842] (3/4) Epoch 27, batch 1100, loss[loss=0.1894, simple_loss=0.2807, pruned_loss=0.04904, over 7197.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2649, pruned_loss=0.04474, over 1422121.55 frames.], batch size: 22, lr: 2.05e-04
2022-05-28 17:17:48,447 INFO [train.py:842] (3/4) Epoch 27, batch 1150, loss[loss=0.1484, simple_loss=0.2397, pruned_loss=0.0285, over 7173.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2645, pruned_loss=0.04432, over 1423786.41 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:18:27,736 INFO [train.py:842] (3/4) Epoch 27, batch 1200, loss[loss=0.1924, simple_loss=0.2805, pruned_loss=0.05209, over 7296.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2652, pruned_loss=0.04462, over 1427357.08 frames.], batch size: 24, lr: 2.05e-04
2022-05-28 17:19:07,428 INFO [train.py:842] (3/4) Epoch 27, batch 1250, loss[loss=0.165, simple_loss=0.2581, pruned_loss=0.036, over 6469.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2647, pruned_loss=0.04429, over 1427279.04 frames.], batch size: 38, lr: 2.05e-04
2022-05-28 17:19:46,486 INFO [train.py:842] (3/4) Epoch 27, batch 1300, loss[loss=0.2103, simple_loss=0.2859, pruned_loss=0.06731, over 7274.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2648, pruned_loss=0.04447, over 1423033.01 frames.], batch size: 18, lr: 2.05e-04
2022-05-28 17:20:26,348 INFO [train.py:842] (3/4) Epoch 27, batch 1350, loss[loss=0.1464, simple_loss=0.2278, pruned_loss=0.03251, over 7414.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2634, pruned_loss=0.04415, over 1426872.36 frames.], batch size: 18, lr: 2.05e-04
2022-05-28 17:21:05,320 INFO [train.py:842] (3/4) Epoch 27, batch 1400, loss[loss=0.179, simple_loss=0.2693, pruned_loss=0.04433, over 7202.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2645, pruned_loss=0.04485, over 1419809.91 frames.], batch size: 23, lr: 2.05e-04
2022-05-28 17:21:44,758 INFO [train.py:842] (3/4) Epoch 27, batch 1450, loss[loss=0.1338, simple_loss=0.2203, pruned_loss=0.02363, over 7281.00 frames.], tot_loss[loss=0.177, simple_loss=0.2643, pruned_loss=0.0448, over 1421383.71 frames.], batch size: 18, lr: 2.05e-04
2022-05-28 17:22:23,932 INFO [train.py:842] (3/4) Epoch 27, batch 1500, loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03858, over 5427.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04454, over 1417682.60 frames.], batch size: 53, lr: 2.05e-04
2022-05-28 17:23:03,677 INFO [train.py:842] (3/4) Epoch 27, batch 1550, loss[loss=0.1723, simple_loss=0.2668, pruned_loss=0.03894, over 7116.00 frames.], tot_loss[loss=0.1761, simple_loss=0.264, pruned_loss=0.04411, over 1421225.96 frames.], batch size: 21, lr: 2.05e-04
2022-05-28 17:23:43,243 INFO [train.py:842] (3/4) Epoch 27, batch 1600, loss[loss=0.1888, simple_loss=0.2723, pruned_loss=0.05266, over 7266.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2637, pruned_loss=0.04403, over 1425990.65 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:24:22,842 INFO [train.py:842] (3/4) Epoch 27, batch 1650, loss[loss=0.1902, simple_loss=0.2853, pruned_loss=0.04756, over 7167.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2649, pruned_loss=0.04463, over 1429617.45 frames.], batch size: 26, lr: 2.05e-04
2022-05-28 17:25:01,991 INFO [train.py:842] (3/4) Epoch 27, batch 1700, loss[loss=0.1614, simple_loss=0.2542, pruned_loss=0.03426, over 7346.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2654, pruned_loss=0.04484, over 1430515.82 frames.], batch size: 22, lr: 2.05e-04
2022-05-28 17:25:41,516 INFO [train.py:842] (3/4) Epoch 27, batch 1750, loss[loss=0.1795, simple_loss=0.2658, pruned_loss=0.04659, over 7213.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2653, pruned_loss=0.04424, over 1430909.54 frames.], batch size: 26, lr: 2.05e-04
2022-05-28 17:26:20,760 INFO [train.py:842] (3/4) Epoch 27, batch 1800, loss[loss=0.1487, simple_loss=0.2566, pruned_loss=0.0204, over 7118.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2648, pruned_loss=0.04447, over 1428532.66 frames.], batch size: 21, lr: 2.05e-04
2022-05-28 17:27:00,463 INFO [train.py:842] (3/4) Epoch 27, batch 1850, loss[loss=0.1975, simple_loss=0.2771, pruned_loss=0.05899, over 4985.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2641, pruned_loss=0.04407, over 1428680.70 frames.], batch size: 52, lr: 2.05e-04
2022-05-28 17:27:40,058 INFO [train.py:842] (3/4) Epoch 27, batch 1900, loss[loss=0.159, simple_loss=0.2523, pruned_loss=0.03282, over 7344.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04435, over 1427257.42 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:28:19,461 INFO [train.py:842] (3/4) Epoch 27, batch 1950, loss[loss=0.1827, simple_loss=0.2703, pruned_loss=0.04753, over 6370.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.0444, over 1424105.84 frames.], batch size: 38, lr: 2.05e-04
2022-05-28 17:28:58,965 INFO [train.py:842] (3/4) Epoch 27, batch 2000, loss[loss=0.1634, simple_loss=0.2499, pruned_loss=0.03848, over 6791.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2641, pruned_loss=0.04414, over 1422595.74 frames.], batch size: 31, lr: 2.05e-04
2022-05-28 17:29:38,278 INFO [train.py:842] (3/4) Epoch 27, batch 2050, loss[loss=0.1774, simple_loss=0.2716, pruned_loss=0.0416, over 7168.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2642, pruned_loss=0.0442, over 1425450.62 frames.], batch size: 26, lr: 2.05e-04
2022-05-28 17:30:17,501 INFO [train.py:842] (3/4) Epoch 27, batch 2100, loss[loss=0.2387, simple_loss=0.3192, pruned_loss=0.07913, over 7212.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2641, pruned_loss=0.04418, over 1424798.24 frames.], batch size: 22, lr: 2.05e-04
2022-05-28 17:30:56,986 INFO [train.py:842] (3/4) Epoch 27, batch 2150, loss[loss=0.2002, simple_loss=0.2841, pruned_loss=0.0581, over 7327.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2652, pruned_loss=0.04433, over 1428182.56 frames.], batch size: 25, lr: 2.05e-04
2022-05-28 17:31:36,225 INFO [train.py:842] (3/4) Epoch 27, batch 2200, loss[loss=0.1588, simple_loss=0.2526, pruned_loss=0.03248, over 7240.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2663, pruned_loss=0.04531, over 1426646.89 frames.], batch size: 20, lr: 2.05e-04
2022-05-28 17:32:15,924 INFO [train.py:842] (3/4) Epoch 27, batch 2250, loss[loss=0.1718, simple_loss=0.2441, pruned_loss=0.04974, over 7423.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04497, over 1432107.94 frames.], batch size: 17, lr: 2.05e-04
2022-05-28 17:32:55,020 INFO [train.py:842] (3/4) Epoch 27, batch 2300, loss[loss=0.1408, simple_loss=0.2315, pruned_loss=0.02505, over 7123.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2657, pruned_loss=0.04432, over 1433090.65 frames.], batch size: 17, lr: 2.05e-04
2022-05-28 17:33:34,536 INFO [train.py:842] (3/4) Epoch 27, batch 2350, loss[loss=0.1825, simple_loss=0.2744, pruned_loss=0.04529, over 7140.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2671, pruned_loss=0.04538, over 1431951.60 frames.], batch size: 20, lr: 2.05e-04
2022-05-28 17:34:13,875 INFO [train.py:842] (3/4) Epoch 27, batch 2400, loss[loss=0.1927, simple_loss=0.2864, pruned_loss=0.04949, over 7301.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2677, pruned_loss=0.04581, over 1433686.83 frames.], batch size: 24, lr: 2.05e-04
2022-05-28 17:34:53,607 INFO [train.py:842] (3/4) Epoch 27, batch 2450, loss[loss=0.195, simple_loss=0.2711, pruned_loss=0.05947, over 7234.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2677, pruned_loss=0.04582, over 1436598.52 frames.], batch size: 20, lr: 2.05e-04
2022-05-28 17:35:32,774 INFO [train.py:842] (3/4) Epoch 27, batch 2500, loss[loss=0.171, simple_loss=0.2591, pruned_loss=0.04143, over 7223.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2668, pruned_loss=0.04582, over 1438023.66 frames.], batch size: 21, lr: 2.05e-04
2022-05-28 17:36:12,384 INFO [train.py:842] (3/4) Epoch 27, batch 2550, loss[loss=0.223, simple_loss=0.3067, pruned_loss=0.0696, over 6950.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2665, pruned_loss=0.0455, over 1435370.23 frames.], batch size: 32, lr: 2.05e-04
2022-05-28 17:36:51,716 INFO [train.py:842] (3/4) Epoch 27, batch 2600, loss[loss=0.159, simple_loss=0.2282, pruned_loss=0.04491, over 6782.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2659, pruned_loss=0.04538, over 1434542.97 frames.], batch size: 15, lr: 2.05e-04
2022-05-28 17:37:31,356 INFO [train.py:842] (3/4) Epoch 27, batch 2650, loss[loss=0.1733, simple_loss=0.2612, pruned_loss=0.04268, over 7281.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2659, pruned_loss=0.04554, over 1430432.02 frames.], batch size: 24, lr: 2.05e-04
2022-05-28 17:38:10,556 INFO [train.py:842] (3/4) Epoch 27, batch 2700, loss[loss=0.1855, simple_loss=0.2897, pruned_loss=0.0407, over 7327.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2652, pruned_loss=0.04504, over 1428259.55 frames.], batch size: 22, lr: 2.05e-04
2022-05-28 17:38:50,274 INFO [train.py:842] (3/4) Epoch 27, batch 2750, loss[loss=0.1624, simple_loss=0.2502, pruned_loss=0.03726, over 7164.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2649, pruned_loss=0.04479, over 1427614.78 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:39:29,439 INFO [train.py:842] (3/4) Epoch 27, batch 2800, loss[loss=0.1967, simple_loss=0.2829, pruned_loss=0.05521, over 7306.00 frames.], tot_loss[loss=0.1784, simple_loss=0.266, pruned_loss=0.04546, over 1427273.91 frames.], batch size: 25, lr: 2.05e-04
2022-05-28 17:40:08,859 INFO [train.py:842] (3/4) Epoch 27, batch 2850, loss[loss=0.1707, simple_loss=0.2651, pruned_loss=0.03818, over 7259.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2662, pruned_loss=0.04513, over 1427458.53 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:40:48,074 INFO [train.py:842] (3/4) Epoch 27, batch 2900, loss[loss=0.1475, simple_loss=0.2344, pruned_loss=0.03024, over 7154.00 frames.], tot_loss[loss=0.1768, simple_loss=0.265, pruned_loss=0.04436, over 1426159.32 frames.], batch size: 19, lr: 2.05e-04
2022-05-28 17:41:27,477 INFO [train.py:842] (3/4) Epoch 27, batch 2950, loss[loss=0.1553, simple_loss=0.2528, pruned_loss=0.02889, over 7113.00 frames.], tot_loss[loss=0.1768, simple_loss=0.265, pruned_loss=0.04433, over 1420043.47 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 17:42:06,542 INFO [train.py:842] (3/4) Epoch 27, batch 3000, loss[loss=0.1813, simple_loss=0.2852, pruned_loss=0.03868, over 7419.00 frames.], tot_loss[loss=0.177, simple_loss=0.2652, pruned_loss=0.04439, over 1418680.77 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 17:42:06,543 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 17:42:16,299 INFO [train.py:871] (3/4) Epoch 27, validation: loss=0.1636, simple_loss=0.2622, pruned_loss=0.03251, over 868885.00 frames.
2022-05-28 17:42:56,082 INFO [train.py:842] (3/4) Epoch 27, batch 3050, loss[loss=0.1557, simple_loss=0.2606, pruned_loss=0.02542, over 7115.00 frames.], tot_loss[loss=0.176, simple_loss=0.2643, pruned_loss=0.04386, over 1412077.96 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 17:43:35,173 INFO [train.py:842] (3/4) Epoch 27, batch 3100, loss[loss=0.1656, simple_loss=0.263, pruned_loss=0.0341, over 7318.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04391, over 1417636.82 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 17:44:15,002 INFO [train.py:842] (3/4) Epoch 27, batch 3150, loss[loss=0.2425, simple_loss=0.3234, pruned_loss=0.08083, over 7213.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2657, pruned_loss=0.04436, over 1417852.59 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:44:54,125 INFO [train.py:842] (3/4) Epoch 27, batch 3200, loss[loss=0.224, simple_loss=0.3232, pruned_loss=0.06234, over 7191.00 frames.], tot_loss[loss=0.1776, simple_loss=0.266, pruned_loss=0.04458, over 1420285.11 frames.], batch size: 23, lr: 2.04e-04
2022-05-28 17:45:33,919 INFO [train.py:842] (3/4) Epoch 27, batch 3250, loss[loss=0.2062, simple_loss=0.2928, pruned_loss=0.05981, over 6400.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2662, pruned_loss=0.04469, over 1420066.79 frames.], batch size: 38, lr: 2.04e-04
2022-05-28 17:46:13,069 INFO [train.py:842] (3/4) Epoch 27, batch 3300, loss[loss=0.1905, simple_loss=0.2843, pruned_loss=0.0484, over 6809.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2665, pruned_loss=0.04485, over 1419741.25 frames.], batch size: 31, lr: 2.04e-04
2022-05-28 17:46:52,325 INFO [train.py:842] (3/4) Epoch 27, batch 3350, loss[loss=0.2045, simple_loss=0.2882, pruned_loss=0.06039, over 7332.00 frames.], tot_loss[loss=0.1796, simple_loss=0.268, pruned_loss=0.0456, over 1421308.26 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:47:31,363 INFO [train.py:842] (3/4) Epoch 27, batch 3400, loss[loss=0.1755, simple_loss=0.2624, pruned_loss=0.04425, over 7149.00 frames.], tot_loss[loss=0.18, simple_loss=0.268, pruned_loss=0.04595, over 1418359.04 frames.], batch size: 20, lr: 2.04e-04
2022-05-28 17:48:10,903 INFO [train.py:842] (3/4) Epoch 27, batch 3450, loss[loss=0.185, simple_loss=0.2723, pruned_loss=0.04884, over 7330.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2671, pruned_loss=0.04525, over 1421875.13 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:49:02,137 INFO [train.py:842] (3/4) Epoch 27, batch 3500, loss[loss=0.1592, simple_loss=0.2354, pruned_loss=0.04151, over 6808.00 frames.], tot_loss[loss=0.1766, simple_loss=0.265, pruned_loss=0.04409, over 1424166.52 frames.], batch size: 15, lr: 2.04e-04
2022-05-28 17:49:41,599 INFO [train.py:842] (3/4) Epoch 27, batch 3550, loss[loss=0.2004, simple_loss=0.2787, pruned_loss=0.06101, over 5162.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2637, pruned_loss=0.04346, over 1418371.26 frames.], batch size: 52, lr: 2.04e-04
2022-05-28 17:50:20,546 INFO [train.py:842] (3/4) Epoch 27, batch 3600, loss[loss=0.201, simple_loss=0.2889, pruned_loss=0.05656, over 7165.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2647, pruned_loss=0.04386, over 1414915.48 frames.], batch size: 19, lr: 2.04e-04
2022-05-28 17:51:00,304 INFO [train.py:842] (3/4) Epoch 27, batch 3650, loss[loss=0.1746, simple_loss=0.2665, pruned_loss=0.04134, over 7079.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2648, pruned_loss=0.0441, over 1414293.67 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 17:51:50,557 INFO [train.py:842] (3/4) Epoch 27, batch 3700, loss[loss=0.1685, simple_loss=0.2582, pruned_loss=0.03943, over 7194.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.04421, over 1413135.95 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:52:41,192 INFO [train.py:842] (3/4) Epoch 27, batch 3750, loss[loss=0.1518, simple_loss=0.2452, pruned_loss=0.02915, over 7146.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2633, pruned_loss=0.0437, over 1416221.66 frames.], batch size: 19, lr: 2.04e-04
2022-05-28 17:53:20,698 INFO [train.py:842] (3/4) Epoch 27, batch 3800, loss[loss=0.1612, simple_loss=0.242, pruned_loss=0.04019, over 7409.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.04338, over 1420636.97 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 17:54:00,207 INFO [train.py:842] (3/4) Epoch 27, batch 3850, loss[loss=0.1755, simple_loss=0.2562, pruned_loss=0.04737, over 7209.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2632, pruned_loss=0.044, over 1415216.76 frames.], batch size: 23, lr: 2.04e-04
2022-05-28 17:54:39,431 INFO [train.py:842] (3/4) Epoch 27, batch 3900, loss[loss=0.1772, simple_loss=0.2648, pruned_loss=0.04481, over 7208.00 frames.], tot_loss[loss=0.1762, simple_loss=0.264, pruned_loss=0.04417, over 1413482.94 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:55:18,925 INFO [train.py:842] (3/4) Epoch 27, batch 3950, loss[loss=0.1708, simple_loss=0.2633, pruned_loss=0.03914, over 7318.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04413, over 1417711.19 frames.], batch size: 20, lr: 2.04e-04
2022-05-28 17:55:58,115 INFO [train.py:842] (3/4) Epoch 27, batch 4000, loss[loss=0.1754, simple_loss=0.2699, pruned_loss=0.04041, over 7408.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2647, pruned_loss=0.04389, over 1424512.36 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 17:56:37,769 INFO [train.py:842] (3/4) Epoch 27, batch 4050, loss[loss=0.1845, simple_loss=0.2793, pruned_loss=0.04489, over 7213.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2655, pruned_loss=0.04462, over 1426880.79 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:57:17,350 INFO [train.py:842] (3/4) Epoch 27, batch 4100, loss[loss=0.1461, simple_loss=0.2424, pruned_loss=0.02485, over 7258.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2642, pruned_loss=0.04412, over 1429122.71 frames.], batch size: 19, lr: 2.04e-04
2022-05-28 17:57:56,802 INFO [train.py:842] (3/4) Epoch 27, batch 4150, loss[loss=0.148, simple_loss=0.2474, pruned_loss=0.02436, over 7339.00 frames.], tot_loss[loss=0.1752, simple_loss=0.263, pruned_loss=0.04368, over 1423864.59 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 17:58:36,180 INFO [train.py:842] (3/4) Epoch 27, batch 4200, loss[loss=0.1638, simple_loss=0.2582, pruned_loss=0.03471, over 7062.00 frames.], tot_loss[loss=0.1759, simple_loss=0.264, pruned_loss=0.04396, over 1424482.17 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 17:59:15,954 INFO [train.py:842] (3/4) Epoch 27, batch 4250, loss[loss=0.201, simple_loss=0.2947, pruned_loss=0.05365, over 7327.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2651, pruned_loss=0.04498, over 1426104.90 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 17:59:55,123 INFO [train.py:842] (3/4) Epoch 27, batch 4300, loss[loss=0.2195, simple_loss=0.2885, pruned_loss=0.07521, over 7137.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2662, pruned_loss=0.04549, over 1423225.66 frames.], batch size: 17, lr: 2.04e-04
2022-05-28 18:00:34,755 INFO [train.py:842] (3/4) Epoch 27, batch 4350, loss[loss=0.1831, simple_loss=0.2714, pruned_loss=0.04742, over 7302.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2657, pruned_loss=0.04529, over 1420189.02 frames.], batch size: 24, lr: 2.04e-04
2022-05-28 18:01:13,867 INFO [train.py:842] (3/4) Epoch 27, batch 4400, loss[loss=0.1756, simple_loss=0.2684, pruned_loss=0.04138, over 7206.00 frames.], tot_loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04589, over 1419986.65 frames.], batch size: 23, lr: 2.04e-04
2022-05-28 18:01:53,415 INFO [train.py:842] (3/4) Epoch 27, batch 4450, loss[loss=0.202, simple_loss=0.2957, pruned_loss=0.05418, over 7129.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2669, pruned_loss=0.04577, over 1418532.80 frames.], batch size: 28, lr: 2.04e-04
2022-05-28 18:02:32,837 INFO [train.py:842] (3/4) Epoch 27, batch 4500, loss[loss=0.2272, simple_loss=0.3236, pruned_loss=0.06537, over 7410.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2669, pruned_loss=0.04595, over 1424716.38 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 18:03:12,558 INFO [train.py:842] (3/4) Epoch 27, batch 4550, loss[loss=0.2255, simple_loss=0.3004, pruned_loss=0.07528, over 7407.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2667, pruned_loss=0.04591, over 1417505.77 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 18:03:51,740 INFO [train.py:842] (3/4) Epoch 27, batch 4600, loss[loss=0.1646, simple_loss=0.2442, pruned_loss=0.04254, over 7293.00 frames.], tot_loss[loss=0.1784, simple_loss=0.266, pruned_loss=0.04537, over 1417913.95 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 18:04:31,190 INFO [train.py:842] (3/4) Epoch 27, batch 4650, loss[loss=0.1838, simple_loss=0.2592, pruned_loss=0.05418, over 7003.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2647, pruned_loss=0.04483, over 1421021.07 frames.], batch size: 16, lr: 2.04e-04
2022-05-28 18:05:10,264 INFO [train.py:842] (3/4) Epoch 27, batch 4700, loss[loss=0.1611, simple_loss=0.2419, pruned_loss=0.04016, over 7267.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2646, pruned_loss=0.04439, over 1421301.48 frames.], batch size: 19, lr: 2.04e-04
2022-05-28 18:05:49,591 INFO [train.py:842] (3/4) Epoch 27, batch 4750, loss[loss=0.1579, simple_loss=0.2494, pruned_loss=0.03317, over 7215.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04496, over 1424158.81 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 18:06:28,915 INFO [train.py:842] (3/4) Epoch 27, batch 4800, loss[loss=0.1672, simple_loss=0.2518, pruned_loss=0.04133, over 7288.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2653, pruned_loss=0.04474, over 1425323.16 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 18:07:08,547 INFO [train.py:842] (3/4) Epoch 27, batch 4850, loss[loss=0.1925, simple_loss=0.2967, pruned_loss=0.04417, over 7329.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2658, pruned_loss=0.04479, over 1426393.08 frames.], batch size: 21, lr: 2.04e-04
2022-05-28 18:07:47,930 INFO [train.py:842] (3/4) Epoch 27, batch 4900, loss[loss=0.256, simple_loss=0.3425, pruned_loss=0.08479, over 7203.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2666, pruned_loss=0.04484, over 1427650.96 frames.], batch size: 22, lr: 2.04e-04
2022-05-28 18:08:27,477 INFO [train.py:842] (3/4) Epoch 27, batch 4950, loss[loss=0.1485, simple_loss=0.2428, pruned_loss=0.02712, over 7280.00 frames.], tot_loss[loss=0.178, simple_loss=0.2663, pruned_loss=0.04485, over 1422579.07 frames.], batch size: 17, lr: 2.04e-04
2022-05-28 18:09:06,659 INFO [train.py:842] (3/4) Epoch 27, batch 5000, loss[loss=0.2024, simple_loss=0.2936, pruned_loss=0.05556, over 7222.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2658, pruned_loss=0.0448, over 1420757.02 frames.], batch size: 25, lr: 2.04e-04
2022-05-28 18:09:46,211 INFO [train.py:842] (3/4) Epoch 27, batch 5050, loss[loss=0.1604, simple_loss=0.2525, pruned_loss=0.03417, over 7234.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2661, pruned_loss=0.04501, over 1424240.84 frames.], batch size: 20, lr: 2.04e-04
2022-05-28 18:10:25,445 INFO [train.py:842] (3/4) Epoch 27, batch 5100, loss[loss=0.1651, simple_loss=0.2403, pruned_loss=0.04498, over 7284.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2654, pruned_loss=0.0448, over 1422657.38 frames.], batch size: 17, lr: 2.04e-04
2022-05-28 18:11:05,121 INFO [train.py:842] (3/4) Epoch 27, batch 5150, loss[loss=0.215, simple_loss=0.2919, pruned_loss=0.06903, over 7204.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2653, pruned_loss=0.04486, over 1425347.88 frames.], batch size: 23, lr: 2.04e-04
2022-05-28 18:11:44,291 INFO [train.py:842] (3/4) Epoch 27, batch 5200, loss[loss=0.2256, simple_loss=0.3268, pruned_loss=0.06226, over 6290.00 frames.], tot_loss[loss=0.1793, simple_loss=0.267, pruned_loss=0.0458, over 1424775.52 frames.], batch size: 37, lr: 2.04e-04
2022-05-28 18:12:24,101 INFO [train.py:842] (3/4) Epoch 27, batch 5250, loss[loss=0.1627, simple_loss=0.2425, pruned_loss=0.04148, over 7158.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2676, pruned_loss=0.04658, over 1427529.16 frames.], batch size: 19, lr: 2.04e-04
2022-05-28 18:13:03,671 INFO [train.py:842] (3/4) Epoch 27, batch 5300, loss[loss=0.1607, simple_loss=0.2443, pruned_loss=0.03858, over 7073.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2673, pruned_loss=0.04664, over 1430523.20 frames.], batch size: 18, lr: 2.04e-04
2022-05-28 18:13:43,381 INFO [train.py:842] (3/4) Epoch 27, batch 5350, loss[loss=0.1619, simple_loss=0.2566, pruned_loss=0.03358, over 7110.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2677, pruned_loss=0.04647, over 1428509.67 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:14:22,789 INFO [train.py:842] (3/4) Epoch 27, batch 5400, loss[loss=0.1853, simple_loss=0.2761, pruned_loss=0.04721, over 7419.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2671, pruned_loss=0.04563, over 1429961.73 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:15:02,179 INFO [train.py:842] (3/4) Epoch 27, batch 5450, loss[loss=0.1627, simple_loss=0.2649, pruned_loss=0.03023, over 7062.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2672, pruned_loss=0.04572, over 1427564.17 frames.], batch size: 18, lr: 2.03e-04
2022-05-28 18:15:41,461 INFO [train.py:842] (3/4) Epoch 27, batch 5500, loss[loss=0.2147, simple_loss=0.3033, pruned_loss=0.06307, over 7184.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2667, pruned_loss=0.04524, over 1426596.63 frames.], batch size: 26, lr: 2.03e-04
2022-05-28 18:16:21,201 INFO [train.py:842] (3/4) Epoch 27, batch 5550, loss[loss=0.163, simple_loss=0.2626, pruned_loss=0.03166, over 7406.00 frames.], tot_loss[loss=0.1782, simple_loss=0.266, pruned_loss=0.04515, over 1425400.75 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:17:00,336 INFO [train.py:842] (3/4) Epoch 27, batch 5600, loss[loss=0.158, simple_loss=0.2384, pruned_loss=0.03877, over 7130.00 frames.], tot_loss[loss=0.177, simple_loss=0.2651, pruned_loss=0.04446, over 1425218.49 frames.], batch size: 17, lr: 2.03e-04
2022-05-28 18:17:39,894 INFO [train.py:842] (3/4) Epoch 27, batch 5650, loss[loss=0.1815, simple_loss=0.2713, pruned_loss=0.04581, over 7223.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2655, pruned_loss=0.04465, over 1425181.88 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:18:19,119 INFO [train.py:842] (3/4) Epoch 27, batch 5700, loss[loss=0.1936, simple_loss=0.2804, pruned_loss=0.05343, over 7415.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2656, pruned_loss=0.04484, over 1419695.84 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:18:58,798 INFO [train.py:842] (3/4) Epoch 27, batch 5750, loss[loss=0.1658, simple_loss=0.251, pruned_loss=0.0403, over 7428.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2664, pruned_loss=0.04515, over 1422252.07 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:19:38,107 INFO [train.py:842] (3/4) Epoch 27, batch 5800, loss[loss=0.1479, simple_loss=0.231, pruned_loss=0.03239, over 7002.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2667, pruned_loss=0.04517, over 1417308.90 frames.], batch size: 16, lr: 2.03e-04
2022-05-28 18:20:17,639 INFO [train.py:842] (3/4) Epoch 27, batch 5850, loss[loss=0.209, simple_loss=0.2854, pruned_loss=0.06627, over 7124.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2666, pruned_loss=0.04499, over 1418354.72 frames.], batch size: 26, lr: 2.03e-04
2022-05-28 18:20:57,003 INFO [train.py:842] (3/4) Epoch 27, batch 5900, loss[loss=0.1644, simple_loss=0.2539, pruned_loss=0.03742, over 7442.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2674, pruned_loss=0.04588, over 1423176.96 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:21:36,818 INFO [train.py:842] (3/4) Epoch 27, batch 5950, loss[loss=0.1814, simple_loss=0.2725, pruned_loss=0.0451, over 7229.00 frames.], tot_loss[loss=0.1782, simple_loss=0.266, pruned_loss=0.04522, over 1422063.32 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:22:15,977 INFO [train.py:842] (3/4) Epoch 27, batch 6000, loss[loss=0.1709, simple_loss=0.2656, pruned_loss=0.03813, over 7337.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2667, pruned_loss=0.04573, over 1420442.01 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:22:15,978 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 18:22:25,577 INFO [train.py:871] (3/4) Epoch 27, validation: loss=0.1638, simple_loss=0.2621, pruned_loss=0.03281, over 868885.00 frames.
2022-05-28 18:23:04,750 INFO [train.py:842] (3/4) Epoch 27, batch 6050, loss[loss=0.2045, simple_loss=0.277, pruned_loss=0.06604, over 7354.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2669, pruned_loss=0.04539, over 1415911.81 frames.], batch size: 19, lr: 2.03e-04
2022-05-28 18:23:44,250 INFO [train.py:842] (3/4) Epoch 27, batch 6100, loss[loss=0.196, simple_loss=0.2901, pruned_loss=0.05094, over 7106.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2656, pruned_loss=0.04475, over 1416366.87 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:24:23,888 INFO [train.py:842] (3/4) Epoch 27, batch 6150, loss[loss=0.1513, simple_loss=0.2444, pruned_loss=0.02915, over 7134.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2663, pruned_loss=0.04511, over 1422489.70 frames.], batch size: 17, lr: 2.03e-04
2022-05-28 18:25:03,255 INFO [train.py:842] (3/4) Epoch 27, batch 6200, loss[loss=0.1401, simple_loss=0.2314, pruned_loss=0.02446, over 7269.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2655, pruned_loss=0.04459, over 1425165.01 frames.], batch size: 18, lr: 2.03e-04
2022-05-28 18:25:42,830 INFO [train.py:842] (3/4) Epoch 27, batch 6250, loss[loss=0.176, simple_loss=0.2637, pruned_loss=0.0441, over 7336.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2651, pruned_loss=0.04415, over 1423673.80 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:26:22,137 INFO [train.py:842] (3/4) Epoch 27, batch 6300, loss[loss=0.1623, simple_loss=0.2632, pruned_loss=0.03065, over 7328.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2657, pruned_loss=0.04445, over 1420718.75 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:27:01,768 INFO [train.py:842] (3/4) Epoch 27, batch 6350, loss[loss=0.1579, simple_loss=0.2534, pruned_loss=0.03119, over 7312.00 frames.], tot_loss[loss=0.1781, simple_loss=0.266, pruned_loss=0.04506, over 1420779.68 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:27:40,938 INFO [train.py:842] (3/4) Epoch 27, batch 6400, loss[loss=0.1817, simple_loss=0.282, pruned_loss=0.04073, over 7343.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2642, pruned_loss=0.04411, over 1422034.19 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:28:20,548 INFO [train.py:842] (3/4) Epoch 27, batch 6450, loss[loss=0.2172, simple_loss=0.2968, pruned_loss=0.06875, over 7090.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2653, pruned_loss=0.04502, over 1417713.98 frames.], batch size: 28, lr: 2.03e-04
2022-05-28 18:28:59,834 INFO [train.py:842] (3/4) Epoch 27, batch 6500, loss[loss=0.2109, simple_loss=0.2994, pruned_loss=0.06119, over 7204.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2655, pruned_loss=0.04487, over 1421592.84 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:29:39,277 INFO [train.py:842] (3/4) Epoch 27, batch 6550, loss[loss=0.1914, simple_loss=0.2826, pruned_loss=0.05008, over 7218.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2653, pruned_loss=0.04447, over 1423484.24 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:30:18,670 INFO [train.py:842] (3/4) Epoch 27, batch 6600, loss[loss=0.1558, simple_loss=0.24, pruned_loss=0.0358, over 7428.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2654, pruned_loss=0.04486, over 1423987.76 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:30:58,080 INFO [train.py:842] (3/4) Epoch 27, batch 6650, loss[loss=0.21, simple_loss=0.2945, pruned_loss=0.06277, over 7173.00 frames.], tot_loss[loss=0.179, simple_loss=0.267, pruned_loss=0.0455, over 1422368.03 frames.], batch size: 26, lr: 2.03e-04
2022-05-28 18:31:37,225 INFO [train.py:842] (3/4) Epoch 27, batch 6700, loss[loss=0.1745, simple_loss=0.2656, pruned_loss=0.04172, over 7184.00 frames.], tot_loss[loss=0.18, simple_loss=0.2679, pruned_loss=0.04602, over 1424230.30 frames.], batch size: 26, lr: 2.03e-04
2022-05-28 18:32:16,889 INFO [train.py:842] (3/4) Epoch 27, batch 6750, loss[loss=0.1716, simple_loss=0.2538, pruned_loss=0.04472, over 6833.00 frames.], tot_loss[loss=0.179, simple_loss=0.267, pruned_loss=0.04545, over 1422318.14 frames.], batch size: 15, lr: 2.03e-04
2022-05-28 18:32:56,074 INFO [train.py:842] (3/4) Epoch 27, batch 6800, loss[loss=0.1682, simple_loss=0.2449, pruned_loss=0.04577, over 7269.00 frames.], tot_loss[loss=0.1796, simple_loss=0.268, pruned_loss=0.04563, over 1422933.99 frames.], batch size: 17, lr: 2.03e-04
2022-05-28 18:33:35,609 INFO [train.py:842] (3/4) Epoch 27, batch 6850, loss[loss=0.2308, simple_loss=0.3018, pruned_loss=0.0799, over 7164.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2679, pruned_loss=0.04614, over 1421595.15 frames.], batch size: 18, lr: 2.03e-04
2022-05-28 18:34:14,921 INFO [train.py:842] (3/4) Epoch 27, batch 6900, loss[loss=0.1885, simple_loss=0.2846, pruned_loss=0.04615, over 7156.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2672, pruned_loss=0.0456, over 1424524.05 frames.], batch size: 19, lr: 2.03e-04
2022-05-28 18:34:54,579 INFO [train.py:842] (3/4) Epoch 27, batch 6950, loss[loss=0.1875, simple_loss=0.269, pruned_loss=0.05297, over 6915.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2664, pruned_loss=0.04542, over 1425616.89 frames.], batch size: 31, lr: 2.03e-04
2022-05-28 18:35:33,888 INFO [train.py:842] (3/4) Epoch 27, batch 7000, loss[loss=0.142, simple_loss=0.2229, pruned_loss=0.03052, over 7418.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2662, pruned_loss=0.0456, over 1426947.24 frames.], batch size: 18, lr: 2.03e-04
2022-05-28 18:36:13,577 INFO [train.py:842] (3/4) Epoch 27, batch 7050, loss[loss=0.2007, simple_loss=0.2864, pruned_loss=0.05751, over 7320.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2675, pruned_loss=0.04579, over 1426996.28 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:36:52,888 INFO [train.py:842] (3/4) Epoch 27, batch 7100, loss[loss=0.1742, simple_loss=0.248, pruned_loss=0.05018, over 7263.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2669, pruned_loss=0.04545, over 1422422.72 frames.], batch size: 19, lr: 2.03e-04
2022-05-28 18:37:32,328 INFO [train.py:842] (3/4) Epoch 27, batch 7150, loss[loss=0.1859, simple_loss=0.2845, pruned_loss=0.04359, over 7309.00 frames.], tot_loss[loss=0.18, simple_loss=0.2678, pruned_loss=0.04604, over 1418101.53 frames.], batch size: 24, lr: 2.03e-04
2022-05-28 18:38:11,641 INFO [train.py:842] (3/4) Epoch 27, batch 7200, loss[loss=0.1652, simple_loss=0.2529, pruned_loss=0.03878, over 7271.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2679, pruned_loss=0.04568, over 1421213.62 frames.], batch size: 17, lr: 2.03e-04
2022-05-28 18:38:51,145 INFO [train.py:842] (3/4) Epoch 27, batch 7250, loss[loss=0.1351, simple_loss=0.2176, pruned_loss=0.02631, over 7416.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2679, pruned_loss=0.04534, over 1422582.71 frames.], batch size: 18, lr: 2.03e-04
2022-05-28 18:39:30,099 INFO [train.py:842] (3/4) Epoch 27, batch 7300, loss[loss=0.1586, simple_loss=0.2581, pruned_loss=0.02957, over 7408.00 frames.], tot_loss[loss=0.1783, simple_loss=0.267, pruned_loss=0.04483, over 1424524.05 frames.], batch size: 21, lr: 2.03e-04
2022-05-28 18:40:09,841 INFO [train.py:842] (3/4) Epoch 27, batch 7350, loss[loss=0.134, simple_loss=0.2316, pruned_loss=0.01821, over 7152.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2656, pruned_loss=0.04428, over 1426241.25 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:40:49,112 INFO [train.py:842] (3/4) Epoch 27, batch 7400, loss[loss=0.1977, simple_loss=0.2819, pruned_loss=0.05674, over 7212.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2653, pruned_loss=0.04427, over 1423467.32 frames.], batch size: 23, lr: 2.03e-04
2022-05-28 18:41:28,896 INFO [train.py:842] (3/4) Epoch 27, batch 7450, loss[loss=0.1556, simple_loss=0.2372, pruned_loss=0.03698, over 7289.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2654, pruned_loss=0.04447, over 1427634.05 frames.], batch size: 17, lr: 2.03e-04
2022-05-28 18:42:08,192 INFO [train.py:842] (3/4) Epoch 27, batch 7500, loss[loss=0.2356, simple_loss=0.3202, pruned_loss=0.07553, over 4754.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2668, pruned_loss=0.04498, over 1424350.65 frames.], batch size: 52, lr: 2.03e-04
2022-05-28 18:42:47,793 INFO [train.py:842] (3/4) Epoch 27, batch 7550, loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02868, over 7328.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2656, pruned_loss=0.04465, over 1426017.45 frames.], batch size: 20, lr: 2.03e-04
2022-05-28 18:43:27,149 INFO [train.py:842] (3/4) Epoch 27, batch 7600, loss[loss=0.1948, simple_loss=0.2937, pruned_loss=0.04793, over 7331.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04403, over 1428122.34 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:44:07,170 INFO [train.py:842] (3/4) Epoch 27, batch 7650, loss[loss=0.2137, simple_loss=0.3037, pruned_loss=0.06187, over 7272.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2636, pruned_loss=0.04358, over 1432494.33 frames.], batch size: 24, lr: 2.03e-04
2022-05-28 18:44:46,365 INFO [train.py:842] (3/4) Epoch 27, batch 7700, loss[loss=0.1728, simple_loss=0.2581, pruned_loss=0.04373, over 7212.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2632, pruned_loss=0.04361, over 1426837.89 frames.], batch size: 22, lr: 2.03e-04
2022-05-28 18:45:26,188 INFO [train.py:842] (3/4) Epoch 27, batch 7750, loss[loss=0.175, simple_loss=0.2656, pruned_loss=0.0422, over 7209.00 frames.], tot_loss[loss=0.1751, simple_loss=0.263, pruned_loss=0.04361, over 1427021.34 frames.], batch size: 22, lr: 2.02e-04
2022-05-28 18:46:05,420 INFO [train.py:842] (3/4) Epoch 27, batch 7800, loss[loss=0.1669, simple_loss=0.2529, pruned_loss=0.04041, over 7278.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2629, pruned_loss=0.04348, over 1429393.09 frames.], batch size: 25, lr: 2.02e-04
2022-05-28 18:46:45,078 INFO [train.py:842] (3/4) Epoch 27, batch 7850, loss[loss=0.1434, simple_loss=0.2268, pruned_loss=0.03003, over 6803.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2626, pruned_loss=0.04357, over 1428728.89 frames.], batch size: 15, lr: 2.02e-04
2022-05-28 18:47:24,275 INFO [train.py:842] (3/4) Epoch 27, batch 7900, loss[loss=0.1631, simple_loss=0.2574, pruned_loss=0.03433, over 7323.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2635, pruned_loss=0.04381, over 1427034.76 frames.], batch size: 21, lr: 2.02e-04
2022-05-28 18:48:03,882 INFO [train.py:842] (3/4) Epoch 27, batch 7950, loss[loss=0.1662, simple_loss=0.2443, pruned_loss=0.04403, over 7265.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2643, pruned_loss=0.04421, over 1424757.80 frames.], batch size: 17, lr: 2.02e-04
2022-05-28 18:48:42,918 INFO [train.py:842] (3/4) Epoch 27, batch 8000, loss[loss=0.1906, simple_loss=0.2708, pruned_loss=0.05524, over 7141.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2646, pruned_loss=0.04446, over 1417658.80 frames.], batch size: 17, lr: 2.02e-04
2022-05-28 18:49:22,389 INFO [train.py:842] (3/4) Epoch 27, batch 8050, loss[loss=0.1696, simple_loss=0.267, pruned_loss=0.03611, over 7158.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2645, pruned_loss=0.04447, over 1417382.09 frames.], batch size: 26, lr: 2.02e-04
2022-05-28 18:50:01,722 INFO [train.py:842] (3/4) Epoch 27, batch 8100, loss[loss=0.1594, simple_loss=0.2496, pruned_loss=0.03458, over 7225.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2641, pruned_loss=0.04442, over 1419902.01 frames.], batch size: 20, lr: 2.02e-04
2022-05-28 18:50:41,131 INFO [train.py:842] (3/4) Epoch 27, batch 8150, loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03362, over 7338.00 frames.], tot_loss[loss=0.1776, simple_loss=0.265, pruned_loss=0.04512, over 1417909.64 frames.], batch size: 19, lr: 2.02e-04
2022-05-28 18:51:20,453 INFO [train.py:842] (3/4) Epoch 27, batch 8200, loss[loss=0.182, simple_loss=0.2657, pruned_loss=0.04916, over 6795.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2649, pruned_loss=0.04483, over 1421565.40 frames.], batch size: 15, lr: 2.02e-04
2022-05-28 18:51:59,975 INFO [train.py:842] (3/4) Epoch 27, batch 8250, loss[loss=0.1615, simple_loss=0.2534, pruned_loss=0.03482, over 6629.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2645, pruned_loss=0.04434, over 1418476.23 frames.], batch size: 31, lr: 2.02e-04
2022-05-28 18:52:39,243 INFO [train.py:842] (3/4) Epoch 27, batch 8300, loss[loss=0.1926, simple_loss=0.2856, pruned_loss=0.0498, over 7126.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2649, pruned_loss=0.04446, over 1421950.43 frames.], batch size: 21, lr: 2.02e-04
2022-05-28 18:53:18,911 INFO [train.py:842] (3/4) Epoch 27, batch 8350, loss[loss=0.1555, simple_loss=0.2509, pruned_loss=0.03007, over 7141.00 frames.], tot_loss[loss=0.177, simple_loss=0.2649, pruned_loss=0.04448, over 1420752.28 frames.], batch size: 17, lr: 2.02e-04
2022-05-28 18:53:58,063 INFO [train.py:842] (3/4) Epoch 27, batch 8400, loss[loss=0.1648, simple_loss=0.2544, pruned_loss=0.03765, over 7406.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2657, pruned_loss=0.04412, over 1423864.01 frames.], batch size: 21, lr: 2.02e-04
2022-05-28 18:54:37,708 INFO [train.py:842] (3/4) Epoch 27, batch 8450, loss[loss=0.158, simple_loss=0.2424, pruned_loss=0.0368, over 7162.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2663, pruned_loss=0.04447, over 1423605.38 frames.], batch size: 18, lr: 2.02e-04
2022-05-28 18:55:16,694 INFO [train.py:842] (3/4) Epoch 27, batch 8500, loss[loss=0.1951, simple_loss=0.2772, pruned_loss=0.05645, over 7203.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2665, pruned_loss=0.04485, over 1425633.58 frames.], batch size: 22, lr: 2.02e-04
2022-05-28 18:55:56,078 INFO [train.py:842] (3/4) Epoch 27, batch 8550, loss[loss=0.2005, simple_loss=0.2879, pruned_loss=0.05652, over 6675.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2673, pruned_loss=0.0452, over 1423850.99 frames.], batch size: 31, lr: 2.02e-04
2022-05-28 18:56:35,120 INFO [train.py:842] (3/4) Epoch 27, batch 8600, loss[loss=0.1781, simple_loss=0.2832, pruned_loss=0.03653, over 7104.00 frames.], tot_loss[loss=0.1786, simple_loss=0.267, pruned_loss=0.04509, over 1421954.11 frames.], batch size: 21, lr: 2.02e-04
2022-05-28 18:57:14,403 INFO [train.py:842] (3/4) Epoch 27, batch 8650, loss[loss=0.1695, simple_loss=0.268, pruned_loss=0.03553, over 7213.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2672, pruned_loss=0.04506, over 1417265.01 frames.], batch size: 21, lr: 2.02e-04
2022-05-28 18:57:53,608 INFO [train.py:842] (3/4) Epoch 27, batch 8700, loss[loss=0.2093, simple_loss=0.293, pruned_loss=0.06279, over 7207.00 frames.], tot_loss[loss=0.1784, simple_loss=0.267, pruned_loss=0.04485, over 1418655.06 frames.], batch size: 22, lr: 2.02e-04
2022-05-28 18:58:33,176 INFO [train.py:842] (3/4) Epoch 27, batch 8750, loss[loss=0.162, simple_loss=0.2425, pruned_loss=0.04079, over 7208.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2673, pruned_loss=0.04545, over 1414839.78 frames.], batch size: 22, lr: 2.02e-04
2022-05-28 18:59:12,360 INFO [train.py:842] (3/4) Epoch 27, batch 8800, loss[loss=0.1401, simple_loss=0.2185, pruned_loss=0.03081, over 7216.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2677, pruned_loss=0.04548, over 1411531.28 frames.], batch size: 16, lr: 2.02e-04
2022-05-28 18:59:51,577 INFO [train.py:842] (3/4) Epoch 27, batch 8850, loss[loss=0.1336, simple_loss=0.2272, pruned_loss=0.01995, over 7070.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2663, pruned_loss=0.0446, over 1414648.36 frames.], batch size: 18, lr: 2.02e-04
2022-05-28 19:00:30,277 INFO [train.py:842] (3/4) Epoch 27, batch 8900, loss[loss=0.1921, simple_loss=0.288, pruned_loss=0.04807, over 7205.00 frames.], tot_loss[loss=0.178, simple_loss=0.2665, pruned_loss=0.04474, over 1408690.97 frames.], batch size: 22, lr: 2.02e-04
2022-05-28 19:01:09,130 INFO [train.py:842] (3/4) Epoch 27, batch 8950, loss[loss=0.1585, simple_loss=0.2433, pruned_loss=0.03679, over 7001.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2676, pruned_loss=0.04514, over 1405539.21 frames.], batch size: 16, lr: 2.02e-04
2022-05-28 19:01:47,933 INFO [train.py:842] (3/4) Epoch 27, batch 9000, loss[loss=0.1785, simple_loss=0.267, pruned_loss=0.04501, over 7168.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2675, pruned_loss=0.04547, over 1397717.45 frames.], batch size: 28, lr: 2.02e-04
2022-05-28 19:01:47,934 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 19:01:58,049 INFO [train.py:871] (3/4) Epoch 27, validation: loss=0.1653, simple_loss=0.2632, pruned_loss=0.03366, over 868885.00 frames.
2022-05-28 19:02:39,580 INFO [train.py:842] (3/4) Epoch 27, batch 9050, loss[loss=0.1997, simple_loss=0.2834, pruned_loss=0.05802, over 6374.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2695, pruned_loss=0.04647, over 1372336.57 frames.], batch size: 37, lr: 2.02e-04
2022-05-28 19:03:17,103 INFO [train.py:842] (3/4) Epoch 27, batch 9100, loss[loss=0.1697, simple_loss=0.2616, pruned_loss=0.03887, over 6802.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2715, pruned_loss=0.04738, over 1334284.00 frames.], batch size: 31, lr: 2.02e-04
2022-05-28 19:03:55,314 INFO [train.py:842] (3/4) Epoch 27, batch 9150, loss[loss=0.197, simple_loss=0.2816, pruned_loss=0.05626, over 5037.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2751, pruned_loss=0.05051, over 1267936.31 frames.], batch size: 52, lr: 2.02e-04
2022-05-28 19:04:48,255 INFO [train.py:842] (3/4) Epoch 28, batch 0, loss[loss=0.1722, simple_loss=0.2596, pruned_loss=0.04239, over 7263.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2596, pruned_loss=0.04239, over 7263.00 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:05:27,965 INFO [train.py:842] (3/4) Epoch 28, batch 50, loss[loss=0.1707, simple_loss=0.2628, pruned_loss=0.03934, over 7270.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2678, pruned_loss=0.04552, over 321361.38 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:06:07,158 INFO [train.py:842] (3/4) Epoch 28, batch 100, loss[loss=0.1667, simple_loss=0.2574, pruned_loss=0.03804, over 7139.00 frames.], tot_loss[loss=0.177, simple_loss=0.2654, pruned_loss=0.04434, over 564769.02 frames.], batch size: 20, lr: 1.98e-04
2022-05-28 19:06:46,670 INFO [train.py:842] (3/4) Epoch 28, batch 150, loss[loss=0.1751, simple_loss=0.2782, pruned_loss=0.03593, over 6463.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2652, pruned_loss=0.04394, over 753995.77 frames.], batch size: 37, lr: 1.98e-04
2022-05-28 19:07:25,775 INFO [train.py:842] (3/4) Epoch 28, batch 200, loss[loss=0.2309, simple_loss=0.3145, pruned_loss=0.07361, over 7203.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2658, pruned_loss=0.04419, over 900807.93 frames.], batch size: 23, lr: 1.98e-04
2022-05-28 19:08:05,230 INFO [train.py:842] (3/4) Epoch 28, batch 250, loss[loss=0.1887, simple_loss=0.2746, pruned_loss=0.05142, over 7296.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2661, pruned_loss=0.04462, over 1017334.58 frames.], batch size: 24, lr: 1.98e-04
2022-05-28 19:08:44,442 INFO [train.py:842] (3/4) Epoch 28, batch 300, loss[loss=0.1743, simple_loss=0.2659, pruned_loss=0.04134, over 6747.00 frames.], tot_loss[loss=0.178, simple_loss=0.2667, pruned_loss=0.04464, over 1107491.71 frames.], batch size: 31, lr: 1.98e-04
2022-05-28 19:09:23,905 INFO [train.py:842] (3/4) Epoch 28, batch 350, loss[loss=0.1854, simple_loss=0.2732, pruned_loss=0.04884, over 7158.00 frames.], tot_loss[loss=0.178, simple_loss=0.2666, pruned_loss=0.04472, over 1179086.96 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:10:03,153 INFO [train.py:842] (3/4) Epoch 28, batch 400, loss[loss=0.1595, simple_loss=0.2443, pruned_loss=0.03733, over 7128.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2661, pruned_loss=0.0447, over 1234626.12 frames.], batch size: 17, lr: 1.98e-04
2022-05-28 19:10:42,627 INFO [train.py:842] (3/4) Epoch 28, batch 450, loss[loss=0.1931, simple_loss=0.2832, pruned_loss=0.05149, over 7309.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2664, pruned_loss=0.04535, over 1271804.51 frames.], batch size: 25, lr: 1.98e-04
2022-05-28 19:11:21,988 INFO [train.py:842] (3/4) Epoch 28, batch 500, loss[loss=0.1825, simple_loss=0.2806, pruned_loss=0.0422, over 7315.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2664, pruned_loss=0.04474, over 1308723.74 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:12:01,652 INFO [train.py:842] (3/4) Epoch 28, batch 550, loss[loss=0.1942, simple_loss=0.2734, pruned_loss=0.05749, over 7065.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2658, pruned_loss=0.0445, over 1331267.79 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:12:41,043 INFO [train.py:842] (3/4) Epoch 28, batch 600, loss[loss=0.1723, simple_loss=0.2593, pruned_loss=0.04264, over 7328.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04501, over 1349712.98 frames.], batch size: 20, lr: 1.98e-04
2022-05-28 19:13:20,409 INFO [train.py:842] (3/4) Epoch 28, batch 650, loss[loss=0.1868, simple_loss=0.2728, pruned_loss=0.05035, over 6995.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2653, pruned_loss=0.04462, over 1366608.64 frames.], batch size: 28, lr: 1.98e-04
2022-05-28 19:13:59,771 INFO [train.py:842] (3/4) Epoch 28, batch 700, loss[loss=0.1683, simple_loss=0.2506, pruned_loss=0.04294, over 7070.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2636, pruned_loss=0.04386, over 1380373.83 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:14:39,584 INFO [train.py:842] (3/4) Epoch 28, batch 750, loss[loss=0.1813, simple_loss=0.2717, pruned_loss=0.04542, over 7218.00 frames.], tot_loss[loss=0.1751, simple_loss=0.263, pruned_loss=0.0436, over 1391339.39 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:15:18,800 INFO [train.py:842] (3/4) Epoch 28, batch 800, loss[loss=0.1593, simple_loss=0.2571, pruned_loss=0.03073, over 7088.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2634, pruned_loss=0.04344, over 1397710.15 frames.], batch size: 28, lr: 1.98e-04
2022-05-28 19:15:58,579 INFO [train.py:842] (3/4) Epoch 28, batch 850, loss[loss=0.2152, simple_loss=0.3018, pruned_loss=0.06435, over 7315.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2632, pruned_loss=0.04327, over 1405577.78 frames.], batch size: 25, lr: 1.98e-04
2022-05-28 19:16:37,620 INFO [train.py:842] (3/4) Epoch 28, batch 900, loss[loss=0.1964, simple_loss=0.2781, pruned_loss=0.05734, over 6990.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04376, over 1407593.75 frames.], batch size: 16, lr: 1.98e-04
2022-05-28 19:17:17,021 INFO [train.py:842] (3/4) Epoch 28, batch 950, loss[loss=0.1252, simple_loss=0.2171, pruned_loss=0.01662, over 7157.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04389, over 1409399.03 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:17:56,538 INFO [train.py:842] (3/4) Epoch 28, batch 1000, loss[loss=0.1636, simple_loss=0.2573, pruned_loss=0.03501, over 7436.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2652, pruned_loss=0.04391, over 1415828.45 frames.], batch size: 20, lr: 1.98e-04
2022-05-28 19:18:36,068 INFO [train.py:842] (3/4) Epoch 28, batch 1050, loss[loss=0.2119, simple_loss=0.2969, pruned_loss=0.06346, over 7415.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2662, pruned_loss=0.04471, over 1416052.57 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:19:15,240 INFO [train.py:842] (3/4) Epoch 28, batch 1100, loss[loss=0.1895, simple_loss=0.2698, pruned_loss=0.05463, over 7070.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2662, pruned_loss=0.0448, over 1416180.19 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:19:55,033 INFO [train.py:842] (3/4) Epoch 28, batch 1150, loss[loss=0.212, simple_loss=0.3038, pruned_loss=0.06007, over 7204.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2657, pruned_loss=0.04485, over 1421558.04 frames.], batch size: 23, lr: 1.98e-04
2022-05-28 19:20:34,397 INFO [train.py:842] (3/4) Epoch 28, batch 1200, loss[loss=0.1604, simple_loss=0.2456, pruned_loss=0.03763, over 7131.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2654, pruned_loss=0.04457, over 1425597.61 frames.], batch size: 17, lr: 1.98e-04
2022-05-28 19:21:13,760 INFO [train.py:842] (3/4) Epoch 28, batch 1250, loss[loss=0.1439, simple_loss=0.228, pruned_loss=0.02993, over 7126.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2656, pruned_loss=0.04489, over 1422114.56 frames.], batch size: 17, lr: 1.98e-04
2022-05-28 19:21:53,008 INFO [train.py:842] (3/4) Epoch 28, batch 1300, loss[loss=0.148, simple_loss=0.2352, pruned_loss=0.0304, over 7294.00 frames.], tot_loss[loss=0.179, simple_loss=0.2668, pruned_loss=0.04564, over 1418354.31 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:22:32,612 INFO [train.py:842] (3/4) Epoch 28, batch 1350, loss[loss=0.1595, simple_loss=0.2611, pruned_loss=0.02899, over 7353.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2664, pruned_loss=0.04523, over 1418875.82 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:23:11,781 INFO [train.py:842] (3/4) Epoch 28, batch 1400, loss[loss=0.2019, simple_loss=0.2917, pruned_loss=0.05606, over 7070.00 frames.], tot_loss[loss=0.1787, simple_loss=0.267, pruned_loss=0.04519, over 1418406.03 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:23:51,615 INFO [train.py:842] (3/4) Epoch 28, batch 1450, loss[loss=0.1711, simple_loss=0.2652, pruned_loss=0.03851, over 7324.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2661, pruned_loss=0.04475, over 1421004.08 frames.], batch size: 20, lr: 1.98e-04
2022-05-28 19:24:30,657 INFO [train.py:842] (3/4) Epoch 28, batch 1500, loss[loss=0.1722, simple_loss=0.2631, pruned_loss=0.04067, over 7108.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2668, pruned_loss=0.04501, over 1422705.31 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:25:10,190 INFO [train.py:842] (3/4) Epoch 28, batch 1550, loss[loss=0.1638, simple_loss=0.2403, pruned_loss=0.04363, over 6815.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2668, pruned_loss=0.04484, over 1419852.84 frames.], batch size: 15, lr: 1.98e-04
2022-05-28 19:25:49,460 INFO [train.py:842] (3/4) Epoch 28, batch 1600, loss[loss=0.1683, simple_loss=0.2677, pruned_loss=0.03441, over 7418.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2668, pruned_loss=0.04481, over 1424418.62 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:26:29,072 INFO [train.py:842] (3/4) Epoch 28, batch 1650, loss[loss=0.1796, simple_loss=0.2651, pruned_loss=0.04703, over 7066.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2656, pruned_loss=0.04409, over 1424758.23 frames.], batch size: 18, lr: 1.98e-04
2022-05-28 19:27:08,140 INFO [train.py:842] (3/4) Epoch 28, batch 1700, loss[loss=0.1652, simple_loss=0.2503, pruned_loss=0.04003, over 7359.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2663, pruned_loss=0.04438, over 1426514.87 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:27:48,087 INFO [train.py:842] (3/4) Epoch 28, batch 1750, loss[loss=0.1674, simple_loss=0.2591, pruned_loss=0.03791, over 6716.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2648, pruned_loss=0.04376, over 1428824.37 frames.], batch size: 31, lr: 1.98e-04
2022-05-28 19:28:27,165 INFO [train.py:842] (3/4) Epoch 28, batch 1800, loss[loss=0.1751, simple_loss=0.2765, pruned_loss=0.03685, over 7233.00 frames.], tot_loss[loss=0.176, simple_loss=0.2646, pruned_loss=0.04372, over 1428649.31 frames.], batch size: 20, lr: 1.98e-04
2022-05-28 19:29:06,925 INFO [train.py:842] (3/4) Epoch 28, batch 1850, loss[loss=0.1544, simple_loss=0.2407, pruned_loss=0.03401, over 7149.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2644, pruned_loss=0.0434, over 1431149.18 frames.], batch size: 19, lr: 1.98e-04
2022-05-28 19:29:46,151 INFO [train.py:842] (3/4) Epoch 28, batch 1900, loss[loss=0.162, simple_loss=0.2442, pruned_loss=0.03991, over 7280.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2653, pruned_loss=0.04362, over 1430704.19 frames.], batch size: 17, lr: 1.98e-04
2022-05-28 19:30:25,831 INFO [train.py:842] (3/4) Epoch 28, batch 1950, loss[loss=0.1965, simple_loss=0.2864, pruned_loss=0.05323, over 6112.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2665, pruned_loss=0.04499, over 1425094.98 frames.], batch size: 37, lr: 1.98e-04
2022-05-28 19:31:05,145 INFO [train.py:842] (3/4) Epoch 28, batch 2000, loss[loss=0.1815, simple_loss=0.2814, pruned_loss=0.0408, over 7232.00 frames.], tot_loss[loss=0.1789, simple_loss=0.267, pruned_loss=0.04538, over 1424348.46 frames.], batch size: 21, lr: 1.98e-04
2022-05-28 19:31:44,625 INFO [train.py:842] (3/4) Epoch 28, batch 2050, loss[loss=0.1948, simple_loss=0.2675, pruned_loss=0.06108, over 7202.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2682, pruned_loss=0.04675, over 1422630.37 frames.], batch size: 23, lr: 1.97e-04
2022-05-28 19:32:34,480 INFO [train.py:842] (3/4) Epoch 28, batch 2100, loss[loss=0.2325, simple_loss=0.3069, pruned_loss=0.07906, over 7279.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2669, pruned_loss=0.04632, over 1421895.18 frames.], batch size: 25, lr: 1.97e-04
2022-05-28 19:33:13,876 INFO [train.py:842] (3/4) Epoch 28, batch 2150, loss[loss=0.1795, simple_loss=0.2651, pruned_loss=0.04693, over 7150.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2666, pruned_loss=0.04584, over 1421283.56 frames.], batch size: 17, lr: 1.97e-04
2022-05-28 19:33:53,210 INFO [train.py:842] (3/4) Epoch 28, batch 2200, loss[loss=0.1868, simple_loss=0.2814, pruned_loss=0.04606, over 7295.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2661, pruned_loss=0.04563, over 1420883.24 frames.], batch size: 24, lr: 1.97e-04
2022-05-28 19:34:32,650 INFO [train.py:842] (3/4) Epoch 28, batch 2250, loss[loss=0.1996, simple_loss=0.2855, pruned_loss=0.05686, over 7338.00 frames.], tot_loss[loss=0.179, simple_loss=0.2664, pruned_loss=0.04582, over 1424090.00 frames.], batch size: 22, lr: 1.97e-04
2022-05-28 19:35:11,852 INFO [train.py:842] (3/4) Epoch 28, batch 2300, loss[loss=0.1757, simple_loss=0.2623, pruned_loss=0.04453, over 7154.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2667, pruned_loss=0.04573, over 1421521.08 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:35:51,210 INFO [train.py:842] (3/4) Epoch 28, batch 2350, loss[loss=0.1598, simple_loss=0.2443, pruned_loss=0.03766, over 7153.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2669, pruned_loss=0.04563, over 1419541.88 frames.], batch size: 19, lr: 1.97e-04
2022-05-28 19:36:30,502 INFO [train.py:842] (3/4) Epoch 28, batch 2400, loss[loss=0.1739, simple_loss=0.261, pruned_loss=0.04342, over 7196.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2672, pruned_loss=0.04559, over 1422494.99 frames.], batch size: 23, lr: 1.97e-04
2022-05-28 19:37:10,210 INFO [train.py:842] (3/4) Epoch 28, batch 2450, loss[loss=0.1664, simple_loss=0.2493, pruned_loss=0.04179, over 6272.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2661, pruned_loss=0.04513, over 1423314.66 frames.], batch size: 37, lr: 1.97e-04
2022-05-28 19:37:49,529 INFO [train.py:842] (3/4) Epoch 28, batch 2500, loss[loss=0.1587, simple_loss=0.2443, pruned_loss=0.03651, over 7222.00 frames.], tot_loss[loss=0.178, simple_loss=0.2658, pruned_loss=0.04507, over 1420936.17 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 19:38:29,253 INFO [train.py:842] (3/4) Epoch 28, batch 2550, loss[loss=0.1794, simple_loss=0.2674, pruned_loss=0.04573, over 7266.00 frames.], tot_loss[loss=0.179, simple_loss=0.2667, pruned_loss=0.04566, over 1422043.64 frames.], batch size: 19, lr: 1.97e-04
2022-05-28 19:39:08,391 INFO [train.py:842] (3/4) Epoch 28, batch 2600, loss[loss=0.1632, simple_loss=0.2509, pruned_loss=0.03772, over 7231.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2664, pruned_loss=0.04544, over 1421941.60 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:39:48,062 INFO [train.py:842] (3/4) Epoch 28, batch 2650, loss[loss=0.1228, simple_loss=0.2093, pruned_loss=0.01809, over 7014.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2659, pruned_loss=0.04485, over 1419834.54 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 19:40:27,363 INFO [train.py:842] (3/4) Epoch 28, batch 2700, loss[loss=0.1747, simple_loss=0.2708, pruned_loss=0.03929, over 7329.00 frames.], tot_loss[loss=0.178, simple_loss=0.2662, pruned_loss=0.04492, over 1421941.41 frames.], batch size: 21, lr: 1.97e-04
2022-05-28 19:41:06,911 INFO [train.py:842] (3/4) Epoch 28, batch 2750, loss[loss=0.1669, simple_loss=0.2517, pruned_loss=0.0411, over 7252.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04493, over 1419993.89 frames.], batch size: 19, lr: 1.97e-04
2022-05-28 19:41:45,950 INFO [train.py:842] (3/4) Epoch 28, batch 2800, loss[loss=0.1786, simple_loss=0.2687, pruned_loss=0.04421, over 7248.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2645, pruned_loss=0.04415, over 1416073.32 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:42:25,474 INFO [train.py:842] (3/4) Epoch 28, batch 2850, loss[loss=0.1369, simple_loss=0.2227, pruned_loss=0.0256, over 7129.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2643, pruned_loss=0.04402, over 1419870.34 frames.], batch size: 17, lr: 1.97e-04
2022-05-28 19:43:04,597 INFO [train.py:842] (3/4) Epoch 28, batch 2900, loss[loss=0.1823, simple_loss=0.2694, pruned_loss=0.04759, over 7290.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2656, pruned_loss=0.04436, over 1418819.72 frames.], batch size: 25, lr: 1.97e-04
2022-05-28 19:43:43,946 INFO [train.py:842] (3/4) Epoch 28, batch 2950, loss[loss=0.1569, simple_loss=0.2545, pruned_loss=0.02971, over 7190.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2656, pruned_loss=0.0446, over 1421984.51 frames.], batch size: 23, lr: 1.97e-04
2022-05-28 19:44:22,910 INFO [train.py:842] (3/4) Epoch 28, batch 3000, loss[loss=0.2084, simple_loss=0.2924, pruned_loss=0.06219, over 6987.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2654, pruned_loss=0.04437, over 1424184.57 frames.], batch size: 28, lr: 1.97e-04
2022-05-28 19:44:22,911 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 19:44:32,547 INFO [train.py:871] (3/4) Epoch 28, validation: loss=0.165, simple_loss=0.263, pruned_loss=0.03349, over 868885.00 frames.
2022-05-28 19:45:12,191 INFO [train.py:842] (3/4) Epoch 28, batch 3050, loss[loss=0.1478, simple_loss=0.2237, pruned_loss=0.03598, over 7143.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04408, over 1425836.94 frames.], batch size: 17, lr: 1.97e-04
2022-05-28 19:45:51,483 INFO [train.py:842] (3/4) Epoch 28, batch 3100, loss[loss=0.2245, simple_loss=0.315, pruned_loss=0.06694, over 7377.00 frames.], tot_loss[loss=0.1774, simple_loss=0.265, pruned_loss=0.04489, over 1425108.78 frames.], batch size: 23, lr: 1.97e-04
2022-05-28 19:46:31,148 INFO [train.py:842] (3/4) Epoch 28, batch 3150, loss[loss=0.1536, simple_loss=0.2354, pruned_loss=0.03592, over 7403.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04452, over 1423750.56 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 19:47:10,214 INFO [train.py:842] (3/4) Epoch 28, batch 3200, loss[loss=0.1974, simple_loss=0.2915, pruned_loss=0.0516, over 7306.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2649, pruned_loss=0.04471, over 1424194.07 frames.], batch size: 21, lr: 1.97e-04
2022-05-28 19:47:50,137 INFO [train.py:842] (3/4) Epoch 28, batch 3250, loss[loss=0.128, simple_loss=0.2155, pruned_loss=0.02021, over 7164.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2644, pruned_loss=0.0447, over 1423112.97 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 19:48:29,261 INFO [train.py:842] (3/4) Epoch 28, batch 3300, loss[loss=0.1325, simple_loss=0.2236, pruned_loss=0.02072, over 6989.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2654, pruned_loss=0.04513, over 1422581.56 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 19:49:08,809 INFO [train.py:842] (3/4) Epoch 28, batch 3350, loss[loss=0.18, simple_loss=0.2769, pruned_loss=0.04151, over 7369.00 frames.], tot_loss[loss=0.1775, simple_loss=0.265, pruned_loss=0.04497, over 1419967.09 frames.], batch size: 23, lr: 1.97e-04
2022-05-28 19:49:48,157 INFO [train.py:842] (3/4) Epoch 28, batch 3400, loss[loss=0.1698, simple_loss=0.2607, pruned_loss=0.03943, over 7319.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2652, pruned_loss=0.04509, over 1421837.22 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:50:27,855 INFO [train.py:842] (3/4) Epoch 28, batch 3450, loss[loss=0.2271, simple_loss=0.3073, pruned_loss=0.07341, over 7222.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2659, pruned_loss=0.04554, over 1423149.15 frames.], batch size: 22, lr: 1.97e-04
2022-05-28 19:51:07,239 INFO [train.py:842] (3/4) Epoch 28, batch 3500, loss[loss=0.172, simple_loss=0.2523, pruned_loss=0.04587, over 7059.00 frames.], tot_loss[loss=0.179, simple_loss=0.2663, pruned_loss=0.04588, over 1422541.30 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 19:51:46,803 INFO [train.py:842] (3/4) Epoch 28, batch 3550, loss[loss=0.1742, simple_loss=0.2734, pruned_loss=0.03745, over 7330.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2662, pruned_loss=0.04527, over 1423251.38 frames.], batch size: 22, lr: 1.97e-04
2022-05-28 19:52:25,755 INFO [train.py:842] (3/4) Epoch 28, batch 3600, loss[loss=0.1921, simple_loss=0.27, pruned_loss=0.05715, over 7076.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2666, pruned_loss=0.0448, over 1422680.06 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 19:53:05,428 INFO [train.py:842] (3/4) Epoch 28, batch 3650, loss[loss=0.1783, simple_loss=0.2543, pruned_loss=0.05112, over 7147.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2649, pruned_loss=0.04425, over 1422757.44 frames.], batch size: 17, lr: 1.97e-04
2022-05-28 19:53:44,359 INFO [train.py:842] (3/4) Epoch 28, batch 3700, loss[loss=0.1474, simple_loss=0.237, pruned_loss=0.02886, over 7431.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2653, pruned_loss=0.04483, over 1422783.68 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:54:23,832 INFO [train.py:842] (3/4) Epoch 28, batch 3750, loss[loss=0.1585, simple_loss=0.2465, pruned_loss=0.0353, over 7337.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2648, pruned_loss=0.04433, over 1422995.90 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:55:02,967 INFO [train.py:842] (3/4) Epoch 28, batch 3800, loss[loss=0.176, simple_loss=0.2681, pruned_loss=0.04198, over 7204.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2664, pruned_loss=0.04513, over 1422190.03 frames.], batch size: 22, lr: 1.97e-04
2022-05-28 19:55:42,646 INFO [train.py:842] (3/4) Epoch 28, batch 3850, loss[loss=0.1935, simple_loss=0.2967, pruned_loss=0.04515, over 7153.00 frames.], tot_loss[loss=0.177, simple_loss=0.2656, pruned_loss=0.0442, over 1427426.04 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 19:56:21,930 INFO [train.py:842] (3/4) Epoch 28, batch 3900, loss[loss=0.1537, simple_loss=0.2418, pruned_loss=0.03279, over 7007.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04395, over 1427366.81 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 19:57:01,263 INFO [train.py:842] (3/4) Epoch 28, batch 3950, loss[loss=0.1607, simple_loss=0.2354, pruned_loss=0.04304, over 7005.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2658, pruned_loss=0.04439, over 1426879.48 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 19:57:40,588 INFO [train.py:842] (3/4) Epoch 28, batch 4000, loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03298, over 7327.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2665, pruned_loss=0.0447, over 1428091.18 frames.], batch size: 21, lr: 1.97e-04
2022-05-28 19:58:20,471 INFO [train.py:842] (3/4) Epoch 28, batch 4050, loss[loss=0.185, simple_loss=0.2807, pruned_loss=0.04466, over 7275.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2646, pruned_loss=0.04382, over 1429311.22 frames.], batch size: 24, lr: 1.97e-04
2022-05-28 19:58:59,888 INFO [train.py:842] (3/4) Epoch 28, batch 4100, loss[loss=0.1607, simple_loss=0.2366, pruned_loss=0.04238, over 6765.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2649, pruned_loss=0.04433, over 1425238.53 frames.], batch size: 15, lr: 1.97e-04
2022-05-28 19:59:39,564 INFO [train.py:842] (3/4) Epoch 28, batch 4150, loss[loss=0.1353, simple_loss=0.2254, pruned_loss=0.02261, over 7405.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2651, pruned_loss=0.04412, over 1424429.59 frames.], batch size: 21, lr: 1.97e-04
2022-05-28 20:00:18,979 INFO [train.py:842] (3/4) Epoch 28, batch 4200, loss[loss=0.145, simple_loss=0.2366, pruned_loss=0.02663, over 7138.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2651, pruned_loss=0.04435, over 1426969.65 frames.], batch size: 17, lr: 1.97e-04
2022-05-28 20:00:58,746 INFO [train.py:842] (3/4) Epoch 28, batch 4250, loss[loss=0.1921, simple_loss=0.2732, pruned_loss=0.0555, over 7226.00 frames.], tot_loss[loss=0.1766, simple_loss=0.265, pruned_loss=0.04406, over 1428339.87 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 20:01:38,108 INFO [train.py:842] (3/4) Epoch 28, batch 4300, loss[loss=0.1627, simple_loss=0.2511, pruned_loss=0.03713, over 7157.00 frames.], tot_loss[loss=0.1767, simple_loss=0.265, pruned_loss=0.04419, over 1426751.41 frames.], batch size: 19, lr: 1.97e-04
2022-05-28 20:02:17,319 INFO [train.py:842] (3/4) Epoch 28, batch 4350, loss[loss=0.1739, simple_loss=0.264, pruned_loss=0.04194, over 7225.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2663, pruned_loss=0.04459, over 1420274.76 frames.], batch size: 20, lr: 1.97e-04
2022-05-28 20:02:56,653 INFO [train.py:842] (3/4) Epoch 28, batch 4400, loss[loss=0.1446, simple_loss=0.2337, pruned_loss=0.02774, over 6995.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2663, pruned_loss=0.04468, over 1421481.18 frames.], batch size: 16, lr: 1.97e-04
2022-05-28 20:03:36,358 INFO [train.py:842] (3/4) Epoch 28, batch 4450, loss[loss=0.1436, simple_loss=0.229, pruned_loss=0.02912, over 7266.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04398, over 1425219.24 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 20:04:15,400 INFO [train.py:842] (3/4) Epoch 28, batch 4500, loss[loss=0.1622, simple_loss=0.2571, pruned_loss=0.03364, over 7323.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2663, pruned_loss=0.04459, over 1425602.88 frames.], batch size: 22, lr: 1.97e-04
2022-05-28 20:04:54,892 INFO [train.py:842] (3/4) Epoch 28, batch 4550, loss[loss=0.166, simple_loss=0.2492, pruned_loss=0.04138, over 7163.00 frames.], tot_loss[loss=0.178, simple_loss=0.2666, pruned_loss=0.04465, over 1420774.98 frames.], batch size: 18, lr: 1.97e-04
2022-05-28 20:05:33,894 INFO [train.py:842] (3/4) Epoch 28, batch 4600, loss[loss=0.1589, simple_loss=0.2465, pruned_loss=0.03559, over 7159.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2666, pruned_loss=0.04455, over 1423259.14 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:06:13,390 INFO [train.py:842] (3/4) Epoch 28, batch 4650, loss[loss=0.1835, simple_loss=0.2644, pruned_loss=0.0513, over 6750.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2669, pruned_loss=0.04478, over 1423774.53 frames.], batch size: 31, lr: 1.96e-04
2022-05-28 20:06:52,740 INFO [train.py:842] (3/4) Epoch 28, batch 4700, loss[loss=0.1493, simple_loss=0.2341, pruned_loss=0.03224, over 7292.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2663, pruned_loss=0.04492, over 1422576.68 frames.], batch size: 18, lr: 1.96e-04
2022-05-28 20:07:32,431 INFO [train.py:842] (3/4) Epoch 28, batch 4750, loss[loss=0.1987, simple_loss=0.2855, pruned_loss=0.05599, over 7199.00 frames.], tot_loss[loss=0.179, simple_loss=0.267, pruned_loss=0.04554, over 1422728.90 frames.], batch size: 22, lr: 1.96e-04
2022-05-28 20:08:11,806 INFO [train.py:842] (3/4) Epoch 28, batch 4800, loss[loss=0.1765, simple_loss=0.2684, pruned_loss=0.04232, over 6803.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2654, pruned_loss=0.04457, over 1417679.72 frames.], batch size: 31, lr: 1.96e-04
2022-05-28 20:08:51,424 INFO [train.py:842] (3/4) Epoch 28, batch 4850, loss[loss=0.1695, simple_loss=0.2636, pruned_loss=0.03769, over 7315.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2649, pruned_loss=0.0441, over 1420919.58 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:09:30,520 INFO [train.py:842] (3/4) Epoch 28, batch 4900, loss[loss=0.2101, simple_loss=0.2955, pruned_loss=0.06239, over 7335.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2663, pruned_loss=0.04464, over 1422390.48 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:10:10,236 INFO [train.py:842] (3/4) Epoch 28, batch 4950, loss[loss=0.1775, simple_loss=0.2685, pruned_loss=0.04326, over 7333.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2663, pruned_loss=0.04463, over 1423215.71 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:10:49,470 INFO [train.py:842] (3/4) Epoch 28, batch 5000, loss[loss=0.1934, simple_loss=0.2849, pruned_loss=0.05094, over 7314.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2654, pruned_loss=0.04396, over 1427422.59 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:11:28,978 INFO [train.py:842] (3/4) Epoch 28, batch 5050, loss[loss=0.1427, simple_loss=0.2137, pruned_loss=0.03584, over 7195.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2639, pruned_loss=0.04334, over 1421638.25 frames.], batch size: 16, lr: 1.96e-04
2022-05-28 20:12:08,126 INFO [train.py:842] (3/4) Epoch 28, batch 5100, loss[loss=0.1748, simple_loss=0.2605, pruned_loss=0.0446, over 7241.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2643, pruned_loss=0.04343, over 1418951.38 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:12:47,612 INFO [train.py:842] (3/4) Epoch 28, batch 5150, loss[loss=0.139, simple_loss=0.232, pruned_loss=0.02294, over 7280.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2631, pruned_loss=0.04269, over 1417010.22 frames.], batch size: 18, lr: 1.96e-04
2022-05-28 20:13:26,678 INFO [train.py:842] (3/4) Epoch 28, batch 5200, loss[loss=0.1739, simple_loss=0.2618, pruned_loss=0.04298, over 7322.00 frames.], tot_loss[loss=0.1749, simple_loss=0.264, pruned_loss=0.04288, over 1418207.76 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:14:06,377 INFO [train.py:842] (3/4) Epoch 28, batch 5250, loss[loss=0.1576, simple_loss=0.251, pruned_loss=0.03205, over 7344.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2639, pruned_loss=0.04292, over 1420250.63 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:14:45,254 INFO [train.py:842] (3/4) Epoch 28, batch 5300, loss[loss=0.1951, simple_loss=0.2835, pruned_loss=0.05337, over 7388.00 frames.], tot_loss[loss=0.1751, simple_loss=0.264, pruned_loss=0.04308, over 1414522.11 frames.], batch size: 23, lr: 1.96e-04
2022-05-28 20:15:25,190 INFO [train.py:842] (3/4) Epoch 28, batch 5350, loss[loss=0.1987, simple_loss=0.2766, pruned_loss=0.06039, over 7390.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2643, pruned_loss=0.04367, over 1417230.97 frames.], batch size: 23, lr: 1.96e-04
2022-05-28 20:16:04,666 INFO [train.py:842] (3/4) Epoch 28, batch 5400, loss[loss=0.1734, simple_loss=0.26, pruned_loss=0.04346, over 6743.00 frames.], tot_loss[loss=0.175, simple_loss=0.2634, pruned_loss=0.04336, over 1420701.28 frames.], batch size: 31, lr: 1.96e-04
2022-05-28 20:16:44,125 INFO [train.py:842] (3/4) Epoch 28, batch 5450, loss[loss=0.1666, simple_loss=0.2498, pruned_loss=0.04172, over 7269.00 frames.], tot_loss[loss=0.1757, simple_loss=0.264, pruned_loss=0.04374, over 1416021.86 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:17:23,286 INFO [train.py:842] (3/4) Epoch 28, batch 5500, loss[loss=0.2061, simple_loss=0.2962, pruned_loss=0.05797, over 7304.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2652, pruned_loss=0.04426, over 1416107.93 frames.], batch size: 24, lr: 1.96e-04
2022-05-28 20:18:02,980 INFO [train.py:842] (3/4) Epoch 28, batch 5550, loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03147, over 7281.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2649, pruned_loss=0.04378, over 1420998.52 frames.], batch size: 18, lr: 1.96e-04
2022-05-28 20:18:42,360 INFO [train.py:842] (3/4) Epoch 28, batch 5600, loss[loss=0.2461, simple_loss=0.3222, pruned_loss=0.08501, over 7345.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2648, pruned_loss=0.04405, over 1420903.74 frames.], batch size: 22, lr: 1.96e-04
2022-05-28 20:19:22,327 INFO [train.py:842] (3/4) Epoch 28, batch 5650, loss[loss=0.2234, simple_loss=0.3033, pruned_loss=0.07177, over 7333.00 frames.], tot_loss[loss=0.1767, simple_loss=0.265, pruned_loss=0.04418, over 1426389.13 frames.], batch size: 22, lr: 1.96e-04
2022-05-28 20:20:01,629 INFO [train.py:842] (3/4) Epoch 28, batch 5700, loss[loss=0.1869, simple_loss=0.2712, pruned_loss=0.05133, over 7152.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2655, pruned_loss=0.04464, over 1429331.31 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:20:41,265 INFO [train.py:842] (3/4) Epoch 28, batch 5750, loss[loss=0.1912, simple_loss=0.2876, pruned_loss=0.04741, over 7314.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2659, pruned_loss=0.0448, over 1426576.49 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:21:20,855 INFO [train.py:842] (3/4) Epoch 28, batch 5800, loss[loss=0.1795, simple_loss=0.2727, pruned_loss=0.04313, over 7149.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2658, pruned_loss=0.04462, over 1430999.50 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:22:00,590 INFO [train.py:842] (3/4) Epoch 28, batch 5850, loss[loss=0.2126, simple_loss=0.2891, pruned_loss=0.06807, over 7157.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.0441, over 1432817.75 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:22:39,832 INFO [train.py:842] (3/4) Epoch 28, batch 5900, loss[loss=0.1684, simple_loss=0.2538, pruned_loss=0.04153, over 7425.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2638, pruned_loss=0.04379, over 1436095.55 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:23:19,416 INFO [train.py:842] (3/4) Epoch 28, batch 5950, loss[loss=0.2415, simple_loss=0.3072, pruned_loss=0.08785, over 7323.00 frames.], tot_loss[loss=0.177, simple_loss=0.265, pruned_loss=0.04448, over 1436502.99 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:23:58,872 INFO [train.py:842] (3/4) Epoch 28, batch 6000, loss[loss=0.2089, simple_loss=0.3047, pruned_loss=0.05654, over 7213.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2658, pruned_loss=0.04495, over 1436794.07 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:23:58,873 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 20:24:08,606 INFO [train.py:871] (3/4) Epoch 28, validation: loss=0.1653, simple_loss=0.2626, pruned_loss=0.03405, over 868885.00 frames.
2022-05-28 20:24:48,333 INFO [train.py:842] (3/4) Epoch 28, batch 6050, loss[loss=0.2476, simple_loss=0.3204, pruned_loss=0.08744, over 6949.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2663, pruned_loss=0.04535, over 1432407.64 frames.], batch size: 28, lr: 1.96e-04
2022-05-28 20:25:27,639 INFO [train.py:842] (3/4) Epoch 28, batch 6100, loss[loss=0.1614, simple_loss=0.2481, pruned_loss=0.03735, over 7448.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2655, pruned_loss=0.04492, over 1430071.92 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:26:07,247 INFO [train.py:842] (3/4) Epoch 28, batch 6150, loss[loss=0.2666, simple_loss=0.3314, pruned_loss=0.1009, over 7316.00 frames.], tot_loss[loss=0.1772, simple_loss=0.265, pruned_loss=0.04475, over 1430781.09 frames.], batch size: 25, lr: 1.96e-04
2022-05-28 20:26:46,812 INFO [train.py:842] (3/4) Epoch 28, batch 6200, loss[loss=0.1995, simple_loss=0.2938, pruned_loss=0.05262, over 7201.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2649, pruned_loss=0.04435, over 1427842.40 frames.], batch size: 22, lr: 1.96e-04
2022-05-28 20:27:26,700 INFO [train.py:842] (3/4) Epoch 28, batch 6250, loss[loss=0.1571, simple_loss=0.2471, pruned_loss=0.03351, over 7258.00 frames.], tot_loss[loss=0.177, simple_loss=0.2652, pruned_loss=0.04438, over 1426491.38 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:28:17,039 INFO [train.py:842] (3/4) Epoch 28, batch 6300, loss[loss=0.2088, simple_loss=0.3141, pruned_loss=0.05171, over 7215.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2649, pruned_loss=0.04444, over 1424228.30 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:28:56,511 INFO [train.py:842] (3/4) Epoch 28, batch 6350, loss[loss=0.1715, simple_loss=0.2639, pruned_loss=0.03949, over 7147.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2657, pruned_loss=0.04477, over 1421033.09 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:29:35,551 INFO [train.py:842] (3/4) Epoch 28, batch 6400, loss[loss=0.2065, simple_loss=0.2947, pruned_loss=0.05915, over 7148.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2655, pruned_loss=0.04473, over 1418379.01 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:30:15,239 INFO [train.py:842] (3/4) Epoch 28, batch 6450, loss[loss=0.1891, simple_loss=0.2702, pruned_loss=0.05396, over 7353.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2645, pruned_loss=0.04441, over 1413648.55 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:30:54,534 INFO [train.py:842] (3/4) Epoch 28, batch 6500, loss[loss=0.1693, simple_loss=0.2634, pruned_loss=0.03758, over 7151.00 frames.], tot_loss[loss=0.178, simple_loss=0.2659, pruned_loss=0.04506, over 1415330.12 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:31:33,940 INFO [train.py:842] (3/4) Epoch 28, batch 6550, loss[loss=0.235, simple_loss=0.3066, pruned_loss=0.08173, over 4797.00 frames.], tot_loss[loss=0.179, simple_loss=0.267, pruned_loss=0.04552, over 1414273.84 frames.], batch size: 52, lr: 1.96e-04
2022-05-28 20:32:34,873 INFO [train.py:842] (3/4) Epoch 28, batch 6600, loss[loss=0.1392, simple_loss=0.2292, pruned_loss=0.02457, over 7123.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2661, pruned_loss=0.04527, over 1410703.86 frames.], batch size: 17, lr: 1.96e-04
2022-05-28 20:33:14,415 INFO [train.py:842] (3/4) Epoch 28, batch 6650, loss[loss=0.1803, simple_loss=0.2698, pruned_loss=0.04539, over 7218.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2661, pruned_loss=0.04526, over 1414218.85 frames.], batch size: 23, lr: 1.96e-04
2022-05-28 20:33:53,570 INFO [train.py:842] (3/4) Epoch 28, batch 6700, loss[loss=0.2298, simple_loss=0.3116, pruned_loss=0.07402, over 7127.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2657, pruned_loss=0.04444, over 1419905.20 frames.], batch size: 26, lr: 1.96e-04
2022-05-28 20:34:33,406 INFO [train.py:842] (3/4) Epoch 28, batch 6750, loss[loss=0.1661, simple_loss=0.2562, pruned_loss=0.03795, over 7381.00 frames.], tot_loss[loss=0.1764, simple_loss=0.265, pruned_loss=0.04393, over 1422015.77 frames.], batch size: 23, lr: 1.96e-04
2022-05-28 20:35:12,648 INFO [train.py:842] (3/4) Epoch 28, batch 6800, loss[loss=0.152, simple_loss=0.2327, pruned_loss=0.03562, over 7283.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2646, pruned_loss=0.04351, over 1423581.86 frames.], batch size: 18, lr: 1.96e-04
2022-05-28 20:35:52,286 INFO [train.py:842] (3/4) Epoch 28, batch 6850, loss[loss=0.2027, simple_loss=0.2886, pruned_loss=0.05835, over 7043.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2653, pruned_loss=0.04379, over 1419013.80 frames.], batch size: 28, lr: 1.96e-04
2022-05-28 20:36:31,712 INFO [train.py:842] (3/4) Epoch 28, batch 6900, loss[loss=0.1816, simple_loss=0.2771, pruned_loss=0.04303, over 7113.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2658, pruned_loss=0.0444, over 1419991.25 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:37:11,520 INFO [train.py:842] (3/4) Epoch 28, batch 6950, loss[loss=0.1823, simple_loss=0.278, pruned_loss=0.04327, over 7275.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2646, pruned_loss=0.04377, over 1422719.03 frames.], batch size: 25, lr: 1.96e-04
2022-05-28 20:37:50,765 INFO [train.py:842] (3/4) Epoch 28, batch 7000, loss[loss=0.2414, simple_loss=0.3269, pruned_loss=0.07791, over 7146.00 frames.], tot_loss[loss=0.176, simple_loss=0.2644, pruned_loss=0.04378, over 1423405.66 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:38:30,302 INFO [train.py:842] (3/4) Epoch 28, batch 7050, loss[loss=0.1544, simple_loss=0.2415, pruned_loss=0.03361, over 7365.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2641, pruned_loss=0.04358, over 1422941.93 frames.], batch size: 19, lr: 1.96e-04
2022-05-28 20:39:09,616 INFO [train.py:842] (3/4) Epoch 28, batch 7100, loss[loss=0.1828, simple_loss=0.2729, pruned_loss=0.0464, over 7427.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2634, pruned_loss=0.04314, over 1426064.35 frames.], batch size: 20, lr: 1.96e-04
2022-05-28 20:39:49,133 INFO [train.py:842] (3/4) Epoch 28, batch 7150, loss[loss=0.1549, simple_loss=0.2511, pruned_loss=0.02934, over 7107.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2646, pruned_loss=0.04384, over 1425174.38 frames.], batch size: 21, lr: 1.96e-04
2022-05-28 20:40:28,338 INFO [train.py:842] (3/4) Epoch 28, batch 7200, loss[loss=0.1953, simple_loss=0.266, pruned_loss=0.06228, over 6995.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2651, pruned_loss=0.04426, over 1422333.42 frames.], batch size: 16, lr: 1.95e-04
2022-05-28 20:41:07,987 INFO [train.py:842] (3/4) Epoch 28, batch 7250, loss[loss=0.1835, simple_loss=0.2723, pruned_loss=0.04737, over 6812.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2655, pruned_loss=0.04435, over 1420266.85 frames.], batch size: 15, lr: 1.95e-04
2022-05-28 20:41:46,968 INFO [train.py:842] (3/4) Epoch 28, batch 7300, loss[loss=0.18, simple_loss=0.2779, pruned_loss=0.04107, over 7226.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2656, pruned_loss=0.04431, over 1419954.85 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 20:42:26,421 INFO [train.py:842] (3/4) Epoch 28, batch 7350, loss[loss=0.1722, simple_loss=0.2535, pruned_loss=0.04546, over 7171.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2651, pruned_loss=0.04421, over 1421118.95 frames.], batch size: 18, lr: 1.95e-04
2022-05-28 20:43:05,474 INFO [train.py:842] (3/4) Epoch 28, batch 7400, loss[loss=0.1714, simple_loss=0.2794, pruned_loss=0.03166, over 7331.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2658, pruned_loss=0.0445, over 1417274.90 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 20:43:45,210 INFO [train.py:842] (3/4) Epoch 28, batch 7450, loss[loss=0.2311, simple_loss=0.3116, pruned_loss=0.07532, over 7426.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04411, over 1422928.92 frames.], batch size: 20, lr: 1.95e-04
2022-05-28 20:44:24,588 INFO [train.py:842] (3/4) Epoch 28, batch 7500, loss[loss=0.1825, simple_loss=0.2757, pruned_loss=0.04467, over 7189.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2647, pruned_loss=0.04427, over 1425514.06 frames.], batch size: 26, lr: 1.95e-04
2022-05-28 20:45:04,400 INFO [train.py:842] (3/4) Epoch 28, batch 7550, loss[loss=0.1693, simple_loss=0.2613, pruned_loss=0.03867, over 7346.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2656, pruned_loss=0.04544, over 1427279.14 frames.], batch size: 22, lr: 1.95e-04
2022-05-28 20:45:43,616 INFO [train.py:842] (3/4) Epoch 28, batch 7600, loss[loss=0.1986, simple_loss=0.2755, pruned_loss=0.06091, over 6823.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.04456, over 1426816.85 frames.], batch size: 15, lr: 1.95e-04
2022-05-28 20:46:23,194 INFO [train.py:842] (3/4) Epoch 28, batch 7650, loss[loss=0.1281, simple_loss=0.2115, pruned_loss=0.02237, over 6792.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2634, pruned_loss=0.04409, over 1426975.35 frames.], batch size: 15, lr: 1.95e-04
2022-05-28 20:47:02,352 INFO [train.py:842] (3/4) Epoch 28, batch 7700, loss[loss=0.207, simple_loss=0.2987, pruned_loss=0.05767, over 7204.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2641, pruned_loss=0.04418, over 1426084.98 frames.], batch size: 22, lr: 1.95e-04
2022-05-28 20:47:42,019 INFO [train.py:842] (3/4) Epoch 28, batch 7750, loss[loss=0.1667, simple_loss=0.2532, pruned_loss=0.0401, over 7166.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2635, pruned_loss=0.04396, over 1421945.32 frames.], batch size: 18, lr: 1.95e-04
2022-05-28 20:48:21,293 INFO [train.py:842] (3/4) Epoch 28, batch 7800, loss[loss=0.2005, simple_loss=0.2944, pruned_loss=0.05337, over 7318.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2635, pruned_loss=0.04339, over 1425234.23 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 20:49:04,101 INFO [train.py:842] (3/4) Epoch 28, batch 7850, loss[loss=0.256, simple_loss=0.331, pruned_loss=0.09051, over 6775.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2646, pruned_loss=0.04455, over 1424948.14 frames.], batch size: 31, lr: 1.95e-04
2022-05-28 20:49:43,309 INFO [train.py:842] (3/4) Epoch 28, batch 7900, loss[loss=0.1472, simple_loss=0.2386, pruned_loss=0.02791, over 7432.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2642, pruned_loss=0.04421, over 1426581.77 frames.], batch size: 20, lr: 1.95e-04
2022-05-28 20:50:22,519 INFO [train.py:842] (3/4) Epoch 28, batch 7950, loss[loss=0.1487, simple_loss=0.2431, pruned_loss=0.02717, over 7330.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04414, over 1421419.02 frames.], batch size: 20, lr: 1.95e-04
2022-05-28 20:51:01,513 INFO [train.py:842] (3/4) Epoch 28, batch 8000, loss[loss=0.1849, simple_loss=0.2744, pruned_loss=0.04767, over 7124.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2644, pruned_loss=0.04432, over 1420068.53 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 20:51:40,853 INFO [train.py:842] (3/4) Epoch 28, batch 8050, loss[loss=0.1988, simple_loss=0.288, pruned_loss=0.0548, over 7230.00 frames.], tot_loss[loss=0.176, simple_loss=0.2639, pruned_loss=0.04407, over 1419851.59 frames.], batch size: 20, lr: 1.95e-04
2022-05-28 20:52:19,891 INFO [train.py:842] (3/4) Epoch 28, batch 8100, loss[loss=0.1812, simple_loss=0.2774, pruned_loss=0.04253, over 7290.00 frames.], tot_loss[loss=0.1774, simple_loss=0.265, pruned_loss=0.04489, over 1420708.37 frames.], batch size: 24, lr: 1.95e-04
2022-05-28 20:52:59,284 INFO [train.py:842] (3/4) Epoch 28, batch 8150, loss[loss=0.1873, simple_loss=0.2556, pruned_loss=0.05948, over 7411.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.04445, over 1415523.68 frames.], batch size: 18, lr: 1.95e-04
2022-05-28 20:53:38,475 INFO [train.py:842] (3/4) Epoch 28, batch 8200, loss[loss=0.206, simple_loss=0.294, pruned_loss=0.05904, over 7301.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2647, pruned_loss=0.04438, over 1418236.01 frames.], batch size: 24, lr: 1.95e-04
2022-05-28 20:54:18,202 INFO [train.py:842] (3/4) Epoch 28, batch 8250, loss[loss=0.1766, simple_loss=0.2742, pruned_loss=0.03956, over 7335.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2638, pruned_loss=0.04352, over 1419926.20 frames.], batch size: 22, lr: 1.95e-04
2022-05-28 20:54:57,222 INFO [train.py:842] (3/4) Epoch 28, batch 8300, loss[loss=0.1745, simple_loss=0.2635, pruned_loss=0.04269, over 7221.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2644, pruned_loss=0.04355, over 1422524.65 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 20:55:36,890 INFO [train.py:842] (3/4) Epoch 28, batch 8350, loss[loss=0.1467, simple_loss=0.2377, pruned_loss=0.02789, over 6812.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2661, pruned_loss=0.04452, over 1424443.35 frames.], batch size: 15, lr: 1.95e-04
2022-05-28 20:56:16,247 INFO [train.py:842] (3/4) Epoch 28, batch 8400, loss[loss=0.149, simple_loss=0.2286, pruned_loss=0.03467, over 7134.00 frames.], tot_loss[loss=0.178, simple_loss=0.2661, pruned_loss=0.04495, over 1424417.69 frames.], batch size: 17, lr: 1.95e-04
2022-05-28 20:56:55,889 INFO [train.py:842] (3/4) Epoch 28, batch 8450, loss[loss=0.1697, simple_loss=0.2567, pruned_loss=0.04133, over 7144.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2667, pruned_loss=0.04539, over 1418970.75 frames.], batch size: 17, lr: 1.95e-04
2022-05-28 20:57:34,977 INFO [train.py:842] (3/4) Epoch 28, batch 8500, loss[loss=0.1922, simple_loss=0.2918, pruned_loss=0.04634, over 7388.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2658, pruned_loss=0.04458, over 1416772.98 frames.], batch size: 23, lr: 1.95e-04
2022-05-28 20:58:14,439 INFO [train.py:842] (3/4) Epoch 28, batch 8550, loss[loss=0.1586, simple_loss=0.2506, pruned_loss=0.0333, over 7366.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2659, pruned_loss=0.04469, over 1414790.09 frames.], batch size: 23, lr: 1.95e-04
2022-05-28 20:58:53,545 INFO [train.py:842] (3/4) Epoch 28, batch 8600, loss[loss=0.1851, simple_loss=0.2711, pruned_loss=0.04959, over 7396.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2661, pruned_loss=0.04509, over 1409565.80 frames.], batch size: 23, lr: 1.95e-04
2022-05-28 20:59:32,624 INFO [train.py:842] (3/4) Epoch 28, batch 8650, loss[loss=0.1866, simple_loss=0.2713, pruned_loss=0.05094, over 7434.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2665, pruned_loss=0.04482, over 1409158.58 frames.], batch size: 20, lr: 1.95e-04
2022-05-28 21:00:11,774 INFO [train.py:842] (3/4) Epoch 28, batch 8700, loss[loss=0.1781, simple_loss=0.2737, pruned_loss=0.04128, over 6484.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2662, pruned_loss=0.04419, over 1411841.96 frames.], batch size: 38, lr: 1.95e-04
2022-05-28 21:00:51,071 INFO [train.py:842] (3/4) Epoch 28, batch 8750, loss[loss=0.2084, simple_loss=0.2971, pruned_loss=0.05988, over 7117.00 frames.], tot_loss[loss=0.1768, simple_loss=0.266, pruned_loss=0.0438, over 1408897.98 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 21:01:30,144 INFO [train.py:842] (3/4) Epoch 28, batch 8800, loss[loss=0.2223, simple_loss=0.3096, pruned_loss=0.06747, over 7371.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2679, pruned_loss=0.04511, over 1406210.82 frames.], batch size: 23, lr: 1.95e-04
2022-05-28 21:02:09,477 INFO [train.py:842] (3/4) Epoch 28, batch 8850, loss[loss=0.1635, simple_loss=0.2521, pruned_loss=0.03748, over 7195.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2675, pruned_loss=0.04497, over 1404613.56 frames.], batch size: 26, lr: 1.95e-04
2022-05-28 21:02:48,601 INFO [train.py:842] (3/4) Epoch 28, batch 8900, loss[loss=0.2272, simple_loss=0.3019, pruned_loss=0.07629, over 5246.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2686, pruned_loss=0.046, over 1393503.17 frames.], batch size: 55, lr: 1.95e-04
2022-05-28 21:03:28,085 INFO [train.py:842] (3/4) Epoch 28, batch 8950, loss[loss=0.1683, simple_loss=0.2612, pruned_loss=0.03767, over 7125.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2673, pruned_loss=0.0456, over 1390388.30 frames.], batch size: 21, lr: 1.95e-04
2022-05-28 21:04:07,038 INFO [train.py:842] (3/4) Epoch 28, batch 9000, loss[loss=0.1444, simple_loss=0.2335, pruned_loss=0.02768, over 7161.00 frames.], tot_loss[loss=0.18, simple_loss=0.2681, pruned_loss=0.04592, over 1382374.58 frames.], batch size: 19, lr: 1.95e-04
2022-05-28 21:04:07,039 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 21:04:16,595 INFO [train.py:871] (3/4) Epoch 28, validation: loss=0.1632, simple_loss=0.2611, pruned_loss=0.03268, over 868885.00 frames.
2022-05-28 21:04:55,646 INFO [train.py:842] (3/4) Epoch 28, batch 9050, loss[loss=0.161, simple_loss=0.2585, pruned_loss=0.03171, over 6234.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2681, pruned_loss=0.04645, over 1359124.07 frames.], batch size: 37, lr: 1.95e-04
2022-05-28 21:05:34,567 INFO [train.py:842] (3/4) Epoch 28, batch 9100, loss[loss=0.168, simple_loss=0.26, pruned_loss=0.03796, over 5018.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2674, pruned_loss=0.04687, over 1333060.32 frames.], batch size: 52, lr: 1.95e-04
2022-05-28 21:06:12,619 INFO [train.py:842] (3/4) Epoch 28, batch 9150, loss[loss=0.1673, simple_loss=0.2637, pruned_loss=0.03541, over 6308.00 frames.], tot_loss[loss=0.1831, simple_loss=0.27, pruned_loss=0.04812, over 1299269.58 frames.], batch size: 37, lr: 1.95e-04
2022-05-28 21:07:04,998 INFO [train.py:842] (3/4) Epoch 29, batch 0, loss[loss=0.1678, simple_loss=0.261, pruned_loss=0.03727, over 6986.00 frames.], tot_loss[loss=0.1678, simple_loss=0.261, pruned_loss=0.03727, over 6986.00 frames.], batch size: 28, lr: 1.91e-04
2022-05-28 21:07:44,650 INFO [train.py:842] (3/4) Epoch 29, batch 50, loss[loss=0.1853, simple_loss=0.2731, pruned_loss=0.04878, over 7270.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2682, pruned_loss=0.0452, over 323531.90 frames.], batch size: 24, lr: 1.91e-04
2022-05-28 21:08:24,035 INFO [train.py:842] (3/4) Epoch 29, batch 100, loss[loss=0.1738, simple_loss=0.2749, pruned_loss=0.03629, over 7317.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2664, pruned_loss=0.04446, over 569323.87 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:09:03,640 INFO [train.py:842] (3/4) Epoch 29, batch 150, loss[loss=0.1767, simple_loss=0.2785, pruned_loss=0.03742, over 7220.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2666, pruned_loss=0.04411, over 759487.86 frames.], batch size: 20, lr: 1.91e-04
2022-05-28 21:09:43,182 INFO [train.py:842] (3/4) Epoch 29, batch 200, loss[loss=0.1545, simple_loss=0.2283, pruned_loss=0.0403, over 7062.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2657, pruned_loss=0.0438, over 909098.92 frames.], batch size: 18, lr: 1.91e-04
2022-05-28 21:10:22,674 INFO [train.py:842] (3/4) Epoch 29, batch 250, loss[loss=0.2466, simple_loss=0.3252, pruned_loss=0.084, over 5078.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2661, pruned_loss=0.04409, over 1019978.93 frames.], batch size: 52, lr: 1.91e-04
2022-05-28 21:11:01,712 INFO [train.py:842] (3/4) Epoch 29, batch 300, loss[loss=0.1667, simple_loss=0.2406, pruned_loss=0.04644, over 7152.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2656, pruned_loss=0.04381, over 1109857.88 frames.], batch size: 18, lr: 1.91e-04
2022-05-28 21:11:41,220 INFO [train.py:842] (3/4) Epoch 29, batch 350, loss[loss=0.1654, simple_loss=0.2593, pruned_loss=0.03569, over 7446.00 frames.], tot_loss[loss=0.177, simple_loss=0.2663, pruned_loss=0.0439, over 1181585.96 frames.], batch size: 19, lr: 1.91e-04
2022-05-28 21:12:20,488 INFO [train.py:842] (3/4) Epoch 29, batch 400, loss[loss=0.245, simple_loss=0.3115, pruned_loss=0.08927, over 7139.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2657, pruned_loss=0.0442, over 1236921.70 frames.], batch size: 20, lr: 1.91e-04
2022-05-28 21:13:00,124 INFO [train.py:842] (3/4) Epoch 29, batch 450, loss[loss=0.191, simple_loss=0.289, pruned_loss=0.04648, over 7101.00 frames.], tot_loss[loss=0.175, simple_loss=0.2637, pruned_loss=0.04319, over 1282799.00 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:13:39,188 INFO [train.py:842] (3/4) Epoch 29, batch 500, loss[loss=0.2069, simple_loss=0.2824, pruned_loss=0.0657, over 5038.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2639, pruned_loss=0.04346, over 1310054.49 frames.], batch size: 52, lr: 1.91e-04
2022-05-28 21:14:18,729 INFO [train.py:842] (3/4) Epoch 29, batch 550, loss[loss=0.2025, simple_loss=0.2963, pruned_loss=0.05434, over 7231.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2635, pruned_loss=0.04342, over 1332219.74 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:14:58,122 INFO [train.py:842] (3/4) Epoch 29, batch 600, loss[loss=0.1722, simple_loss=0.2609, pruned_loss=0.04174, over 7261.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2641, pruned_loss=0.04405, over 1349558.08 frames.], batch size: 19, lr: 1.91e-04
2022-05-28 21:15:37,686 INFO [train.py:842] (3/4) Epoch 29, batch 650, loss[loss=0.1721, simple_loss=0.2686, pruned_loss=0.03779, over 7074.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2637, pruned_loss=0.04378, over 1367722.08 frames.], batch size: 18, lr: 1.91e-04
2022-05-28 21:16:17,145 INFO [train.py:842] (3/4) Epoch 29, batch 700, loss[loss=0.213, simple_loss=0.2973, pruned_loss=0.06434, over 5181.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.04413, over 1376250.58 frames.], batch size: 53, lr: 1.91e-04
2022-05-28 21:16:56,539 INFO [train.py:842] (3/4) Epoch 29, batch 750, loss[loss=0.158, simple_loss=0.2505, pruned_loss=0.03276, over 7434.00 frames.], tot_loss[loss=0.1769, simple_loss=0.265, pruned_loss=0.04443, over 1382917.02 frames.], batch size: 20, lr: 1.91e-04
2022-05-28 21:17:35,621 INFO [train.py:842] (3/4) Epoch 29, batch 800, loss[loss=0.1718, simple_loss=0.2625, pruned_loss=0.04059, over 7120.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2657, pruned_loss=0.04456, over 1388472.72 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:18:15,128 INFO [train.py:842] (3/4) Epoch 29, batch 850, loss[loss=0.1607, simple_loss=0.2578, pruned_loss=0.03178, over 6533.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2654, pruned_loss=0.04437, over 1393357.13 frames.], batch size: 38, lr: 1.91e-04
2022-05-28 21:18:54,098 INFO [train.py:842] (3/4) Epoch 29, batch 900, loss[loss=0.1838, simple_loss=0.2769, pruned_loss=0.04533, over 6784.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2646, pruned_loss=0.04332, over 1399803.44 frames.], batch size: 31, lr: 1.91e-04
2022-05-28 21:19:33,695 INFO [train.py:842] (3/4) Epoch 29, batch 950, loss[loss=0.1768, simple_loss=0.268, pruned_loss=0.04286, over 7215.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2644, pruned_loss=0.04317, over 1408455.14 frames.], batch size: 22, lr: 1.91e-04
2022-05-28 21:20:13,123 INFO [train.py:842] (3/4) Epoch 29, batch 1000, loss[loss=0.1412, simple_loss=0.2252, pruned_loss=0.02861, over 6829.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2638, pruned_loss=0.04319, over 1414025.41 frames.], batch size: 15, lr: 1.91e-04
2022-05-28 21:20:52,895 INFO [train.py:842] (3/4) Epoch 29, batch 1050, loss[loss=0.1829, simple_loss=0.273, pruned_loss=0.04641, over 7414.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2642, pruned_loss=0.04332, over 1419681.60 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:21:32,454 INFO [train.py:842] (3/4) Epoch 29, batch 1100, loss[loss=0.1451, simple_loss=0.2254, pruned_loss=0.03238, over 7281.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2643, pruned_loss=0.04407, over 1422405.13 frames.], batch size: 17, lr: 1.91e-04
2022-05-28 21:22:11,788 INFO [train.py:842] (3/4) Epoch 29, batch 1150, loss[loss=0.164, simple_loss=0.2532, pruned_loss=0.03736, over 7000.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.04413, over 1420591.61 frames.], batch size: 28, lr: 1.91e-04
2022-05-28 21:22:50,766 INFO [train.py:842] (3/4) Epoch 29, batch 1200, loss[loss=0.1825, simple_loss=0.272, pruned_loss=0.04655, over 7055.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2661, pruned_loss=0.04458, over 1423109.24 frames.], batch size: 28, lr: 1.91e-04
2022-05-28 21:23:30,554 INFO [train.py:842] (3/4) Epoch 29, batch 1250, loss[loss=0.1801, simple_loss=0.2732, pruned_loss=0.04345, over 7195.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2657, pruned_loss=0.04479, over 1417362.76 frames.], batch size: 22, lr: 1.91e-04
2022-05-28 21:24:09,896 INFO [train.py:842] (3/4) Epoch 29, batch 1300, loss[loss=0.1906, simple_loss=0.2704, pruned_loss=0.05536, over 7142.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2654, pruned_loss=0.04501, over 1419786.16 frames.], batch size: 20, lr: 1.91e-04
2022-05-28 21:24:49,648 INFO [train.py:842] (3/4) Epoch 29, batch 1350, loss[loss=0.1742, simple_loss=0.2711, pruned_loss=0.03864, over 7110.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2642, pruned_loss=0.04423, over 1425225.09 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:25:29,131 INFO [train.py:842] (3/4) Epoch 29, batch 1400, loss[loss=0.1513, simple_loss=0.2352, pruned_loss=0.03373, over 7282.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2641, pruned_loss=0.04413, over 1426493.69 frames.], batch size: 17, lr: 1.91e-04
2022-05-28 21:26:08,842 INFO [train.py:842] (3/4) Epoch 29, batch 1450, loss[loss=0.1839, simple_loss=0.2742, pruned_loss=0.04686, over 7276.00 frames.], tot_loss[loss=0.1759, simple_loss=0.264, pruned_loss=0.04394, over 1430490.38 frames.], batch size: 24, lr: 1.91e-04
2022-05-28 21:26:47,904 INFO [train.py:842] (3/4) Epoch 29, batch 1500, loss[loss=0.1573, simple_loss=0.2456, pruned_loss=0.03449, over 7329.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2647, pruned_loss=0.04412, over 1426672.98 frames.], batch size: 20, lr: 1.91e-04
2022-05-28 21:27:27,477 INFO [train.py:842] (3/4) Epoch 29, batch 1550, loss[loss=0.1887, simple_loss=0.281, pruned_loss=0.04817, over 7228.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2648, pruned_loss=0.04396, over 1428807.43 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:28:06,659 INFO [train.py:842] (3/4) Epoch 29, batch 1600, loss[loss=0.1398, simple_loss=0.2225, pruned_loss=0.02855, over 7245.00 frames.], tot_loss[loss=0.1764, simple_loss=0.265, pruned_loss=0.04393, over 1427069.21 frames.], batch size: 16, lr: 1.91e-04
2022-05-28 21:28:46,409 INFO [train.py:842] (3/4) Epoch 29, batch 1650, loss[loss=0.1705, simple_loss=0.2436, pruned_loss=0.04874, over 6819.00 frames.], tot_loss[loss=0.1756, simple_loss=0.264, pruned_loss=0.04362, over 1428581.87 frames.], batch size: 15, lr: 1.91e-04
2022-05-28 21:29:25,918 INFO [train.py:842] (3/4) Epoch 29, batch 1700, loss[loss=0.1538, simple_loss=0.2354, pruned_loss=0.03611, over 7263.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2638, pruned_loss=0.04391, over 1431200.94 frames.], batch size: 19, lr: 1.91e-04
2022-05-28 21:30:05,659 INFO [train.py:842] (3/4) Epoch 29, batch 1750, loss[loss=0.1909, simple_loss=0.288, pruned_loss=0.04687, over 7119.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2638, pruned_loss=0.04397, over 1432883.89 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:30:44,935 INFO [train.py:842] (3/4) Epoch 29, batch 1800, loss[loss=0.161, simple_loss=0.2391, pruned_loss=0.04149, over 6998.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2638, pruned_loss=0.04398, over 1423209.10 frames.], batch size: 16, lr: 1.91e-04
2022-05-28 21:31:24,536 INFO [train.py:842] (3/4) Epoch 29, batch 1850, loss[loss=0.1773, simple_loss=0.2502, pruned_loss=0.05223, over 7403.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2655, pruned_loss=0.04442, over 1425274.37 frames.], batch size: 18, lr: 1.91e-04
2022-05-28 21:32:03,691 INFO [train.py:842] (3/4) Epoch 29, batch 1900, loss[loss=0.21, simple_loss=0.2906, pruned_loss=0.06465, over 7179.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2649, pruned_loss=0.04405, over 1425692.57 frames.], batch size: 26, lr: 1.91e-04
2022-05-28 21:32:43,278 INFO [train.py:842] (3/4) Epoch 29, batch 1950, loss[loss=0.1739, simple_loss=0.259, pruned_loss=0.04441, over 7309.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2658, pruned_loss=0.04441, over 1428154.80 frames.], batch size: 25, lr: 1.91e-04
2022-05-28 21:33:22,694 INFO [train.py:842] (3/4) Epoch 29, batch 2000, loss[loss=0.1929, simple_loss=0.2906, pruned_loss=0.04764, over 7200.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2654, pruned_loss=0.04443, over 1431184.08 frames.], batch size: 23, lr: 1.91e-04
2022-05-28 21:34:02,058 INFO [train.py:842] (3/4) Epoch 29, batch 2050, loss[loss=0.1849, simple_loss=0.2745, pruned_loss=0.04769, over 7330.00 frames.], tot_loss[loss=0.1779, simple_loss=0.266, pruned_loss=0.04496, over 1424954.65 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:34:41,401 INFO [train.py:842] (3/4) Epoch 29, batch 2100, loss[loss=0.1769, simple_loss=0.2678, pruned_loss=0.04299, over 7317.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.04442, over 1427189.61 frames.], batch size: 25, lr: 1.91e-04
2022-05-28 21:35:21,033 INFO [train.py:842] (3/4) Epoch 29, batch 2150, loss[loss=0.1748, simple_loss=0.271, pruned_loss=0.03934, over 7220.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2647, pruned_loss=0.04424, over 1428297.89 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:36:00,008 INFO [train.py:842] (3/4) Epoch 29, batch 2200, loss[loss=0.2014, simple_loss=0.3012, pruned_loss=0.05079, over 7326.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2647, pruned_loss=0.04429, over 1422656.79 frames.], batch size: 25, lr: 1.91e-04
2022-05-28 21:36:39,495 INFO [train.py:842] (3/4) Epoch 29, batch 2250, loss[loss=0.1579, simple_loss=0.2576, pruned_loss=0.02911, over 7110.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2644, pruned_loss=0.04401, over 1426546.21 frames.], batch size: 21, lr: 1.91e-04
2022-05-28 21:37:18,738 INFO [train.py:842] (3/4) Epoch 29, batch 2300, loss[loss=0.1546, simple_loss=0.2486, pruned_loss=0.03027, over 7287.00 frames.], tot_loss[loss=0.175, simple_loss=0.2629, pruned_loss=0.04352, over 1427886.31 frames.], batch size: 24, lr: 1.91e-04
2022-05-28 21:37:58,229 INFO [train.py:842] (3/4) Epoch 29, batch 2350, loss[loss=0.2196, simple_loss=0.295, pruned_loss=0.07214, over 7070.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2639, pruned_loss=0.04389, over 1425841.71 frames.], batch size: 18, lr: 1.91e-04
2022-05-28 21:38:37,565 INFO [train.py:842] (3/4) Epoch 29, batch 2400, loss[loss=0.1375, simple_loss=0.2297, pruned_loss=0.02269, over 7359.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2625, pruned_loss=0.04333, over 1426814.00 frames.], batch size: 19, lr: 1.90e-04
2022-05-28 21:39:16,874 INFO [train.py:842] (3/4) Epoch 29, batch 2450, loss[loss=0.1504, simple_loss=0.2388, pruned_loss=0.03106, over 7110.00 frames.], tot_loss[loss=0.176, simple_loss=0.2638, pruned_loss=0.0441, over 1417047.36 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:39:56,308 INFO [train.py:842] (3/4) Epoch 29, batch 2500, loss[loss=0.1443, simple_loss=0.2269, pruned_loss=0.03081, over 7390.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2626, pruned_loss=0.04347, over 1420104.75 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:40:35,886 INFO [train.py:842] (3/4) Epoch 29, batch 2550, loss[loss=0.1396, simple_loss=0.2355, pruned_loss=0.02186, over 7165.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2626, pruned_loss=0.04323, over 1416859.91 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:41:14,985 INFO [train.py:842] (3/4) Epoch 29, batch 2600, loss[loss=0.2052, simple_loss=0.2928, pruned_loss=0.05885, over 7201.00 frames.], tot_loss[loss=0.1742, simple_loss=0.262, pruned_loss=0.04327, over 1415069.17 frames.], batch size: 23, lr: 1.90e-04
2022-05-28 21:41:54,638 INFO [train.py:842] (3/4) Epoch 29, batch 2650, loss[loss=0.1632, simple_loss=0.2533, pruned_loss=0.03652, over 7399.00 frames.], tot_loss[loss=0.174, simple_loss=0.2618, pruned_loss=0.04308, over 1417997.05 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:42:33,909 INFO [train.py:842] (3/4) Epoch 29, batch 2700, loss[loss=0.2054, simple_loss=0.2903, pruned_loss=0.06021, over 5315.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2618, pruned_loss=0.04346, over 1418556.79 frames.], batch size: 52, lr: 1.90e-04
2022-05-28 21:43:13,538 INFO [train.py:842] (3/4) Epoch 29, batch 2750, loss[loss=0.1942, simple_loss=0.2899, pruned_loss=0.04927, over 7321.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2625, pruned_loss=0.04343, over 1414776.69 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:43:52,903 INFO [train.py:842] (3/4) Epoch 29, batch 2800, loss[loss=0.1678, simple_loss=0.2657, pruned_loss=0.0349, over 7337.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2626, pruned_loss=0.04305, over 1418032.87 frames.], batch size: 22, lr: 1.90e-04
2022-05-28 21:44:32,561 INFO [train.py:842] (3/4) Epoch 29, batch 2850, loss[loss=0.1779, simple_loss=0.2604, pruned_loss=0.04771, over 7273.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04281, over 1419320.11 frames.], batch size: 19, lr: 1.90e-04
2022-05-28 21:45:11,789 INFO [train.py:842] (3/4) Epoch 29, batch 2900, loss[loss=0.1731, simple_loss=0.2524, pruned_loss=0.0469, over 7260.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04233, over 1419460.19 frames.], batch size: 17, lr: 1.90e-04
2022-05-28 21:45:51,687 INFO [train.py:842] (3/4) Epoch 29, batch 2950, loss[loss=0.1472, simple_loss=0.2277, pruned_loss=0.03332, over 7129.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2608, pruned_loss=0.04254, over 1419026.47 frames.], batch size: 17, lr: 1.90e-04
2022-05-28 21:46:30,718 INFO [train.py:842] (3/4) Epoch 29, batch 3000, loss[loss=0.163, simple_loss=0.2553, pruned_loss=0.03538, over 7232.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2614, pruned_loss=0.04267, over 1419552.72 frames.], batch size: 20, lr: 1.90e-04
2022-05-28 21:46:30,719 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 21:46:40,407 INFO [train.py:871] (3/4) Epoch 29, validation: loss=0.1638, simple_loss=0.2614, pruned_loss=0.03305, over 868885.00 frames.
2022-05-28 21:47:20,126 INFO [train.py:842] (3/4) Epoch 29, batch 3050, loss[loss=0.1363, simple_loss=0.226, pruned_loss=0.02329, over 7148.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2614, pruned_loss=0.04291, over 1422107.83 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:47:59,335 INFO [train.py:842] (3/4) Epoch 29, batch 3100, loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.04225, over 7285.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2621, pruned_loss=0.0432, over 1418859.95 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:48:38,805 INFO [train.py:842] (3/4) Epoch 29, batch 3150, loss[loss=0.1668, simple_loss=0.2539, pruned_loss=0.03979, over 7220.00 frames.], tot_loss[loss=0.176, simple_loss=0.2635, pruned_loss=0.04428, over 1422051.70 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:49:18,089 INFO [train.py:842] (3/4) Epoch 29, batch 3200, loss[loss=0.1733, simple_loss=0.2545, pruned_loss=0.04609, over 7114.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2647, pruned_loss=0.04502, over 1421932.09 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:49:57,949 INFO [train.py:842] (3/4) Epoch 29, batch 3250, loss[loss=0.1452, simple_loss=0.2316, pruned_loss=0.0294, over 7259.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2654, pruned_loss=0.04538, over 1422089.57 frames.], batch size: 16, lr: 1.90e-04
2022-05-28 21:50:37,011 INFO [train.py:842] (3/4) Epoch 29, batch 3300, loss[loss=0.1458, simple_loss=0.2391, pruned_loss=0.02626, over 7220.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2651, pruned_loss=0.04494, over 1421267.55 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:51:16,444 INFO [train.py:842] (3/4) Epoch 29, batch 3350, loss[loss=0.1681, simple_loss=0.2562, pruned_loss=0.04003, over 7097.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2647, pruned_loss=0.04521, over 1418850.92 frames.], batch size: 28, lr: 1.90e-04
2022-05-28 21:51:55,690 INFO [train.py:842] (3/4) Epoch 29, batch 3400, loss[loss=0.1654, simple_loss=0.2511, pruned_loss=0.03981, over 7072.00 frames.], tot_loss[loss=0.178, simple_loss=0.2653, pruned_loss=0.04533, over 1417675.67 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:52:35,475 INFO [train.py:842] (3/4) Epoch 29, batch 3450, loss[loss=0.1747, simple_loss=0.2461, pruned_loss=0.05164, over 7299.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2637, pruned_loss=0.04423, over 1420554.95 frames.], batch size: 17, lr: 1.90e-04
2022-05-28 21:53:14,708 INFO [train.py:842] (3/4) Epoch 29, batch 3500, loss[loss=0.1722, simple_loss=0.2581, pruned_loss=0.04315, over 6775.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2646, pruned_loss=0.0444, over 1419561.14 frames.], batch size: 31, lr: 1.90e-04
2022-05-28 21:53:54,285 INFO [train.py:842] (3/4) Epoch 29, batch 3550, loss[loss=0.1837, simple_loss=0.2614, pruned_loss=0.05299, over 7288.00 frames.], tot_loss[loss=0.176, simple_loss=0.2642, pruned_loss=0.04384, over 1422949.27 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:54:33,670 INFO [train.py:842] (3/4) Epoch 29, batch 3600, loss[loss=0.1225, simple_loss=0.2054, pruned_loss=0.01981, over 7211.00 frames.], tot_loss[loss=0.1769, simple_loss=0.265, pruned_loss=0.04438, over 1423319.73 frames.], batch size: 16, lr: 1.90e-04
2022-05-28 21:55:13,234 INFO [train.py:842] (3/4) Epoch 29, batch 3650, loss[loss=0.1767, simple_loss=0.2648, pruned_loss=0.04429, over 7335.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2649, pruned_loss=0.04429, over 1426585.87 frames.], batch size: 22, lr: 1.90e-04
2022-05-28 21:55:52,642 INFO [train.py:842] (3/4) Epoch 29, batch 3700, loss[loss=0.2122, simple_loss=0.2973, pruned_loss=0.06361, over 7200.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2651, pruned_loss=0.04429, over 1426362.75 frames.], batch size: 23, lr: 1.90e-04
2022-05-28 21:56:32,195 INFO [train.py:842] (3/4) Epoch 29, batch 3750, loss[loss=0.1934, simple_loss=0.2843, pruned_loss=0.05124, over 5273.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2652, pruned_loss=0.04409, over 1425438.68 frames.], batch size: 53, lr: 1.90e-04
2022-05-28 21:57:11,439 INFO [train.py:842] (3/4) Epoch 29, batch 3800, loss[loss=0.1464, simple_loss=0.2323, pruned_loss=0.03021, over 7052.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2658, pruned_loss=0.04417, over 1427693.74 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:57:51,303 INFO [train.py:842] (3/4) Epoch 29, batch 3850, loss[loss=0.157, simple_loss=0.2344, pruned_loss=0.03983, over 7233.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2647, pruned_loss=0.0435, over 1426010.12 frames.], batch size: 16, lr: 1.90e-04
2022-05-28 21:58:30,621 INFO [train.py:842] (3/4) Epoch 29, batch 3900, loss[loss=0.1609, simple_loss=0.243, pruned_loss=0.03943, over 7407.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2643, pruned_loss=0.04343, over 1428187.94 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 21:59:10,122 INFO [train.py:842] (3/4) Epoch 29, batch 3950, loss[loss=0.1683, simple_loss=0.2695, pruned_loss=0.03356, over 7119.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2642, pruned_loss=0.04323, over 1429345.68 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 21:59:49,043 INFO [train.py:842] (3/4) Epoch 29, batch 4000, loss[loss=0.2225, simple_loss=0.2989, pruned_loss=0.07302, over 7109.00 frames.], tot_loss[loss=0.1758, simple_loss=0.265, pruned_loss=0.04331, over 1428948.04 frames.], batch size: 21, lr: 1.90e-04
2022-05-28 22:00:28,494 INFO [train.py:842] (3/4) Epoch 29, batch 4050, loss[loss=0.1672, simple_loss=0.2547, pruned_loss=0.03985, over 7059.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2654, pruned_loss=0.04361, over 1428235.88 frames.], batch size: 28, lr: 1.90e-04
2022-05-28 22:01:07,538 INFO [train.py:842] (3/4) Epoch 29, batch 4100, loss[loss=0.1809, simple_loss=0.2743, pruned_loss=0.04376, over 7097.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2648, pruned_loss=0.04392, over 1429364.42 frames.], batch size: 28, lr: 1.90e-04
2022-05-28 22:01:47,194 INFO [train.py:842] (3/4) Epoch 29, batch 4150, loss[loss=0.1903, simple_loss=0.2831, pruned_loss=0.0487, over 7242.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2648, pruned_loss=0.04397, over 1431579.17 frames.], batch size: 20, lr: 1.90e-04
2022-05-28 22:02:26,303 INFO [train.py:842] (3/4) Epoch 29, batch 4200, loss[loss=0.1911, simple_loss=0.2907, pruned_loss=0.04578, over 7331.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2649, pruned_loss=0.04417, over 1427047.13 frames.], batch size: 22, lr: 1.90e-04
2022-05-28 22:03:06,011 INFO [train.py:842] (3/4) Epoch 29, batch 4250, loss[loss=0.1767, simple_loss=0.2592, pruned_loss=0.04713, over 7255.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04378, over 1426312.51 frames.], batch size: 19, lr: 1.90e-04
2022-05-28 22:03:45,571 INFO [train.py:842] (3/4) Epoch 29, batch 4300, loss[loss=0.1451, simple_loss=0.2254, pruned_loss=0.03245, over 6830.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2638, pruned_loss=0.04341, over 1427482.93 frames.], batch size: 15, lr: 1.90e-04
2022-05-28 22:04:25,105 INFO [train.py:842] (3/4) Epoch 29, batch 4350, loss[loss=0.2152, simple_loss=0.3027, pruned_loss=0.06391, over 7164.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2651, pruned_loss=0.04372, over 1429931.23 frames.], batch size: 26, lr: 1.90e-04
2022-05-28 22:05:04,083 INFO [train.py:842] (3/4) Epoch 29, batch 4400, loss[loss=0.2114, simple_loss=0.2931, pruned_loss=0.06482, over 4918.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2652, pruned_loss=0.04375, over 1425859.98 frames.], batch size: 52, lr: 1.90e-04
2022-05-28 22:05:43,314 INFO [train.py:842] (3/4) Epoch 29, batch 4450, loss[loss=0.1569, simple_loss=0.2519, pruned_loss=0.03093, over 6683.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2641, pruned_loss=0.04328, over 1426404.50 frames.], batch size: 31, lr: 1.90e-04
2022-05-28 22:06:22,582 INFO [train.py:842] (3/4) Epoch 29, batch 4500, loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.03222, over 7328.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2633, pruned_loss=0.04267, over 1428702.57 frames.], batch size: 22, lr: 1.90e-04
2022-05-28 22:07:02,130 INFO [train.py:842] (3/4) Epoch 29, batch 4550, loss[loss=0.1718, simple_loss=0.2529, pruned_loss=0.04535, over 6843.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2645, pruned_loss=0.04363, over 1427189.86 frames.], batch size: 15, lr: 1.90e-04
2022-05-28 22:07:41,339 INFO [train.py:842] (3/4) Epoch 29, batch 4600, loss[loss=0.1737, simple_loss=0.27, pruned_loss=0.0387, over 7430.00 frames.], tot_loss[loss=0.175, simple_loss=0.2641, pruned_loss=0.04301, over 1428381.18 frames.], batch size: 20, lr: 1.90e-04
2022-05-28 22:08:21,051 INFO [train.py:842] (3/4) Epoch 29, batch 4650, loss[loss=0.1778, simple_loss=0.2622, pruned_loss=0.0467, over 7200.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2646, pruned_loss=0.04461, over 1428221.02 frames.], batch size: 22, lr: 1.90e-04
2022-05-28 22:09:00,209 INFO [train.py:842] (3/4) Epoch 29, batch 4700, loss[loss=0.1757, simple_loss=0.2752, pruned_loss=0.03814, over 7172.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2647, pruned_loss=0.04486, over 1423741.04 frames.], batch size: 19, lr: 1.90e-04
2022-05-28 22:09:50,605 INFO [train.py:842] (3/4) Epoch 29, batch 4750, loss[loss=0.1717, simple_loss=0.2679, pruned_loss=0.03772, over 7253.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2656, pruned_loss=0.04494, over 1423291.66 frames.], batch size: 24, lr: 1.90e-04
2022-05-28 22:10:29,983 INFO [train.py:842] (3/4) Epoch 29, batch 4800, loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02999, over 7247.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2656, pruned_loss=0.04496, over 1426952.62 frames.], batch size: 19, lr: 1.90e-04
2022-05-28 22:11:09,556 INFO [train.py:842] (3/4) Epoch 29, batch 4850, loss[loss=0.1743, simple_loss=0.27, pruned_loss=0.03926, over 7240.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2654, pruned_loss=0.04455, over 1428294.65 frames.], batch size: 20, lr: 1.90e-04
2022-05-28 22:11:48,948 INFO [train.py:842] (3/4) Epoch 29, batch 4900, loss[loss=0.1706, simple_loss=0.2521, pruned_loss=0.04454, over 7076.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2645, pruned_loss=0.0439, over 1428356.14 frames.], batch size: 18, lr: 1.90e-04
2022-05-28 22:12:28,550 INFO [train.py:842] (3/4) Epoch 29, batch 4950, loss[loss=0.2009, simple_loss=0.2853, pruned_loss=0.05825, over 6305.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2646, pruned_loss=0.04397, over 1428038.73 frames.], batch size: 37, lr: 1.90e-04
2022-05-28 22:13:07,890 INFO [train.py:842] (3/4) Epoch 29, batch 5000, loss[loss=0.1836, simple_loss=0.2715, pruned_loss=0.04786, over 7384.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2656, pruned_loss=0.04464, over 1422572.94 frames.], batch size: 23, lr: 1.90e-04
2022-05-28 22:13:47,725 INFO [train.py:842] (3/4) Epoch 29, batch 5050, loss[loss=0.1214, simple_loss=0.2073, pruned_loss=0.01775, over 7284.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2644, pruned_loss=0.04402, over 1428190.75 frames.], batch size: 17, lr: 1.90e-04
2022-05-28 22:14:27,104 INFO [train.py:842] (3/4) Epoch 29, batch 5100, loss[loss=0.1464, simple_loss=0.2395, pruned_loss=0.02664, over 7134.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2628, pruned_loss=0.043, over 1429017.90 frames.], batch size: 20, lr: 1.90e-04
2022-05-28 22:15:06,701 INFO [train.py:842] (3/4) Epoch 29, batch 5150, loss[loss=0.1896, simple_loss=0.2773, pruned_loss=0.0509, over 6596.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2632, pruned_loss=0.04306, over 1430677.09 frames.], batch size: 38, lr: 1.89e-04
2022-05-28 22:15:45,844 INFO [train.py:842] (3/4) Epoch 29, batch 5200, loss[loss=0.1683, simple_loss=0.2615, pruned_loss=0.03757, over 7069.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2635, pruned_loss=0.04316, over 1429652.07 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:16:25,573 INFO [train.py:842] (3/4) Epoch 29, batch 5250, loss[loss=0.1459, simple_loss=0.234, pruned_loss=0.02889, over 7169.00 frames.], tot_loss[loss=0.175, simple_loss=0.264, pruned_loss=0.04294, over 1431153.77 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:17:04,964 INFO [train.py:842] (3/4) Epoch 29, batch 5300, loss[loss=0.1577, simple_loss=0.2481, pruned_loss=0.03368, over 7115.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2648, pruned_loss=0.04307, over 1431748.02 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:17:44,479 INFO [train.py:842] (3/4) Epoch 29, batch 5350, loss[loss=0.1488, simple_loss=0.2331, pruned_loss=0.03223, over 7285.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2634, pruned_loss=0.04293, over 1428856.66 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:18:23,827 INFO [train.py:842] (3/4) Epoch 29, batch 5400, loss[loss=0.1872, simple_loss=0.2804, pruned_loss=0.047, over 7382.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2637, pruned_loss=0.04297, over 1427571.92 frames.], batch size: 23, lr: 1.89e-04
2022-05-28 22:19:03,677 INFO [train.py:842] (3/4) Epoch 29, batch 5450, loss[loss=0.1809, simple_loss=0.2756, pruned_loss=0.04306, over 7325.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04376, over 1430216.43 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:19:42,617 INFO [train.py:842] (3/4) Epoch 29, batch 5500, loss[loss=0.2081, simple_loss=0.3145, pruned_loss=0.05081, over 7200.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2658, pruned_loss=0.04447, over 1429669.59 frames.], batch size: 22, lr: 1.89e-04
2022-05-28 22:20:22,042 INFO [train.py:842] (3/4) Epoch 29, batch 5550, loss[loss=0.1822, simple_loss=0.2764, pruned_loss=0.04406, over 5055.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04394, over 1426020.18 frames.], batch size: 52, lr: 1.89e-04
2022-05-28 22:21:01,166 INFO [train.py:842] (3/4) Epoch 29, batch 5600, loss[loss=0.1552, simple_loss=0.2407, pruned_loss=0.0348, over 7278.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2655, pruned_loss=0.04369, over 1427872.10 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:21:40,631 INFO [train.py:842] (3/4) Epoch 29, batch 5650, loss[loss=0.16, simple_loss=0.2401, pruned_loss=0.04, over 7282.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2641, pruned_loss=0.04254, over 1428638.85 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:22:19,837 INFO [train.py:842] (3/4) Epoch 29, batch 5700, loss[loss=0.1603, simple_loss=0.2528, pruned_loss=0.03384, over 6856.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2637, pruned_loss=0.04271, over 1429326.25 frames.], batch size: 32, lr: 1.89e-04
2022-05-28 22:22:59,409 INFO [train.py:842] (3/4) Epoch 29, batch 5750, loss[loss=0.1597, simple_loss=0.239, pruned_loss=0.0402, over 7280.00 frames.], tot_loss[loss=0.175, simple_loss=0.2642, pruned_loss=0.04286, over 1428597.70 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:23:38,539 INFO [train.py:842] (3/4) Epoch 29, batch 5800, loss[loss=0.1651, simple_loss=0.2555, pruned_loss=0.03735, over 7147.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2639, pruned_loss=0.04281, over 1423386.66 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:24:18,030 INFO [train.py:842] (3/4) Epoch 29, batch 5850, loss[loss=0.159, simple_loss=0.2543, pruned_loss=0.03184, over 7417.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2645, pruned_loss=0.04301, over 1420475.33 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:24:57,141 INFO [train.py:842] (3/4) Epoch 29, batch 5900, loss[loss=0.1871, simple_loss=0.2908, pruned_loss=0.04166, over 7145.00 frames.], tot_loss[loss=0.176, simple_loss=0.2649, pruned_loss=0.04357, over 1423802.33 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:25:36,557 INFO [train.py:842] (3/4) Epoch 29, batch 5950, loss[loss=0.2006, simple_loss=0.2856, pruned_loss=0.05781, over 7231.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2647, pruned_loss=0.04323, over 1420331.28 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:26:15,717 INFO [train.py:842] (3/4) Epoch 29, batch 6000, loss[loss=0.1453, simple_loss=0.2272, pruned_loss=0.03167, over 7131.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.0439, over 1419688.28 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:26:15,718 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 22:26:26,014 INFO [train.py:871] (3/4) Epoch 29, validation: loss=0.1668, simple_loss=0.2645, pruned_loss=0.03459, over 868885.00 frames.
2022-05-28 22:27:05,786 INFO [train.py:842] (3/4) Epoch 29, batch 6050, loss[loss=0.1646, simple_loss=0.2588, pruned_loss=0.0352, over 7214.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2635, pruned_loss=0.04304, over 1422552.14 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:27:44,935 INFO [train.py:842] (3/4) Epoch 29, batch 6100, loss[loss=0.2491, simple_loss=0.3147, pruned_loss=0.09174, over 7232.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2637, pruned_loss=0.0433, over 1422465.24 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:28:24,715 INFO [train.py:842] (3/4) Epoch 29, batch 6150, loss[loss=0.1376, simple_loss=0.217, pruned_loss=0.02903, over 7287.00 frames.], tot_loss[loss=0.174, simple_loss=0.2627, pruned_loss=0.04263, over 1423097.05 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:29:03,821 INFO [train.py:842] (3/4) Epoch 29, batch 6200, loss[loss=0.1709, simple_loss=0.2594, pruned_loss=0.04118, over 7422.00 frames.], tot_loss[loss=0.1746, simple_loss=0.263, pruned_loss=0.04306, over 1420028.22 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:29:43,487 INFO [train.py:842] (3/4) Epoch 29, batch 6250, loss[loss=0.1859, simple_loss=0.2798, pruned_loss=0.04602, over 7205.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2635, pruned_loss=0.0435, over 1424764.69 frames.], batch size: 22, lr: 1.89e-04
2022-05-28 22:30:22,906 INFO [train.py:842] (3/4) Epoch 29, batch 6300, loss[loss=0.1801, simple_loss=0.275, pruned_loss=0.04256, over 7324.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2639, pruned_loss=0.04385, over 1427403.30 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:31:02,425 INFO [train.py:842] (3/4) Epoch 29, batch 6350, loss[loss=0.1813, simple_loss=0.2781, pruned_loss=0.04222, over 7100.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2635, pruned_loss=0.04368, over 1426640.63 frames.], batch size: 28, lr: 1.89e-04
2022-05-28 22:31:41,481 INFO [train.py:842] (3/4) Epoch 29, batch 6400, loss[loss=0.1881, simple_loss=0.2767, pruned_loss=0.04976, over 7423.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2646, pruned_loss=0.04422, over 1423388.65 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:32:20,980 INFO [train.py:842] (3/4) Epoch 29, batch 6450, loss[loss=0.1529, simple_loss=0.2518, pruned_loss=0.027, over 7163.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2645, pruned_loss=0.0437, over 1424574.27 frames.], batch size: 19, lr: 1.89e-04
2022-05-28 22:33:00,155 INFO [train.py:842] (3/4) Epoch 29, batch 6500, loss[loss=0.1759, simple_loss=0.2704, pruned_loss=0.04072, over 7222.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2654, pruned_loss=0.0441, over 1423616.11 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:33:39,831 INFO [train.py:842] (3/4) Epoch 29, batch 6550, loss[loss=0.1732, simple_loss=0.261, pruned_loss=0.04267, over 7325.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2639, pruned_loss=0.0432, over 1423381.43 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:34:18,935 INFO [train.py:842] (3/4) Epoch 29, batch 6600, loss[loss=0.1998, simple_loss=0.285, pruned_loss=0.05736, over 7145.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2639, pruned_loss=0.0435, over 1421512.74 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:35:01,083 INFO [train.py:842] (3/4) Epoch 29, batch 6650, loss[loss=0.1651, simple_loss=0.2595, pruned_loss=0.03535, over 7370.00 frames.], tot_loss[loss=0.176, simple_loss=0.2644, pruned_loss=0.04384, over 1423227.88 frames.], batch size: 23, lr: 1.89e-04
2022-05-28 22:35:40,381 INFO [train.py:842] (3/4) Epoch 29, batch 6700, loss[loss=0.1371, simple_loss=0.2225, pruned_loss=0.02585, over 7285.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2627, pruned_loss=0.04336, over 1417629.57 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:36:19,866 INFO [train.py:842] (3/4) Epoch 29, batch 6750, loss[loss=0.1993, simple_loss=0.2916, pruned_loss=0.05349, over 7191.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2634, pruned_loss=0.04367, over 1416214.12 frames.], batch size: 23, lr: 1.89e-04
2022-05-28 22:36:58,897 INFO [train.py:842] (3/4) Epoch 29, batch 6800, loss[loss=0.1717, simple_loss=0.262, pruned_loss=0.04072, over 6704.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2634, pruned_loss=0.04342, over 1419131.72 frames.], batch size: 31, lr: 1.89e-04
2022-05-28 22:37:38,503 INFO [train.py:842] (3/4) Epoch 29, batch 6850, loss[loss=0.177, simple_loss=0.2657, pruned_loss=0.04409, over 4805.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2654, pruned_loss=0.04448, over 1415448.14 frames.], batch size: 52, lr: 1.89e-04
2022-05-28 22:38:17,546 INFO [train.py:842] (3/4) Epoch 29, batch 6900, loss[loss=0.1643, simple_loss=0.2518, pruned_loss=0.03837, over 6837.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2654, pruned_loss=0.04456, over 1418067.62 frames.], batch size: 31, lr: 1.89e-04
2022-05-28 22:38:57,140 INFO [train.py:842] (3/4) Epoch 29, batch 6950, loss[loss=0.1454, simple_loss=0.229, pruned_loss=0.03093, over 7146.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.04444, over 1417646.36 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:39:36,337 INFO [train.py:842] (3/4) Epoch 29, batch 7000, loss[loss=0.1759, simple_loss=0.2668, pruned_loss=0.0425, over 7168.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2645, pruned_loss=0.04443, over 1418338.51 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:40:15,852 INFO [train.py:842] (3/4) Epoch 29, batch 7050, loss[loss=0.1588, simple_loss=0.248, pruned_loss=0.03476, over 7056.00 frames.], tot_loss[loss=0.1759, simple_loss=0.264, pruned_loss=0.04388, over 1420602.97 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:40:54,882 INFO [train.py:842] (3/4) Epoch 29, batch 7100, loss[loss=0.1879, simple_loss=0.276, pruned_loss=0.04995, over 7214.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2657, pruned_loss=0.04456, over 1416061.25 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:41:34,452 INFO [train.py:842] (3/4) Epoch 29, batch 7150, loss[loss=0.141, simple_loss=0.2279, pruned_loss=0.02707, over 7162.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2663, pruned_loss=0.04497, over 1416280.54 frames.], batch size: 19, lr: 1.89e-04
2022-05-28 22:42:14,010 INFO [train.py:842] (3/4) Epoch 29, batch 7200, loss[loss=0.1574, simple_loss=0.2508, pruned_loss=0.03197, over 7290.00 frames.], tot_loss[loss=0.1778, simple_loss=0.266, pruned_loss=0.04478, over 1419966.82 frames.], batch size: 24, lr: 1.89e-04
2022-05-28 22:42:53,936 INFO [train.py:842] (3/4) Epoch 29, batch 7250, loss[loss=0.1634, simple_loss=0.2609, pruned_loss=0.03293, over 7218.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2649, pruned_loss=0.04481, over 1426420.60 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:43:33,139 INFO [train.py:842] (3/4) Epoch 29, batch 7300, loss[loss=0.1955, simple_loss=0.2938, pruned_loss=0.04857, over 6351.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2656, pruned_loss=0.04512, over 1428446.31 frames.], batch size: 37, lr: 1.89e-04
2022-05-28 22:44:12,680 INFO [train.py:842] (3/4) Epoch 29, batch 7350, loss[loss=0.1952, simple_loss=0.2813, pruned_loss=0.05461, over 7411.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.04426, over 1428589.72 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:44:51,856 INFO [train.py:842] (3/4) Epoch 29, batch 7400, loss[loss=0.1893, simple_loss=0.2819, pruned_loss=0.04839, over 6734.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2636, pruned_loss=0.04387, over 1426228.92 frames.], batch size: 31, lr: 1.89e-04
2022-05-28 22:45:31,644 INFO [train.py:842] (3/4) Epoch 29, batch 7450, loss[loss=0.1646, simple_loss=0.247, pruned_loss=0.04107, over 7169.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04435, over 1423695.16 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:46:10,859 INFO [train.py:842] (3/4) Epoch 29, batch 7500, loss[loss=0.1429, simple_loss=0.2286, pruned_loss=0.02858, over 7154.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2635, pruned_loss=0.04414, over 1423041.26 frames.], batch size: 17, lr: 1.89e-04
2022-05-28 22:46:50,625 INFO [train.py:842] (3/4) Epoch 29, batch 7550, loss[loss=0.1591, simple_loss=0.2511, pruned_loss=0.03349, over 7065.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2631, pruned_loss=0.04363, over 1425933.70 frames.], batch size: 18, lr: 1.89e-04
2022-05-28 22:47:29,693 INFO [train.py:842] (3/4) Epoch 29, batch 7600, loss[loss=0.1582, simple_loss=0.2515, pruned_loss=0.03239, over 7321.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2631, pruned_loss=0.04335, over 1423134.54 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:48:09,274 INFO [train.py:842] (3/4) Epoch 29, batch 7650, loss[loss=0.1538, simple_loss=0.2498, pruned_loss=0.02892, over 7311.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2636, pruned_loss=0.04382, over 1422488.01 frames.], batch size: 21, lr: 1.89e-04
2022-05-28 22:48:48,383 INFO [train.py:842] (3/4) Epoch 29, batch 7700, loss[loss=0.175, simple_loss=0.272, pruned_loss=0.03904, over 7148.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2652, pruned_loss=0.04447, over 1424034.96 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:49:27,968 INFO [train.py:842] (3/4) Epoch 29, batch 7750, loss[loss=0.1579, simple_loss=0.2503, pruned_loss=0.03273, over 7233.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2662, pruned_loss=0.04442, over 1421953.05 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:50:07,206 INFO [train.py:842] (3/4) Epoch 29, batch 7800, loss[loss=0.1879, simple_loss=0.2811, pruned_loss=0.04739, over 7136.00 frames.], tot_loss[loss=0.177, simple_loss=0.2654, pruned_loss=0.04426, over 1419622.11 frames.], batch size: 20, lr: 1.89e-04
2022-05-28 22:50:46,763 INFO [train.py:842] (3/4) Epoch 29, batch 7850, loss[loss=0.2374, simple_loss=0.3139, pruned_loss=0.08043, over 6548.00 frames.], tot_loss[loss=0.1764, simple_loss=0.265, pruned_loss=0.04383, over 1419489.31 frames.], batch size: 38, lr: 1.89e-04
2022-05-28 22:51:26,065 INFO [train.py:842] (3/4) Epoch 29, batch 7900, loss[loss=0.181, simple_loss=0.2743, pruned_loss=0.04385, over 7343.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2643, pruned_loss=0.04371, over 1420561.41 frames.], batch size: 22, lr: 1.89e-04
2022-05-28 22:52:05,561 INFO [train.py:842] (3/4) Epoch 29, batch 7950, loss[loss=0.167, simple_loss=0.2419, pruned_loss=0.04605, over 7278.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2642, pruned_loss=0.04353, over 1420371.73 frames.], batch size: 17, lr: 1.88e-04
2022-05-28 22:52:44,476 INFO [train.py:842] (3/4) Epoch 29, batch 8000, loss[loss=0.1804, simple_loss=0.2788, pruned_loss=0.04103, over 7335.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2662, pruned_loss=0.04478, over 1419074.21 frames.], batch size: 22, lr: 1.88e-04
2022-05-28 22:53:24,185 INFO [train.py:842] (3/4) Epoch 29, batch 8050, loss[loss=0.1693, simple_loss=0.2542, pruned_loss=0.04218, over 7427.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2652, pruned_loss=0.04381, over 1424721.92 frames.], batch size: 20, lr: 1.88e-04
2022-05-28 22:54:03,205 INFO [train.py:842] (3/4) Epoch 29, batch 8100, loss[loss=0.1613, simple_loss=0.2549, pruned_loss=0.03389, over 7289.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2661, pruned_loss=0.04435, over 1424950.34 frames.], batch size: 25, lr: 1.88e-04
2022-05-28 22:54:43,010 INFO [train.py:842] (3/4) Epoch 29, batch 8150, loss[loss=0.1527, simple_loss=0.2401, pruned_loss=0.03269, over 7277.00 frames.], tot_loss[loss=0.177, simple_loss=0.2652, pruned_loss=0.04441, over 1424372.70 frames.], batch size: 17, lr: 1.88e-04
2022-05-28 22:55:22,240 INFO [train.py:842] (3/4) Epoch 29, batch 8200, loss[loss=0.1542, simple_loss=0.2432, pruned_loss=0.03256, over 7234.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2645, pruned_loss=0.04418, over 1421882.27 frames.], batch size: 20, lr: 1.88e-04
2022-05-28 22:56:01,685 INFO [train.py:842] (3/4) Epoch 29, batch 8250, loss[loss=0.1749, simple_loss=0.2595, pruned_loss=0.04514, over 7160.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2632, pruned_loss=0.0432, over 1424879.26 frames.], batch size: 19, lr: 1.88e-04
2022-05-28 22:56:40,907 INFO [train.py:842] (3/4) Epoch 29, batch 8300, loss[loss=0.162, simple_loss=0.2469, pruned_loss=0.03851, over 7331.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2635, pruned_loss=0.04361, over 1425172.34 frames.], batch size: 20, lr: 1.88e-04
2022-05-28 22:57:20,362 INFO [train.py:842] (3/4) Epoch 29, batch 8350, loss[loss=0.1334, simple_loss=0.2127, pruned_loss=0.02702, over 6999.00 frames.], tot_loss[loss=0.174, simple_loss=0.2625, pruned_loss=0.04272, over 1422680.27 frames.], batch size: 16, lr: 1.88e-04
2022-05-28 22:57:59,584 INFO [train.py:842] (3/4) Epoch 29, batch 8400, loss[loss=0.1932, simple_loss=0.2786, pruned_loss=0.05391, over 7424.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2635, pruned_loss=0.04329, over 1421317.01 frames.], batch size: 20, lr: 1.88e-04
2022-05-28 22:58:38,727 INFO [train.py:842] (3/4) Epoch 29, batch 8450, loss[loss=0.2094, simple_loss=0.2976, pruned_loss=0.06056, over 7200.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2638, pruned_loss=0.04353, over 1414538.60 frames.], batch size: 23, lr: 1.88e-04
2022-05-28 22:59:17,806 INFO [train.py:842] (3/4) Epoch 29, batch 8500, loss[loss=0.1536, simple_loss=0.2434, pruned_loss=0.03195, over 7320.00 frames.], tot_loss[loss=0.1752, simple_loss=0.264, pruned_loss=0.04318, over 1418464.75 frames.], batch size: 20, lr: 1.88e-04
2022-05-28 22:59:57,410 INFO [train.py:842] (3/4) Epoch 29, batch 8550, loss[loss=0.1762, simple_loss=0.2574, pruned_loss=0.0475, over 7247.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2639, pruned_loss=0.04328, over 1419136.04 frames.], batch size: 19, lr: 1.88e-04
2022-05-28 23:00:36,799 INFO [train.py:842] (3/4) Epoch 29, batch 8600, loss[loss=0.2042, simple_loss=0.2997, pruned_loss=0.05433, over 7331.00 frames.], tot_loss[loss=0.1751, simple_loss=0.264, pruned_loss=0.04312, over 1422353.40 frames.], batch size: 21, lr: 1.88e-04
2022-05-28 23:01:16,272 INFO [train.py:842] (3/4) Epoch 29, batch 8650, loss[loss=0.1576, simple_loss=0.2369, pruned_loss=0.03916, over 6784.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2644, pruned_loss=0.04314, over 1422053.05 frames.], batch size: 15, lr: 1.88e-04
2022-05-28 23:01:55,560 INFO [train.py:842] (3/4) Epoch 29, batch 8700, loss[loss=0.1536, simple_loss=0.2391, pruned_loss=0.03404, over 7354.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2638, pruned_loss=0.04274, over 1419160.37 frames.], batch size: 19, lr: 1.88e-04
2022-05-28 23:02:35,304 INFO [train.py:842] (3/4) Epoch 29, batch 8750, loss[loss=0.2172, simple_loss=0.3094, pruned_loss=0.06251, over 7322.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2646, pruned_loss=0.04347, over 1423150.12 frames.], batch size: 25, lr: 1.88e-04
2022-05-28 23:03:14,644 INFO [train.py:842] (3/4) Epoch 29, batch 8800, loss[loss=0.1302, simple_loss=0.2134, pruned_loss=0.02346, over 6990.00 frames.], tot_loss[loss=0.175, simple_loss=0.264, pruned_loss=0.04303, over 1425382.57 frames.], batch size: 16, lr: 1.88e-04
2022-05-28 23:03:54,173 INFO [train.py:842] (3/4) Epoch 29, batch 8850, loss[loss=0.1946, simple_loss=0.2918, pruned_loss=0.04873, over 7149.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2645, pruned_loss=0.0436, over 1415326.03 frames.], batch size: 19, lr: 1.88e-04
2022-05-28 23:04:33,297 INFO [train.py:842] (3/4) Epoch 29, batch 8900, loss[loss=0.2077, simple_loss=0.2995, pruned_loss=0.05792, over 6848.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2648, pruned_loss=0.04398, over 1412921.73 frames.], batch size: 31, lr: 1.88e-04
2022-05-28 23:05:12,324 INFO [train.py:842] (3/4) Epoch 29, batch 8950, loss[loss=0.1943, simple_loss=0.2804, pruned_loss=0.05408, over 7219.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2651, pruned_loss=0.04416, over 1400354.77 frames.], batch size: 22, lr: 1.88e-04
2022-05-28 23:05:50,705 INFO [train.py:842] (3/4) Epoch 29, batch 9000, loss[loss=0.1522, simple_loss=0.2482, pruned_loss=0.02813, over 6341.00 frames.], tot_loss[loss=0.1786, simple_loss=0.267, pruned_loss=0.04513, over 1381562.03 frames.], batch size: 37, lr: 1.88e-04
2022-05-28 23:05:50,706 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 23:06:00,408 INFO [train.py:871] (3/4) Epoch 29, validation: loss=0.164, simple_loss=0.2612, pruned_loss=0.03344, over 868885.00 frames.
2022-05-28 23:06:39,664 INFO [train.py:842] (3/4) Epoch 29, batch 9050, loss[loss=0.2029, simple_loss=0.2892, pruned_loss=0.05826, over 7116.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2676, pruned_loss=0.04586, over 1364318.96 frames.], batch size: 28, lr: 1.88e-04
2022-05-28 23:07:27,907 INFO [train.py:842] (3/4) Epoch 29, batch 9100, loss[loss=0.2116, simple_loss=0.2905, pruned_loss=0.06634, over 4982.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2701, pruned_loss=0.04729, over 1313160.27 frames.], batch size: 52, lr: 1.88e-04
2022-05-28 23:08:06,154 INFO [train.py:842] (3/4) Epoch 29, batch 9150, loss[loss=0.2927, simple_loss=0.3677, pruned_loss=0.1089, over 5013.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2737, pruned_loss=0.05005, over 1245153.83 frames.], batch size: 52, lr: 1.88e-04
2022-05-28 23:08:53,873 INFO [train.py:842] (3/4) Epoch 30, batch 0, loss[loss=0.1691, simple_loss=0.2614, pruned_loss=0.03837, over 7326.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2614, pruned_loss=0.03837, over 7326.00 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:09:44,407 INFO [train.py:842] (3/4) Epoch 30, batch 50, loss[loss=0.1389, simple_loss=0.2256, pruned_loss=0.02613, over 7270.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2611, pruned_loss=0.04109, over 324135.86 frames.], batch size: 18, lr: 1.85e-04
2022-05-28 23:10:34,883 INFO [train.py:842] (3/4) Epoch 30, batch 100, loss[loss=0.1833, simple_loss=0.2623, pruned_loss=0.0522, over 7266.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2627, pruned_loss=0.04339, over 571999.26 frames.], batch size: 17, lr: 1.85e-04
2022-05-28 23:11:14,510 INFO [train.py:842] (3/4) Epoch 30, batch 150, loss[loss=0.21, simple_loss=0.2903, pruned_loss=0.06487, over 7273.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2634, pruned_loss=0.04404, over 749847.17 frames.], batch size: 24, lr: 1.85e-04
2022-05-28 23:11:53,935 INFO [train.py:842] (3/4) Epoch 30, batch 200, loss[loss=0.1415, simple_loss=0.2357, pruned_loss=0.02367, over 7356.00 frames.], tot_loss[loss=0.175, simple_loss=0.2628, pruned_loss=0.04356, over 899804.75 frames.], batch size: 19, lr: 1.85e-04
2022-05-28 23:12:33,256 INFO [train.py:842] (3/4) Epoch 30, batch 250, loss[loss=0.1524, simple_loss=0.2331, pruned_loss=0.03579, over 6863.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2647, pruned_loss=0.044, over 1015609.21 frames.], batch size: 15, lr: 1.85e-04
2022-05-28 23:13:12,490 INFO [train.py:842] (3/4) Epoch 30, batch 300, loss[loss=0.1756, simple_loss=0.2539, pruned_loss=0.0486, over 7273.00 frames.], tot_loss[loss=0.177, simple_loss=0.2655, pruned_loss=0.04427, over 1108622.72 frames.], batch size: 18, lr: 1.85e-04
2022-05-28 23:13:52,332 INFO [train.py:842] (3/4) Epoch 30, batch 350, loss[loss=0.1558, simple_loss=0.2443, pruned_loss=0.03367, over 7343.00 frames.], tot_loss[loss=0.177, simple_loss=0.2651, pruned_loss=0.04445, over 1181951.25 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:14:31,577 INFO [train.py:842] (3/4) Epoch 30, batch 400, loss[loss=0.1735, simple_loss=0.2681, pruned_loss=0.03949, over 7289.00 frames.], tot_loss[loss=0.1769, simple_loss=0.265, pruned_loss=0.04439, over 1237432.34 frames.], batch size: 24, lr: 1.85e-04
2022-05-28 23:15:11,157 INFO [train.py:842] (3/4) Epoch 30, batch 450, loss[loss=0.202, simple_loss=0.292, pruned_loss=0.05599, over 7416.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2643, pruned_loss=0.0442, over 1280277.84 frames.], batch size: 21, lr: 1.85e-04
2022-05-28 23:15:50,245 INFO [train.py:842] (3/4) Epoch 30, batch 500, loss[loss=0.1572, simple_loss=0.2534, pruned_loss=0.03048, over 7327.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.04448, over 1308238.15 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:16:29,806 INFO [train.py:842] (3/4) Epoch 30, batch 550, loss[loss=0.1891, simple_loss=0.2796, pruned_loss=0.04931, over 7280.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2653, pruned_loss=0.04479, over 1335911.43 frames.], batch size: 24, lr: 1.85e-04
2022-05-28 23:17:08,975 INFO [train.py:842] (3/4) Epoch 30, batch 600, loss[loss=0.1536, simple_loss=0.2432, pruned_loss=0.03198, over 7203.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2648, pruned_loss=0.04423, over 1351639.23 frames.], batch size: 22, lr: 1.85e-04
2022-05-28 23:17:48,549 INFO [train.py:842] (3/4) Epoch 30, batch 650, loss[loss=0.1694, simple_loss=0.2634, pruned_loss=0.03774, over 7067.00 frames.], tot_loss[loss=0.1755, simple_loss=0.264, pruned_loss=0.04345, over 1366528.75 frames.], batch size: 18, lr: 1.85e-04
2022-05-28 23:18:27,659 INFO [train.py:842] (3/4) Epoch 30, batch 700, loss[loss=0.2147, simple_loss=0.2976, pruned_loss=0.06594, over 7334.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.044, over 1374918.21 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:19:07,251 INFO [train.py:842] (3/4) Epoch 30, batch 750, loss[loss=0.1886, simple_loss=0.2708, pruned_loss=0.05323, over 7236.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2647, pruned_loss=0.04393, over 1382277.15 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:19:46,348 INFO [train.py:842] (3/4) Epoch 30, batch 800, loss[loss=0.1677, simple_loss=0.2607, pruned_loss=0.03734, over 7332.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2637, pruned_loss=0.04335, over 1388837.17 frames.], batch size: 22, lr: 1.85e-04
2022-05-28 23:20:25,960 INFO [train.py:842] (3/4) Epoch 30, batch 850, loss[loss=0.1791, simple_loss=0.2582, pruned_loss=0.04994, over 7061.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2622, pruned_loss=0.0428, over 1397920.25 frames.], batch size: 18, lr: 1.85e-04
2022-05-28 23:21:05,181 INFO [train.py:842] (3/4) Epoch 30, batch 900, loss[loss=0.1774, simple_loss=0.2681, pruned_loss=0.04334, over 7219.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2629, pruned_loss=0.04312, over 1401518.34 frames.], batch size: 21, lr: 1.85e-04
2022-05-28 23:21:44,672 INFO [train.py:842] (3/4) Epoch 30, batch 950, loss[loss=0.2122, simple_loss=0.3065, pruned_loss=0.05896, over 7103.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2647, pruned_loss=0.04415, over 1407360.28 frames.], batch size: 21, lr: 1.85e-04
2022-05-28 23:22:23,777 INFO [train.py:842] (3/4) Epoch 30, batch 1000, loss[loss=0.1441, simple_loss=0.2421, pruned_loss=0.023, over 7148.00 frames.], tot_loss[loss=0.177, simple_loss=0.2655, pruned_loss=0.04423, over 1410996.79 frames.], batch size: 20, lr: 1.85e-04
2022-05-28 23:23:03,150 INFO [train.py:842] (3/4) Epoch 30, batch 1050, loss[loss=0.1349, simple_loss=0.219, pruned_loss=0.02537, over 7270.00 frames.], tot_loss[loss=0.1775, simple_loss=0.266, pruned_loss=0.0445, over 1407815.84 frames.], batch size: 18, lr: 1.85e-04
2022-05-28 23:23:42,407 INFO [train.py:842] (3/4) Epoch 30, batch 1100, loss[loss=0.1864, simple_loss=0.268, pruned_loss=0.05244, over 7322.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2663, pruned_loss=0.04435, over 1417238.03 frames.], batch size: 21, lr: 1.85e-04
2022-05-28 23:24:21,888 INFO [train.py:842] (3/4) Epoch 30, batch 1150, loss[loss=0.203, simple_loss=0.2774, pruned_loss=0.06435, over 6996.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2658, pruned_loss=0.0439, over 1417920.68 frames.], batch size: 16, lr: 1.85e-04
2022-05-28 23:25:01,233 INFO [train.py:842] (3/4) Epoch 30, batch 1200, loss[loss=0.1698, simple_loss=0.2577, pruned_loss=0.04094, over 7170.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2655, pruned_loss=0.04374, over 1422627.71 frames.], batch size: 19, lr: 1.85e-04
2022-05-28 23:25:40,908 INFO [train.py:842] (3/4) Epoch 30, batch 1250, loss[loss=0.2307, simple_loss=0.298, pruned_loss=0.08168, over 4868.00 frames.], tot_loss[loss=0.177, simple_loss=0.2655, pruned_loss=0.04423, over 1417143.56 frames.], batch size: 53, lr: 1.84e-04
2022-05-28 23:26:20,218 INFO [train.py:842] (3/4) Epoch 30, batch 1300, loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03431, over 7328.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2652, pruned_loss=0.0441, over 1418254.44 frames.], batch size: 22, lr: 1.84e-04
2022-05-28 23:26:59,742 INFO [train.py:842] (3/4) Epoch 30, batch 1350, loss[loss=0.1746, simple_loss=0.269, pruned_loss=0.04006, over 6388.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2659, pruned_loss=0.04447, over 1419109.39 frames.], batch size: 38, lr: 1.84e-04
2022-05-28 23:27:39,232 INFO [train.py:842] (3/4) Epoch 30, batch 1400, loss[loss=0.1528, simple_loss=0.2242, pruned_loss=0.04074, over 6802.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2644, pruned_loss=0.04363, over 1419558.50 frames.], batch size: 15, lr: 1.84e-04
2022-05-28 23:28:18,752 INFO [train.py:842] (3/4) Epoch 30, batch 1450, loss[loss=0.1904, simple_loss=0.2851, pruned_loss=0.04783, over 7114.00 frames.], tot_loss[loss=0.177, simple_loss=0.2655, pruned_loss=0.04421, over 1418470.40 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:28:58,162 INFO [train.py:842] (3/4) Epoch 30, batch 1500, loss[loss=0.1323, simple_loss=0.2255, pruned_loss=0.01957, over 7242.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2661, pruned_loss=0.04444, over 1417258.86 frames.], batch size: 19, lr: 1.84e-04
2022-05-28 23:29:37,430 INFO [train.py:842] (3/4) Epoch 30, batch 1550, loss[loss=0.1927, simple_loss=0.2734, pruned_loss=0.05603, over 7191.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2656, pruned_loss=0.04403, over 1417764.01 frames.], batch size: 23, lr: 1.84e-04
2022-05-28 23:30:16,506 INFO [train.py:842] (3/4) Epoch 30, batch 1600, loss[loss=0.1786, simple_loss=0.2822, pruned_loss=0.03749, over 7318.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2663, pruned_loss=0.04395, over 1419042.41 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:30:56,233 INFO [train.py:842] (3/4) Epoch 30, batch 1650, loss[loss=0.1839, simple_loss=0.2778, pruned_loss=0.04498, over 7176.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2656, pruned_loss=0.0438, over 1423385.62 frames.], batch size: 26, lr: 1.84e-04
2022-05-28 23:31:35,535 INFO [train.py:842] (3/4) Epoch 30, batch 1700, loss[loss=0.1469, simple_loss=0.2326, pruned_loss=0.03059, over 7145.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2658, pruned_loss=0.04415, over 1426700.46 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:32:15,251 INFO [train.py:842] (3/4) Epoch 30, batch 1750, loss[loss=0.1872, simple_loss=0.2831, pruned_loss=0.04563, over 7146.00 frames.], tot_loss[loss=0.176, simple_loss=0.2648, pruned_loss=0.04362, over 1422637.99 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:32:54,402 INFO [train.py:842] (3/4) Epoch 30, batch 1800, loss[loss=0.1779, simple_loss=0.2563, pruned_loss=0.04982, over 5445.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2652, pruned_loss=0.04373, over 1420381.40 frames.], batch size: 55, lr: 1.84e-04
2022-05-28 23:33:33,943 INFO [train.py:842] (3/4) Epoch 30, batch 1850, loss[loss=0.1678, simple_loss=0.264, pruned_loss=0.03582, over 7108.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2648, pruned_loss=0.04339, over 1424951.05 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:34:13,207 INFO [train.py:842] (3/4) Epoch 30, batch 1900, loss[loss=0.1934, simple_loss=0.2674, pruned_loss=0.05966, over 6845.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2645, pruned_loss=0.04346, over 1426982.75 frames.], batch size: 15, lr: 1.84e-04
2022-05-28 23:34:52,931 INFO [train.py:842] (3/4) Epoch 30, batch 1950, loss[loss=0.15, simple_loss=0.236, pruned_loss=0.03199, over 7274.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2643, pruned_loss=0.0435, over 1428950.95 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:35:32,321 INFO [train.py:842] (3/4) Epoch 30, batch 2000, loss[loss=0.1823, simple_loss=0.2642, pruned_loss=0.05021, over 7343.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2637, pruned_loss=0.043, over 1430230.32 frames.], batch size: 22, lr: 1.84e-04
2022-05-28 23:36:11,886 INFO [train.py:842] (3/4) Epoch 30, batch 2050, loss[loss=0.2575, simple_loss=0.3378, pruned_loss=0.08861, over 7217.00 frames.], tot_loss[loss=0.175, simple_loss=0.2638, pruned_loss=0.04307, over 1430387.45 frames.], batch size: 23, lr: 1.84e-04
2022-05-28 23:36:50,960 INFO [train.py:842] (3/4) Epoch 30, batch 2100, loss[loss=0.1635, simple_loss=0.2601, pruned_loss=0.03345, over 7140.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2634, pruned_loss=0.0431, over 1429090.50 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:37:30,442 INFO [train.py:842] (3/4) Epoch 30, batch 2150, loss[loss=0.1701, simple_loss=0.2436, pruned_loss=0.04832, over 7135.00 frames.], tot_loss[loss=0.1757, simple_loss=0.264, pruned_loss=0.04374, over 1428265.52 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:38:09,548 INFO [train.py:842] (3/4) Epoch 30, batch 2200, loss[loss=0.1907, simple_loss=0.281, pruned_loss=0.05024, over 7315.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2638, pruned_loss=0.04381, over 1423185.71 frames.], batch size: 24, lr: 1.84e-04
2022-05-28 23:38:49,029 INFO [train.py:842] (3/4) Epoch 30, batch 2250, loss[loss=0.2128, simple_loss=0.3051, pruned_loss=0.06028, over 7162.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2647, pruned_loss=0.0444, over 1421991.22 frames.], batch size: 26, lr: 1.84e-04
2022-05-28 23:39:28,072 INFO [train.py:842] (3/4) Epoch 30, batch 2300, loss[loss=0.1455, simple_loss=0.2359, pruned_loss=0.02756, over 7325.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2647, pruned_loss=0.04435, over 1418994.67 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:40:07,923 INFO [train.py:842] (3/4) Epoch 30, batch 2350, loss[loss=0.1616, simple_loss=0.2589, pruned_loss=0.03212, over 7333.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2649, pruned_loss=0.04438, over 1420838.40 frames.], batch size: 22, lr: 1.84e-04
2022-05-28 23:40:47,275 INFO [train.py:842] (3/4) Epoch 30, batch 2400, loss[loss=0.1921, simple_loss=0.2739, pruned_loss=0.0552, over 7286.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2646, pruned_loss=0.0439, over 1422068.50 frames.], batch size: 25, lr: 1.84e-04
2022-05-28 23:41:27,101 INFO [train.py:842] (3/4) Epoch 30, batch 2450, loss[loss=0.1585, simple_loss=0.2527, pruned_loss=0.03216, over 7137.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2628, pruned_loss=0.04279, over 1425966.83 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:42:06,586 INFO [train.py:842] (3/4) Epoch 30, batch 2500, loss[loss=0.1271, simple_loss=0.2136, pruned_loss=0.02028, over 7209.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04261, over 1430471.21 frames.], batch size: 16, lr: 1.84e-04
2022-05-28 23:42:46,107 INFO [train.py:842] (3/4) Epoch 30, batch 2550, loss[loss=0.1567, simple_loss=0.2387, pruned_loss=0.03736, over 7398.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04244, over 1427023.87 frames.], batch size: 18, lr: 1.84e-04
2022-05-28 23:43:25,274 INFO [train.py:842] (3/4) Epoch 30, batch 2600, loss[loss=0.1696, simple_loss=0.2608, pruned_loss=0.03925, over 7112.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2625, pruned_loss=0.04324, over 1426442.03 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:44:04,905 INFO [train.py:842] (3/4) Epoch 30, batch 2650, loss[loss=0.1321, simple_loss=0.2247, pruned_loss=0.01971, over 7141.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2636, pruned_loss=0.04368, over 1428269.92 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:44:44,023 INFO [train.py:842] (3/4) Epoch 30, batch 2700, loss[loss=0.2447, simple_loss=0.3336, pruned_loss=0.07788, over 7115.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2654, pruned_loss=0.04463, over 1428727.76 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:45:23,609 INFO [train.py:842] (3/4) Epoch 30, batch 2750, loss[loss=0.1553, simple_loss=0.2507, pruned_loss=0.02993, over 7239.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2662, pruned_loss=0.04502, over 1424312.61 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:46:02,918 INFO [train.py:842] (3/4) Epoch 30, batch 2800, loss[loss=0.1636, simple_loss=0.2662, pruned_loss=0.03054, over 7329.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2645, pruned_loss=0.04359, over 1423574.91 frames.], batch size: 22, lr: 1.84e-04
2022-05-28 23:46:42,635 INFO [train.py:842] (3/4) Epoch 30, batch 2850, loss[loss=0.1654, simple_loss=0.2597, pruned_loss=0.03555, over 7239.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2634, pruned_loss=0.04306, over 1417515.19 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:47:21,863 INFO [train.py:842] (3/4) Epoch 30, batch 2900, loss[loss=0.1594, simple_loss=0.2516, pruned_loss=0.03359, over 7002.00 frames.], tot_loss[loss=0.174, simple_loss=0.2623, pruned_loss=0.04283, over 1420246.01 frames.], batch size: 16, lr: 1.84e-04
2022-05-28 23:48:01,442 INFO [train.py:842] (3/4) Epoch 30, batch 2950, loss[loss=0.2013, simple_loss=0.2929, pruned_loss=0.05483, over 6363.00 frames.], tot_loss[loss=0.1737, simple_loss=0.262, pruned_loss=0.0427, over 1421083.33 frames.], batch size: 38, lr: 1.84e-04
2022-05-28 23:48:40,735 INFO [train.py:842] (3/4) Epoch 30, batch 3000, loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03058, over 7122.00 frames.], tot_loss[loss=0.174, simple_loss=0.2624, pruned_loss=0.04277, over 1423597.70 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:48:40,736 INFO [train.py:862] (3/4) Computing validation loss
2022-05-28 23:48:50,532 INFO [train.py:871] (3/4) Epoch 30, validation: loss=0.1622, simple_loss=0.26, pruned_loss=0.03222, over 868885.00 frames.
2022-05-28 23:49:30,135 INFO [train.py:842] (3/4) Epoch 30, batch 3050, loss[loss=0.1812, simple_loss=0.2719, pruned_loss=0.04529, over 7108.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2632, pruned_loss=0.04291, over 1425704.88 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:50:09,349 INFO [train.py:842] (3/4) Epoch 30, batch 3100, loss[loss=0.1654, simple_loss=0.2528, pruned_loss=0.03895, over 7405.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2635, pruned_loss=0.0431, over 1426433.48 frames.], batch size: 21, lr: 1.84e-04
2022-05-28 23:50:48,884 INFO [train.py:842] (3/4) Epoch 30, batch 3150, loss[loss=0.1598, simple_loss=0.2462, pruned_loss=0.03668, over 7168.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2632, pruned_loss=0.04349, over 1421998.40 frames.], batch size: 18, lr: 1.84e-04
2022-05-28 23:51:28,430 INFO [train.py:842] (3/4) Epoch 30, batch 3200, loss[loss=0.1591, simple_loss=0.25, pruned_loss=0.03409, over 7257.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2617, pruned_loss=0.04287, over 1424822.23 frames.], batch size: 19, lr: 1.84e-04
2022-05-28 23:52:08,010 INFO [train.py:842] (3/4) Epoch 30, batch 3250, loss[loss=0.1931, simple_loss=0.2825, pruned_loss=0.05189, over 7086.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2622, pruned_loss=0.04278, over 1420144.78 frames.], batch size: 28, lr: 1.84e-04
2022-05-28 23:52:47,277 INFO [train.py:842] (3/4) Epoch 30, batch 3300, loss[loss=0.1681, simple_loss=0.2537, pruned_loss=0.04128, over 7329.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2629, pruned_loss=0.04292, over 1423132.57 frames.], batch size: 20, lr: 1.84e-04
2022-05-28 23:53:26,892 INFO [train.py:842] (3/4) Epoch 30, batch 3350, loss[loss=0.1433, simple_loss=0.2208, pruned_loss=0.03288, over 7279.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2624, pruned_loss=0.04289, over 1427474.99 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:54:06,114 INFO [train.py:842] (3/4) Epoch 30, batch 3400, loss[loss=0.1844, simple_loss=0.2697, pruned_loss=0.0496, over 4923.00 frames.], tot_loss[loss=0.1746, simple_loss=0.263, pruned_loss=0.0431, over 1424018.93 frames.], batch size: 53, lr: 1.84e-04
2022-05-28 23:54:45,903 INFO [train.py:842] (3/4) Epoch 30, batch 3450, loss[loss=0.1874, simple_loss=0.2709, pruned_loss=0.05194, over 7308.00 frames.], tot_loss[loss=0.1737, simple_loss=0.262, pruned_loss=0.04268, over 1421016.16 frames.], batch size: 24, lr: 1.84e-04
2022-05-28 23:55:25,198 INFO [train.py:842] (3/4) Epoch 30, batch 3500, loss[loss=0.1638, simple_loss=0.2626, pruned_loss=0.03247, over 7227.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2623, pruned_loss=0.04256, over 1422909.30 frames.], batch size: 26, lr: 1.84e-04
2022-05-28 23:56:04,854 INFO [train.py:842] (3/4) Epoch 30, batch 3550, loss[loss=0.1769, simple_loss=0.2604, pruned_loss=0.04673, over 7181.00 frames.], tot_loss[loss=0.1736, simple_loss=0.262, pruned_loss=0.04258, over 1422689.87 frames.], batch size: 18, lr: 1.84e-04
2022-05-28 23:56:44,229 INFO [train.py:842] (3/4) Epoch 30, batch 3600, loss[loss=0.1679, simple_loss=0.2516, pruned_loss=0.04212, over 7270.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2614, pruned_loss=0.04219, over 1427343.66 frames.], batch size: 19, lr: 1.84e-04
2022-05-28 23:57:23,888 INFO [train.py:842] (3/4) Epoch 30, batch 3650, loss[loss=0.1688, simple_loss=0.2528, pruned_loss=0.04245, over 6866.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04214, over 1429089.25 frames.], batch size: 31, lr: 1.84e-04
2022-05-28 23:58:03,139 INFO [train.py:842] (3/4) Epoch 30, batch 3700, loss[loss=0.148, simple_loss=0.2337, pruned_loss=0.03111, over 7273.00 frames.], tot_loss[loss=0.1735, simple_loss=0.262, pruned_loss=0.0425, over 1429681.27 frames.], batch size: 17, lr: 1.84e-04
2022-05-28 23:58:42,918 INFO [train.py:842] (3/4) Epoch 30, batch 3750, loss[loss=0.19, simple_loss=0.2715, pruned_loss=0.0543, over 7113.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2623, pruned_loss=0.04255, over 1432519.26 frames.], batch size: 28, lr: 1.84e-04
2022-05-28 23:59:21,926 INFO [train.py:842] (3/4) Epoch 30, batch 3800, loss[loss=0.1689, simple_loss=0.2551, pruned_loss=0.04129, over 7214.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2643, pruned_loss=0.04345, over 1425107.96 frames.], batch size: 22, lr: 1.84e-04
2022-05-29 00:00:01,403 INFO [train.py:842] (3/4) Epoch 30, batch 3850, loss[loss=0.1972, simple_loss=0.2919, pruned_loss=0.05128, over 7210.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2637, pruned_loss=0.04264, over 1427284.31 frames.], batch size: 22, lr: 1.84e-04
2022-05-29 00:00:40,351 INFO [train.py:842] (3/4) Epoch 30, batch 3900, loss[loss=0.2009, simple_loss=0.2827, pruned_loss=0.05958, over 7217.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2651, pruned_loss=0.04341, over 1427113.96 frames.], batch size: 21, lr: 1.84e-04
2022-05-29 00:01:19,901 INFO [train.py:842] (3/4) Epoch 30, batch 3950, loss[loss=0.1871, simple_loss=0.2692, pruned_loss=0.05252, over 7347.00 frames.], tot_loss[loss=0.1762, simple_loss=0.265, pruned_loss=0.04371, over 1425846.85 frames.], batch size: 19, lr: 1.84e-04
2022-05-29 00:01:59,034 INFO [train.py:842] (3/4) Epoch 30, batch 4000, loss[loss=0.1566, simple_loss=0.2427, pruned_loss=0.03527, over 7152.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2647, pruned_loss=0.04352, over 1422771.42 frames.], batch size: 18, lr: 1.84e-04
2022-05-29 00:02:38,734 INFO [train.py:842] (3/4) Epoch 30, batch 4050, loss[loss=0.1765, simple_loss=0.2784, pruned_loss=0.03726, over 7308.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2648, pruned_loss=0.04382, over 1422960.20 frames.], batch size: 24, lr: 1.84e-04
2022-05-29 00:03:17,906 INFO [train.py:842] (3/4) Epoch 30, batch 4100, loss[loss=0.1501, simple_loss=0.2477, pruned_loss=0.02626, over 7220.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2649, pruned_loss=0.0444, over 1422221.24 frames.], batch size: 21, lr: 1.84e-04
2022-05-29 00:03:57,523 INFO [train.py:842] (3/4) Epoch 30, batch 4150, loss[loss=0.1658, simple_loss=0.258, pruned_loss=0.03682, over 7277.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2649, pruned_loss=0.04404, over 1425955.30 frames.], batch size: 18, lr: 1.84e-04
2022-05-29 00:04:36,804 INFO [train.py:842] (3/4) Epoch 30, batch 4200, loss[loss=0.1956, simple_loss=0.2872, pruned_loss=0.05198, over 7370.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2636, pruned_loss=0.0434, over 1427987.26 frames.], batch size: 23, lr: 1.83e-04
2022-05-29 00:05:16,544 INFO [train.py:842] (3/4) Epoch 30, batch 4250, loss[loss=0.1833, simple_loss=0.2719, pruned_loss=0.04737, over 7123.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2635, pruned_loss=0.04354, over 1428078.44 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:05:55,557 INFO [train.py:842] (3/4) Epoch 30, batch 4300, loss[loss=0.1814, simple_loss=0.2726, pruned_loss=0.04507, over 7320.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2649, pruned_loss=0.04421, over 1427900.63 frames.], batch size: 25, lr: 1.83e-04
2022-05-29 00:06:35,232 INFO [train.py:842] (3/4) Epoch 30, batch 4350, loss[loss=0.1565, simple_loss=0.238, pruned_loss=0.03756, over 6991.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2653, pruned_loss=0.04469, over 1426359.46 frames.], batch size: 16, lr: 1.83e-04
2022-05-29 00:07:14,651 INFO [train.py:842] (3/4) Epoch 30, batch 4400, loss[loss=0.1615, simple_loss=0.2483, pruned_loss=0.03732, over 7431.00 frames.], tot_loss[loss=0.1766, simple_loss=0.265, pruned_loss=0.04414, over 1429588.84 frames.], batch size: 20, lr: 1.83e-04
2022-05-29 00:07:54,186 INFO [train.py:842] (3/4) Epoch 30, batch 4450, loss[loss=0.2048, simple_loss=0.2839, pruned_loss=0.0628, over 7151.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2643, pruned_loss=0.04365, over 1429091.82 frames.], batch size: 26, lr: 1.83e-04
2022-05-29 00:08:33,360 INFO [train.py:842] (3/4) Epoch 30, batch 4500, loss[loss=0.1913, simple_loss=0.2805, pruned_loss=0.05109, over 7324.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2642, pruned_loss=0.04371, over 1425993.65 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:09:13,168 INFO [train.py:842] (3/4) Epoch 30, batch 4550, loss[loss=0.1938, simple_loss=0.2707, pruned_loss=0.05845, over 7423.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2639, pruned_loss=0.04393, over 1428693.77 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:09:52,420 INFO [train.py:842] (3/4) Epoch 30, batch 4600, loss[loss=0.2007, simple_loss=0.2821, pruned_loss=0.05966, over 7203.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2636, pruned_loss=0.0434, over 1425546.65 frames.], batch size: 22, lr: 1.83e-04
2022-05-29 00:10:32,204 INFO [train.py:842] (3/4) Epoch 30, batch 4650, loss[loss=0.1626, simple_loss=0.2498, pruned_loss=0.03775, over 6757.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2642, pruned_loss=0.04352, over 1426086.01 frames.], batch size: 31, lr: 1.83e-04
2022-05-29 00:11:11,568 INFO [train.py:842] (3/4) Epoch 30, batch 4700, loss[loss=0.1939, simple_loss=0.2875, pruned_loss=0.05011, over 7294.00 frames.], tot_loss[loss=0.174, simple_loss=0.263, pruned_loss=0.0425, over 1428219.76 frames.], batch size: 24, lr: 1.83e-04
2022-05-29 00:11:51,340 INFO [train.py:842] (3/4) Epoch 30, batch 4750, loss[loss=0.1819, simple_loss=0.2642, pruned_loss=0.04977, over 7153.00 frames.], tot_loss[loss=0.176, simple_loss=0.2646, pruned_loss=0.04373, over 1428697.42 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:12:30,801 INFO [train.py:842] (3/4) Epoch 30, batch 4800, loss[loss=0.1704, simple_loss=0.2653, pruned_loss=0.03775, over 7354.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2655, pruned_loss=0.04402, over 1429833.87 frames.], batch size: 23, lr: 1.83e-04
2022-05-29 00:13:10,339 INFO [train.py:842] (3/4) Epoch 30, batch 4850, loss[loss=0.1378, simple_loss=0.2292, pruned_loss=0.02321, over 7218.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2655, pruned_loss=0.04398, over 1428795.83 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:13:49,482 INFO [train.py:842] (3/4) Epoch 30, batch 4900, loss[loss=0.1438, simple_loss=0.2308, pruned_loss=0.02844, over 7415.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2655, pruned_loss=0.04395, over 1427613.16 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:14:29,097 INFO [train.py:842] (3/4) Epoch 30, batch 4950, loss[loss=0.2118, simple_loss=0.2959, pruned_loss=0.06386, over 7303.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2666, pruned_loss=0.04427, over 1423052.51 frames.], batch size: 24, lr: 1.83e-04
2022-05-29 00:15:08,322 INFO [train.py:842] (3/4) Epoch 30, batch 5000, loss[loss=0.1586, simple_loss=0.2422, pruned_loss=0.03752, over 7208.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2653, pruned_loss=0.04382, over 1424124.13 frames.], batch size: 16, lr: 1.83e-04
2022-05-29 00:15:47,593 INFO [train.py:842] (3/4) Epoch 30, batch 5050, loss[loss=0.1808, simple_loss=0.2732, pruned_loss=0.04417, over 7099.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2662, pruned_loss=0.04417, over 1418903.89 frames.], batch size: 28, lr: 1.83e-04
2022-05-29 00:16:27,105 INFO [train.py:842] (3/4) Epoch 30, batch 5100, loss[loss=0.1479, simple_loss=0.2368, pruned_loss=0.02955, over 7233.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2646, pruned_loss=0.04374, over 1416909.26 frames.], batch size: 16, lr: 1.83e-04
2022-05-29 00:17:06,616 INFO [train.py:842] (3/4) Epoch 30, batch 5150, loss[loss=0.196, simple_loss=0.2817, pruned_loss=0.05518, over 7278.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2659, pruned_loss=0.04492, over 1413220.76 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:17:45,818 INFO [train.py:842] (3/4) Epoch 30, batch 5200, loss[loss=0.1884, simple_loss=0.2732, pruned_loss=0.05179, over 7377.00 frames.], tot_loss[loss=0.177, simple_loss=0.265, pruned_loss=0.0445, over 1417637.24 frames.], batch size: 23, lr: 1.83e-04
2022-05-29 00:18:25,607 INFO [train.py:842] (3/4) Epoch 30, batch 5250, loss[loss=0.1785, simple_loss=0.2608, pruned_loss=0.0481, over 7321.00 frames.], tot_loss[loss=0.1759, simple_loss=0.264, pruned_loss=0.04388, over 1420456.22 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:19:04,595 INFO [train.py:842] (3/4) Epoch 30, batch 5300, loss[loss=0.1937, simple_loss=0.2699, pruned_loss=0.05878, over 7160.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2656, pruned_loss=0.04442, over 1422078.34 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:19:44,232 INFO [train.py:842] (3/4) Epoch 30, batch 5350, loss[loss=0.1459, simple_loss=0.2332, pruned_loss=0.02931, over 7158.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2654, pruned_loss=0.04442, over 1424759.02 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:20:23,305 INFO [train.py:842] (3/4) Epoch 30, batch 5400, loss[loss=0.1975, simple_loss=0.2746, pruned_loss=0.06024, over 7148.00 frames.], tot_loss[loss=0.177, simple_loss=0.2651, pruned_loss=0.04451, over 1423885.32 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:21:05,458 INFO [train.py:842] (3/4) Epoch 30, batch 5450, loss[loss=0.1689, simple_loss=0.2565, pruned_loss=0.04065, over 7260.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2658, pruned_loss=0.04424, over 1424326.30 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:21:44,401 INFO [train.py:842] (3/4) Epoch 30, batch 5500, loss[loss=0.2064, simple_loss=0.2844, pruned_loss=0.06417, over 7411.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2657, pruned_loss=0.04452, over 1423370.11 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:22:23,777 INFO [train.py:842] (3/4) Epoch 30, batch 5550, loss[loss=0.1535, simple_loss=0.2474, pruned_loss=0.0298, over 7320.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2664, pruned_loss=0.04468, over 1420963.32 frames.], batch size: 20, lr: 1.83e-04
2022-05-29 00:23:02,856 INFO [train.py:842] (3/4) Epoch 30, batch 5600, loss[loss=0.1752, simple_loss=0.2625, pruned_loss=0.04394, over 7365.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2662, pruned_loss=0.04482, over 1410306.92 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:23:42,338 INFO [train.py:842] (3/4) Epoch 30, batch 5650, loss[loss=0.2052, simple_loss=0.2882, pruned_loss=0.06109, over 7351.00 frames.], tot_loss[loss=0.1775, simple_loss=0.266, pruned_loss=0.04449, over 1409959.35 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:24:21,761 INFO [train.py:842] (3/4) Epoch 30, batch 5700, loss[loss=0.1712, simple_loss=0.2534, pruned_loss=0.04448, over 6989.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2643, pruned_loss=0.04391, over 1417058.76 frames.], batch size: 16, lr: 1.83e-04
2022-05-29 00:25:01,292 INFO [train.py:842] (3/4) Epoch 30, batch 5750, loss[loss=0.2074, simple_loss=0.3075, pruned_loss=0.05369, over 7278.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2641, pruned_loss=0.04386, over 1420525.64 frames.], batch size: 24, lr: 1.83e-04
2022-05-29 00:25:40,650 INFO [train.py:842] (3/4) Epoch 30, batch 5800, loss[loss=0.1541, simple_loss=0.2395, pruned_loss=0.03438, over 7439.00 frames.], tot_loss[loss=0.175, simple_loss=0.2635, pruned_loss=0.04328, over 1421393.81 frames.], batch size: 20, lr: 1.83e-04
2022-05-29 00:26:19,845 INFO [train.py:842] (3/4) Epoch 30, batch 5850, loss[loss=0.1836, simple_loss=0.2609, pruned_loss=0.05317, over 7078.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2643, pruned_loss=0.04362, over 1421352.77 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:26:59,097 INFO [train.py:842] (3/4) Epoch 30, batch 5900, loss[loss=0.2123, simple_loss=0.2973, pruned_loss=0.06366, over 7155.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2637, pruned_loss=0.04334, over 1422817.05 frames.], batch size: 20, lr: 1.83e-04
2022-05-29 00:27:38,798 INFO [train.py:842] (3/4) Epoch 30, batch 5950, loss[loss=0.1719, simple_loss=0.2569, pruned_loss=0.04345, over 7124.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2641, pruned_loss=0.04367, over 1426737.71 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:28:18,041 INFO [train.py:842] (3/4) Epoch 30, batch 6000, loss[loss=0.1682, simple_loss=0.2628, pruned_loss=0.03677, over 7422.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2636, pruned_loss=0.04349, over 1425213.43 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:28:18,043 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 00:28:27,764 INFO [train.py:871] (3/4) Epoch 30, validation: loss=0.1626, simple_loss=0.2605, pruned_loss=0.03232, over 868885.00 frames.
2022-05-29 00:29:07,511 INFO [train.py:842] (3/4) Epoch 30, batch 6050, loss[loss=0.1605, simple_loss=0.2358, pruned_loss=0.04255, over 7159.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2641, pruned_loss=0.04378, over 1424968.76 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:29:46,804 INFO [train.py:842] (3/4) Epoch 30, batch 6100, loss[loss=0.1476, simple_loss=0.225, pruned_loss=0.03511, over 7064.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2645, pruned_loss=0.04414, over 1423132.64 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:30:26,357 INFO [train.py:842] (3/4) Epoch 30, batch 6150, loss[loss=0.1648, simple_loss=0.2482, pruned_loss=0.04072, over 7367.00 frames.], tot_loss[loss=0.176, simple_loss=0.2644, pruned_loss=0.04383, over 1420458.56 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:31:05,522 INFO [train.py:842] (3/4) Epoch 30, batch 6200, loss[loss=0.1904, simple_loss=0.2676, pruned_loss=0.05661, over 7277.00 frames.], tot_loss[loss=0.1754, simple_loss=0.264, pruned_loss=0.04346, over 1420044.20 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:31:45,362 INFO [train.py:842] (3/4) Epoch 30, batch 6250, loss[loss=0.1512, simple_loss=0.244, pruned_loss=0.02917, over 7152.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2635, pruned_loss=0.043, over 1422342.85 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:32:24,489 INFO [train.py:842] (3/4) Epoch 30, batch 6300, loss[loss=0.1438, simple_loss=0.2452, pruned_loss=0.02123, over 6808.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2632, pruned_loss=0.04249, over 1426712.91 frames.], batch size: 31, lr: 1.83e-04
2022-05-29 00:33:03,725 INFO [train.py:842] (3/4) Epoch 30, batch 6350, loss[loss=0.1453, simple_loss=0.2321, pruned_loss=0.02927, over 7280.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2655, pruned_loss=0.04378, over 1426383.66 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:33:42,844 INFO [train.py:842] (3/4) Epoch 30, batch 6400, loss[loss=0.1367, simple_loss=0.2252, pruned_loss=0.02407, over 7130.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2655, pruned_loss=0.04388, over 1424018.03 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:34:22,398 INFO [train.py:842] (3/4) Epoch 30, batch 6450, loss[loss=0.1882, simple_loss=0.2687, pruned_loss=0.05383, over 7278.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2656, pruned_loss=0.04403, over 1425487.18 frames.], batch size: 24, lr: 1.83e-04
2022-05-29 00:35:01,383 INFO [train.py:842] (3/4) Epoch 30, batch 6500, loss[loss=0.2204, simple_loss=0.3144, pruned_loss=0.06324, over 7280.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2653, pruned_loss=0.04348, over 1426595.69 frames.], batch size: 24, lr: 1.83e-04
2022-05-29 00:35:41,140 INFO [train.py:842] (3/4) Epoch 30, batch 6550, loss[loss=0.1713, simple_loss=0.2674, pruned_loss=0.03762, over 7422.00 frames.], tot_loss[loss=0.176, simple_loss=0.2646, pruned_loss=0.04367, over 1425283.84 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:36:20,423 INFO [train.py:842] (3/4) Epoch 30, batch 6600, loss[loss=0.1524, simple_loss=0.2361, pruned_loss=0.03434, over 7411.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2648, pruned_loss=0.04396, over 1427016.79 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:37:00,149 INFO [train.py:842] (3/4) Epoch 30, batch 6650, loss[loss=0.1661, simple_loss=0.2573, pruned_loss=0.03745, over 7161.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2633, pruned_loss=0.04312, over 1425967.04 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:37:39,121 INFO [train.py:842] (3/4) Epoch 30, batch 6700, loss[loss=0.1405, simple_loss=0.2298, pruned_loss=0.0256, over 7291.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2632, pruned_loss=0.0432, over 1422586.17 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:38:18,808 INFO [train.py:842] (3/4) Epoch 30, batch 6750, loss[loss=0.1468, simple_loss=0.2329, pruned_loss=0.03038, over 7392.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2616, pruned_loss=0.04264, over 1424449.61 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:38:57,959 INFO [train.py:842] (3/4) Epoch 30, batch 6800, loss[loss=0.1752, simple_loss=0.2587, pruned_loss=0.04584, over 7319.00 frames.], tot_loss[loss=0.174, simple_loss=0.2626, pruned_loss=0.04269, over 1424879.31 frames.], batch size: 25, lr: 1.83e-04
2022-05-29 00:39:37,551 INFO [train.py:842] (3/4) Epoch 30, batch 6850, loss[loss=0.2269, simple_loss=0.3116, pruned_loss=0.07111, over 7201.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2631, pruned_loss=0.04287, over 1425237.94 frames.], batch size: 22, lr: 1.83e-04
2022-05-29 00:40:16,991 INFO [train.py:842] (3/4) Epoch 30, batch 6900, loss[loss=0.1323, simple_loss=0.2098, pruned_loss=0.0274, over 7277.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.04265, over 1423810.39 frames.], batch size: 17, lr: 1.83e-04
2022-05-29 00:40:56,514 INFO [train.py:842] (3/4) Epoch 30, batch 6950, loss[loss=0.1468, simple_loss=0.2277, pruned_loss=0.03299, over 7069.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2641, pruned_loss=0.04359, over 1420886.12 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:41:35,820 INFO [train.py:842] (3/4) Epoch 30, batch 7000, loss[loss=0.1674, simple_loss=0.2591, pruned_loss=0.03782, over 7255.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2643, pruned_loss=0.04371, over 1421072.93 frames.], batch size: 19, lr: 1.83e-04
2022-05-29 00:42:15,300 INFO [train.py:842] (3/4) Epoch 30, batch 7050, loss[loss=0.198, simple_loss=0.2992, pruned_loss=0.0484, over 7324.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2647, pruned_loss=0.04348, over 1420659.31 frames.], batch size: 21, lr: 1.83e-04
2022-05-29 00:42:54,739 INFO [train.py:842] (3/4) Epoch 30, batch 7100, loss[loss=0.1469, simple_loss=0.2369, pruned_loss=0.02841, over 7425.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2645, pruned_loss=0.04383, over 1417056.11 frames.], batch size: 18, lr: 1.83e-04
2022-05-29 00:43:34,112 INFO [train.py:842] (3/4) Epoch 30, batch 7150, loss[loss=0.1692, simple_loss=0.2595, pruned_loss=0.03944, over 7195.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2639, pruned_loss=0.04356, over 1417932.21 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 00:44:13,162 INFO [train.py:842] (3/4) Epoch 30, batch 7200, loss[loss=0.1732, simple_loss=0.2811, pruned_loss=0.03268, over 7123.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2641, pruned_loss=0.04391, over 1416137.54 frames.], batch size: 21, lr: 1.82e-04
2022-05-29 00:44:52,848 INFO [train.py:842] (3/4) Epoch 30, batch 7250, loss[loss=0.1783, simple_loss=0.2822, pruned_loss=0.03724, over 7343.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2635, pruned_loss=0.04346, over 1417622.34 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 00:45:32,258 INFO [train.py:842] (3/4) Epoch 30, batch 7300, loss[loss=0.1462, simple_loss=0.2316, pruned_loss=0.03046, over 7064.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2619, pruned_loss=0.04257, over 1420623.03 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 00:46:12,045 INFO [train.py:842] (3/4) Epoch 30, batch 7350, loss[loss=0.1519, simple_loss=0.243, pruned_loss=0.03042, over 7110.00 frames.], tot_loss[loss=0.173, simple_loss=0.2614, pruned_loss=0.04228, over 1422870.89 frames.], batch size: 28, lr: 1.82e-04
2022-05-29 00:47:02,179 INFO [train.py:842] (3/4) Epoch 30, batch 7400, loss[loss=0.1708, simple_loss=0.267, pruned_loss=0.03733, over 6898.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2609, pruned_loss=0.04216, over 1422260.53 frames.], batch size: 32, lr: 1.82e-04
2022-05-29 00:47:41,633 INFO [train.py:842] (3/4) Epoch 30, batch 7450, loss[loss=0.2492, simple_loss=0.3252, pruned_loss=0.0866, over 7311.00 frames.], tot_loss[loss=0.174, simple_loss=0.2623, pruned_loss=0.0428, over 1427213.14 frames.], batch size: 21, lr: 1.82e-04
2022-05-29 00:48:20,892 INFO [train.py:842] (3/4) Epoch 30, batch 7500, loss[loss=0.1588, simple_loss=0.25, pruned_loss=0.03378, over 7068.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2633, pruned_loss=0.04316, over 1426547.16 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 00:49:00,508 INFO [train.py:842] (3/4) Epoch 30, batch 7550, loss[loss=0.1716, simple_loss=0.2493, pruned_loss=0.04693, over 7148.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2633, pruned_loss=0.04298, over 1423651.01 frames.], batch size: 19, lr: 1.82e-04
2022-05-29 00:49:39,623 INFO [train.py:842] (3/4) Epoch 30, batch 7600, loss[loss=0.15, simple_loss=0.2477, pruned_loss=0.02618, over 7320.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2638, pruned_loss=0.04319, over 1423088.99 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 00:50:19,173 INFO [train.py:842] (3/4) Epoch 30, batch 7650, loss[loss=0.1621, simple_loss=0.2598, pruned_loss=0.03223, over 7236.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2641, pruned_loss=0.0436, over 1422360.84 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 00:50:58,430 INFO [train.py:842] (3/4) Epoch 30, batch 7700, loss[loss=0.2803, simple_loss=0.359, pruned_loss=0.1008, over 7300.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2643, pruned_loss=0.04391, over 1419638.23 frames.], batch size: 25, lr: 1.82e-04
2022-05-29 00:51:38,124 INFO [train.py:842] (3/4) Epoch 30, batch 7750, loss[loss=0.1974, simple_loss=0.2746, pruned_loss=0.06013, over 7357.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2648, pruned_loss=0.04409, over 1419637.02 frames.], batch size: 19, lr: 1.82e-04
2022-05-29 00:52:17,441 INFO [train.py:842] (3/4) Epoch 30, batch 7800, loss[loss=0.1637, simple_loss=0.2488, pruned_loss=0.03928, over 7069.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2646, pruned_loss=0.04404, over 1421753.57 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 00:52:57,223 INFO [train.py:842] (3/4) Epoch 30, batch 7850, loss[loss=0.1664, simple_loss=0.2492, pruned_loss=0.0418, over 6814.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2639, pruned_loss=0.04365, over 1426491.47 frames.], batch size: 15, lr: 1.82e-04
2022-05-29 00:53:36,712 INFO [train.py:842] (3/4) Epoch 30, batch 7900, loss[loss=0.1888, simple_loss=0.284, pruned_loss=0.04678, over 7319.00 frames.], tot_loss[loss=0.175, simple_loss=0.2629, pruned_loss=0.04352, over 1423123.08 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 00:54:16,409 INFO [train.py:842] (3/4) Epoch 30, batch 7950, loss[loss=0.1713, simple_loss=0.2582, pruned_loss=0.0422, over 7153.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2618, pruned_loss=0.04329, over 1422641.23 frames.], batch size: 19, lr: 1.82e-04
2022-05-29 00:54:55,589 INFO [train.py:842] (3/4) Epoch 30, batch 8000, loss[loss=0.1608, simple_loss=0.2623, pruned_loss=0.02965, over 7206.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2631, pruned_loss=0.04402, over 1424516.20 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 00:55:35,098 INFO [train.py:842] (3/4) Epoch 30, batch 8050, loss[loss=0.1858, simple_loss=0.2767, pruned_loss=0.04749, over 7245.00 frames.], tot_loss[loss=0.1731, simple_loss=0.261, pruned_loss=0.04255, over 1428172.96 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 00:56:14,424 INFO [train.py:842] (3/4) Epoch 30, batch 8100, loss[loss=0.2155, simple_loss=0.2995, pruned_loss=0.06576, over 7139.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2627, pruned_loss=0.04325, over 1430881.13 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 00:56:53,796 INFO [train.py:842] (3/4) Epoch 30, batch 8150, loss[loss=0.1758, simple_loss=0.2771, pruned_loss=0.0373, over 7335.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2626, pruned_loss=0.04302, over 1422300.23 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 00:57:33,239 INFO [train.py:842] (3/4) Epoch 30, batch 8200, loss[loss=0.2392, simple_loss=0.3261, pruned_loss=0.07621, over 7170.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04269, over 1424550.18 frames.], batch size: 26, lr: 1.82e-04
2022-05-29 00:58:12,723 INFO [train.py:842] (3/4) Epoch 30, batch 8250, loss[loss=0.1543, simple_loss=0.2393, pruned_loss=0.03469, over 7415.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04287, over 1423217.33 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 00:58:51,880 INFO [train.py:842] (3/4) Epoch 30, batch 8300, loss[loss=0.1578, simple_loss=0.2543, pruned_loss=0.0306, over 7230.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2621, pruned_loss=0.04275, over 1425635.88 frames.], batch size: 21, lr: 1.82e-04
2022-05-29 00:59:31,522 INFO [train.py:842] (3/4) Epoch 30, batch 8350, loss[loss=0.1955, simple_loss=0.2797, pruned_loss=0.05568, over 7103.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04255, over 1429861.80 frames.], batch size: 28, lr: 1.82e-04
2022-05-29 01:00:10,549 INFO [train.py:842] (3/4) Epoch 30, batch 8400, loss[loss=0.1736, simple_loss=0.2462, pruned_loss=0.05044, over 6985.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2625, pruned_loss=0.04231, over 1426683.24 frames.], batch size: 16, lr: 1.82e-04
2022-05-29 01:00:49,931 INFO [train.py:842] (3/4) Epoch 30, batch 8450, loss[loss=0.1631, simple_loss=0.2534, pruned_loss=0.03643, over 7217.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2631, pruned_loss=0.0424, over 1423709.66 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 01:01:28,969 INFO [train.py:842] (3/4) Epoch 30, batch 8500, loss[loss=0.1574, simple_loss=0.2513, pruned_loss=0.03175, over 7229.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2628, pruned_loss=0.04234, over 1422682.42 frames.], batch size: 20, lr: 1.82e-04
2022-05-29 01:02:08,199 INFO [train.py:842] (3/4) Epoch 30, batch 8550, loss[loss=0.161, simple_loss=0.2472, pruned_loss=0.0374, over 7000.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04277, over 1420536.55 frames.], batch size: 16, lr: 1.82e-04
2022-05-29 01:02:47,571 INFO [train.py:842] (3/4) Epoch 30, batch 8600, loss[loss=0.1855, simple_loss=0.2675, pruned_loss=0.05174, over 7219.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04285, over 1418643.39 frames.], batch size: 21, lr: 1.82e-04
2022-05-29 01:03:27,008 INFO [train.py:842] (3/4) Epoch 30, batch 8650, loss[loss=0.1918, simple_loss=0.2879, pruned_loss=0.04783, over 7206.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2632, pruned_loss=0.04273, over 1420148.86 frames.], batch size: 23, lr: 1.82e-04
2022-05-29 01:04:06,160 INFO [train.py:842] (3/4) Epoch 30, batch 8700, loss[loss=0.1583, simple_loss=0.234, pruned_loss=0.04133, over 6779.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2637, pruned_loss=0.04331, over 1416602.89 frames.], batch size: 15, lr: 1.82e-04
2022-05-29 01:04:45,524 INFO [train.py:842] (3/4) Epoch 30, batch 8750, loss[loss=0.1869, simple_loss=0.2739, pruned_loss=0.04995, over 5503.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2636, pruned_loss=0.04287, over 1415121.25 frames.], batch size: 53, lr: 1.82e-04
2022-05-29 01:05:24,820 INFO [train.py:842] (3/4) Epoch 30, batch 8800, loss[loss=0.2202, simple_loss=0.3145, pruned_loss=0.06299, over 7112.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2636, pruned_loss=0.04334, over 1418324.54 frames.], batch size: 21, lr: 1.82e-04
2022-05-29 01:06:04,535 INFO [train.py:842] (3/4) Epoch 30, batch 8850, loss[loss=0.1658, simple_loss=0.2558, pruned_loss=0.03788, over 7219.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2629, pruned_loss=0.04292, over 1420812.09 frames.], batch size: 22, lr: 1.82e-04
2022-05-29 01:06:43,631 INFO [train.py:842] (3/4) Epoch 30, batch 8900, loss[loss=0.1775, simple_loss=0.2708, pruned_loss=0.04208, over 7152.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2622, pruned_loss=0.04284, over 1414555.72 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 01:07:22,757 INFO [train.py:842] (3/4) Epoch 30, batch 8950, loss[loss=0.1387, simple_loss=0.2222, pruned_loss=0.02757, over 7410.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2627, pruned_loss=0.0431, over 1404789.19 frames.], batch size: 18, lr: 1.82e-04
2022-05-29 01:08:01,604 INFO [train.py:842] (3/4) Epoch 30, batch 9000, loss[loss=0.1747, simple_loss=0.2764, pruned_loss=0.03655, over 6763.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2634, pruned_loss=0.04357, over 1391776.76 frames.], batch size: 31, lr: 1.82e-04
2022-05-29 01:08:01,604 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 01:08:11,200 INFO [train.py:871] (3/4) Epoch 30, validation: loss=0.1653, simple_loss=0.2631, pruned_loss=0.03376, over 868885.00 frames.
2022-05-29 01:08:49,668 INFO [train.py:842] (3/4) Epoch 30, batch 9050, loss[loss=0.2591, simple_loss=0.3374, pruned_loss=0.09047, over 5082.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2653, pruned_loss=0.04392, over 1375161.77 frames.], batch size: 52, lr: 1.82e-04
2022-05-29 01:09:27,650 INFO [train.py:842] (3/4) Epoch 30, batch 9100, loss[loss=0.1705, simple_loss=0.2564, pruned_loss=0.04234, over 6414.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2678, pruned_loss=0.0453, over 1332613.87 frames.], batch size: 37, lr: 1.82e-04
2022-05-29 01:10:06,020 INFO [train.py:842] (3/4) Epoch 30, batch 9150, loss[loss=0.2135, simple_loss=0.2941, pruned_loss=0.06649, over 5228.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2714, pruned_loss=0.04821, over 1264739.24 frames.], batch size: 53, lr: 1.82e-04
2022-05-29 01:10:56,770 INFO [train.py:842] (3/4) Epoch 31, batch 0, loss[loss=0.167, simple_loss=0.257, pruned_loss=0.03844, over 7328.00 frames.], tot_loss[loss=0.167, simple_loss=0.257, pruned_loss=0.03844, over 7328.00 frames.], batch size: 20, lr: 1.79e-04
2022-05-29 01:11:36,500 INFO [train.py:842] (3/4) Epoch 31, batch 50, loss[loss=0.1517, simple_loss=0.2399, pruned_loss=0.03177, over 7263.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2615, pruned_loss=0.04431, over 317267.51 frames.], batch size: 19, lr: 1.79e-04
2022-05-29 01:12:15,785 INFO [train.py:842] (3/4) Epoch 31, batch 100, loss[loss=0.1779, simple_loss=0.2739, pruned_loss=0.04101, over 7382.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2649, pruned_loss=0.04532, over 562266.74 frames.], batch size: 23, lr: 1.79e-04
2022-05-29 01:12:55,635 INFO [train.py:842] (3/4) Epoch 31, batch 150, loss[loss=0.2002, simple_loss=0.2801, pruned_loss=0.06017, over 7204.00 frames.], tot_loss[loss=0.178, simple_loss=0.2647, pruned_loss=0.04567, over 756751.28 frames.], batch size: 22, lr: 1.79e-04
2022-05-29 01:13:34,938 INFO [train.py:842] (3/4) Epoch 31, batch 200, loss[loss=0.2406, simple_loss=0.2933, pruned_loss=0.09397, over 4843.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2647, pruned_loss=0.0451, over 900959.68 frames.], batch size: 52, lr: 1.79e-04
2022-05-29 01:14:14,354 INFO [train.py:842] (3/4) Epoch 31, batch 250, loss[loss=0.1853, simple_loss=0.2801, pruned_loss=0.0452, over 7299.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2668, pruned_loss=0.0451, over 1014956.55 frames.], batch size: 25, lr: 1.79e-04
2022-05-29 01:14:53,619 INFO [train.py:842] (3/4) Epoch 31, batch 300, loss[loss=0.1574, simple_loss=0.2546, pruned_loss=0.0301, over 7318.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2646, pruned_loss=0.04355, over 1106023.46 frames.], batch size: 21, lr: 1.79e-04
2022-05-29 01:15:33,029 INFO [train.py:842] (3/4) Epoch 31, batch 350, loss[loss=0.1473, simple_loss=0.2324, pruned_loss=0.03108, over 7168.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04377, over 1173550.04 frames.], batch size: 18, lr: 1.79e-04
2022-05-29 01:16:12,232 INFO [train.py:842] (3/4) Epoch 31, batch 400, loss[loss=0.2052, simple_loss=0.2945, pruned_loss=0.05798, over 7233.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2649, pruned_loss=0.04374, over 1224902.63 frames.], batch size: 21, lr: 1.79e-04
2022-05-29 01:16:51,534 INFO [train.py:842] (3/4) Epoch 31, batch 450, loss[loss=0.179, simple_loss=0.2738, pruned_loss=0.0421, over 7173.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2646, pruned_loss=0.04293, over 1267012.06 frames.], batch size: 26, lr: 1.79e-04
2022-05-29 01:17:30,778 INFO [train.py:842] (3/4) Epoch 31, batch 500, loss[loss=0.1423, simple_loss=0.2256, pruned_loss=0.02951, over 7296.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2635, pruned_loss=0.04286, over 1302244.90 frames.], batch size: 17, lr: 1.79e-04
2022-05-29 01:18:10,313 INFO [train.py:842] (3/4) Epoch 31, batch 550, loss[loss=0.1788, simple_loss=0.2702, pruned_loss=0.04371, over 7407.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2637, pruned_loss=0.04345, over 1328800.92 frames.], batch size: 21, lr: 1.79e-04
2022-05-29 01:18:49,312 INFO [train.py:842] (3/4) Epoch 31, batch 600, loss[loss=0.1804, simple_loss=0.2665, pruned_loss=0.04715, over 7069.00 frames.], tot_loss[loss=0.176, simple_loss=0.2649, pruned_loss=0.04358, over 1348630.49 frames.], batch size: 18, lr: 1.79e-04
2022-05-29 01:19:29,049 INFO [train.py:842] (3/4) Epoch 31, batch 650, loss[loss=0.2146, simple_loss=0.3088, pruned_loss=0.0602, over 7147.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2649, pruned_loss=0.04369, over 1369961.56 frames.], batch size: 20, lr: 1.79e-04
2022-05-29 01:20:08,322 INFO [train.py:842] (3/4) Epoch 31, batch 700, loss[loss=0.1634, simple_loss=0.2358, pruned_loss=0.04544, over 6817.00 frames.], tot_loss[loss=0.1755, simple_loss=0.264, pruned_loss=0.04345, over 1379444.45 frames.], batch size: 15, lr: 1.79e-04
2022-05-29 01:20:47,937 INFO [train.py:842] (3/4) Epoch 31, batch 750, loss[loss=0.1598, simple_loss=0.2504, pruned_loss=0.03456, over 7244.00 frames.], tot_loss[loss=0.1747, simple_loss=0.263, pruned_loss=0.04315, over 1387675.10 frames.], batch size: 20, lr: 1.79e-04
2022-05-29 01:21:27,079 INFO [train.py:842] (3/4) Epoch 31, batch 800, loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03158, over 7325.00 frames.], tot_loss[loss=0.1748, simple_loss=0.263, pruned_loss=0.04325, over 1395716.70 frames.], batch size: 20, lr: 1.79e-04
2022-05-29 01:22:06,674 INFO [train.py:842] (3/4) Epoch 31, batch 850, loss[loss=0.1441, simple_loss=0.2395, pruned_loss=0.02437, over 7430.00 frames.], tot_loss[loss=0.1739, simple_loss=0.262, pruned_loss=0.04291, over 1399995.30 frames.], batch size: 20, lr: 1.79e-04
2022-05-29 01:22:46,071 INFO [train.py:842] (3/4) Epoch 31, batch 900, loss[loss=0.1637, simple_loss=0.2449, pruned_loss=0.04121, over 6852.00 frames.], tot_loss[loss=0.174, simple_loss=0.2623, pruned_loss=0.04287, over 1404108.79 frames.], batch size: 15, lr: 1.79e-04
2022-05-29 01:23:25,752 INFO [train.py:842] (3/4) Epoch 31, batch 950, loss[loss=0.2383, simple_loss=0.3191, pruned_loss=0.07876, over 7073.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2615, pruned_loss=0.04242, over 1405464.24 frames.], batch size: 28, lr: 1.79e-04
2022-05-29 01:24:04,930 INFO [train.py:842] (3/4) Epoch 31, batch 1000, loss[loss=0.1632, simple_loss=0.2617, pruned_loss=0.03238, over 7351.00 frames.], tot_loss[loss=0.1748, simple_loss=0.263, pruned_loss=0.04328, over 1408615.95 frames.], batch size: 22, lr: 1.79e-04
2022-05-29 01:24:44,400 INFO [train.py:842] (3/4) Epoch 31, batch 1050, loss[loss=0.1826, simple_loss=0.2781, pruned_loss=0.04356, over 7112.00 frames.], tot_loss[loss=0.175, simple_loss=0.2635, pruned_loss=0.0433, over 1410865.06 frames.], batch size: 28, lr: 1.79e-04
2022-05-29 01:25:23,496 INFO [train.py:842] (3/4) Epoch 31, batch 1100, loss[loss=0.1572, simple_loss=0.2493, pruned_loss=0.03254, over 7054.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2626, pruned_loss=0.04275, over 1414715.67 frames.], batch size: 18, lr: 1.79e-04
2022-05-29 01:26:03,322 INFO [train.py:842] (3/4) Epoch 31, batch 1150, loss[loss=0.1622, simple_loss=0.2453, pruned_loss=0.03954, over 7057.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04192, over 1416447.96 frames.], batch size: 18, lr: 1.79e-04
2022-05-29 01:26:42,698 INFO [train.py:842] (3/4) Epoch 31, batch 1200, loss[loss=0.1715, simple_loss=0.2638, pruned_loss=0.03956, over 7206.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2617, pruned_loss=0.04194, over 1417989.86 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 01:27:22,223 INFO [train.py:842] (3/4) Epoch 31, batch 1250, loss[loss=0.1685, simple_loss=0.2487, pruned_loss=0.04419, over 7411.00 frames.], tot_loss[loss=0.174, simple_loss=0.2627, pruned_loss=0.0426, over 1417919.60 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:28:01,511 INFO [train.py:842] (3/4) Epoch 31, batch 1300, loss[loss=0.1548, simple_loss=0.2562, pruned_loss=0.02672, over 7156.00 frames.], tot_loss[loss=0.174, simple_loss=0.263, pruned_loss=0.04247, over 1417263.64 frames.], batch size: 26, lr: 1.78e-04
2022-05-29 01:28:40,929 INFO [train.py:842] (3/4) Epoch 31, batch 1350, loss[loss=0.1728, simple_loss=0.2492, pruned_loss=0.0482, over 7140.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2644, pruned_loss=0.0431, over 1415023.87 frames.], batch size: 17, lr: 1.78e-04
2022-05-29 01:29:20,129 INFO [train.py:842] (3/4) Epoch 31, batch 1400, loss[loss=0.1628, simple_loss=0.2573, pruned_loss=0.03417, over 7346.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2645, pruned_loss=0.04298, over 1419533.84 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 01:29:59,781 INFO [train.py:842] (3/4) Epoch 31, batch 1450, loss[loss=0.1761, simple_loss=0.272, pruned_loss=0.04016, over 7148.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2634, pruned_loss=0.04221, over 1420800.86 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:30:38,804 INFO [train.py:842] (3/4) Epoch 31, batch 1500, loss[loss=0.1742, simple_loss=0.2649, pruned_loss=0.04171, over 7305.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2642, pruned_loss=0.04213, over 1426409.62 frames.], batch size: 25, lr: 1.78e-04
2022-05-29 01:31:18,558 INFO [train.py:842] (3/4) Epoch 31, batch 1550, loss[loss=0.2357, simple_loss=0.3235, pruned_loss=0.07396, over 7307.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2632, pruned_loss=0.04207, over 1428175.46 frames.], batch size: 25, lr: 1.78e-04
2022-05-29 01:31:57,813 INFO [train.py:842] (3/4) Epoch 31, batch 1600, loss[loss=0.162, simple_loss=0.2496, pruned_loss=0.0372, over 7257.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2633, pruned_loss=0.04261, over 1429647.50 frames.], batch size: 19, lr: 1.78e-04
2022-05-29 01:32:37,069 INFO [train.py:842] (3/4) Epoch 31, batch 1650, loss[loss=0.1599, simple_loss=0.2561, pruned_loss=0.03182, over 7112.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2647, pruned_loss=0.04305, over 1429494.31 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:33:16,441 INFO [train.py:842] (3/4) Epoch 31, batch 1700, loss[loss=0.1743, simple_loss=0.2705, pruned_loss=0.03908, over 7309.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2631, pruned_loss=0.04293, over 1426574.86 frames.], batch size: 24, lr: 1.78e-04
2022-05-29 01:33:55,905 INFO [train.py:842] (3/4) Epoch 31, batch 1750, loss[loss=0.1958, simple_loss=0.284, pruned_loss=0.05379, over 7388.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2639, pruned_loss=0.04333, over 1429090.90 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:34:34,918 INFO [train.py:842] (3/4) Epoch 31, batch 1800, loss[loss=0.1717, simple_loss=0.2507, pruned_loss=0.04637, over 7431.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2632, pruned_loss=0.04329, over 1425514.44 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:35:14,399 INFO [train.py:842] (3/4) Epoch 31, batch 1850, loss[loss=0.1684, simple_loss=0.2556, pruned_loss=0.04062, over 7119.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2624, pruned_loss=0.04271, over 1423294.56 frames.], batch size: 17, lr: 1.78e-04
2022-05-29 01:35:53,709 INFO [train.py:842] (3/4) Epoch 31, batch 1900, loss[loss=0.1635, simple_loss=0.2517, pruned_loss=0.03765, over 7329.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2633, pruned_loss=0.04306, over 1426715.84 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:36:33,267 INFO [train.py:842] (3/4) Epoch 31, batch 1950, loss[loss=0.1931, simple_loss=0.2834, pruned_loss=0.05136, over 7380.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2639, pruned_loss=0.04333, over 1426167.58 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:37:12,635 INFO [train.py:842] (3/4) Epoch 31, batch 2000, loss[loss=0.1325, simple_loss=0.2227, pruned_loss=0.02115, over 7164.00 frames.], tot_loss[loss=0.174, simple_loss=0.2625, pruned_loss=0.04275, over 1427939.93 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:37:52,323 INFO [train.py:842] (3/4) Epoch 31, batch 2050, loss[loss=0.1863, simple_loss=0.2742, pruned_loss=0.04921, over 7203.00 frames.], tot_loss[loss=0.173, simple_loss=0.2612, pruned_loss=0.04241, over 1424808.79 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 01:38:31,278 INFO [train.py:842] (3/4) Epoch 31, batch 2100, loss[loss=0.1639, simple_loss=0.2621, pruned_loss=0.03286, over 7154.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2622, pruned_loss=0.04263, over 1423489.07 frames.], batch size: 19, lr: 1.78e-04
2022-05-29 01:39:10,901 INFO [train.py:842] (3/4) Epoch 31, batch 2150, loss[loss=0.1626, simple_loss=0.246, pruned_loss=0.03959, over 7168.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2617, pruned_loss=0.04221, over 1427033.19 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:39:50,082 INFO [train.py:842] (3/4) Epoch 31, batch 2200, loss[loss=0.2, simple_loss=0.2919, pruned_loss=0.05405, over 7072.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2621, pruned_loss=0.04191, over 1428067.70 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:40:29,757 INFO [train.py:842] (3/4) Epoch 31, batch 2250, loss[loss=0.1769, simple_loss=0.2635, pruned_loss=0.04515, over 7217.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2636, pruned_loss=0.04254, over 1426954.65 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:41:09,345 INFO [train.py:842] (3/4) Epoch 31, batch 2300, loss[loss=0.1917, simple_loss=0.273, pruned_loss=0.05521, over 7265.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2621, pruned_loss=0.04176, over 1429154.37 frames.], batch size: 19, lr: 1.78e-04
2022-05-29 01:41:48,933 INFO [train.py:842] (3/4) Epoch 31, batch 2350, loss[loss=0.1705, simple_loss=0.2437, pruned_loss=0.04871, over 7067.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2617, pruned_loss=0.04173, over 1429288.95 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:42:27,933 INFO [train.py:842] (3/4) Epoch 31, batch 2400, loss[loss=0.1854, simple_loss=0.2749, pruned_loss=0.04792, over 7211.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2631, pruned_loss=0.04224, over 1427477.11 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:43:07,278 INFO [train.py:842] (3/4) Epoch 31, batch 2450, loss[loss=0.1821, simple_loss=0.2761, pruned_loss=0.04402, over 7212.00 frames.], tot_loss[loss=0.174, simple_loss=0.2633, pruned_loss=0.04236, over 1424138.50 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:43:46,454 INFO [train.py:842] (3/4) Epoch 31, batch 2500, loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03054, over 7333.00 frames.], tot_loss[loss=0.1726, simple_loss=0.262, pruned_loss=0.04157, over 1426741.78 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 01:44:37,210 INFO [train.py:842] (3/4) Epoch 31, batch 2550, loss[loss=0.1689, simple_loss=0.2594, pruned_loss=0.03925, over 7190.00 frames.], tot_loss[loss=0.1714, simple_loss=0.261, pruned_loss=0.04083, over 1428395.98 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:45:16,367 INFO [train.py:842] (3/4) Epoch 31, batch 2600, loss[loss=0.1429, simple_loss=0.2249, pruned_loss=0.03046, over 7408.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04059, over 1428579.76 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:45:55,655 INFO [train.py:842] (3/4) Epoch 31, batch 2650, loss[loss=0.1635, simple_loss=0.2611, pruned_loss=0.0329, over 7415.00 frames.], tot_loss[loss=0.172, simple_loss=0.2614, pruned_loss=0.04132, over 1425275.36 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:46:34,530 INFO [train.py:842] (3/4) Epoch 31, batch 2700, loss[loss=0.1758, simple_loss=0.255, pruned_loss=0.04828, over 7302.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2623, pruned_loss=0.04191, over 1419336.73 frames.], batch size: 25, lr: 1.78e-04
2022-05-29 01:47:14,153 INFO [train.py:842] (3/4) Epoch 31, batch 2750, loss[loss=0.207, simple_loss=0.283, pruned_loss=0.06546, over 7155.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04205, over 1419882.46 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:47:53,488 INFO [train.py:842] (3/4) Epoch 31, batch 2800, loss[loss=0.181, simple_loss=0.2703, pruned_loss=0.0458, over 7160.00 frames.], tot_loss[loss=0.1729, simple_loss=0.262, pruned_loss=0.04185, over 1422163.74 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 01:48:43,781 INFO [train.py:842] (3/4) Epoch 31, batch 2850, loss[loss=0.2058, simple_loss=0.2883, pruned_loss=0.06165, over 7197.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.04211, over 1420380.66 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 01:49:23,045 INFO [train.py:842] (3/4) Epoch 31, batch 2900, loss[loss=0.1343, simple_loss=0.2276, pruned_loss=0.02047, over 7114.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2632, pruned_loss=0.04248, over 1424831.74 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:50:02,450 INFO [train.py:842] (3/4) Epoch 31, batch 2950, loss[loss=0.2022, simple_loss=0.2823, pruned_loss=0.06105, over 7257.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.0422, over 1424208.52 frames.], batch size: 19, lr: 1.78e-04
2022-05-29 01:50:52,148 INFO [train.py:842] (3/4) Epoch 31, batch 3000, loss[loss=0.1624, simple_loss=0.2501, pruned_loss=0.0374, over 7338.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2623, pruned_loss=0.04227, over 1424023.65 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:50:52,148 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 01:51:02,034 INFO [train.py:871] (3/4) Epoch 31, validation: loss=0.165, simple_loss=0.262, pruned_loss=0.03402, over 868885.00 frames.
2022-05-29 01:51:41,772 INFO [train.py:842] (3/4) Epoch 31, batch 3050, loss[loss=0.1775, simple_loss=0.2639, pruned_loss=0.04558, over 7000.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2624, pruned_loss=0.04201, over 1423183.61 frames.], batch size: 16, lr: 1.78e-04
2022-05-29 01:52:21,218 INFO [train.py:842] (3/4) Epoch 31, batch 3100, loss[loss=0.1625, simple_loss=0.2548, pruned_loss=0.03516, over 7306.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2619, pruned_loss=0.04217, over 1426339.15 frames.], batch size: 25, lr: 1.78e-04
2022-05-29 01:53:00,805 INFO [train.py:842] (3/4) Epoch 31, batch 3150, loss[loss=0.1904, simple_loss=0.2684, pruned_loss=0.05622, over 6981.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2622, pruned_loss=0.04243, over 1425661.83 frames.], batch size: 16, lr: 1.78e-04
2022-05-29 01:53:39,934 INFO [train.py:842] (3/4) Epoch 31, batch 3200, loss[loss=0.2054, simple_loss=0.3003, pruned_loss=0.05525, over 7188.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2627, pruned_loss=0.04306, over 1416876.81 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:54:19,552 INFO [train.py:842] (3/4) Epoch 31, batch 3250, loss[loss=0.1635, simple_loss=0.2577, pruned_loss=0.03464, over 7157.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2637, pruned_loss=0.04325, over 1415795.12 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:54:58,982 INFO [train.py:842] (3/4) Epoch 31, batch 3300, loss[loss=0.1424, simple_loss=0.225, pruned_loss=0.02991, over 7297.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2636, pruned_loss=0.04347, over 1422100.49 frames.], batch size: 17, lr: 1.78e-04
2022-05-29 01:55:38,517 INFO [train.py:842] (3/4) Epoch 31, batch 3350, loss[loss=0.1452, simple_loss=0.2445, pruned_loss=0.02295, over 7228.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2628, pruned_loss=0.04309, over 1421740.78 frames.], batch size: 21, lr: 1.78e-04
2022-05-29 01:56:17,503 INFO [train.py:842] (3/4) Epoch 31, batch 3400, loss[loss=0.1877, simple_loss=0.2769, pruned_loss=0.04928, over 7260.00 frames.], tot_loss[loss=0.1738, simple_loss=0.262, pruned_loss=0.04278, over 1421266.58 frames.], batch size: 25, lr: 1.78e-04
2022-05-29 01:56:57,123 INFO [train.py:842] (3/4) Epoch 31, batch 3450, loss[loss=0.1662, simple_loss=0.2542, pruned_loss=0.03904, over 6224.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2636, pruned_loss=0.04371, over 1425344.10 frames.], batch size: 37, lr: 1.78e-04
2022-05-29 01:57:36,441 INFO [train.py:842] (3/4) Epoch 31, batch 3500, loss[loss=0.1992, simple_loss=0.2977, pruned_loss=0.0503, over 7373.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2631, pruned_loss=0.0435, over 1427386.21 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 01:58:15,848 INFO [train.py:842] (3/4) Epoch 31, batch 3550, loss[loss=0.1692, simple_loss=0.2559, pruned_loss=0.04125, over 7427.00 frames.], tot_loss[loss=0.1758, simple_loss=0.264, pruned_loss=0.04381, over 1428519.64 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 01:58:54,941 INFO [train.py:842] (3/4) Epoch 31, batch 3600, loss[loss=0.1849, simple_loss=0.2773, pruned_loss=0.04622, over 7292.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2641, pruned_loss=0.04336, over 1423454.68 frames.], batch size: 24, lr: 1.78e-04
2022-05-29 01:59:34,574 INFO [train.py:842] (3/4) Epoch 31, batch 3650, loss[loss=0.1623, simple_loss=0.2469, pruned_loss=0.03886, over 7111.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2634, pruned_loss=0.04282, over 1422742.90 frames.], batch size: 17, lr: 1.78e-04
2022-05-29 02:00:14,110 INFO [train.py:842] (3/4) Epoch 31, batch 3700, loss[loss=0.128, simple_loss=0.2075, pruned_loss=0.02426, over 7288.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2623, pruned_loss=0.04237, over 1425232.03 frames.], batch size: 17, lr: 1.78e-04
2022-05-29 02:00:53,397 INFO [train.py:842] (3/4) Epoch 31, batch 3750, loss[loss=0.1646, simple_loss=0.2484, pruned_loss=0.04035, over 7262.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2618, pruned_loss=0.04224, over 1423777.47 frames.], batch size: 19, lr: 1.78e-04
2022-05-29 02:01:33,040 INFO [train.py:842] (3/4) Epoch 31, batch 3800, loss[loss=0.1841, simple_loss=0.2758, pruned_loss=0.04619, over 7384.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2627, pruned_loss=0.04284, over 1427903.76 frames.], batch size: 23, lr: 1.78e-04
2022-05-29 02:02:12,580 INFO [train.py:842] (3/4) Epoch 31, batch 3850, loss[loss=0.163, simple_loss=0.2409, pruned_loss=0.0425, over 7003.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2635, pruned_loss=0.04353, over 1426775.54 frames.], batch size: 16, lr: 1.78e-04
2022-05-29 02:02:51,831 INFO [train.py:842] (3/4) Epoch 31, batch 3900, loss[loss=0.1716, simple_loss=0.2667, pruned_loss=0.0382, over 7330.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2627, pruned_loss=0.04298, over 1430545.38 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 02:03:31,401 INFO [train.py:842] (3/4) Epoch 31, batch 3950, loss[loss=0.1696, simple_loss=0.2559, pruned_loss=0.04167, over 7274.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2632, pruned_loss=0.04297, over 1430758.20 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 02:04:10,622 INFO [train.py:842] (3/4) Epoch 31, batch 4000, loss[loss=0.1732, simple_loss=0.2589, pruned_loss=0.04377, over 7426.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2633, pruned_loss=0.04262, over 1431953.55 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 02:04:50,019 INFO [train.py:842] (3/4) Epoch 31, batch 4050, loss[loss=0.1494, simple_loss=0.2371, pruned_loss=0.03084, over 7004.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2638, pruned_loss=0.04303, over 1428463.91 frames.], batch size: 16, lr: 1.78e-04
2022-05-29 02:05:29,188 INFO [train.py:842] (3/4) Epoch 31, batch 4100, loss[loss=0.1615, simple_loss=0.2567, pruned_loss=0.03312, over 7414.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2639, pruned_loss=0.04295, over 1428379.52 frames.], batch size: 18, lr: 1.78e-04
2022-05-29 02:06:08,817 INFO [train.py:842] (3/4) Epoch 31, batch 4150, loss[loss=0.1673, simple_loss=0.2574, pruned_loss=0.03863, over 7141.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04284, over 1430486.58 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 02:06:47,965 INFO [train.py:842] (3/4) Epoch 31, batch 4200, loss[loss=0.1777, simple_loss=0.2629, pruned_loss=0.04626, over 7434.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2637, pruned_loss=0.04246, over 1430038.93 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 02:07:30,422 INFO [train.py:842] (3/4) Epoch 31, batch 4250, loss[loss=0.1585, simple_loss=0.2487, pruned_loss=0.03419, over 7332.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2628, pruned_loss=0.04234, over 1431403.93 frames.], batch size: 22, lr: 1.78e-04
2022-05-29 02:08:09,330 INFO [train.py:842] (3/4) Epoch 31, batch 4300, loss[loss=0.1822, simple_loss=0.2666, pruned_loss=0.04891, over 7329.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2633, pruned_loss=0.04248, over 1430826.33 frames.], batch size: 20, lr: 1.78e-04
2022-05-29 02:08:48,997 INFO [train.py:842] (3/4) Epoch 31, batch 4350, loss[loss=0.1627, simple_loss=0.2622, pruned_loss=0.03166, over 7061.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2629, pruned_loss=0.04238, over 1431765.40 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:09:28,390 INFO [train.py:842] (3/4) Epoch 31, batch 4400, loss[loss=0.1746, simple_loss=0.2769, pruned_loss=0.03615, over 7018.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2623, pruned_loss=0.04205, over 1433709.38 frames.], batch size: 28, lr: 1.77e-04
2022-05-29 02:10:08,094 INFO [train.py:842] (3/4) Epoch 31, batch 4450, loss[loss=0.1654, simple_loss=0.2542, pruned_loss=0.03834, over 7170.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2617, pruned_loss=0.04166, over 1434002.95 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:10:47,343 INFO [train.py:842] (3/4) Epoch 31, batch 4500, loss[loss=0.1992, simple_loss=0.2892, pruned_loss=0.05464, over 7205.00 frames.], tot_loss[loss=0.173, simple_loss=0.2626, pruned_loss=0.04172, over 1429932.20 frames.], batch size: 22, lr: 1.77e-04
2022-05-29 02:11:26,829 INFO [train.py:842] (3/4) Epoch 31, batch 4550, loss[loss=0.2257, simple_loss=0.3051, pruned_loss=0.07314, over 4964.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2631, pruned_loss=0.04231, over 1422207.73 frames.], batch size: 52, lr: 1.77e-04
2022-05-29 02:12:06,241 INFO [train.py:842] (3/4) Epoch 31, batch 4600, loss[loss=0.162, simple_loss=0.2673, pruned_loss=0.02833, over 7148.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2623, pruned_loss=0.04203, over 1424622.69 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:12:45,692 INFO [train.py:842] (3/4) Epoch 31, batch 4650, loss[loss=0.2092, simple_loss=0.3015, pruned_loss=0.05846, over 7434.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2633, pruned_loss=0.04256, over 1424969.90 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:13:24,771 INFO [train.py:842] (3/4) Epoch 31, batch 4700, loss[loss=0.1501, simple_loss=0.237, pruned_loss=0.03166, over 7251.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2642, pruned_loss=0.04311, over 1423611.65 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:14:04,546 INFO [train.py:842] (3/4) Epoch 31, batch 4750, loss[loss=0.161, simple_loss=0.248, pruned_loss=0.03695, over 7158.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2641, pruned_loss=0.04282, over 1425860.91 frames.], batch size: 17, lr: 1.77e-04
2022-05-29 02:14:43,760 INFO [train.py:842] (3/4) Epoch 31, batch 4800, loss[loss=0.1753, simple_loss=0.2694, pruned_loss=0.04066, over 7152.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2642, pruned_loss=0.0431, over 1425751.81 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:15:23,356 INFO [train.py:842] (3/4) Epoch 31, batch 4850, loss[loss=0.1705, simple_loss=0.2631, pruned_loss=0.03893, over 6460.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2647, pruned_loss=0.04323, over 1419285.71 frames.], batch size: 38, lr: 1.77e-04
2022-05-29 02:16:02,464 INFO [train.py:842] (3/4) Epoch 31, batch 4900, loss[loss=0.1398, simple_loss=0.2351, pruned_loss=0.02225, over 7442.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2644, pruned_loss=0.04294, over 1420247.62 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:16:42,085 INFO [train.py:842] (3/4) Epoch 31, batch 4950, loss[loss=0.1662, simple_loss=0.2522, pruned_loss=0.04012, over 7075.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2635, pruned_loss=0.04244, over 1417311.68 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:17:21,112 INFO [train.py:842] (3/4) Epoch 31, batch 5000, loss[loss=0.1547, simple_loss=0.2497, pruned_loss=0.02983, over 7077.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2652, pruned_loss=0.04348, over 1416328.09 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:18:00,734 INFO [train.py:842] (3/4) Epoch 31, batch 5050, loss[loss=0.1486, simple_loss=0.2488, pruned_loss=0.02422, over 7166.00 frames.], tot_loss[loss=0.176, simple_loss=0.265, pruned_loss=0.04344, over 1416817.83 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:18:39,771 INFO [train.py:842] (3/4) Epoch 31, batch 5100, loss[loss=0.2141, simple_loss=0.2896, pruned_loss=0.06929, over 7414.00 frames.], tot_loss[loss=0.1757, simple_loss=0.265, pruned_loss=0.04325, over 1422041.63 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:19:19,614 INFO [train.py:842] (3/4) Epoch 31, batch 5150, loss[loss=0.1482, simple_loss=0.2301, pruned_loss=0.03316, over 7134.00 frames.], tot_loss[loss=0.1757, simple_loss=0.265, pruned_loss=0.04322, over 1424008.65 frames.], batch size: 17, lr: 1.77e-04
2022-05-29 02:19:59,018 INFO [train.py:842] (3/4) Epoch 31, batch 5200, loss[loss=0.146, simple_loss=0.2426, pruned_loss=0.02469, over 7264.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2638, pruned_loss=0.0427, over 1424604.83 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:20:38,697 INFO [train.py:842] (3/4) Epoch 31, batch 5250, loss[loss=0.1829, simple_loss=0.2838, pruned_loss=0.04098, over 7113.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2628, pruned_loss=0.04204, over 1422914.81 frames.], batch size: 28, lr: 1.77e-04
2022-05-29 02:21:18,187 INFO [train.py:842] (3/4) Epoch 31, batch 5300, loss[loss=0.2091, simple_loss=0.2879, pruned_loss=0.06517, over 7387.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04212, over 1423649.31 frames.], batch size: 23, lr: 1.77e-04
2022-05-29 02:21:57,660 INFO [train.py:842] (3/4) Epoch 31, batch 5350, loss[loss=0.1743, simple_loss=0.2658, pruned_loss=0.04143, over 5173.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2614, pruned_loss=0.04164, over 1420412.12 frames.], batch size: 53, lr: 1.77e-04
2022-05-29 02:22:36,643 INFO [train.py:842] (3/4) Epoch 31, batch 5400, loss[loss=0.1858, simple_loss=0.2743, pruned_loss=0.04866, over 7318.00 frames.], tot_loss[loss=0.174, simple_loss=0.2632, pruned_loss=0.04244, over 1421735.49 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:23:16,002 INFO [train.py:842] (3/4) Epoch 31, batch 5450, loss[loss=0.1585, simple_loss=0.2409, pruned_loss=0.03801, over 6994.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2635, pruned_loss=0.04314, over 1417747.67 frames.], batch size: 16, lr: 1.77e-04
2022-05-29 02:23:55,236 INFO [train.py:842] (3/4) Epoch 31, batch 5500, loss[loss=0.1715, simple_loss=0.2584, pruned_loss=0.04227, over 7325.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2646, pruned_loss=0.04357, over 1419658.43 frames.], batch size: 22, lr: 1.77e-04
2022-05-29 02:24:34,763 INFO [train.py:842] (3/4) Epoch 31, batch 5550, loss[loss=0.1566, simple_loss=0.2553, pruned_loss=0.02896, over 7413.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2642, pruned_loss=0.0433, over 1420872.06 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:25:13,912 INFO [train.py:842] (3/4) Epoch 31, batch 5600, loss[loss=0.1378, simple_loss=0.2186, pruned_loss=0.02847, over 6989.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2636, pruned_loss=0.0433, over 1420395.18 frames.], batch size: 16, lr: 1.77e-04
2022-05-29 02:25:53,477 INFO [train.py:842] (3/4) Epoch 31, batch 5650, loss[loss=0.1588, simple_loss=0.24, pruned_loss=0.03884, over 7422.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2636, pruned_loss=0.04304, over 1420342.25 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:26:32,513 INFO [train.py:842] (3/4) Epoch 31, batch 5700, loss[loss=0.173, simple_loss=0.2624, pruned_loss=0.04176, over 7339.00 frames.], tot_loss[loss=0.1763, simple_loss=0.265, pruned_loss=0.04382, over 1414218.15 frames.], batch size: 22, lr: 1.77e-04
2022-05-29 02:27:12,159 INFO [train.py:842] (3/4) Epoch 31, batch 5750, loss[loss=0.1945, simple_loss=0.2937, pruned_loss=0.04763, over 7109.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2644, pruned_loss=0.04308, over 1419494.11 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:27:51,388 INFO [train.py:842] (3/4) Epoch 31, batch 5800, loss[loss=0.164, simple_loss=0.2501, pruned_loss=0.03895, over 7248.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2655, pruned_loss=0.04382, over 1419360.99 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:28:31,167 INFO [train.py:842] (3/4) Epoch 31, batch 5850, loss[loss=0.147, simple_loss=0.2254, pruned_loss=0.03433, over 7395.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2647, pruned_loss=0.04345, over 1423151.97 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:29:10,381 INFO [train.py:842] (3/4) Epoch 31, batch 5900, loss[loss=0.1641, simple_loss=0.2737, pruned_loss=0.02732, over 7338.00 frames.], tot_loss[loss=0.1754, simple_loss=0.264, pruned_loss=0.04339, over 1424177.35 frames.], batch size: 22, lr: 1.77e-04
2022-05-29 02:29:50,358 INFO [train.py:842] (3/4) Epoch 31, batch 5950, loss[loss=0.1647, simple_loss=0.2568, pruned_loss=0.03628, over 7156.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2633, pruned_loss=0.04366, over 1428811.98 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:30:29,427 INFO [train.py:842] (3/4) Epoch 31, batch 6000, loss[loss=0.1647, simple_loss=0.2563, pruned_loss=0.03656, over 7380.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2639, pruned_loss=0.04376, over 1426577.28 frames.], batch size: 23, lr: 1.77e-04
2022-05-29 02:30:29,428 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 02:30:38,842 INFO [train.py:871] (3/4) Epoch 31, validation: loss=0.1644, simple_loss=0.2618, pruned_loss=0.0335, over 868885.00 frames.
2022-05-29 02:31:18,334 INFO [train.py:842] (3/4) Epoch 31, batch 6050, loss[loss=0.1651, simple_loss=0.2589, pruned_loss=0.03567, over 7417.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2641, pruned_loss=0.04372, over 1425776.90 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:31:57,788 INFO [train.py:842] (3/4) Epoch 31, batch 6100, loss[loss=0.1714, simple_loss=0.2481, pruned_loss=0.04737, over 7357.00 frames.], tot_loss[loss=0.175, simple_loss=0.2631, pruned_loss=0.0434, over 1429712.41 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:32:37,357 INFO [train.py:842] (3/4) Epoch 31, batch 6150, loss[loss=0.1344, simple_loss=0.2233, pruned_loss=0.02276, over 7158.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2624, pruned_loss=0.04248, over 1428409.49 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:33:16,227 INFO [train.py:842] (3/4) Epoch 31, batch 6200, loss[loss=0.1556, simple_loss=0.2546, pruned_loss=0.02833, over 7142.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2644, pruned_loss=0.04353, over 1422243.46 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:33:55,521 INFO [train.py:842] (3/4) Epoch 31, batch 6250, loss[loss=0.2085, simple_loss=0.3023, pruned_loss=0.05736, over 6726.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2648, pruned_loss=0.04328, over 1422844.93 frames.], batch size: 31, lr: 1.77e-04
2022-05-29 02:34:34,689 INFO [train.py:842] (3/4) Epoch 31, batch 6300, loss[loss=0.1812, simple_loss=0.2779, pruned_loss=0.04221, over 7340.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2648, pruned_loss=0.04312, over 1421041.62 frames.], batch size: 22, lr: 1.77e-04
2022-05-29 02:35:14,307 INFO [train.py:842] (3/4) Epoch 31, batch 6350, loss[loss=0.1607, simple_loss=0.2575, pruned_loss=0.03196, over 7152.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2652, pruned_loss=0.04323, over 1425557.62 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:35:53,438 INFO [train.py:842] (3/4) Epoch 31, batch 6400, loss[loss=0.174, simple_loss=0.2633, pruned_loss=0.04237, over 6391.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2658, pruned_loss=0.04365, over 1423180.12 frames.], batch size: 37, lr: 1.77e-04
2022-05-29 02:36:33,067 INFO [train.py:842] (3/4) Epoch 31, batch 6450, loss[loss=0.2112, simple_loss=0.2955, pruned_loss=0.06347, over 7430.00 frames.], tot_loss[loss=0.176, simple_loss=0.2651, pruned_loss=0.04342, over 1420607.20 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:37:12,532 INFO [train.py:842] (3/4) Epoch 31, batch 6500, loss[loss=0.1827, simple_loss=0.2672, pruned_loss=0.04907, over 7261.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2635, pruned_loss=0.04269, over 1427237.51 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:37:52,298 INFO [train.py:842] (3/4) Epoch 31, batch 6550, loss[loss=0.1687, simple_loss=0.2483, pruned_loss=0.04458, over 7002.00 frames.], tot_loss[loss=0.174, simple_loss=0.2632, pruned_loss=0.04239, over 1424050.45 frames.], batch size: 16, lr: 1.77e-04
2022-05-29 02:38:31,495 INFO [train.py:842] (3/4) Epoch 31, batch 6600, loss[loss=0.1944, simple_loss=0.296, pruned_loss=0.04637, over 7193.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2638, pruned_loss=0.04293, over 1423225.15 frames.], batch size: 23, lr: 1.77e-04
2022-05-29 02:39:11,128 INFO [train.py:842] (3/4) Epoch 31, batch 6650, loss[loss=0.1773, simple_loss=0.2636, pruned_loss=0.04552, over 7429.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2638, pruned_loss=0.04319, over 1427700.46 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:39:50,730 INFO [train.py:842] (3/4) Epoch 31, batch 6700, loss[loss=0.1904, simple_loss=0.2902, pruned_loss=0.04532, over 7216.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2634, pruned_loss=0.043, over 1432231.31 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:40:30,533 INFO [train.py:842] (3/4) Epoch 31, batch 6750, loss[loss=0.1575, simple_loss=0.2513, pruned_loss=0.03187, over 7264.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2627, pruned_loss=0.0424, over 1429960.38 frames.], batch size: 24, lr: 1.77e-04
2022-05-29 02:41:09,526 INFO [train.py:842] (3/4) Epoch 31, batch 6800, loss[loss=0.1743, simple_loss=0.2666, pruned_loss=0.04098, over 6400.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2627, pruned_loss=0.04253, over 1429442.19 frames.], batch size: 37, lr: 1.77e-04
2022-05-29 02:41:49,179 INFO [train.py:842] (3/4) Epoch 31, batch 6850, loss[loss=0.1502, simple_loss=0.2322, pruned_loss=0.03413, over 7257.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2632, pruned_loss=0.04231, over 1425614.88 frames.], batch size: 18, lr: 1.77e-04
2022-05-29 02:42:28,726 INFO [train.py:842] (3/4) Epoch 31, batch 6900, loss[loss=0.199, simple_loss=0.2883, pruned_loss=0.05486, over 7128.00 frames.], tot_loss[loss=0.1741, simple_loss=0.263, pruned_loss=0.04257, over 1425241.63 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:43:08,189 INFO [train.py:842] (3/4) Epoch 31, batch 6950, loss[loss=0.1711, simple_loss=0.2748, pruned_loss=0.0337, over 7319.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2646, pruned_loss=0.04332, over 1421804.17 frames.], batch size: 21, lr: 1.77e-04
2022-05-29 02:43:47,668 INFO [train.py:842] (3/4) Epoch 31, batch 7000, loss[loss=0.1481, simple_loss=0.2402, pruned_loss=0.02798, over 7327.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2646, pruned_loss=0.04329, over 1418104.45 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:44:27,092 INFO [train.py:842] (3/4) Epoch 31, batch 7050, loss[loss=0.1723, simple_loss=0.2552, pruned_loss=0.04471, over 7250.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2642, pruned_loss=0.04339, over 1407711.17 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:45:06,187 INFO [train.py:842] (3/4) Epoch 31, batch 7100, loss[loss=0.1817, simple_loss=0.2725, pruned_loss=0.04547, over 7414.00 frames.], tot_loss[loss=0.176, simple_loss=0.2648, pruned_loss=0.04361, over 1399257.84 frames.], batch size: 20, lr: 1.77e-04
2022-05-29 02:45:46,088 INFO [train.py:842] (3/4) Epoch 31, batch 7150, loss[loss=0.1832, simple_loss=0.269, pruned_loss=0.04872, over 7253.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2635, pruned_loss=0.04337, over 1401594.27 frames.], batch size: 19, lr: 1.77e-04
2022-05-29 02:46:25,417 INFO [train.py:842] (3/4) Epoch 31, batch 7200, loss[loss=0.1865, simple_loss=0.2619, pruned_loss=0.05555, over 6832.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2646, pruned_loss=0.04382, over 1400861.83 frames.], batch size: 15, lr: 1.77e-04
2022-05-29 02:47:05,324 INFO [train.py:842] (3/4) Epoch 31, batch 7250, loss[loss=0.1793, simple_loss=0.2577, pruned_loss=0.05039, over 7258.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2636, pruned_loss=0.04356, over 1408104.06 frames.], batch size: 16, lr: 1.77e-04
2022-05-29 02:47:44,468 INFO [train.py:842] (3/4) Epoch 31, batch 7300, loss[loss=0.1435, simple_loss=0.2204, pruned_loss=0.03333, over 7275.00 frames.], tot_loss[loss=0.174, simple_loss=0.2627, pruned_loss=0.0426, over 1410247.21 frames.], batch size: 17, lr: 1.77e-04
2022-05-29 02:48:24,359 INFO [train.py:842] (3/4) Epoch 31, batch 7350, loss[loss=0.1403, simple_loss=0.2242, pruned_loss=0.02817, over 7282.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2618, pruned_loss=0.04231, over 1412773.11 frames.], batch size: 17, lr: 1.77e-04
2022-05-29 02:49:03,704 INFO [train.py:842] (3/4) Epoch 31, batch 7400, loss[loss=0.1808, simple_loss=0.2694, pruned_loss=0.04606, over 6454.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2624, pruned_loss=0.04252, over 1416977.42 frames.], batch size: 38, lr: 1.77e-04
2022-05-29 02:49:43,389 INFO [train.py:842] (3/4) Epoch 31, batch 7450, loss[loss=0.1455, simple_loss=0.2339, pruned_loss=0.0286, over 7247.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04245, over 1418340.41 frames.], batch size: 16, lr: 1.77e-04
2022-05-29 02:50:22,773 INFO [train.py:842] (3/4) Epoch 31, batch 7500, loss[loss=0.1608, simple_loss=0.257, pruned_loss=0.03228, over 7251.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2623, pruned_loss=0.04293, over 1415135.67 frames.], batch size: 19, lr: 1.76e-04
2022-05-29 02:51:02,365 INFO [train.py:842] (3/4) Epoch 31, batch 7550, loss[loss=0.1718, simple_loss=0.266, pruned_loss=0.03883, over 7143.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2638, pruned_loss=0.04331, over 1416247.58 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 02:51:41,390 INFO [train.py:842] (3/4) Epoch 31, batch 7600, loss[loss=0.1616, simple_loss=0.2579, pruned_loss=0.0326, over 7422.00 frames.], tot_loss[loss=0.1755, simple_loss=0.264, pruned_loss=0.04355, over 1415751.79 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 02:52:20,782 INFO [train.py:842] (3/4) Epoch 31, batch 7650, loss[loss=0.146, simple_loss=0.2287, pruned_loss=0.03165, over 7256.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2641, pruned_loss=0.04351, over 1416357.64 frames.], batch size: 19, lr: 1.76e-04
2022-05-29 02:53:00,135 INFO [train.py:842] (3/4) Epoch 31, batch 7700, loss[loss=0.1841, simple_loss=0.2818, pruned_loss=0.04317, over 5114.00 frames.], tot_loss[loss=0.175, simple_loss=0.2637, pruned_loss=0.04311, over 1418681.55 frames.], batch size: 53, lr: 1.76e-04
2022-05-29 02:53:39,835 INFO [train.py:842] (3/4) Epoch 31, batch 7750, loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.03851, over 7335.00 frames.], tot_loss[loss=0.175, simple_loss=0.2637, pruned_loss=0.0431, over 1419637.19 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 02:54:19,340 INFO [train.py:842] (3/4) Epoch 31, batch 7800, loss[loss=0.1514, simple_loss=0.2388, pruned_loss=0.03202, over 7333.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2628, pruned_loss=0.0429, over 1420680.21 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 02:54:58,958 INFO [train.py:842] (3/4) Epoch 31, batch 7850, loss[loss=0.2282, simple_loss=0.3108, pruned_loss=0.07281, over 7284.00 frames.], tot_loss[loss=0.1759, simple_loss=0.264, pruned_loss=0.04388, over 1419689.67 frames.], batch size: 25, lr: 1.76e-04
2022-05-29 02:55:38,156 INFO [train.py:842] (3/4) Epoch 31, batch 7900, loss[loss=0.1228, simple_loss=0.2048, pruned_loss=0.02046, over 7418.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2646, pruned_loss=0.04405, over 1419329.22 frames.], batch size: 18, lr: 1.76e-04
2022-05-29 02:56:17,852 INFO [train.py:842] (3/4) Epoch 31, batch 7950, loss[loss=0.1649, simple_loss=0.2571, pruned_loss=0.03635, over 7395.00 frames.], tot_loss[loss=0.176, simple_loss=0.2642, pruned_loss=0.04394, over 1419758.53 frames.], batch size: 18, lr: 1.76e-04
2022-05-29 02:56:57,330 INFO [train.py:842] (3/4) Epoch 31, batch 8000, loss[loss=0.1951, simple_loss=0.2747, pruned_loss=0.05778, over 7426.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2639, pruned_loss=0.04374, over 1419841.23 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 02:57:36,928 INFO [train.py:842] (3/4) Epoch 31, batch 8050, loss[loss=0.1913, simple_loss=0.2819, pruned_loss=0.05035, over 7225.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2642, pruned_loss=0.04378, over 1416128.31 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 02:58:16,068 INFO [train.py:842] (3/4) Epoch 31, batch 8100, loss[loss=0.1697, simple_loss=0.2662, pruned_loss=0.03662, over 7341.00 frames.], tot_loss[loss=0.1764, simple_loss=0.265, pruned_loss=0.04388, over 1415264.29 frames.], batch size: 22, lr: 1.76e-04
2022-05-29 02:58:55,602 INFO [train.py:842] (3/4) Epoch 31, batch 8150, loss[loss=0.1487, simple_loss=0.2327, pruned_loss=0.03236, over 7271.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2652, pruned_loss=0.04436, over 1418667.39 frames.], batch size: 17, lr: 1.76e-04
2022-05-29 02:59:34,721 INFO [train.py:842] (3/4) Epoch 31, batch 8200, loss[loss=0.1515, simple_loss=0.2332, pruned_loss=0.03485, over 7129.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2632, pruned_loss=0.04326, over 1418454.02 frames.], batch size: 17, lr: 1.76e-04
2022-05-29 03:00:14,446 INFO [train.py:842] (3/4) Epoch 31, batch 8250, loss[loss=0.1566, simple_loss=0.2358, pruned_loss=0.03867, over 7275.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2631, pruned_loss=0.04318, over 1414827.38 frames.], batch size: 17, lr: 1.76e-04
2022-05-29 03:00:53,614 INFO [train.py:842] (3/4) Epoch 31, batch 8300, loss[loss=0.1641, simple_loss=0.2475, pruned_loss=0.04035, over 7283.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2619, pruned_loss=0.0427, over 1413641.09 frames.], batch size: 18, lr: 1.76e-04
2022-05-29 03:01:33,343 INFO [train.py:842] (3/4) Epoch 31, batch 8350, loss[loss=0.1898, simple_loss=0.2826, pruned_loss=0.04847, over 7108.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2625, pruned_loss=0.04295, over 1414864.30 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 03:02:12,651 INFO [train.py:842] (3/4) Epoch 31, batch 8400, loss[loss=0.19, simple_loss=0.2793, pruned_loss=0.05035, over 7221.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2624, pruned_loss=0.04261, over 1415058.52 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 03:02:52,213 INFO [train.py:842] (3/4) Epoch 31, batch 8450, loss[loss=0.174, simple_loss=0.2676, pruned_loss=0.04018, over 7323.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04204, over 1416452.26 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 03:03:31,494 INFO [train.py:842] (3/4) Epoch 31, batch 8500, loss[loss=0.1913, simple_loss=0.2873, pruned_loss=0.04767, over 7146.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2627, pruned_loss=0.04296, over 1414731.11 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 03:04:11,192 INFO [train.py:842] (3/4) Epoch 31, batch 8550, loss[loss=0.198, simple_loss=0.2845, pruned_loss=0.05578, over 7417.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2628, pruned_loss=0.04304, over 1414323.94 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 03:04:50,565 INFO [train.py:842] (3/4) Epoch 31, batch 8600, loss[loss=0.1609, simple_loss=0.2575, pruned_loss=0.03215, over 7316.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2619, pruned_loss=0.04266, over 1417563.20 frames.], batch size: 21, lr: 1.76e-04
2022-05-29 03:05:30,258 INFO [train.py:842] (3/4) Epoch 31, batch 8650, loss[loss=0.1891, simple_loss=0.2832, pruned_loss=0.04746, over 6333.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2622, pruned_loss=0.04262, over 1419761.84 frames.], batch size: 38, lr: 1.76e-04
2022-05-29 03:06:09,464 INFO [train.py:842] (3/4) Epoch 31, batch 8700, loss[loss=0.1347, simple_loss=0.2216, pruned_loss=0.02384, over 7013.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2626, pruned_loss=0.0428, over 1420216.12 frames.], batch size: 16, lr: 1.76e-04
2022-05-29 03:06:48,569 INFO [train.py:842] (3/4) Epoch 31, batch 8750, loss[loss=0.172, simple_loss=0.2661, pruned_loss=0.03891, over 6693.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2627, pruned_loss=0.04292, over 1409596.84 frames.], batch size: 31, lr: 1.76e-04
2022-05-29 03:07:28,082 INFO [train.py:842] (3/4) Epoch 31, batch 8800, loss[loss=0.1369, simple_loss=0.2247, pruned_loss=0.02456, over 7232.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2621, pruned_loss=0.04312, over 1409300.03 frames.], batch size: 16, lr: 1.76e-04
2022-05-29 03:08:07,340 INFO [train.py:842] (3/4) Epoch 31, batch 8850, loss[loss=0.1532, simple_loss=0.2379, pruned_loss=0.03422, over 7412.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2637, pruned_loss=0.04373, over 1404818.62 frames.], batch size: 18, lr: 1.76e-04
2022-05-29 03:08:46,506 INFO [train.py:842] (3/4) Epoch 31, batch 8900, loss[loss=0.2119, simple_loss=0.2912, pruned_loss=0.06633, over 5102.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2652, pruned_loss=0.04474, over 1395971.10 frames.], batch size: 53, lr: 1.76e-04
2022-05-29 03:09:25,611 INFO [train.py:842] (3/4) Epoch 31, batch 8950, loss[loss=0.1604, simple_loss=0.2536, pruned_loss=0.03358, over 7328.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2656, pruned_loss=0.04443, over 1393112.91 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 03:10:04,393 INFO [train.py:842] (3/4) Epoch 31, batch 9000, loss[loss=0.2025, simple_loss=0.2847, pruned_loss=0.06015, over 7231.00 frames.], tot_loss[loss=0.1787, simple_loss=0.267, pruned_loss=0.0452, over 1390594.33 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 03:10:04,394 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 03:10:13,977 INFO [train.py:871] (3/4) Epoch 31, validation: loss=0.1628, simple_loss=0.2602, pruned_loss=0.03268, over 868885.00 frames.
2022-05-29 03:10:53,015 INFO [train.py:842] (3/4) Epoch 31, batch 9050, loss[loss=0.1738, simple_loss=0.2653, pruned_loss=0.04113, over 6495.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2671, pruned_loss=0.04541, over 1372719.90 frames.], batch size: 38, lr: 1.76e-04
2022-05-29 03:11:31,605 INFO [train.py:842] (3/4) Epoch 31, batch 9100, loss[loss=0.164, simple_loss=0.2534, pruned_loss=0.03727, over 7325.00 frames.], tot_loss[loss=0.178, simple_loss=0.2665, pruned_loss=0.0448, over 1359000.89 frames.], batch size: 20, lr: 1.76e-04
2022-05-29 03:12:10,278 INFO [train.py:842] (3/4) Epoch 31, batch 9150, loss[loss=0.1846, simple_loss=0.2835, pruned_loss=0.04279, over 6246.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2684, pruned_loss=0.04593, over 1326696.34 frames.], batch size: 37, lr: 1.76e-04
2022-05-29 03:13:02,501 INFO [train.py:842] (3/4) Epoch 32, batch 0, loss[loss=0.1785, simple_loss=0.2657, pruned_loss=0.04564, over 5085.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2657, pruned_loss=0.04564, over 5085.00 frames.], batch size: 52, lr: 1.73e-04
2022-05-29 03:13:41,587 INFO [train.py:842] (3/4) Epoch 32, batch 50, loss[loss=0.2153, simple_loss=0.2929, pruned_loss=0.06882, over 6463.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2652, pruned_loss=0.04225, over 319238.77 frames.], batch size: 38, lr: 1.73e-04
2022-05-29 03:14:21,213 INFO [train.py:842] (3/4) Epoch 32, batch 100, loss[loss=0.2536, simple_loss=0.3245, pruned_loss=0.09132, over 7324.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2681, pruned_loss=0.04474, over 566160.56 frames.], batch size: 25, lr: 1.73e-04
2022-05-29 03:15:00,456 INFO [train.py:842] (3/4) Epoch 32, batch 150, loss[loss=0.1886, simple_loss=0.2791, pruned_loss=0.0491, over 7115.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2666, pruned_loss=0.04377, over 757990.64 frames.], batch size: 26, lr: 1.73e-04
2022-05-29 03:15:39,810 INFO [train.py:842] (3/4) Epoch 32, batch 200, loss[loss=0.1465, simple_loss=0.2356, pruned_loss=0.02875, over 6990.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2662, pruned_loss=0.04365, over 903283.95 frames.], batch size: 16, lr: 1.73e-04
2022-05-29 03:16:19,190 INFO [train.py:842] (3/4) Epoch 32, batch 250, loss[loss=0.1755, simple_loss=0.2764, pruned_loss=0.03736, over 7289.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2633, pruned_loss=0.0417, over 1023037.67 frames.], batch size: 24, lr: 1.73e-04
2022-05-29 03:16:58,587 INFO [train.py:842] (3/4) Epoch 32, batch 300, loss[loss=0.1784, simple_loss=0.2801, pruned_loss=0.03834, over 7278.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2631, pruned_loss=0.04193, over 1113302.75 frames.], batch size: 24, lr: 1.73e-04
2022-05-29 03:17:37,878 INFO [train.py:842] (3/4) Epoch 32, batch 350, loss[loss=0.1955, simple_loss=0.2841, pruned_loss=0.05342, over 7073.00 frames.], tot_loss[loss=0.173, simple_loss=0.2624, pruned_loss=0.04176, over 1181333.10 frames.], batch size: 28, lr: 1.73e-04
2022-05-29 03:18:17,602 INFO [train.py:842] (3/4) Epoch 32, batch 400, loss[loss=0.1732, simple_loss=0.2782, pruned_loss=0.0341, over 7154.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2628, pruned_loss=0.04193, over 1236806.75 frames.], batch size: 26, lr: 1.73e-04
2022-05-29 03:18:56,910 INFO [train.py:842] (3/4) Epoch 32, batch 450, loss[loss=0.1517, simple_loss=0.2533, pruned_loss=0.02506, over 7312.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2625, pruned_loss=0.0422, over 1276507.81 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:19:36,528 INFO [train.py:842] (3/4) Epoch 32, batch 500, loss[loss=0.1674, simple_loss=0.2687, pruned_loss=0.03309, over 7331.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04156, over 1311822.48 frames.], batch size: 22, lr: 1.73e-04
2022-05-29 03:20:15,862 INFO [train.py:842] (3/4) Epoch 32, batch 550, loss[loss=0.1629, simple_loss=0.2582, pruned_loss=0.03379, over 7333.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2622, pruned_loss=0.04228, over 1340489.77 frames.], batch size: 22, lr: 1.73e-04
2022-05-29 03:20:55,439 INFO [train.py:842] (3/4) Epoch 32, batch 600, loss[loss=0.159, simple_loss=0.244, pruned_loss=0.03696, over 7121.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2613, pruned_loss=0.04205, over 1363268.30 frames.], batch size: 17, lr: 1.73e-04
2022-05-29 03:21:45,350 INFO [train.py:842] (3/4) Epoch 32, batch 650, loss[loss=0.1494, simple_loss=0.2361, pruned_loss=0.03137, over 7020.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2618, pruned_loss=0.04234, over 1379085.46 frames.], batch size: 16, lr: 1.73e-04
2022-05-29 03:22:24,807 INFO [train.py:842] (3/4) Epoch 32, batch 700, loss[loss=0.1894, simple_loss=0.2699, pruned_loss=0.0545, over 7207.00 frames.], tot_loss[loss=0.1742, simple_loss=0.263, pruned_loss=0.04269, over 1387767.82 frames.], batch size: 23, lr: 1.73e-04
2022-05-29 03:23:04,321 INFO [train.py:842] (3/4) Epoch 32, batch 750, loss[loss=0.1762, simple_loss=0.2629, pruned_loss=0.04477, over 7105.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2644, pruned_loss=0.04355, over 1396319.25 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:23:43,764 INFO [train.py:842] (3/4) Epoch 32, batch 800, loss[loss=0.1662, simple_loss=0.2392, pruned_loss=0.04656, over 7275.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2637, pruned_loss=0.04298, over 1401080.46 frames.], batch size: 18, lr: 1.73e-04
2022-05-29 03:24:22,943 INFO [train.py:842] (3/4) Epoch 32, batch 850, loss[loss=0.1817, simple_loss=0.2781, pruned_loss=0.04264, over 7313.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2645, pruned_loss=0.04324, over 1408336.92 frames.], batch size: 25, lr: 1.73e-04
2022-05-29 03:25:02,012 INFO [train.py:842] (3/4) Epoch 32, batch 900, loss[loss=0.1608, simple_loss=0.2637, pruned_loss=0.02897, over 7329.00 frames.], tot_loss[loss=0.1758, simple_loss=0.265, pruned_loss=0.04326, over 1410255.79 frames.], batch size: 22, lr: 1.73e-04
2022-05-29 03:25:41,196 INFO [train.py:842] (3/4) Epoch 32, batch 950, loss[loss=0.143, simple_loss=0.2258, pruned_loss=0.03009, over 7214.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2631, pruned_loss=0.04303, over 1412267.11 frames.], batch size: 16, lr: 1.73e-04
2022-05-29 03:26:20,881 INFO [train.py:842] (3/4) Epoch 32, batch 1000, loss[loss=0.1414, simple_loss=0.231, pruned_loss=0.02592, over 7416.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2631, pruned_loss=0.04299, over 1415966.02 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:27:00,307 INFO [train.py:842] (3/4) Epoch 32, batch 1050, loss[loss=0.185, simple_loss=0.2802, pruned_loss=0.04494, over 7228.00 frames.], tot_loss[loss=0.174, simple_loss=0.2623, pruned_loss=0.04286, over 1420005.71 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:27:39,950 INFO [train.py:842] (3/4) Epoch 32, batch 1100, loss[loss=0.2125, simple_loss=0.2943, pruned_loss=0.06538, over 7212.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2612, pruned_loss=0.042, over 1419110.93 frames.], batch size: 22, lr: 1.73e-04
2022-05-29 03:28:19,226 INFO [train.py:842] (3/4) Epoch 32, batch 1150, loss[loss=0.1431, simple_loss=0.237, pruned_loss=0.02467, over 7147.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04136, over 1422482.92 frames.], batch size: 17, lr: 1.73e-04
2022-05-29 03:28:59,064 INFO [train.py:842] (3/4) Epoch 32, batch 1200, loss[loss=0.1567, simple_loss=0.2472, pruned_loss=0.03307, over 7414.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2611, pruned_loss=0.0417, over 1424522.23 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:29:38,276 INFO [train.py:842] (3/4) Epoch 32, batch 1250, loss[loss=0.1761, simple_loss=0.2701, pruned_loss=0.04103, over 7195.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2612, pruned_loss=0.04159, over 1418549.46 frames.], batch size: 23, lr: 1.73e-04
2022-05-29 03:30:17,923 INFO [train.py:842] (3/4) Epoch 32, batch 1300, loss[loss=0.1583, simple_loss=0.2433, pruned_loss=0.03666, over 7162.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2618, pruned_loss=0.04184, over 1423533.59 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:30:57,284 INFO [train.py:842] (3/4) Epoch 32, batch 1350, loss[loss=0.1902, simple_loss=0.27, pruned_loss=0.05521, over 7334.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2615, pruned_loss=0.04189, over 1421735.46 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:31:37,063 INFO [train.py:842] (3/4) Epoch 32, batch 1400, loss[loss=0.1777, simple_loss=0.2716, pruned_loss=0.04187, over 7232.00 frames.], tot_loss[loss=0.173, simple_loss=0.2615, pruned_loss=0.04222, over 1422919.14 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:32:16,163 INFO [train.py:842] (3/4) Epoch 32, batch 1450, loss[loss=0.1724, simple_loss=0.2718, pruned_loss=0.03647, over 7314.00 frames.], tot_loss[loss=0.174, simple_loss=0.2624, pruned_loss=0.04278, over 1424812.70 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:32:55,631 INFO [train.py:842] (3/4) Epoch 32, batch 1500, loss[loss=0.2494, simple_loss=0.3342, pruned_loss=0.08228, over 5064.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2618, pruned_loss=0.04229, over 1423346.19 frames.], batch size: 52, lr: 1.73e-04
2022-05-29 03:33:35,101 INFO [train.py:842] (3/4) Epoch 32, batch 1550, loss[loss=0.1922, simple_loss=0.2789, pruned_loss=0.05272, over 7401.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2627, pruned_loss=0.04315, over 1423364.10 frames.], batch size: 18, lr: 1.73e-04
2022-05-29 03:34:14,490 INFO [train.py:842] (3/4) Epoch 32, batch 1600, loss[loss=0.2114, simple_loss=0.2965, pruned_loss=0.06312, over 7209.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2622, pruned_loss=0.04268, over 1419195.72 frames.], batch size: 23, lr: 1.73e-04
2022-05-29 03:34:53,751 INFO [train.py:842] (3/4) Epoch 32, batch 1650, loss[loss=0.1658, simple_loss=0.2564, pruned_loss=0.0376, over 7413.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.04258, over 1417674.64 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:35:33,279 INFO [train.py:842] (3/4) Epoch 32, batch 1700, loss[loss=0.1852, simple_loss=0.2799, pruned_loss=0.04525, over 7113.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2624, pruned_loss=0.04287, over 1412419.44 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:36:12,380 INFO [train.py:842] (3/4) Epoch 32, batch 1750, loss[loss=0.231, simple_loss=0.3073, pruned_loss=0.0774, over 4461.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2626, pruned_loss=0.04297, over 1408636.45 frames.], batch size: 52, lr: 1.73e-04
2022-05-29 03:36:51,800 INFO [train.py:842] (3/4) Epoch 32, batch 1800, loss[loss=0.1825, simple_loss=0.2636, pruned_loss=0.05069, over 7230.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2636, pruned_loss=0.04344, over 1410195.11 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:37:30,776 INFO [train.py:842] (3/4) Epoch 32, batch 1850, loss[loss=0.1613, simple_loss=0.244, pruned_loss=0.03928, over 6980.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2641, pruned_loss=0.0438, over 1405342.67 frames.], batch size: 16, lr: 1.73e-04
2022-05-29 03:38:10,526 INFO [train.py:842] (3/4) Epoch 32, batch 1900, loss[loss=0.1629, simple_loss=0.2404, pruned_loss=0.04269, over 7363.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2616, pruned_loss=0.04272, over 1411444.27 frames.], batch size: 19, lr: 1.73e-04
2022-05-29 03:38:49,841 INFO [train.py:842] (3/4) Epoch 32, batch 1950, loss[loss=0.1697, simple_loss=0.2538, pruned_loss=0.04285, over 7342.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2615, pruned_loss=0.04251, over 1417373.01 frames.], batch size: 19, lr: 1.73e-04
2022-05-29 03:39:29,628 INFO [train.py:842] (3/4) Epoch 32, batch 2000, loss[loss=0.1561, simple_loss=0.2357, pruned_loss=0.03825, over 7280.00 frames.], tot_loss[loss=0.1724, simple_loss=0.261, pruned_loss=0.04193, over 1419258.85 frames.], batch size: 18, lr: 1.73e-04
2022-05-29 03:40:08,890 INFO [train.py:842] (3/4) Epoch 32, batch 2050, loss[loss=0.1623, simple_loss=0.2617, pruned_loss=0.03145, over 7146.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2603, pruned_loss=0.04156, over 1416191.13 frames.], batch size: 20, lr: 1.73e-04
2022-05-29 03:40:48,260 INFO [train.py:842] (3/4) Epoch 32, batch 2100, loss[loss=0.176, simple_loss=0.2461, pruned_loss=0.05294, over 6839.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04243, over 1415964.74 frames.], batch size: 15, lr: 1.73e-04
2022-05-29 03:41:27,439 INFO [train.py:842] (3/4) Epoch 32, batch 2150, loss[loss=0.1389, simple_loss=0.2308, pruned_loss=0.02347, over 7233.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2628, pruned_loss=0.04252, over 1420044.71 frames.], batch size: 21, lr: 1.73e-04
2022-05-29 03:42:07,267 INFO [train.py:842] (3/4) Epoch 32, batch 2200, loss[loss=0.2056, simple_loss=0.2841, pruned_loss=0.06362, over 7150.00 frames.], tot_loss[loss=0.174, simple_loss=0.2629, pruned_loss=0.04254, over 1423971.77 frames.], batch size: 26, lr: 1.73e-04
2022-05-29 03:42:46,578 INFO [train.py:842] (3/4) Epoch 32, batch 2250, loss[loss=0.2389, simple_loss=0.3163, pruned_loss=0.08072, over 7073.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2624, pruned_loss=0.04208, over 1425233.46 frames.], batch size: 18, lr: 1.73e-04
2022-05-29 03:43:25,962 INFO [train.py:842] (3/4) Epoch 32, batch 2300, loss[loss=0.1613, simple_loss=0.263, pruned_loss=0.02977, over 7337.00 frames.], tot_loss[loss=0.1745, simple_loss=0.263, pruned_loss=0.04302, over 1421734.37 frames.], batch size: 22, lr: 1.73e-04
2022-05-29 03:44:05,268 INFO [train.py:842] (3/4) Epoch 32, batch 2350, loss[loss=0.189, simple_loss=0.2652, pruned_loss=0.05639, over 7264.00 frames.], tot_loss[loss=0.174, simple_loss=0.2626, pruned_loss=0.04265, over 1425808.18 frames.], batch size: 17, lr: 1.73e-04
2022-05-29 03:44:44,573 INFO [train.py:842] (3/4) Epoch 32, batch 2400, loss[loss=0.1852, simple_loss=0.2745, pruned_loss=0.04798, over 7321.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2621, pruned_loss=0.04273, over 1421429.16 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:45:24,067 INFO [train.py:842] (3/4) Epoch 32, batch 2450, loss[loss=0.2124, simple_loss=0.2979, pruned_loss=0.06346, over 7150.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2614, pruned_loss=0.04256, over 1422816.03 frames.], batch size: 26, lr: 1.72e-04
2022-05-29 03:46:03,804 INFO [train.py:842] (3/4) Epoch 32, batch 2500, loss[loss=0.1527, simple_loss=0.2411, pruned_loss=0.03219, over 7281.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2618, pruned_loss=0.04263, over 1425175.37 frames.], batch size: 17, lr: 1.72e-04
2022-05-29 03:46:43,176 INFO [train.py:842] (3/4) Epoch 32, batch 2550, loss[loss=0.166, simple_loss=0.2498, pruned_loss=0.04112, over 7333.00 frames.], tot_loss[loss=0.175, simple_loss=0.2632, pruned_loss=0.04345, over 1422585.39 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:47:22,978 INFO [train.py:842] (3/4) Epoch 32, batch 2600, loss[loss=0.1565, simple_loss=0.2407, pruned_loss=0.03614, over 7126.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2633, pruned_loss=0.04362, over 1421402.07 frames.], batch size: 17, lr: 1.72e-04
2022-05-29 03:48:02,155 INFO [train.py:842] (3/4) Epoch 32, batch 2650, loss[loss=0.1812, simple_loss=0.2657, pruned_loss=0.04837, over 7161.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2626, pruned_loss=0.04322, over 1424127.22 frames.], batch size: 26, lr: 1.72e-04
2022-05-29 03:48:41,718 INFO [train.py:842] (3/4) Epoch 32, batch 2700, loss[loss=0.1497, simple_loss=0.2385, pruned_loss=0.03043, over 7335.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2633, pruned_loss=0.04347, over 1422772.57 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:49:21,047 INFO [train.py:842] (3/4) Epoch 32, batch 2750, loss[loss=0.1864, simple_loss=0.2758, pruned_loss=0.04852, over 7040.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2628, pruned_loss=0.04298, over 1425124.66 frames.], batch size: 28, lr: 1.72e-04
2022-05-29 03:50:00,744 INFO [train.py:842] (3/4) Epoch 32, batch 2800, loss[loss=0.1503, simple_loss=0.2274, pruned_loss=0.03656, over 7413.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2617, pruned_loss=0.04271, over 1424424.17 frames.], batch size: 18, lr: 1.72e-04
2022-05-29 03:50:40,058 INFO [train.py:842] (3/4) Epoch 32, batch 2850, loss[loss=0.1505, simple_loss=0.2467, pruned_loss=0.02711, over 6534.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2625, pruned_loss=0.04288, over 1420916.11 frames.], batch size: 38, lr: 1.72e-04
2022-05-29 03:51:19,913 INFO [train.py:842] (3/4) Epoch 32, batch 2900, loss[loss=0.1753, simple_loss=0.2676, pruned_loss=0.04154, over 7237.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04372, over 1424924.37 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:51:58,817 INFO [train.py:842] (3/4) Epoch 32, batch 2950, loss[loss=0.2012, simple_loss=0.2861, pruned_loss=0.05816, over 7184.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2645, pruned_loss=0.04346, over 1418369.26 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 03:52:38,256 INFO [train.py:842] (3/4) Epoch 32, batch 3000, loss[loss=0.2087, simple_loss=0.2946, pruned_loss=0.06136, over 7427.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2648, pruned_loss=0.04389, over 1419708.60 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:52:38,258 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 03:52:48,107 INFO [train.py:871] (3/4) Epoch 32, validation: loss=0.1619, simple_loss=0.2592, pruned_loss=0.03236, over 868885.00 frames.
2022-05-29 03:53:27,715 INFO [train.py:842] (3/4) Epoch 32, batch 3050, loss[loss=0.1846, simple_loss=0.2854, pruned_loss=0.04186, over 7339.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2642, pruned_loss=0.04349, over 1424442.79 frames.], batch size: 25, lr: 1.72e-04
2022-05-29 03:54:10,058 INFO [train.py:842] (3/4) Epoch 32, batch 3100, loss[loss=0.1724, simple_loss=0.2597, pruned_loss=0.04261, over 7006.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2638, pruned_loss=0.04357, over 1427059.47 frames.], batch size: 28, lr: 1.72e-04
2022-05-29 03:54:49,466 INFO [train.py:842] (3/4) Epoch 32, batch 3150, loss[loss=0.1387, simple_loss=0.2197, pruned_loss=0.0288, over 7291.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2623, pruned_loss=0.04275, over 1425017.84 frames.], batch size: 17, lr: 1.72e-04
2022-05-29 03:55:29,007 INFO [train.py:842] (3/4) Epoch 32, batch 3200, loss[loss=0.1535, simple_loss=0.2398, pruned_loss=0.03357, over 7123.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2632, pruned_loss=0.04272, over 1427471.53 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 03:56:08,332 INFO [train.py:842] (3/4) Epoch 32, batch 3250, loss[loss=0.2127, simple_loss=0.2993, pruned_loss=0.06298, over 7343.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2632, pruned_loss=0.04253, over 1428217.64 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 03:56:47,719 INFO [train.py:842] (3/4) Epoch 32, batch 3300, loss[loss=0.1801, simple_loss=0.2713, pruned_loss=0.04443, over 7434.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2637, pruned_loss=0.04273, over 1424133.21 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:57:27,357 INFO [train.py:842] (3/4) Epoch 32, batch 3350, loss[loss=0.1855, simple_loss=0.2802, pruned_loss=0.04545, over 7315.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04242, over 1425761.09 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 03:58:06,777 INFO [train.py:842] (3/4) Epoch 32, batch 3400, loss[loss=0.1793, simple_loss=0.2622, pruned_loss=0.04826, over 7328.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2633, pruned_loss=0.0426, over 1422295.60 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 03:58:45,720 INFO [train.py:842] (3/4) Epoch 32, batch 3450, loss[loss=0.1975, simple_loss=0.292, pruned_loss=0.05146, over 7193.00 frames.], tot_loss[loss=0.175, simple_loss=0.2642, pruned_loss=0.04289, over 1424896.19 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 03:59:25,415 INFO [train.py:842] (3/4) Epoch 32, batch 3500, loss[loss=0.1731, simple_loss=0.265, pruned_loss=0.04061, over 7289.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2644, pruned_loss=0.04285, over 1427585.33 frames.], batch size: 24, lr: 1.72e-04
2022-05-29 04:00:04,749 INFO [train.py:842] (3/4) Epoch 32, batch 3550, loss[loss=0.186, simple_loss=0.2765, pruned_loss=0.04775, over 7362.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04282, over 1430507.72 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 04:00:44,332 INFO [train.py:842] (3/4) Epoch 32, batch 3600, loss[loss=0.1927, simple_loss=0.2791, pruned_loss=0.05313, over 6552.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2623, pruned_loss=0.04198, over 1428774.72 frames.], batch size: 38, lr: 1.72e-04
2022-05-29 04:01:23,440 INFO [train.py:842] (3/4) Epoch 32, batch 3650, loss[loss=0.1334, simple_loss=0.2256, pruned_loss=0.02057, over 7234.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2636, pruned_loss=0.04267, over 1428091.00 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:02:03,207 INFO [train.py:842] (3/4) Epoch 32, batch 3700, loss[loss=0.1699, simple_loss=0.2415, pruned_loss=0.0492, over 7134.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2626, pruned_loss=0.04236, over 1430182.68 frames.], batch size: 17, lr: 1.72e-04
2022-05-29 04:02:42,028 INFO [train.py:842] (3/4) Epoch 32, batch 3750, loss[loss=0.2042, simple_loss=0.2907, pruned_loss=0.05885, over 7217.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2628, pruned_loss=0.04236, over 1425160.67 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 04:03:21,673 INFO [train.py:842] (3/4) Epoch 32, batch 3800, loss[loss=0.1778, simple_loss=0.2643, pruned_loss=0.04569, over 7373.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2629, pruned_loss=0.04202, over 1426090.53 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 04:04:01,025 INFO [train.py:842] (3/4) Epoch 32, batch 3850, loss[loss=0.1761, simple_loss=0.2686, pruned_loss=0.0418, over 7434.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2625, pruned_loss=0.04195, over 1428507.66 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:04:40,446 INFO [train.py:842] (3/4) Epoch 32, batch 3900, loss[loss=0.1862, simple_loss=0.2712, pruned_loss=0.05054, over 7162.00 frames.], tot_loss[loss=0.173, simple_loss=0.2619, pruned_loss=0.0421, over 1429300.43 frames.], batch size: 18, lr: 1.72e-04
2022-05-29 04:05:19,800 INFO [train.py:842] (3/4) Epoch 32, batch 3950, loss[loss=0.1524, simple_loss=0.2459, pruned_loss=0.02945, over 7229.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2626, pruned_loss=0.04248, over 1423982.53 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:05:59,331 INFO [train.py:842] (3/4) Epoch 32, batch 4000, loss[loss=0.1596, simple_loss=0.2465, pruned_loss=0.0364, over 7403.00 frames.], tot_loss[loss=0.173, simple_loss=0.2615, pruned_loss=0.04228, over 1421110.04 frames.], batch size: 18, lr: 1.72e-04
2022-05-29 04:06:38,596 INFO [train.py:842] (3/4) Epoch 32, batch 4050, loss[loss=0.173, simple_loss=0.2658, pruned_loss=0.04011, over 7377.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.0427, over 1419791.43 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 04:07:17,983 INFO [train.py:842] (3/4) Epoch 32, batch 4100, loss[loss=0.1632, simple_loss=0.2663, pruned_loss=0.03001, over 7152.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2637, pruned_loss=0.04306, over 1419518.58 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:07:57,049 INFO [train.py:842] (3/4) Epoch 32, batch 4150, loss[loss=0.1657, simple_loss=0.2663, pruned_loss=0.03254, over 7027.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2647, pruned_loss=0.04343, over 1422644.15 frames.], batch size: 32, lr: 1.72e-04
2022-05-29 04:08:36,789 INFO [train.py:842] (3/4) Epoch 32, batch 4200, loss[loss=0.1819, simple_loss=0.2812, pruned_loss=0.04133, over 7318.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2638, pruned_loss=0.04303, over 1426162.52 frames.], batch size: 24, lr: 1.72e-04
2022-05-29 04:09:15,973 INFO [train.py:842] (3/4) Epoch 32, batch 4250, loss[loss=0.1755, simple_loss=0.2694, pruned_loss=0.04085, over 7242.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2637, pruned_loss=0.04323, over 1421797.33 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:09:55,681 INFO [train.py:842] (3/4) Epoch 32, batch 4300, loss[loss=0.1627, simple_loss=0.2518, pruned_loss=0.03685, over 7153.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2627, pruned_loss=0.04247, over 1424214.89 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:10:34,788 INFO [train.py:842] (3/4) Epoch 32, batch 4350, loss[loss=0.1576, simple_loss=0.2515, pruned_loss=0.03181, over 6326.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2627, pruned_loss=0.0423, over 1426000.74 frames.], batch size: 37, lr: 1.72e-04
2022-05-29 04:11:14,402 INFO [train.py:842] (3/4) Epoch 32, batch 4400, loss[loss=0.1679, simple_loss=0.2681, pruned_loss=0.03381, over 7327.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2627, pruned_loss=0.04249, over 1426351.32 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 04:11:53,992 INFO [train.py:842] (3/4) Epoch 32, batch 4450, loss[loss=0.1824, simple_loss=0.29, pruned_loss=0.03737, over 7263.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2615, pruned_loss=0.0421, over 1430398.13 frames.], batch size: 19, lr: 1.72e-04
2022-05-29 04:12:33,492 INFO [train.py:842] (3/4) Epoch 32, batch 4500, loss[loss=0.1693, simple_loss=0.2565, pruned_loss=0.04105, over 7123.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2616, pruned_loss=0.04195, over 1425230.04 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:13:12,633 INFO [train.py:842] (3/4) Epoch 32, batch 4550, loss[loss=0.1768, simple_loss=0.266, pruned_loss=0.04373, over 7344.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2614, pruned_loss=0.04192, over 1417012.49 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 04:13:52,364 INFO [train.py:842] (3/4) Epoch 32, batch 4600, loss[loss=0.1564, simple_loss=0.2423, pruned_loss=0.0353, over 7009.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2614, pruned_loss=0.04183, over 1419951.54 frames.], batch size: 16, lr: 1.72e-04
2022-05-29 04:14:31,876 INFO [train.py:842] (3/4) Epoch 32, batch 4650, loss[loss=0.1669, simple_loss=0.2629, pruned_loss=0.03543, over 7227.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2626, pruned_loss=0.04245, over 1424465.39 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:15:11,521 INFO [train.py:842] (3/4) Epoch 32, batch 4700, loss[loss=0.2008, simple_loss=0.2822, pruned_loss=0.05968, over 7235.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2629, pruned_loss=0.043, over 1425879.92 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:15:51,133 INFO [train.py:842] (3/4) Epoch 32, batch 4750, loss[loss=0.1851, simple_loss=0.271, pruned_loss=0.04956, over 7210.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.04268, over 1424602.49 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 04:16:30,618 INFO [train.py:842] (3/4) Epoch 32, batch 4800, loss[loss=0.1708, simple_loss=0.2641, pruned_loss=0.0388, over 7325.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2623, pruned_loss=0.04263, over 1420950.87 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:17:09,882 INFO [train.py:842] (3/4) Epoch 32, batch 4850, loss[loss=0.1684, simple_loss=0.2616, pruned_loss=0.03763, over 7224.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2619, pruned_loss=0.04211, over 1421423.99 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:17:49,604 INFO [train.py:842] (3/4) Epoch 32, batch 4900, loss[loss=0.1938, simple_loss=0.287, pruned_loss=0.05026, over 7291.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2625, pruned_loss=0.04245, over 1423054.86 frames.], batch size: 25, lr: 1.72e-04
2022-05-29 04:18:28,912 INFO [train.py:842] (3/4) Epoch 32, batch 4950, loss[loss=0.1502, simple_loss=0.24, pruned_loss=0.03018, over 7428.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2622, pruned_loss=0.04218, over 1426470.50 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:19:08,246 INFO [train.py:842] (3/4) Epoch 32, batch 5000, loss[loss=0.1914, simple_loss=0.2694, pruned_loss=0.05667, over 6677.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2637, pruned_loss=0.04291, over 1425052.56 frames.], batch size: 31, lr: 1.72e-04
2022-05-29 04:19:47,597 INFO [train.py:842] (3/4) Epoch 32, batch 5050, loss[loss=0.1542, simple_loss=0.2464, pruned_loss=0.03093, over 7278.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2625, pruned_loss=0.04233, over 1424611.51 frames.], batch size: 18, lr: 1.72e-04
2022-05-29 04:20:27,259 INFO [train.py:842] (3/4) Epoch 32, batch 5100, loss[loss=0.1819, simple_loss=0.2697, pruned_loss=0.04703, over 7315.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2616, pruned_loss=0.042, over 1423053.57 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:21:06,325 INFO [train.py:842] (3/4) Epoch 32, batch 5150, loss[loss=0.1665, simple_loss=0.258, pruned_loss=0.03753, over 7065.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2627, pruned_loss=0.04254, over 1418099.68 frames.], batch size: 18, lr: 1.72e-04
2022-05-29 04:21:45,904 INFO [train.py:842] (3/4) Epoch 32, batch 5200, loss[loss=0.1344, simple_loss=0.2194, pruned_loss=0.02474, over 7283.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2631, pruned_loss=0.04286, over 1420325.35 frames.], batch size: 17, lr: 1.72e-04
2022-05-29 04:22:25,268 INFO [train.py:842] (3/4) Epoch 32, batch 5250, loss[loss=0.2149, simple_loss=0.2763, pruned_loss=0.07675, over 7009.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2627, pruned_loss=0.04305, over 1420464.84 frames.], batch size: 16, lr: 1.72e-04
2022-05-29 04:23:04,883 INFO [train.py:842] (3/4) Epoch 32, batch 5300, loss[loss=0.1473, simple_loss=0.2407, pruned_loss=0.02692, over 7232.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2616, pruned_loss=0.04286, over 1421635.48 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:23:43,923 INFO [train.py:842] (3/4) Epoch 32, batch 5350, loss[loss=0.1849, simple_loss=0.2723, pruned_loss=0.04872, over 7377.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2618, pruned_loss=0.04258, over 1424342.24 frames.], batch size: 23, lr: 1.72e-04
2022-05-29 04:24:23,435 INFO [train.py:842] (3/4) Epoch 32, batch 5400, loss[loss=0.1597, simple_loss=0.2492, pruned_loss=0.03514, over 7144.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2621, pruned_loss=0.0427, over 1425950.01 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:25:13,712 INFO [train.py:842] (3/4) Epoch 32, batch 5450, loss[loss=0.1219, simple_loss=0.205, pruned_loss=0.01934, over 6773.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2619, pruned_loss=0.04249, over 1427905.87 frames.], batch size: 15, lr: 1.72e-04
2022-05-29 04:25:53,349 INFO [train.py:842] (3/4) Epoch 32, batch 5500, loss[loss=0.1602, simple_loss=0.2635, pruned_loss=0.02846, over 7211.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.04217, over 1425339.45 frames.], batch size: 22, lr: 1.72e-04
2022-05-29 04:26:32,598 INFO [train.py:842] (3/4) Epoch 32, batch 5550, loss[loss=0.1825, simple_loss=0.2823, pruned_loss=0.04136, over 7409.00 frames.], tot_loss[loss=0.1733, simple_loss=0.262, pruned_loss=0.04228, over 1424953.49 frames.], batch size: 21, lr: 1.72e-04
2022-05-29 04:27:12,142 INFO [train.py:842] (3/4) Epoch 32, batch 5600, loss[loss=0.2131, simple_loss=0.2825, pruned_loss=0.07186, over 4989.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2618, pruned_loss=0.04192, over 1425583.09 frames.], batch size: 52, lr: 1.72e-04
2022-05-29 04:27:51,463 INFO [train.py:842] (3/4) Epoch 32, batch 5650, loss[loss=0.1991, simple_loss=0.2811, pruned_loss=0.05859, over 7319.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2635, pruned_loss=0.04286, over 1426024.32 frames.], batch size: 20, lr: 1.72e-04
2022-05-29 04:28:41,650 INFO [train.py:842] (3/4) Epoch 32, batch 5700, loss[loss=0.1959, simple_loss=0.2835, pruned_loss=0.0541, over 6998.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2634, pruned_loss=0.04293, over 1420240.81 frames.], batch size: 16, lr: 1.72e-04
2022-05-29 04:29:21,095 INFO [train.py:842] (3/4) Epoch 32, batch 5750, loss[loss=0.1875, simple_loss=0.2715, pruned_loss=0.05171, over 7449.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2622, pruned_loss=0.04241, over 1422671.15 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:30:11,326 INFO [train.py:842] (3/4) Epoch 32, batch 5800, loss[loss=0.1559, simple_loss=0.2449, pruned_loss=0.03342, over 7331.00 frames.], tot_loss[loss=0.173, simple_loss=0.2621, pruned_loss=0.04199, over 1419448.63 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:30:50,470 INFO [train.py:842] (3/4) Epoch 32, batch 5850, loss[loss=0.1516, simple_loss=0.2345, pruned_loss=0.03437, over 7348.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04241, over 1418386.55 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:31:30,326 INFO [train.py:842] (3/4) Epoch 32, batch 5900, loss[loss=0.2247, simple_loss=0.2909, pruned_loss=0.07922, over 7275.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2615, pruned_loss=0.04203, over 1424243.33 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 04:32:09,723 INFO [train.py:842] (3/4) Epoch 32, batch 5950, loss[loss=0.1559, simple_loss=0.256, pruned_loss=0.02792, over 7230.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2601, pruned_loss=0.04156, over 1422635.35 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:32:48,996 INFO [train.py:842] (3/4) Epoch 32, batch 6000, loss[loss=0.1478, simple_loss=0.2344, pruned_loss=0.03063, over 6990.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2613, pruned_loss=0.04252, over 1418021.26 frames.], batch size: 16, lr: 1.71e-04
2022-05-29 04:32:48,997 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 04:32:58,749 INFO [train.py:871] (3/4) Epoch 32, validation: loss=0.1638, simple_loss=0.2607, pruned_loss=0.0334, over 868885.00 frames.
2022-05-29 04:33:38,113 INFO [train.py:842] (3/4) Epoch 32, batch 6050, loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04501, over 7271.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2611, pruned_loss=0.04193, over 1420938.98 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 04:34:17,903 INFO [train.py:842] (3/4) Epoch 32, batch 6100, loss[loss=0.1594, simple_loss=0.2493, pruned_loss=0.0347, over 7425.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2622, pruned_loss=0.04214, over 1422771.34 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:34:57,144 INFO [train.py:842] (3/4) Epoch 32, batch 6150, loss[loss=0.2307, simple_loss=0.3216, pruned_loss=0.06986, over 7287.00 frames.], tot_loss[loss=0.174, simple_loss=0.2629, pruned_loss=0.04258, over 1420984.32 frames.], batch size: 25, lr: 1.71e-04
2022-05-29 04:35:36,539 INFO [train.py:842] (3/4) Epoch 32, batch 6200, loss[loss=0.168, simple_loss=0.2688, pruned_loss=0.03361, over 7415.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2635, pruned_loss=0.04259, over 1423425.56 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 04:36:16,135 INFO [train.py:842] (3/4) Epoch 32, batch 6250, loss[loss=0.1654, simple_loss=0.2492, pruned_loss=0.04082, over 7424.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2623, pruned_loss=0.04217, over 1426474.97 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 04:36:55,665 INFO [train.py:842] (3/4) Epoch 32, batch 6300, loss[loss=0.1423, simple_loss=0.2303, pruned_loss=0.02716, over 7070.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2623, pruned_loss=0.04221, over 1425478.73 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 04:37:34,967 INFO [train.py:842] (3/4) Epoch 32, batch 6350, loss[loss=0.1718, simple_loss=0.2688, pruned_loss=0.03744, over 7362.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.0422, over 1424194.17 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:38:14,643 INFO [train.py:842] (3/4) Epoch 32, batch 6400, loss[loss=0.202, simple_loss=0.2867, pruned_loss=0.05865, over 7301.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2629, pruned_loss=0.04213, over 1424392.50 frames.], batch size: 25, lr: 1.71e-04
2022-05-29 04:38:53,836 INFO [train.py:842] (3/4) Epoch 32, batch 6450, loss[loss=0.1585, simple_loss=0.2534, pruned_loss=0.03178, over 7436.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2622, pruned_loss=0.04207, over 1425974.89 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:39:33,298 INFO [train.py:842] (3/4) Epoch 32, batch 6500, loss[loss=0.1804, simple_loss=0.27, pruned_loss=0.04543, over 7292.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2634, pruned_loss=0.04321, over 1424100.40 frames.], batch size: 24, lr: 1.71e-04
2022-05-29 04:40:12,630 INFO [train.py:842] (3/4) Epoch 32, batch 6550, loss[loss=0.1629, simple_loss=0.2426, pruned_loss=0.04165, over 7424.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2625, pruned_loss=0.04268, over 1420634.92 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 04:40:52,226 INFO [train.py:842] (3/4) Epoch 32, batch 6600, loss[loss=0.1581, simple_loss=0.2483, pruned_loss=0.03395, over 6725.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2618, pruned_loss=0.0424, over 1421931.76 frames.], batch size: 31, lr: 1.71e-04
2022-05-29 04:41:31,515 INFO [train.py:842] (3/4) Epoch 32, batch 6650, loss[loss=0.1704, simple_loss=0.2613, pruned_loss=0.03971, over 7292.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2608, pruned_loss=0.04169, over 1419599.45 frames.], batch size: 25, lr: 1.71e-04
2022-05-29 04:42:11,091 INFO [train.py:842] (3/4) Epoch 32, batch 6700, loss[loss=0.1227, simple_loss=0.2148, pruned_loss=0.01527, over 7155.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2612, pruned_loss=0.04163, over 1418925.09 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:42:50,503 INFO [train.py:842] (3/4) Epoch 32, batch 6750, loss[loss=0.1707, simple_loss=0.2672, pruned_loss=0.0371, over 7205.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2616, pruned_loss=0.04172, over 1420042.58 frames.], batch size: 26, lr: 1.71e-04
2022-05-29 04:43:30,252 INFO [train.py:842] (3/4) Epoch 32, batch 6800, loss[loss=0.1779, simple_loss=0.2662, pruned_loss=0.04482, over 7240.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2615, pruned_loss=0.04184, over 1424951.75 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:44:09,487 INFO [train.py:842] (3/4) Epoch 32, batch 6850, loss[loss=0.1509, simple_loss=0.2408, pruned_loss=0.03056, over 7258.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2625, pruned_loss=0.0423, over 1425328.21 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:44:48,839 INFO [train.py:842] (3/4) Epoch 32, batch 6900, loss[loss=0.1644, simple_loss=0.2645, pruned_loss=0.03212, over 7234.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2621, pruned_loss=0.04166, over 1424662.17 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:45:27,994 INFO [train.py:842] (3/4) Epoch 32, batch 6950, loss[loss=0.176, simple_loss=0.2643, pruned_loss=0.04382, over 7155.00 frames.], tot_loss[loss=0.1737, simple_loss=0.263, pruned_loss=0.04216, over 1427392.68 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:46:07,538 INFO [train.py:842] (3/4) Epoch 32, batch 7000, loss[loss=0.1749, simple_loss=0.2621, pruned_loss=0.04389, over 7161.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2625, pruned_loss=0.04238, over 1426384.49 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:46:46,442 INFO [train.py:842] (3/4) Epoch 32, batch 7050, loss[loss=0.1872, simple_loss=0.2768, pruned_loss=0.04883, over 7191.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04281, over 1427355.26 frames.], batch size: 23, lr: 1.71e-04
2022-05-29 04:47:25,843 INFO [train.py:842] (3/4) Epoch 32, batch 7100, loss[loss=0.1888, simple_loss=0.271, pruned_loss=0.05325, over 7211.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2635, pruned_loss=0.04268, over 1426055.42 frames.], batch size: 22, lr: 1.71e-04
2022-05-29 04:48:04,905 INFO [train.py:842] (3/4) Epoch 32, batch 7150, loss[loss=0.1683, simple_loss=0.2595, pruned_loss=0.03861, over 6907.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2636, pruned_loss=0.04301, over 1422860.29 frames.], batch size: 31, lr: 1.71e-04
2022-05-29 04:48:44,510 INFO [train.py:842] (3/4) Epoch 32, batch 7200, loss[loss=0.1794, simple_loss=0.2719, pruned_loss=0.04348, over 7217.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2634, pruned_loss=0.04267, over 1424570.56 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 04:49:23,978 INFO [train.py:842] (3/4) Epoch 32, batch 7250, loss[loss=0.1696, simple_loss=0.2659, pruned_loss=0.03666, over 7422.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2631, pruned_loss=0.04262, over 1429664.31 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 04:50:03,700 INFO [train.py:842] (3/4) Epoch 32, batch 7300, loss[loss=0.1723, simple_loss=0.2701, pruned_loss=0.03722, over 7407.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2613, pruned_loss=0.04205, over 1431869.54 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 04:50:43,032 INFO [train.py:842] (3/4) Epoch 32, batch 7350, loss[loss=0.1563, simple_loss=0.2557, pruned_loss=0.02845, over 7365.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04194, over 1430866.70 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:51:22,730 INFO [train.py:842] (3/4) Epoch 32, batch 7400, loss[loss=0.2324, simple_loss=0.3133, pruned_loss=0.07573, over 5146.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2618, pruned_loss=0.0422, over 1427007.82 frames.], batch size: 54, lr: 1.71e-04
2022-05-29 04:52:02,065 INFO [train.py:842] (3/4) Epoch 32, batch 7450, loss[loss=0.1705, simple_loss=0.262, pruned_loss=0.03954, over 7301.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2623, pruned_loss=0.04216, over 1428515.35 frames.], batch size: 24, lr: 1.71e-04
2022-05-29 04:52:41,502 INFO [train.py:842] (3/4) Epoch 32, batch 7500, loss[loss=0.2674, simple_loss=0.3336, pruned_loss=0.1006, over 7334.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2622, pruned_loss=0.04236, over 1426664.38 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:53:20,833 INFO [train.py:842] (3/4) Epoch 32, batch 7550, loss[loss=0.1838, simple_loss=0.2754, pruned_loss=0.04609, over 7298.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.04177, over 1426307.01 frames.], batch size: 24, lr: 1.71e-04
2022-05-29 04:54:00,365 INFO [train.py:842] (3/4) Epoch 32, batch 7600, loss[loss=0.1449, simple_loss=0.2419, pruned_loss=0.02393, over 7352.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2615, pruned_loss=0.04175, over 1424675.23 frames.], batch size: 19, lr: 1.71e-04
2022-05-29 04:54:39,827 INFO [train.py:842] (3/4) Epoch 32, batch 7650, loss[loss=0.2021, simple_loss=0.275, pruned_loss=0.0646, over 7228.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04188, over 1426320.82 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:55:19,482 INFO [train.py:842] (3/4) Epoch 32, batch 7700, loss[loss=0.202, simple_loss=0.2941, pruned_loss=0.05499, over 7296.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2614, pruned_loss=0.04204, over 1428232.15 frames.], batch size: 24, lr: 1.71e-04
2022-05-29 04:55:58,593 INFO [train.py:842] (3/4) Epoch 32, batch 7750, loss[loss=0.1802, simple_loss=0.2659, pruned_loss=0.04725, over 7048.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2622, pruned_loss=0.04285, over 1422539.37 frames.], batch size: 28, lr: 1.71e-04
2022-05-29 04:56:38,175 INFO [train.py:842] (3/4) Epoch 32, batch 7800, loss[loss=0.1973, simple_loss=0.2926, pruned_loss=0.05103, over 6704.00 frames.], tot_loss[loss=0.174, simple_loss=0.262, pruned_loss=0.04302, over 1422669.66 frames.], batch size: 38, lr: 1.71e-04
2022-05-29 04:57:17,406 INFO [train.py:842] (3/4) Epoch 32, batch 7850, loss[loss=0.1418, simple_loss=0.2244, pruned_loss=0.02961, over 7137.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2614, pruned_loss=0.04236, over 1422556.04 frames.], batch size: 17, lr: 1.71e-04
2022-05-29 04:57:56,992 INFO [train.py:842] (3/4) Epoch 32, batch 7900, loss[loss=0.1839, simple_loss=0.2732, pruned_loss=0.04728, over 7236.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2617, pruned_loss=0.04245, over 1422782.56 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:58:36,031 INFO [train.py:842] (3/4) Epoch 32, batch 7950, loss[loss=0.1851, simple_loss=0.2749, pruned_loss=0.04767, over 6757.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2639, pruned_loss=0.04334, over 1424544.37 frames.], batch size: 31, lr: 1.71e-04
2022-05-29 04:59:15,401 INFO [train.py:842] (3/4) Epoch 32, batch 8000, loss[loss=0.1681, simple_loss=0.268, pruned_loss=0.03404, over 7329.00 frames.], tot_loss[loss=0.1744, simple_loss=0.263, pruned_loss=0.04285, over 1423141.06 frames.], batch size: 20, lr: 1.71e-04
2022-05-29 04:59:54,733 INFO [train.py:842] (3/4) Epoch 32, batch 8050, loss[loss=0.1643, simple_loss=0.2422, pruned_loss=0.04317, over 7417.00 frames.], tot_loss[loss=0.1746, simple_loss=0.263, pruned_loss=0.04307, over 1419995.49 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:00:34,445 INFO [train.py:842] (3/4) Epoch 32, batch 8100, loss[loss=0.1633, simple_loss=0.2502, pruned_loss=0.03819, over 6779.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2633, pruned_loss=0.04284, over 1419330.60 frames.], batch size: 15, lr: 1.71e-04
2022-05-29 05:01:13,708 INFO [train.py:842] (3/4) Epoch 32, batch 8150, loss[loss=0.1805, simple_loss=0.2655, pruned_loss=0.04772, over 7127.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2647, pruned_loss=0.04335, over 1421773.94 frames.], batch size: 26, lr: 1.71e-04
2022-05-29 05:01:53,227 INFO [train.py:842] (3/4) Epoch 32, batch 8200, loss[loss=0.1864, simple_loss=0.295, pruned_loss=0.03893, over 7220.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2651, pruned_loss=0.04393, over 1421575.13 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 05:02:32,283 INFO [train.py:842] (3/4) Epoch 32, batch 8250, loss[loss=0.1845, simple_loss=0.2746, pruned_loss=0.04723, over 6405.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2634, pruned_loss=0.04307, over 1419976.65 frames.], batch size: 37, lr: 1.71e-04
2022-05-29 05:03:11,975 INFO [train.py:842] (3/4) Epoch 32, batch 8300, loss[loss=0.1531, simple_loss=0.2354, pruned_loss=0.03542, over 7058.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2633, pruned_loss=0.04344, over 1423544.87 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:03:50,998 INFO [train.py:842] (3/4) Epoch 32, batch 8350, loss[loss=0.1664, simple_loss=0.2586, pruned_loss=0.03714, over 7073.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2641, pruned_loss=0.04332, over 1424608.41 frames.], batch size: 28, lr: 1.71e-04
2022-05-29 05:04:30,246 INFO [train.py:842] (3/4) Epoch 32, batch 8400, loss[loss=0.1606, simple_loss=0.2501, pruned_loss=0.03552, over 7162.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2644, pruned_loss=0.04329, over 1420766.67 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:05:09,527 INFO [train.py:842] (3/4) Epoch 32, batch 8450, loss[loss=0.1953, simple_loss=0.2684, pruned_loss=0.06116, over 7280.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2642, pruned_loss=0.0437, over 1417584.40 frames.], batch size: 17, lr: 1.71e-04
2022-05-29 05:05:49,206 INFO [train.py:842] (3/4) Epoch 32, batch 8500, loss[loss=0.1577, simple_loss=0.2447, pruned_loss=0.0353, over 7056.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2632, pruned_loss=0.04359, over 1417248.99 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:06:28,103 INFO [train.py:842] (3/4) Epoch 32, batch 8550, loss[loss=0.1964, simple_loss=0.2806, pruned_loss=0.05611, over 7113.00 frames.], tot_loss[loss=0.1749, simple_loss=0.263, pruned_loss=0.04339, over 1417413.32 frames.], batch size: 28, lr: 1.71e-04
2022-05-29 05:07:07,498 INFO [train.py:842] (3/4) Epoch 32, batch 8600, loss[loss=0.1749, simple_loss=0.272, pruned_loss=0.03886, over 7227.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2629, pruned_loss=0.04315, over 1415103.99 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 05:07:46,522 INFO [train.py:842] (3/4) Epoch 32, batch 8650, loss[loss=0.1379, simple_loss=0.2221, pruned_loss=0.02683, over 6817.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2619, pruned_loss=0.04273, over 1418933.81 frames.], batch size: 15, lr: 1.71e-04
2022-05-29 05:08:26,010 INFO [train.py:842] (3/4) Epoch 32, batch 8700, loss[loss=0.1355, simple_loss=0.2162, pruned_loss=0.02747, over 7421.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2621, pruned_loss=0.04302, over 1422929.27 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:09:05,098 INFO [train.py:842] (3/4) Epoch 32, batch 8750, loss[loss=0.287, simple_loss=0.3574, pruned_loss=0.1083, over 4910.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.04331, over 1417094.37 frames.], batch size: 52, lr: 1.71e-04
2022-05-29 05:09:44,433 INFO [train.py:842] (3/4) Epoch 32, batch 8800, loss[loss=0.2244, simple_loss=0.3158, pruned_loss=0.06654, over 7293.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2614, pruned_loss=0.04273, over 1410523.81 frames.], batch size: 24, lr: 1.71e-04
2022-05-29 05:10:23,514 INFO [train.py:842] (3/4) Epoch 32, batch 8850, loss[loss=0.1823, simple_loss=0.2615, pruned_loss=0.05156, over 7064.00 frames.], tot_loss[loss=0.1751, simple_loss=0.263, pruned_loss=0.04358, over 1409643.27 frames.], batch size: 18, lr: 1.71e-04
2022-05-29 05:11:02,874 INFO [train.py:842] (3/4) Epoch 32, batch 8900, loss[loss=0.1776, simple_loss=0.2763, pruned_loss=0.03945, over 7329.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2638, pruned_loss=0.04434, over 1400027.65 frames.], batch size: 21, lr: 1.71e-04
2022-05-29 05:11:41,551 INFO [train.py:842] (3/4) Epoch 32, batch 8950, loss[loss=0.203, simple_loss=0.2957, pruned_loss=0.05515, over 4779.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2648, pruned_loss=0.04466, over 1395148.95 frames.], batch size: 52, lr: 1.71e-04
2022-05-29 05:12:20,912 INFO [train.py:842] (3/4) Epoch 32, batch 9000, loss[loss=0.1491, simple_loss=0.2282, pruned_loss=0.03505, over 6802.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2648, pruned_loss=0.04486, over 1389253.88 frames.], batch size: 15, lr: 1.71e-04
2022-05-29 05:12:20,913 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 05:12:30,815 INFO [train.py:871] (3/4) Epoch 32, validation: loss=0.1637, simple_loss=0.261, pruned_loss=0.03323, over 868885.00 frames.
2022-05-29 05:13:09,666 INFO [train.py:842] (3/4) Epoch 32, batch 9050, loss[loss=0.2148, simple_loss=0.3032, pruned_loss=0.06317, over 7065.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04502, over 1378781.66 frames.], batch size: 28, lr: 1.71e-04
2022-05-29 05:13:48,012 INFO [train.py:842] (3/4) Epoch 32, batch 9100, loss[loss=0.2555, simple_loss=0.3193, pruned_loss=0.09586, over 5174.00 frames.], tot_loss[loss=0.182, simple_loss=0.2692, pruned_loss=0.04738, over 1329704.98 frames.], batch size: 52, lr: 1.71e-04
2022-05-29 05:14:25,948 INFO [train.py:842] (3/4) Epoch 32, batch 9150, loss[loss=0.1837, simple_loss=0.2692, pruned_loss=0.04911, over 4953.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2713, pruned_loss=0.04912, over 1257279.83 frames.], batch size: 52, lr: 1.71e-04
2022-05-29 05:15:18,087 INFO [train.py:842] (3/4) Epoch 33, batch 0, loss[loss=0.1599, simple_loss=0.2481, pruned_loss=0.03588, over 6808.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2481, pruned_loss=0.03588, over 6808.00 frames.], batch size: 31, lr: 1.68e-04
2022-05-29 05:15:57,438 INFO [train.py:842] (3/4) Epoch 33, batch 50, loss[loss=0.2076, simple_loss=0.291, pruned_loss=0.06206, over 4877.00 frames.], tot_loss[loss=0.1732, simple_loss=0.264, pruned_loss=0.04121, over 314371.34 frames.], batch size: 53, lr: 1.68e-04
2022-05-29 05:16:36,927 INFO [train.py:842] (3/4) Epoch 33, batch 100, loss[loss=0.1579, simple_loss=0.2535, pruned_loss=0.03114, over 6334.00 frames.], tot_loss[loss=0.1738, simple_loss=0.264, pruned_loss=0.04181, over 559111.67 frames.], batch size: 37, lr: 1.68e-04
2022-05-29 05:17:16,107 INFO [train.py:842] (3/4) Epoch 33, batch 150, loss[loss=0.1855, simple_loss=0.2712, pruned_loss=0.04986, over 7197.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2655, pruned_loss=0.0426, over 752079.71 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:17:55,493 INFO [train.py:842] (3/4) Epoch 33, batch 200, loss[loss=0.1522, simple_loss=0.2307, pruned_loss=0.03689, over 6999.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2634, pruned_loss=0.04182, over 895451.80 frames.], batch size: 16, lr: 1.68e-04
2022-05-29 05:18:34,585 INFO [train.py:842] (3/4) Epoch 33, batch 250, loss[loss=0.1621, simple_loss=0.2563, pruned_loss=0.03398, over 7232.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2637, pruned_loss=0.04175, over 1009591.96 frames.], batch size: 20, lr: 1.68e-04
2022-05-29 05:19:13,849 INFO [train.py:842] (3/4) Epoch 33, batch 300, loss[loss=0.2072, simple_loss=0.2974, pruned_loss=0.05843, over 6715.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2642, pruned_loss=0.04233, over 1093117.70 frames.], batch size: 31, lr: 1.68e-04
2022-05-29 05:19:52,985 INFO [train.py:842] (3/4) Epoch 33, batch 350, loss[loss=0.1478, simple_loss=0.2232, pruned_loss=0.0362, over 7422.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2642, pruned_loss=0.04252, over 1164237.54 frames.], batch size: 18, lr: 1.68e-04
2022-05-29 05:20:32,729 INFO [train.py:842] (3/4) Epoch 33, batch 400, loss[loss=0.1884, simple_loss=0.2711, pruned_loss=0.05283, over 7426.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2626, pruned_loss=0.04225, over 1220877.52 frames.], batch size: 20, lr: 1.68e-04
2022-05-29 05:21:12,026 INFO [train.py:842] (3/4) Epoch 33, batch 450, loss[loss=0.185, simple_loss=0.2745, pruned_loss=0.04769, over 6702.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2614, pruned_loss=0.04193, over 1262659.30 frames.], batch size: 31, lr: 1.68e-04
2022-05-29 05:21:51,584 INFO [train.py:842] (3/4) Epoch 33, batch 500, loss[loss=0.1548, simple_loss=0.2517, pruned_loss=0.02893, over 7205.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2624, pruned_loss=0.04214, over 1300560.70 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:22:30,647 INFO [train.py:842] (3/4) Epoch 33, batch 550, loss[loss=0.148, simple_loss=0.2413, pruned_loss=0.02735, over 7307.00 frames.], tot_loss[loss=0.1741, simple_loss=0.263, pruned_loss=0.04255, over 1329489.12 frames.], batch size: 21, lr: 1.68e-04
2022-05-29 05:23:09,948 INFO [train.py:842] (3/4) Epoch 33, batch 600, loss[loss=0.207, simple_loss=0.2912, pruned_loss=0.06138, over 7303.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2637, pruned_loss=0.04231, over 1347380.56 frames.], batch size: 24, lr: 1.68e-04
2022-05-29 05:23:49,151 INFO [train.py:842] (3/4) Epoch 33, batch 650, loss[loss=0.1763, simple_loss=0.2635, pruned_loss=0.0445, over 7196.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2633, pruned_loss=0.04221, over 1364550.06 frames.], batch size: 26, lr: 1.68e-04
2022-05-29 05:24:28,747 INFO [train.py:842] (3/4) Epoch 33, batch 700, loss[loss=0.1509, simple_loss=0.2299, pruned_loss=0.0359, over 7149.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2633, pruned_loss=0.04251, over 1375909.83 frames.], batch size: 17, lr: 1.68e-04
2022-05-29 05:25:07,953 INFO [train.py:842] (3/4) Epoch 33, batch 750, loss[loss=0.1912, simple_loss=0.292, pruned_loss=0.04518, over 7217.00 frames.], tot_loss[loss=0.175, simple_loss=0.2643, pruned_loss=0.04282, over 1381240.39 frames.], batch size: 21, lr: 1.68e-04
2022-05-29 05:25:47,805 INFO [train.py:842] (3/4) Epoch 33, batch 800, loss[loss=0.171, simple_loss=0.2489, pruned_loss=0.04651, over 7438.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2624, pruned_loss=0.04229, over 1392339.34 frames.], batch size: 20, lr: 1.68e-04
2022-05-29 05:26:26,906 INFO [train.py:842] (3/4) Epoch 33, batch 850, loss[loss=0.1645, simple_loss=0.2586, pruned_loss=0.03521, over 7388.00 frames.], tot_loss[loss=0.1738, simple_loss=0.263, pruned_loss=0.04229, over 1399395.11 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:27:06,489 INFO [train.py:842] (3/4) Epoch 33, batch 900, loss[loss=0.1814, simple_loss=0.2673, pruned_loss=0.04774, over 7190.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2618, pruned_loss=0.04201, over 1408777.87 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:27:45,844 INFO [train.py:842] (3/4) Epoch 33, batch 950, loss[loss=0.1568, simple_loss=0.2594, pruned_loss=0.02714, over 7427.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2621, pruned_loss=0.04204, over 1413767.32 frames.], batch size: 20, lr: 1.68e-04
2022-05-29 05:28:25,579 INFO [train.py:842] (3/4) Epoch 33, batch 1000, loss[loss=0.1656, simple_loss=0.2518, pruned_loss=0.03972, over 7189.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2613, pruned_loss=0.0419, over 1413419.28 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:29:04,495 INFO [train.py:842] (3/4) Epoch 33, batch 1050, loss[loss=0.1753, simple_loss=0.2623, pruned_loss=0.04417, over 7103.00 frames.], tot_loss[loss=0.1731, simple_loss=0.262, pruned_loss=0.04208, over 1412380.22 frames.], batch size: 28, lr: 1.68e-04
2022-05-29 05:29:43,858 INFO [train.py:842] (3/4) Epoch 33, batch 1100, loss[loss=0.1821, simple_loss=0.2804, pruned_loss=0.04191, over 7317.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04248, over 1417463.49 frames.], batch size: 24, lr: 1.68e-04
2022-05-29 05:30:22,966 INFO [train.py:842] (3/4) Epoch 33, batch 1150, loss[loss=0.1868, simple_loss=0.2808, pruned_loss=0.04644, over 7197.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2632, pruned_loss=0.04256, over 1418903.03 frames.], batch size: 23, lr: 1.68e-04
2022-05-29 05:31:02,275 INFO [train.py:842] (3/4) Epoch 33, batch 1200, loss[loss=0.195, simple_loss=0.2822, pruned_loss=0.05392, over 7200.00 frames.], tot_loss[loss=0.174, simple_loss=0.2635, pruned_loss=0.04221, over 1421671.64 frames.], batch size: 26, lr: 1.68e-04
2022-05-29 05:31:41,537 INFO [train.py:842] (3/4) Epoch 33, batch 1250, loss[loss=0.1873, simple_loss=0.2785, pruned_loss=0.04811, over 6619.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2629, pruned_loss=0.04181, over 1421084.09 frames.], batch size: 38, lr: 1.68e-04
2022-05-29 05:32:21,175 INFO [train.py:842] (3/4) Epoch 33, batch 1300, loss[loss=0.1541, simple_loss=0.2559, pruned_loss=0.02617, over 7216.00 frames.], tot_loss[loss=0.173, simple_loss=0.2627, pruned_loss=0.04161, over 1421429.97 frames.], batch size: 21, lr: 1.68e-04
2022-05-29 05:33:00,654 INFO [train.py:842] (3/4) Epoch 33, batch 1350, loss[loss=0.1764, simple_loss=0.2443, pruned_loss=0.05431, over 7254.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2623, pruned_loss=0.0416, over 1420593.28 frames.], batch size: 17, lr: 1.68e-04
2022-05-29 05:33:40,400 INFO [train.py:842] (3/4) Epoch 33, batch 1400, loss[loss=0.1973, simple_loss=0.2831, pruned_loss=0.05572, over 7145.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2612, pruned_loss=0.04115, over 1422607.00 frames.], batch size: 20, lr: 1.68e-04
2022-05-29 05:34:19,616 INFO [train.py:842] (3/4) Epoch 33, batch 1450, loss[loss=0.1861, simple_loss=0.2723, pruned_loss=0.05, over 6871.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2619, pruned_loss=0.04154, over 1425958.44 frames.], batch size: 31, lr: 1.67e-04
2022-05-29 05:34:59,088 INFO [train.py:842] (3/4) Epoch 33, batch 1500, loss[loss=0.1805, simple_loss=0.2784, pruned_loss=0.0413, over 4766.00 frames.], tot_loss[loss=0.1729, simple_loss=0.262, pruned_loss=0.04193, over 1423260.49 frames.], batch size: 52, lr: 1.67e-04
2022-05-29 05:35:38,249 INFO [train.py:842] (3/4) Epoch 33, batch 1550, loss[loss=0.2051, simple_loss=0.3012, pruned_loss=0.05449, over 7215.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2631, pruned_loss=0.04252, over 1419667.53 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:36:17,806 INFO [train.py:842] (3/4) Epoch 33, batch 1600, loss[loss=0.1887, simple_loss=0.2816, pruned_loss=0.04793, over 7415.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2622, pruned_loss=0.04232, over 1420337.55 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:36:57,045 INFO [train.py:842] (3/4) Epoch 33, batch 1650, loss[loss=0.213, simple_loss=0.3098, pruned_loss=0.05812, over 7226.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2618, pruned_loss=0.04237, over 1421463.57 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:37:36,356 INFO [train.py:842] (3/4) Epoch 33, batch 1700, loss[loss=0.2047, simple_loss=0.3069, pruned_loss=0.05131, over 7303.00 frames.], tot_loss[loss=0.174, simple_loss=0.263, pruned_loss=0.04255, over 1423921.24 frames.], batch size: 24, lr: 1.67e-04
2022-05-29 05:38:15,197 INFO [train.py:842] (3/4) Epoch 33, batch 1750, loss[loss=0.1896, simple_loss=0.2785, pruned_loss=0.0504, over 7104.00 frames.], tot_loss[loss=0.176, simple_loss=0.2645, pruned_loss=0.04371, over 1416776.13 frames.], batch size: 28, lr: 1.67e-04
2022-05-29 05:38:54,947 INFO [train.py:842] (3/4) Epoch 33, batch 1800, loss[loss=0.1561, simple_loss=0.2544, pruned_loss=0.02883, over 7247.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2633, pruned_loss=0.043, over 1419840.54 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 05:39:34,279 INFO [train.py:842] (3/4) Epoch 33, batch 1850, loss[loss=0.2009, simple_loss=0.2996, pruned_loss=0.05116, over 7311.00 frames.], tot_loss[loss=0.174, simple_loss=0.2626, pruned_loss=0.04271, over 1423210.02 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:40:16,633 INFO [train.py:842] (3/4) Epoch 33, batch 1900, loss[loss=0.1613, simple_loss=0.2656, pruned_loss=0.02851, over 7376.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2617, pruned_loss=0.04192, over 1425813.21 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 05:40:55,663 INFO [train.py:842] (3/4) Epoch 33, batch 1950, loss[loss=0.172, simple_loss=0.2691, pruned_loss=0.03748, over 7302.00 frames.], tot_loss[loss=0.173, simple_loss=0.2621, pruned_loss=0.04198, over 1423937.47 frames.], batch size: 24, lr: 1.67e-04
2022-05-29 05:41:35,624 INFO [train.py:842] (3/4) Epoch 33, batch 2000, loss[loss=0.1691, simple_loss=0.2638, pruned_loss=0.03715, over 6471.00 frames.], tot_loss[loss=0.173, simple_loss=0.2619, pruned_loss=0.04202, over 1425395.26 frames.], batch size: 38, lr: 1.67e-04
2022-05-29 05:42:14,878 INFO [train.py:842] (3/4) Epoch 33, batch 2050, loss[loss=0.1633, simple_loss=0.2464, pruned_loss=0.04005, over 7160.00 frames.], tot_loss[loss=0.173, simple_loss=0.2618, pruned_loss=0.04206, over 1425334.60 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:42:54,712 INFO [train.py:842] (3/4) Epoch 33, batch 2100, loss[loss=0.1573, simple_loss=0.2488, pruned_loss=0.03293, over 7157.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2612, pruned_loss=0.04162, over 1427121.75 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 05:43:33,969 INFO [train.py:842] (3/4) Epoch 33, batch 2150, loss[loss=0.1288, simple_loss=0.2108, pruned_loss=0.02338, over 7390.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2613, pruned_loss=0.04145, over 1427673.26 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:44:13,558 INFO [train.py:842] (3/4) Epoch 33, batch 2200, loss[loss=0.2144, simple_loss=0.2919, pruned_loss=0.06849, over 5321.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2616, pruned_loss=0.04187, over 1422295.23 frames.], batch size: 52, lr: 1.67e-04
2022-05-29 05:44:52,672 INFO [train.py:842] (3/4) Epoch 33, batch 2250, loss[loss=0.2088, simple_loss=0.2899, pruned_loss=0.06391, over 7123.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04211, over 1419401.69 frames.], batch size: 26, lr: 1.67e-04
2022-05-29 05:45:32,521 INFO [train.py:842] (3/4) Epoch 33, batch 2300, loss[loss=0.1634, simple_loss=0.2537, pruned_loss=0.03659, over 7199.00 frames.], tot_loss[loss=0.172, simple_loss=0.2604, pruned_loss=0.04183, over 1418491.79 frames.], batch size: 22, lr: 1.67e-04
2022-05-29 05:46:11,757 INFO [train.py:842] (3/4) Epoch 33, batch 2350, loss[loss=0.15, simple_loss=0.2414, pruned_loss=0.02926, over 7224.00 frames.], tot_loss[loss=0.171, simple_loss=0.2596, pruned_loss=0.04117, over 1421392.18 frames.], batch size: 16, lr: 1.67e-04
2022-05-29 05:46:51,692 INFO [train.py:842] (3/4) Epoch 33, batch 2400, loss[loss=0.1483, simple_loss=0.2463, pruned_loss=0.02512, over 7424.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2588, pruned_loss=0.04068, over 1424358.39 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 05:47:31,145 INFO [train.py:842] (3/4) Epoch 33, batch 2450, loss[loss=0.1584, simple_loss=0.251, pruned_loss=0.03285, over 7250.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2588, pruned_loss=0.04091, over 1425968.48 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 05:48:10,880 INFO [train.py:842] (3/4) Epoch 33, batch 2500, loss[loss=0.1513, simple_loss=0.2471, pruned_loss=0.02773, over 7315.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2588, pruned_loss=0.04094, over 1427677.49 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:48:50,232 INFO [train.py:842] (3/4) Epoch 33, batch 2550, loss[loss=0.2022, simple_loss=0.2829, pruned_loss=0.06069, over 7369.00 frames.], tot_loss[loss=0.1719, simple_loss=0.26, pruned_loss=0.04186, over 1427581.90 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 05:49:30,012 INFO [train.py:842] (3/4) Epoch 33, batch 2600, loss[loss=0.1807, simple_loss=0.2811, pruned_loss=0.04015, over 7215.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2599, pruned_loss=0.04187, over 1429016.51 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 05:50:08,990 INFO [train.py:842] (3/4) Epoch 33, batch 2650, loss[loss=0.148, simple_loss=0.2241, pruned_loss=0.03596, over 6801.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04115, over 1424450.82 frames.], batch size: 15, lr: 1.67e-04
2022-05-29 05:50:48,479 INFO [train.py:842] (3/4) Epoch 33, batch 2700, loss[loss=0.1619, simple_loss=0.2538, pruned_loss=0.03495, over 7427.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2616, pruned_loss=0.04176, over 1425491.21 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 05:51:27,575 INFO [train.py:842] (3/4) Epoch 33, batch 2750, loss[loss=0.1507, simple_loss=0.241, pruned_loss=0.03019, over 7272.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2618, pruned_loss=0.04156, over 1426791.64 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:52:07,123 INFO [train.py:842] (3/4) Epoch 33, batch 2800, loss[loss=0.1692, simple_loss=0.2707, pruned_loss=0.03388, over 7176.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04153, over 1425579.57 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 05:52:46,425 INFO [train.py:842] (3/4) Epoch 33, batch 2850, loss[loss=0.1546, simple_loss=0.2442, pruned_loss=0.03251, over 7314.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.04186, over 1426725.58 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 05:53:25,965 INFO [train.py:842] (3/4) Epoch 33, batch 2900, loss[loss=0.1658, simple_loss=0.2612, pruned_loss=0.03513, over 7262.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2624, pruned_loss=0.04233, over 1426110.51 frames.], batch size: 25, lr: 1.67e-04
2022-05-29 05:54:05,092 INFO [train.py:842] (3/4) Epoch 33, batch 2950, loss[loss=0.1756, simple_loss=0.2649, pruned_loss=0.0432, over 7431.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2641, pruned_loss=0.04273, over 1428330.34 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 05:54:44,641 INFO [train.py:842] (3/4) Epoch 33, batch 3000, loss[loss=0.1621, simple_loss=0.2547, pruned_loss=0.0348, over 7065.00 frames.], tot_loss[loss=0.1739, simple_loss=0.263, pruned_loss=0.04236, over 1427103.81 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:54:44,642 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 05:54:54,324 INFO [train.py:871] (3/4) Epoch 33, validation: loss=0.1647, simple_loss=0.2614, pruned_loss=0.03398, over 868885.00 frames.
2022-05-29 05:55:33,709 INFO [train.py:842] (3/4) Epoch 33, batch 3050, loss[loss=0.1863, simple_loss=0.2721, pruned_loss=0.05028, over 6510.00 frames.], tot_loss[loss=0.173, simple_loss=0.2621, pruned_loss=0.04197, over 1424126.75 frames.], batch size: 38, lr: 1.67e-04
2022-05-29 05:56:13,276 INFO [train.py:842] (3/4) Epoch 33, batch 3100, loss[loss=0.1886, simple_loss=0.285, pruned_loss=0.04607, over 7370.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2623, pruned_loss=0.0423, over 1424010.86 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 05:56:52,618 INFO [train.py:842] (3/4) Epoch 33, batch 3150, loss[loss=0.1501, simple_loss=0.2481, pruned_loss=0.02608, over 7067.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2614, pruned_loss=0.04174, over 1421284.88 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:57:42,964 INFO [train.py:842] (3/4) Epoch 33, batch 3200, loss[loss=0.1591, simple_loss=0.2412, pruned_loss=0.03847, over 6815.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2609, pruned_loss=0.04149, over 1422234.85 frames.], batch size: 15, lr: 1.67e-04
2022-05-29 05:58:22,118 INFO [train.py:842] (3/4) Epoch 33, batch 3250, loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03137, over 7282.00 frames.], tot_loss[loss=0.172, simple_loss=0.2611, pruned_loss=0.04148, over 1419519.32 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 05:59:02,052 INFO [train.py:842] (3/4) Epoch 33, batch 3300, loss[loss=0.1982, simple_loss=0.2966, pruned_loss=0.04986, over 7232.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2605, pruned_loss=0.0413, over 1424299.30 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 05:59:41,366 INFO [train.py:842] (3/4) Epoch 33, batch 3350, loss[loss=0.2005, simple_loss=0.2728, pruned_loss=0.06408, over 7318.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2623, pruned_loss=0.04264, over 1427937.49 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:00:20,944 INFO [train.py:842] (3/4) Epoch 33, batch 3400, loss[loss=0.1206, simple_loss=0.2136, pruned_loss=0.01376, over 7280.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.04264, over 1427749.52 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 06:01:00,247 INFO [train.py:842] (3/4) Epoch 33, batch 3450, loss[loss=0.184, simple_loss=0.2691, pruned_loss=0.0495, over 7321.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2622, pruned_loss=0.04244, over 1431883.69 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 06:01:39,797 INFO [train.py:842] (3/4) Epoch 33, batch 3500, loss[loss=0.1927, simple_loss=0.2807, pruned_loss=0.05231, over 7376.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2625, pruned_loss=0.04263, over 1427847.86 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 06:02:19,042 INFO [train.py:842] (3/4) Epoch 33, batch 3550, loss[loss=0.2305, simple_loss=0.299, pruned_loss=0.08102, over 7421.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04245, over 1427086.01 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 06:02:58,536 INFO [train.py:842] (3/4) Epoch 33, batch 3600, loss[loss=0.1802, simple_loss=0.2749, pruned_loss=0.04273, over 7336.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2626, pruned_loss=0.04224, over 1423857.30 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 06:03:38,070 INFO [train.py:842] (3/4) Epoch 33, batch 3650, loss[loss=0.1712, simple_loss=0.2614, pruned_loss=0.04046, over 7328.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2619, pruned_loss=0.04213, over 1423012.77 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 06:04:17,609 INFO [train.py:842] (3/4) Epoch 33, batch 3700, loss[loss=0.1568, simple_loss=0.2419, pruned_loss=0.03585, over 7277.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2628, pruned_loss=0.04224, over 1426323.07 frames.], batch size: 17, lr: 1.67e-04
2022-05-29 06:04:56,728 INFO [train.py:842] (3/4) Epoch 33, batch 3750, loss[loss=0.1936, simple_loss=0.2885, pruned_loss=0.04936, over 7220.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2627, pruned_loss=0.04234, over 1426281.31 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:05:36,560 INFO [train.py:842] (3/4) Epoch 33, batch 3800, loss[loss=0.2072, simple_loss=0.3093, pruned_loss=0.05259, over 7198.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2627, pruned_loss=0.04253, over 1427560.79 frames.], batch size: 23, lr: 1.67e-04
2022-05-29 06:06:15,674 INFO [train.py:842] (3/4) Epoch 33, batch 3850, loss[loss=0.1787, simple_loss=0.2727, pruned_loss=0.04242, over 7308.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2621, pruned_loss=0.04166, over 1428198.83 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:06:55,079 INFO [train.py:842] (3/4) Epoch 33, batch 3900, loss[loss=0.2052, simple_loss=0.2764, pruned_loss=0.06695, over 6867.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2634, pruned_loss=0.04248, over 1428472.73 frames.], batch size: 15, lr: 1.67e-04
2022-05-29 06:07:34,361 INFO [train.py:842] (3/4) Epoch 33, batch 3950, loss[loss=0.1713, simple_loss=0.2548, pruned_loss=0.04385, over 6822.00 frames.], tot_loss[loss=0.1749, simple_loss=0.264, pruned_loss=0.04285, over 1429003.06 frames.], batch size: 15, lr: 1.67e-04
2022-05-29 06:08:14,165 INFO [train.py:842] (3/4) Epoch 33, batch 4000, loss[loss=0.1886, simple_loss=0.2746, pruned_loss=0.05134, over 5258.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2628, pruned_loss=0.04239, over 1430335.13 frames.], batch size: 55, lr: 1.67e-04
2022-05-29 06:08:53,353 INFO [train.py:842] (3/4) Epoch 33, batch 4050, loss[loss=0.155, simple_loss=0.2528, pruned_loss=0.02859, over 7258.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2618, pruned_loss=0.04176, over 1426062.55 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 06:09:33,031 INFO [train.py:842] (3/4) Epoch 33, batch 4100, loss[loss=0.2099, simple_loss=0.2965, pruned_loss=0.0617, over 7305.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2615, pruned_loss=0.04236, over 1425285.70 frames.], batch size: 25, lr: 1.67e-04
2022-05-29 06:10:12,289 INFO [train.py:842] (3/4) Epoch 33, batch 4150, loss[loss=0.1514, simple_loss=0.241, pruned_loss=0.03089, over 7152.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2617, pruned_loss=0.04224, over 1420815.97 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 06:10:52,086 INFO [train.py:842] (3/4) Epoch 33, batch 4200, loss[loss=0.1639, simple_loss=0.2563, pruned_loss=0.03577, over 7410.00 frames.], tot_loss[loss=0.1736, simple_loss=0.262, pruned_loss=0.04255, over 1426134.60 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:11:31,149 INFO [train.py:842] (3/4) Epoch 33, batch 4250, loss[loss=0.1878, simple_loss=0.2852, pruned_loss=0.0452, over 7338.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2632, pruned_loss=0.04291, over 1425158.39 frames.], batch size: 22, lr: 1.67e-04
2022-05-29 06:12:10,731 INFO [train.py:842] (3/4) Epoch 33, batch 4300, loss[loss=0.1777, simple_loss=0.2635, pruned_loss=0.046, over 7160.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04263, over 1424194.04 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 06:12:50,168 INFO [train.py:842] (3/4) Epoch 33, batch 4350, loss[loss=0.1793, simple_loss=0.2716, pruned_loss=0.04348, over 7242.00 frames.], tot_loss[loss=0.174, simple_loss=0.2628, pruned_loss=0.04256, over 1425636.84 frames.], batch size: 20, lr: 1.67e-04
2022-05-29 06:13:29,835 INFO [train.py:842] (3/4) Epoch 33, batch 4400, loss[loss=0.2643, simple_loss=0.3384, pruned_loss=0.09517, over 6515.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2633, pruned_loss=0.04285, over 1424167.76 frames.], batch size: 38, lr: 1.67e-04
2022-05-29 06:14:09,287 INFO [train.py:842] (3/4) Epoch 33, batch 4450, loss[loss=0.1825, simple_loss=0.251, pruned_loss=0.05701, over 7006.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2635, pruned_loss=0.04297, over 1423417.96 frames.], batch size: 16, lr: 1.67e-04
2022-05-29 06:14:48,786 INFO [train.py:842] (3/4) Epoch 33, batch 4500, loss[loss=0.1842, simple_loss=0.2692, pruned_loss=0.04962, over 7324.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2642, pruned_loss=0.0433, over 1425865.79 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:15:28,041 INFO [train.py:842] (3/4) Epoch 33, batch 4550, loss[loss=0.1649, simple_loss=0.2598, pruned_loss=0.03497, over 7276.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2639, pruned_loss=0.04287, over 1424198.79 frames.], batch size: 25, lr: 1.67e-04
2022-05-29 06:16:07,562 INFO [train.py:842] (3/4) Epoch 33, batch 4600, loss[loss=0.2131, simple_loss=0.295, pruned_loss=0.06562, over 6767.00 frames.], tot_loss[loss=0.1753, simple_loss=0.264, pruned_loss=0.04328, over 1423364.22 frames.], batch size: 31, lr: 1.67e-04
2022-05-29 06:16:46,689 INFO [train.py:842] (3/4) Epoch 33, batch 4650, loss[loss=0.1792, simple_loss=0.2602, pruned_loss=0.04911, over 7404.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2638, pruned_loss=0.0434, over 1421076.87 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 06:17:26,308 INFO [train.py:842] (3/4) Epoch 33, batch 4700, loss[loss=0.1808, simple_loss=0.2721, pruned_loss=0.04477, over 6505.00 frames.], tot_loss[loss=0.1765, simple_loss=0.265, pruned_loss=0.04397, over 1422635.73 frames.], batch size: 38, lr: 1.67e-04
2022-05-29 06:18:05,559 INFO [train.py:842] (3/4) Epoch 33, batch 4750, loss[loss=0.1696, simple_loss=0.2415, pruned_loss=0.04884, over 7295.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2643, pruned_loss=0.04372, over 1423147.03 frames.], batch size: 17, lr: 1.67e-04
2022-05-29 06:18:45,213 INFO [train.py:842] (3/4) Epoch 33, batch 4800, loss[loss=0.1586, simple_loss=0.2572, pruned_loss=0.02997, over 7122.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2644, pruned_loss=0.04355, over 1424317.47 frames.], batch size: 21, lr: 1.67e-04
2022-05-29 06:19:24,414 INFO [train.py:842] (3/4) Epoch 33, batch 4850, loss[loss=0.1978, simple_loss=0.2875, pruned_loss=0.05407, over 6401.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2637, pruned_loss=0.04329, over 1419549.58 frames.], batch size: 38, lr: 1.67e-04
2022-05-29 06:20:04,003 INFO [train.py:842] (3/4) Epoch 33, batch 4900, loss[loss=0.1658, simple_loss=0.2575, pruned_loss=0.03707, over 7250.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04244, over 1419551.35 frames.], batch size: 19, lr: 1.67e-04
2022-05-29 06:20:43,324 INFO [train.py:842] (3/4) Epoch 33, batch 4950, loss[loss=0.1871, simple_loss=0.276, pruned_loss=0.0491, over 7060.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2635, pruned_loss=0.04309, over 1417501.52 frames.], batch size: 18, lr: 1.67e-04
2022-05-29 06:21:22,726 INFO [train.py:842] (3/4) Epoch 33, batch 5000, loss[loss=0.1557, simple_loss=0.2498, pruned_loss=0.03084, over 6719.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2639, pruned_loss=0.04325, over 1414183.86 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 06:22:02,173 INFO [train.py:842] (3/4) Epoch 33, batch 5050, loss[loss=0.1835, simple_loss=0.2707, pruned_loss=0.04817, over 7136.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2638, pruned_loss=0.04288, over 1414871.12 frames.], batch size: 26, lr: 1.66e-04
2022-05-29 06:22:41,617 INFO [train.py:842] (3/4) Epoch 33, batch 5100, loss[loss=0.1727, simple_loss=0.261, pruned_loss=0.04217, over 7284.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2644, pruned_loss=0.04305, over 1412192.63 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:23:20,494 INFO [train.py:842] (3/4) Epoch 33, batch 5150, loss[loss=0.184, simple_loss=0.2778, pruned_loss=0.04507, over 7216.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2644, pruned_loss=0.04334, over 1405423.33 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:24:00,145 INFO [train.py:842] (3/4) Epoch 33, batch 5200, loss[loss=0.1399, simple_loss=0.2216, pruned_loss=0.02915, over 6992.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2646, pruned_loss=0.04328, over 1412291.46 frames.], batch size: 16, lr: 1.66e-04
2022-05-29 06:24:38,961 INFO [train.py:842] (3/4) Epoch 33, batch 5250, loss[loss=0.179, simple_loss=0.2721, pruned_loss=0.04301, over 7146.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2643, pruned_loss=0.04291, over 1413608.32 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:25:18,432 INFO [train.py:842] (3/4) Epoch 33, batch 5300, loss[loss=0.1531, simple_loss=0.2422, pruned_loss=0.03197, over 7065.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2638, pruned_loss=0.04281, over 1415399.32 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:25:57,805 INFO [train.py:842] (3/4) Epoch 33, batch 5350, loss[loss=0.1607, simple_loss=0.2553, pruned_loss=0.03307, over 7225.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2626, pruned_loss=0.04204, over 1418596.24 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:26:37,411 INFO [train.py:842] (3/4) Epoch 33, batch 5400, loss[loss=0.1865, simple_loss=0.2717, pruned_loss=0.05062, over 6820.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2621, pruned_loss=0.04189, over 1419787.49 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 06:27:16,752 INFO [train.py:842] (3/4) Epoch 33, batch 5450, loss[loss=0.1883, simple_loss=0.2874, pruned_loss=0.04456, over 7337.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2612, pruned_loss=0.04119, over 1422096.92 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 06:27:56,408 INFO [train.py:842] (3/4) Epoch 33, batch 5500, loss[loss=0.1316, simple_loss=0.2135, pruned_loss=0.02484, over 7281.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2607, pruned_loss=0.04122, over 1425597.26 frames.], batch size: 17, lr: 1.66e-04
2022-05-29 06:28:35,868 INFO [train.py:842] (3/4) Epoch 33, batch 5550, loss[loss=0.1512, simple_loss=0.2442, pruned_loss=0.02905, over 7418.00 frames.], tot_loss[loss=0.1709, simple_loss=0.26, pruned_loss=0.04088, over 1426830.23 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:29:15,492 INFO [train.py:842] (3/4) Epoch 33, batch 5600, loss[loss=0.2009, simple_loss=0.2816, pruned_loss=0.06009, over 4820.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2604, pruned_loss=0.04143, over 1421697.37 frames.], batch size: 53, lr: 1.66e-04
2022-05-29 06:29:54,978 INFO [train.py:842] (3/4) Epoch 33, batch 5650, loss[loss=0.1987, simple_loss=0.2774, pruned_loss=0.06005, over 7366.00 frames.], tot_loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.04166, over 1424186.00 frames.], batch size: 23, lr: 1.66e-04
2022-05-29 06:30:34,473 INFO [train.py:842] (3/4) Epoch 33, batch 5700, loss[loss=0.1784, simple_loss=0.2611, pruned_loss=0.04779, over 6562.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2604, pruned_loss=0.04115, over 1417298.36 frames.], batch size: 38, lr: 1.66e-04
2022-05-29 06:31:13,690 INFO [train.py:842] (3/4) Epoch 33, batch 5750, loss[loss=0.1423, simple_loss=0.2241, pruned_loss=0.0303, over 7052.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2618, pruned_loss=0.04201, over 1420364.32 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:31:53,521 INFO [train.py:842] (3/4) Epoch 33, batch 5800, loss[loss=0.2085, simple_loss=0.2938, pruned_loss=0.06162, over 7343.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2621, pruned_loss=0.04233, over 1420665.94 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 06:32:32,838 INFO [train.py:842] (3/4) Epoch 33, batch 5850, loss[loss=0.1846, simple_loss=0.2619, pruned_loss=0.0536, over 7417.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2622, pruned_loss=0.04227, over 1419944.77 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:33:12,611 INFO [train.py:842] (3/4) Epoch 33, batch 5900, loss[loss=0.1628, simple_loss=0.253, pruned_loss=0.03624, over 7435.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2618, pruned_loss=0.04214, over 1425314.25 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:33:51,677 INFO [train.py:842] (3/4) Epoch 33, batch 5950, loss[loss=0.1716, simple_loss=0.2666, pruned_loss=0.03827, over 6330.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2625, pruned_loss=0.04243, over 1428516.57 frames.], batch size: 38, lr: 1.66e-04
2022-05-29 06:34:31,364 INFO [train.py:842] (3/4) Epoch 33, batch 6000, loss[loss=0.2042, simple_loss=0.3058, pruned_loss=0.05132, over 7145.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2627, pruned_loss=0.04252, over 1428664.05 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:34:31,365 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 06:34:41,081 INFO [train.py:871] (3/4) Epoch 33, validation: loss=0.1642, simple_loss=0.2614, pruned_loss=0.03347, over 868885.00 frames.
2022-05-29 06:35:20,446 INFO [train.py:842] (3/4) Epoch 33, batch 6050, loss[loss=0.1888, simple_loss=0.2762, pruned_loss=0.05072, over 7218.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04219, over 1428280.97 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 06:35:59,987 INFO [train.py:842] (3/4) Epoch 33, batch 6100, loss[loss=0.1866, simple_loss=0.2782, pruned_loss=0.04748, over 7335.00 frames.], tot_loss[loss=0.1732, simple_loss=0.262, pruned_loss=0.04222, over 1425458.54 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 06:36:39,103 INFO [train.py:842] (3/4) Epoch 33, batch 6150, loss[loss=0.1449, simple_loss=0.2263, pruned_loss=0.03179, over 6733.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2619, pruned_loss=0.04199, over 1424959.15 frames.], batch size: 15, lr: 1.66e-04
2022-05-29 06:37:18,640 INFO [train.py:842] (3/4) Epoch 33, batch 6200, loss[loss=0.1671, simple_loss=0.2602, pruned_loss=0.03695, over 7419.00 frames.], tot_loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.0416, over 1423901.52 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:37:57,944 INFO [train.py:842] (3/4) Epoch 33, batch 6250, loss[loss=0.1644, simple_loss=0.2467, pruned_loss=0.04101, over 7138.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2604, pruned_loss=0.04132, over 1425924.23 frames.], batch size: 17, lr: 1.66e-04
2022-05-29 06:38:37,898 INFO [train.py:842] (3/4) Epoch 33, batch 6300, loss[loss=0.1829, simple_loss=0.2651, pruned_loss=0.05031, over 7301.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2607, pruned_loss=0.0415, over 1425520.91 frames.], batch size: 24, lr: 1.66e-04
2022-05-29 06:39:17,427 INFO [train.py:842] (3/4) Epoch 33, batch 6350, loss[loss=0.1707, simple_loss=0.2524, pruned_loss=0.0445, over 7175.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2608, pruned_loss=0.04175, over 1427392.67 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:39:57,026 INFO [train.py:842] (3/4) Epoch 33, batch 6400, loss[loss=0.157, simple_loss=0.254, pruned_loss=0.02999, over 7243.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2607, pruned_loss=0.0418, over 1426261.27 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:40:36,424 INFO [train.py:842] (3/4) Epoch 33, batch 6450, loss[loss=0.1667, simple_loss=0.2604, pruned_loss=0.0365, over 7387.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2602, pruned_loss=0.04172, over 1426828.16 frames.], batch size: 23, lr: 1.66e-04
2022-05-29 06:41:16,139 INFO [train.py:842] (3/4) Epoch 33, batch 6500, loss[loss=0.2179, simple_loss=0.3035, pruned_loss=0.06616, over 7416.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2611, pruned_loss=0.04188, over 1428885.56 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:41:55,400 INFO [train.py:842] (3/4) Epoch 33, batch 6550, loss[loss=0.1551, simple_loss=0.2387, pruned_loss=0.03573, over 7181.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2622, pruned_loss=0.0423, over 1427673.05 frames.], batch size: 16, lr: 1.66e-04
2022-05-29 06:42:34,841 INFO [train.py:842] (3/4) Epoch 33, batch 6600, loss[loss=0.153, simple_loss=0.2413, pruned_loss=0.03236, over 6988.00 frames.], tot_loss[loss=0.174, simple_loss=0.2629, pruned_loss=0.04251, over 1426546.59 frames.], batch size: 16, lr: 1.66e-04
2022-05-29 06:43:14,060 INFO [train.py:842] (3/4) Epoch 33, batch 6650, loss[loss=0.1867, simple_loss=0.2801, pruned_loss=0.04666, over 6847.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2634, pruned_loss=0.0431, over 1424376.25 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 06:43:53,715 INFO [train.py:842] (3/4) Epoch 33, batch 6700, loss[loss=0.1447, simple_loss=0.2317, pruned_loss=0.02891, over 7069.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2622, pruned_loss=0.04269, over 1420853.66 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:44:32,928 INFO [train.py:842] (3/4) Epoch 33, batch 6750, loss[loss=0.1495, simple_loss=0.2409, pruned_loss=0.0291, over 7168.00 frames.], tot_loss[loss=0.174, simple_loss=0.2624, pruned_loss=0.04279, over 1420982.80 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:45:12,730 INFO [train.py:842] (3/4) Epoch 33, batch 6800, loss[loss=0.1932, simple_loss=0.283, pruned_loss=0.0517, over 7201.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2617, pruned_loss=0.04253, over 1417500.43 frames.], batch size: 23, lr: 1.66e-04
2022-05-29 06:45:51,935 INFO [train.py:842] (3/4) Epoch 33, batch 6850, loss[loss=0.1966, simple_loss=0.2856, pruned_loss=0.05381, over 7217.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2616, pruned_loss=0.04237, over 1422553.75 frames.], batch size: 26, lr: 1.66e-04
2022-05-29 06:46:31,102 INFO [train.py:842] (3/4) Epoch 33, batch 6900, loss[loss=0.1606, simple_loss=0.2534, pruned_loss=0.03388, over 6797.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2621, pruned_loss=0.04266, over 1418907.68 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 06:47:10,475 INFO [train.py:842] (3/4) Epoch 33, batch 6950, loss[loss=0.1712, simple_loss=0.2642, pruned_loss=0.03905, over 7438.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2611, pruned_loss=0.04212, over 1425503.62 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:47:50,201 INFO [train.py:842] (3/4) Epoch 33, batch 7000, loss[loss=0.1746, simple_loss=0.2634, pruned_loss=0.0429, over 7061.00 frames.], tot_loss[loss=0.172, simple_loss=0.2607, pruned_loss=0.04161, over 1427199.50 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:48:29,621 INFO [train.py:842] (3/4) Epoch 33, batch 7050, loss[loss=0.1343, simple_loss=0.2198, pruned_loss=0.02439, over 7151.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2617, pruned_loss=0.04256, over 1424943.30 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:49:09,096 INFO [train.py:842] (3/4) Epoch 33, batch 7100, loss[loss=0.2002, simple_loss=0.2848, pruned_loss=0.0578, over 7204.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2624, pruned_loss=0.04273, over 1427244.77 frames.], batch size: 26, lr: 1.66e-04
2022-05-29 06:49:48,458 INFO [train.py:842] (3/4) Epoch 33, batch 7150, loss[loss=0.1726, simple_loss=0.2697, pruned_loss=0.03775, over 7109.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2625, pruned_loss=0.04271, over 1430341.06 frames.], batch size: 26, lr: 1.66e-04
2022-05-29 06:50:28,351 INFO [train.py:842] (3/4) Epoch 33, batch 7200, loss[loss=0.1678, simple_loss=0.2577, pruned_loss=0.039, over 7314.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2629, pruned_loss=0.04316, over 1428704.50 frames.], batch size: 24, lr: 1.66e-04
2022-05-29 06:51:07,736 INFO [train.py:842] (3/4) Epoch 33, batch 7250, loss[loss=0.1686, simple_loss=0.2447, pruned_loss=0.04629, over 7254.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2626, pruned_loss=0.04319, over 1425886.93 frames.], batch size: 19, lr: 1.66e-04
2022-05-29 06:51:47,000 INFO [train.py:842] (3/4) Epoch 33, batch 7300, loss[loss=0.1835, simple_loss=0.2723, pruned_loss=0.04735, over 7163.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2635, pruned_loss=0.04359, over 1427096.55 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:52:26,321 INFO [train.py:842] (3/4) Epoch 33, batch 7350, loss[loss=0.1913, simple_loss=0.2841, pruned_loss=0.04924, over 7219.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2647, pruned_loss=0.04399, over 1426860.32 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:53:05,856 INFO [train.py:842] (3/4) Epoch 33, batch 7400, loss[loss=0.2011, simple_loss=0.2826, pruned_loss=0.05986, over 5314.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2637, pruned_loss=0.04307, over 1423476.95 frames.], batch size: 54, lr: 1.66e-04
2022-05-29 06:53:45,065 INFO [train.py:842] (3/4) Epoch 33, batch 7450, loss[loss=0.1753, simple_loss=0.262, pruned_loss=0.04427, over 7264.00 frames.], tot_loss[loss=0.1743, simple_loss=0.263, pruned_loss=0.04283, over 1415935.60 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:54:24,430 INFO [train.py:842] (3/4) Epoch 33, batch 7500, loss[loss=0.1965, simple_loss=0.2891, pruned_loss=0.05192, over 6289.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2626, pruned_loss=0.04215, over 1419958.94 frames.], batch size: 37, lr: 1.66e-04
2022-05-29 06:55:03,711 INFO [train.py:842] (3/4) Epoch 33, batch 7550, loss[loss=0.1388, simple_loss=0.223, pruned_loss=0.02732, over 7423.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2603, pruned_loss=0.04127, over 1422831.17 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:55:43,322 INFO [train.py:842] (3/4) Epoch 33, batch 7600, loss[loss=0.1979, simple_loss=0.2901, pruned_loss=0.05286, over 7113.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2615, pruned_loss=0.04177, over 1427441.61 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 06:56:22,534 INFO [train.py:842] (3/4) Epoch 33, batch 7650, loss[loss=0.1719, simple_loss=0.2437, pruned_loss=0.04999, over 7278.00 frames.], tot_loss[loss=0.1728, simple_loss=0.262, pruned_loss=0.04178, over 1426204.49 frames.], batch size: 18, lr: 1.66e-04
2022-05-29 06:57:02,119 INFO [train.py:842] (3/4) Epoch 33, batch 7700, loss[loss=0.137, simple_loss=0.2165, pruned_loss=0.02875, over 6786.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2611, pruned_loss=0.04168, over 1425100.95 frames.], batch size: 15, lr: 1.66e-04
2022-05-29 06:57:41,117 INFO [train.py:842] (3/4) Epoch 33, batch 7750, loss[loss=0.1695, simple_loss=0.2534, pruned_loss=0.04278, over 7437.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2623, pruned_loss=0.04216, over 1423858.88 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:58:20,697 INFO [train.py:842] (3/4) Epoch 33, batch 7800, loss[loss=0.1681, simple_loss=0.2643, pruned_loss=0.03594, over 6702.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04251, over 1424381.93 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 06:58:59,890 INFO [train.py:842] (3/4) Epoch 33, batch 7850, loss[loss=0.1751, simple_loss=0.2644, pruned_loss=0.04294, over 7318.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2624, pruned_loss=0.04235, over 1426558.09 frames.], batch size: 20, lr: 1.66e-04
2022-05-29 06:59:39,499 INFO [train.py:842] (3/4) Epoch 33, batch 7900, loss[loss=0.1863, simple_loss=0.297, pruned_loss=0.03785, over 7343.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2631, pruned_loss=0.04303, over 1429372.45 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 07:00:18,941 INFO [train.py:842] (3/4) Epoch 33, batch 7950, loss[loss=0.2052, simple_loss=0.2976, pruned_loss=0.05644, over 6448.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2625, pruned_loss=0.04287, over 1427055.95 frames.], batch size: 37, lr: 1.66e-04
2022-05-29 07:00:58,319 INFO [train.py:842] (3/4) Epoch 33, batch 8000, loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03743, over 7107.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2637, pruned_loss=0.043, over 1425853.85 frames.], batch size: 28, lr: 1.66e-04
2022-05-29 07:01:37,406 INFO [train.py:842] (3/4) Epoch 33, batch 8050, loss[loss=0.2417, simple_loss=0.323, pruned_loss=0.08018, over 7105.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2643, pruned_loss=0.04339, over 1425478.13 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 07:02:17,324 INFO [train.py:842] (3/4) Epoch 33, batch 8100, loss[loss=0.195, simple_loss=0.2821, pruned_loss=0.05395, over 7232.00 frames.], tot_loss[loss=0.1742, simple_loss=0.263, pruned_loss=0.0427, over 1424862.14 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 07:02:56,303 INFO [train.py:842] (3/4) Epoch 33, batch 8150, loss[loss=0.1981, simple_loss=0.2928, pruned_loss=0.05171, over 7330.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2643, pruned_loss=0.0432, over 1422932.51 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 07:03:35,706 INFO [train.py:842] (3/4) Epoch 33, batch 8200, loss[loss=0.1852, simple_loss=0.2633, pruned_loss=0.05356, over 5209.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2633, pruned_loss=0.0427, over 1420559.31 frames.], batch size: 52, lr: 1.66e-04
2022-05-29 07:04:25,743 INFO [train.py:842] (3/4) Epoch 33, batch 8250, loss[loss=0.1212, simple_loss=0.2134, pruned_loss=0.01451, over 7013.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2624, pruned_loss=0.04211, over 1426466.97 frames.], batch size: 16, lr: 1.66e-04
2022-05-29 07:05:05,271 INFO [train.py:842] (3/4) Epoch 33, batch 8300, loss[loss=0.1311, simple_loss=0.2153, pruned_loss=0.02343, over 7001.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2622, pruned_loss=0.04181, over 1423388.70 frames.], batch size: 16, lr: 1.66e-04
2022-05-29 07:05:44,148 INFO [train.py:842] (3/4) Epoch 33, batch 8350, loss[loss=0.1604, simple_loss=0.2518, pruned_loss=0.03444, over 7219.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2624, pruned_loss=0.04203, over 1421675.22 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 07:06:23,452 INFO [train.py:842] (3/4) Epoch 33, batch 8400, loss[loss=0.1465, simple_loss=0.2457, pruned_loss=0.02368, over 7332.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2625, pruned_loss=0.04208, over 1416724.69 frames.], batch size: 22, lr: 1.66e-04
2022-05-29 07:07:02,629 INFO [train.py:842] (3/4) Epoch 33, batch 8450, loss[loss=0.1775, simple_loss=0.2714, pruned_loss=0.04177, over 7036.00 frames.], tot_loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.04131, over 1420100.70 frames.], batch size: 28, lr: 1.66e-04
2022-05-29 07:07:53,981 INFO [train.py:842] (3/4) Epoch 33, batch 8500, loss[loss=0.2047, simple_loss=0.3043, pruned_loss=0.05257, over 7310.00 frames.], tot_loss[loss=0.172, simple_loss=0.2612, pruned_loss=0.04143, over 1422179.08 frames.], batch size: 21, lr: 1.66e-04
2022-05-29 07:08:33,107 INFO [train.py:842] (3/4) Epoch 33, batch 8550, loss[loss=0.1986, simple_loss=0.2833, pruned_loss=0.05692, over 6803.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04156, over 1421579.60 frames.], batch size: 31, lr: 1.66e-04
2022-05-29 07:09:23,045 INFO [train.py:842] (3/4) Epoch 33, batch 8600, loss[loss=0.2455, simple_loss=0.3341, pruned_loss=0.07842, over 4947.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04242, over 1414028.91 frames.], batch size: 52, lr: 1.65e-04
2022-05-29 07:10:01,975 INFO [train.py:842] (3/4) Epoch 33, batch 8650, loss[loss=0.2291, simple_loss=0.3035, pruned_loss=0.07729, over 7158.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2635, pruned_loss=0.04287, over 1406573.27 frames.], batch size: 26, lr: 1.65e-04
2022-05-29 07:10:41,477 INFO [train.py:842] (3/4) Epoch 33, batch 8700, loss[loss=0.202, simple_loss=0.2823, pruned_loss=0.0609, over 4863.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2642, pruned_loss=0.04312, over 1402972.21 frames.], batch size: 53, lr: 1.65e-04
2022-05-29 07:11:20,641 INFO [train.py:842] (3/4) Epoch 33, batch 8750, loss[loss=0.1991, simple_loss=0.2997, pruned_loss=0.04924, over 6540.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2655, pruned_loss=0.04348, over 1406327.35 frames.], batch size: 38, lr: 1.65e-04
2022-05-29 07:11:59,649 INFO [train.py:842] (3/4) Epoch 33, batch 8800, loss[loss=0.1672, simple_loss=0.258, pruned_loss=0.0382, over 7152.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2661, pruned_loss=0.04378, over 1403075.12 frames.], batch size: 20, lr: 1.65e-04
2022-05-29 07:12:38,574 INFO [train.py:842] (3/4) Epoch 33, batch 8850, loss[loss=0.1334, simple_loss=0.2338, pruned_loss=0.01649, over 7218.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2667, pruned_loss=0.04406, over 1388938.22 frames.], batch size: 21, lr: 1.65e-04
2022-05-29 07:13:17,804 INFO [train.py:842] (3/4) Epoch 33, batch 8900, loss[loss=0.213, simple_loss=0.3126, pruned_loss=0.05674, over 7135.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2674, pruned_loss=0.04444, over 1389117.72 frames.], batch size: 26, lr: 1.65e-04
2022-05-29 07:13:56,494 INFO [train.py:842] (3/4) Epoch 33, batch 8950, loss[loss=0.1837, simple_loss=0.2703, pruned_loss=0.04859, over 7260.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2679, pruned_loss=0.04492, over 1382275.07 frames.], batch size: 19, lr: 1.65e-04
2022-05-29 07:14:35,683 INFO [train.py:842] (3/4) Epoch 33, batch 9000, loss[loss=0.1672, simple_loss=0.2602, pruned_loss=0.03714, over 7207.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2675, pruned_loss=0.04478, over 1377672.61 frames.], batch size: 23, lr: 1.65e-04
2022-05-29 07:14:35,684 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 07:14:45,195 INFO [train.py:871] (3/4) Epoch 33, validation: loss=0.1641, simple_loss=0.2616, pruned_loss=0.03332, over 868885.00 frames.
2022-05-29 07:15:24,277 INFO [train.py:842] (3/4) Epoch 33, batch 9050, loss[loss=0.1695, simple_loss=0.2699, pruned_loss=0.0346, over 7063.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2672, pruned_loss=0.0451, over 1372269.95 frames.], batch size: 28, lr: 1.65e-04
2022-05-29 07:16:03,490 INFO [train.py:842] (3/4) Epoch 33, batch 9100, loss[loss=0.1844, simple_loss=0.2666, pruned_loss=0.05106, over 4859.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2676, pruned_loss=0.04571, over 1353650.11 frames.], batch size: 52, lr: 1.65e-04
2022-05-29 07:16:41,699 INFO [train.py:842] (3/4) Epoch 33, batch 9150, loss[loss=0.2005, simple_loss=0.2877, pruned_loss=0.0566, over 4854.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2699, pruned_loss=0.0468, over 1305528.72 frames.], batch size: 52, lr: 1.65e-04
2022-05-29 07:17:29,982 INFO [train.py:842] (3/4) Epoch 34, batch 0, loss[loss=0.1509, simple_loss=0.2449, pruned_loss=0.0285, over 7436.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2449, pruned_loss=0.0285, over 7436.00 frames.], batch size: 20, lr: 1.63e-04
2022-05-29 07:18:09,726 INFO [train.py:842] (3/4) Epoch 34, batch 50, loss[loss=0.1676, simple_loss=0.2696, pruned_loss=0.03283, over 7077.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2579, pruned_loss=0.03973, over 324849.37 frames.], batch size: 28, lr: 1.63e-04
2022-05-29 07:18:49,370 INFO [train.py:842] (3/4) Epoch 34, batch 100, loss[loss=0.2129, simple_loss=0.2991, pruned_loss=0.06338, over 7117.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2636, pruned_loss=0.04232, over 566097.27 frames.], batch size: 21, lr: 1.63e-04
2022-05-29 07:19:28,896 INFO [train.py:842] (3/4) Epoch 34, batch 150, loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03432, over 7079.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2635, pruned_loss=0.04357, over 755683.30 frames.], batch size: 18, lr: 1.63e-04
2022-05-29 07:20:08,756 INFO [train.py:842] (3/4) Epoch 34, batch 200, loss[loss=0.1812, simple_loss=0.2614, pruned_loss=0.05049, over 7295.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2621, pruned_loss=0.04234, over 906542.60 frames.], batch size: 17, lr: 1.63e-04
2022-05-29 07:20:48,021 INFO [train.py:842] (3/4) Epoch 34, batch 250, loss[loss=0.2237, simple_loss=0.3069, pruned_loss=0.07025, over 5154.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04107, over 1013401.53 frames.], batch size: 52, lr: 1.63e-04
2022-05-29 07:21:27,653 INFO [train.py:842] (3/4) Epoch 34, batch 300, loss[loss=0.1645, simple_loss=0.2626, pruned_loss=0.03316, over 7378.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2595, pruned_loss=0.04102, over 1103374.10 frames.], batch size: 23, lr: 1.63e-04
2022-05-29 07:22:06,461 INFO [train.py:842] (3/4) Epoch 34, batch 350, loss[loss=0.1446, simple_loss=0.2237, pruned_loss=0.03272, over 7150.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2618, pruned_loss=0.0418, over 1168529.88 frames.], batch size: 17, lr: 1.63e-04
2022-05-29 07:22:46,340 INFO [train.py:842] (3/4) Epoch 34, batch 400, loss[loss=0.1707, simple_loss=0.2696, pruned_loss=0.03594, over 7412.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2613, pruned_loss=0.04166, over 1229453.15 frames.], batch size: 21, lr: 1.63e-04
2022-05-29 07:23:25,548 INFO [train.py:842] (3/4) Epoch 34, batch 450, loss[loss=0.151, simple_loss=0.2379, pruned_loss=0.03203, over 7412.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.0421, over 1273853.19 frames.], batch size: 18, lr: 1.63e-04
2022-05-29 07:24:05,253 INFO [train.py:842] (3/4) Epoch 34, batch 500, loss[loss=0.1748, simple_loss=0.2616, pruned_loss=0.04397, over 7291.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2639, pruned_loss=0.0426, over 1307042.94 frames.], batch size: 24, lr: 1.63e-04
2022-05-29 07:24:44,508 INFO [train.py:842] (3/4) Epoch 34, batch 550, loss[loss=0.1522, simple_loss=0.2488, pruned_loss=0.02778, over 6466.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2638, pruned_loss=0.04262, over 1331229.39 frames.], batch size: 38, lr: 1.63e-04
2022-05-29 07:25:24,089 INFO [train.py:842] (3/4) Epoch 34, batch 600, loss[loss=0.1824, simple_loss=0.2744, pruned_loss=0.04513, over 7283.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2642, pruned_loss=0.04252, over 1353286.10 frames.], batch size: 25, lr: 1.63e-04
2022-05-29 07:26:03,424 INFO [train.py:842] (3/4) Epoch 34, batch 650, loss[loss=0.1646, simple_loss=0.253, pruned_loss=0.03811, over 7159.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2648, pruned_loss=0.04301, over 1371431.37 frames.], batch size: 18, lr: 1.63e-04
2022-05-29 07:26:46,185 INFO [train.py:842] (3/4) Epoch 34, batch 700, loss[loss=0.1568, simple_loss=0.2363, pruned_loss=0.03863, over 7128.00 frames.], tot_loss[loss=0.1742, simple_loss=0.263, pruned_loss=0.04268, over 1378854.11 frames.], batch size: 17, lr: 1.63e-04
2022-05-29 07:27:25,328 INFO [train.py:842] (3/4) Epoch 34, batch 750, loss[loss=0.2182, simple_loss=0.3114, pruned_loss=0.06243, over 7206.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2624, pruned_loss=0.04203, over 1390173.44 frames.], batch size: 23, lr: 1.63e-04
2022-05-29 07:28:04,896 INFO [train.py:842] (3/4) Epoch 34, batch 800, loss[loss=0.1304, simple_loss=0.2174, pruned_loss=0.02168, over 7292.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2617, pruned_loss=0.04144, over 1396056.73 frames.], batch size: 18, lr: 1.63e-04
2022-05-29 07:28:44,208 INFO [train.py:842] (3/4) Epoch 34, batch 850, loss[loss=0.162, simple_loss=0.2649, pruned_loss=0.02958, over 6388.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2612, pruned_loss=0.04125, over 1405518.48 frames.], batch size: 37, lr: 1.63e-04
2022-05-29 07:29:23,956 INFO [train.py:842] (3/4) Epoch 34, batch 900, loss[loss=0.1997, simple_loss=0.2871, pruned_loss=0.05613, over 5092.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2602, pruned_loss=0.04125, over 1410076.91 frames.], batch size: 52, lr: 1.63e-04
2022-05-29 07:30:03,382 INFO [train.py:842] (3/4) Epoch 34, batch 950, loss[loss=0.1556, simple_loss=0.2516, pruned_loss=0.02979, over 7284.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2603, pruned_loss=0.04126, over 1408980.14 frames.], batch size: 18, lr: 1.63e-04
2022-05-29 07:30:43,032 INFO [train.py:842] (3/4) Epoch 34, batch 1000, loss[loss=0.1654, simple_loss=0.2569, pruned_loss=0.03697, over 7436.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2595, pruned_loss=0.04052, over 1411079.38 frames.], batch size: 20, lr: 1.63e-04
2022-05-29 07:31:22,405 INFO [train.py:842] (3/4) Epoch 34, batch 1050, loss[loss=0.1333, simple_loss=0.2302, pruned_loss=0.01821, over 7155.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2596, pruned_loss=0.04045, over 1416831.89 frames.], batch size: 19, lr: 1.63e-04
2022-05-29 07:32:01,649 INFO [train.py:842] (3/4) Epoch 34, batch 1100, loss[loss=0.1853, simple_loss=0.2745, pruned_loss=0.04798, over 6302.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2606, pruned_loss=0.04091, over 1414615.91 frames.], batch size: 37, lr: 1.63e-04
2022-05-29 07:32:40,976 INFO [train.py:842] (3/4) Epoch 34, batch 1150, loss[loss=0.1816, simple_loss=0.2717, pruned_loss=0.04572, over 7431.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2613, pruned_loss=0.04148, over 1416965.77 frames.], batch size: 20, lr: 1.63e-04
2022-05-29 07:33:20,634 INFO [train.py:842] (3/4) Epoch 34, batch 1200, loss[loss=0.181, simple_loss=0.269, pruned_loss=0.04654, over 7209.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04192, over 1420956.20 frames.], batch size: 23, lr: 1.63e-04
2022-05-29 07:33:59,717 INFO [train.py:842] (3/4) Epoch 34, batch 1250, loss[loss=0.1549, simple_loss=0.2523, pruned_loss=0.02879, over 7331.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2628, pruned_loss=0.04269, over 1417792.93 frames.], batch size: 22, lr: 1.63e-04
2022-05-29 07:34:39,360 INFO [train.py:842] (3/4) Epoch 34, batch 1300, loss[loss=0.2529, simple_loss=0.3239, pruned_loss=0.09097, over 7189.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2628, pruned_loss=0.04308, over 1417763.69 frames.], batch size: 26, lr: 1.63e-04
2022-05-29 07:35:18,869 INFO [train.py:842] (3/4) Epoch 34, batch 1350, loss[loss=0.2265, simple_loss=0.3116, pruned_loss=0.07066, over 7214.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2624, pruned_loss=0.04298, over 1419166.06 frames.], batch size: 21, lr: 1.63e-04
2022-05-29 07:35:58,700 INFO [train.py:842] (3/4) Epoch 34, batch 1400, loss[loss=0.1848, simple_loss=0.2743, pruned_loss=0.04769, over 7259.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04267, over 1421914.77 frames.], batch size: 19, lr: 1.63e-04
2022-05-29 07:36:38,137 INFO [train.py:842] (3/4) Epoch 34, batch 1450, loss[loss=0.1808, simple_loss=0.2841, pruned_loss=0.03878, over 7410.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2622, pruned_loss=0.04304, over 1425584.63 frames.], batch size: 21, lr: 1.63e-04
2022-05-29 07:37:17,576 INFO [train.py:842] (3/4) Epoch 34, batch 1500, loss[loss=0.1706, simple_loss=0.2579, pruned_loss=0.04171, over 7375.00 frames.], tot_loss[loss=0.175, simple_loss=0.2634, pruned_loss=0.04333, over 1423826.13 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 07:37:56,924 INFO [train.py:842] (3/4) Epoch 34, batch 1550, loss[loss=0.1635, simple_loss=0.2574, pruned_loss=0.03483, over 7279.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2622, pruned_loss=0.04268, over 1421042.35 frames.], batch size: 24, lr: 1.62e-04
2022-05-29 07:38:36,533 INFO [train.py:842] (3/4) Epoch 34, batch 1600, loss[loss=0.1597, simple_loss=0.2557, pruned_loss=0.03183, over 7321.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2628, pruned_loss=0.04311, over 1422614.71 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 07:39:15,582 INFO [train.py:842] (3/4) Epoch 34, batch 1650, loss[loss=0.1797, simple_loss=0.2659, pruned_loss=0.04673, over 7207.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2625, pruned_loss=0.04263, over 1422864.32 frames.], batch size: 22, lr: 1.62e-04
2022-05-29 07:39:54,971 INFO [train.py:842] (3/4) Epoch 34, batch 1700, loss[loss=0.1725, simple_loss=0.2697, pruned_loss=0.03771, over 7391.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2619, pruned_loss=0.04181, over 1427124.93 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 07:40:34,191 INFO [train.py:842] (3/4) Epoch 34, batch 1750, loss[loss=0.1752, simple_loss=0.2686, pruned_loss=0.04089, over 7074.00 frames.], tot_loss[loss=0.1732, simple_loss=0.262, pruned_loss=0.04214, over 1421595.71 frames.], batch size: 28, lr: 1.62e-04
2022-05-29 07:41:13,661 INFO [train.py:842] (3/4) Epoch 34, batch 1800, loss[loss=0.1303, simple_loss=0.227, pruned_loss=0.0168, over 7289.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2629, pruned_loss=0.04234, over 1422394.55 frames.], batch size: 17, lr: 1.62e-04
2022-05-29 07:41:52,956 INFO [train.py:842] (3/4) Epoch 34, batch 1850, loss[loss=0.1694, simple_loss=0.2625, pruned_loss=0.03814, over 7317.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2623, pruned_loss=0.04235, over 1414522.39 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 07:42:32,386 INFO [train.py:842] (3/4) Epoch 34, batch 1900, loss[loss=0.1619, simple_loss=0.2524, pruned_loss=0.03569, over 6749.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2626, pruned_loss=0.04238, over 1410199.98 frames.], batch size: 31, lr: 1.62e-04
2022-05-29 07:43:11,715 INFO [train.py:842] (3/4) Epoch 34, batch 1950, loss[loss=0.1452, simple_loss=0.2293, pruned_loss=0.03057, over 6994.00 frames.], tot_loss[loss=0.173, simple_loss=0.2622, pruned_loss=0.04192, over 1416292.47 frames.], batch size: 16, lr: 1.62e-04
2022-05-29 07:43:51,639 INFO [train.py:842] (3/4) Epoch 34, batch 2000, loss[loss=0.1784, simple_loss=0.2503, pruned_loss=0.05327, over 7421.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2619, pruned_loss=0.04175, over 1421408.58 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 07:44:31,048 INFO [train.py:842] (3/4) Epoch 34, batch 2050, loss[loss=0.1812, simple_loss=0.2701, pruned_loss=0.0461, over 7197.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2608, pruned_loss=0.04152, over 1421257.31 frames.], batch size: 26, lr: 1.62e-04
2022-05-29 07:45:10,525 INFO [train.py:842] (3/4) Epoch 34, batch 2100, loss[loss=0.2415, simple_loss=0.3385, pruned_loss=0.07228, over 7215.00 frames.], tot_loss[loss=0.1743, simple_loss=0.263, pruned_loss=0.04284, over 1424298.62 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 07:45:49,755 INFO [train.py:842] (3/4) Epoch 34, batch 2150, loss[loss=0.1894, simple_loss=0.2786, pruned_loss=0.05006, over 7297.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2629, pruned_loss=0.04268, over 1423996.51 frames.], batch size: 24, lr: 1.62e-04
2022-05-29 07:46:29,280 INFO [train.py:842] (3/4) Epoch 34, batch 2200, loss[loss=0.1618, simple_loss=0.2566, pruned_loss=0.03345, over 7320.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2632, pruned_loss=0.04232, over 1426744.97 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 07:47:08,693 INFO [train.py:842] (3/4) Epoch 34, batch 2250, loss[loss=0.1363, simple_loss=0.2136, pruned_loss=0.02948, over 7280.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2625, pruned_loss=0.04255, over 1423748.83 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 07:47:47,851 INFO [train.py:842] (3/4) Epoch 34, batch 2300, loss[loss=0.1662, simple_loss=0.2549, pruned_loss=0.0388, over 7156.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2638, pruned_loss=0.04246, over 1424610.25 frames.], batch size: 19, lr: 1.62e-04
2022-05-29 07:48:27,198 INFO [train.py:842] (3/4) Epoch 34, batch 2350, loss[loss=0.162, simple_loss=0.2572, pruned_loss=0.03345, over 7152.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2626, pruned_loss=0.04226, over 1425258.55 frames.], batch size: 19, lr: 1.62e-04
2022-05-29 07:49:06,852 INFO [train.py:842] (3/4) Epoch 34, batch 2400, loss[loss=0.1903, simple_loss=0.2792, pruned_loss=0.05069, over 7349.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2622, pruned_loss=0.04199, over 1426406.55 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 07:49:45,768 INFO [train.py:842] (3/4) Epoch 34, batch 2450, loss[loss=0.1878, simple_loss=0.2835, pruned_loss=0.04605, over 7212.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2637, pruned_loss=0.04266, over 1420153.77 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 07:50:25,174 INFO [train.py:842] (3/4) Epoch 34, batch 2500, loss[loss=0.1315, simple_loss=0.2153, pruned_loss=0.02385, over 7015.00 frames.], tot_loss[loss=0.174, simple_loss=0.2632, pruned_loss=0.04243, over 1418963.38 frames.], batch size: 16, lr: 1.62e-04
2022-05-29 07:51:04,344 INFO [train.py:842] (3/4) Epoch 34, batch 2550, loss[loss=0.1708, simple_loss=0.2633, pruned_loss=0.03915, over 7328.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2626, pruned_loss=0.04203, over 1420403.06 frames.], batch size: 22, lr: 1.62e-04
2022-05-29 07:51:44,002 INFO [train.py:842] (3/4) Epoch 34, batch 2600, loss[loss=0.167, simple_loss=0.2518, pruned_loss=0.0411, over 7070.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2625, pruned_loss=0.04198, over 1419777.86 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 07:52:23,461 INFO [train.py:842] (3/4) Epoch 34, batch 2650, loss[loss=0.1789, simple_loss=0.2822, pruned_loss=0.03777, over 7328.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04114, over 1420442.65 frames.], batch size: 22, lr: 1.62e-04
2022-05-29 07:53:03,143 INFO [train.py:842] (3/4) Epoch 34, batch 2700, loss[loss=0.1556, simple_loss=0.2356, pruned_loss=0.03774, over 7268.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2606, pruned_loss=0.04101, over 1425125.71 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 07:53:42,409 INFO [train.py:842] (3/4) Epoch 34, batch 2750, loss[loss=0.1646, simple_loss=0.2522, pruned_loss=0.0385, over 7314.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2602, pruned_loss=0.04069, over 1424639.85 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 07:54:21,964 INFO [train.py:842] (3/4) Epoch 34, batch 2800, loss[loss=0.1482, simple_loss=0.225, pruned_loss=0.03565, over 7408.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2599, pruned_loss=0.04024, over 1429296.54 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 07:55:01,271 INFO [train.py:842] (3/4) Epoch 34, batch 2850, loss[loss=0.2177, simple_loss=0.292, pruned_loss=0.07167, over 7203.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2606, pruned_loss=0.04063, over 1430028.32 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 07:55:40,896 INFO [train.py:842] (3/4) Epoch 34, batch 2900, loss[loss=0.199, simple_loss=0.3016, pruned_loss=0.0482, over 7147.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2622, pruned_loss=0.04148, over 1427747.76 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 07:56:20,246 INFO [train.py:842] (3/4) Epoch 34, batch 2950, loss[loss=0.1499, simple_loss=0.2406, pruned_loss=0.02963, over 7152.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.04126, over 1427481.01 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 07:56:59,641 INFO [train.py:842] (3/4) Epoch 34, batch 3000, loss[loss=0.1441, simple_loss=0.2288, pruned_loss=0.02976, over 7354.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2612, pruned_loss=0.04112, over 1427709.71 frames.], batch size: 19, lr: 1.62e-04
2022-05-29 07:56:59,642 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 07:57:09,214 INFO [train.py:871] (3/4) Epoch 34, validation: loss=0.165, simple_loss=0.2618, pruned_loss=0.03414, over 868885.00 frames.
2022-05-29 07:57:48,366 INFO [train.py:842] (3/4) Epoch 34, batch 3050, loss[loss=0.1611, simple_loss=0.2452, pruned_loss=0.03844, over 7357.00 frames.], tot_loss[loss=0.172, simple_loss=0.2615, pruned_loss=0.04123, over 1427985.90 frames.], batch size: 19, lr: 1.62e-04
2022-05-29 07:58:28,171 INFO [train.py:842] (3/4) Epoch 34, batch 3100, loss[loss=0.1613, simple_loss=0.251, pruned_loss=0.03584, over 6768.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2614, pruned_loss=0.0414, over 1428827.21 frames.], batch size: 15, lr: 1.62e-04
2022-05-29 07:59:07,373 INFO [train.py:842] (3/4) Epoch 34, batch 3150, loss[loss=0.1644, simple_loss=0.244, pruned_loss=0.04244, over 7277.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2605, pruned_loss=0.04093, over 1428736.34 frames.], batch size: 17, lr: 1.62e-04
2022-05-29 07:59:46,879 INFO [train.py:842] (3/4) Epoch 34, batch 3200, loss[loss=0.1998, simple_loss=0.2771, pruned_loss=0.06119, over 5294.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2596, pruned_loss=0.04061, over 1424592.97 frames.], batch size: 52, lr: 1.62e-04
2022-05-29 08:00:26,151 INFO [train.py:842] (3/4) Epoch 34, batch 3250, loss[loss=0.1719, simple_loss=0.2475, pruned_loss=0.04814, over 7147.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2597, pruned_loss=0.04071, over 1422143.83 frames.], batch size: 17, lr: 1.62e-04
2022-05-29 08:01:05,726 INFO [train.py:842] (3/4) Epoch 34, batch 3300, loss[loss=0.1729, simple_loss=0.2662, pruned_loss=0.03981, over 7101.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2598, pruned_loss=0.04067, over 1418439.18 frames.], batch size: 28, lr: 1.62e-04
2022-05-29 08:01:45,234 INFO [train.py:842] (3/4) Epoch 34, batch 3350, loss[loss=0.1592, simple_loss=0.2578, pruned_loss=0.0303, over 7148.00 frames.], tot_loss[loss=0.1699, simple_loss=0.259, pruned_loss=0.0404, over 1421086.48 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:02:24,818 INFO [train.py:842] (3/4) Epoch 34, batch 3400, loss[loss=0.1625, simple_loss=0.2593, pruned_loss=0.03288, over 7195.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04103, over 1421845.95 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 08:03:04,115 INFO [train.py:842] (3/4) Epoch 34, batch 3450, loss[loss=0.1385, simple_loss=0.2193, pruned_loss=0.02884, over 6994.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2616, pruned_loss=0.04175, over 1427361.45 frames.], batch size: 16, lr: 1.62e-04
2022-05-29 08:03:43,422 INFO [train.py:842] (3/4) Epoch 34, batch 3500, loss[loss=0.1847, simple_loss=0.2806, pruned_loss=0.04434, over 7211.00 frames.], tot_loss[loss=0.1736, simple_loss=0.263, pruned_loss=0.04211, over 1429128.66 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 08:04:22,903 INFO [train.py:842] (3/4) Epoch 34, batch 3550, loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04084, over 7278.00 frames.], tot_loss[loss=0.1729, simple_loss=0.262, pruned_loss=0.04187, over 1431349.75 frames.], batch size: 17, lr: 1.62e-04
2022-05-29 08:05:02,706 INFO [train.py:842] (3/4) Epoch 34, batch 3600, loss[loss=0.1991, simple_loss=0.2886, pruned_loss=0.05477, over 7322.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2632, pruned_loss=0.04267, over 1433431.37 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 08:05:42,003 INFO [train.py:842] (3/4) Epoch 34, batch 3650, loss[loss=0.1664, simple_loss=0.2499, pruned_loss=0.04147, over 7432.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2634, pruned_loss=0.04289, over 1430466.72 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:06:21,230 INFO [train.py:842] (3/4) Epoch 34, batch 3700, loss[loss=0.1885, simple_loss=0.2786, pruned_loss=0.0492, over 5011.00 frames.], tot_loss[loss=0.1738, simple_loss=0.262, pruned_loss=0.04275, over 1423556.33 frames.], batch size: 53, lr: 1.62e-04
2022-05-29 08:07:00,392 INFO [train.py:842] (3/4) Epoch 34, batch 3750, loss[loss=0.1928, simple_loss=0.272, pruned_loss=0.05679, over 7128.00 frames.], tot_loss[loss=0.173, simple_loss=0.2613, pruned_loss=0.04236, over 1421387.51 frames.], batch size: 17, lr: 1.62e-04
2022-05-29 08:07:40,328 INFO [train.py:842] (3/4) Epoch 34, batch 3800, loss[loss=0.2402, simple_loss=0.3379, pruned_loss=0.07129, over 7235.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2597, pruned_loss=0.04147, over 1423860.74 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:08:19,524 INFO [train.py:842] (3/4) Epoch 34, batch 3850, loss[loss=0.1507, simple_loss=0.2482, pruned_loss=0.02664, over 6966.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2602, pruned_loss=0.04145, over 1425484.43 frames.], batch size: 28, lr: 1.62e-04
2022-05-29 08:08:59,250 INFO [train.py:842] (3/4) Epoch 34, batch 3900, loss[loss=0.1375, simple_loss=0.2315, pruned_loss=0.02178, over 7351.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2595, pruned_loss=0.04092, over 1428489.90 frames.], batch size: 19, lr: 1.62e-04
2022-05-29 08:09:38,364 INFO [train.py:842] (3/4) Epoch 34, batch 3950, loss[loss=0.1763, simple_loss=0.2683, pruned_loss=0.04216, over 7330.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2597, pruned_loss=0.041, over 1421188.51 frames.], batch size: 22, lr: 1.62e-04
2022-05-29 08:10:18,084 INFO [train.py:842] (3/4) Epoch 34, batch 4000, loss[loss=0.2088, simple_loss=0.2888, pruned_loss=0.0644, over 7144.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2594, pruned_loss=0.04071, over 1424678.70 frames.], batch size: 26, lr: 1.62e-04
2022-05-29 08:10:57,409 INFO [train.py:842] (3/4) Epoch 34, batch 4050, loss[loss=0.1408, simple_loss=0.2354, pruned_loss=0.02304, over 7437.00 frames.], tot_loss[loss=0.17, simple_loss=0.2588, pruned_loss=0.04059, over 1424192.94 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:11:36,848 INFO [train.py:842] (3/4) Epoch 34, batch 4100, loss[loss=0.1594, simple_loss=0.2431, pruned_loss=0.03783, over 7330.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2611, pruned_loss=0.04189, over 1422037.94 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:12:16,166 INFO [train.py:842] (3/4) Epoch 34, batch 4150, loss[loss=0.1632, simple_loss=0.254, pruned_loss=0.03622, over 7418.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2601, pruned_loss=0.04146, over 1423824.21 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:12:55,745 INFO [train.py:842] (3/4) Epoch 34, batch 4200, loss[loss=0.1515, simple_loss=0.2461, pruned_loss=0.02848, over 6726.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2611, pruned_loss=0.04174, over 1421372.78 frames.], batch size: 31, lr: 1.62e-04
2022-05-29 08:13:35,025 INFO [train.py:842] (3/4) Epoch 34, batch 4250, loss[loss=0.1675, simple_loss=0.2578, pruned_loss=0.03858, over 7328.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2619, pruned_loss=0.04159, over 1424448.64 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:14:14,630 INFO [train.py:842] (3/4) Epoch 34, batch 4300, loss[loss=0.1485, simple_loss=0.2487, pruned_loss=0.02419, over 6737.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2612, pruned_loss=0.04152, over 1425962.25 frames.], batch size: 31, lr: 1.62e-04
2022-05-29 08:14:53,548 INFO [train.py:842] (3/4) Epoch 34, batch 4350, loss[loss=0.1597, simple_loss=0.2571, pruned_loss=0.03118, over 7313.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2628, pruned_loss=0.04182, over 1425399.38 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 08:15:33,262 INFO [train.py:842] (3/4) Epoch 34, batch 4400, loss[loss=0.1509, simple_loss=0.2478, pruned_loss=0.02706, over 7234.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2623, pruned_loss=0.04179, over 1427987.21 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:16:12,436 INFO [train.py:842] (3/4) Epoch 34, batch 4450, loss[loss=0.2452, simple_loss=0.3331, pruned_loss=0.07861, over 7225.00 frames.], tot_loss[loss=0.1735, simple_loss=0.263, pruned_loss=0.04207, over 1426758.46 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 08:16:52,068 INFO [train.py:842] (3/4) Epoch 34, batch 4500, loss[loss=0.1565, simple_loss=0.2333, pruned_loss=0.03988, over 7189.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2624, pruned_loss=0.04202, over 1426431.96 frames.], batch size: 16, lr: 1.62e-04
2022-05-29 08:17:31,647 INFO [train.py:842] (3/4) Epoch 34, batch 4550, loss[loss=0.1473, simple_loss=0.2325, pruned_loss=0.03109, over 7270.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2614, pruned_loss=0.04151, over 1427597.45 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 08:18:11,496 INFO [train.py:842] (3/4) Epoch 34, batch 4600, loss[loss=0.1965, simple_loss=0.2873, pruned_loss=0.05291, over 6546.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2614, pruned_loss=0.04198, over 1421870.81 frames.], batch size: 37, lr: 1.62e-04
2022-05-29 08:18:50,835 INFO [train.py:842] (3/4) Epoch 34, batch 4650, loss[loss=0.1597, simple_loss=0.2589, pruned_loss=0.03029, over 7426.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2617, pruned_loss=0.04222, over 1423100.37 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 08:19:30,461 INFO [train.py:842] (3/4) Epoch 34, batch 4700, loss[loss=0.1748, simple_loss=0.2487, pruned_loss=0.05046, over 7286.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04227, over 1421696.00 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 08:20:09,794 INFO [train.py:842] (3/4) Epoch 34, batch 4750, loss[loss=0.1583, simple_loss=0.2493, pruned_loss=0.03363, over 7140.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04178, over 1422194.57 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:20:49,493 INFO [train.py:842] (3/4) Epoch 34, batch 4800, loss[loss=0.2408, simple_loss=0.3242, pruned_loss=0.07864, over 7408.00 frames.], tot_loss[loss=0.172, simple_loss=0.2611, pruned_loss=0.04142, over 1424777.53 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 08:21:28,559 INFO [train.py:842] (3/4) Epoch 34, batch 4850, loss[loss=0.222, simple_loss=0.3047, pruned_loss=0.06965, over 7427.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2615, pruned_loss=0.04141, over 1424891.20 frames.], batch size: 21, lr: 1.62e-04
2022-05-29 08:22:08,258 INFO [train.py:842] (3/4) Epoch 34, batch 4900, loss[loss=0.2098, simple_loss=0.2972, pruned_loss=0.06113, over 7320.00 frames.], tot_loss[loss=0.1728, simple_loss=0.262, pruned_loss=0.04178, over 1422983.65 frames.], batch size: 22, lr: 1.62e-04
2022-05-29 08:22:47,451 INFO [train.py:842] (3/4) Epoch 34, batch 4950, loss[loss=0.15, simple_loss=0.2283, pruned_loss=0.03584, over 6991.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2618, pruned_loss=0.04183, over 1421232.21 frames.], batch size: 16, lr: 1.62e-04
2022-05-29 08:23:27,046 INFO [train.py:842] (3/4) Epoch 34, batch 5000, loss[loss=0.169, simple_loss=0.2727, pruned_loss=0.03264, over 7151.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2613, pruned_loss=0.04154, over 1419429.29 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:24:06,282 INFO [train.py:842] (3/4) Epoch 34, batch 5050, loss[loss=0.1817, simple_loss=0.2565, pruned_loss=0.05345, over 7294.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2622, pruned_loss=0.04234, over 1423194.52 frames.], batch size: 18, lr: 1.62e-04
2022-05-29 08:24:46,031 INFO [train.py:842] (3/4) Epoch 34, batch 5100, loss[loss=0.1569, simple_loss=0.2528, pruned_loss=0.03045, over 7315.00 frames.], tot_loss[loss=0.173, simple_loss=0.2622, pruned_loss=0.04188, over 1427362.78 frames.], batch size: 25, lr: 1.62e-04
2022-05-29 08:25:25,116 INFO [train.py:842] (3/4) Epoch 34, batch 5150, loss[loss=0.1684, simple_loss=0.2606, pruned_loss=0.03813, over 6749.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2616, pruned_loss=0.04212, over 1424119.00 frames.], batch size: 31, lr: 1.62e-04
2022-05-29 08:26:04,891 INFO [train.py:842] (3/4) Epoch 34, batch 5200, loss[loss=0.155, simple_loss=0.2397, pruned_loss=0.03517, over 7430.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2602, pruned_loss=0.04153, over 1425287.75 frames.], batch size: 20, lr: 1.62e-04
2022-05-29 08:26:44,211 INFO [train.py:842] (3/4) Epoch 34, batch 5250, loss[loss=0.2148, simple_loss=0.3095, pruned_loss=0.06, over 7375.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2606, pruned_loss=0.04153, over 1426293.90 frames.], batch size: 23, lr: 1.62e-04
2022-05-29 08:27:23,826 INFO [train.py:842] (3/4) Epoch 34, batch 5300, loss[loss=0.1509, simple_loss=0.2336, pruned_loss=0.03413, over 7281.00 frames.], tot_loss[loss=0.1725, simple_loss=0.261, pruned_loss=0.04198, over 1425992.26 frames.], batch size: 17, lr: 1.61e-04
2022-05-29 08:28:03,181 INFO [train.py:842] (3/4) Epoch 34, batch 5350, loss[loss=0.2073, simple_loss=0.2785, pruned_loss=0.06801, over 7152.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04257, over 1418271.88 frames.], batch size: 17, lr: 1.61e-04
2022-05-29 08:28:42,831 INFO [train.py:842] (3/4) Epoch 34, batch 5400, loss[loss=0.1993, simple_loss=0.2872, pruned_loss=0.05566, over 7296.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2634, pruned_loss=0.04287, over 1420443.14 frames.], batch size: 25, lr: 1.61e-04
2022-05-29 08:29:21,737 INFO [train.py:842] (3/4) Epoch 34, batch 5450, loss[loss=0.1897, simple_loss=0.2832, pruned_loss=0.04815, over 6473.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2628, pruned_loss=0.04233, over 1417710.28 frames.], batch size: 38, lr: 1.61e-04
2022-05-29 08:30:01,363 INFO [train.py:842] (3/4) Epoch 34, batch 5500, loss[loss=0.1751, simple_loss=0.2695, pruned_loss=0.04033, over 7207.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2625, pruned_loss=0.042, over 1420184.98 frames.], batch size: 22, lr: 1.61e-04
2022-05-29 08:30:40,416 INFO [train.py:842] (3/4) Epoch 34, batch 5550, loss[loss=0.1518, simple_loss=0.2445, pruned_loss=0.02951, over 7231.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2638, pruned_loss=0.04255, over 1418745.72 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:31:19,883 INFO [train.py:842] (3/4) Epoch 34, batch 5600, loss[loss=0.185, simple_loss=0.285, pruned_loss=0.04252, over 7323.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2635, pruned_loss=0.0424, over 1420368.80 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:31:59,165 INFO [train.py:842] (3/4) Epoch 34, batch 5650, loss[loss=0.1757, simple_loss=0.2783, pruned_loss=0.03652, over 7200.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2624, pruned_loss=0.04204, over 1419168.39 frames.], batch size: 23, lr: 1.61e-04
2022-05-29 08:32:38,756 INFO [train.py:842] (3/4) Epoch 34, batch 5700, loss[loss=0.228, simple_loss=0.3034, pruned_loss=0.07625, over 7313.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2625, pruned_loss=0.04217, over 1421062.75 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:33:17,960 INFO [train.py:842] (3/4) Epoch 34, batch 5750, loss[loss=0.1621, simple_loss=0.2498, pruned_loss=0.03718, over 7364.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2614, pruned_loss=0.04141, over 1423198.14 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 08:33:57,821 INFO [train.py:842] (3/4) Epoch 34, batch 5800, loss[loss=0.1583, simple_loss=0.2558, pruned_loss=0.03043, over 7316.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2609, pruned_loss=0.041, over 1423053.25 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:34:37,235 INFO [train.py:842] (3/4) Epoch 34, batch 5850, loss[loss=0.2051, simple_loss=0.2947, pruned_loss=0.05771, over 6391.00 frames.], tot_loss[loss=0.171, simple_loss=0.2601, pruned_loss=0.04098, over 1425679.29 frames.], batch size: 37, lr: 1.61e-04
2022-05-29 08:35:27,495 INFO [train.py:842] (3/4) Epoch 34, batch 5900, loss[loss=0.1712, simple_loss=0.2658, pruned_loss=0.03826, over 7217.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.04132, over 1420648.53 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:36:06,835 INFO [train.py:842] (3/4) Epoch 34, batch 5950, loss[loss=0.1721, simple_loss=0.2741, pruned_loss=0.03503, over 6222.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.04179, over 1421532.04 frames.], batch size: 37, lr: 1.61e-04
2022-05-29 08:36:46,435 INFO [train.py:842] (3/4) Epoch 34, batch 6000, loss[loss=0.1537, simple_loss=0.2294, pruned_loss=0.03896, over 6985.00 frames.], tot_loss[loss=0.1742, simple_loss=0.263, pruned_loss=0.04277, over 1422225.78 frames.], batch size: 16, lr: 1.61e-04
2022-05-29 08:36:46,436 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 08:36:56,770 INFO [train.py:871] (3/4) Epoch 34, validation: loss=0.1642, simple_loss=0.2613, pruned_loss=0.03356, over 868885.00 frames.
2022-05-29 08:37:36,215 INFO [train.py:842] (3/4) Epoch 34, batch 6050, loss[loss=0.1861, simple_loss=0.2693, pruned_loss=0.05145, over 5087.00 frames.], tot_loss[loss=0.175, simple_loss=0.2637, pruned_loss=0.04313, over 1425595.18 frames.], batch size: 53, lr: 1.61e-04
2022-05-29 08:38:15,767 INFO [train.py:842] (3/4) Epoch 34, batch 6100, loss[loss=0.1884, simple_loss=0.2723, pruned_loss=0.05226, over 7238.00 frames.], tot_loss[loss=0.1753, simple_loss=0.264, pruned_loss=0.04331, over 1423671.57 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:38:55,094 INFO [train.py:842] (3/4) Epoch 34, batch 6150, loss[loss=0.187, simple_loss=0.2724, pruned_loss=0.05085, over 7188.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2639, pruned_loss=0.04332, over 1425280.22 frames.], batch size: 23, lr: 1.61e-04
2022-05-29 08:39:34,494 INFO [train.py:842] (3/4) Epoch 34, batch 6200, loss[loss=0.1799, simple_loss=0.2591, pruned_loss=0.05038, over 7288.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2644, pruned_loss=0.04345, over 1424195.98 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:40:13,623 INFO [train.py:842] (3/4) Epoch 34, batch 6250, loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03272, over 7222.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04241, over 1427383.94 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:40:53,093 INFO [train.py:842] (3/4) Epoch 34, batch 6300, loss[loss=0.1485, simple_loss=0.225, pruned_loss=0.03602, over 7159.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2621, pruned_loss=0.0416, over 1430947.13 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:41:32,256 INFO [train.py:842] (3/4) Epoch 34, batch 6350, loss[loss=0.1867, simple_loss=0.2737, pruned_loss=0.04984, over 7151.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2629, pruned_loss=0.04205, over 1427927.73 frames.], batch size: 26, lr: 1.61e-04
2022-05-29 08:42:12,055 INFO [train.py:842] (3/4) Epoch 34, batch 6400, loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03326, over 7337.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2622, pruned_loss=0.04175, over 1430983.54 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:42:51,297 INFO [train.py:842] (3/4) Epoch 34, batch 6450, loss[loss=0.1617, simple_loss=0.259, pruned_loss=0.03221, over 7228.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2619, pruned_loss=0.0418, over 1426884.19 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:43:31,041 INFO [train.py:842] (3/4) Epoch 34, batch 6500, loss[loss=0.1531, simple_loss=0.2353, pruned_loss=0.03548, over 7399.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2621, pruned_loss=0.04132, over 1429239.05 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:44:10,231 INFO [train.py:842] (3/4) Epoch 34, batch 6550, loss[loss=0.1524, simple_loss=0.2513, pruned_loss=0.02677, over 7112.00 frames.], tot_loss[loss=0.172, simple_loss=0.2619, pruned_loss=0.0411, over 1430054.27 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:44:50,116 INFO [train.py:842] (3/4) Epoch 34, batch 6600, loss[loss=0.1508, simple_loss=0.2356, pruned_loss=0.03304, over 7271.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2609, pruned_loss=0.04115, over 1432408.99 frames.], batch size: 16, lr: 1.61e-04
2022-05-29 08:45:29,268 INFO [train.py:842] (3/4) Epoch 34, batch 6650, loss[loss=0.1525, simple_loss=0.2411, pruned_loss=0.03194, over 7164.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2614, pruned_loss=0.04148, over 1427406.44 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:46:08,633 INFO [train.py:842] (3/4) Epoch 34, batch 6700, loss[loss=0.1495, simple_loss=0.2498, pruned_loss=0.02456, over 7220.00 frames.], tot_loss[loss=0.1736, simple_loss=0.263, pruned_loss=0.0421, over 1425746.84 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:46:47,744 INFO [train.py:842] (3/4) Epoch 34, batch 6750, loss[loss=0.1728, simple_loss=0.2611, pruned_loss=0.04223, over 7217.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2646, pruned_loss=0.04291, over 1423205.61 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:47:27,255 INFO [train.py:842] (3/4) Epoch 34, batch 6800, loss[loss=0.1932, simple_loss=0.2845, pruned_loss=0.05097, over 7143.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2646, pruned_loss=0.04309, over 1415055.67 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:48:06,413 INFO [train.py:842] (3/4) Epoch 34, batch 6850, loss[loss=0.1813, simple_loss=0.2716, pruned_loss=0.04548, over 6713.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2641, pruned_loss=0.04288, over 1415379.16 frames.], batch size: 31, lr: 1.61e-04
2022-05-29 08:48:45,882 INFO [train.py:842] (3/4) Epoch 34, batch 6900, loss[loss=0.1706, simple_loss=0.2649, pruned_loss=0.03821, over 6828.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2636, pruned_loss=0.04274, over 1415547.46 frames.], batch size: 31, lr: 1.61e-04
2022-05-29 08:49:25,585 INFO [train.py:842] (3/4) Epoch 34, batch 6950, loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.04137, over 7133.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2627, pruned_loss=0.04247, over 1420342.97 frames.], batch size: 26, lr: 1.61e-04
2022-05-29 08:50:05,182 INFO [train.py:842] (3/4) Epoch 34, batch 7000, loss[loss=0.2046, simple_loss=0.2929, pruned_loss=0.05814, over 7168.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04224, over 1419166.86 frames.], batch size: 26, lr: 1.61e-04
2022-05-29 08:50:44,483 INFO [train.py:842] (3/4) Epoch 34, batch 7050, loss[loss=0.1831, simple_loss=0.2693, pruned_loss=0.04845, over 7067.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04194, over 1419463.28 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:51:24,153 INFO [train.py:842] (3/4) Epoch 34, batch 7100, loss[loss=0.1899, simple_loss=0.2794, pruned_loss=0.0502, over 7418.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2621, pruned_loss=0.04236, over 1424108.59 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:52:03,391 INFO [train.py:842] (3/4) Epoch 34, batch 7150, loss[loss=0.1737, simple_loss=0.2704, pruned_loss=0.03849, over 7429.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2622, pruned_loss=0.04249, over 1425288.45 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 08:52:43,310 INFO [train.py:842] (3/4) Epoch 34, batch 7200, loss[loss=0.1706, simple_loss=0.2541, pruned_loss=0.04354, over 7165.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04215, over 1423411.05 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 08:53:22,468 INFO [train.py:842] (3/4) Epoch 34, batch 7250, loss[loss=0.1901, simple_loss=0.2705, pruned_loss=0.05487, over 7212.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04258, over 1422099.88 frames.], batch size: 16, lr: 1.61e-04
2022-05-29 08:54:02,129 INFO [train.py:842] (3/4) Epoch 34, batch 7300, loss[loss=0.1713, simple_loss=0.2533, pruned_loss=0.04469, over 7154.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2615, pruned_loss=0.04229, over 1425231.40 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 08:54:41,349 INFO [train.py:842] (3/4) Epoch 34, batch 7350, loss[loss=0.1808, simple_loss=0.2886, pruned_loss=0.03647, over 7082.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2619, pruned_loss=0.04252, over 1421741.41 frames.], batch size: 28, lr: 1.61e-04
2022-05-29 08:55:20,719 INFO [train.py:842] (3/4) Epoch 34, batch 7400, loss[loss=0.1633, simple_loss=0.2558, pruned_loss=0.03542, over 7059.00 frames.], tot_loss[loss=0.175, simple_loss=0.2635, pruned_loss=0.04328, over 1419691.17 frames.], batch size: 28, lr: 1.61e-04
2022-05-29 08:55:59,983 INFO [train.py:842] (3/4) Epoch 34, batch 7450, loss[loss=0.1794, simple_loss=0.2802, pruned_loss=0.0393, over 7110.00 frames.], tot_loss[loss=0.1756, simple_loss=0.264, pruned_loss=0.04355, over 1422244.95 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:56:39,513 INFO [train.py:842] (3/4) Epoch 34, batch 7500, loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03249, over 7312.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2622, pruned_loss=0.04257, over 1423663.27 frames.], batch size: 25, lr: 1.61e-04
2022-05-29 08:57:18,923 INFO [train.py:842] (3/4) Epoch 34, batch 7550, loss[loss=0.2402, simple_loss=0.3041, pruned_loss=0.08813, over 6817.00 frames.], tot_loss[loss=0.1726, simple_loss=0.261, pruned_loss=0.04208, over 1423403.29 frames.], batch size: 15, lr: 1.61e-04
2022-05-29 08:57:58,724 INFO [train.py:842] (3/4) Epoch 34, batch 7600, loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03221, over 6823.00 frames.], tot_loss[loss=0.1735, simple_loss=0.262, pruned_loss=0.04247, over 1427952.52 frames.], batch size: 15, lr: 1.61e-04
2022-05-29 08:58:37,747 INFO [train.py:842] (3/4) Epoch 34, batch 7650, loss[loss=0.1867, simple_loss=0.2779, pruned_loss=0.04775, over 7110.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2612, pruned_loss=0.04165, over 1427899.39 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 08:59:17,462 INFO [train.py:842] (3/4) Epoch 34, batch 7700, loss[loss=0.1785, simple_loss=0.271, pruned_loss=0.04295, over 7185.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04194, over 1426443.54 frames.], batch size: 26, lr: 1.61e-04
2022-05-29 08:59:56,668 INFO [train.py:842] (3/4) Epoch 34, batch 7750, loss[loss=0.1707, simple_loss=0.2551, pruned_loss=0.04321, over 7370.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2603, pruned_loss=0.0415, over 1427862.92 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 09:00:36,155 INFO [train.py:842] (3/4) Epoch 34, batch 7800, loss[loss=0.1488, simple_loss=0.2274, pruned_loss=0.03516, over 7276.00 frames.], tot_loss[loss=0.1723, simple_loss=0.261, pruned_loss=0.04179, over 1424633.92 frames.], batch size: 17, lr: 1.61e-04
2022-05-29 09:01:15,313 INFO [train.py:842] (3/4) Epoch 34, batch 7850, loss[loss=0.2573, simple_loss=0.3234, pruned_loss=0.09561, over 5298.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2619, pruned_loss=0.04224, over 1424309.51 frames.], batch size: 52, lr: 1.61e-04
2022-05-29 09:01:54,542 INFO [train.py:842] (3/4) Epoch 34, batch 7900, loss[loss=0.2811, simple_loss=0.343, pruned_loss=0.1096, over 4768.00 frames.], tot_loss[loss=0.1743, simple_loss=0.263, pruned_loss=0.04281, over 1417483.49 frames.], batch size: 52, lr: 1.61e-04
2022-05-29 09:02:33,807 INFO [train.py:842] (3/4) Epoch 34, batch 7950, loss[loss=0.1772, simple_loss=0.2713, pruned_loss=0.04153, over 7285.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2626, pruned_loss=0.04252, over 1420535.61 frames.], batch size: 24, lr: 1.61e-04
2022-05-29 09:03:13,371 INFO [train.py:842] (3/4) Epoch 34, batch 8000, loss[loss=0.2068, simple_loss=0.2934, pruned_loss=0.0601, over 7209.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2615, pruned_loss=0.04176, over 1418886.12 frames.], batch size: 23, lr: 1.61e-04
2022-05-29 09:03:52,526 INFO [train.py:842] (3/4) Epoch 34, batch 8050, loss[loss=0.1581, simple_loss=0.2455, pruned_loss=0.0354, over 7162.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2617, pruned_loss=0.04162, over 1415354.22 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 09:04:32,350 INFO [train.py:842] (3/4) Epoch 34, batch 8100, loss[loss=0.1712, simple_loss=0.2591, pruned_loss=0.04168, over 7252.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2609, pruned_loss=0.04106, over 1420946.69 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 09:05:11,684 INFO [train.py:842] (3/4) Epoch 34, batch 8150, loss[loss=0.1533, simple_loss=0.2474, pruned_loss=0.02958, over 7221.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04097, over 1422163.68 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 09:05:51,186 INFO [train.py:842] (3/4) Epoch 34, batch 8200, loss[loss=0.1797, simple_loss=0.2802, pruned_loss=0.03958, over 7116.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04088, over 1423078.98 frames.], batch size: 28, lr: 1.61e-04
2022-05-29 09:06:30,371 INFO [train.py:842] (3/4) Epoch 34, batch 8250, loss[loss=0.1673, simple_loss=0.2697, pruned_loss=0.0324, over 7335.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2607, pruned_loss=0.04077, over 1419473.73 frames.], batch size: 25, lr: 1.61e-04
2022-05-29 09:07:09,895 INFO [train.py:842] (3/4) Epoch 34, batch 8300, loss[loss=0.2826, simple_loss=0.3444, pruned_loss=0.1104, over 5020.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2613, pruned_loss=0.04162, over 1420149.99 frames.], batch size: 53, lr: 1.61e-04
2022-05-29 09:07:49,134 INFO [train.py:842] (3/4) Epoch 34, batch 8350, loss[loss=0.1371, simple_loss=0.2247, pruned_loss=0.02478, over 7167.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2613, pruned_loss=0.04183, over 1417626.75 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 09:08:28,623 INFO [train.py:842] (3/4) Epoch 34, batch 8400, loss[loss=0.145, simple_loss=0.2341, pruned_loss=0.02802, over 7268.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04253, over 1417995.06 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 09:09:07,971 INFO [train.py:842] (3/4) Epoch 34, batch 8450, loss[loss=0.1423, simple_loss=0.2306, pruned_loss=0.02697, over 7153.00 frames.], tot_loss[loss=0.1742, simple_loss=0.263, pruned_loss=0.04277, over 1418882.75 frames.], batch size: 17, lr: 1.61e-04
2022-05-29 09:09:47,757 INFO [train.py:842] (3/4) Epoch 34, batch 8500, loss[loss=0.1781, simple_loss=0.2727, pruned_loss=0.04177, over 7147.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2635, pruned_loss=0.04311, over 1417982.84 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 09:10:26,701 INFO [train.py:842] (3/4) Epoch 34, batch 8550, loss[loss=0.1853, simple_loss=0.271, pruned_loss=0.04976, over 7214.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2634, pruned_loss=0.04308, over 1416595.90 frames.], batch size: 23, lr: 1.61e-04
2022-05-29 09:11:06,071 INFO [train.py:842] (3/4) Epoch 34, batch 8600, loss[loss=0.136, simple_loss=0.2287, pruned_loss=0.02165, over 7239.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2639, pruned_loss=0.04313, over 1419892.37 frames.], batch size: 16, lr: 1.61e-04
2022-05-29 09:11:45,256 INFO [train.py:842] (3/4) Epoch 34, batch 8650, loss[loss=0.1559, simple_loss=0.239, pruned_loss=0.03647, over 7270.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2636, pruned_loss=0.04297, over 1416890.19 frames.], batch size: 18, lr: 1.61e-04
2022-05-29 09:12:27,540 INFO [train.py:842] (3/4) Epoch 34, batch 8700, loss[loss=0.1693, simple_loss=0.2596, pruned_loss=0.03948, over 7172.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2639, pruned_loss=0.043, over 1414114.89 frames.], batch size: 26, lr: 1.61e-04
2022-05-29 09:13:06,630 INFO [train.py:842] (3/4) Epoch 34, batch 8750, loss[loss=0.1623, simple_loss=0.2565, pruned_loss=0.03402, over 7324.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2644, pruned_loss=0.04332, over 1413984.76 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 09:13:45,939 INFO [train.py:842] (3/4) Epoch 34, batch 8800, loss[loss=0.2014, simple_loss=0.2955, pruned_loss=0.05366, over 7329.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2644, pruned_loss=0.0432, over 1407024.67 frames.], batch size: 20, lr: 1.61e-04
2022-05-29 09:14:24,647 INFO [train.py:842] (3/4) Epoch 34, batch 8850, loss[loss=0.1512, simple_loss=0.2479, pruned_loss=0.02725, over 7422.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2644, pruned_loss=0.0432, over 1406315.46 frames.], batch size: 21, lr: 1.61e-04
2022-05-29 09:15:04,298 INFO [train.py:842] (3/4) Epoch 34, batch 8900, loss[loss=0.1758, simple_loss=0.2653, pruned_loss=0.04313, over 6757.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2651, pruned_loss=0.04361, over 1407183.06 frames.], batch size: 31, lr: 1.61e-04
2022-05-29 09:15:43,404 INFO [train.py:842] (3/4) Epoch 34, batch 8950, loss[loss=0.1387, simple_loss=0.2267, pruned_loss=0.02529, over 7155.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2637, pruned_loss=0.04285, over 1407609.91 frames.], batch size: 19, lr: 1.61e-04
2022-05-29 09:16:22,300 INFO [train.py:842] (3/4) Epoch 34, batch 9000, loss[loss=0.1555, simple_loss=0.243, pruned_loss=0.03406, over 7189.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2652, pruned_loss=0.04376, over 1396918.60 frames.], batch size: 22, lr: 1.61e-04
2022-05-29 09:16:22,301 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 09:16:31,957 INFO [train.py:871] (3/4) Epoch 34, validation: loss=0.1642, simple_loss=0.2613, pruned_loss=0.03353, over 868885.00 frames.
2022-05-29 09:17:10,344 INFO [train.py:842] (3/4) Epoch 34, batch 9050, loss[loss=0.1639, simple_loss=0.2597, pruned_loss=0.03402, over 6518.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2667, pruned_loss=0.04477, over 1376550.14 frames.], batch size: 38, lr: 1.61e-04
2022-05-29 09:17:48,525 INFO [train.py:842] (3/4) Epoch 34, batch 9100, loss[loss=0.2129, simple_loss=0.2997, pruned_loss=0.06307, over 6526.00 frames.], tot_loss[loss=0.18, simple_loss=0.2688, pruned_loss=0.04565, over 1338663.17 frames.], batch size: 38, lr: 1.61e-04
2022-05-29 09:18:26,618 INFO [train.py:842] (3/4) Epoch 34, batch 9150, loss[loss=0.2359, simple_loss=0.3124, pruned_loss=0.07968, over 4947.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2717, pruned_loss=0.04806, over 1273597.77 frames.], batch size: 52, lr: 1.60e-04
2022-05-29 09:19:15,513 INFO [train.py:842] (3/4) Epoch 35, batch 0, loss[loss=0.1843, simple_loss=0.2768, pruned_loss=0.04592, over 7229.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2768, pruned_loss=0.04592, over 7229.00 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:19:54,664 INFO [train.py:842] (3/4) Epoch 35, batch 50, loss[loss=0.1895, simple_loss=0.2809, pruned_loss=0.04909, over 7289.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2666, pruned_loss=0.04344, over 318548.78 frames.], batch size: 24, lr: 1.58e-04
2022-05-29 09:20:34,666 INFO [train.py:842] (3/4) Epoch 35, batch 100, loss[loss=0.1742, simple_loss=0.2783, pruned_loss=0.035, over 7181.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2617, pruned_loss=0.04053, over 568239.81 frames.], batch size: 26, lr: 1.58e-04
2022-05-29 09:21:14,023 INFO [train.py:842] (3/4) Epoch 35, batch 150, loss[loss=0.2058, simple_loss=0.289, pruned_loss=0.06125, over 7385.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2628, pruned_loss=0.04093, over 760589.61 frames.], batch size: 23, lr: 1.58e-04
2022-05-29 09:21:53,708 INFO [train.py:842] (3/4) Epoch 35, batch 200, loss[loss=0.1651, simple_loss=0.2539, pruned_loss=0.03818, over 7463.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2617, pruned_loss=0.04097, over 909637.06 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:22:33,040 INFO [train.py:842] (3/4) Epoch 35, batch 250, loss[loss=0.1621, simple_loss=0.2589, pruned_loss=0.03267, over 7235.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2602, pruned_loss=0.04054, over 1027567.08 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:23:12,685 INFO [train.py:842] (3/4) Epoch 35, batch 300, loss[loss=0.1536, simple_loss=0.2406, pruned_loss=0.03332, over 7158.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2598, pruned_loss=0.04023, over 1113865.76 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:23:51,962 INFO [train.py:842] (3/4) Epoch 35, batch 350, loss[loss=0.2004, simple_loss=0.2859, pruned_loss=0.05749, over 7197.00 frames.], tot_loss[loss=0.1698, simple_loss=0.259, pruned_loss=0.04028, over 1185869.58 frames.], batch size: 23, lr: 1.58e-04
2022-05-29 09:24:31,411 INFO [train.py:842] (3/4) Epoch 35, batch 400, loss[loss=0.1507, simple_loss=0.2435, pruned_loss=0.02899, over 7335.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2593, pruned_loss=0.04057, over 1240364.54 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:25:10,946 INFO [train.py:842] (3/4) Epoch 35, batch 450, loss[loss=0.1603, simple_loss=0.2524, pruned_loss=0.03412, over 6833.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2593, pruned_loss=0.04049, over 1285941.02 frames.], batch size: 31, lr: 1.58e-04
2022-05-29 09:25:50,491 INFO [train.py:842] (3/4) Epoch 35, batch 500, loss[loss=0.2348, simple_loss=0.3024, pruned_loss=0.08362, over 7317.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2606, pruned_loss=0.04129, over 1315079.03 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:26:29,933 INFO [train.py:842] (3/4) Epoch 35, batch 550, loss[loss=0.166, simple_loss=0.2493, pruned_loss=0.04136, over 7060.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2597, pruned_loss=0.04075, over 1335873.33 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:27:09,491 INFO [train.py:842] (3/4) Epoch 35, batch 600, loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03503, over 7344.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2603, pruned_loss=0.04088, over 1355119.05 frames.], batch size: 22, lr: 1.58e-04
2022-05-29 09:27:48,652 INFO [train.py:842] (3/4) Epoch 35, batch 650, loss[loss=0.1511, simple_loss=0.2328, pruned_loss=0.03469, over 7154.00 frames.], tot_loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.04131, over 1373930.78 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:28:28,628 INFO [train.py:842] (3/4) Epoch 35, batch 700, loss[loss=0.1709, simple_loss=0.2498, pruned_loss=0.04596, over 7268.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2602, pruned_loss=0.04057, over 1387716.94 frames.], batch size: 17, lr: 1.58e-04
2022-05-29 09:29:08,066 INFO [train.py:842] (3/4) Epoch 35, batch 750, loss[loss=0.1581, simple_loss=0.25, pruned_loss=0.03312, over 7257.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2595, pruned_loss=0.04016, over 1394408.96 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:29:47,606 INFO [train.py:842] (3/4) Epoch 35, batch 800, loss[loss=0.1995, simple_loss=0.2975, pruned_loss=0.05079, over 7221.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2603, pruned_loss=0.04029, over 1402454.09 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:30:26,764 INFO [train.py:842] (3/4) Epoch 35, batch 850, loss[loss=0.1735, simple_loss=0.276, pruned_loss=0.03553, over 7306.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2615, pruned_loss=0.04091, over 1403046.26 frames.], batch size: 24, lr: 1.58e-04
2022-05-29 09:31:06,382 INFO [train.py:842] (3/4) Epoch 35, batch 900, loss[loss=0.1939, simple_loss=0.2782, pruned_loss=0.05481, over 5115.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04088, over 1406116.29 frames.], batch size: 53, lr: 1.58e-04
2022-05-29 09:31:45,712 INFO [train.py:842] (3/4) Epoch 35, batch 950, loss[loss=0.1621, simple_loss=0.2514, pruned_loss=0.03642, over 7248.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2599, pruned_loss=0.04087, over 1409558.34 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:32:25,395 INFO [train.py:842] (3/4) Epoch 35, batch 1000, loss[loss=0.1837, simple_loss=0.2706, pruned_loss=0.04842, over 6773.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2584, pruned_loss=0.03996, over 1411688.78 frames.], batch size: 31, lr: 1.58e-04
2022-05-29 09:33:04,764 INFO [train.py:842] (3/4) Epoch 35, batch 1050, loss[loss=0.1761, simple_loss=0.2663, pruned_loss=0.04298, over 7411.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2582, pruned_loss=0.03995, over 1416337.15 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:33:44,559 INFO [train.py:842] (3/4) Epoch 35, batch 1100, loss[loss=0.1647, simple_loss=0.2608, pruned_loss=0.03431, over 7360.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2576, pruned_loss=0.03937, over 1420460.36 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:34:23,691 INFO [train.py:842] (3/4) Epoch 35, batch 1150, loss[loss=0.1828, simple_loss=0.2817, pruned_loss=0.04193, over 7211.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2594, pruned_loss=0.0402, over 1422110.62 frames.], batch size: 23, lr: 1.58e-04
2022-05-29 09:35:03,465 INFO [train.py:842] (3/4) Epoch 35, batch 1200, loss[loss=0.1424, simple_loss=0.2284, pruned_loss=0.0282, over 7289.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2592, pruned_loss=0.03966, over 1425712.40 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:35:42,629 INFO [train.py:842] (3/4) Epoch 35, batch 1250, loss[loss=0.1926, simple_loss=0.2816, pruned_loss=0.05181, over 7343.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2599, pruned_loss=0.04056, over 1424505.63 frames.], batch size: 22, lr: 1.58e-04
2022-05-29 09:36:21,922 INFO [train.py:842] (3/4) Epoch 35, batch 1300, loss[loss=0.2044, simple_loss=0.2907, pruned_loss=0.05906, over 7147.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2606, pruned_loss=0.04103, over 1420785.51 frames.], batch size: 28, lr: 1.58e-04
2022-05-29 09:37:00,979 INFO [train.py:842] (3/4) Epoch 35, batch 1350, loss[loss=0.2223, simple_loss=0.3101, pruned_loss=0.0673, over 6999.00 frames.], tot_loss[loss=0.172, simple_loss=0.2612, pruned_loss=0.04138, over 1423427.54 frames.], batch size: 28, lr: 1.58e-04
2022-05-29 09:37:40,280 INFO [train.py:842] (3/4) Epoch 35, batch 1400, loss[loss=0.1567, simple_loss=0.2443, pruned_loss=0.0345, over 7332.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2623, pruned_loss=0.04173, over 1421210.84 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:38:19,788 INFO [train.py:842] (3/4) Epoch 35, batch 1450, loss[loss=0.1581, simple_loss=0.2487, pruned_loss=0.03372, over 7260.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2611, pruned_loss=0.04128, over 1418955.43 frames.], batch size: 19, lr: 1.58e-04
2022-05-29 09:38:59,587 INFO [train.py:842] (3/4) Epoch 35, batch 1500, loss[loss=0.1869, simple_loss=0.2717, pruned_loss=0.05101, over 7122.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2625, pruned_loss=0.04207, over 1419952.45 frames.], batch size: 17, lr: 1.58e-04
2022-05-29 09:39:38,708 INFO [train.py:842] (3/4) Epoch 35, batch 1550, loss[loss=0.1854, simple_loss=0.2846, pruned_loss=0.04316, over 7216.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2638, pruned_loss=0.04265, over 1420259.16 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:40:18,432 INFO [train.py:842] (3/4) Epoch 35, batch 1600, loss[loss=0.1512, simple_loss=0.2343, pruned_loss=0.03405, over 7092.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2626, pruned_loss=0.04216, over 1422179.53 frames.], batch size: 28, lr: 1.58e-04
2022-05-29 09:40:57,764 INFO [train.py:842] (3/4) Epoch 35, batch 1650, loss[loss=0.1732, simple_loss=0.2511, pruned_loss=0.04766, over 7411.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04214, over 1426534.17 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:41:48,206 INFO [train.py:842] (3/4) Epoch 35, batch 1700, loss[loss=0.299, simple_loss=0.3652, pruned_loss=0.1164, over 4904.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2624, pruned_loss=0.04253, over 1425480.89 frames.], batch size: 52, lr: 1.58e-04
2022-05-29 09:42:27,689 INFO [train.py:842] (3/4) Epoch 35, batch 1750, loss[loss=0.1463, simple_loss=0.2364, pruned_loss=0.02815, over 7155.00 frames.], tot_loss[loss=0.173, simple_loss=0.2613, pruned_loss=0.04231, over 1425266.57 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:43:07,480 INFO [train.py:842] (3/4) Epoch 35, batch 1800, loss[loss=0.1921, simple_loss=0.2787, pruned_loss=0.05278, over 7264.00 frames.], tot_loss[loss=0.1723, simple_loss=0.261, pruned_loss=0.0418, over 1429535.47 frames.], batch size: 25, lr: 1.58e-04
2022-05-29 09:43:46,600 INFO [train.py:842] (3/4) Epoch 35, batch 1850, loss[loss=0.1469, simple_loss=0.2339, pruned_loss=0.02999, over 7057.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2614, pruned_loss=0.04182, over 1425604.94 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:44:26,183 INFO [train.py:842] (3/4) Epoch 35, batch 1900, loss[loss=0.1773, simple_loss=0.269, pruned_loss=0.04284, over 7377.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04196, over 1425010.03 frames.], batch size: 23, lr: 1.58e-04
2022-05-29 09:45:05,565 INFO [train.py:842] (3/4) Epoch 35, batch 1950, loss[loss=0.1421, simple_loss=0.2283, pruned_loss=0.02792, over 7163.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2623, pruned_loss=0.0427, over 1423985.84 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:45:55,997 INFO [train.py:842] (3/4) Epoch 35, batch 2000, loss[loss=0.1858, simple_loss=0.275, pruned_loss=0.04826, over 6543.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2623, pruned_loss=0.04264, over 1419964.23 frames.], batch size: 38, lr: 1.58e-04
2022-05-29 09:46:35,136 INFO [train.py:842] (3/4) Epoch 35, batch 2050, loss[loss=0.2189, simple_loss=0.3133, pruned_loss=0.06219, over 7111.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2631, pruned_loss=0.043, over 1421252.71 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:47:25,681 INFO [train.py:842] (3/4) Epoch 35, batch 2100, loss[loss=0.1596, simple_loss=0.2537, pruned_loss=0.03279, over 7411.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2638, pruned_loss=0.04268, over 1423450.87 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:48:05,107 INFO [train.py:842] (3/4) Epoch 35, batch 2150, loss[loss=0.1682, simple_loss=0.263, pruned_loss=0.03671, over 6461.00 frames.], tot_loss[loss=0.1751, simple_loss=0.264, pruned_loss=0.0431, over 1427128.14 frames.], batch size: 38, lr: 1.58e-04
2022-05-29 09:48:44,614 INFO [train.py:842] (3/4) Epoch 35, batch 2200, loss[loss=0.1587, simple_loss=0.2519, pruned_loss=0.03278, over 7426.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2636, pruned_loss=0.04277, over 1423872.24 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:49:23,729 INFO [train.py:842] (3/4) Epoch 35, batch 2250, loss[loss=0.1846, simple_loss=0.26, pruned_loss=0.05455, over 7273.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2629, pruned_loss=0.04215, over 1421250.33 frames.], batch size: 18, lr: 1.58e-04
2022-05-29 09:50:03,234 INFO [train.py:842] (3/4) Epoch 35, batch 2300, loss[loss=0.1942, simple_loss=0.2809, pruned_loss=0.05379, over 7203.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2619, pruned_loss=0.04196, over 1418515.83 frames.], batch size: 26, lr: 1.58e-04
2022-05-29 09:50:42,252 INFO [train.py:842] (3/4) Epoch 35, batch 2350, loss[loss=0.1762, simple_loss=0.2851, pruned_loss=0.03364, over 7092.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2626, pruned_loss=0.04238, over 1416878.24 frames.], batch size: 28, lr: 1.58e-04
2022-05-29 09:51:21,884 INFO [train.py:842] (3/4) Epoch 35, batch 2400, loss[loss=0.1604, simple_loss=0.2415, pruned_loss=0.03968, over 6999.00 frames.], tot_loss[loss=0.173, simple_loss=0.262, pruned_loss=0.04197, over 1421718.47 frames.], batch size: 16, lr: 1.58e-04
2022-05-29 09:52:01,218 INFO [train.py:842] (3/4) Epoch 35, batch 2450, loss[loss=0.1492, simple_loss=0.2474, pruned_loss=0.02552, over 7432.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2601, pruned_loss=0.04107, over 1421542.70 frames.], batch size: 20, lr: 1.58e-04
2022-05-29 09:52:41,079 INFO [train.py:842] (3/4) Epoch 35, batch 2500, loss[loss=0.1816, simple_loss=0.2739, pruned_loss=0.04461, over 6212.00 frames.], tot_loss[loss=0.1713, simple_loss=0.26, pruned_loss=0.04133, over 1422873.50 frames.], batch size: 37, lr: 1.58e-04
2022-05-29 09:53:20,280 INFO [train.py:842] (3/4) Epoch 35, batch 2550, loss[loss=0.1631, simple_loss=0.2591, pruned_loss=0.03349, over 7123.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2599, pruned_loss=0.04146, over 1423940.98 frames.], batch size: 21, lr: 1.58e-04
2022-05-29 09:53:59,857 INFO [train.py:842] (3/4) Epoch 35, batch 2600, loss[loss=0.1726, simple_loss=0.2638, pruned_loss=0.04074, over 7205.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04138, over 1422643.66 frames.], batch size: 22, lr: 1.58e-04
2022-05-29 09:54:38,860 INFO [train.py:842] (3/4) Epoch 35, batch 2650, loss[loss=0.1845, simple_loss=0.2759, pruned_loss=0.04657, over 7203.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2602, pruned_loss=0.04121, over 1421124.70 frames.], batch size: 23, lr: 1.58e-04
2022-05-29 09:55:18,679 INFO [train.py:842] (3/4) Epoch 35, batch 2700, loss[loss=0.1801, simple_loss=0.2796, pruned_loss=0.04028, over 7117.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2609, pruned_loss=0.04115, over 1422529.38 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 09:55:57,889 INFO [train.py:842] (3/4) Epoch 35, batch 2750, loss[loss=0.184, simple_loss=0.2799, pruned_loss=0.04403, over 7314.00 frames.], tot_loss[loss=0.171, simple_loss=0.2604, pruned_loss=0.04077, over 1422751.88 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 09:56:37,373 INFO [train.py:842] (3/4) Epoch 35, batch 2800, loss[loss=0.1712, simple_loss=0.2625, pruned_loss=0.03991, over 7328.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2599, pruned_loss=0.04017, over 1424727.71 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 09:57:16,506 INFO [train.py:842] (3/4) Epoch 35, batch 2850, loss[loss=0.1554, simple_loss=0.2473, pruned_loss=0.03171, over 7161.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2613, pruned_loss=0.04107, over 1423004.79 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 09:57:56,052 INFO [train.py:842] (3/4) Epoch 35, batch 2900, loss[loss=0.1801, simple_loss=0.2835, pruned_loss=0.03833, over 6144.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.04103, over 1422609.49 frames.], batch size: 37, lr: 1.57e-04
2022-05-29 09:58:34,907 INFO [train.py:842] (3/4) Epoch 35, batch 2950, loss[loss=0.155, simple_loss=0.2394, pruned_loss=0.03526, over 6778.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2621, pruned_loss=0.04151, over 1415782.70 frames.], batch size: 15, lr: 1.57e-04
2022-05-29 09:59:14,511 INFO [train.py:842] (3/4) Epoch 35, batch 3000, loss[loss=0.1871, simple_loss=0.276, pruned_loss=0.04908, over 7370.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2611, pruned_loss=0.04127, over 1420140.21 frames.], batch size: 23, lr: 1.57e-04
2022-05-29 09:59:14,512 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 09:59:24,201 INFO [train.py:871] (3/4) Epoch 35, validation: loss=0.1643, simple_loss=0.2608, pruned_loss=0.03387, over 868885.00 frames.
2022-05-29 10:00:03,537 INFO [train.py:842] (3/4) Epoch 35, batch 3050, loss[loss=0.1747, simple_loss=0.269, pruned_loss=0.04027, over 7242.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2615, pruned_loss=0.04107, over 1423443.22 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:00:43,001 INFO [train.py:842] (3/4) Epoch 35, batch 3100, loss[loss=0.2448, simple_loss=0.3265, pruned_loss=0.08158, over 7381.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2626, pruned_loss=0.04178, over 1420592.63 frames.], batch size: 23, lr: 1.57e-04
2022-05-29 10:01:22,496 INFO [train.py:842] (3/4) Epoch 35, batch 3150, loss[loss=0.1824, simple_loss=0.2757, pruned_loss=0.04461, over 7200.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2602, pruned_loss=0.04076, over 1422887.01 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:02:01,992 INFO [train.py:842] (3/4) Epoch 35, batch 3200, loss[loss=0.1816, simple_loss=0.2657, pruned_loss=0.04876, over 7196.00 frames.], tot_loss[loss=0.1712, simple_loss=0.261, pruned_loss=0.04073, over 1427722.57 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:02:41,284 INFO [train.py:842] (3/4) Epoch 35, batch 3250, loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03067, over 7432.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04092, over 1426021.58 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:03:20,911 INFO [train.py:842] (3/4) Epoch 35, batch 3300, loss[loss=0.145, simple_loss=0.2315, pruned_loss=0.0293, over 7435.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2609, pruned_loss=0.04068, over 1426352.34 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:04:00,229 INFO [train.py:842] (3/4) Epoch 35, batch 3350, loss[loss=0.1905, simple_loss=0.2783, pruned_loss=0.05132, over 7435.00 frames.], tot_loss[loss=0.1713, simple_loss=0.261, pruned_loss=0.04077, over 1429231.67 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:04:39,792 INFO [train.py:842] (3/4) Epoch 35, batch 3400, loss[loss=0.1727, simple_loss=0.254, pruned_loss=0.0457, over 7281.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2601, pruned_loss=0.0403, over 1425528.68 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:05:18,853 INFO [train.py:842] (3/4) Epoch 35, batch 3450, loss[loss=0.1545, simple_loss=0.2419, pruned_loss=0.03353, over 6998.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04087, over 1428560.99 frames.], batch size: 16, lr: 1.57e-04
2022-05-29 10:05:58,345 INFO [train.py:842] (3/4) Epoch 35, batch 3500, loss[loss=0.17, simple_loss=0.2743, pruned_loss=0.03285, over 7329.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2608, pruned_loss=0.04078, over 1427613.52 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:06:37,436 INFO [train.py:842] (3/4) Epoch 35, batch 3550, loss[loss=0.1604, simple_loss=0.2618, pruned_loss=0.02954, over 6962.00 frames.], tot_loss[loss=0.172, simple_loss=0.2615, pruned_loss=0.04127, over 1421355.45 frames.], batch size: 32, lr: 1.57e-04
2022-05-29 10:07:17,147 INFO [train.py:842] (3/4) Epoch 35, batch 3600, loss[loss=0.2067, simple_loss=0.2888, pruned_loss=0.06225, over 7198.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2617, pruned_loss=0.04157, over 1420228.03 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:07:56,177 INFO [train.py:842] (3/4) Epoch 35, batch 3650, loss[loss=0.2049, simple_loss=0.2903, pruned_loss=0.05978, over 7282.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.041, over 1420996.73 frames.], batch size: 25, lr: 1.57e-04
2022-05-29 10:08:35,627 INFO [train.py:842] (3/4) Epoch 35, batch 3700, loss[loss=0.1832, simple_loss=0.2745, pruned_loss=0.04598, over 6276.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2612, pruned_loss=0.0412, over 1420739.86 frames.], batch size: 37, lr: 1.57e-04
2022-05-29 10:09:14,949 INFO [train.py:842] (3/4) Epoch 35, batch 3750, loss[loss=0.1898, simple_loss=0.2771, pruned_loss=0.05122, over 4930.00 frames.], tot_loss[loss=0.1726, simple_loss=0.262, pruned_loss=0.04156, over 1418327.72 frames.], batch size: 55, lr: 1.57e-04
2022-05-29 10:09:54,405 INFO [train.py:842] (3/4) Epoch 35, batch 3800, loss[loss=0.1814, simple_loss=0.2694, pruned_loss=0.04672, over 5160.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2631, pruned_loss=0.04195, over 1418823.19 frames.], batch size: 53, lr: 1.57e-04
2022-05-29 10:10:33,436 INFO [train.py:842] (3/4) Epoch 35, batch 3850, loss[loss=0.2041, simple_loss=0.2696, pruned_loss=0.06933, over 6991.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2638, pruned_loss=0.04242, over 1420509.49 frames.], batch size: 16, lr: 1.57e-04
2022-05-29 10:11:12,941 INFO [train.py:842] (3/4) Epoch 35, batch 3900, loss[loss=0.1693, simple_loss=0.2426, pruned_loss=0.04795, over 7274.00 frames.], tot_loss[loss=0.174, simple_loss=0.2634, pruned_loss=0.0423, over 1417388.27 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:11:52,227 INFO [train.py:842] (3/4) Epoch 35, batch 3950, loss[loss=0.192, simple_loss=0.2739, pruned_loss=0.05506, over 7149.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.04212, over 1416292.83 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:12:31,911 INFO [train.py:842] (3/4) Epoch 35, batch 4000, loss[loss=0.1909, simple_loss=0.2879, pruned_loss=0.04694, over 7232.00 frames.], tot_loss[loss=0.173, simple_loss=0.2625, pruned_loss=0.04174, over 1417726.08 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:13:11,436 INFO [train.py:842] (3/4) Epoch 35, batch 4050, loss[loss=0.1804, simple_loss=0.2751, pruned_loss=0.0428, over 7208.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2625, pruned_loss=0.04199, over 1421124.42 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:13:50,834 INFO [train.py:842] (3/4) Epoch 35, batch 4100, loss[loss=0.2, simple_loss=0.2801, pruned_loss=0.05993, over 6786.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2621, pruned_loss=0.04158, over 1423906.31 frames.], batch size: 31, lr: 1.57e-04
2022-05-29 10:14:30,165 INFO [train.py:842] (3/4) Epoch 35, batch 4150, loss[loss=0.1322, simple_loss=0.2136, pruned_loss=0.0254, over 7273.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04121, over 1428019.95 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:15:09,592 INFO [train.py:842] (3/4) Epoch 35, batch 4200, loss[loss=0.1808, simple_loss=0.2719, pruned_loss=0.04489, over 7434.00 frames.], tot_loss[loss=0.1707, simple_loss=0.26, pruned_loss=0.04065, over 1424549.97 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:15:48,852 INFO [train.py:842] (3/4) Epoch 35, batch 4250, loss[loss=0.1695, simple_loss=0.2473, pruned_loss=0.04585, over 7153.00 frames.], tot_loss[loss=0.171, simple_loss=0.2602, pruned_loss=0.04086, over 1425962.99 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:16:28,519 INFO [train.py:842] (3/4) Epoch 35, batch 4300, loss[loss=0.1551, simple_loss=0.2337, pruned_loss=0.03828, over 7140.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2605, pruned_loss=0.04162, over 1429142.51 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:17:07,788 INFO [train.py:842] (3/4) Epoch 35, batch 4350, loss[loss=0.1642, simple_loss=0.2593, pruned_loss=0.03453, over 7318.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04193, over 1432333.39 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 10:17:47,278 INFO [train.py:842] (3/4) Epoch 35, batch 4400, loss[loss=0.1957, simple_loss=0.2901, pruned_loss=0.05069, over 7218.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2619, pruned_loss=0.04214, over 1424363.97 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:18:26,590 INFO [train.py:842] (3/4) Epoch 35, batch 4450, loss[loss=0.1854, simple_loss=0.278, pruned_loss=0.04644, over 7281.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2608, pruned_loss=0.0419, over 1421731.37 frames.], batch size: 24, lr: 1.57e-04
2022-05-29 10:19:06,147 INFO [train.py:842] (3/4) Epoch 35, batch 4500, loss[loss=0.1588, simple_loss=0.2329, pruned_loss=0.04234, over 6843.00 frames.], tot_loss[loss=0.172, simple_loss=0.2605, pruned_loss=0.0417, over 1421078.13 frames.], batch size: 15, lr: 1.57e-04
2022-05-29 10:19:45,374 INFO [train.py:842] (3/4) Epoch 35, batch 4550, loss[loss=0.1852, simple_loss=0.2802, pruned_loss=0.04516, over 7208.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2606, pruned_loss=0.04189, over 1419100.94 frames.], batch size: 23, lr: 1.57e-04
2022-05-29 10:20:25,314 INFO [train.py:842] (3/4) Epoch 35, batch 4600, loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02956, over 7144.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2594, pruned_loss=0.04105, over 1420157.74 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:21:04,529 INFO [train.py:842] (3/4) Epoch 35, batch 4650, loss[loss=0.1665, simple_loss=0.2482, pruned_loss=0.04236, over 7239.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2592, pruned_loss=0.04113, over 1417829.89 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:21:44,084 INFO [train.py:842] (3/4) Epoch 35, batch 4700, loss[loss=0.1584, simple_loss=0.2575, pruned_loss=0.02968, over 7234.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2594, pruned_loss=0.04106, over 1419052.54 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 10:22:23,131 INFO [train.py:842] (3/4) Epoch 35, batch 4750, loss[loss=0.1909, simple_loss=0.28, pruned_loss=0.05087, over 7197.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2602, pruned_loss=0.04142, over 1419430.81 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:23:02,779 INFO [train.py:842] (3/4) Epoch 35, batch 4800, loss[loss=0.1633, simple_loss=0.2491, pruned_loss=0.03873, over 7259.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2597, pruned_loss=0.04091, over 1425835.87 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:23:42,030 INFO [train.py:842] (3/4) Epoch 35, batch 4850, loss[loss=0.2392, simple_loss=0.3223, pruned_loss=0.07808, over 4839.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2605, pruned_loss=0.04107, over 1423609.02 frames.], batch size: 52, lr: 1.57e-04
2022-05-29 10:24:21,738 INFO [train.py:842] (3/4) Epoch 35, batch 4900, loss[loss=0.1747, simple_loss=0.2533, pruned_loss=0.04804, over 7277.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2604, pruned_loss=0.04131, over 1424506.11 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:25:01,014 INFO [train.py:842] (3/4) Epoch 35, batch 4950, loss[loss=0.1637, simple_loss=0.2489, pruned_loss=0.03927, over 7437.00 frames.], tot_loss[loss=0.1711, simple_loss=0.26, pruned_loss=0.04111, over 1427943.52 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:25:40,538 INFO [train.py:842] (3/4) Epoch 35, batch 5000, loss[loss=0.1995, simple_loss=0.2971, pruned_loss=0.05095, over 7218.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04123, over 1427822.76 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 10:26:19,937 INFO [train.py:842] (3/4) Epoch 35, batch 5050, loss[loss=0.1896, simple_loss=0.2779, pruned_loss=0.05069, over 7157.00 frames.], tot_loss[loss=0.1719, simple_loss=0.261, pruned_loss=0.04142, over 1431162.46 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:26:59,255 INFO [train.py:842] (3/4) Epoch 35, batch 5100, loss[loss=0.1656, simple_loss=0.2432, pruned_loss=0.04403, over 7283.00 frames.], tot_loss[loss=0.172, simple_loss=0.2618, pruned_loss=0.0411, over 1427741.87 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:27:38,602 INFO [train.py:842] (3/4) Epoch 35, batch 5150, loss[loss=0.1859, simple_loss=0.2788, pruned_loss=0.04653, over 7311.00 frames.], tot_loss[loss=0.1733, simple_loss=0.263, pruned_loss=0.04183, over 1427456.63 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 10:28:18,459 INFO [train.py:842] (3/4) Epoch 35, batch 5200, loss[loss=0.1361, simple_loss=0.212, pruned_loss=0.0301, over 6792.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2621, pruned_loss=0.04173, over 1428701.42 frames.], batch size: 15, lr: 1.57e-04
2022-05-29 10:28:57,720 INFO [train.py:842] (3/4) Epoch 35, batch 5250, loss[loss=0.1637, simple_loss=0.2463, pruned_loss=0.04048, over 7362.00 frames.], tot_loss[loss=0.171, simple_loss=0.2605, pruned_loss=0.04079, over 1429235.14 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:29:37,084 INFO [train.py:842] (3/4) Epoch 35, batch 5300, loss[loss=0.1751, simple_loss=0.2666, pruned_loss=0.04184, over 7315.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04057, over 1428649.28 frames.], batch size: 24, lr: 1.57e-04
2022-05-29 10:30:16,498 INFO [train.py:842] (3/4) Epoch 35, batch 5350, loss[loss=0.194, simple_loss=0.2853, pruned_loss=0.05132, over 7323.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2596, pruned_loss=0.04039, over 1427405.91 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:30:56,250 INFO [train.py:842] (3/4) Epoch 35, batch 5400, loss[loss=0.1705, simple_loss=0.2603, pruned_loss=0.04036, over 7339.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2611, pruned_loss=0.04125, over 1431952.19 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:31:35,712 INFO [train.py:842] (3/4) Epoch 35, batch 5450, loss[loss=0.1868, simple_loss=0.2674, pruned_loss=0.05309, over 7158.00 frames.], tot_loss[loss=0.171, simple_loss=0.26, pruned_loss=0.04095, over 1433381.65 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:32:14,949 INFO [train.py:842] (3/4) Epoch 35, batch 5500, loss[loss=0.1553, simple_loss=0.2489, pruned_loss=0.03085, over 7146.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2605, pruned_loss=0.04101, over 1428346.44 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:32:54,344 INFO [train.py:842] (3/4) Epoch 35, batch 5550, loss[loss=0.1505, simple_loss=0.2281, pruned_loss=0.03645, over 7275.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04177, over 1426533.51 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:33:33,914 INFO [train.py:842] (3/4) Epoch 35, batch 5600, loss[loss=0.2321, simple_loss=0.3032, pruned_loss=0.08051, over 7231.00 frames.], tot_loss[loss=0.172, simple_loss=0.2605, pruned_loss=0.04172, over 1425327.99 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:34:13,258 INFO [train.py:842] (3/4) Epoch 35, batch 5650, loss[loss=0.1434, simple_loss=0.24, pruned_loss=0.02337, over 7160.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2614, pruned_loss=0.04208, over 1427072.32 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:34:52,904 INFO [train.py:842] (3/4) Epoch 35, batch 5700, loss[loss=0.1511, simple_loss=0.2442, pruned_loss=0.029, over 7293.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2607, pruned_loss=0.04143, over 1429481.06 frames.], batch size: 24, lr: 1.57e-04
2022-05-29 10:35:32,113 INFO [train.py:842] (3/4) Epoch 35, batch 5750, loss[loss=0.2087, simple_loss=0.3016, pruned_loss=0.05793, over 6663.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2613, pruned_loss=0.04156, over 1432278.35 frames.], batch size: 31, lr: 1.57e-04
2022-05-29 10:36:11,768 INFO [train.py:842] (3/4) Epoch 35, batch 5800, loss[loss=0.1668, simple_loss=0.264, pruned_loss=0.03482, over 7241.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2606, pruned_loss=0.04117, over 1430279.34 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:36:51,164 INFO [train.py:842] (3/4) Epoch 35, batch 5850, loss[loss=0.2374, simple_loss=0.3257, pruned_loss=0.07458, over 7003.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04097, over 1429475.13 frames.], batch size: 28, lr: 1.57e-04
2022-05-29 10:37:30,760 INFO [train.py:842] (3/4) Epoch 35, batch 5900, loss[loss=0.2112, simple_loss=0.3015, pruned_loss=0.0605, over 7177.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2608, pruned_loss=0.04134, over 1428569.69 frames.], batch size: 23, lr: 1.57e-04
2022-05-29 10:38:10,027 INFO [train.py:842] (3/4) Epoch 35, batch 5950, loss[loss=0.1418, simple_loss=0.2261, pruned_loss=0.02871, over 7259.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2604, pruned_loss=0.04137, over 1428139.04 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:38:49,679 INFO [train.py:842] (3/4) Epoch 35, batch 6000, loss[loss=0.1727, simple_loss=0.2685, pruned_loss=0.03842, over 7328.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2599, pruned_loss=0.0412, over 1430703.67 frames.], batch size: 22, lr: 1.57e-04
2022-05-29 10:38:49,681 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 10:38:59,233 INFO [train.py:871] (3/4) Epoch 35, validation: loss=0.1626, simple_loss=0.2599, pruned_loss=0.03269, over 868885.00 frames.
2022-05-29 10:39:38,652 INFO [train.py:842] (3/4) Epoch 35, batch 6050, loss[loss=0.1908, simple_loss=0.2736, pruned_loss=0.05398, over 6990.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2596, pruned_loss=0.04089, over 1429873.10 frames.], batch size: 16, lr: 1.57e-04
2022-05-29 10:40:18,136 INFO [train.py:842] (3/4) Epoch 35, batch 6100, loss[loss=0.1415, simple_loss=0.2259, pruned_loss=0.02856, over 6987.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2606, pruned_loss=0.0412, over 1423749.41 frames.], batch size: 16, lr: 1.57e-04
2022-05-29 10:40:57,378 INFO [train.py:842] (3/4) Epoch 35, batch 6150, loss[loss=0.1682, simple_loss=0.2614, pruned_loss=0.03749, over 7059.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2611, pruned_loss=0.04118, over 1421983.28 frames.], batch size: 28, lr: 1.57e-04
2022-05-29 10:41:36,732 INFO [train.py:842] (3/4) Epoch 35, batch 6200, loss[loss=0.1587, simple_loss=0.2542, pruned_loss=0.03163, over 7234.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2624, pruned_loss=0.0415, over 1425659.93 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:42:16,073 INFO [train.py:842] (3/4) Epoch 35, batch 6250, loss[loss=0.1737, simple_loss=0.2735, pruned_loss=0.03692, over 7411.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2622, pruned_loss=0.04128, over 1429195.13 frames.], batch size: 21, lr: 1.57e-04
2022-05-29 10:42:55,570 INFO [train.py:842] (3/4) Epoch 35, batch 6300, loss[loss=0.1406, simple_loss=0.2229, pruned_loss=0.02913, over 7295.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2619, pruned_loss=0.04159, over 1426869.34 frames.], batch size: 18, lr: 1.57e-04
2022-05-29 10:43:34,627 INFO [train.py:842] (3/4) Epoch 35, batch 6350, loss[loss=0.1838, simple_loss=0.274, pruned_loss=0.04677, over 5075.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2604, pruned_loss=0.04087, over 1426937.57 frames.], batch size: 52, lr: 1.57e-04
2022-05-29 10:44:14,137 INFO [train.py:842] (3/4) Epoch 35, batch 6400, loss[loss=0.1821, simple_loss=0.2634, pruned_loss=0.05043, over 7270.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2606, pruned_loss=0.0408, over 1426651.01 frames.], batch size: 24, lr: 1.57e-04
2022-05-29 10:44:53,496 INFO [train.py:842] (3/4) Epoch 35, batch 6450, loss[loss=0.2, simple_loss=0.2927, pruned_loss=0.05365, over 7144.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2611, pruned_loss=0.04082, over 1427262.25 frames.], batch size: 20, lr: 1.57e-04
2022-05-29 10:45:32,963 INFO [train.py:842] (3/4) Epoch 35, batch 6500, loss[loss=0.1664, simple_loss=0.2618, pruned_loss=0.03549, over 6587.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2611, pruned_loss=0.04087, over 1428318.90 frames.], batch size: 31, lr: 1.57e-04
2022-05-29 10:46:12,229 INFO [train.py:842] (3/4) Epoch 35, batch 6550, loss[loss=0.1765, simple_loss=0.2682, pruned_loss=0.0424, over 7364.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2603, pruned_loss=0.04079, over 1426320.14 frames.], batch size: 19, lr: 1.57e-04
2022-05-29 10:46:51,878 INFO [train.py:842] (3/4) Epoch 35, batch 6600, loss[loss=0.1855, simple_loss=0.2791, pruned_loss=0.04589, over 7009.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2611, pruned_loss=0.04161, over 1418896.19 frames.], batch size: 28, lr: 1.57e-04
2022-05-29 10:47:31,068 INFO [train.py:842] (3/4) Epoch 35, batch 6650, loss[loss=0.1631, simple_loss=0.2476, pruned_loss=0.03929, over 7126.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2622, pruned_loss=0.042, over 1418788.20 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:48:10,538 INFO [train.py:842] (3/4) Epoch 35, batch 6700, loss[loss=0.1492, simple_loss=0.237, pruned_loss=0.03073, over 7275.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.0418, over 1416783.17 frames.], batch size: 17, lr: 1.57e-04
2022-05-29 10:48:49,710 INFO [train.py:842] (3/4) Epoch 35, batch 6750, loss[loss=0.1301, simple_loss=0.2144, pruned_loss=0.02286, over 7130.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2623, pruned_loss=0.04253, over 1412881.33 frames.], batch size: 17, lr: 1.56e-04
2022-05-29 10:49:29,341 INFO [train.py:842] (3/4) Epoch 35, batch 6800, loss[loss=0.1787, simple_loss=0.2744, pruned_loss=0.04154, over 6770.00 frames.], tot_loss[loss=0.172, simple_loss=0.2609, pruned_loss=0.0415, over 1417106.23 frames.], batch size: 31, lr: 1.56e-04
2022-05-29 10:50:08,374 INFO [train.py:842] (3/4) Epoch 35, batch 6850, loss[loss=0.1526, simple_loss=0.234, pruned_loss=0.03554, over 7249.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2616, pruned_loss=0.04154, over 1418863.33 frames.], batch size: 16, lr: 1.56e-04
2022-05-29 10:50:47,899 INFO [train.py:842] (3/4) Epoch 35, batch 6900, loss[loss=0.167, simple_loss=0.2605, pruned_loss=0.03677, over 7229.00 frames.], tot_loss[loss=0.1717, simple_loss=0.261, pruned_loss=0.04116, over 1420531.14 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 10:51:27,294 INFO [train.py:842] (3/4) Epoch 35, batch 6950, loss[loss=0.1814, simple_loss=0.2711, pruned_loss=0.04581, over 7385.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2613, pruned_loss=0.04114, over 1423157.26 frames.], batch size: 23, lr: 1.56e-04
2022-05-29 10:52:07,014 INFO [train.py:842] (3/4) Epoch 35, batch 7000, loss[loss=0.2178, simple_loss=0.2975, pruned_loss=0.06908, over 7197.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2607, pruned_loss=0.04093, over 1428043.82 frames.], batch size: 22, lr: 1.56e-04
2022-05-29 10:52:46,318 INFO [train.py:842] (3/4) Epoch 35, batch 7050, loss[loss=0.1883, simple_loss=0.2747, pruned_loss=0.05097, over 7310.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2609, pruned_loss=0.04122, over 1427592.21 frames.], batch size: 21, lr: 1.56e-04
2022-05-29 10:53:25,716 INFO [train.py:842] (3/4) Epoch 35, batch 7100, loss[loss=0.1461, simple_loss=0.2459, pruned_loss=0.02313, over 7166.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2609, pruned_loss=0.04124, over 1428036.60 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 10:54:05,040 INFO [train.py:842] (3/4) Epoch 35, batch 7150, loss[loss=0.153, simple_loss=0.2413, pruned_loss=0.0323, over 7368.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2607, pruned_loss=0.04148, over 1427326.99 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 10:54:44,610 INFO [train.py:842] (3/4) Epoch 35, batch 7200, loss[loss=0.1858, simple_loss=0.2838, pruned_loss=0.0439, over 7315.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04158, over 1430141.78 frames.], batch size: 21, lr: 1.56e-04
2022-05-29 10:55:23,872 INFO [train.py:842] (3/4) Epoch 35, batch 7250, loss[loss=0.1668, simple_loss=0.262, pruned_loss=0.03581, over 7297.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2605, pruned_loss=0.04113, over 1429353.46 frames.], batch size: 25, lr: 1.56e-04
2022-05-29 10:56:03,405 INFO [train.py:842] (3/4) Epoch 35, batch 7300, loss[loss=0.1505, simple_loss=0.2446, pruned_loss=0.02815, over 7326.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2604, pruned_loss=0.04092, over 1428743.55 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 10:56:42,472 INFO [train.py:842] (3/4) Epoch 35, batch 7350, loss[loss=0.1516, simple_loss=0.2385, pruned_loss=0.03239, over 6746.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2609, pruned_loss=0.04163, over 1428751.96 frames.], batch size: 15, lr: 1.56e-04
2022-05-29 10:57:22,080 INFO [train.py:842] (3/4) Epoch 35, batch 7400, loss[loss=0.1741, simple_loss=0.2739, pruned_loss=0.03711, over 7325.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2619, pruned_loss=0.04167, over 1431059.56 frames.], batch size: 25, lr: 1.56e-04
2022-05-29 10:58:01,181 INFO [train.py:842] (3/4) Epoch 35, batch 7450, loss[loss=0.204, simple_loss=0.2868, pruned_loss=0.06055, over 6798.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2626, pruned_loss=0.04239, over 1427141.35 frames.], batch size: 31, lr: 1.56e-04
2022-05-29 10:58:43,696 INFO [train.py:842] (3/4) Epoch 35, batch 7500, loss[loss=0.1582, simple_loss=0.2437, pruned_loss=0.03634, over 7428.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2618, pruned_loss=0.0417, over 1428776.22 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 10:59:23,000 INFO [train.py:842] (3/4) Epoch 35, batch 7550, loss[loss=0.1584, simple_loss=0.2456, pruned_loss=0.03566, over 7361.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2618, pruned_loss=0.0416, over 1430332.99 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 11:00:02,453 INFO [train.py:842] (3/4) Epoch 35, batch 7600, loss[loss=0.18, simple_loss=0.277, pruned_loss=0.04145, over 7239.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2621, pruned_loss=0.04178, over 1421926.73 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:00:41,982 INFO [train.py:842] (3/4) Epoch 35, batch 7650, loss[loss=0.1512, simple_loss=0.2353, pruned_loss=0.03348, over 7209.00 frames.], tot_loss[loss=0.1718, simple_loss=0.261, pruned_loss=0.04132, over 1425383.22 frames.], batch size: 16, lr: 1.56e-04
2022-05-29 11:01:21,771 INFO [train.py:842] (3/4) Epoch 35, batch 7700, loss[loss=0.1739, simple_loss=0.2609, pruned_loss=0.04351, over 7096.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2605, pruned_loss=0.04093, over 1425366.28 frames.], batch size: 28, lr: 1.56e-04
2022-05-29 11:02:00,846 INFO [train.py:842] (3/4) Epoch 35, batch 7750, loss[loss=0.1652, simple_loss=0.2527, pruned_loss=0.03883, over 7327.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2619, pruned_loss=0.04146, over 1429431.98 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:02:40,396 INFO [train.py:842] (3/4) Epoch 35, batch 7800, loss[loss=0.181, simple_loss=0.2757, pruned_loss=0.04313, over 7198.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2628, pruned_loss=0.04167, over 1427501.70 frames.], batch size: 22, lr: 1.56e-04
2022-05-29 11:03:19,922 INFO [train.py:842] (3/4) Epoch 35, batch 7850, loss[loss=0.1809, simple_loss=0.27, pruned_loss=0.04585, over 7347.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2619, pruned_loss=0.04142, over 1430909.33 frames.], batch size: 22, lr: 1.56e-04
2022-05-29 11:03:59,695 INFO [train.py:842] (3/4) Epoch 35, batch 7900, loss[loss=0.1987, simple_loss=0.2811, pruned_loss=0.05818, over 7208.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2611, pruned_loss=0.04155, over 1429958.37 frames.], batch size: 22, lr: 1.56e-04
2022-05-29 11:04:38,839 INFO [train.py:842] (3/4) Epoch 35, batch 7950, loss[loss=0.1511, simple_loss=0.2453, pruned_loss=0.02846, over 7298.00 frames.], tot_loss[loss=0.1719, simple_loss=0.261, pruned_loss=0.04134, over 1428783.94 frames.], batch size: 25, lr: 1.56e-04
2022-05-29 11:05:18,270 INFO [train.py:842] (3/4) Epoch 35, batch 8000, loss[loss=0.1524, simple_loss=0.2394, pruned_loss=0.03274, over 7285.00 frames.], tot_loss[loss=0.173, simple_loss=0.2623, pruned_loss=0.04186, over 1428643.79 frames.], batch size: 24, lr: 1.56e-04
2022-05-29 11:05:57,363 INFO [train.py:842] (3/4) Epoch 35, batch 8050, loss[loss=0.1928, simple_loss=0.2843, pruned_loss=0.05063, over 7057.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2632, pruned_loss=0.04277, over 1430985.13 frames.], batch size: 28, lr: 1.56e-04
2022-05-29 11:06:36,969 INFO [train.py:842] (3/4) Epoch 35, batch 8100, loss[loss=0.186, simple_loss=0.281, pruned_loss=0.04548, over 7278.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.04216, over 1431335.60 frames.], batch size: 24, lr: 1.56e-04
2022-05-29 11:07:15,993 INFO [train.py:842] (3/4) Epoch 35, batch 8150, loss[loss=0.1805, simple_loss=0.2686, pruned_loss=0.04623, over 7362.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2616, pruned_loss=0.04195, over 1428200.05 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 11:07:55,445 INFO [train.py:842] (3/4) Epoch 35, batch 8200, loss[loss=0.2272, simple_loss=0.3101, pruned_loss=0.0722, over 6876.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2625, pruned_loss=0.04253, over 1428972.94 frames.], batch size: 32, lr: 1.56e-04
2022-05-29 11:08:34,646 INFO [train.py:842] (3/4) Epoch 35, batch 8250, loss[loss=0.1819, simple_loss=0.2772, pruned_loss=0.04331, over 7306.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2621, pruned_loss=0.04248, over 1423130.34 frames.], batch size: 25, lr: 1.56e-04
2022-05-29 11:09:14,305 INFO [train.py:842] (3/4) Epoch 35, batch 8300, loss[loss=0.1769, simple_loss=0.2647, pruned_loss=0.04456, over 7256.00 frames.], tot_loss[loss=0.1736, simple_loss=0.262, pruned_loss=0.04257, over 1422351.49 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 11:09:53,345 INFO [train.py:842] (3/4) Epoch 35, batch 8350, loss[loss=0.1542, simple_loss=0.2463, pruned_loss=0.03102, over 7429.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2617, pruned_loss=0.04161, over 1425563.06 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:10:32,660 INFO [train.py:842] (3/4) Epoch 35, batch 8400, loss[loss=0.1864, simple_loss=0.2825, pruned_loss=0.04512, over 7151.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2607, pruned_loss=0.04125, over 1417586.98 frames.], batch size: 26, lr: 1.56e-04
2022-05-29 11:11:11,754 INFO [train.py:842] (3/4) Epoch 35, batch 8450, loss[loss=0.1644, simple_loss=0.2645, pruned_loss=0.03215, over 7156.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2609, pruned_loss=0.04169, over 1413864.11 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:11:51,469 INFO [train.py:842] (3/4) Epoch 35, batch 8500, loss[loss=0.1504, simple_loss=0.2331, pruned_loss=0.03388, over 7063.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2608, pruned_loss=0.04194, over 1417034.74 frames.], batch size: 18, lr: 1.56e-04
2022-05-29 11:12:41,668 INFO [train.py:842] (3/4) Epoch 35, batch 8550, loss[loss=0.1705, simple_loss=0.2633, pruned_loss=0.03888, over 6811.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2609, pruned_loss=0.04204, over 1417925.93 frames.], batch size: 31, lr: 1.56e-04
2022-05-29 11:13:21,190 INFO [train.py:842] (3/4) Epoch 35, batch 8600, loss[loss=0.1747, simple_loss=0.2677, pruned_loss=0.04087, over 5288.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2613, pruned_loss=0.04205, over 1412080.35 frames.], batch size: 52, lr: 1.56e-04
2022-05-29 11:14:00,828 INFO [train.py:842] (3/4) Epoch 35, batch 8650, loss[loss=0.1665, simple_loss=0.2664, pruned_loss=0.0333, over 7211.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2612, pruned_loss=0.04177, over 1418626.46 frames.], batch size: 21, lr: 1.56e-04
2022-05-29 11:14:40,511 INFO [train.py:842] (3/4) Epoch 35, batch 8700, loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.03068, over 7361.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2604, pruned_loss=0.04107, over 1415362.15 frames.], batch size: 19, lr: 1.56e-04
2022-05-29 11:15:19,856 INFO [train.py:842] (3/4) Epoch 35, batch 8750, loss[loss=0.1548, simple_loss=0.2447, pruned_loss=0.03246, over 7431.00 frames.], tot_loss[loss=0.172, simple_loss=0.2605, pruned_loss=0.04171, over 1415213.77 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:15:59,192 INFO [train.py:842] (3/4) Epoch 35, batch 8800, loss[loss=0.1666, simple_loss=0.2628, pruned_loss=0.03518, over 7339.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04207, over 1411080.48 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:16:38,449 INFO [train.py:842] (3/4) Epoch 35, batch 8850, loss[loss=0.1882, simple_loss=0.286, pruned_loss=0.04516, over 7226.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2608, pruned_loss=0.04193, over 1407863.19 frames.], batch size: 21, lr: 1.56e-04
2022-05-29 11:17:17,824 INFO [train.py:842] (3/4) Epoch 35, batch 8900, loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.03636, over 7329.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2599, pruned_loss=0.04094, over 1409814.14 frames.], batch size: 20, lr: 1.56e-04
2022-05-29 11:17:56,610 INFO [train.py:842] (3/4) Epoch 35, batch 8950, loss[loss=0.2076, simple_loss=0.2956, pruned_loss=0.05978, over 4745.00 frames.], tot_loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.04159, over 1400752.42 frames.], batch size: 53, lr: 1.56e-04
2022-05-29 11:18:35,203 INFO [train.py:842] (3/4) Epoch 35, batch 9000, loss[loss=0.1684, simple_loss=0.2574, pruned_loss=0.03966, over 6539.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2656, pruned_loss=0.04396, over 1378336.89 frames.], batch size: 39, lr: 1.56e-04
2022-05-29 11:18:35,204 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 11:18:44,739 INFO [train.py:871] (3/4) Epoch 35, validation: loss=0.1633, simple_loss=0.2602, pruned_loss=0.03324, over 868885.00 frames.
2022-05-29 11:19:22,588 INFO [train.py:842] (3/4) Epoch 35, batch 9050, loss[loss=0.1804, simple_loss=0.276, pruned_loss=0.04245, over 6549.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2682, pruned_loss=0.04527, over 1346433.64 frames.], batch size: 38, lr: 1.56e-04
2022-05-29 11:20:00,792 INFO [train.py:842] (3/4) Epoch 35, batch 9100, loss[loss=0.1835, simple_loss=0.2681, pruned_loss=0.04943, over 5040.00 frames.], tot_loss[loss=0.183, simple_loss=0.2712, pruned_loss=0.04735, over 1289364.36 frames.], batch size: 52, lr: 1.56e-04
2022-05-29 11:20:38,919 INFO [train.py:842] (3/4) Epoch 35, batch 9150, loss[loss=0.2118, simple_loss=0.2861, pruned_loss=0.06871, over 4930.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2746, pruned_loss=0.05009, over 1228473.40 frames.], batch size: 53, lr: 1.56e-04
2022-05-29 11:21:27,242 INFO [train.py:842] (3/4) Epoch 36, batch 0, loss[loss=0.1688, simple_loss=0.2693, pruned_loss=0.03411, over 7328.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2693, pruned_loss=0.03411, over 7328.00 frames.], batch size: 20, lr: 1.54e-04
2022-05-29 11:22:06,520 INFO [train.py:842] (3/4) Epoch 36, batch 50, loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03398, over 7429.00 frames.], tot_loss[loss=0.173, simple_loss=0.2608, pruned_loss=0.04262, over 316117.16 frames.], batch size: 20, lr: 1.54e-04
2022-05-29 11:22:46,058 INFO [train.py:842] (3/4) Epoch 36, batch 100, loss[loss=0.1565, simple_loss=0.2444, pruned_loss=0.03426, over 5190.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2606, pruned_loss=0.04133, over 561851.64 frames.], batch size: 53, lr: 1.54e-04
2022-05-29 11:23:25,176 INFO [train.py:842] (3/4) Epoch 36, batch 150, loss[loss=0.1569, simple_loss=0.2584, pruned_loss=0.02768, over 7241.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04105, over 751345.54 frames.], batch size: 20, lr: 1.54e-04
2022-05-29 11:24:04,871 INFO [train.py:842] (3/4) Epoch 36, batch 200, loss[loss=0.1644, simple_loss=0.2546, pruned_loss=0.03709, over 7321.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2597, pruned_loss=0.04066, over 901633.80 frames.], batch size: 21, lr: 1.54e-04
2022-05-29 11:24:44,255 INFO [train.py:842] (3/4) Epoch 36, batch 250, loss[loss=0.1554, simple_loss=0.2537, pruned_loss=0.02851, over 7155.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2595, pruned_loss=0.03997, over 1020431.69 frames.], batch size: 19, lr: 1.54e-04
2022-05-29 11:25:23,538 INFO [train.py:842] (3/4) Epoch 36, batch 300, loss[loss=0.2083, simple_loss=0.2965, pruned_loss=0.06008, over 7194.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2597, pruned_loss=0.04059, over 1104978.38 frames.], batch size: 26, lr: 1.54e-04
2022-05-29 11:26:02,706 INFO [train.py:842] (3/4) Epoch 36, batch 350, loss[loss=0.1625, simple_loss=0.2482, pruned_loss=0.03846, over 6813.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2603, pruned_loss=0.04046, over 1174597.06 frames.], batch size: 31, lr: 1.54e-04
2022-05-29 11:26:41,953 INFO [train.py:842] (3/4) Epoch 36, batch 400, loss[loss=0.1862, simple_loss=0.2808, pruned_loss=0.04587, over 7204.00 frames.], tot_loss[loss=0.171, simple_loss=0.2606, pruned_loss=0.0407, over 1230555.66 frames.], batch size: 22, lr: 1.54e-04
2022-05-29 11:27:21,315 INFO [train.py:842] (3/4) Epoch 36, batch 450, loss[loss=0.1765, simple_loss=0.2649, pruned_loss=0.04407, over 7192.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2607, pruned_loss=0.04083, over 1278147.59 frames.], batch size: 26, lr: 1.54e-04
2022-05-29 11:28:00,719 INFO [train.py:842] (3/4) Epoch 36, batch 500, loss[loss=0.18, simple_loss=0.2677, pruned_loss=0.04609, over 7206.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2616, pruned_loss=0.04109, over 1309659.91 frames.], batch size: 23, lr: 1.54e-04
2022-05-29 11:28:39,895 INFO [train.py:842] (3/4) Epoch 36, batch 550, loss[loss=0.1748, simple_loss=0.2697, pruned_loss=0.03989, over 7428.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2624, pruned_loss=0.04103, over 1335594.47 frames.], batch size: 20, lr: 1.54e-04
2022-05-29 11:29:19,646 INFO [train.py:842] (3/4) Epoch 36, batch 600, loss[loss=0.1827, simple_loss=0.279, pruned_loss=0.04316, over 7209.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2612, pruned_loss=0.04052, over 1358208.42 frames.], batch size: 23, lr: 1.54e-04
2022-05-29 11:29:59,106 INFO [train.py:842] (3/4) Epoch 36, batch 650, loss[loss=0.1524, simple_loss=0.251, pruned_loss=0.02688, over 7160.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2606, pruned_loss=0.04092, over 1372914.82 frames.], batch size: 19, lr: 1.54e-04
2022-05-29 11:30:38,737 INFO [train.py:842] (3/4) Epoch 36, batch 700, loss[loss=0.1406, simple_loss=0.2308, pruned_loss=0.02519, over 7260.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2602, pruned_loss=0.04079, over 1384920.76 frames.], batch size: 19, lr: 1.54e-04
2022-05-29 11:31:17,852 INFO [train.py:842] (3/4) Epoch 36, batch 750, loss[loss=0.1616, simple_loss=0.2496, pruned_loss=0.03682, over 7336.00 frames.], tot_loss[loss=0.1719, simple_loss=0.261, pruned_loss=0.04135, over 1384129.80 frames.], batch size: 20, lr: 1.54e-04
2022-05-29 11:31:57,503 INFO [train.py:842] (3/4) Epoch 36, batch 800, loss[loss=0.1881, simple_loss=0.2755, pruned_loss=0.05031, over 7420.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2619, pruned_loss=0.04151, over 1391986.62 frames.], batch size: 21, lr: 1.54e-04
2022-05-29 11:32:36,721 INFO [train.py:842] (3/4) Epoch 36, batch 850, loss[loss=0.1864, simple_loss=0.2851, pruned_loss=0.04384, over 7216.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2616, pruned_loss=0.04126, over 1393955.02 frames.], batch size: 21, lr: 1.54e-04
2022-05-29 11:33:16,401 INFO [train.py:842] (3/4) Epoch 36, batch 900, loss[loss=0.1792, simple_loss=0.2772, pruned_loss=0.04055, over 6685.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2609, pruned_loss=0.04045, over 1400972.80 frames.], batch size: 31, lr: 1.54e-04
2022-05-29 11:33:55,578 INFO [train.py:842] (3/4) Epoch 36, batch 950, loss[loss=0.1493, simple_loss=0.236, pruned_loss=0.03127, over 7001.00 frames.], tot_loss[loss=0.1711, simple_loss=0.261, pruned_loss=0.04058, over 1404443.69 frames.], batch size: 16, lr: 1.53e-04
2022-05-29 11:34:35,041 INFO [train.py:842] (3/4) Epoch 36, batch 1000, loss[loss=0.1589, simple_loss=0.2316, pruned_loss=0.04307, over 7279.00 frames.], tot_loss[loss=0.172, simple_loss=0.262, pruned_loss=0.04098, over 1406473.42 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 11:35:14,271 INFO [train.py:842] (3/4) Epoch 36, batch 1050, loss[loss=0.152, simple_loss=0.235, pruned_loss=0.03448, over 7352.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2608, pruned_loss=0.04053, over 1406691.87 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:35:53,844 INFO [train.py:842] (3/4) Epoch 36, batch 1100, loss[loss=0.1596, simple_loss=0.2544, pruned_loss=0.0324, over 7210.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2608, pruned_loss=0.04052, over 1407175.64 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 11:36:33,138 INFO [train.py:842] (3/4) Epoch 36, batch 1150, loss[loss=0.1674, simple_loss=0.2648, pruned_loss=0.03498, over 7275.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2603, pruned_loss=0.04063, over 1412792.75 frames.], batch size: 24, lr: 1.53e-04
2022-05-29 11:37:12,457 INFO [train.py:842] (3/4) Epoch 36, batch 1200, loss[loss=0.1455, simple_loss=0.2292, pruned_loss=0.03096, over 7276.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2623, pruned_loss=0.04199, over 1409036.09 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 11:37:51,887 INFO [train.py:842] (3/4) Epoch 36, batch 1250, loss[loss=0.1596, simple_loss=0.2364, pruned_loss=0.04139, over 7000.00 frames.], tot_loss[loss=0.172, simple_loss=0.2609, pruned_loss=0.04149, over 1411254.51 frames.], batch size: 16, lr: 1.53e-04
2022-05-29 11:38:31,212 INFO [train.py:842] (3/4) Epoch 36, batch 1300, loss[loss=0.145, simple_loss=0.2273, pruned_loss=0.03137, over 7135.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2621, pruned_loss=0.04216, over 1415052.01 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 11:39:10,493 INFO [train.py:842] (3/4) Epoch 36, batch 1350, loss[loss=0.1865, simple_loss=0.2714, pruned_loss=0.05081, over 7261.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04123, over 1419825.66 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:39:49,831 INFO [train.py:842] (3/4) Epoch 36, batch 1400, loss[loss=0.1489, simple_loss=0.238, pruned_loss=0.02991, over 7005.00 frames.], tot_loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.0413, over 1418378.15 frames.], batch size: 16, lr: 1.53e-04
2022-05-29 11:40:29,037 INFO [train.py:842] (3/4) Epoch 36, batch 1450, loss[loss=0.1325, simple_loss=0.2164, pruned_loss=0.02427, over 6833.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2609, pruned_loss=0.04077, over 1414724.98 frames.], batch size: 15, lr: 1.53e-04
2022-05-29 11:41:08,699 INFO [train.py:842] (3/4) Epoch 36, batch 1500, loss[loss=0.1499, simple_loss=0.2496, pruned_loss=0.02512, over 7327.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2605, pruned_loss=0.04043, over 1418804.95 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:41:47,974 INFO [train.py:842] (3/4) Epoch 36, batch 1550, loss[loss=0.1877, simple_loss=0.2798, pruned_loss=0.0478, over 7236.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2603, pruned_loss=0.04005, over 1419900.96 frames.], batch size: 20, lr: 1.53e-04
2022-05-29 11:42:27,491 INFO [train.py:842] (3/4) Epoch 36, batch 1600, loss[loss=0.2001, simple_loss=0.2834, pruned_loss=0.0584, over 7379.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2602, pruned_loss=0.04046, over 1419852.81 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 11:43:06,830 INFO [train.py:842] (3/4) Epoch 36, batch 1650, loss[loss=0.1999, simple_loss=0.2889, pruned_loss=0.05546, over 7163.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04092, over 1421089.27 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:43:46,270 INFO [train.py:842] (3/4) Epoch 36, batch 1700, loss[loss=0.2676, simple_loss=0.3365, pruned_loss=0.09935, over 7332.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2607, pruned_loss=0.04077, over 1423523.87 frames.], batch size: 25, lr: 1.53e-04
2022-05-29 11:44:25,382 INFO [train.py:842] (3/4) Epoch 36, batch 1750, loss[loss=0.2209, simple_loss=0.299, pruned_loss=0.07137, over 7293.00 frames.], tot_loss[loss=0.1712, simple_loss=0.261, pruned_loss=0.04076, over 1419007.65 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 11:45:04,894 INFO [train.py:842] (3/4) Epoch 36, batch 1800, loss[loss=0.1622, simple_loss=0.256, pruned_loss=0.03421, over 7219.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2628, pruned_loss=0.04169, over 1421238.50 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 11:45:44,147 INFO [train.py:842] (3/4) Epoch 36, batch 1850, loss[loss=0.1467, simple_loss=0.2431, pruned_loss=0.02508, over 7120.00 frames.], tot_loss[loss=0.174, simple_loss=0.2637, pruned_loss=0.04216, over 1424125.03 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:46:23,718 INFO [train.py:842] (3/4) Epoch 36, batch 1900, loss[loss=0.1684, simple_loss=0.2559, pruned_loss=0.04046, over 6770.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2627, pruned_loss=0.04188, over 1424782.69 frames.], batch size: 31, lr: 1.53e-04
2022-05-29 11:47:02,850 INFO [train.py:842] (3/4) Epoch 36, batch 1950, loss[loss=0.1705, simple_loss=0.2702, pruned_loss=0.03537, over 7241.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.04216, over 1421902.71 frames.], batch size: 20, lr: 1.53e-04
2022-05-29 11:47:42,042 INFO [train.py:842] (3/4) Epoch 36, batch 2000, loss[loss=0.1767, simple_loss=0.247, pruned_loss=0.05319, over 6984.00 frames.], tot_loss[loss=0.1727, simple_loss=0.262, pruned_loss=0.04171, over 1419071.71 frames.], batch size: 16, lr: 1.53e-04
2022-05-29 11:48:21,478 INFO [train.py:842] (3/4) Epoch 36, batch 2050, loss[loss=0.1656, simple_loss=0.2672, pruned_loss=0.03199, over 7321.00 frames.], tot_loss[loss=0.1725, simple_loss=0.262, pruned_loss=0.04154, over 1423421.02 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:49:01,245 INFO [train.py:842] (3/4) Epoch 36, batch 2100, loss[loss=0.1761, simple_loss=0.2712, pruned_loss=0.04054, over 7417.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2622, pruned_loss=0.04183, over 1422911.58 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:49:40,709 INFO [train.py:842] (3/4) Epoch 36, batch 2150, loss[loss=0.1557, simple_loss=0.2443, pruned_loss=0.03353, over 7263.00 frames.], tot_loss[loss=0.172, simple_loss=0.2611, pruned_loss=0.04144, over 1425970.37 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:50:20,116 INFO [train.py:842] (3/4) Epoch 36, batch 2200, loss[loss=0.1789, simple_loss=0.2629, pruned_loss=0.04749, over 7420.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2615, pruned_loss=0.04184, over 1425588.15 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 11:50:58,864 INFO [train.py:842] (3/4) Epoch 36, batch 2250, loss[loss=0.1545, simple_loss=0.2532, pruned_loss=0.02789, over 7327.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2629, pruned_loss=0.0422, over 1422483.03 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 11:51:38,562 INFO [train.py:842] (3/4) Epoch 36, batch 2300, loss[loss=0.1441, simple_loss=0.229, pruned_loss=0.02958, over 7123.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2612, pruned_loss=0.04181, over 1425564.96 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 11:52:17,589 INFO [train.py:842] (3/4) Epoch 36, batch 2350, loss[loss=0.251, simple_loss=0.3294, pruned_loss=0.08635, over 4931.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04131, over 1423788.75 frames.], batch size: 52, lr: 1.53e-04
2022-05-29 11:52:57,231 INFO [train.py:842] (3/4) Epoch 36, batch 2400, loss[loss=0.1375, simple_loss=0.2227, pruned_loss=0.02613, over 7428.00 frames.], tot_loss[loss=0.171, simple_loss=0.2603, pruned_loss=0.04086, over 1426420.05 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 11:53:36,451 INFO [train.py:842] (3/4) Epoch 36, batch 2450, loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03078, over 7167.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2609, pruned_loss=0.04121, over 1422958.59 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 11:54:16,227 INFO [train.py:842] (3/4) Epoch 36, batch 2500, loss[loss=0.1783, simple_loss=0.2639, pruned_loss=0.04639, over 7137.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2612, pruned_loss=0.04167, over 1426285.40 frames.], batch size: 20, lr: 1.53e-04
2022-05-29 11:54:55,461 INFO [train.py:842] (3/4) Epoch 36, batch 2550, loss[loss=0.1474, simple_loss=0.2359, pruned_loss=0.02945, over 7361.00 frames.], tot_loss[loss=0.172, simple_loss=0.2611, pruned_loss=0.04146, over 1423259.36 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:55:34,926 INFO [train.py:842] (3/4) Epoch 36, batch 2600, loss[loss=0.1869, simple_loss=0.2685, pruned_loss=0.05263, over 7153.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2614, pruned_loss=0.04153, over 1424071.16 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 11:56:14,155 INFO [train.py:842] (3/4) Epoch 36, batch 2650, loss[loss=0.1924, simple_loss=0.2766, pruned_loss=0.05411, over 5106.00 frames.], tot_loss[loss=0.172, simple_loss=0.261, pruned_loss=0.0415, over 1423050.70 frames.], batch size: 52, lr: 1.53e-04
2022-05-29 11:56:54,021 INFO [train.py:842] (3/4) Epoch 36, batch 2700, loss[loss=0.1607, simple_loss=0.2565, pruned_loss=0.03248, over 7324.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2605, pruned_loss=0.04141, over 1423810.51 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:57:33,307 INFO [train.py:842] (3/4) Epoch 36, batch 2750, loss[loss=0.1788, simple_loss=0.2771, pruned_loss=0.04026, over 7106.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2597, pruned_loss=0.04105, over 1425799.11 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 11:58:12,914 INFO [train.py:842] (3/4) Epoch 36, batch 2800, loss[loss=0.2218, simple_loss=0.3125, pruned_loss=0.06553, over 7209.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2601, pruned_loss=0.04149, over 1427634.01 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 11:58:52,385 INFO [train.py:842] (3/4) Epoch 36, batch 2850, loss[loss=0.1289, simple_loss=0.2076, pruned_loss=0.02514, over 7285.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.04177, over 1428239.51 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 11:59:32,204 INFO [train.py:842] (3/4) Epoch 36, batch 2900, loss[loss=0.1369, simple_loss=0.2286, pruned_loss=0.02257, over 7255.00 frames.], tot_loss[loss=0.17, simple_loss=0.2583, pruned_loss=0.04084, over 1427972.69 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 12:00:11,113 INFO [train.py:842] (3/4) Epoch 36, batch 2950, loss[loss=0.1447, simple_loss=0.2343, pruned_loss=0.02751, over 7169.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2588, pruned_loss=0.04043, over 1425941.83 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 12:00:50,576 INFO [train.py:842] (3/4) Epoch 36, batch 3000, loss[loss=0.1706, simple_loss=0.2606, pruned_loss=0.04035, over 7163.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2599, pruned_loss=0.04092, over 1422429.09 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 12:00:50,577 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 12:01:00,560 INFO [train.py:871] (3/4) Epoch 36, validation: loss=0.1657, simple_loss=0.263, pruned_loss=0.03426, over 868885.00 frames.
2022-05-29 12:01:39,803 INFO [train.py:842] (3/4) Epoch 36, batch 3050, loss[loss=0.1585, simple_loss=0.2464, pruned_loss=0.0353, over 7287.00 frames.], tot_loss[loss=0.171, simple_loss=0.2603, pruned_loss=0.04086, over 1425356.59 frames.], batch size: 24, lr: 1.53e-04
2022-05-29 12:02:19,607 INFO [train.py:842] (3/4) Epoch 36, batch 3100, loss[loss=0.2308, simple_loss=0.2959, pruned_loss=0.08286, over 7295.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2601, pruned_loss=0.04089, over 1429324.52 frames.], batch size: 25, lr: 1.53e-04
2022-05-29 12:02:58,640 INFO [train.py:842] (3/4) Epoch 36, batch 3150, loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03142, over 7384.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2609, pruned_loss=0.041, over 1426922.14 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:03:38,036 INFO [train.py:842] (3/4) Epoch 36, batch 3200, loss[loss=0.1796, simple_loss=0.2603, pruned_loss=0.04939, over 7136.00 frames.], tot_loss[loss=0.173, simple_loss=0.262, pruned_loss=0.04194, over 1420991.15 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 12:04:17,313 INFO [train.py:842] (3/4) Epoch 36, batch 3250, loss[loss=0.2324, simple_loss=0.305, pruned_loss=0.07984, over 4910.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2621, pruned_loss=0.04217, over 1418448.22 frames.], batch size: 52, lr: 1.53e-04
2022-05-29 12:04:56,916 INFO [train.py:842] (3/4) Epoch 36, batch 3300, loss[loss=0.1597, simple_loss=0.256, pruned_loss=0.03163, over 7205.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2617, pruned_loss=0.04186, over 1422148.65 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:05:36,381 INFO [train.py:842] (3/4) Epoch 36, batch 3350, loss[loss=0.1635, simple_loss=0.2619, pruned_loss=0.03259, over 7218.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.04227, over 1425889.81 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:06:16,105 INFO [train.py:842] (3/4) Epoch 36, batch 3400, loss[loss=0.1672, simple_loss=0.244, pruned_loss=0.04521, over 7248.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2624, pruned_loss=0.04237, over 1423995.42 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 12:06:55,250 INFO [train.py:842] (3/4) Epoch 36, batch 3450, loss[loss=0.1426, simple_loss=0.228, pruned_loss=0.02862, over 7291.00 frames.], tot_loss[loss=0.174, simple_loss=0.2626, pruned_loss=0.04266, over 1421744.99 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 12:07:34,903 INFO [train.py:842] (3/4) Epoch 36, batch 3500, loss[loss=0.1861, simple_loss=0.2855, pruned_loss=0.04335, over 7417.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2614, pruned_loss=0.04203, over 1417866.72 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 12:08:13,978 INFO [train.py:842] (3/4) Epoch 36, batch 3550, loss[loss=0.1724, simple_loss=0.2719, pruned_loss=0.03639, over 7016.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.04181, over 1422112.60 frames.], batch size: 28, lr: 1.53e-04
2022-05-29 12:08:53,425 INFO [train.py:842] (3/4) Epoch 36, batch 3600, loss[loss=0.1774, simple_loss=0.2803, pruned_loss=0.03723, over 7284.00 frames.], tot_loss[loss=0.1727, simple_loss=0.262, pruned_loss=0.04173, over 1421116.99 frames.], batch size: 25, lr: 1.53e-04
2022-05-29 12:09:32,748 INFO [train.py:842] (3/4) Epoch 36, batch 3650, loss[loss=0.1853, simple_loss=0.2694, pruned_loss=0.05063, over 7273.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04119, over 1423103.42 frames.], batch size: 24, lr: 1.53e-04
2022-05-29 12:10:12,435 INFO [train.py:842] (3/4) Epoch 36, batch 3700, loss[loss=0.1944, simple_loss=0.2808, pruned_loss=0.05404, over 7102.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2605, pruned_loss=0.04105, over 1426495.44 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 12:10:51,869 INFO [train.py:842] (3/4) Epoch 36, batch 3750, loss[loss=0.1652, simple_loss=0.2562, pruned_loss=0.03709, over 7336.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2595, pruned_loss=0.0406, over 1426135.65 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 12:11:31,369 INFO [train.py:842] (3/4) Epoch 36, batch 3800, loss[loss=0.1502, simple_loss=0.2339, pruned_loss=0.03325, over 7354.00 frames.], tot_loss[loss=0.1706, simple_loss=0.26, pruned_loss=0.04058, over 1427274.12 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 12:12:10,353 INFO [train.py:842] (3/4) Epoch 36, batch 3850, loss[loss=0.1519, simple_loss=0.228, pruned_loss=0.03788, over 6994.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2603, pruned_loss=0.04091, over 1423366.84 frames.], batch size: 16, lr: 1.53e-04
2022-05-29 12:12:50,340 INFO [train.py:842] (3/4) Epoch 36, batch 3900, loss[loss=0.1809, simple_loss=0.2702, pruned_loss=0.04573, over 7216.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2599, pruned_loss=0.04068, over 1425768.27 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:13:29,191 INFO [train.py:842] (3/4) Epoch 36, batch 3950, loss[loss=0.1721, simple_loss=0.267, pruned_loss=0.03861, over 6779.00 frames.], tot_loss[loss=0.172, simple_loss=0.2609, pruned_loss=0.04152, over 1424282.09 frames.], batch size: 31, lr: 1.53e-04
2022-05-29 12:14:08,390 INFO [train.py:842] (3/4) Epoch 36, batch 4000, loss[loss=0.1703, simple_loss=0.2616, pruned_loss=0.03952, over 7062.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2627, pruned_loss=0.04213, over 1424267.94 frames.], batch size: 28, lr: 1.53e-04
2022-05-29 12:14:47,657 INFO [train.py:842] (3/4) Epoch 36, batch 4050, loss[loss=0.1439, simple_loss=0.2352, pruned_loss=0.02635, over 6331.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2627, pruned_loss=0.0417, over 1425126.97 frames.], batch size: 37, lr: 1.53e-04
2022-05-29 12:15:27,259 INFO [train.py:842] (3/4) Epoch 36, batch 4100, loss[loss=0.1758, simple_loss=0.2627, pruned_loss=0.04445, over 7238.00 frames.], tot_loss[loss=0.174, simple_loss=0.2635, pruned_loss=0.04223, over 1426284.78 frames.], batch size: 20, lr: 1.53e-04
2022-05-29 12:16:06,492 INFO [train.py:842] (3/4) Epoch 36, batch 4150, loss[loss=0.2093, simple_loss=0.2983, pruned_loss=0.0601, over 7347.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2637, pruned_loss=0.04253, over 1423642.38 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 12:16:45,808 INFO [train.py:842] (3/4) Epoch 36, batch 4200, loss[loss=0.1723, simple_loss=0.2758, pruned_loss=0.03441, over 7337.00 frames.], tot_loss[loss=0.174, simple_loss=0.2635, pruned_loss=0.04224, over 1417802.67 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 12:17:25,119 INFO [train.py:842] (3/4) Epoch 36, batch 4250, loss[loss=0.2262, simple_loss=0.3006, pruned_loss=0.07584, over 7211.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2629, pruned_loss=0.04168, over 1418012.08 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 12:18:04,954 INFO [train.py:842] (3/4) Epoch 36, batch 4300, loss[loss=0.1744, simple_loss=0.2727, pruned_loss=0.038, over 7199.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2623, pruned_loss=0.04178, over 1418953.45 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:18:44,053 INFO [train.py:842] (3/4) Epoch 36, batch 4350, loss[loss=0.1678, simple_loss=0.2645, pruned_loss=0.03554, over 7367.00 frames.], tot_loss[loss=0.1736, simple_loss=0.263, pruned_loss=0.04214, over 1413585.27 frames.], batch size: 19, lr: 1.53e-04
2022-05-29 12:19:23,726 INFO [train.py:842] (3/4) Epoch 36, batch 4400, loss[loss=0.176, simple_loss=0.2694, pruned_loss=0.04132, over 6852.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2627, pruned_loss=0.04222, over 1417142.91 frames.], batch size: 31, lr: 1.53e-04
2022-05-29 12:20:13,642 INFO [train.py:842] (3/4) Epoch 36, batch 4450, loss[loss=0.2079, simple_loss=0.2933, pruned_loss=0.06125, over 7408.00 frames.], tot_loss[loss=0.1736, simple_loss=0.263, pruned_loss=0.04211, over 1417393.43 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 12:20:53,267 INFO [train.py:842] (3/4) Epoch 36, batch 4500, loss[loss=0.1517, simple_loss=0.2409, pruned_loss=0.03124, over 7164.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2627, pruned_loss=0.0417, over 1421445.00 frames.], batch size: 18, lr: 1.53e-04
2022-05-29 12:21:32,473 INFO [train.py:842] (3/4) Epoch 36, batch 4550, loss[loss=0.1612, simple_loss=0.2525, pruned_loss=0.03497, over 7388.00 frames.], tot_loss[loss=0.173, simple_loss=0.2628, pruned_loss=0.04158, over 1421360.41 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:22:11,944 INFO [train.py:842] (3/4) Epoch 36, batch 4600, loss[loss=0.1828, simple_loss=0.2695, pruned_loss=0.04806, over 5136.00 frames.], tot_loss[loss=0.1732, simple_loss=0.263, pruned_loss=0.04175, over 1418365.70 frames.], batch size: 52, lr: 1.53e-04
2022-05-29 12:22:50,825 INFO [train.py:842] (3/4) Epoch 36, batch 4650, loss[loss=0.1319, simple_loss=0.2137, pruned_loss=0.02506, over 7267.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2619, pruned_loss=0.04147, over 1415339.07 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 12:23:30,508 INFO [train.py:842] (3/4) Epoch 36, batch 4700, loss[loss=0.1773, simple_loss=0.2715, pruned_loss=0.04156, over 6272.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2613, pruned_loss=0.04089, over 1418522.39 frames.], batch size: 37, lr: 1.53e-04
2022-05-29 12:24:09,549 INFO [train.py:842] (3/4) Epoch 36, batch 4750, loss[loss=0.2175, simple_loss=0.302, pruned_loss=0.06653, over 7059.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2622, pruned_loss=0.04157, over 1413658.94 frames.], batch size: 28, lr: 1.53e-04
2022-05-29 12:24:49,159 INFO [train.py:842] (3/4) Epoch 36, batch 4800, loss[loss=0.1966, simple_loss=0.2887, pruned_loss=0.05224, over 7208.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2621, pruned_loss=0.04171, over 1413799.41 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:25:49,851 INFO [train.py:842] (3/4) Epoch 36, batch 4850, loss[loss=0.173, simple_loss=0.2643, pruned_loss=0.04089, over 7115.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2623, pruned_loss=0.04127, over 1414993.34 frames.], batch size: 21, lr: 1.53e-04
2022-05-29 12:26:29,663 INFO [train.py:842] (3/4) Epoch 36, batch 4900, loss[loss=0.1752, simple_loss=0.2513, pruned_loss=0.04952, over 7290.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.04099, over 1420282.02 frames.], batch size: 17, lr: 1.53e-04
2022-05-29 12:27:08,913 INFO [train.py:842] (3/4) Epoch 36, batch 4950, loss[loss=0.1681, simple_loss=0.2594, pruned_loss=0.0384, over 7300.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2606, pruned_loss=0.04098, over 1420739.39 frames.], batch size: 25, lr: 1.53e-04
2022-05-29 12:27:48,600 INFO [train.py:842] (3/4) Epoch 36, batch 5000, loss[loss=0.171, simple_loss=0.2633, pruned_loss=0.03934, over 7369.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.0413, over 1424384.36 frames.], batch size: 23, lr: 1.53e-04
2022-05-29 12:28:27,756 INFO [train.py:842] (3/4) Epoch 36, batch 5050, loss[loss=0.2085, simple_loss=0.2922, pruned_loss=0.06239, over 4989.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04104, over 1419899.93 frames.], batch size: 52, lr: 1.53e-04
2022-05-29 12:29:07,328 INFO [train.py:842] (3/4) Epoch 36, batch 5100, loss[loss=0.1507, simple_loss=0.2492, pruned_loss=0.02605, over 6975.00 frames.], tot_loss[loss=0.172, simple_loss=0.2616, pruned_loss=0.04122, over 1421361.32 frames.], batch size: 28, lr: 1.53e-04
2022-05-29 12:29:46,365 INFO [train.py:842] (3/4) Epoch 36, batch 5150, loss[loss=0.1716, simple_loss=0.2685, pruned_loss=0.03733, over 7347.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2631, pruned_loss=0.04198, over 1422065.84 frames.], batch size: 22, lr: 1.53e-04
2022-05-29 12:30:26,083 INFO [train.py:842] (3/4) Epoch 36, batch 5200, loss[loss=0.1438, simple_loss=0.2338, pruned_loss=0.02691, over 7352.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2636, pruned_loss=0.04243, over 1421068.33 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:31:05,224 INFO [train.py:842] (3/4) Epoch 36, batch 5250, loss[loss=0.1825, simple_loss=0.2755, pruned_loss=0.04474, over 7113.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2641, pruned_loss=0.0426, over 1423878.54 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 12:31:44,699 INFO [train.py:842] (3/4) Epoch 36, batch 5300, loss[loss=0.1879, simple_loss=0.2728, pruned_loss=0.05151, over 7208.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2644, pruned_loss=0.04265, over 1427794.58 frames.], batch size: 23, lr: 1.52e-04
2022-05-29 12:32:23,858 INFO [train.py:842] (3/4) Epoch 36, batch 5350, loss[loss=0.1593, simple_loss=0.2551, pruned_loss=0.03178, over 7298.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2632, pruned_loss=0.04198, over 1423682.13 frames.], batch size: 24, lr: 1.52e-04
2022-05-29 12:33:03,182 INFO [train.py:842] (3/4) Epoch 36, batch 5400, loss[loss=0.161, simple_loss=0.2529, pruned_loss=0.03451, over 7057.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2629, pruned_loss=0.04192, over 1417901.20 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:33:42,367 INFO [train.py:842] (3/4) Epoch 36, batch 5450, loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02913, over 7167.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2623, pruned_loss=0.04169, over 1417888.11 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:34:21,822 INFO [train.py:842] (3/4) Epoch 36, batch 5500, loss[loss=0.1606, simple_loss=0.2582, pruned_loss=0.0315, over 7202.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2618, pruned_loss=0.0412, over 1419475.02 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 12:35:00,657 INFO [train.py:842] (3/4) Epoch 36, batch 5550, loss[loss=0.1416, simple_loss=0.2344, pruned_loss=0.02445, over 7335.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2614, pruned_loss=0.04069, over 1416380.87 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:35:40,084 INFO [train.py:842] (3/4) Epoch 36, batch 5600, loss[loss=0.1824, simple_loss=0.2771, pruned_loss=0.04387, over 7328.00 frames.], tot_loss[loss=0.172, simple_loss=0.2616, pruned_loss=0.04114, over 1417804.63 frames.], batch size: 22, lr: 1.52e-04
2022-05-29 12:36:19,263 INFO [train.py:842] (3/4) Epoch 36, batch 5650, loss[loss=0.1777, simple_loss=0.2791, pruned_loss=0.03813, over 7384.00 frames.], tot_loss[loss=0.173, simple_loss=0.2623, pruned_loss=0.04189, over 1418137.57 frames.], batch size: 23, lr: 1.52e-04
2022-05-29 12:36:58,859 INFO [train.py:842] (3/4) Epoch 36, batch 5700, loss[loss=0.1663, simple_loss=0.2574, pruned_loss=0.03767, over 7407.00 frames.], tot_loss[loss=0.1729, simple_loss=0.262, pruned_loss=0.04195, over 1415595.51 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:37:37,876 INFO [train.py:842] (3/4) Epoch 36, batch 5750, loss[loss=0.1739, simple_loss=0.2668, pruned_loss=0.04048, over 7310.00 frames.], tot_loss[loss=0.173, simple_loss=0.2621, pruned_loss=0.04191, over 1412113.63 frames.], batch size: 25, lr: 1.52e-04
2022-05-29 12:38:17,294 INFO [train.py:842] (3/4) Epoch 36, batch 5800, loss[loss=0.1766, simple_loss=0.2644, pruned_loss=0.04436, over 7021.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2611, pruned_loss=0.04133, over 1415754.18 frames.], batch size: 28, lr: 1.52e-04
2022-05-29 12:38:56,600 INFO [train.py:842] (3/4) Epoch 36, batch 5850, loss[loss=0.1538, simple_loss=0.2324, pruned_loss=0.03754, over 7165.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2606, pruned_loss=0.041, over 1419735.94 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:39:36,368 INFO [train.py:842] (3/4) Epoch 36, batch 5900, loss[loss=0.1265, simple_loss=0.2127, pruned_loss=0.02014, over 7407.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2603, pruned_loss=0.04117, over 1419937.11 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:40:15,759 INFO [train.py:842] (3/4) Epoch 36, batch 5950, loss[loss=0.1707, simple_loss=0.2586, pruned_loss=0.0414, over 7158.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2598, pruned_loss=0.04103, over 1419779.49 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:40:55,468 INFO [train.py:842] (3/4) Epoch 36, batch 6000, loss[loss=0.1711, simple_loss=0.2534, pruned_loss=0.04442, over 7193.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2605, pruned_loss=0.04098, over 1420455.69 frames.], batch size: 22, lr: 1.52e-04
2022-05-29 12:40:55,469 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 12:41:05,037 INFO [train.py:871] (3/4) Epoch 36, validation: loss=0.1636, simple_loss=0.2603, pruned_loss=0.03352, over 868885.00 frames.
2022-05-29 12:41:44,521 INFO [train.py:842] (3/4) Epoch 36, batch 6050, loss[loss=0.1233, simple_loss=0.206, pruned_loss=0.02035, over 7128.00 frames.], tot_loss[loss=0.171, simple_loss=0.2602, pruned_loss=0.04093, over 1420373.80 frames.], batch size: 17, lr: 1.52e-04
2022-05-29 12:42:24,247 INFO [train.py:842] (3/4) Epoch 36, batch 6100, loss[loss=0.1466, simple_loss=0.2466, pruned_loss=0.02332, over 7172.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2599, pruned_loss=0.04096, over 1422090.99 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:43:03,496 INFO [train.py:842] (3/4) Epoch 36, batch 6150, loss[loss=0.169, simple_loss=0.2603, pruned_loss=0.03882, over 7334.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2592, pruned_loss=0.04063, over 1424034.07 frames.], batch size: 22, lr: 1.52e-04
2022-05-29 12:43:43,182 INFO [train.py:842] (3/4) Epoch 36, batch 6200, loss[loss=0.1757, simple_loss=0.2731, pruned_loss=0.03918, over 6983.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2597, pruned_loss=0.04055, over 1421560.80 frames.], batch size: 28, lr: 1.52e-04
2022-05-29 12:44:22,468 INFO [train.py:842] (3/4) Epoch 36, batch 6250, loss[loss=0.196, simple_loss=0.2823, pruned_loss=0.05483, over 7307.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2601, pruned_loss=0.0408, over 1421693.09 frames.], batch size: 25, lr: 1.52e-04
2022-05-29 12:45:04,925 INFO [train.py:842] (3/4) Epoch 36, batch 6300, loss[loss=0.1475, simple_loss=0.2322, pruned_loss=0.03142, over 7128.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2616, pruned_loss=0.04239, over 1420091.87 frames.], batch size: 17, lr: 1.52e-04
2022-05-29 12:45:44,279 INFO [train.py:842] (3/4) Epoch 36, batch 6350, loss[loss=0.183, simple_loss=0.2815, pruned_loss=0.04222, over 7329.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2607, pruned_loss=0.04154, over 1419367.56 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 12:46:23,731 INFO [train.py:842] (3/4) Epoch 36, batch 6400, loss[loss=0.2027, simple_loss=0.2953, pruned_loss=0.055, over 7331.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2598, pruned_loss=0.04077, over 1421370.41 frames.], batch size: 22, lr: 1.52e-04
2022-05-29 12:47:02,941 INFO [train.py:842] (3/4) Epoch 36, batch 6450, loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02964, over 7250.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2602, pruned_loss=0.04073, over 1423003.13 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:47:42,446 INFO [train.py:842] (3/4) Epoch 36, batch 6500, loss[loss=0.1515, simple_loss=0.2467, pruned_loss=0.02821, over 7165.00 frames.], tot_loss[loss=0.1704, simple_loss=0.26, pruned_loss=0.04044, over 1422341.80 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:48:21,606 INFO [train.py:842] (3/4) Epoch 36, batch 6550, loss[loss=0.1545, simple_loss=0.2543, pruned_loss=0.02733, over 7139.00 frames.], tot_loss[loss=0.1726, simple_loss=0.262, pruned_loss=0.04161, over 1421263.15 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:49:01,363 INFO [train.py:842] (3/4) Epoch 36, batch 6600, loss[loss=0.1489, simple_loss=0.2426, pruned_loss=0.0276, over 7158.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2618, pruned_loss=0.04134, over 1422322.05 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:49:40,678 INFO [train.py:842] (3/4) Epoch 36, batch 6650, loss[loss=0.1677, simple_loss=0.2629, pruned_loss=0.03622, over 6854.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2625, pruned_loss=0.04212, over 1423880.26 frames.], batch size: 31, lr: 1.52e-04
2022-05-29 12:50:20,361 INFO [train.py:842] (3/4) Epoch 36, batch 6700, loss[loss=0.1648, simple_loss=0.2657, pruned_loss=0.03201, over 7235.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2623, pruned_loss=0.04201, over 1425640.25 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:50:59,336 INFO [train.py:842] (3/4) Epoch 36, batch 6750, loss[loss=0.1342, simple_loss=0.2364, pruned_loss=0.01606, over 7349.00 frames.], tot_loss[loss=0.1738, simple_loss=0.263, pruned_loss=0.04229, over 1419758.16 frames.], batch size: 22, lr: 1.52e-04
2022-05-29 12:51:38,819 INFO [train.py:842] (3/4) Epoch 36, batch 6800, loss[loss=0.1647, simple_loss=0.2487, pruned_loss=0.04034, over 7361.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2632, pruned_loss=0.04198, over 1424236.35 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:52:18,244 INFO [train.py:842] (3/4) Epoch 36, batch 6850, loss[loss=0.2017, simple_loss=0.2944, pruned_loss=0.05445, over 7083.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2631, pruned_loss=0.04221, over 1424212.83 frames.], batch size: 28, lr: 1.52e-04
2022-05-29 12:52:57,980 INFO [train.py:842] (3/4) Epoch 36, batch 6900, loss[loss=0.1951, simple_loss=0.2894, pruned_loss=0.05043, over 7433.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2628, pruned_loss=0.04207, over 1425957.87 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:53:37,213 INFO [train.py:842] (3/4) Epoch 36, batch 6950, loss[loss=0.1542, simple_loss=0.2506, pruned_loss=0.02893, over 7223.00 frames.], tot_loss[loss=0.173, simple_loss=0.2627, pruned_loss=0.04161, over 1427689.19 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:54:16,985 INFO [train.py:842] (3/4) Epoch 36, batch 7000, loss[loss=0.1966, simple_loss=0.2776, pruned_loss=0.0578, over 7435.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2624, pruned_loss=0.04165, over 1429586.79 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:54:56,290 INFO [train.py:842] (3/4) Epoch 36, batch 7050, loss[loss=0.1704, simple_loss=0.2536, pruned_loss=0.0436, over 7419.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2626, pruned_loss=0.0421, over 1426340.69 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 12:55:36,073 INFO [train.py:842] (3/4) Epoch 36, batch 7100, loss[loss=0.2176, simple_loss=0.31, pruned_loss=0.06262, over 7270.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2611, pruned_loss=0.04177, over 1427528.60 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 12:56:15,259 INFO [train.py:842] (3/4) Epoch 36, batch 7150, loss[loss=0.1763, simple_loss=0.2622, pruned_loss=0.04515, over 7304.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2619, pruned_loss=0.04185, over 1430837.81 frames.], batch size: 24, lr: 1.52e-04
2022-05-29 12:56:54,971 INFO [train.py:842] (3/4) Epoch 36, batch 7200, loss[loss=0.153, simple_loss=0.2438, pruned_loss=0.03111, over 7297.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2604, pruned_loss=0.04144, over 1428508.60 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 12:57:34,362 INFO [train.py:842] (3/4) Epoch 36, batch 7250, loss[loss=0.1574, simple_loss=0.2474, pruned_loss=0.03365, over 7176.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2607, pruned_loss=0.04154, over 1427569.10 frames.], batch size: 26, lr: 1.52e-04
2022-05-29 12:58:13,741 INFO [train.py:842] (3/4) Epoch 36, batch 7300, loss[loss=0.1881, simple_loss=0.2806, pruned_loss=0.0478, over 7161.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.04128, over 1425573.18 frames.], batch size: 28, lr: 1.52e-04
2022-05-29 12:58:52,911 INFO [train.py:842] (3/4) Epoch 36, batch 7350, loss[loss=0.1626, simple_loss=0.25, pruned_loss=0.03759, over 7256.00 frames.], tot_loss[loss=0.173, simple_loss=0.2624, pruned_loss=0.04183, over 1426359.82 frames.], batch size: 16, lr: 1.52e-04
2022-05-29 12:59:32,494 INFO [train.py:842] (3/4) Epoch 36, batch 7400, loss[loss=0.1503, simple_loss=0.2369, pruned_loss=0.03189, over 7422.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04109, over 1424151.15 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:00:11,793 INFO [train.py:842] (3/4) Epoch 36, batch 7450, loss[loss=0.1287, simple_loss=0.2061, pruned_loss=0.02559, over 7406.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2607, pruned_loss=0.04131, over 1421498.91 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 13:00:51,490 INFO [train.py:842] (3/4) Epoch 36, batch 7500, loss[loss=0.1795, simple_loss=0.2564, pruned_loss=0.05128, over 7153.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2609, pruned_loss=0.0417, over 1424430.59 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 13:01:30,833 INFO [train.py:842] (3/4) Epoch 36, batch 7550, loss[loss=0.2066, simple_loss=0.3012, pruned_loss=0.05594, over 7227.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2605, pruned_loss=0.04126, over 1424451.48 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:02:10,493 INFO [train.py:842] (3/4) Epoch 36, batch 7600, loss[loss=0.1228, simple_loss=0.2062, pruned_loss=0.01965, over 7282.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2613, pruned_loss=0.04148, over 1421236.80 frames.], batch size: 17, lr: 1.52e-04
2022-05-29 13:02:49,614 INFO [train.py:842] (3/4) Epoch 36, batch 7650, loss[loss=0.226, simple_loss=0.312, pruned_loss=0.07004, over 7363.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2621, pruned_loss=0.04176, over 1419898.86 frames.], batch size: 23, lr: 1.52e-04
2022-05-29 13:03:29,309 INFO [train.py:842] (3/4) Epoch 36, batch 7700, loss[loss=0.1744, simple_loss=0.2758, pruned_loss=0.0365, over 7227.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2606, pruned_loss=0.04105, over 1424351.56 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:04:08,596 INFO [train.py:842] (3/4) Epoch 36, batch 7750, loss[loss=0.1472, simple_loss=0.2405, pruned_loss=0.02693, over 7163.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2611, pruned_loss=0.04153, over 1425106.24 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 13:04:48,285 INFO [train.py:842] (3/4) Epoch 36, batch 7800, loss[loss=0.1688, simple_loss=0.2572, pruned_loss=0.04019, over 7436.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2606, pruned_loss=0.04131, over 1424729.10 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:05:27,430 INFO [train.py:842] (3/4) Epoch 36, batch 7850, loss[loss=0.1762, simple_loss=0.2722, pruned_loss=0.04006, over 7415.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2603, pruned_loss=0.04092, over 1426875.16 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:06:06,999 INFO [train.py:842] (3/4) Epoch 36, batch 7900, loss[loss=0.1316, simple_loss=0.222, pruned_loss=0.02066, over 7061.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2595, pruned_loss=0.04054, over 1426880.84 frames.], batch size: 18, lr: 1.52e-04
2022-05-29 13:06:46,360 INFO [train.py:842] (3/4) Epoch 36, batch 7950, loss[loss=0.1713, simple_loss=0.273, pruned_loss=0.03483, over 7087.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2605, pruned_loss=0.041, over 1426185.03 frames.], batch size: 28, lr: 1.52e-04
2022-05-29 13:07:25,889 INFO [train.py:842] (3/4) Epoch 36, batch 8000, loss[loss=0.163, simple_loss=0.2675, pruned_loss=0.02927, over 7314.00 frames.], tot_loss[loss=0.172, simple_loss=0.2611, pruned_loss=0.04144, over 1425892.64 frames.], batch size: 24, lr: 1.52e-04
2022-05-29 13:08:05,187 INFO [train.py:842] (3/4) Epoch 36, batch 8050, loss[loss=0.1705, simple_loss=0.2682, pruned_loss=0.03642, over 6781.00 frames.], tot_loss[loss=0.171, simple_loss=0.2602, pruned_loss=0.04092, over 1424000.25 frames.], batch size: 31, lr: 1.52e-04
2022-05-29 13:08:44,860 INFO [train.py:842] (3/4) Epoch 36, batch 8100, loss[loss=0.1663, simple_loss=0.2498, pruned_loss=0.04138, over 7363.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04105, over 1423493.77 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 13:09:24,172 INFO [train.py:842] (3/4) Epoch 36, batch 8150, loss[loss=0.191, simple_loss=0.286, pruned_loss=0.04801, over 7290.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04112, over 1424615.84 frames.], batch size: 25, lr: 1.52e-04
2022-05-29 13:10:03,994 INFO [train.py:842] (3/4) Epoch 36, batch 8200, loss[loss=0.1833, simple_loss=0.27, pruned_loss=0.04831, over 7200.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2612, pruned_loss=0.04176, over 1428481.82 frames.], batch size: 26, lr: 1.52e-04
2022-05-29 13:10:43,083 INFO [train.py:842] (3/4) Epoch 36, batch 8250, loss[loss=0.2015, simple_loss=0.2933, pruned_loss=0.05486, over 7228.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2616, pruned_loss=0.0417, over 1425572.58 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:11:22,816 INFO [train.py:842] (3/4) Epoch 36, batch 8300, loss[loss=0.171, simple_loss=0.253, pruned_loss=0.04456, over 7143.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2614, pruned_loss=0.04172, over 1418624.67 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:12:02,065 INFO [train.py:842] (3/4) Epoch 36, batch 8350, loss[loss=0.1473, simple_loss=0.2434, pruned_loss=0.02562, over 7307.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2625, pruned_loss=0.0421, over 1419134.03 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:12:41,467 INFO [train.py:842] (3/4) Epoch 36, batch 8400, loss[loss=0.1423, simple_loss=0.2303, pruned_loss=0.02712, over 7003.00 frames.], tot_loss[loss=0.1719, simple_loss=0.261, pruned_loss=0.04137, over 1419445.89 frames.], batch size: 16, lr: 1.52e-04
2022-05-29 13:13:20,658 INFO [train.py:842] (3/4) Epoch 36, batch 8450, loss[loss=0.1938, simple_loss=0.2689, pruned_loss=0.05932, over 5137.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2603, pruned_loss=0.04125, over 1419170.49 frames.], batch size: 52, lr: 1.52e-04
2022-05-29 13:14:00,539 INFO [train.py:842] (3/4) Epoch 36, batch 8500, loss[loss=0.1788, simple_loss=0.2646, pruned_loss=0.04646, over 7143.00 frames.], tot_loss[loss=0.1714, simple_loss=0.26, pruned_loss=0.04139, over 1418631.12 frames.], batch size: 17, lr: 1.52e-04
2022-05-29 13:14:39,943 INFO [train.py:842] (3/4) Epoch 36, batch 8550, loss[loss=0.1634, simple_loss=0.2559, pruned_loss=0.03539, over 7235.00 frames.], tot_loss[loss=0.1712, simple_loss=0.26, pruned_loss=0.04117, over 1416964.39 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:15:19,728 INFO [train.py:842] (3/4) Epoch 36, batch 8600, loss[loss=0.2283, simple_loss=0.3161, pruned_loss=0.0703, over 7211.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2602, pruned_loss=0.04102, over 1413409.54 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:15:59,163 INFO [train.py:842] (3/4) Epoch 36, batch 8650, loss[loss=0.345, simple_loss=0.3945, pruned_loss=0.1477, over 5112.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2603, pruned_loss=0.04107, over 1413587.25 frames.], batch size: 52, lr: 1.52e-04
2022-05-29 13:16:38,732 INFO [train.py:842] (3/4) Epoch 36, batch 8700, loss[loss=0.1633, simple_loss=0.271, pruned_loss=0.0278, over 6464.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2603, pruned_loss=0.04062, over 1411191.25 frames.], batch size: 38, lr: 1.52e-04
2022-05-29 13:17:17,994 INFO [train.py:842] (3/4) Epoch 36, batch 8750, loss[loss=0.1725, simple_loss=0.2591, pruned_loss=0.04296, over 7237.00 frames.], tot_loss[loss=0.173, simple_loss=0.2622, pruned_loss=0.04195, over 1412202.89 frames.], batch size: 20, lr: 1.52e-04
2022-05-29 13:17:57,597 INFO [train.py:842] (3/4) Epoch 36, batch 8800, loss[loss=0.1755, simple_loss=0.2785, pruned_loss=0.03628, over 7217.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2615, pruned_loss=0.04137, over 1412142.83 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:18:36,668 INFO [train.py:842] (3/4) Epoch 36, batch 8850, loss[loss=0.1798, simple_loss=0.2663, pruned_loss=0.04665, over 5139.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2604, pruned_loss=0.04117, over 1397371.30 frames.], batch size: 52, lr: 1.52e-04
2022-05-29 13:19:16,423 INFO [train.py:842] (3/4) Epoch 36, batch 8900, loss[loss=0.193, simple_loss=0.2782, pruned_loss=0.05385, over 5060.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04138, over 1398357.67 frames.], batch size: 52, lr: 1.52e-04
2022-05-29 13:19:55,424 INFO [train.py:842] (3/4) Epoch 36, batch 8950, loss[loss=0.1864, simple_loss=0.2806, pruned_loss=0.04607, over 7317.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04118, over 1392964.64 frames.], batch size: 21, lr: 1.52e-04
2022-05-29 13:20:34,580 INFO [train.py:842] (3/4) Epoch 36, batch 9000, loss[loss=0.1786, simple_loss=0.2693, pruned_loss=0.04398, over 7270.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2601, pruned_loss=0.04109, over 1385038.78 frames.], batch size: 19, lr: 1.52e-04
2022-05-29 13:20:34,581 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 13:20:44,416 INFO [train.py:871] (3/4) Epoch 36, validation: loss=0.1634, simple_loss=0.2603, pruned_loss=0.03321, over 868885.00 frames.
2022-05-29 13:21:23,709 INFO [train.py:842] (3/4) Epoch 36, batch 9050, loss[loss=0.1583, simple_loss=0.238, pruned_loss=0.0393, over 6993.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2591, pruned_loss=0.04079, over 1385505.10 frames.], batch size: 16, lr: 1.52e-04
2022-05-29 13:22:03,044 INFO [train.py:842] (3/4) Epoch 36, batch 9100, loss[loss=0.1745, simple_loss=0.2712, pruned_loss=0.03894, over 4854.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2589, pruned_loss=0.04075, over 1371131.21 frames.], batch size: 52, lr: 1.52e-04
2022-05-29 13:22:41,486 INFO [train.py:842] (3/4) Epoch 36, batch 9150, loss[loss=0.2218, simple_loss=0.309, pruned_loss=0.06731, over 5279.00 frames.], tot_loss[loss=0.1727, simple_loss=0.261, pruned_loss=0.04223, over 1320553.02 frames.], batch size: 53, lr: 1.52e-04
2022-05-29 13:23:33,552 INFO [train.py:842] (3/4) Epoch 37, batch 0, loss[loss=0.2244, simple_loss=0.3103, pruned_loss=0.06919, over 7328.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3103, pruned_loss=0.06919, over 7328.00 frames.], batch size: 22, lr: 1.50e-04
2022-05-29 13:24:13,143 INFO [train.py:842] (3/4) Epoch 37, batch 50, loss[loss=0.1533, simple_loss=0.2413, pruned_loss=0.03268, over 7059.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2598, pruned_loss=0.03976, over 321464.48 frames.], batch size: 18, lr: 1.50e-04
2022-05-29 13:24:52,832 INFO [train.py:842] (3/4) Epoch 37, batch 100, loss[loss=0.1718, simple_loss=0.2618, pruned_loss=0.0409, over 7326.00 frames.], tot_loss[loss=0.17, simple_loss=0.2591, pruned_loss=0.04046, over 566824.32 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:25:32,067 INFO [train.py:842] (3/4) Epoch 37, batch 150, loss[loss=0.1868, simple_loss=0.2828, pruned_loss=0.04534, over 7074.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2614, pruned_loss=0.04162, over 754694.49 frames.], batch size: 28, lr: 1.49e-04
2022-05-29 13:26:11,461 INFO [train.py:842] (3/4) Epoch 37, batch 200, loss[loss=0.1662, simple_loss=0.2574, pruned_loss=0.03752, over 7318.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2637, pruned_loss=0.04253, over 906023.65 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 13:26:50,735 INFO [train.py:842] (3/4) Epoch 37, batch 250, loss[loss=0.1642, simple_loss=0.2633, pruned_loss=0.03256, over 7266.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2623, pruned_loss=0.04161, over 1017034.57 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:27:30,276 INFO [train.py:842] (3/4) Epoch 37, batch 300, loss[loss=0.1689, simple_loss=0.2614, pruned_loss=0.03823, over 7330.00 frames.], tot_loss[loss=0.1727, simple_loss=0.262, pruned_loss=0.04171, over 1103638.56 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 13:28:09,428 INFO [train.py:842] (3/4) Epoch 37, batch 350, loss[loss=0.1748, simple_loss=0.2613, pruned_loss=0.04409, over 7163.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2629, pruned_loss=0.04227, over 1172395.88 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 13:28:49,104 INFO [train.py:842] (3/4) Epoch 37, batch 400, loss[loss=0.1944, simple_loss=0.2907, pruned_loss=0.04907, over 7233.00 frames.], tot_loss[loss=0.1735, simple_loss=0.263, pruned_loss=0.04204, over 1231730.29 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:29:28,318 INFO [train.py:842] (3/4) Epoch 37, batch 450, loss[loss=0.1505, simple_loss=0.2466, pruned_loss=0.02713, over 7150.00 frames.], tot_loss[loss=0.173, simple_loss=0.2626, pruned_loss=0.04169, over 1276476.42 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:30:07,662 INFO [train.py:842] (3/4) Epoch 37, batch 500, loss[loss=0.156, simple_loss=0.2481, pruned_loss=0.03196, over 7236.00 frames.], tot_loss[loss=0.1733, simple_loss=0.263, pruned_loss=0.04185, over 1306294.65 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:30:46,590 INFO [train.py:842] (3/4) Epoch 37, batch 550, loss[loss=0.172, simple_loss=0.2569, pruned_loss=0.04361, over 7061.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2631, pruned_loss=0.04204, over 1322415.59 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 13:31:26,454 INFO [train.py:842] (3/4) Epoch 37, batch 600, loss[loss=0.1673, simple_loss=0.254, pruned_loss=0.04028, over 7407.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2607, pruned_loss=0.04087, over 1347837.98 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:32:06,323 INFO [train.py:842] (3/4) Epoch 37, batch 650, loss[loss=0.1412, simple_loss=0.223, pruned_loss=0.02964, over 7140.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2598, pruned_loss=0.04091, over 1366938.96 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 13:32:45,851 INFO [train.py:842] (3/4) Epoch 37, batch 700, loss[loss=0.1545, simple_loss=0.2543, pruned_loss=0.02738, over 7238.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2606, pruned_loss=0.04084, over 1380052.96 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:33:25,175 INFO [train.py:842] (3/4) Epoch 37, batch 750, loss[loss=0.1756, simple_loss=0.2685, pruned_loss=0.04132, over 7153.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2606, pruned_loss=0.04037, over 1388765.39 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:34:04,878 INFO [train.py:842] (3/4) Epoch 37, batch 800, loss[loss=0.1485, simple_loss=0.2377, pruned_loss=0.02962, over 7428.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2604, pruned_loss=0.04047, over 1398461.57 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 13:34:43,822 INFO [train.py:842] (3/4) Epoch 37, batch 850, loss[loss=0.1452, simple_loss=0.2388, pruned_loss=0.0258, over 7257.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2607, pruned_loss=0.04071, over 1397412.25 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:35:23,653 INFO [train.py:842] (3/4) Epoch 37, batch 900, loss[loss=0.1516, simple_loss=0.2331, pruned_loss=0.03505, over 7073.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2602, pruned_loss=0.04048, over 1406698.34 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 13:36:02,982 INFO [train.py:842] (3/4) Epoch 37, batch 950, loss[loss=0.1878, simple_loss=0.2683, pruned_loss=0.0536, over 7280.00 frames.], tot_loss[loss=0.171, simple_loss=0.2606, pruned_loss=0.04073, over 1410441.25 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 13:36:42,591 INFO [train.py:842] (3/4) Epoch 37, batch 1000, loss[loss=0.1551, simple_loss=0.2541, pruned_loss=0.02804, over 6708.00 frames.], tot_loss[loss=0.1701, simple_loss=0.26, pruned_loss=0.04009, over 1412532.53 frames.], batch size: 31, lr: 1.49e-04
2022-05-29 13:37:22,112 INFO [train.py:842] (3/4) Epoch 37, batch 1050, loss[loss=0.1893, simple_loss=0.2721, pruned_loss=0.05323, over 7378.00 frames.], tot_loss[loss=0.17, simple_loss=0.2596, pruned_loss=0.04022, over 1416353.63 frames.], batch size: 23, lr: 1.49e-04
2022-05-29 13:38:01,745 INFO [train.py:842] (3/4) Epoch 37, batch 1100, loss[loss=0.1642, simple_loss=0.2664, pruned_loss=0.03099, over 7210.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2598, pruned_loss=0.04047, over 1417744.97 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 13:38:41,081 INFO [train.py:842] (3/4) Epoch 37, batch 1150, loss[loss=0.2617, simple_loss=0.3448, pruned_loss=0.0893, over 5060.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04124, over 1417562.80 frames.], batch size: 52, lr: 1.49e-04
2022-05-29 13:39:20,633 INFO [train.py:842] (3/4) Epoch 37, batch 1200, loss[loss=0.1687, simple_loss=0.2619, pruned_loss=0.03781, over 7133.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2607, pruned_loss=0.04093, over 1419006.74 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:39:59,665 INFO [train.py:842] (3/4) Epoch 37, batch 1250, loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04124, over 7206.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2622, pruned_loss=0.04179, over 1419136.75 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 13:40:39,211 INFO [train.py:842] (3/4) Epoch 37, batch 1300, loss[loss=0.1562, simple_loss=0.2357, pruned_loss=0.03832, over 7157.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2617, pruned_loss=0.04161, over 1421892.32 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 13:41:18,361 INFO [train.py:842] (3/4) Epoch 37, batch 1350, loss[loss=0.1392, simple_loss=0.2268, pruned_loss=0.02586, over 7449.00 frames.], tot_loss[loss=0.172, simple_loss=0.2609, pruned_loss=0.04152, over 1418568.54 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:41:58,019 INFO [train.py:842] (3/4) Epoch 37, batch 1400, loss[loss=0.1587, simple_loss=0.2457, pruned_loss=0.03586, over 7007.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04108, over 1418878.17 frames.], batch size: 16, lr: 1.49e-04
2022-05-29 13:42:37,204 INFO [train.py:842] (3/4) Epoch 37, batch 1450, loss[loss=0.1655, simple_loss=0.2581, pruned_loss=0.03651, over 7326.00 frames.], tot_loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.04136, over 1419893.35 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 13:43:16,542 INFO [train.py:842] (3/4) Epoch 37, batch 1500, loss[loss=0.1708, simple_loss=0.2688, pruned_loss=0.03638, over 7318.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2628, pruned_loss=0.04236, over 1416916.55 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 13:43:55,712 INFO [train.py:842] (3/4) Epoch 37, batch 1550, loss[loss=0.1609, simple_loss=0.2538, pruned_loss=0.03403, over 6800.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2621, pruned_loss=0.04232, over 1411501.86 frames.], batch size: 31, lr: 1.49e-04
2022-05-29 13:44:35,497 INFO [train.py:842] (3/4) Epoch 37, batch 1600, loss[loss=0.1947, simple_loss=0.284, pruned_loss=0.05275, over 7395.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2627, pruned_loss=0.04297, over 1411276.61 frames.], batch size: 23, lr: 1.49e-04
2022-05-29 13:45:14,789 INFO [train.py:842] (3/4) Epoch 37, batch 1650, loss[loss=0.1859, simple_loss=0.2785, pruned_loss=0.04661, over 7200.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04262, over 1414777.56 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 13:45:53,949 INFO [train.py:842] (3/4) Epoch 37, batch 1700, loss[loss=0.1796, simple_loss=0.2724, pruned_loss=0.0434, over 7163.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2626, pruned_loss=0.04226, over 1413413.52 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:46:43,585 INFO [train.py:842] (3/4) Epoch 37, batch 1750, loss[loss=0.139, simple_loss=0.2236, pruned_loss=0.02721, over 7363.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2616, pruned_loss=0.04205, over 1407980.54 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:47:22,943 INFO [train.py:842] (3/4) Epoch 37, batch 1800, loss[loss=0.1784, simple_loss=0.2678, pruned_loss=0.04446, over 7304.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2625, pruned_loss=0.0421, over 1410621.07 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 13:48:02,135 INFO [train.py:842] (3/4) Epoch 37, batch 1850, loss[loss=0.1736, simple_loss=0.2551, pruned_loss=0.04603, over 7264.00 frames.], tot_loss[loss=0.1709, simple_loss=0.26, pruned_loss=0.04093, over 1411791.43 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:48:41,601 INFO [train.py:842] (3/4) Epoch 37, batch 1900, loss[loss=0.1978, simple_loss=0.2895, pruned_loss=0.05306, over 6816.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2608, pruned_loss=0.04092, over 1418296.29 frames.], batch size: 31, lr: 1.49e-04
2022-05-29 13:49:20,990 INFO [train.py:842] (3/4) Epoch 37, batch 1950, loss[loss=0.1841, simple_loss=0.2747, pruned_loss=0.04673, over 7215.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2596, pruned_loss=0.0401, over 1421411.57 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 13:50:00,418 INFO [train.py:842] (3/4) Epoch 37, batch 2000, loss[loss=0.1575, simple_loss=0.256, pruned_loss=0.02952, over 7408.00 frames.], tot_loss[loss=0.17, simple_loss=0.2598, pruned_loss=0.04007, over 1419465.52 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 13:50:39,839 INFO [train.py:842] (3/4) Epoch 37, batch 2050, loss[loss=0.1671, simple_loss=0.259, pruned_loss=0.0376, over 7235.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2591, pruned_loss=0.03987, over 1421601.44 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:51:19,304 INFO [train.py:842] (3/4) Epoch 37, batch 2100, loss[loss=0.1723, simple_loss=0.2641, pruned_loss=0.04023, over 7139.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2598, pruned_loss=0.04053, over 1421492.51 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:51:58,350 INFO [train.py:842] (3/4) Epoch 37, batch 2150, loss[loss=0.1436, simple_loss=0.2474, pruned_loss=0.01987, over 7421.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2607, pruned_loss=0.04082, over 1419739.52 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 13:52:37,796 INFO [train.py:842] (3/4) Epoch 37, batch 2200, loss[loss=0.1571, simple_loss=0.2492, pruned_loss=0.03249, over 7257.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2601, pruned_loss=0.04052, over 1420717.63 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:53:16,127 INFO [train.py:842] (3/4) Epoch 37, batch 2250, loss[loss=0.1866, simple_loss=0.2728, pruned_loss=0.05022, over 7149.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2611, pruned_loss=0.04099, over 1421220.00 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 13:53:54,637 INFO [train.py:842] (3/4) Epoch 37, batch 2300, loss[loss=0.1596, simple_loss=0.2539, pruned_loss=0.03269, over 7210.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2603, pruned_loss=0.04059, over 1420564.69 frames.], batch size: 23, lr: 1.49e-04
2022-05-29 13:54:32,873 INFO [train.py:842] (3/4) Epoch 37, batch 2350, loss[loss=0.1379, simple_loss=0.2269, pruned_loss=0.02448, over 7240.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2607, pruned_loss=0.04051, over 1413922.92 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 13:55:11,706 INFO [train.py:842] (3/4) Epoch 37, batch 2400, loss[loss=0.1829, simple_loss=0.2792, pruned_loss=0.04335, over 7298.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2597, pruned_loss=0.04062, over 1420375.55 frames.], batch size: 25, lr: 1.49e-04
2022-05-29 13:55:50,277 INFO [train.py:842] (3/4) Epoch 37, batch 2450, loss[loss=0.2051, simple_loss=0.2921, pruned_loss=0.05901, over 7164.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2591, pruned_loss=0.04008, over 1425889.58 frames.], batch size: 26, lr: 1.49e-04
2022-05-29 13:56:28,826 INFO [train.py:842] (3/4) Epoch 37, batch 2500, loss[loss=0.1845, simple_loss=0.2715, pruned_loss=0.04874, over 7160.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2589, pruned_loss=0.03979, over 1428081.69 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 13:57:07,138 INFO [train.py:842] (3/4) Epoch 37, batch 2550, loss[loss=0.1728, simple_loss=0.2623, pruned_loss=0.04167, over 7277.00 frames.], tot_loss[loss=0.169, simple_loss=0.2585, pruned_loss=0.03977, over 1428226.87 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 13:57:45,689 INFO [train.py:842] (3/4) Epoch 37, batch 2600, loss[loss=0.1567, simple_loss=0.2319, pruned_loss=0.04079, over 6802.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2588, pruned_loss=0.04001, over 1424742.36 frames.], batch size: 15, lr: 1.49e-04
2022-05-29 13:58:24,129 INFO [train.py:842] (3/4) Epoch 37, batch 2650, loss[loss=0.2015, simple_loss=0.2886, pruned_loss=0.05719, over 7205.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2605, pruned_loss=0.04085, over 1428007.25 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 13:59:02,658 INFO [train.py:842] (3/4) Epoch 37, batch 2700, loss[loss=0.1934, simple_loss=0.2944, pruned_loss=0.04621, over 6668.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2609, pruned_loss=0.04093, over 1424589.75 frames.], batch size: 38, lr: 1.49e-04
2022-05-29 13:59:40,788 INFO [train.py:842] (3/4) Epoch 37, batch 2750, loss[loss=0.2487, simple_loss=0.3193, pruned_loss=0.08901, over 5036.00 frames.], tot_loss[loss=0.173, simple_loss=0.2624, pruned_loss=0.04184, over 1425003.57 frames.], batch size: 53, lr: 1.49e-04
2022-05-29 14:00:19,748 INFO [train.py:842] (3/4) Epoch 37, batch 2800, loss[loss=0.1258, simple_loss=0.2123, pruned_loss=0.01967, over 7276.00 frames.], tot_loss[loss=0.172, simple_loss=0.2614, pruned_loss=0.04132, over 1429437.23 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 14:00:58,252 INFO [train.py:842] (3/4) Epoch 37, batch 2850, loss[loss=0.1376, simple_loss=0.232, pruned_loss=0.0216, over 6350.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04114, over 1427814.83 frames.], batch size: 37, lr: 1.49e-04
2022-05-29 14:01:37,129 INFO [train.py:842] (3/4) Epoch 37, batch 2900, loss[loss=0.1533, simple_loss=0.2355, pruned_loss=0.03559, over 6998.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2597, pruned_loss=0.04032, over 1428302.18 frames.], batch size: 16, lr: 1.49e-04
2022-05-29 14:02:15,631 INFO [train.py:842] (3/4) Epoch 37, batch 2950, loss[loss=0.1444, simple_loss=0.2407, pruned_loss=0.02408, over 7430.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2597, pruned_loss=0.04058, over 1424795.05 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 14:02:54,137 INFO [train.py:842] (3/4) Epoch 37, batch 3000, loss[loss=0.1815, simple_loss=0.2749, pruned_loss=0.04408, over 7217.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2599, pruned_loss=0.04066, over 1421326.67 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 14:02:54,138 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 14:03:03,497 INFO [train.py:871] (3/4) Epoch 37, validation: loss=0.1648, simple_loss=0.2616, pruned_loss=0.03398, over 868885.00 frames.
2022-05-29 14:03:41,920 INFO [train.py:842] (3/4) Epoch 37, batch 3050, loss[loss=0.184, simple_loss=0.2592, pruned_loss=0.05446, over 7220.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2601, pruned_loss=0.04105, over 1420900.28 frames.], batch size: 16, lr: 1.49e-04
2022-05-29 14:04:20,737 INFO [train.py:842] (3/4) Epoch 37, batch 3100, loss[loss=0.1757, simple_loss=0.2519, pruned_loss=0.0498, over 7070.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2605, pruned_loss=0.04129, over 1418906.42 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 14:04:59,183 INFO [train.py:842] (3/4) Epoch 37, batch 3150, loss[loss=0.1788, simple_loss=0.2502, pruned_loss=0.05364, over 6986.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2609, pruned_loss=0.04184, over 1417930.01 frames.], batch size: 16, lr: 1.49e-04
2022-05-29 14:05:37,827 INFO [train.py:842] (3/4) Epoch 37, batch 3200, loss[loss=0.3311, simple_loss=0.3759, pruned_loss=0.1432, over 5252.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2612, pruned_loss=0.04185, over 1418704.90 frames.], batch size: 52, lr: 1.49e-04
2022-05-29 14:06:16,122 INFO [train.py:842] (3/4) Epoch 37, batch 3250, loss[loss=0.1946, simple_loss=0.2786, pruned_loss=0.05527, over 7208.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2615, pruned_loss=0.04211, over 1418551.19 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 14:06:54,709 INFO [train.py:842] (3/4) Epoch 37, batch 3300, loss[loss=0.1577, simple_loss=0.2526, pruned_loss=0.03139, over 7410.00 frames.], tot_loss[loss=0.172, simple_loss=0.2613, pruned_loss=0.04142, over 1416003.17 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 14:07:32,803 INFO [train.py:842] (3/4) Epoch 37, batch 3350, loss[loss=0.1434, simple_loss=0.2354, pruned_loss=0.02567, over 7386.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2625, pruned_loss=0.04181, over 1412063.33 frames.], batch size: 23, lr: 1.49e-04
2022-05-29 14:08:11,597 INFO [train.py:842] (3/4) Epoch 37, batch 3400, loss[loss=0.2248, simple_loss=0.2986, pruned_loss=0.07553, over 7139.00 frames.], tot_loss[loss=0.1737, simple_loss=0.263, pruned_loss=0.04215, over 1416231.80 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 14:08:50,149 INFO [train.py:842] (3/4) Epoch 37, batch 3450, loss[loss=0.1205, simple_loss=0.2055, pruned_loss=0.01776, over 7296.00 frames.], tot_loss[loss=0.1717, simple_loss=0.261, pruned_loss=0.04123, over 1420107.75 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 14:09:28,742 INFO [train.py:842] (3/4) Epoch 37, batch 3500, loss[loss=0.1981, simple_loss=0.2796, pruned_loss=0.05833, over 7358.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2606, pruned_loss=0.0408, over 1418597.18 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 14:10:06,959 INFO [train.py:842] (3/4) Epoch 37, batch 3550, loss[loss=0.1447, simple_loss=0.2322, pruned_loss=0.02862, over 6813.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2606, pruned_loss=0.04056, over 1415823.31 frames.], batch size: 15, lr: 1.49e-04
2022-05-29 14:10:45,923 INFO [train.py:842] (3/4) Epoch 37, batch 3600, loss[loss=0.1561, simple_loss=0.2341, pruned_loss=0.03901, over 7021.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2589, pruned_loss=0.03989, over 1422041.37 frames.], batch size: 16, lr: 1.49e-04
2022-05-29 14:11:24,123 INFO [train.py:842] (3/4) Epoch 37, batch 3650, loss[loss=0.1445, simple_loss=0.2339, pruned_loss=0.02759, over 7170.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2599, pruned_loss=0.04047, over 1424177.70 frames.], batch size: 19, lr: 1.49e-04
2022-05-29 14:12:02,925 INFO [train.py:842] (3/4) Epoch 37, batch 3700, loss[loss=0.1662, simple_loss=0.2636, pruned_loss=0.03437, over 7234.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2594, pruned_loss=0.04003, over 1427602.45 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 14:12:41,215 INFO [train.py:842] (3/4) Epoch 37, batch 3750, loss[loss=0.172, simple_loss=0.2622, pruned_loss=0.0409, over 7298.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2602, pruned_loss=0.04021, over 1424008.79 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 14:13:20,012 INFO [train.py:842] (3/4) Epoch 37, batch 3800, loss[loss=0.1281, simple_loss=0.212, pruned_loss=0.02209, over 7288.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2594, pruned_loss=0.04006, over 1426347.52 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 14:13:58,269 INFO [train.py:842] (3/4) Epoch 37, batch 3850, loss[loss=0.1955, simple_loss=0.2733, pruned_loss=0.05883, over 4943.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2605, pruned_loss=0.04102, over 1424342.64 frames.], batch size: 53, lr: 1.49e-04
2022-05-29 14:14:37,044 INFO [train.py:842] (3/4) Epoch 37, batch 3900, loss[loss=0.1636, simple_loss=0.2525, pruned_loss=0.03737, over 7333.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2605, pruned_loss=0.04114, over 1425861.44 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 14:15:15,728 INFO [train.py:842] (3/4) Epoch 37, batch 3950, loss[loss=0.1482, simple_loss=0.2323, pruned_loss=0.03203, over 7269.00 frames.], tot_loss[loss=0.1712, simple_loss=0.26, pruned_loss=0.04123, over 1427119.88 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 14:15:54,294 INFO [train.py:842] (3/4) Epoch 37, batch 4000, loss[loss=0.1839, simple_loss=0.2759, pruned_loss=0.04593, over 7067.00 frames.], tot_loss[loss=0.172, simple_loss=0.2607, pruned_loss=0.0416, over 1427271.55 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 14:16:32,616 INFO [train.py:842] (3/4) Epoch 37, batch 4050, loss[loss=0.1732, simple_loss=0.2492, pruned_loss=0.04858, over 7276.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2611, pruned_loss=0.0414, over 1428586.20 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 14:17:11,141 INFO [train.py:842] (3/4) Epoch 37, batch 4100, loss[loss=0.1675, simple_loss=0.2628, pruned_loss=0.03611, over 7115.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2608, pruned_loss=0.04086, over 1424870.93 frames.], batch size: 21, lr: 1.49e-04
2022-05-29 14:17:49,543 INFO [train.py:842] (3/4) Epoch 37, batch 4150, loss[loss=0.1676, simple_loss=0.2632, pruned_loss=0.036, over 7301.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2599, pruned_loss=0.04056, over 1424794.55 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 14:18:28,600 INFO [train.py:842] (3/4) Epoch 37, batch 4200, loss[loss=0.1477, simple_loss=0.2325, pruned_loss=0.03141, over 7277.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2591, pruned_loss=0.0403, over 1427912.31 frames.], batch size: 17, lr: 1.49e-04
2022-05-29 14:19:06,944 INFO [train.py:842] (3/4) Epoch 37, batch 4250, loss[loss=0.175, simple_loss=0.2677, pruned_loss=0.04118, over 7218.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2598, pruned_loss=0.04084, over 1427872.91 frames.], batch size: 20, lr: 1.49e-04
2022-05-29 14:19:45,858 INFO [train.py:842] (3/4) Epoch 37, batch 4300, loss[loss=0.1981, simple_loss=0.2587, pruned_loss=0.06881, over 7417.00 frames.], tot_loss[loss=0.1711, simple_loss=0.26, pruned_loss=0.0411, over 1430482.88 frames.], batch size: 18, lr: 1.49e-04
2022-05-29 14:20:24,427 INFO [train.py:842] (3/4) Epoch 37, batch 4350, loss[loss=0.1645, simple_loss=0.2661, pruned_loss=0.03143, over 7051.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2597, pruned_loss=0.0409, over 1428412.16 frames.], batch size: 28, lr: 1.49e-04
2022-05-29 14:21:03,037 INFO [train.py:842] (3/4) Epoch 37, batch 4400, loss[loss=0.1969, simple_loss=0.2962, pruned_loss=0.04884, over 7345.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2612, pruned_loss=0.04164, over 1427009.50 frames.], batch size: 22, lr: 1.49e-04
2022-05-29 14:21:41,591 INFO [train.py:842] (3/4) Epoch 37, batch 4450, loss[loss=0.1761, simple_loss=0.2646, pruned_loss=0.04384, over 7109.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2606, pruned_loss=0.04158, over 1429900.92 frames.], batch size: 28, lr: 1.49e-04
2022-05-29 14:22:20,387 INFO [train.py:842] (3/4) Epoch 37, batch 4500, loss[loss=0.2347, simple_loss=0.32, pruned_loss=0.07465, over 7305.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2602, pruned_loss=0.0417, over 1427067.17 frames.], batch size: 24, lr: 1.49e-04
2022-05-29 14:22:58,727 INFO [train.py:842] (3/4) Epoch 37, batch 4550, loss[loss=0.1966, simple_loss=0.2922, pruned_loss=0.05045, over 7293.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2608, pruned_loss=0.04206, over 1426208.64 frames.], batch size: 25, lr: 1.48e-04
2022-05-29 14:23:37,643 INFO [train.py:842] (3/4) Epoch 37, batch 4600, loss[loss=0.1478, simple_loss=0.2303, pruned_loss=0.03264, over 7173.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2614, pruned_loss=0.04209, over 1424366.56 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:24:16,129 INFO [train.py:842] (3/4) Epoch 37, batch 4650, loss[loss=0.1701, simple_loss=0.2539, pruned_loss=0.04313, over 7145.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2603, pruned_loss=0.04152, over 1425506.48 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:24:54,777 INFO [train.py:842] (3/4) Epoch 37, batch 4700, loss[loss=0.1692, simple_loss=0.2611, pruned_loss=0.03866, over 6662.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2599, pruned_loss=0.04111, over 1423898.24 frames.], batch size: 31, lr: 1.48e-04
2022-05-29 14:25:33,372 INFO [train.py:842] (3/4) Epoch 37, batch 4750, loss[loss=0.1738, simple_loss=0.2651, pruned_loss=0.04131, over 7230.00 frames.], tot_loss[loss=0.1713, simple_loss=0.26, pruned_loss=0.04128, over 1427062.93 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:26:11,879 INFO [train.py:842] (3/4) Epoch 37, batch 4800, loss[loss=0.1982, simple_loss=0.2943, pruned_loss=0.05107, over 7165.00 frames.], tot_loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.04156, over 1425346.53 frames.], batch size: 26, lr: 1.48e-04
2022-05-29 14:26:50,422 INFO [train.py:842] (3/4) Epoch 37, batch 4850, loss[loss=0.2017, simple_loss=0.2927, pruned_loss=0.05532, over 7118.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2615, pruned_loss=0.04204, over 1430132.24 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:27:29,129 INFO [train.py:842] (3/4) Epoch 37, batch 4900, loss[loss=0.129, simple_loss=0.2115, pruned_loss=0.02323, over 7209.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2619, pruned_loss=0.04198, over 1432878.41 frames.], batch size: 16, lr: 1.48e-04
2022-05-29 14:28:07,582 INFO [train.py:842] (3/4) Epoch 37, batch 4950, loss[loss=0.1609, simple_loss=0.2535, pruned_loss=0.03419, over 7407.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04199, over 1434784.57 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:28:46,393 INFO [train.py:842] (3/4) Epoch 37, batch 5000, loss[loss=0.1492, simple_loss=0.2277, pruned_loss=0.0354, over 7275.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2608, pruned_loss=0.04174, over 1431138.77 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 14:29:24,656 INFO [train.py:842] (3/4) Epoch 37, batch 5050, loss[loss=0.1574, simple_loss=0.2477, pruned_loss=0.03353, over 7056.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04209, over 1427196.45 frames.], batch size: 28, lr: 1.48e-04
2022-05-29 14:30:06,289 INFO [train.py:842] (3/4) Epoch 37, batch 5100, loss[loss=0.1786, simple_loss=0.2644, pruned_loss=0.04641, over 7225.00 frames.], tot_loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.04158, over 1420927.12 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:30:44,614 INFO [train.py:842] (3/4) Epoch 37, batch 5150, loss[loss=0.1562, simple_loss=0.2557, pruned_loss=0.02835, over 7089.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2617, pruned_loss=0.04148, over 1420060.53 frames.], batch size: 28, lr: 1.48e-04
2022-05-29 14:31:23,412 INFO [train.py:842] (3/4) Epoch 37, batch 5200, loss[loss=0.1729, simple_loss=0.2584, pruned_loss=0.0437, over 7275.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2604, pruned_loss=0.04085, over 1422173.24 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:32:01,741 INFO [train.py:842] (3/4) Epoch 37, batch 5250, loss[loss=0.1253, simple_loss=0.2185, pruned_loss=0.01599, over 6794.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2595, pruned_loss=0.03993, over 1423375.65 frames.], batch size: 15, lr: 1.48e-04
2022-05-29 14:32:40,361 INFO [train.py:842] (3/4) Epoch 37, batch 5300, loss[loss=0.1604, simple_loss=0.2573, pruned_loss=0.03177, over 7322.00 frames.], tot_loss[loss=0.171, simple_loss=0.2607, pruned_loss=0.04068, over 1426683.78 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:33:18,734 INFO [train.py:842] (3/4) Epoch 37, batch 5350, loss[loss=0.1858, simple_loss=0.2896, pruned_loss=0.04103, over 7335.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2603, pruned_loss=0.04006, over 1427803.77 frames.], batch size: 22, lr: 1.48e-04
2022-05-29 14:33:57,372 INFO [train.py:842] (3/4) Epoch 37, batch 5400, loss[loss=0.1807, simple_loss=0.2673, pruned_loss=0.04704, over 7285.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2611, pruned_loss=0.04095, over 1424928.14 frames.], batch size: 25, lr: 1.48e-04
2022-05-29 14:34:35,838 INFO [train.py:842] (3/4) Epoch 37, batch 5450, loss[loss=0.1679, simple_loss=0.2708, pruned_loss=0.03255, over 7387.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04095, over 1426041.07 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 14:35:14,229 INFO [train.py:842] (3/4) Epoch 37, batch 5500, loss[loss=0.1974, simple_loss=0.2768, pruned_loss=0.05896, over 7242.00 frames.], tot_loss[loss=0.1719, simple_loss=0.261, pruned_loss=0.04142, over 1421761.69 frames.], batch size: 19, lr: 1.48e-04
2022-05-29 14:35:52,479 INFO [train.py:842] (3/4) Epoch 37, batch 5550, loss[loss=0.1819, simple_loss=0.2772, pruned_loss=0.04329, over 7205.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2616, pruned_loss=0.04171, over 1419022.52 frames.], batch size: 22, lr: 1.48e-04
2022-05-29 14:36:31,233 INFO [train.py:842] (3/4) Epoch 37, batch 5600, loss[loss=0.1903, simple_loss=0.285, pruned_loss=0.04786, over 7055.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04116, over 1419239.35 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:37:09,322 INFO [train.py:842] (3/4) Epoch 37, batch 5650, loss[loss=0.1881, simple_loss=0.2778, pruned_loss=0.04917, over 7318.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2617, pruned_loss=0.04133, over 1416187.21 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:37:47,976 INFO [train.py:842] (3/4) Epoch 37, batch 5700, loss[loss=0.2249, simple_loss=0.3076, pruned_loss=0.0711, over 7153.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2617, pruned_loss=0.04123, over 1417284.30 frames.], batch size: 19, lr: 1.48e-04
2022-05-29 14:38:26,361 INFO [train.py:842] (3/4) Epoch 37, batch 5750, loss[loss=0.1345, simple_loss=0.2265, pruned_loss=0.02123, over 7269.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2611, pruned_loss=0.04117, over 1417741.84 frames.], batch size: 19, lr: 1.48e-04
2022-05-29 14:39:04,967 INFO [train.py:842] (3/4) Epoch 37, batch 5800, loss[loss=0.1643, simple_loss=0.2692, pruned_loss=0.02973, over 7419.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2629, pruned_loss=0.04179, over 1419593.20 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:39:43,224 INFO [train.py:842] (3/4) Epoch 37, batch 5850, loss[loss=0.1676, simple_loss=0.2639, pruned_loss=0.03564, over 7079.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2629, pruned_loss=0.04192, over 1420339.75 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:40:22,000 INFO [train.py:842] (3/4) Epoch 37, batch 5900, loss[loss=0.1833, simple_loss=0.2795, pruned_loss=0.04358, over 7155.00 frames.], tot_loss[loss=0.172, simple_loss=0.2614, pruned_loss=0.04131, over 1422243.12 frames.], batch size: 26, lr: 1.48e-04
2022-05-29 14:41:00,168 INFO [train.py:842] (3/4) Epoch 37, batch 5950, loss[loss=0.1693, simple_loss=0.2592, pruned_loss=0.03974, over 7065.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2622, pruned_loss=0.04145, over 1421255.26 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:41:39,113 INFO [train.py:842] (3/4) Epoch 37, batch 6000, loss[loss=0.1582, simple_loss=0.2448, pruned_loss=0.03577, over 7421.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2608, pruned_loss=0.04103, over 1424450.83 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:41:39,114 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 14:41:48,826 INFO [train.py:871] (3/4) Epoch 37, validation: loss=0.1649, simple_loss=0.2613, pruned_loss=0.03429, over 868885.00 frames.
2022-05-29 14:42:27,126 INFO [train.py:842] (3/4) Epoch 37, batch 6050, loss[loss=0.1882, simple_loss=0.2638, pruned_loss=0.05629, over 7321.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2617, pruned_loss=0.04164, over 1422884.07 frames.], batch size: 25, lr: 1.48e-04
2022-05-29 14:43:05,756 INFO [train.py:842] (3/4) Epoch 37, batch 6100, loss[loss=0.1408, simple_loss=0.2334, pruned_loss=0.02412, over 7319.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2621, pruned_loss=0.04166, over 1424101.28 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:43:43,963 INFO [train.py:842] (3/4) Epoch 37, batch 6150, loss[loss=0.1434, simple_loss=0.2177, pruned_loss=0.03451, over 7013.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2623, pruned_loss=0.04173, over 1419277.30 frames.], batch size: 16, lr: 1.48e-04
2022-05-29 14:44:22,783 INFO [train.py:842] (3/4) Epoch 37, batch 6200, loss[loss=0.1925, simple_loss=0.2783, pruned_loss=0.05332, over 7074.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2623, pruned_loss=0.04178, over 1417427.19 frames.], batch size: 28, lr: 1.48e-04
2022-05-29 14:45:01,306 INFO [train.py:842] (3/4) Epoch 37, batch 6250, loss[loss=0.1731, simple_loss=0.2484, pruned_loss=0.04889, over 7149.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2613, pruned_loss=0.04152, over 1421373.88 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 14:45:40,237 INFO [train.py:842] (3/4) Epoch 37, batch 6300, loss[loss=0.1409, simple_loss=0.223, pruned_loss=0.02942, over 6995.00 frames.], tot_loss[loss=0.171, simple_loss=0.2597, pruned_loss=0.04115, over 1422333.18 frames.], batch size: 16, lr: 1.48e-04
2022-05-29 14:46:18,706 INFO [train.py:842] (3/4) Epoch 37, batch 6350, loss[loss=0.1874, simple_loss=0.2777, pruned_loss=0.04851, over 7180.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2584, pruned_loss=0.04066, over 1423851.54 frames.], batch size: 26, lr: 1.48e-04
2022-05-29 14:46:57,205 INFO [train.py:842] (3/4) Epoch 37, batch 6400, loss[loss=0.1567, simple_loss=0.254, pruned_loss=0.02972, over 7322.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04003, over 1421970.21 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:47:35,899 INFO [train.py:842] (3/4) Epoch 37, batch 6450, loss[loss=0.1592, simple_loss=0.257, pruned_loss=0.03068, over 6520.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2586, pruned_loss=0.04041, over 1423250.30 frames.], batch size: 38, lr: 1.48e-04
2022-05-29 14:48:14,952 INFO [train.py:842] (3/4) Epoch 37, batch 6500, loss[loss=0.1594, simple_loss=0.2534, pruned_loss=0.03275, over 7140.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04005, over 1426708.90 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:48:53,199 INFO [train.py:842] (3/4) Epoch 37, batch 6550, loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03288, over 7307.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2598, pruned_loss=0.04081, over 1422145.82 frames.], batch size: 24, lr: 1.48e-04
2022-05-29 14:49:31,832 INFO [train.py:842] (3/4) Epoch 37, batch 6600, loss[loss=0.1948, simple_loss=0.2848, pruned_loss=0.05235, over 7375.00 frames.], tot_loss[loss=0.171, simple_loss=0.2598, pruned_loss=0.04112, over 1419315.44 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 14:50:10,227 INFO [train.py:842] (3/4) Epoch 37, batch 6650, loss[loss=0.1882, simple_loss=0.2871, pruned_loss=0.04464, over 7122.00 frames.], tot_loss[loss=0.171, simple_loss=0.26, pruned_loss=0.04102, over 1416650.97 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:50:48,914 INFO [train.py:842] (3/4) Epoch 37, batch 6700, loss[loss=0.2899, simple_loss=0.3444, pruned_loss=0.1177, over 7148.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2613, pruned_loss=0.04173, over 1416055.40 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:51:27,551 INFO [train.py:842] (3/4) Epoch 37, batch 6750, loss[loss=0.1975, simple_loss=0.2826, pruned_loss=0.05616, over 7419.00 frames.], tot_loss[loss=0.1711, simple_loss=0.26, pruned_loss=0.04114, over 1419739.15 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:52:06,470 INFO [train.py:842] (3/4) Epoch 37, batch 6800, loss[loss=0.1743, simple_loss=0.2717, pruned_loss=0.03846, over 7224.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2598, pruned_loss=0.04067, over 1423343.36 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 14:52:44,814 INFO [train.py:842] (3/4) Epoch 37, batch 6850, loss[loss=0.1784, simple_loss=0.2709, pruned_loss=0.04295, over 7200.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2594, pruned_loss=0.0408, over 1416548.80 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 14:53:23,553 INFO [train.py:842] (3/4) Epoch 37, batch 6900, loss[loss=0.1801, simple_loss=0.2711, pruned_loss=0.04457, over 7231.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2592, pruned_loss=0.04061, over 1420290.02 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:54:01,944 INFO [train.py:842] (3/4) Epoch 37, batch 6950, loss[loss=0.1488, simple_loss=0.2367, pruned_loss=0.03041, over 7364.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2594, pruned_loss=0.04062, over 1420903.37 frames.], batch size: 19, lr: 1.48e-04
2022-05-29 14:54:40,638 INFO [train.py:842] (3/4) Epoch 37, batch 7000, loss[loss=0.1782, simple_loss=0.2782, pruned_loss=0.03909, over 7374.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2593, pruned_loss=0.04088, over 1420048.08 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 14:55:19,147 INFO [train.py:842] (3/4) Epoch 37, batch 7050, loss[loss=0.1632, simple_loss=0.255, pruned_loss=0.03573, over 7221.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2591, pruned_loss=0.04081, over 1420355.46 frames.], batch size: 22, lr: 1.48e-04
2022-05-29 14:55:57,887 INFO [train.py:842] (3/4) Epoch 37, batch 7100, loss[loss=0.1989, simple_loss=0.2822, pruned_loss=0.05786, over 7386.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2591, pruned_loss=0.04071, over 1416094.01 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 14:56:36,271 INFO [train.py:842] (3/4) Epoch 37, batch 7150, loss[loss=0.1713, simple_loss=0.2671, pruned_loss=0.03772, over 6518.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2594, pruned_loss=0.04082, over 1418803.35 frames.], batch size: 38, lr: 1.48e-04
2022-05-29 14:57:14,673 INFO [train.py:842] (3/4) Epoch 37, batch 7200, loss[loss=0.1748, simple_loss=0.2593, pruned_loss=0.04514, over 7291.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04102, over 1415273.83 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 14:58:03,051 INFO [train.py:842] (3/4) Epoch 37, batch 7250, loss[loss=0.2301, simple_loss=0.3151, pruned_loss=0.07259, over 6263.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2599, pruned_loss=0.04074, over 1411481.34 frames.], batch size: 37, lr: 1.48e-04
2022-05-29 14:58:41,382 INFO [train.py:842] (3/4) Epoch 37, batch 7300, loss[loss=0.2114, simple_loss=0.3039, pruned_loss=0.05951, over 7140.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2613, pruned_loss=0.0416, over 1406359.64 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:59:20,073 INFO [train.py:842] (3/4) Epoch 37, batch 7350, loss[loss=0.1981, simple_loss=0.2882, pruned_loss=0.05401, over 7425.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2614, pruned_loss=0.04153, over 1415059.50 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 14:59:58,584 INFO [train.py:842] (3/4) Epoch 37, batch 7400, loss[loss=0.1733, simple_loss=0.2713, pruned_loss=0.03761, over 7206.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2613, pruned_loss=0.04169, over 1411585.62 frames.], batch size: 22, lr: 1.48e-04
2022-05-29 15:00:37,095 INFO [train.py:842] (3/4) Epoch 37, batch 7450, loss[loss=0.212, simple_loss=0.3034, pruned_loss=0.0603, over 7174.00 frames.], tot_loss[loss=0.1718, simple_loss=0.261, pruned_loss=0.04129, over 1415569.37 frames.], batch size: 26, lr: 1.48e-04
2022-05-29 15:01:15,784 INFO [train.py:842] (3/4) Epoch 37, batch 7500, loss[loss=0.153, simple_loss=0.2611, pruned_loss=0.02244, over 7409.00 frames.], tot_loss[loss=0.1717, simple_loss=0.261, pruned_loss=0.04114, over 1417063.86 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:01:54,106 INFO [train.py:842] (3/4) Epoch 37, batch 7550, loss[loss=0.1912, simple_loss=0.2888, pruned_loss=0.04679, over 6837.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2617, pruned_loss=0.04171, over 1420008.61 frames.], batch size: 31, lr: 1.48e-04
2022-05-29 15:02:32,833 INFO [train.py:842] (3/4) Epoch 37, batch 7600, loss[loss=0.1788, simple_loss=0.265, pruned_loss=0.04631, over 4876.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2624, pruned_loss=0.0421, over 1417054.84 frames.], batch size: 52, lr: 1.48e-04
2022-05-29 15:03:20,995 INFO [train.py:842] (3/4) Epoch 37, batch 7650, loss[loss=0.1511, simple_loss=0.2414, pruned_loss=0.03041, over 7419.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2624, pruned_loss=0.04169, over 1422614.72 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:04:09,736 INFO [train.py:842] (3/4) Epoch 37, batch 7700, loss[loss=0.1718, simple_loss=0.2626, pruned_loss=0.04043, over 7192.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2614, pruned_loss=0.04089, over 1423834.17 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 15:04:48,016 INFO [train.py:842] (3/4) Epoch 37, batch 7750, loss[loss=0.139, simple_loss=0.2302, pruned_loss=0.02392, over 6758.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2606, pruned_loss=0.04059, over 1423987.82 frames.], batch size: 15, lr: 1.48e-04
2022-05-29 15:05:26,773 INFO [train.py:842] (3/4) Epoch 37, batch 7800, loss[loss=0.1983, simple_loss=0.2841, pruned_loss=0.05625, over 7329.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2615, pruned_loss=0.0412, over 1424675.41 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:06:05,355 INFO [train.py:842] (3/4) Epoch 37, batch 7850, loss[loss=0.1647, simple_loss=0.2673, pruned_loss=0.03102, over 6251.00 frames.], tot_loss[loss=0.17, simple_loss=0.2596, pruned_loss=0.04018, over 1428983.41 frames.], batch size: 37, lr: 1.48e-04
2022-05-29 15:06:44,248 INFO [train.py:842] (3/4) Epoch 37, batch 7900, loss[loss=0.1511, simple_loss=0.2381, pruned_loss=0.03206, over 7352.00 frames.], tot_loss[loss=0.169, simple_loss=0.2585, pruned_loss=0.03974, over 1431754.12 frames.], batch size: 19, lr: 1.48e-04
2022-05-29 15:07:22,865 INFO [train.py:842] (3/4) Epoch 37, batch 7950, loss[loss=0.2396, simple_loss=0.3242, pruned_loss=0.07753, over 7314.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2589, pruned_loss=0.03969, over 1433134.13 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:08:01,515 INFO [train.py:842] (3/4) Epoch 37, batch 8000, loss[loss=0.1649, simple_loss=0.2435, pruned_loss=0.04311, over 7441.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2588, pruned_loss=0.03999, over 1426641.55 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 15:08:39,696 INFO [train.py:842] (3/4) Epoch 37, batch 8050, loss[loss=0.207, simple_loss=0.2936, pruned_loss=0.06016, over 7142.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2588, pruned_loss=0.03997, over 1424512.91 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:09:18,472 INFO [train.py:842] (3/4) Epoch 37, batch 8100, loss[loss=0.1439, simple_loss=0.2392, pruned_loss=0.02431, over 7317.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2589, pruned_loss=0.03972, over 1425625.07 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:09:56,853 INFO [train.py:842] (3/4) Epoch 37, batch 8150, loss[loss=0.1642, simple_loss=0.2475, pruned_loss=0.0405, over 7303.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2597, pruned_loss=0.04034, over 1417873.80 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:10:35,184 INFO [train.py:842] (3/4) Epoch 37, batch 8200, loss[loss=0.1506, simple_loss=0.2483, pruned_loss=0.02643, over 7144.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2597, pruned_loss=0.03993, over 1418964.04 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:11:13,496 INFO [train.py:842] (3/4) Epoch 37, batch 8250, loss[loss=0.1945, simple_loss=0.287, pruned_loss=0.051, over 7304.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.0406, over 1419549.90 frames.], batch size: 24, lr: 1.48e-04
2022-05-29 15:11:51,976 INFO [train.py:842] (3/4) Epoch 37, batch 8300, loss[loss=0.1853, simple_loss=0.2846, pruned_loss=0.04301, over 7185.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2623, pruned_loss=0.04147, over 1417485.40 frames.], batch size: 23, lr: 1.48e-04
2022-05-29 15:12:30,170 INFO [train.py:842] (3/4) Epoch 37, batch 8350, loss[loss=0.2057, simple_loss=0.3037, pruned_loss=0.05392, over 7336.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2635, pruned_loss=0.04171, over 1420193.19 frames.], batch size: 22, lr: 1.48e-04
2022-05-29 15:13:09,203 INFO [train.py:842] (3/4) Epoch 37, batch 8400, loss[loss=0.1619, simple_loss=0.2381, pruned_loss=0.04286, over 7263.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2626, pruned_loss=0.04179, over 1422032.25 frames.], batch size: 16, lr: 1.48e-04
2022-05-29 15:13:47,734 INFO [train.py:842] (3/4) Epoch 37, batch 8450, loss[loss=0.1633, simple_loss=0.2577, pruned_loss=0.03446, over 7069.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2622, pruned_loss=0.04183, over 1423056.53 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 15:14:26,400 INFO [train.py:842] (3/4) Epoch 37, batch 8500, loss[loss=0.1695, simple_loss=0.25, pruned_loss=0.04445, over 7278.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2617, pruned_loss=0.04126, over 1423551.99 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 15:15:04,519 INFO [train.py:842] (3/4) Epoch 37, batch 8550, loss[loss=0.1974, simple_loss=0.2914, pruned_loss=0.05173, over 7110.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2632, pruned_loss=0.04151, over 1423769.93 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:15:43,244 INFO [train.py:842] (3/4) Epoch 37, batch 8600, loss[loss=0.2178, simple_loss=0.3022, pruned_loss=0.06668, over 7097.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2632, pruned_loss=0.04153, over 1419425.39 frames.], batch size: 28, lr: 1.48e-04
2022-05-29 15:16:21,382 INFO [train.py:842] (3/4) Epoch 37, batch 8650, loss[loss=0.1676, simple_loss=0.2581, pruned_loss=0.03855, over 7431.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2627, pruned_loss=0.04127, over 1418726.46 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:16:59,588 INFO [train.py:842] (3/4) Epoch 37, batch 8700, loss[loss=0.1584, simple_loss=0.2561, pruned_loss=0.03036, over 7436.00 frames.], tot_loss[loss=0.173, simple_loss=0.2629, pruned_loss=0.04152, over 1412908.52 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:17:37,723 INFO [train.py:842] (3/4) Epoch 37, batch 8750, loss[loss=0.1653, simple_loss=0.2553, pruned_loss=0.03767, over 7178.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2641, pruned_loss=0.04227, over 1411949.81 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 15:18:16,308 INFO [train.py:842] (3/4) Epoch 37, batch 8800, loss[loss=0.1576, simple_loss=0.2574, pruned_loss=0.02894, over 7144.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2633, pruned_loss=0.04208, over 1413410.85 frames.], batch size: 20, lr: 1.48e-04
2022-05-29 15:18:54,804 INFO [train.py:842] (3/4) Epoch 37, batch 8850, loss[loss=0.1769, simple_loss=0.2668, pruned_loss=0.0435, over 7287.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2626, pruned_loss=0.04192, over 1412772.93 frames.], batch size: 18, lr: 1.48e-04
2022-05-29 15:19:33,464 INFO [train.py:842] (3/4) Epoch 37, batch 8900, loss[loss=0.1653, simple_loss=0.2605, pruned_loss=0.035, over 6502.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2641, pruned_loss=0.04258, over 1414325.39 frames.], batch size: 38, lr: 1.48e-04
2022-05-29 15:20:11,865 INFO [train.py:842] (3/4) Epoch 37, batch 8950, loss[loss=0.1792, simple_loss=0.2574, pruned_loss=0.05052, over 7146.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2637, pruned_loss=0.04195, over 1413583.50 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 15:20:50,457 INFO [train.py:842] (3/4) Epoch 37, batch 9000, loss[loss=0.15, simple_loss=0.2383, pruned_loss=0.03078, over 7112.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2629, pruned_loss=0.04166, over 1410044.91 frames.], batch size: 21, lr: 1.48e-04
2022-05-29 15:20:50,458 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 15:20:59,818 INFO [train.py:871] (3/4) Epoch 37, validation: loss=0.1648, simple_loss=0.2612, pruned_loss=0.03416, over 868885.00 frames.
2022-05-29 15:21:38,655 INFO [train.py:842] (3/4) Epoch 37, batch 9050, loss[loss=0.1574, simple_loss=0.2446, pruned_loss=0.03506, over 7143.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2598, pruned_loss=0.0412, over 1403549.22 frames.], batch size: 17, lr: 1.48e-04
2022-05-29 15:22:16,589 INFO [train.py:842] (3/4) Epoch 37, batch 9100, loss[loss=0.1844, simple_loss=0.2777, pruned_loss=0.04561, over 6699.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2611, pruned_loss=0.04187, over 1371279.37 frames.], batch size: 38, lr: 1.47e-04
2022-05-29 15:22:53,410 INFO [train.py:842] (3/4) Epoch 37, batch 9150, loss[loss=0.1348, simple_loss=0.2273, pruned_loss=0.02119, over 4711.00 frames.], tot_loss[loss=0.175, simple_loss=0.2638, pruned_loss=0.04316, over 1317453.56 frames.], batch size: 52, lr: 1.47e-04
2022-05-29 15:23:42,240 INFO [train.py:842] (3/4) Epoch 38, batch 0, loss[loss=0.1648, simple_loss=0.2571, pruned_loss=0.03626, over 7357.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2571, pruned_loss=0.03626, over 7357.00 frames.], batch size: 19, lr: 1.46e-04
2022-05-29 15:24:21,099 INFO [train.py:842] (3/4) Epoch 38, batch 50, loss[loss=0.1881, simple_loss=0.2798, pruned_loss=0.04818, over 6464.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2594, pruned_loss=0.04088, over 322205.00 frames.], batch size: 38, lr: 1.46e-04
2022-05-29 15:24:59,388 INFO [train.py:842] (3/4) Epoch 38, batch 100, loss[loss=0.1784, simple_loss=0.2771, pruned_loss=0.03979, over 7254.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2627, pruned_loss=0.04198, over 559946.44 frames.], batch size: 19, lr: 1.46e-04
2022-05-29 15:25:37,984 INFO [train.py:842] (3/4) Epoch 38, batch 150, loss[loss=0.1624, simple_loss=0.26, pruned_loss=0.03241, over 7379.00 frames.], tot_loss[loss=0.172, simple_loss=0.2623, pruned_loss=0.04083, over 747852.11 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 15:26:16,322 INFO [train.py:842] (3/4) Epoch 38, batch 200, loss[loss=0.1631, simple_loss=0.2636, pruned_loss=0.03134, over 7409.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2602, pruned_loss=0.04044, over 896443.26 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 15:26:54,844 INFO [train.py:842] (3/4) Epoch 38, batch 250, loss[loss=0.1629, simple_loss=0.2528, pruned_loss=0.03647, over 7347.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2581, pruned_loss=0.03955, over 1014921.26 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:27:33,121 INFO [train.py:842] (3/4) Epoch 38, batch 300, loss[loss=0.1418, simple_loss=0.2425, pruned_loss=0.02055, over 7240.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2579, pruned_loss=0.03961, over 1105481.39 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:28:11,836 INFO [train.py:842] (3/4) Epoch 38, batch 350, loss[loss=0.1921, simple_loss=0.2756, pruned_loss=0.05432, over 7258.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2585, pruned_loss=0.04, over 1172635.29 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:28:50,328 INFO [train.py:842] (3/4) Epoch 38, batch 400, loss[loss=0.1513, simple_loss=0.2307, pruned_loss=0.03594, over 7273.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2591, pruned_loss=0.04049, over 1232720.40 frames.], batch size: 17, lr: 1.45e-04
2022-05-29 15:29:28,795 INFO [train.py:842] (3/4) Epoch 38, batch 450, loss[loss=0.1591, simple_loss=0.2566, pruned_loss=0.03085, over 7126.00 frames.], tot_loss[loss=0.169, simple_loss=0.2581, pruned_loss=0.04002, over 1276417.58 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 15:30:07,437 INFO [train.py:842] (3/4) Epoch 38, batch 500, loss[loss=0.1627, simple_loss=0.2435, pruned_loss=0.04101, over 7277.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2571, pruned_loss=0.03965, over 1312557.78 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:30:46,040 INFO [train.py:842] (3/4) Epoch 38, batch 550, loss[loss=0.173, simple_loss=0.2613, pruned_loss=0.0423, over 7332.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2577, pruned_loss=0.03933, over 1336550.92 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:31:24,325 INFO [train.py:842] (3/4) Epoch 38, batch 600, loss[loss=0.1746, simple_loss=0.2693, pruned_loss=0.03992, over 7364.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2583, pruned_loss=0.03945, over 1357746.24 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 15:32:03,016 INFO [train.py:842] (3/4) Epoch 38, batch 650, loss[loss=0.1472, simple_loss=0.2464, pruned_loss=0.02402, over 7333.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2593, pruned_loss=0.04019, over 1373525.58 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 15:32:41,279 INFO [train.py:842] (3/4) Epoch 38, batch 700, loss[loss=0.2349, simple_loss=0.297, pruned_loss=0.08636, over 7165.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04109, over 1385881.55 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:33:19,959 INFO [train.py:842] (3/4) Epoch 38, batch 750, loss[loss=0.1759, simple_loss=0.2749, pruned_loss=0.03845, over 7384.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2603, pruned_loss=0.04048, over 1400486.63 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 15:33:58,075 INFO [train.py:842] (3/4) Epoch 38, batch 800, loss[loss=0.1516, simple_loss=0.2327, pruned_loss=0.03521, over 7397.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2608, pruned_loss=0.04027, over 1408090.52 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:34:36,751 INFO [train.py:842] (3/4) Epoch 38, batch 850, loss[loss=0.1688, simple_loss=0.2559, pruned_loss=0.04089, over 7352.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2608, pruned_loss=0.04034, over 1410860.90 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:35:15,006 INFO [train.py:842] (3/4) Epoch 38, batch 900, loss[loss=0.194, simple_loss=0.2911, pruned_loss=0.04849, over 7296.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2604, pruned_loss=0.03999, over 1412602.39 frames.], batch size: 24, lr: 1.45e-04
2022-05-29 15:35:53,549 INFO [train.py:842] (3/4) Epoch 38, batch 950, loss[loss=0.1477, simple_loss=0.2294, pruned_loss=0.03299, over 7261.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2607, pruned_loss=0.04029, over 1417722.43 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:36:31,947 INFO [train.py:842] (3/4) Epoch 38, batch 1000, loss[loss=0.2234, simple_loss=0.3065, pruned_loss=0.07009, over 7203.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2608, pruned_loss=0.04033, over 1420498.12 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 15:37:10,457 INFO [train.py:842] (3/4) Epoch 38, batch 1050, loss[loss=0.1542, simple_loss=0.2465, pruned_loss=0.03099, over 7329.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2613, pruned_loss=0.04057, over 1420501.64 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:37:48,977 INFO [train.py:842] (3/4) Epoch 38, batch 1100, loss[loss=0.1547, simple_loss=0.2394, pruned_loss=0.03499, over 7222.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2622, pruned_loss=0.04133, over 1424053.40 frames.], batch size: 16, lr: 1.45e-04
2022-05-29 15:38:27,636 INFO [train.py:842] (3/4) Epoch 38, batch 1150, loss[loss=0.1409, simple_loss=0.2398, pruned_loss=0.02097, over 7283.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2629, pruned_loss=0.04204, over 1420419.21 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:39:05,898 INFO [train.py:842] (3/4) Epoch 38, batch 1200, loss[loss=0.1623, simple_loss=0.2487, pruned_loss=0.03791, over 7174.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2636, pruned_loss=0.04254, over 1422158.43 frames.], batch size: 26, lr: 1.45e-04
2022-05-29 15:39:44,561 INFO [train.py:842] (3/4) Epoch 38, batch 1250, loss[loss=0.1638, simple_loss=0.2616, pruned_loss=0.033, over 6493.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2632, pruned_loss=0.04215, over 1426093.52 frames.], batch size: 38, lr: 1.45e-04
2022-05-29 15:40:22,863 INFO [train.py:842] (3/4) Epoch 38, batch 1300, loss[loss=0.1307, simple_loss=0.2124, pruned_loss=0.02452, over 7278.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2634, pruned_loss=0.04208, over 1425959.32 frames.], batch size: 17, lr: 1.45e-04
2022-05-29 15:41:01,507 INFO [train.py:842] (3/4) Epoch 38, batch 1350, loss[loss=0.1636, simple_loss=0.2585, pruned_loss=0.03431, over 7118.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2626, pruned_loss=0.04197, over 1419432.81 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 15:41:40,073 INFO [train.py:842] (3/4) Epoch 38, batch 1400, loss[loss=0.1592, simple_loss=0.2435, pruned_loss=0.03744, over 7291.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2611, pruned_loss=0.04171, over 1419835.49 frames.], batch size: 24, lr: 1.45e-04
2022-05-29 15:42:18,713 INFO [train.py:842] (3/4) Epoch 38, batch 1450, loss[loss=0.1645, simple_loss=0.256, pruned_loss=0.03652, over 7199.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04138, over 1424645.80 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 15:42:57,043 INFO [train.py:842] (3/4) Epoch 38, batch 1500, loss[loss=0.1802, simple_loss=0.2693, pruned_loss=0.04558, over 7245.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2601, pruned_loss=0.0407, over 1425253.82 frames.], batch size: 25, lr: 1.45e-04
2022-05-29 15:43:35,789 INFO [train.py:842] (3/4) Epoch 38, batch 1550, loss[loss=0.1779, simple_loss=0.2794, pruned_loss=0.03817, over 7241.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2605, pruned_loss=0.04027, over 1422198.92 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:44:14,290 INFO [train.py:842] (3/4) Epoch 38, batch 1600, loss[loss=0.1653, simple_loss=0.2509, pruned_loss=0.03984, over 7265.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2599, pruned_loss=0.03994, over 1424829.72 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:44:53,036 INFO [train.py:842] (3/4) Epoch 38, batch 1650, loss[loss=0.1563, simple_loss=0.2522, pruned_loss=0.03026, over 7061.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2602, pruned_loss=0.04042, over 1424550.67 frames.], batch size: 28, lr: 1.45e-04
2022-05-29 15:45:31,666 INFO [train.py:842] (3/4) Epoch 38, batch 1700, loss[loss=0.1542, simple_loss=0.2374, pruned_loss=0.03551, over 7175.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2599, pruned_loss=0.04074, over 1423250.93 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:46:10,396 INFO [train.py:842] (3/4) Epoch 38, batch 1750, loss[loss=0.1973, simple_loss=0.2846, pruned_loss=0.05498, over 4933.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04064, over 1422480.65 frames.], batch size: 52, lr: 1.45e-04
2022-05-29 15:46:48,921 INFO [train.py:842] (3/4) Epoch 38, batch 1800, loss[loss=0.1825, simple_loss=0.2733, pruned_loss=0.04586, over 7325.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2607, pruned_loss=0.04126, over 1420116.50 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:47:27,688 INFO [train.py:842] (3/4) Epoch 38, batch 1850, loss[loss=0.1685, simple_loss=0.2472, pruned_loss=0.04492, over 7256.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2611, pruned_loss=0.0414, over 1422183.84 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:48:05,993 INFO [train.py:842] (3/4) Epoch 38, batch 1900, loss[loss=0.1691, simple_loss=0.2481, pruned_loss=0.04504, over 6780.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2612, pruned_loss=0.04083, over 1425562.89 frames.], batch size: 15, lr: 1.45e-04
2022-05-29 15:48:44,642 INFO [train.py:842] (3/4) Epoch 38, batch 1950, loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02862, over 7258.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2617, pruned_loss=0.04075, over 1428200.07 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:49:23,251 INFO [train.py:842] (3/4) Epoch 38, batch 2000, loss[loss=0.1369, simple_loss=0.2184, pruned_loss=0.02769, over 7412.00 frames.], tot_loss[loss=0.1702, simple_loss=0.26, pruned_loss=0.04017, over 1426935.94 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:50:01,710 INFO [train.py:842] (3/4) Epoch 38, batch 2050, loss[loss=0.1309, simple_loss=0.2263, pruned_loss=0.01773, over 7265.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2603, pruned_loss=0.04033, over 1424672.76 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:50:39,902 INFO [train.py:842] (3/4) Epoch 38, batch 2100, loss[loss=0.1735, simple_loss=0.2598, pruned_loss=0.04361, over 7197.00 frames.], tot_loss[loss=0.1712, simple_loss=0.261, pruned_loss=0.04074, over 1418605.56 frames.], batch size: 26, lr: 1.45e-04
2022-05-29 15:51:18,609 INFO [train.py:842] (3/4) Epoch 38, batch 2150, loss[loss=0.126, simple_loss=0.2158, pruned_loss=0.0181, over 7056.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2602, pruned_loss=0.04031, over 1418337.47 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:51:56,336 INFO [train.py:842] (3/4) Epoch 38, batch 2200, loss[loss=0.1419, simple_loss=0.2248, pruned_loss=0.02952, over 7065.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2605, pruned_loss=0.04031, over 1419552.03 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:52:34,385 INFO [train.py:842] (3/4) Epoch 38, batch 2250, loss[loss=0.1762, simple_loss=0.2642, pruned_loss=0.04409, over 6289.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2607, pruned_loss=0.04058, over 1418373.29 frames.], batch size: 37, lr: 1.45e-04
2022-05-29 15:53:12,413 INFO [train.py:842] (3/4) Epoch 38, batch 2300, loss[loss=0.1417, simple_loss=0.2252, pruned_loss=0.02907, over 7072.00 frames.], tot_loss[loss=0.171, simple_loss=0.2609, pruned_loss=0.04056, over 1423044.60 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:53:50,472 INFO [train.py:842] (3/4) Epoch 38, batch 2350, loss[loss=0.1602, simple_loss=0.2677, pruned_loss=0.02629, over 7320.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2609, pruned_loss=0.04058, over 1420568.79 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:54:28,596 INFO [train.py:842] (3/4) Epoch 38, batch 2400, loss[loss=0.1868, simple_loss=0.2733, pruned_loss=0.05014, over 7393.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2611, pruned_loss=0.04089, over 1425423.18 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:55:06,816 INFO [train.py:842] (3/4) Epoch 38, batch 2450, loss[loss=0.1923, simple_loss=0.2845, pruned_loss=0.05001, over 7327.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2615, pruned_loss=0.04108, over 1426842.61 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:55:44,802 INFO [train.py:842] (3/4) Epoch 38, batch 2500, loss[loss=0.1577, simple_loss=0.2477, pruned_loss=0.03383, over 7168.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2609, pruned_loss=0.04075, over 1427220.94 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:56:22,961 INFO [train.py:842] (3/4) Epoch 38, batch 2550, loss[loss=0.1575, simple_loss=0.241, pruned_loss=0.03697, over 7145.00 frames.], tot_loss[loss=0.1714, simple_loss=0.261, pruned_loss=0.04092, over 1424832.96 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 15:57:00,962 INFO [train.py:842] (3/4) Epoch 38, batch 2600, loss[loss=0.1523, simple_loss=0.2514, pruned_loss=0.02666, over 7439.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2605, pruned_loss=0.04041, over 1424611.97 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:57:39,140 INFO [train.py:842] (3/4) Epoch 38, batch 2650, loss[loss=0.1835, simple_loss=0.273, pruned_loss=0.04704, over 7179.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2625, pruned_loss=0.0416, over 1425525.64 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 15:58:17,268 INFO [train.py:842] (3/4) Epoch 38, batch 2700, loss[loss=0.1723, simple_loss=0.2622, pruned_loss=0.04117, over 7233.00 frames.], tot_loss[loss=0.1725, simple_loss=0.262, pruned_loss=0.04143, over 1424264.99 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 15:58:55,524 INFO [train.py:842] (3/4) Epoch 38, batch 2750, loss[loss=0.169, simple_loss=0.2664, pruned_loss=0.03583, over 7359.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2629, pruned_loss=0.04135, over 1426123.25 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 15:59:33,534 INFO [train.py:842] (3/4) Epoch 38, batch 2800, loss[loss=0.1782, simple_loss=0.2675, pruned_loss=0.04445, over 7299.00 frames.], tot_loss[loss=0.173, simple_loss=0.2627, pruned_loss=0.04161, over 1424057.89 frames.], batch size: 24, lr: 1.45e-04
2022-05-29 16:00:11,772 INFO [train.py:842] (3/4) Epoch 38, batch 2850, loss[loss=0.1438, simple_loss=0.2408, pruned_loss=0.02336, over 7418.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2623, pruned_loss=0.04135, over 1424305.44 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 16:00:49,751 INFO [train.py:842] (3/4) Epoch 38, batch 2900, loss[loss=0.1463, simple_loss=0.2316, pruned_loss=0.0305, over 7120.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2606, pruned_loss=0.0409, over 1424632.57 frames.], batch size: 17, lr: 1.45e-04
2022-05-29 16:01:28,082 INFO [train.py:842] (3/4) Epoch 38, batch 2950, loss[loss=0.1733, simple_loss=0.2637, pruned_loss=0.04145, over 7417.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04058, over 1429245.26 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 16:02:05,957 INFO [train.py:842] (3/4) Epoch 38, batch 3000, loss[loss=0.228, simple_loss=0.3187, pruned_loss=0.06867, over 7208.00 frames.], tot_loss[loss=0.172, simple_loss=0.2617, pruned_loss=0.04114, over 1429034.37 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:02:05,958 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 16:02:15,341 INFO [train.py:871] (3/4) Epoch 38, validation: loss=0.1634, simple_loss=0.2602, pruned_loss=0.03326, over 868885.00 frames.
2022-05-29 16:02:53,596 INFO [train.py:842] (3/4) Epoch 38, batch 3050, loss[loss=0.1362, simple_loss=0.2296, pruned_loss=0.02135, over 7158.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2609, pruned_loss=0.04074, over 1428865.20 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 16:03:31,426 INFO [train.py:842] (3/4) Epoch 38, batch 3100, loss[loss=0.1763, simple_loss=0.2608, pruned_loss=0.04596, over 7200.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2609, pruned_loss=0.04105, over 1422086.07 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 16:04:09,675 INFO [train.py:842] (3/4) Epoch 38, batch 3150, loss[loss=0.1611, simple_loss=0.2598, pruned_loss=0.03122, over 7371.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2618, pruned_loss=0.04163, over 1420036.10 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:04:47,700 INFO [train.py:842] (3/4) Epoch 38, batch 3200, loss[loss=0.1581, simple_loss=0.2598, pruned_loss=0.02823, over 7113.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2611, pruned_loss=0.04102, over 1424572.88 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 16:05:26,141 INFO [train.py:842] (3/4) Epoch 38, batch 3250, loss[loss=0.1613, simple_loss=0.237, pruned_loss=0.04283, over 7276.00 frames.], tot_loss[loss=0.1705, simple_loss=0.26, pruned_loss=0.04056, over 1425419.12 frames.], batch size: 18, lr: 1.45e-04
2022-05-29 16:06:04,018 INFO [train.py:842] (3/4) Epoch 38, batch 3300, loss[loss=0.1899, simple_loss=0.2863, pruned_loss=0.04677, over 7240.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2599, pruned_loss=0.04058, over 1425140.31 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:06:41,998 INFO [train.py:842] (3/4) Epoch 38, batch 3350, loss[loss=0.2329, simple_loss=0.3237, pruned_loss=0.07105, over 7207.00 frames.], tot_loss[loss=0.1714, simple_loss=0.261, pruned_loss=0.0409, over 1426162.38 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 16:07:19,991 INFO [train.py:842] (3/4) Epoch 38, batch 3400, loss[loss=0.1723, simple_loss=0.2715, pruned_loss=0.03652, over 6731.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2608, pruned_loss=0.04072, over 1429914.94 frames.], batch size: 31, lr: 1.45e-04
2022-05-29 16:07:58,238 INFO [train.py:842] (3/4) Epoch 38, batch 3450, loss[loss=0.1664, simple_loss=0.2489, pruned_loss=0.04195, over 7436.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2607, pruned_loss=0.04046, over 1431468.82 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:08:36,211 INFO [train.py:842] (3/4) Epoch 38, batch 3500, loss[loss=0.1594, simple_loss=0.2586, pruned_loss=0.03003, over 7231.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2595, pruned_loss=0.03954, over 1430488.79 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:09:14,392 INFO [train.py:842] (3/4) Epoch 38, batch 3550, loss[loss=0.1781, simple_loss=0.2571, pruned_loss=0.04956, over 7138.00 frames.], tot_loss[loss=0.17, simple_loss=0.2603, pruned_loss=0.03982, over 1430627.72 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:09:52,130 INFO [train.py:842] (3/4) Epoch 38, batch 3600, loss[loss=0.2196, simple_loss=0.3115, pruned_loss=0.06386, over 6774.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2607, pruned_loss=0.04004, over 1428615.27 frames.], batch size: 31, lr: 1.45e-04
2022-05-29 16:10:30,410 INFO [train.py:842] (3/4) Epoch 38, batch 3650, loss[loss=0.1772, simple_loss=0.272, pruned_loss=0.0412, over 6957.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2606, pruned_loss=0.03985, over 1430969.41 frames.], batch size: 28, lr: 1.45e-04
2022-05-29 16:11:08,257 INFO [train.py:842] (3/4) Epoch 38, batch 3700, loss[loss=0.1683, simple_loss=0.2729, pruned_loss=0.03183, over 7295.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2603, pruned_loss=0.04, over 1424080.63 frames.], batch size: 24, lr: 1.45e-04
2022-05-29 16:11:46,339 INFO [train.py:842] (3/4) Epoch 38, batch 3750, loss[loss=0.1775, simple_loss=0.2659, pruned_loss=0.0445, over 7159.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2614, pruned_loss=0.04063, over 1419054.50 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 16:12:24,513 INFO [train.py:842] (3/4) Epoch 38, batch 3800, loss[loss=0.1557, simple_loss=0.2505, pruned_loss=0.03051, over 7376.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2613, pruned_loss=0.04097, over 1419459.31 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:13:02,706 INFO [train.py:842] (3/4) Epoch 38, batch 3850, loss[loss=0.1733, simple_loss=0.2662, pruned_loss=0.04025, over 7104.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2606, pruned_loss=0.0406, over 1421234.85 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 16:13:40,947 INFO [train.py:842] (3/4) Epoch 38, batch 3900, loss[loss=0.1458, simple_loss=0.2409, pruned_loss=0.02529, over 7326.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2601, pruned_loss=0.04076, over 1423836.38 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:14:21,832 INFO [train.py:842] (3/4) Epoch 38, batch 3950, loss[loss=0.1659, simple_loss=0.2589, pruned_loss=0.03644, over 6730.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2595, pruned_loss=0.04042, over 1419482.97 frames.], batch size: 31, lr: 1.45e-04
2022-05-29 16:14:59,661 INFO [train.py:842] (3/4) Epoch 38, batch 4000, loss[loss=0.1605, simple_loss=0.2361, pruned_loss=0.04246, over 7152.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2602, pruned_loss=0.04132, over 1419512.11 frames.], batch size: 17, lr: 1.45e-04
2022-05-29 16:15:37,912 INFO [train.py:842] (3/4) Epoch 38, batch 4050, loss[loss=0.1616, simple_loss=0.2401, pruned_loss=0.04148, over 7000.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04096, over 1417146.62 frames.], batch size: 16, lr: 1.45e-04
2022-05-29 16:16:15,911 INFO [train.py:842] (3/4) Epoch 38, batch 4100, loss[loss=0.169, simple_loss=0.2606, pruned_loss=0.03877, over 7150.00 frames.], tot_loss[loss=0.1701, simple_loss=0.259, pruned_loss=0.0406, over 1417992.70 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:16:54,261 INFO [train.py:842] (3/4) Epoch 38, batch 4150, loss[loss=0.1518, simple_loss=0.2329, pruned_loss=0.03537, over 7245.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2589, pruned_loss=0.04064, over 1419861.10 frames.], batch size: 16, lr: 1.45e-04
2022-05-29 16:17:32,190 INFO [train.py:842] (3/4) Epoch 38, batch 4200, loss[loss=0.1889, simple_loss=0.2762, pruned_loss=0.0508, over 7360.00 frames.], tot_loss[loss=0.17, simple_loss=0.2589, pruned_loss=0.04048, over 1419286.20 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 16:18:10,311 INFO [train.py:842] (3/4) Epoch 38, batch 4250, loss[loss=0.223, simple_loss=0.3101, pruned_loss=0.06797, over 7288.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2595, pruned_loss=0.04041, over 1420018.64 frames.], batch size: 24, lr: 1.45e-04
2022-05-29 16:18:57,699 INFO [train.py:842] (3/4) Epoch 38, batch 4300, loss[loss=0.1797, simple_loss=0.2769, pruned_loss=0.04121, over 7332.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2596, pruned_loss=0.04054, over 1423866.12 frames.], batch size: 22, lr: 1.45e-04
2022-05-29 16:19:35,765 INFO [train.py:842] (3/4) Epoch 38, batch 4350, loss[loss=0.1467, simple_loss=0.2323, pruned_loss=0.03055, over 7279.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2599, pruned_loss=0.04044, over 1422970.08 frames.], batch size: 17, lr: 1.45e-04
2022-05-29 16:20:13,808 INFO [train.py:842] (3/4) Epoch 38, batch 4400, loss[loss=0.1733, simple_loss=0.2721, pruned_loss=0.03722, over 7078.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2588, pruned_loss=0.03982, over 1423067.77 frames.], batch size: 28, lr: 1.45e-04
2022-05-29 16:20:52,136 INFO [train.py:842] (3/4) Epoch 38, batch 4450, loss[loss=0.1658, simple_loss=0.258, pruned_loss=0.03679, over 7327.00 frames.], tot_loss[loss=0.169, simple_loss=0.2587, pruned_loss=0.03962, over 1425233.63 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:21:30,249 INFO [train.py:842] (3/4) Epoch 38, batch 4500, loss[loss=0.1367, simple_loss=0.2317, pruned_loss=0.0208, over 7115.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2589, pruned_loss=0.04023, over 1428694.80 frames.], batch size: 21, lr: 1.45e-04
2022-05-29 16:22:08,249 INFO [train.py:842] (3/4) Epoch 38, batch 4550, loss[loss=0.1847, simple_loss=0.2693, pruned_loss=0.05004, over 7259.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2601, pruned_loss=0.04059, over 1430201.29 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 16:22:46,097 INFO [train.py:842] (3/4) Epoch 38, batch 4600, loss[loss=0.1763, simple_loss=0.2742, pruned_loss=0.03923, over 7377.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2593, pruned_loss=0.04023, over 1428441.93 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:23:24,376 INFO [train.py:842] (3/4) Epoch 38, batch 4650, loss[loss=0.1979, simple_loss=0.2777, pruned_loss=0.05909, over 7373.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2592, pruned_loss=0.04024, over 1429933.48 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:24:02,472 INFO [train.py:842] (3/4) Epoch 38, batch 4700, loss[loss=0.1753, simple_loss=0.264, pruned_loss=0.04328, over 7203.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2586, pruned_loss=0.04029, over 1425372.96 frames.], batch size: 23, lr: 1.45e-04
2022-05-29 16:24:40,732 INFO [train.py:842] (3/4) Epoch 38, batch 4750, loss[loss=0.1777, simple_loss=0.2638, pruned_loss=0.04582, over 7162.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2588, pruned_loss=0.04039, over 1422732.11 frames.], batch size: 19, lr: 1.45e-04
2022-05-29 16:25:18,461 INFO [train.py:842] (3/4) Epoch 38, batch 4800, loss[loss=0.1536, simple_loss=0.2536, pruned_loss=0.02678, over 7151.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2602, pruned_loss=0.04107, over 1423413.88 frames.], batch size: 20, lr: 1.45e-04
2022-05-29 16:25:56,657 INFO [train.py:842] (3/4) Epoch 38, batch 4850, loss[loss=0.1984, simple_loss=0.2936, pruned_loss=0.05158, over 7096.00 frames.], tot_loss[loss=0.171, simple_loss=0.26, pruned_loss=0.04097, over 1420796.71 frames.], batch size: 28, lr: 1.44e-04
2022-05-29 16:26:34,242 INFO [train.py:842] (3/4) Epoch 38, batch 4900, loss[loss=0.1688, simple_loss=0.2632, pruned_loss=0.03722, over 7218.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2612, pruned_loss=0.04096, over 1414986.24 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 16:27:12,494 INFO [train.py:842] (3/4) Epoch 38, batch 4950, loss[loss=0.1722, simple_loss=0.2592, pruned_loss=0.04257, over 7066.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2602, pruned_loss=0.04032, over 1418990.95 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:27:50,536 INFO [train.py:842] (3/4) Epoch 38, batch 5000, loss[loss=0.179, simple_loss=0.2731, pruned_loss=0.04242, over 7191.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2596, pruned_loss=0.04037, over 1421982.56 frames.], batch size: 26, lr: 1.44e-04
2022-05-29 16:28:28,907 INFO [train.py:842] (3/4) Epoch 38, batch 5050, loss[loss=0.1764, simple_loss=0.2785, pruned_loss=0.03713, over 6468.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2601, pruned_loss=0.04064, over 1426054.63 frames.], batch size: 38, lr: 1.44e-04
2022-05-29 16:29:07,183 INFO [train.py:842] (3/4) Epoch 38, batch 5100, loss[loss=0.194, simple_loss=0.2795, pruned_loss=0.0543, over 7291.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2583, pruned_loss=0.04029, over 1426839.97 frames.], batch size: 24, lr: 1.44e-04
2022-05-29 16:29:45,467 INFO [train.py:842] (3/4) Epoch 38, batch 5150, loss[loss=0.1852, simple_loss=0.2728, pruned_loss=0.04885, over 7435.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2583, pruned_loss=0.03995, over 1428281.43 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:30:23,537 INFO [train.py:842] (3/4) Epoch 38, batch 5200, loss[loss=0.1571, simple_loss=0.2554, pruned_loss=0.02939, over 7223.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2576, pruned_loss=0.03971, over 1426132.81 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 16:31:01,718 INFO [train.py:842] (3/4) Epoch 38, batch 5250, loss[loss=0.1642, simple_loss=0.2608, pruned_loss=0.0338, over 7324.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2585, pruned_loss=0.04021, over 1423093.42 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:31:39,574 INFO [train.py:842] (3/4) Epoch 38, batch 5300, loss[loss=0.1866, simple_loss=0.269, pruned_loss=0.0521, over 4813.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2585, pruned_loss=0.04044, over 1418381.81 frames.], batch size: 52, lr: 1.44e-04
2022-05-29 16:32:17,627 INFO [train.py:842] (3/4) Epoch 38, batch 5350, loss[loss=0.1606, simple_loss=0.2492, pruned_loss=0.036, over 7302.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2596, pruned_loss=0.04096, over 1412270.66 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:32:55,665 INFO [train.py:842] (3/4) Epoch 38, batch 5400, loss[loss=0.1754, simple_loss=0.2784, pruned_loss=0.03622, over 7339.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2607, pruned_loss=0.04187, over 1416120.88 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 16:33:34,076 INFO [train.py:842] (3/4) Epoch 38, batch 5450, loss[loss=0.1499, simple_loss=0.2542, pruned_loss=0.02282, over 7215.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2599, pruned_loss=0.04123, over 1418174.13 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 16:34:11,850 INFO [train.py:842] (3/4) Epoch 38, batch 5500, loss[loss=0.128, simple_loss=0.2144, pruned_loss=0.02082, over 7423.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2608, pruned_loss=0.04134, over 1419786.04 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:34:50,172 INFO [train.py:842] (3/4) Epoch 38, batch 5550, loss[loss=0.1538, simple_loss=0.2498, pruned_loss=0.02893, over 7330.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2605, pruned_loss=0.04096, over 1419367.70 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:35:27,888 INFO [train.py:842] (3/4) Epoch 38, batch 5600, loss[loss=0.1753, simple_loss=0.2806, pruned_loss=0.03497, over 7320.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.0412, over 1417409.18 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 16:36:06,397 INFO [train.py:842] (3/4) Epoch 38, batch 5650, loss[loss=0.1621, simple_loss=0.241, pruned_loss=0.04158, over 7404.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2596, pruned_loss=0.04058, over 1422651.95 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:36:44,332 INFO [train.py:842] (3/4) Epoch 38, batch 5700, loss[loss=0.1818, simple_loss=0.29, pruned_loss=0.03678, over 7303.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2598, pruned_loss=0.04051, over 1422383.62 frames.], batch size: 24, lr: 1.44e-04
2022-05-29 16:37:22,676 INFO [train.py:842] (3/4) Epoch 38, batch 5750, loss[loss=0.1661, simple_loss=0.25, pruned_loss=0.04103, over 7066.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2603, pruned_loss=0.04038, over 1426398.43 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:38:00,884 INFO [train.py:842] (3/4) Epoch 38, batch 5800, loss[loss=0.1475, simple_loss=0.2348, pruned_loss=0.03007, over 7274.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2589, pruned_loss=0.03979, over 1430000.25 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:38:39,002 INFO [train.py:842] (3/4) Epoch 38, batch 5850, loss[loss=0.1681, simple_loss=0.2574, pruned_loss=0.03942, over 6908.00 frames.], tot_loss[loss=0.1692, simple_loss=0.259, pruned_loss=0.03966, over 1423754.59 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 16:39:16,846 INFO [train.py:842] (3/4) Epoch 38, batch 5900, loss[loss=0.1879, simple_loss=0.2583, pruned_loss=0.0587, over 7202.00 frames.], tot_loss[loss=0.171, simple_loss=0.261, pruned_loss=0.04052, over 1423513.11 frames.], batch size: 16, lr: 1.44e-04
2022-05-29 16:39:55,213 INFO [train.py:842] (3/4) Epoch 38, batch 5950, loss[loss=0.1676, simple_loss=0.2559, pruned_loss=0.03967, over 7294.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2597, pruned_loss=0.04039, over 1423442.51 frames.], batch size: 25, lr: 1.44e-04
2022-05-29 16:40:33,182 INFO [train.py:842] (3/4) Epoch 38, batch 6000, loss[loss=0.2329, simple_loss=0.3108, pruned_loss=0.07752, over 7166.00 frames.], tot_loss[loss=0.1715, simple_loss=0.261, pruned_loss=0.041, over 1421031.66 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:40:33,183 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 16:40:42,179 INFO [train.py:871] (3/4) Epoch 38, validation: loss=0.1638, simple_loss=0.2604, pruned_loss=0.03358, over 868885.00 frames.
2022-05-29 16:41:20,632 INFO [train.py:842] (3/4) Epoch 38, batch 6050, loss[loss=0.1599, simple_loss=0.2527, pruned_loss=0.0335, over 7264.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2603, pruned_loss=0.04046, over 1416783.10 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:41:58,590 INFO [train.py:842] (3/4) Epoch 38, batch 6100, loss[loss=0.1432, simple_loss=0.2349, pruned_loss=0.02573, over 7332.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04059, over 1416818.29 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 16:42:37,003 INFO [train.py:842] (3/4) Epoch 38, batch 6150, loss[loss=0.1845, simple_loss=0.2743, pruned_loss=0.04739, over 6805.00 frames.], tot_loss[loss=0.171, simple_loss=0.2605, pruned_loss=0.04081, over 1418478.36 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 16:43:15,006 INFO [train.py:842] (3/4) Epoch 38, batch 6200, loss[loss=0.2211, simple_loss=0.3113, pruned_loss=0.06547, over 7340.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2606, pruned_loss=0.04061, over 1420257.80 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 16:43:53,229 INFO [train.py:842] (3/4) Epoch 38, batch 6250, loss[loss=0.1589, simple_loss=0.2481, pruned_loss=0.03485, over 7166.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2609, pruned_loss=0.04085, over 1422033.72 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:44:31,157 INFO [train.py:842] (3/4) Epoch 38, batch 6300, loss[loss=0.1679, simple_loss=0.2608, pruned_loss=0.03748, over 7353.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2604, pruned_loss=0.04057, over 1423588.09 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:45:09,395 INFO [train.py:842] (3/4) Epoch 38, batch 6350, loss[loss=0.1803, simple_loss=0.2799, pruned_loss=0.04034, over 7396.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2597, pruned_loss=0.04004, over 1425057.70 frames.], batch size: 23, lr: 1.44e-04
2022-05-29 16:45:47,318 INFO [train.py:842] (3/4) Epoch 38, batch 6400, loss[loss=0.1703, simple_loss=0.2545, pruned_loss=0.04309, over 7256.00 frames.], tot_loss[loss=0.17, simple_loss=0.2599, pruned_loss=0.04002, over 1424139.48 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:46:25,810 INFO [train.py:842] (3/4) Epoch 38, batch 6450, loss[loss=0.1795, simple_loss=0.2729, pruned_loss=0.04304, over 7239.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2576, pruned_loss=0.03916, over 1424749.97 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:47:03,931 INFO [train.py:842] (3/4) Epoch 38, batch 6500, loss[loss=0.1903, simple_loss=0.2934, pruned_loss=0.04367, over 7147.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2581, pruned_loss=0.03936, over 1427520.09 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:47:42,061 INFO [train.py:842] (3/4) Epoch 38, batch 6550, loss[loss=0.1698, simple_loss=0.2617, pruned_loss=0.03894, over 7148.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2583, pruned_loss=0.03932, over 1428310.87 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:48:20,074 INFO [train.py:842] (3/4) Epoch 38, batch 6600, loss[loss=0.1829, simple_loss=0.2793, pruned_loss=0.04326, over 7130.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2587, pruned_loss=0.03991, over 1425073.55 frames.], batch size: 26, lr: 1.44e-04
2022-05-29 16:48:58,338 INFO [train.py:842] (3/4) Epoch 38, batch 6650, loss[loss=0.1677, simple_loss=0.2498, pruned_loss=0.04274, over 7365.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2593, pruned_loss=0.04068, over 1423097.63 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:49:36,291 INFO [train.py:842] (3/4) Epoch 38, batch 6700, loss[loss=0.1723, simple_loss=0.256, pruned_loss=0.04434, over 6828.00 frames.], tot_loss[loss=0.17, simple_loss=0.2592, pruned_loss=0.04043, over 1424172.10 frames.], batch size: 15, lr: 1.44e-04
2022-05-29 16:50:14,385 INFO [train.py:842] (3/4) Epoch 38, batch 6750, loss[loss=0.168, simple_loss=0.2604, pruned_loss=0.03782, over 7180.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2596, pruned_loss=0.04076, over 1418913.50 frames.], batch size: 23, lr: 1.44e-04
2022-05-29 16:50:52,135 INFO [train.py:842] (3/4) Epoch 38, batch 6800, loss[loss=0.1705, simple_loss=0.2616, pruned_loss=0.03966, over 7318.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2608, pruned_loss=0.04115, over 1417585.14 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:51:30,589 INFO [train.py:842] (3/4) Epoch 38, batch 6850, loss[loss=0.1423, simple_loss=0.2212, pruned_loss=0.03166, over 7272.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2605, pruned_loss=0.04056, over 1422198.82 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:52:08,722 INFO [train.py:842] (3/4) Epoch 38, batch 6900, loss[loss=0.1831, simple_loss=0.2718, pruned_loss=0.04717, over 7310.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2602, pruned_loss=0.04061, over 1427726.22 frames.], batch size: 24, lr: 1.44e-04
2022-05-29 16:52:46,982 INFO [train.py:842] (3/4) Epoch 38, batch 6950, loss[loss=0.1723, simple_loss=0.2384, pruned_loss=0.05313, over 7413.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2598, pruned_loss=0.04056, over 1427919.69 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:53:24,875 INFO [train.py:842] (3/4) Epoch 38, batch 7000, loss[loss=0.161, simple_loss=0.2555, pruned_loss=0.03329, over 7055.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2599, pruned_loss=0.04036, over 1428433.29 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:54:03,217 INFO [train.py:842] (3/4) Epoch 38, batch 7050, loss[loss=0.1576, simple_loss=0.2424, pruned_loss=0.0364, over 7368.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2599, pruned_loss=0.0408, over 1428702.05 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 16:54:41,065 INFO [train.py:842] (3/4) Epoch 38, batch 7100, loss[loss=0.1607, simple_loss=0.2647, pruned_loss=0.02837, over 7122.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2602, pruned_loss=0.04085, over 1425094.47 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 16:55:19,348 INFO [train.py:842] (3/4) Epoch 38, batch 7150, loss[loss=0.1548, simple_loss=0.2509, pruned_loss=0.02937, over 6465.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2599, pruned_loss=0.04083, over 1424434.81 frames.], batch size: 38, lr: 1.44e-04
2022-05-29 16:55:57,121 INFO [train.py:842] (3/4) Epoch 38, batch 7200, loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02908, over 7413.00 frames.], tot_loss[loss=0.1696, simple_loss=0.259, pruned_loss=0.04016, over 1424063.65 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 16:56:35,189 INFO [train.py:842] (3/4) Epoch 38, batch 7250, loss[loss=0.1846, simple_loss=0.2787, pruned_loss=0.04526, over 7381.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2597, pruned_loss=0.04026, over 1425293.37 frames.], batch size: 23, lr: 1.44e-04
2022-05-29 16:57:13,245 INFO [train.py:842] (3/4) Epoch 38, batch 7300, loss[loss=0.1286, simple_loss=0.2135, pruned_loss=0.02182, over 7411.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2593, pruned_loss=0.03999, over 1428678.21 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 16:57:51,514 INFO [train.py:842] (3/4) Epoch 38, batch 7350, loss[loss=0.1514, simple_loss=0.2293, pruned_loss=0.03673, over 7009.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2594, pruned_loss=0.04045, over 1430681.35 frames.], batch size: 16, lr: 1.44e-04
2022-05-29 16:58:29,505 INFO [train.py:842] (3/4) Epoch 38, batch 7400, loss[loss=0.1929, simple_loss=0.2845, pruned_loss=0.05067, over 7407.00 frames.], tot_loss[loss=0.1696, simple_loss=0.259, pruned_loss=0.04006, over 1431927.01 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 16:59:07,992 INFO [train.py:842] (3/4) Epoch 38, batch 7450, loss[loss=0.1836, simple_loss=0.2697, pruned_loss=0.04881, over 7048.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2579, pruned_loss=0.03969, over 1435257.86 frames.], batch size: 28, lr: 1.44e-04
2022-05-29 16:59:45,800 INFO [train.py:842] (3/4) Epoch 38, batch 7500, loss[loss=0.1856, simple_loss=0.2796, pruned_loss=0.04581, over 7157.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2576, pruned_loss=0.03924, over 1432092.20 frames.], batch size: 26, lr: 1.44e-04
2022-05-29 17:00:24,000 INFO [train.py:842] (3/4) Epoch 38, batch 7550, loss[loss=0.1936, simple_loss=0.2809, pruned_loss=0.05313, over 6811.00 frames.], tot_loss[loss=0.1688, simple_loss=0.259, pruned_loss=0.03937, over 1431604.70 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 17:01:01,997 INFO [train.py:842] (3/4) Epoch 38, batch 7600, loss[loss=0.1953, simple_loss=0.2836, pruned_loss=0.05345, over 7111.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2584, pruned_loss=0.03918, over 1431800.47 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 17:01:40,333 INFO [train.py:842] (3/4) Epoch 38, batch 7650, loss[loss=0.2128, simple_loss=0.2921, pruned_loss=0.0667, over 7231.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2582, pruned_loss=0.03958, over 1432702.09 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 17:02:18,338 INFO [train.py:842] (3/4) Epoch 38, batch 7700, loss[loss=0.1693, simple_loss=0.2655, pruned_loss=0.03657, over 7295.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.0395, over 1431721.13 frames.], batch size: 24, lr: 1.44e-04
2022-05-29 17:02:56,565 INFO [train.py:842] (3/4) Epoch 38, batch 7750, loss[loss=0.1641, simple_loss=0.2561, pruned_loss=0.03608, over 7213.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2585, pruned_loss=0.03984, over 1430616.64 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 17:03:34,686 INFO [train.py:842] (3/4) Epoch 38, batch 7800, loss[loss=0.1524, simple_loss=0.2516, pruned_loss=0.02664, over 7215.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.03952, over 1428390.62 frames.], batch size: 23, lr: 1.44e-04
2022-05-29 17:04:13,048 INFO [train.py:842] (3/4) Epoch 38, batch 7850, loss[loss=0.184, simple_loss=0.2763, pruned_loss=0.0459, over 6820.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2575, pruned_loss=0.03953, over 1430678.04 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 17:04:51,073 INFO [train.py:842] (3/4) Epoch 38, batch 7900, loss[loss=0.3073, simple_loss=0.3897, pruned_loss=0.1125, over 7167.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04093, over 1428569.79 frames.], batch size: 23, lr: 1.44e-04
2022-05-29 17:05:29,268 INFO [train.py:842] (3/4) Epoch 38, batch 7950, loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04125, over 6459.00 frames.], tot_loss[loss=0.1699, simple_loss=0.259, pruned_loss=0.04045, over 1426410.04 frames.], batch size: 37, lr: 1.44e-04
2022-05-29 17:06:07,457 INFO [train.py:842] (3/4) Epoch 38, batch 8000, loss[loss=0.1728, simple_loss=0.2665, pruned_loss=0.03958, over 7357.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2592, pruned_loss=0.04078, over 1429422.73 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 17:06:45,759 INFO [train.py:842] (3/4) Epoch 38, batch 8050, loss[loss=0.1554, simple_loss=0.2578, pruned_loss=0.02652, over 7325.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2594, pruned_loss=0.04061, over 1430472.87 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 17:07:23,710 INFO [train.py:842] (3/4) Epoch 38, batch 8100, loss[loss=0.206, simple_loss=0.2949, pruned_loss=0.0586, over 7199.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2602, pruned_loss=0.04103, over 1427529.52 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 17:08:01,987 INFO [train.py:842] (3/4) Epoch 38, batch 8150, loss[loss=0.1821, simple_loss=0.2767, pruned_loss=0.04372, over 7184.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2628, pruned_loss=0.04174, over 1430384.07 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 17:08:39,922 INFO [train.py:842] (3/4) Epoch 38, batch 8200, loss[loss=0.1385, simple_loss=0.2243, pruned_loss=0.02635, over 7011.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2628, pruned_loss=0.04221, over 1425528.32 frames.], batch size: 16, lr: 1.44e-04
2022-05-29 17:09:18,218 INFO [train.py:842] (3/4) Epoch 38, batch 8250, loss[loss=0.1338, simple_loss=0.2228, pruned_loss=0.02237, over 6998.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2639, pruned_loss=0.04263, over 1425606.77 frames.], batch size: 16, lr: 1.44e-04
2022-05-29 17:09:56,318 INFO [train.py:842] (3/4) Epoch 38, batch 8300, loss[loss=0.2304, simple_loss=0.3032, pruned_loss=0.07881, over 7269.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2624, pruned_loss=0.04217, over 1426806.67 frames.], batch size: 25, lr: 1.44e-04
2022-05-29 17:10:34,659 INFO [train.py:842] (3/4) Epoch 38, batch 8350, loss[loss=0.2369, simple_loss=0.3234, pruned_loss=0.07521, over 7224.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2632, pruned_loss=0.04213, over 1427305.13 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 17:11:12,614 INFO [train.py:842] (3/4) Epoch 38, batch 8400, loss[loss=0.1934, simple_loss=0.2812, pruned_loss=0.05278, over 6822.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2617, pruned_loss=0.04158, over 1425889.17 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 17:11:50,864 INFO [train.py:842] (3/4) Epoch 38, batch 8450, loss[loss=0.1709, simple_loss=0.2646, pruned_loss=0.03866, over 6606.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2617, pruned_loss=0.0418, over 1425037.05 frames.], batch size: 31, lr: 1.44e-04
2022-05-29 17:12:28,631 INFO [train.py:842] (3/4) Epoch 38, batch 8500, loss[loss=0.1802, simple_loss=0.2786, pruned_loss=0.04091, over 7341.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2627, pruned_loss=0.04235, over 1418493.78 frames.], batch size: 22, lr: 1.44e-04
2022-05-29 17:13:06,637 INFO [train.py:842] (3/4) Epoch 38, batch 8550, loss[loss=0.1331, simple_loss=0.215, pruned_loss=0.02563, over 7118.00 frames.], tot_loss[loss=0.173, simple_loss=0.2621, pruned_loss=0.04201, over 1418955.60 frames.], batch size: 17, lr: 1.44e-04
2022-05-29 17:13:44,597 INFO [train.py:842] (3/4) Epoch 38, batch 8600, loss[loss=0.1605, simple_loss=0.2485, pruned_loss=0.03623, over 7161.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2622, pruned_loss=0.04197, over 1417479.20 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 17:14:22,664 INFO [train.py:842] (3/4) Epoch 38, batch 8650, loss[loss=0.1371, simple_loss=0.219, pruned_loss=0.02761, over 7141.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2615, pruned_loss=0.04133, over 1416409.33 frames.], batch size: 17, lr: 1.44e-04
2022-05-29 17:15:00,647 INFO [train.py:842] (3/4) Epoch 38, batch 8700, loss[loss=0.148, simple_loss=0.2383, pruned_loss=0.02885, over 7329.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2604, pruned_loss=0.0407, over 1418588.69 frames.], batch size: 20, lr: 1.44e-04
2022-05-29 17:15:38,999 INFO [train.py:842] (3/4) Epoch 38, batch 8750, loss[loss=0.1566, simple_loss=0.2351, pruned_loss=0.03904, over 6872.00 frames.], tot_loss[loss=0.1697, simple_loss=0.259, pruned_loss=0.04016, over 1414098.48 frames.], batch size: 15, lr: 1.44e-04
2022-05-29 17:16:17,268 INFO [train.py:842] (3/4) Epoch 38, batch 8800, loss[loss=0.1733, simple_loss=0.2482, pruned_loss=0.04922, over 7370.00 frames.], tot_loss[loss=0.1689, simple_loss=0.258, pruned_loss=0.03984, over 1413194.21 frames.], batch size: 19, lr: 1.44e-04
2022-05-29 17:16:55,765 INFO [train.py:842] (3/4) Epoch 38, batch 8850, loss[loss=0.151, simple_loss=0.2382, pruned_loss=0.03192, over 7004.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2583, pruned_loss=0.04014, over 1411707.71 frames.], batch size: 16, lr: 1.44e-04
2022-05-29 17:17:33,409 INFO [train.py:842] (3/4) Epoch 38, batch 8900, loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.03049, over 7415.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2588, pruned_loss=0.04036, over 1404146.04 frames.], batch size: 21, lr: 1.44e-04
2022-05-29 17:18:11,740 INFO [train.py:842] (3/4) Epoch 38, batch 8950, loss[loss=0.1371, simple_loss=0.2265, pruned_loss=0.02385, over 7265.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2587, pruned_loss=0.04045, over 1404563.72 frames.], batch size: 18, lr: 1.44e-04
2022-05-29 17:18:49,639 INFO [train.py:842] (3/4) Epoch 38, batch 9000, loss[loss=0.169, simple_loss=0.2551, pruned_loss=0.04142, over 6518.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2578, pruned_loss=0.04039, over 1392456.13 frames.], batch size: 38, lr: 1.44e-04
2022-05-29 17:18:49,639 INFO [train.py:862] (3/4) Computing validation loss
2022-05-29 17:18:58,750 INFO [train.py:871] (3/4) Epoch 38, validation: loss=0.165, simple_loss=0.2618, pruned_loss=0.03413, over 868885.00 frames.
2022-05-29 17:19:36,246 INFO [train.py:842] (3/4) Epoch 38, batch 9050, loss[loss=0.2714, simple_loss=0.3478, pruned_loss=0.09748, over 5108.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2602, pruned_loss=0.04147, over 1354305.74 frames.], batch size: 52, lr: 1.44e-04
2022-05-29 17:20:12,626 INFO [train.py:842] (3/4) Epoch 38, batch 9100, loss[loss=0.2452, simple_loss=0.3287, pruned_loss=0.08084, over 4917.00 frames.], tot_loss[loss=0.175, simple_loss=0.2634, pruned_loss=0.04331, over 1304181.00 frames.], batch size: 52, lr: 1.44e-04
2022-05-29 17:20:49,734 INFO [train.py:842] (3/4) Epoch 38, batch 9150, loss[loss=0.1703, simple_loss=0.2549, pruned_loss=0.04283, over 5424.00 frames.], tot_loss[loss=0.179, simple_loss=0.2667, pruned_loss=0.04566, over 1239679.90 frames.], batch size: 52, lr: 1.44e-04
2022-05-29 17:21:35,361 INFO [train.py:842] (3/4) Epoch 39, batch 0, loss[loss=0.151, simple_loss=0.2416, pruned_loss=0.03023, over 7266.00 frames.], tot_loss[loss=0.151, simple_loss=0.2416, pruned_loss=0.03023, over 7266.00 frames.], batch size: 19, lr: 1.42e-04
2022-05-29 17:22:13,624 INFO [train.py:842] (3/4) Epoch 39, batch 50, loss[loss=0.1819, simple_loss=0.2814, pruned_loss=0.04119, over 7142.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2631, pruned_loss=0.04052, over 320189.46 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:22:51,511 INFO [train.py:842] (3/4) Epoch 39, batch 100, loss[loss=0.1824, simple_loss=0.2709, pruned_loss=0.04697, over 6714.00 frames.], tot_loss[loss=0.1711, simple_loss=0.262, pruned_loss=0.04008, over 566024.71 frames.], batch size: 31, lr: 1.42e-04
2022-05-29 17:23:30,000 INFO [train.py:842] (3/4) Epoch 39, batch 150, loss[loss=0.1683, simple_loss=0.2547, pruned_loss=0.04101, over 7163.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2617, pruned_loss=0.04136, over 754958.68 frames.], batch size: 18, lr: 1.42e-04
2022-05-29 17:24:07,935 INFO [train.py:842] (3/4) Epoch 39, batch 200, loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03363, over 7432.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2648, pruned_loss=0.04316, over 901570.08 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:24:45,993 INFO [train.py:842] (3/4) Epoch 39, batch 250, loss[loss=0.2008, simple_loss=0.287, pruned_loss=0.05731, over 6484.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2636, pruned_loss=0.04241, over 1017341.81 frames.], batch size: 38, lr: 1.42e-04
2022-05-29 17:25:24,163 INFO [train.py:842] (3/4) Epoch 39, batch 300, loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.0353, over 7422.00 frames.], tot_loss[loss=0.173, simple_loss=0.2622, pruned_loss=0.04188, over 1112045.92 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:26:02,389 INFO [train.py:842] (3/4) Epoch 39, batch 350, loss[loss=0.1703, simple_loss=0.2683, pruned_loss=0.03614, over 7280.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2607, pruned_loss=0.04116, over 1178793.45 frames.], batch size: 24, lr: 1.42e-04
2022-05-29 17:26:40,287 INFO [train.py:842] (3/4) Epoch 39, batch 400, loss[loss=0.2231, simple_loss=0.3167, pruned_loss=0.06476, over 7234.00 frames.], tot_loss[loss=0.1699, simple_loss=0.259, pruned_loss=0.04045, over 1227980.37 frames.], batch size: 21, lr: 1.42e-04
2022-05-29 17:27:18,770 INFO [train.py:842] (3/4) Epoch 39, batch 450, loss[loss=0.166, simple_loss=0.2637, pruned_loss=0.03417, over 7213.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04103, over 1273369.10 frames.], batch size: 23, lr: 1.42e-04
2022-05-29 17:27:56,690 INFO [train.py:842] (3/4) Epoch 39, batch 500, loss[loss=0.1384, simple_loss=0.2298, pruned_loss=0.02344, over 7146.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2598, pruned_loss=0.0408, over 1299337.39 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:28:35,074 INFO [train.py:842] (3/4) Epoch 39, batch 550, loss[loss=0.2163, simple_loss=0.2989, pruned_loss=0.06679, over 7416.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2596, pruned_loss=0.04055, over 1325031.76 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:29:12,934 INFO [train.py:842] (3/4) Epoch 39, batch 600, loss[loss=0.2051, simple_loss=0.2905, pruned_loss=0.05991, over 7169.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2597, pruned_loss=0.0401, over 1343942.52 frames.], batch size: 18, lr: 1.42e-04
2022-05-29 17:29:51,406 INFO [train.py:842] (3/4) Epoch 39, batch 650, loss[loss=0.1533, simple_loss=0.2372, pruned_loss=0.03475, over 7268.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2587, pruned_loss=0.03995, over 1363199.35 frames.], batch size: 17, lr: 1.42e-04
2022-05-29 17:30:39,078 INFO [train.py:842] (3/4) Epoch 39, batch 700, loss[loss=0.1456, simple_loss=0.2293, pruned_loss=0.03094, over 6800.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04, over 1375733.95 frames.], batch size: 15, lr: 1.42e-04
2022-05-29 17:31:17,525 INFO [train.py:842] (3/4) Epoch 39, batch 750, loss[loss=0.1725, simple_loss=0.2757, pruned_loss=0.03465, over 6478.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2585, pruned_loss=0.03996, over 1385090.73 frames.], batch size: 38, lr: 1.42e-04
2022-05-29 17:31:55,670 INFO [train.py:842] (3/4) Epoch 39, batch 800, loss[loss=0.1878, simple_loss=0.2777, pruned_loss=0.04894, over 7229.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2588, pruned_loss=0.03984, over 1398192.92 frames.], batch size: 20, lr: 1.42e-04
2022-05-29 17:32:33,971 INFO [train.py:842] (3/4) Epoch 39, batch 850, loss[loss=0.1686, simple_loss=0.2639, pruned_loss=0.03664, over 7061.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2589, pruned_loss=0.03991, over 1404471.34 frames.], batch size: 28, lr: 1.42e-04
2022-05-29 17:33:11,861 INFO [train.py:842] (3/4) Epoch 39, batch 900, loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.0346, over 7414.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2586, pruned_loss=0.0398, over 1402981.11 frames.], batch size: 21, lr: 1.42e-04
2022-05-29 17:33:49,933 INFO [train.py:842] (3/4) Epoch 39, batch 950, loss[loss=0.1524, simple_loss=0.2377, pruned_loss=0.03353, over 7122.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2598, pruned_loss=0.04042, over 1404041.50 frames.], batch size: 17, lr: 1.42e-04
2022-05-29 17:34:28,098 INFO [train.py:842] (3/4) Epoch 39, batch 1000, loss[loss=0.1889, simple_loss=0.2591, pruned_loss=0.05937, over 7361.00 frames.], tot_loss[loss=0.17, simple_loss=0.2595, pruned_loss=0.04028, over 1407670.64 frames.], batch size: 19, lr: 1.42e-04
2022-05-29 17:35:06,304 INFO [train.py:842] (3/4) Epoch 39, batch 1050, loss[loss=0.1569, simple_loss=0.2526, pruned_loss=0.03063, over 6765.00 frames.], tot_loss[loss=0.17, simple_loss=0.2593, pruned_loss=0.04032, over 1410594.87 frames.], batch size: 31, lr: 1.42e-04
2022-05-29 17:35:53,924 INFO [train.py:842] (3/4) Epoch 39, batch 1100, loss[loss=0.1472, simple_loss=0.234, pruned_loss=0.03014, over 7392.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2582, pruned_loss=0.04046, over 1415591.08 frames.], batch size: 23, lr: 1.42e-04
2022-05-29 17:36:32,299 INFO [train.py:842] (3/4) Epoch 39, batch 1150, loss[loss=0.1375, simple_loss=0.2268, pruned_loss=0.02407, over 7272.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2567, pruned_loss=0.03947, over 1419039.67 frames.], batch size: 18, lr: 1.42e-04
2022-05-29 17:37:19,677 INFO [train.py:842] (3/4) Epoch 39, batch 1200, loss[loss=0.1796, simple_loss=0.2735, pruned_loss=0.04292, over 7014.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2585, pruned_loss=0.04037, over 1420990.30 frames.], batch size: 32, lr: 1.42e-04
2022-05-29 17:37:57,977 INFO [train.py:842] (3/4) Epoch 39, batch 1250, loss[loss=0.1425, simple_loss=0.2283, pruned_loss=0.02832, over 7447.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2588, pruned_loss=0.04035, over 1421702.86 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:38:36,167 INFO [train.py:842] (3/4) Epoch 39, batch 1300, loss[loss=0.1396, simple_loss=0.226, pruned_loss=0.02656, over 7263.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2585, pruned_loss=0.04024, over 1426229.48 frames.], batch size: 17, lr: 1.41e-04
2022-05-29 17:39:14,324 INFO [train.py:842] (3/4) Epoch 39, batch 1350, loss[loss=0.14, simple_loss=0.2302, pruned_loss=0.02488, over 7327.00 frames.], tot_loss[loss=0.169, simple_loss=0.2582, pruned_loss=0.03991, over 1426158.21 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:39:52,322 INFO [train.py:842] (3/4) Epoch 39, batch 1400, loss[loss=0.1738, simple_loss=0.2664, pruned_loss=0.04062, over 7154.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2585, pruned_loss=0.03997, over 1424514.72 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:40:30,527 INFO [train.py:842] (3/4) Epoch 39, batch 1450, loss[loss=0.1642, simple_loss=0.2644, pruned_loss=0.03198, over 7289.00 frames.], tot_loss[loss=0.171, simple_loss=0.2608, pruned_loss=0.04058, over 1424462.99 frames.], batch size: 25, lr: 1.41e-04
2022-05-29 17:41:08,509 INFO [train.py:842] (3/4) Epoch 39, batch 1500, loss[loss=0.1733, simple_loss=0.269, pruned_loss=0.03878, over 7118.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2608, pruned_loss=0.04045, over 1423641.30 frames.], batch size: 21, lr: 1.41e-04
2022-05-29 17:41:46,925 INFO [train.py:842] (3/4) Epoch 39, batch 1550, loss[loss=0.1553, simple_loss=0.25, pruned_loss=0.03028, over 7206.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2599, pruned_loss=0.04031, over 1423520.77 frames.], batch size: 22, lr: 1.41e-04
2022-05-29 17:42:25,017 INFO [train.py:842] (3/4) Epoch 39, batch 1600, loss[loss=0.1447, simple_loss=0.2363, pruned_loss=0.02657, over 6755.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2577, pruned_loss=0.03928, over 1425504.49 frames.], batch size: 31, lr: 1.41e-04
2022-05-29 17:43:03,334 INFO [train.py:842] (3/4) Epoch 39, batch 1650, loss[loss=0.1473, simple_loss=0.2468, pruned_loss=0.02385, over 7222.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2577, pruned_loss=0.03936, over 1424391.09 frames.], batch size: 21, lr: 1.41e-04
2022-05-29 17:43:41,234 INFO [train.py:842] (3/4) Epoch 39, batch 1700, loss[loss=0.1619, simple_loss=0.2566, pruned_loss=0.03365, over 7052.00 frames.], tot_loss[loss=0.1691, simple_loss=0.259, pruned_loss=0.03959, over 1426843.40 frames.], batch size: 28, lr: 1.41e-04
2022-05-29 17:44:19,441 INFO [train.py:842] (3/4) Epoch 39, batch 1750, loss[loss=0.1928, simple_loss=0.2895, pruned_loss=0.04802, over 7424.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2603, pruned_loss=0.03964, over 1426425.16 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:44:57,272 INFO [train.py:842] (3/4) Epoch 39, batch 1800, loss[loss=0.1651, simple_loss=0.2631, pruned_loss=0.03357, over 7194.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2598, pruned_loss=0.03949, over 1423732.03 frames.], batch size: 23, lr: 1.41e-04
2022-05-29 17:45:35,468 INFO [train.py:842] (3/4) Epoch 39, batch 1850, loss[loss=0.1738, simple_loss=0.2646, pruned_loss=0.04153, over 7145.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2591, pruned_loss=0.03937, over 1421646.30 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:46:13,565 INFO [train.py:842] (3/4) Epoch 39, batch 1900, loss[loss=0.1523, simple_loss=0.2368, pruned_loss=0.03387, over 7288.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2595, pruned_loss=0.03964, over 1424876.24 frames.], batch size: 18, lr: 1.41e-04
2022-05-29 17:46:51,821 INFO [train.py:842] (3/4) Epoch 39, batch 1950, loss[loss=0.1675, simple_loss=0.2593, pruned_loss=0.03779, over 7317.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2588, pruned_loss=0.03923, over 1424459.47 frames.], batch size: 21, lr: 1.41e-04
2022-05-29 17:47:29,747 INFO [train.py:842] (3/4) Epoch 39, batch 2000, loss[loss=0.148, simple_loss=0.2473, pruned_loss=0.02437, over 7258.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2586, pruned_loss=0.0389, over 1422819.19 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:48:07,765 INFO [train.py:842] (3/4) Epoch 39, batch 2050, loss[loss=0.1915, simple_loss=0.2741, pruned_loss=0.05445, over 7323.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2595, pruned_loss=0.03973, over 1421925.43 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:48:45,830 INFO [train.py:842] (3/4) Epoch 39, batch 2100, loss[loss=0.133, simple_loss=0.2208, pruned_loss=0.02259, over 7184.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2592, pruned_loss=0.03982, over 1424188.69 frames.], batch size: 16, lr: 1.41e-04
2022-05-29 17:49:24,062 INFO [train.py:842] (3/4) Epoch 39, batch 2150, loss[loss=0.1438, simple_loss=0.2404, pruned_loss=0.0236, over 7263.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2591, pruned_loss=0.03972, over 1421827.84 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:50:01,950 INFO [train.py:842] (3/4) Epoch 39, batch 2200, loss[loss=0.203, simple_loss=0.292, pruned_loss=0.05703, over 7186.00 frames.], tot_loss[loss=0.1703, simple_loss=0.26, pruned_loss=0.04032, over 1422029.96 frames.], batch size: 22, lr: 1.41e-04
2022-05-29 17:50:40,603 INFO [train.py:842] (3/4) Epoch 39, batch 2250, loss[loss=0.1926, simple_loss=0.2831, pruned_loss=0.05098, over 7158.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2581, pruned_loss=0.03952, over 1424263.39 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:51:18,400 INFO [train.py:842] (3/4) Epoch 39, batch 2300, loss[loss=0.2379, simple_loss=0.3181, pruned_loss=0.0788, over 7154.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2596, pruned_loss=0.04043, over 1423843.48 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:51:56,801 INFO [train.py:842] (3/4) Epoch 39, batch 2350, loss[loss=0.1563, simple_loss=0.2525, pruned_loss=0.03007, over 7230.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2584, pruned_loss=0.03949, over 1425642.29 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:52:34,842 INFO [train.py:842] (3/4) Epoch 39, batch 2400, loss[loss=0.1891, simple_loss=0.2833, pruned_loss=0.04745, over 7141.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2595, pruned_loss=0.0405, over 1428640.58 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:53:13,356 INFO [train.py:842] (3/4) Epoch 39, batch 2450, loss[loss=0.1515, simple_loss=0.2372, pruned_loss=0.03292, over 7423.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2584, pruned_loss=0.03966, over 1429192.26 frames.], batch size: 18, lr: 1.41e-04
2022-05-29 17:53:51,361 INFO [train.py:842] (3/4) Epoch 39, batch 2500, loss[loss=0.1619, simple_loss=0.2431, pruned_loss=0.0404, over 7406.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2587, pruned_loss=0.03957, over 1426949.77 frames.], batch size: 18, lr: 1.41e-04
2022-05-29 17:54:29,857 INFO [train.py:842] (3/4) Epoch 39, batch 2550, loss[loss=0.1612, simple_loss=0.2626, pruned_loss=0.02992, over 7426.00 frames.], tot_loss[loss=0.1704, simple_loss=0.26, pruned_loss=0.04037, over 1431350.17 frames.], batch size: 20, lr: 1.41e-04
2022-05-29 17:55:07,768 INFO [train.py:842] (3/4) Epoch 39, batch 2600, loss[loss=0.1757, simple_loss=0.2799, pruned_loss=0.03572, over 7218.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2595, pruned_loss=0.04001, over 1429080.43 frames.], batch size: 26, lr: 1.41e-04
2022-05-29 17:55:46,326 INFO [train.py:842] (3/4) Epoch 39, batch 2650, loss[loss=0.1658, simple_loss=0.2688, pruned_loss=0.0314, over 7094.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2606, pruned_loss=0.04047, over 1430136.96 frames.], batch size: 28, lr: 1.41e-04
2022-05-29 17:56:24,501 INFO [train.py:842] (3/4) Epoch 39, batch 2700, loss[loss=0.1688, simple_loss=0.2573, pruned_loss=0.04013, over 7311.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2603, pruned_loss=0.04038, over 1428419.67 frames.], batch size: 25, lr: 1.41e-04
2022-05-29 17:57:06,510 INFO [train.py:842] (3/4) Epoch 39, batch 2750, loss[loss=0.1561, simple_loss=0.2416, pruned_loss=0.0353, over 7159.00 frames.], tot_loss[loss=0.169, simple_loss=0.2588, pruned_loss=0.0396, over 1428873.06 frames.], batch size: 19, lr: 1.41e-04
2022-05-29 17:57:44,936 INFO [train.py:842] (3/4) Epoch 39, batch 2800, loss[loss=0.1548, simple_loss=0.2495, pruned_loss=0.03005, over 7338.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2588, pruned_loss=0.03953, over 1426156.11 frames.], batch size: 22, lr: 1.41e-04
2022-05-29 17:58:23,835 INFO [train.py:842] (3/4) Epoch 39, batch 2850, loss[loss=0.1467, simple_loss=0.2599, pruned_loss=0.01675, over 6406.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2599, pruned_loss=0.04025, over 1426079.11 frames.], batch size: 37, lr: 1.41e-04