| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002528304367392964, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3245, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.0302, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.7242, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2668, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5193, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1466, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0462, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7075, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5202, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1509, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4468, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0541, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1905, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8179, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0296, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0647, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3423, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6224, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3795, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5578, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0889, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3747, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.9868, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3326, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.856, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6524, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2403, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.021, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7178, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7909, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4629, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6591, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.4752, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0742, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9453, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3289, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.431, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4762, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.0352, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3314, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2719, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6705, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.434, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6516, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.197, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "step": 50, | |
| "total_flos": 408469398607872.0, | |
| "train_loss": 1.9394794535636901, | |
| "train_runtime": 76.3235, | |
| "train_samples_per_second": 0.655, | |
| "train_steps_per_second": 0.655 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 408469398607872.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |