| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.988739357319417, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 5.2801, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 4.0432, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.7257, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 3.4456169605255127, | |
| "eval_rouge2_fmeasure": 0.0619, | |
| "eval_rouge2_precision": 0.0751, | |
| "eval_rouge2_recall": 0.0686, | |
| "eval_runtime": 10201.4024, | |
| "eval_samples_per_second": 0.089, | |
| "eval_steps_per_second": 0.089, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.6021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 3.505, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4611, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 3.324451446533203, | |
| "eval_rouge2_fmeasure": 0.064, | |
| "eval_rouge2_precision": 0.0771, | |
| "eval_rouge2_recall": 0.0724, | |
| "eval_runtime": 10238.3889, | |
| "eval_samples_per_second": 0.089, | |
| "eval_steps_per_second": 0.089, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.8529411764705885e-05, | |
| "loss": 3.4327, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 3.3307, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.558823529411765e-05, | |
| "loss": 3.2866, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 3.268772602081299, | |
| "eval_rouge2_fmeasure": 0.0675, | |
| "eval_rouge2_precision": 0.0787, | |
| "eval_rouge2_recall": 0.0787, | |
| "eval_runtime": 11096.9726, | |
| "eval_samples_per_second": 0.082, | |
| "eval_steps_per_second": 0.082, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 3.3072, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.2647058823529415e-05, | |
| "loss": 3.2516, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 3.1896, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 3.2407822608947754, | |
| "eval_rouge2_fmeasure": 0.0688, | |
| "eval_rouge2_precision": 0.0806, | |
| "eval_rouge2_recall": 0.0802, | |
| "eval_runtime": 10753.114, | |
| "eval_samples_per_second": 0.085, | |
| "eval_steps_per_second": 0.085, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.970588235294117e-05, | |
| "loss": 3.1495, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 3.8235294117647055e-05, | |
| "loss": 3.1904, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.6764705882352945e-05, | |
| "loss": 3.1541, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 3.230734348297119, | |
| "eval_rouge2_fmeasure": 0.0704, | |
| "eval_rouge2_precision": 0.081, | |
| "eval_rouge2_recall": 0.083, | |
| "eval_runtime": 11594.4275, | |
| "eval_samples_per_second": 0.078, | |
| "eval_steps_per_second": 0.078, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 3.0879, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3.382352941176471e-05, | |
| "loss": 3.0753, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 3.235294117647059e-05, | |
| "loss": 3.1243, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 3.2160983085632324, | |
| "eval_rouge2_fmeasure": 0.0707, | |
| "eval_rouge2_precision": 0.0821, | |
| "eval_rouge2_recall": 0.0817, | |
| "eval_runtime": 11304.2042, | |
| "eval_samples_per_second": 0.081, | |
| "eval_steps_per_second": 0.081, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 3.0882352941176475e-05, | |
| "loss": 3.0364, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 3.0249, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 2.7941176470588236e-05, | |
| "loss": 3.0428, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 3.2113523483276367, | |
| "eval_rouge2_fmeasure": 0.072, | |
| "eval_rouge2_precision": 0.0828, | |
| "eval_rouge2_recall": 0.0848, | |
| "eval_runtime": 11113.1913, | |
| "eval_samples_per_second": 0.082, | |
| "eval_steps_per_second": 0.082, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 3.0229, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.979, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 2.975, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "eval_loss": 3.213066339492798, | |
| "eval_rouge2_fmeasure": 0.0728, | |
| "eval_rouge2_precision": 0.0841, | |
| "eval_rouge2_recall": 0.085, | |
| "eval_runtime": 11135.6948, | |
| "eval_samples_per_second": 0.082, | |
| "eval_steps_per_second": 0.082, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 3.0022, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 2.9825, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1.9117647058823528e-05, | |
| "loss": 2.9392, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "eval_loss": 3.2107818126678467, | |
| "eval_rouge2_fmeasure": 0.073, | |
| "eval_rouge2_precision": 0.0839, | |
| "eval_rouge2_recall": 0.0848, | |
| "eval_runtime": 11088.831, | |
| "eval_samples_per_second": 0.082, | |
| "eval_steps_per_second": 0.082, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 2.9429, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.6176470588235296e-05, | |
| "loss": 2.9304, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 2.9204, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "eval_loss": 3.2088212966918945, | |
| "eval_rouge2_fmeasure": 0.073, | |
| "eval_rouge2_precision": 0.0833, | |
| "eval_rouge2_recall": 0.0865, | |
| "eval_runtime": 11327.9603, | |
| "eval_samples_per_second": 0.08, | |
| "eval_steps_per_second": 0.08, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 2.8969, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.9162, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.0294117647058824e-05, | |
| "loss": 2.9233, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_loss": 3.210251808166504, | |
| "eval_rouge2_fmeasure": 0.0738, | |
| "eval_rouge2_precision": 0.0849, | |
| "eval_rouge2_recall": 0.0859, | |
| "eval_runtime": 11276.9504, | |
| "eval_samples_per_second": 0.081, | |
| "eval_steps_per_second": 0.081, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 2.8888, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 7.3529411764705884e-06, | |
| "loss": 2.8771, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 2.9142, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_loss": 3.206127643585205, | |
| "eval_rouge2_fmeasure": 0.0728, | |
| "eval_rouge2_precision": 0.0831, | |
| "eval_rouge2_recall": 0.0855, | |
| "eval_runtime": 11283.9811, | |
| "eval_samples_per_second": 0.081, | |
| "eval_steps_per_second": 0.081, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 2.857, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 2.8846, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 2.8889, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "eval_loss": 3.2091023921966553, | |
| "eval_rouge2_fmeasure": 0.0729, | |
| "eval_rouge2_precision": 0.0835, | |
| "eval_rouge2_recall": 0.0849, | |
| "eval_runtime": 11160.0848, | |
| "eval_samples_per_second": 0.082, | |
| "eval_steps_per_second": 0.082, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.0, | |
| "loss": 2.8707, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 11, | |
| "total_flos": 1.560566442271703e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |