| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 155, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0009897649706262473, | |
| "loss": 0.7217, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0009594789058101153, | |
| "loss": 0.4332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0009103817206036382, | |
| "loss": 0.41, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0008444834595378434, | |
| "loss": 0.4098, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0007644820051634812, | |
| "loss": 0.308, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0006736526264224101, | |
| "loss": 0.3254, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0005757138887522884, | |
| "loss": 0.1859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0004746754155806437, | |
| "loss": 0.2975, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.00037467373387063967, | |
| "loss": 0.2897, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0002798029242211828, | |
| "loss": 0.1815, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.00019394700872616856, | |
| "loss": 0.2632, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00012062093865360457, | |
| "loss": 0.109, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.282669192770896e-05, | |
| "loss": 0.2943, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.2930371799975592e-05, | |
| "loss": 0.0821, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.5653383040524227e-06, | |
| "loss": 0.1791, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 155, | |
| "total_flos": 1.7897091891019776e+16, | |
| "train_loss": 0.29589878051511703, | |
| "train_runtime": 277.1475, | |
| "train_samples_per_second": 2.219, | |
| "train_steps_per_second": 0.559 | |
| } | |
| ], | |
| "max_steps": 155, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.7897091891019776e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |