| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.8924418604651163, | |
| "eval_steps": 500, | |
| "global_step": 4912, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.981851179673322e-05, | |
| "loss": 1.0342, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019963702359346644, | |
| "loss": 1.0067, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018893599838481728, | |
| "loss": 0.9593, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00017783161720169593, | |
| "loss": 0.9689, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00016672723601857462, | |
| "loss": 0.9962, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00015562285483545327, | |
| "loss": 0.9603, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00014451847365233193, | |
| "loss": 0.9125, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00013341409246921059, | |
| "loss": 0.8879, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00012230971128608924, | |
| "loss": 0.9288, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001112053301029679, | |
| "loss": 0.9478, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00010010094891984656, | |
| "loss": 0.8882, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.899656773672523e-05, | |
| "loss": 0.844, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.789218655360388e-05, | |
| "loss": 0.8717, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 6.678780537048254e-05, | |
| "loss": 0.9223, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 5.5683424187361196e-05, | |
| "loss": 0.8723, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.457904300423986e-05, | |
| "loss": 0.8354, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 3.3474661821118516e-05, | |
| "loss": 0.8243, | |
| "step": 4675 | |
| } | |
| ], | |
| "logging_steps": 275, | |
| "max_steps": 5504, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 3.4368102065189683e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |