| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.700832238282961, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.018000000000000002, | |
| "loss": 2.8089, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.016, | |
| "loss": 1.4307, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.013999999999999999, | |
| "loss": 1.2707, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.012, | |
| "loss": 1.3679, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.01, | |
| "loss": 1.1691, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.008, | |
| "loss": 1.1082, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.006, | |
| "loss": 1.1135, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.004, | |
| "loss": 1.1645, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.002, | |
| "loss": 1.1788, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0, | |
| "loss": 1.1268, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.38662884933632e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |