| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.388888888888889, | |
| "eval_steps": 500, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7231, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.883, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001875, | |
| "loss": 1.6195, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.000175, | |
| "loss": 1.1922, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00016250000000000002, | |
| "loss": 1.4483, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0528, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0001375, | |
| "loss": 1.2183, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 54, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1707177525903360.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |