| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 4705, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3e-05, | |
| "loss": 0.353, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2194, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1763, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1648, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1385, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1273, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1095, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1005, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0881, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 4705, | |
| "train_runtime": 56515.0815, | |
| "train_samples_per_second": 0.083 | |
| } | |
| ], | |
| "max_steps": 4705, | |
| "num_train_epochs": 5, | |
| "total_flos": 363611501376110592, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |