| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 1662, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.337121285067684e-06, | |
| "loss": 3.63, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.442531108856201, | |
| "eval_runtime": 165.1636, | |
| "eval_samples_per_second": 160.968, | |
| "eval_steps_per_second": 5.031, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 5.009099042085838e-06, | |
| "loss": 3.6184, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.0015755222436686e-05, | |
| "loss": 3.5811, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.3535778522491455, | |
| "eval_runtime": 165.2268, | |
| "eval_samples_per_second": 160.906, | |
| "eval_steps_per_second": 5.029, | |
| "step": 1662 | |
| } | |
| ], | |
| "max_steps": 3324, | |
| "num_train_epochs": 4, | |
| "total_flos": 1.401078900289536e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |