| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6489292667099286, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.837767683322518e-05, | |
| "loss": 0.1601, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.6755353666450355e-05, | |
| "loss": 0.0226, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.5133030499675535e-05, | |
| "loss": 0.0105, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3510707332900715e-05, | |
| "loss": 0.0054, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 15410, | |
| "num_train_epochs": 5, | |
| "total_flos": 300589216447776.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |