| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994431037683311, | |
| "global_step": 1346, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.3971924029727499e-05, | |
| "loss": 0.746, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.6209, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.749131441116333, | |
| "eval_runtime": 7.8642, | |
| "eval_samples_per_second": 22.761, | |
| "step": 1346 | |
| } | |
| ], | |
| "max_steps": 1346, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.772919366675661e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |