| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.1156558533145273, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.824635637047485e-06, | |
| "loss": 0.2885, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.2095741480588913, | |
| "eval_runtime": 14.7617, | |
| "eval_samples_per_second": 192.051, | |
| "eval_steps_per_second": 12.058, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6492712740949693e-06, | |
| "loss": 0.1876, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9354497354497354, | |
| "eval_loss": 0.22086860239505768, | |
| "eval_runtime": 14.1485, | |
| "eval_samples_per_second": 200.374, | |
| "eval_steps_per_second": 12.581, | |
| "step": 1418 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.4739069111424542e-06, | |
| "loss": 0.1728, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 2127, | |
| "num_train_epochs": 3, | |
| "total_flos": 6311507995975680.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |