| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 38.4, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.66, | |
| "eval_loss": 1.381475567817688, | |
| "eval_runtime": 88.5509, | |
| "eval_samples_per_second": 4.517, | |
| "eval_steps_per_second": 2.259, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7775, | |
| "eval_loss": 0.8648924231529236, | |
| "eval_runtime": 87.4735, | |
| "eval_samples_per_second": 4.573, | |
| "eval_steps_per_second": 2.286, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.785, | |
| "eval_loss": 0.9166873693466187, | |
| "eval_runtime": 87.4248, | |
| "eval_samples_per_second": 4.575, | |
| "eval_steps_per_second": 2.288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.79, | |
| "eval_loss": 0.9467521905899048, | |
| "eval_runtime": 89.9359, | |
| "eval_samples_per_second": 4.448, | |
| "eval_steps_per_second": 2.224, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 480, | |
| "num_train_epochs": 40, | |
| "total_flos": 8154344545320960.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |