| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.982530890498509, | |
| "global_step": 7000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.999289873597501e-05, | |
| "loss": 0.4718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.89, | |
| "eval_loss": 0.23648260533809662, | |
| "eval_runtime": 31.0846, | |
| "eval_samples_per_second": 3.217, | |
| "eval_steps_per_second": 0.418, | |
| "step": 2347 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.23966342210769653, | |
| "eval_runtime": 4863.3895, | |
| "eval_samples_per_second": 0.021, | |
| "eval_steps_per_second": 0.003, | |
| "step": 4694 | |
| } | |
| ], | |
| "max_steps": 7041, | |
| "num_train_epochs": 3, | |
| "total_flos": 2580901877465088.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |