| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.7052, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6902039051055908, | |
| "eval_runtime": 0.5271, | |
| "eval_samples_per_second": 134.707, | |
| "eval_steps_per_second": 17.076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.6957, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.7012577056884766, | |
| "eval_runtime": 0.5221, | |
| "eval_samples_per_second": 135.995, | |
| "eval_steps_per_second": 17.239, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6898, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5352112676056338, | |
| "eval_loss": 0.6898324489593506, | |
| "eval_runtime": 0.5232, | |
| "eval_samples_per_second": 135.691, | |
| "eval_steps_per_second": 17.2, | |
| "step": 120 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 5, | |
| "total_flos": 338783333160960.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |