| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 12.087431693989071, | |
| "global_step": 1100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.999725244532367e-06, | |
| "loss": 0.0243, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 4.998900978129465e-06, | |
| "loss": 0.0192, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 4.998076711726564e-06, | |
| "loss": 0.0175, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 4.997252445323663e-06, | |
| "loss": 0.0174, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 4.996428178920761e-06, | |
| "loss": 0.0168, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 4.995609407627212e-06, | |
| "loss": 0.0175, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 4.994785141224311e-06, | |
| "loss": 0.0168, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "eval_loss": 0.23020002245903015, | |
| "eval_runtime": 433.719, | |
| "eval_samples_per_second": 9.407, | |
| "eval_steps_per_second": 1.176, | |
| "eval_wer": 0.16092909535452324, | |
| "step": 1100 | |
| } | |
| ], | |
| "max_steps": 910000, | |
| "num_train_epochs": 10000, | |
| "total_flos": 3.930570221142893e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |