| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.30232558139535, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.920000000000001e-05, | |
| "loss": 9.9787, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 3.0419623851776123, | |
| "eval_runtime": 81.9377, | |
| "eval_samples_per_second": 23.323, | |
| "eval_steps_per_second": 2.917, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 6.253164556962025e-05, | |
| "loss": 2.7264, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 1.3224282264709473, | |
| "eval_runtime": 81.6615, | |
| "eval_samples_per_second": 23.401, | |
| "eval_steps_per_second": 2.927, | |
| "eval_wer": 1.067686658506732, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 1.189873417721519e-05, | |
| "loss": 0.9607, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 0.6051472425460815, | |
| "eval_runtime": 80.842, | |
| "eval_samples_per_second": 23.639, | |
| "eval_steps_per_second": 2.956, | |
| "eval_wer": 0.7376988984088128, | |
| "step": 1200 | |
| } | |
| ], | |
| "max_steps": 1290, | |
| "num_train_epochs": 10, | |
| "total_flos": 4.3671042896313257e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |