| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.541798941798942, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0249, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.3500341773033142, | |
| "eval_runtime": 218.9102, | |
| "eval_samples_per_second": 15.399, | |
| "eval_steps_per_second": 1.928, | |
| "eval_wer": 0.2325649086040284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 9.991518235793045e-05, | |
| "loss": 0.0468, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.3051254153251648, | |
| "eval_runtime": 153.0625, | |
| "eval_samples_per_second": 22.024, | |
| "eval_steps_per_second": 2.757, | |
| "eval_wer": 0.22418209337524742, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 9.98303647158609e-05, | |
| "loss": 0.0412, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.3074679672718048, | |
| "eval_runtime": 155.3125, | |
| "eval_samples_per_second": 21.705, | |
| "eval_steps_per_second": 2.717, | |
| "eval_wer": 0.22563744324135523, | |
| "step": 300 | |
| } | |
| ], | |
| "max_steps": 118000, | |
| "num_train_epochs": 1000, | |
| "total_flos": 6.832318928753621e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |