| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6389776357827476, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0007307692307692308, | |
| "loss": 4.2559, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0007115384615384615, | |
| "loss": 3.068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 3.058549165725708, | |
| "eval_runtime": 3.3353, | |
| "eval_samples_per_second": 29.982, | |
| "eval_steps_per_second": 1.199, | |
| "eval_wer": 1.0, | |
| "step": 50 | |
| } | |
| ], | |
| "max_steps": 780, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.755792033779712e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |