| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8886558635735519, |
| "eval_steps": 25000, |
| "global_step": 50000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.44, |
| "learning_rate": 4.782225068488277e-05, |
| "loss": 2.8517, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_loss": 3.018819808959961, |
| "eval_runtime": 13.8146, |
| "eval_samples_per_second": 50.671, |
| "eval_steps_per_second": 6.37, |
| "eval_wer": 0.9749303621169917, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 4.559993951684634e-05, |
| "loss": 2.8942, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.89, |
| "eval_loss": 3.0555782318115234, |
| "eval_runtime": 13.676, |
| "eval_samples_per_second": 51.185, |
| "eval_steps_per_second": 6.435, |
| "eval_wer": 0.9996285979572888, |
| "step": 50000 |
| } |
| ], |
| "logging_steps": 25000, |
| "max_steps": 562640, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 50000, |
| "total_flos": 4.38681696546068e+20, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
