| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6230529595015576, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21, |
| "learning_rate": 2.842473646947527e-06, |
| "loss": 0.1561, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 0.16617341339588165, |
| "eval_runtime": 237.5111, |
| "eval_samples_per_second": 7.878, |
| "eval_wer": 0.25878220140515223, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 2.63105872341108e-06, |
| "loss": 0.152, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.42, |
| "eval_loss": 0.16523481905460358, |
| "eval_runtime": 238.503, |
| "eval_samples_per_second": 7.845, |
| "eval_wer": 0.25843091334894613, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 2.4196437998746334e-06, |
| "loss": 0.1537, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.62, |
| "eval_loss": 0.16467183828353882, |
| "eval_runtime": 240.7886, |
| "eval_samples_per_second": 7.77, |
| "eval_wer": 0.2573770491803279, |
| "step": 1200 |
| } |
| ], |
| "max_steps": 5778, |
| "num_train_epochs": 3, |
| "total_flos": 6.372500637308682e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
