| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 2750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0003, | |
| "loss": 4.1674, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.8416548371315002, | |
| "eval_runtime": 101.0995, | |
| "eval_samples_per_second": 7.794, | |
| "eval_wer": 0.8985163204747775, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.000225, | |
| "loss": 0.3273, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.6257408857345581, | |
| "eval_runtime": 102.9185, | |
| "eval_samples_per_second": 7.657, | |
| "eval_wer": 0.6571711177052423, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1125, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.709644615650177, | |
| "eval_runtime": 103.3162, | |
| "eval_samples_per_second": 7.627, | |
| "eval_wer": 0.6631058358061326, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0718, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.7290266156196594, | |
| "eval_runtime": 109.3818, | |
| "eval_samples_per_second": 7.204, | |
| "eval_wer": 0.6189910979228487, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0551, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.7108353972434998, | |
| "eval_runtime": 106.4037, | |
| "eval_samples_per_second": 7.406, | |
| "eval_wer": 0.6126607319485657, | |
| "step": 2750 | |
| } | |
| ], | |
| "max_steps": 2750, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.1543543816112128e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |