| { | |
| "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 | |
| } | |