| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 1920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.8576, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.8285567164421082, | |
| "eval_runtime": 55.5454, | |
| "eval_samples_per_second": 5.113, | |
| "eval_wer": 0.38298498675301734, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 0.0002788732394366197, | |
| "loss": 0.4686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_loss": 0.8982126712799072, | |
| "eval_runtime": 54.9334, | |
| "eval_samples_per_second": 5.17, | |
| "eval_wer": 0.3567853988813659, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 0.00021549295774647887, | |
| "loss": 0.3311, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "eval_loss": 0.9844297170639038, | |
| "eval_runtime": 55.0404, | |
| "eval_samples_per_second": 5.16, | |
| "eval_wer": 0.3453046806005299, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 0.000152112676056338, | |
| "loss": 0.2365, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "eval_loss": 1.0644716024398804, | |
| "eval_runtime": 55.4598, | |
| "eval_samples_per_second": 5.121, | |
| "eval_wer": 0.3506034736532234, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 8.873239436619717e-05, | |
| "loss": 0.1936, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "eval_loss": 1.0275092124938965, | |
| "eval_runtime": 55.6571, | |
| "eval_samples_per_second": 5.103, | |
| "eval_wer": 0.32999705622608183, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 2.5352112676056335e-05, | |
| "loss": 0.1694, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "eval_loss": 1.1164253950119019, | |
| "eval_runtime": 55.1147, | |
| "eval_samples_per_second": 5.153, | |
| "eval_wer": 0.3211657344715926, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 1920, | |
| "total_flos": 1.105589862217553e+19, | |
| "train_runtime": 10193.2109, | |
| "train_samples_per_second": 0.188 | |
| } | |
| ], | |
| "max_steps": 1920, | |
| "num_train_epochs": 30, | |
| "total_flos": 1.105589862217553e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |