| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 21.238938053097346, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0001926605504587156, | |
| "loss": NaN, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 2.914095878601074, | |
| "eval_runtime": 779.3384, | |
| "eval_samples_per_second": 9.78, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.0001779816513761468, | |
| "loss": NaN, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "eval_loss": 0.5257614850997925, | |
| "eval_runtime": 808.0741, | |
| "eval_samples_per_second": 9.432, | |
| "eval_wer": 0.4909435120753172, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 0.00016330275229357798, | |
| "loss": NaN, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "eval_loss": 0.4604354500770569, | |
| "eval_runtime": 816.9678, | |
| "eval_samples_per_second": 9.33, | |
| "eval_wer": 0.444765656979124, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 0.00014862385321100919, | |
| "loss": NaN, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "eval_loss": 0.4556906819343567, | |
| "eval_runtime": 788.8971, | |
| "eval_samples_per_second": 9.662, | |
| "eval_wer": 0.4178008595988539, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 0.00013394495412844036, | |
| "loss": NaN, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_loss": 0.44174715876579285, | |
| "eval_runtime": 788.0029, | |
| "eval_samples_per_second": 9.673, | |
| "eval_wer": 0.4084885386819484, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 0.00011926605504587157, | |
| "loss": NaN, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "eval_loss": 0.43745675683021545, | |
| "eval_runtime": 797.2999, | |
| "eval_samples_per_second": 9.56, | |
| "eval_wer": 0.4028602128530495, | |
| "step": 2400 | |
| } | |
| ], | |
| "max_steps": 5650, | |
| "num_train_epochs": 50, | |
| "total_flos": 8.638551360908018e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |