| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.528428093645484, | |
| "global_step": 4400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.4877, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 1.0936583280563354, | |
| "eval_runtime": 158.101, | |
| "eval_samples_per_second": 13.2, | |
| "eval_wer": 0.8853237689026755, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.0002773299748110831, | |
| "loss": 0.7501, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 0.8788074851036072, | |
| "eval_runtime": 158.2433, | |
| "eval_samples_per_second": 13.189, | |
| "eval_wer": 0.768030244280729, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.00024710327455919394, | |
| "loss": 0.4114, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 0.8623701333999634, | |
| "eval_runtime": 160.5429, | |
| "eval_samples_per_second": 13.0, | |
| "eval_wer": 0.702016285381931, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 0.00021687657430730477, | |
| "loss": 0.2676, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "eval_loss": 0.8885830640792847, | |
| "eval_runtime": 159.9177, | |
| "eval_samples_per_second": 13.05, | |
| "eval_wer": 0.6879604497867391, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 0.0001866498740554156, | |
| "loss": 0.194, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "eval_loss": 0.9405023455619812, | |
| "eval_runtime": 154.7945, | |
| "eval_samples_per_second": 13.482, | |
| "eval_wer": 0.6577161690577743, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 0.00015642317380352644, | |
| "loss": 0.1496, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "eval_loss": 1.0035845041275024, | |
| "eval_runtime": 153.8389, | |
| "eval_samples_per_second": 13.566, | |
| "eval_wer": 0.6553896859247771, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 0.00012619647355163727, | |
| "loss": 0.1227, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "eval_loss": 0.9778856635093689, | |
| "eval_runtime": 153.4023, | |
| "eval_samples_per_second": 13.605, | |
| "eval_wer": 0.6457929430011632, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 9.59697732997481e-05, | |
| "loss": 0.0982, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "eval_loss": 1.0781689882278442, | |
| "eval_runtime": 154.2908, | |
| "eval_samples_per_second": 13.526, | |
| "eval_wer": 0.6339666537417604, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 6.574307304785894e-05, | |
| "loss": 0.0852, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "eval_loss": 1.066897988319397, | |
| "eval_runtime": 154.9275, | |
| "eval_samples_per_second": 13.471, | |
| "eval_wer": 0.6234974796432726, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 3.551637279596977e-05, | |
| "loss": 0.0715, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "eval_loss": 1.0754976272583008, | |
| "eval_runtime": 156.8919, | |
| "eval_samples_per_second": 13.302, | |
| "eval_wer": 0.6209771229158588, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "learning_rate": 5.289672544080604e-06, | |
| "loss": 0.0678, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "eval_loss": 1.0621362924575806, | |
| "eval_runtime": 157.2718, | |
| "eval_samples_per_second": 13.27, | |
| "eval_wer": 0.6191353237689027, | |
| "step": 4400 | |
| } | |
| ], | |
| "max_steps": 4470, | |
| "num_train_epochs": 30, | |
| "total_flos": 1.2337798222367355e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |