| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 2940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 5.039, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_loss": 2.9455764293670654, | |
| "eval_runtime": 358.486, | |
| "eval_samples_per_second": 6.999, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00028770491803278684, | |
| "loss": 2.9411, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_loss": 2.8372132778167725, | |
| "eval_runtime": 362.2267, | |
| "eval_samples_per_second": 6.927, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 0.00025081967213114756, | |
| "loss": 0.9286, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 0.3580135107040405, | |
| "eval_runtime": 372.9874, | |
| "eval_samples_per_second": 6.727, | |
| "eval_wer": 0.514917421417155, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 0.0002139344262295082, | |
| "loss": 0.3039, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "eval_loss": 0.33028751611709595, | |
| "eval_runtime": 377.8898, | |
| "eval_samples_per_second": 6.64, | |
| "eval_wer": 0.44296084176878, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 0.00017704918032786883, | |
| "loss": 0.2022, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "eval_loss": 0.30936819314956665, | |
| "eval_runtime": 374.6431, | |
| "eval_samples_per_second": 6.697, | |
| "eval_wer": 0.4007059136920618, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 0.00014016393442622951, | |
| "loss": 0.1529, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "eval_loss": 0.3163447976112366, | |
| "eval_runtime": 381.4751, | |
| "eval_samples_per_second": 6.577, | |
| "eval_wer": 0.38395711241342567, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 0.00010327868852459015, | |
| "loss": 0.1165, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "eval_loss": 0.3391939103603363, | |
| "eval_runtime": 380.5289, | |
| "eval_samples_per_second": 6.593, | |
| "eval_wer": 0.3692061800745871, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 6.639344262295081e-05, | |
| "loss": 0.1058, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "eval_loss": 0.35883328318595886, | |
| "eval_runtime": 376.435, | |
| "eval_samples_per_second": 6.665, | |
| "eval_wer": 0.3648774640383591, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 2.950819672131147e-05, | |
| "loss": 0.086, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "eval_loss": 0.35711735486984253, | |
| "eval_runtime": 376.6441, | |
| "eval_samples_per_second": 6.661, | |
| "eval_wer": 0.3572522642514651, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 2940, | |
| "total_flos": 3.401354569939134e+19, | |
| "train_runtime": 32379.322, | |
| "train_samples_per_second": 0.091 | |
| } | |
| ], | |
| "max_steps": 2940, | |
| "num_train_epochs": 30, | |
| "total_flos": 3.401354569939134e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |