| { | |
| "best_metric": 4.342790966994789, | |
| "best_model_checkpoint": "./whisper-small-clean_3-400/checkpoint-300", | |
| "epoch": 1.1425, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 40.23651885986328, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 2.5163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 7.506647109985352, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.2556, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 1.3846545219421387, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.0402, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 2.7268073558807373, | |
| "learning_rate": 8.685714285714287e-06, | |
| "loss": 0.0726, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.07324936985969543, | |
| "eval_runtime": 637.792, | |
| "eval_samples_per_second": 2.708, | |
| "eval_steps_per_second": 0.085, | |
| "eval_wer": 11.29125651418645, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 1.9880954027175903, | |
| "learning_rate": 7.971428571428572e-06, | |
| "loss": 0.0443, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 2.2768521308898926, | |
| "learning_rate": 7.257142857142858e-06, | |
| "loss": 0.0098, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 1.8922802209854126, | |
| "learning_rate": 6.542857142857143e-06, | |
| "loss": 0.0132, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 23.585607528686523, | |
| "learning_rate": 5.828571428571429e-06, | |
| "loss": 0.0477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.05271298438310623, | |
| "eval_runtime": 666.0602, | |
| "eval_samples_per_second": 2.593, | |
| "eval_steps_per_second": 0.081, | |
| "eval_wer": 7.81702374059062, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 7.002109527587891, | |
| "learning_rate": 5.114285714285715e-06, | |
| "loss": 1.2932, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.0175, | |
| "grad_norm": 3.1741580963134766, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.2595, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.846144437789917, | |
| "learning_rate": 3.6857142857142857e-06, | |
| "loss": 0.0087, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.1425, | |
| "grad_norm": 0.018214385956525803, | |
| "learning_rate": 2.9714285714285716e-06, | |
| "loss": 0.0025, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1425, | |
| "eval_loss": 0.024332880973815918, | |
| "eval_runtime": 640.1006, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 0.084, | |
| "eval_wer": 4.342790966994789, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.53910817374208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |