| { | |
| "best_metric": 34.77924089852827, | |
| "best_model_checkpoint": "./whisper-small-clean_v6/checkpoint-100", | |
| "epoch": 0.2, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 24.222782135009766, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.5789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 3.7403714656829834, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.2766, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 3.9098994731903076, | |
| "learning_rate": 9.533333333333334e-06, | |
| "loss": 0.1533, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.8178775310516357, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 0.1354, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.4426867365837097, | |
| "eval_runtime": 177.5025, | |
| "eval_samples_per_second": 1.792, | |
| "eval_steps_per_second": 0.056, | |
| "eval_wer": 34.77924089852827, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "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": 1.846946562048e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |