| { | |
| "best_metric": 88.49801162434996, | |
| "best_model_checkpoint": "../KevinKibe/whisper-small-finetuned_sw_rw-finetuned/checkpoint-300", | |
| "epoch": 4.096, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.074, | |
| "grad_norm": 2.8384125232696533, | |
| "learning_rate": 0.0008416666666666667, | |
| "loss": 4.4905, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.074, | |
| "eval_loss": 2.8438520431518555, | |
| "eval_runtime": 383.425, | |
| "eval_samples_per_second": 1.043, | |
| "eval_steps_per_second": 0.034, | |
| "eval_wer": 92.78066687060263, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.022, | |
| "grad_norm": 1.2937822341918945, | |
| "learning_rate": 0.0006333333333333333, | |
| "loss": 1.6483, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.022, | |
| "eval_loss": 2.450817346572876, | |
| "eval_runtime": 372.7904, | |
| "eval_samples_per_second": 1.073, | |
| "eval_steps_per_second": 0.035, | |
| "eval_wer": 89.47690425206486, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.096, | |
| "grad_norm": 1.0265976190567017, | |
| "learning_rate": 0.000425, | |
| "loss": 1.1522, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.096, | |
| "eval_loss": 2.3149287700653076, | |
| "eval_runtime": 268.4788, | |
| "eval_samples_per_second": 1.49, | |
| "eval_steps_per_second": 0.048, | |
| "eval_wer": 88.49801162434996, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "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": 2.80054659022848e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |