| { | |
| "best_global_step": 100, | |
| "best_metric": 26.867363647814585, | |
| "best_model_checkpoint": "whisper-base-synth-v1/checkpoint-100", | |
| "epoch": 2.127659574468085, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26595744680851063, | |
| "grad_norm": 81.76741790771484, | |
| "learning_rate": 1.1702127659574467e-06, | |
| "loss": 13.222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 17.427486419677734, | |
| "learning_rate": 2.5e-06, | |
| "loss": 7.0809, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "grad_norm": 6.602798938751221, | |
| "learning_rate": 3.8297872340425535e-06, | |
| "loss": 5.3964, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 4.553112983703613, | |
| "learning_rate": 5.159574468085106e-06, | |
| "loss": 4.8621, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_loss": 0.21504688262939453, | |
| "eval_runtime": 699.3473, | |
| "eval_samples_per_second": 4.005, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 26.867363647814585, | |
| "eval_wer_ortho": 29.74588938714499, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 4.06046724319458, | |
| "learning_rate": 6.489361702127659e-06, | |
| "loss": 4.6403, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 4.466408729553223, | |
| "learning_rate": 7.819148936170213e-06, | |
| "loss": 4.4984, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.8617021276595744, | |
| "grad_norm": 4.118725776672363, | |
| "learning_rate": 9.148936170212767e-06, | |
| "loss": 4.3114, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 3.9775619506835938, | |
| "learning_rate": 1.047872340425532e-05, | |
| "loss": 4.0801, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_loss": 0.42653512954711914, | |
| "eval_runtime": 777.2367, | |
| "eval_samples_per_second": 3.604, | |
| "eval_steps_per_second": 0.057, | |
| "eval_wer": 82.38653062938238, | |
| "eval_wer_ortho": 79.16874273376516, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 9400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "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": 8.2813243097088e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |