| { |
| "best_global_step": 1000, |
| "best_metric": 288.4273750105744, |
| "best_model_checkpoint": "/workspace/output/whisper-changhua-noise-augment/checkpoint-1000", |
| "epoch": 13.157894736842104, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6578947368421053, |
| "grad_norm": 21.399112701416016, |
| "learning_rate": 9.800000000000001e-07, |
| "loss": 5.5843, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "grad_norm": 20.421926498413086, |
| "learning_rate": 1.98e-06, |
| "loss": 2.9342, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "eval_cer": 308.20573555536754, |
| "eval_loss": 2.089763879776001, |
| "eval_runtime": 36.6175, |
| "eval_samples_per_second": 12.371, |
| "eval_steps_per_second": 3.113, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.973684210526316, |
| "grad_norm": 12.31893253326416, |
| "learning_rate": 2.9800000000000003e-06, |
| "loss": 1.6917, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "grad_norm": 9.420328140258789, |
| "learning_rate": 3.980000000000001e-06, |
| "loss": 1.2816, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "eval_cer": 292.1834024194231, |
| "eval_loss": 1.3020572662353516, |
| "eval_runtime": 36.4379, |
| "eval_samples_per_second": 12.432, |
| "eval_steps_per_second": 3.129, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.2894736842105265, |
| "grad_norm": 8.891965866088867, |
| "learning_rate": 4.980000000000001e-06, |
| "loss": 1.0707, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.9473684210526314, |
| "grad_norm": 7.001476287841797, |
| "learning_rate": 5.98e-06, |
| "loss": 0.7935, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.9473684210526314, |
| "eval_cer": 293.7822519245411, |
| "eval_loss": 0.6184566617012024, |
| "eval_runtime": 36.5211, |
| "eval_samples_per_second": 12.404, |
| "eval_steps_per_second": 3.121, |
| "step": 300 |
| }, |
| { |
| "epoch": 4.605263157894737, |
| "grad_norm": 4.6337056159973145, |
| "learning_rate": 6.98e-06, |
| "loss": 0.4507, |
| "step": 350 |
| }, |
| { |
| "epoch": 5.2631578947368425, |
| "grad_norm": 4.506453037261963, |
| "learning_rate": 7.980000000000002e-06, |
| "loss": 0.3631, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.2631578947368425, |
| "eval_cer": 307.46129769055074, |
| "eval_loss": 0.5401062965393066, |
| "eval_runtime": 37.0582, |
| "eval_samples_per_second": 12.224, |
| "eval_steps_per_second": 3.076, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.921052631578947, |
| "grad_norm": 4.677835941314697, |
| "learning_rate": 8.98e-06, |
| "loss": 0.2982, |
| "step": 450 |
| }, |
| { |
| "epoch": 6.578947368421053, |
| "grad_norm": 4.149691104888916, |
| "learning_rate": 9.980000000000001e-06, |
| "loss": 0.2073, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.578947368421053, |
| "eval_cer": 308.4764402334828, |
| "eval_loss": 0.5505404472351074, |
| "eval_runtime": 37.288, |
| "eval_samples_per_second": 12.149, |
| "eval_steps_per_second": 3.057, |
| "step": 500 |
| }, |
| { |
| "epoch": 7.2368421052631575, |
| "grad_norm": 2.7972090244293213, |
| "learning_rate": 9.94842105263158e-06, |
| "loss": 0.173, |
| "step": 550 |
| }, |
| { |
| "epoch": 7.894736842105263, |
| "grad_norm": 3.728022336959839, |
| "learning_rate": 9.895789473684212e-06, |
| "loss": 0.1286, |
| "step": 600 |
| }, |
| { |
| "epoch": 7.894736842105263, |
| "eval_cer": 298.18966246510445, |
| "eval_loss": 0.5637083649635315, |
| "eval_runtime": 36.7159, |
| "eval_samples_per_second": 12.338, |
| "eval_steps_per_second": 3.105, |
| "step": 600 |
| }, |
| { |
| "epoch": 8.552631578947368, |
| "grad_norm": 2.9424517154693604, |
| "learning_rate": 9.843157894736843e-06, |
| "loss": 0.0844, |
| "step": 650 |
| }, |
| { |
| "epoch": 9.210526315789474, |
| "grad_norm": 2.0768165588378906, |
| "learning_rate": 9.790526315789475e-06, |
| "loss": 0.0662, |
| "step": 700 |
| }, |
| { |
| "epoch": 9.210526315789474, |
| "eval_cer": 297.74130784197615, |
| "eval_loss": 0.5866815447807312, |
| "eval_runtime": 36.914, |
| "eval_samples_per_second": 12.272, |
| "eval_steps_per_second": 3.088, |
| "step": 700 |
| }, |
| { |
| "epoch": 9.868421052631579, |
| "grad_norm": 3.016207456588745, |
| "learning_rate": 9.737894736842107e-06, |
| "loss": 0.0475, |
| "step": 750 |
| }, |
| { |
| "epoch": 10.526315789473685, |
| "grad_norm": 2.538983106613159, |
| "learning_rate": 9.685263157894738e-06, |
| "loss": 0.0337, |
| "step": 800 |
| }, |
| { |
| "epoch": 10.526315789473685, |
| "eval_cer": 299.323238304712, |
| "eval_loss": 0.6221126317977905, |
| "eval_runtime": 36.8407, |
| "eval_samples_per_second": 12.296, |
| "eval_steps_per_second": 3.094, |
| "step": 800 |
| }, |
| { |
| "epoch": 11.18421052631579, |
| "grad_norm": 1.640647053718567, |
| "learning_rate": 9.63263157894737e-06, |
| "loss": 0.0305, |
| "step": 850 |
| }, |
| { |
| "epoch": 11.842105263157894, |
| "grad_norm": 2.073720932006836, |
| "learning_rate": 9.58e-06, |
| "loss": 0.022, |
| "step": 900 |
| }, |
| { |
| "epoch": 11.842105263157894, |
| "eval_cer": 288.73191777345403, |
| "eval_loss": 0.651242733001709, |
| "eval_runtime": 36.7863, |
| "eval_samples_per_second": 12.314, |
| "eval_steps_per_second": 3.099, |
| "step": 900 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 1.0177150964736938, |
| "learning_rate": 9.527368421052631e-06, |
| "loss": 0.0187, |
| "step": 950 |
| }, |
| { |
| "epoch": 13.157894736842104, |
| "grad_norm": 0.913955569267273, |
| "learning_rate": 9.474736842105265e-06, |
| "loss": 0.0169, |
| "step": 1000 |
| }, |
| { |
| "epoch": 13.157894736842104, |
| "eval_cer": 288.4273750105744, |
| "eval_loss": 0.6658270359039307, |
| "eval_runtime": 36.8153, |
| "eval_samples_per_second": 12.305, |
| "eval_steps_per_second": 3.097, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 132, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 10, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.385209966087897e+19, |
| "train_batch_size": 12, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
