| { |
| "best_metric": 31.703204047217536, |
| "best_model_checkpoint": "./whisper-tiny-hindi2_test/checkpoint-80", |
| "epoch": 6.349206349206349, |
| "eval_steps": 40, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6349206349206349, |
| "grad_norm": 5.663797855377197, |
| "learning_rate": 3.75e-05, |
| "loss": 0.3885, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "grad_norm": 4.554736137390137, |
| "learning_rate": 3.75e-05, |
| "loss": 0.2894, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "eval_loss": 0.21782219409942627, |
| "eval_runtime": 55.5859, |
| "eval_samples_per_second": 1.799, |
| "eval_steps_per_second": 1.799, |
| "eval_wer": 32.96795952782462, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 4.489897727966309, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1965, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "grad_norm": 2.790485382080078, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1333, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "eval_loss": 0.2209174931049347, |
| "eval_runtime": 55.2087, |
| "eval_samples_per_second": 1.811, |
| "eval_steps_per_second": 1.811, |
| "eval_wer": 31.703204047217536, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1746031746031744, |
| "grad_norm": 2.2434844970703125, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1016, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "grad_norm": 2.5447564125061035, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0599, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "eval_loss": 0.23671233654022217, |
| "eval_runtime": 55.6056, |
| "eval_samples_per_second": 1.798, |
| "eval_steps_per_second": 1.798, |
| "eval_wer": 33.22091062394604, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 2.4546711444854736, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0414, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "grad_norm": 1.9287947416305542, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0332, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "eval_loss": 0.24990424513816833, |
| "eval_runtime": 55.3919, |
| "eval_samples_per_second": 1.805, |
| "eval_steps_per_second": 1.805, |
| "eval_wer": 31.871838111298484, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.714285714285714, |
| "grad_norm": 2.413437843322754, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0232, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "grad_norm": 2.503246784210205, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0189, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "eval_loss": 0.27371078729629517, |
| "eval_runtime": 55.2258, |
| "eval_samples_per_second": 1.811, |
| "eval_steps_per_second": 1.811, |
| "eval_wer": 33.05227655986509, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "step": 200, |
| "total_flos": 1.5637915828224e+17, |
| "train_loss": 0.1285850764811039, |
| "train_runtime": 1129.5385, |
| "train_samples_per_second": 5.666, |
| "train_steps_per_second": 0.177 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "save_steps": 40, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5637915828224e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
