| { |
| "best_metric": 37.60539629005059, |
| "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": 5.881579875946045, |
| "learning_rate": 3.75e-05, |
| "loss": 0.3939, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "grad_norm": 4.580193996429443, |
| "learning_rate": 3.75e-05, |
| "loss": 0.312, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "eval_loss": 0.26820191740989685, |
| "eval_runtime": 55.3328, |
| "eval_samples_per_second": 1.807, |
| "eval_steps_per_second": 1.807, |
| "eval_wer": 38.61720067453626, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 4.671483039855957, |
| "learning_rate": 3.75e-05, |
| "loss": 0.2298, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "grad_norm": 4.34619140625, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1574, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "eval_loss": 0.2759854197502136, |
| "eval_runtime": 55.1922, |
| "eval_samples_per_second": 1.812, |
| "eval_steps_per_second": 1.812, |
| "eval_wer": 37.60539629005059, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1746031746031744, |
| "grad_norm": 2.468874216079712, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1358, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "grad_norm": 3.0758771896362305, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0914, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "eval_loss": 0.29828593134880066, |
| "eval_runtime": 54.9217, |
| "eval_samples_per_second": 1.821, |
| "eval_steps_per_second": 1.821, |
| "eval_wer": 37.60539629005059, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 2.6510117053985596, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0666, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "grad_norm": 1.7483832836151123, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0579, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "eval_loss": 0.3087254464626312, |
| "eval_runtime": 54.9389, |
| "eval_samples_per_second": 1.82, |
| "eval_steps_per_second": 1.82, |
| "eval_wer": 37.77403035413153, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.714285714285714, |
| "grad_norm": 2.245854139328003, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0354, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "grad_norm": 1.88152015209198, |
| "learning_rate": 3.75e-05, |
| "loss": 0.028, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "eval_loss": 0.3585308790206909, |
| "eval_runtime": 54.6288, |
| "eval_samples_per_second": 1.831, |
| "eval_steps_per_second": 1.831, |
| "eval_wer": 38.27993254637437, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "step": 200, |
| "total_flos": 1.5637915828224e+17, |
| "train_loss": 0.15080839216709138, |
| "train_runtime": 1129.7922, |
| "train_samples_per_second": 5.665, |
| "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 |
| } |
|
|
