| { |
| "best_metric": 41.31534569983137, |
| "best_model_checkpoint": "./whisper-tiny-hindi2_test/checkpoint-160", |
| "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": 5.291396141052246, |
| "learning_rate": 3.75e-05, |
| "loss": 0.486, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "grad_norm": 4.965972423553467, |
| "learning_rate": 3.75e-05, |
| "loss": 0.3869, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "eval_loss": 0.35420987010002136, |
| "eval_runtime": 54.9702, |
| "eval_samples_per_second": 1.819, |
| "eval_steps_per_second": 1.819, |
| "eval_wer": 46.964586846543, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 5.148536682128906, |
| "learning_rate": 3.75e-05, |
| "loss": 0.3043, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "grad_norm": 4.049417972564697, |
| "learning_rate": 3.75e-05, |
| "loss": 0.2215, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.5396825396825395, |
| "eval_loss": 0.3464047908782959, |
| "eval_runtime": 55.3552, |
| "eval_samples_per_second": 1.807, |
| "eval_steps_per_second": 1.807, |
| "eval_wer": 45.27824620573356, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1746031746031744, |
| "grad_norm": 3.4034841060638428, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1888, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "grad_norm": 4.5857930183410645, |
| "learning_rate": 3.75e-05, |
| "loss": 0.1394, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "eval_loss": 0.34948885440826416, |
| "eval_runtime": 54.9671, |
| "eval_samples_per_second": 1.819, |
| "eval_steps_per_second": 1.819, |
| "eval_wer": 43.00168634064081, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 3.3065757751464844, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0954, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "grad_norm": 2.241292953491211, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0857, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.079365079365079, |
| "eval_loss": 0.37522462010383606, |
| "eval_runtime": 55.4528, |
| "eval_samples_per_second": 1.803, |
| "eval_steps_per_second": 1.803, |
| "eval_wer": 41.31534569983137, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.714285714285714, |
| "grad_norm": 2.4962286949157715, |
| "learning_rate": 3.75e-05, |
| "loss": 0.055, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "grad_norm": 2.652437210083008, |
| "learning_rate": 3.75e-05, |
| "loss": 0.0434, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "eval_loss": 0.40884342789649963, |
| "eval_runtime": 55.4835, |
| "eval_samples_per_second": 1.802, |
| "eval_steps_per_second": 1.802, |
| "eval_wer": 43.76053962900506, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.349206349206349, |
| "step": 200, |
| "total_flos": 1.5637915828224e+17, |
| "train_loss": 0.2006339970231056, |
| "train_runtime": 1120.101, |
| "train_samples_per_second": 5.714, |
| "train_steps_per_second": 0.179 |
| } |
| ], |
| "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 |
| } |
|
|
