| { |
| "best_global_step": 1500, |
| "best_metric": 29.051360086819074, |
| "best_model_checkpoint": "./ZINASR/checkpoint-1500", |
| "epoch": 2.5778159931212383, |
| "eval_steps": 500, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.34393809114359414, |
| "grad_norm": 3.4750354290008545, |
| "learning_rate": 9.9e-06, |
| "loss": 0.1655, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6878761822871883, |
| "grad_norm": 3.458239793777466, |
| "learning_rate": 8.719275549805952e-06, |
| "loss": 0.1352, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8598452278589854, |
| "eval_loss": 0.43551918864250183, |
| "eval_runtime": 3356.5685, |
| "eval_samples_per_second": 1.385, |
| "eval_steps_per_second": 0.173, |
| "eval_wer": 30.011560148158633, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0309544282029235, |
| "grad_norm": 2.6634328365325928, |
| "learning_rate": 7.425614489003882e-06, |
| "loss": 0.135, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.3748925193465176, |
| "grad_norm": 3.2597954273223877, |
| "learning_rate": 6.1319534282018115e-06, |
| "loss": 0.0783, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.7188306104901119, |
| "grad_norm": 3.3078627586364746, |
| "learning_rate": 4.838292367399742e-06, |
| "loss": 0.0944, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7188306104901119, |
| "eval_loss": 0.43551915884017944, |
| "eval_runtime": 3363.7968, |
| "eval_samples_per_second": 1.382, |
| "eval_steps_per_second": 0.173, |
| "eval_wer": 29.334465756010097, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.061908856405847, |
| "grad_norm": 3.6673755645751953, |
| "learning_rate": 3.5446313065976717e-06, |
| "loss": 0.1003, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.405846947549441, |
| "grad_norm": 3.501398801803589, |
| "learning_rate": 2.2509702457956016e-06, |
| "loss": 0.0474, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.5778159931212383, |
| "eval_loss": 0.45564955472946167, |
| "eval_runtime": 3360.7459, |
| "eval_samples_per_second": 1.384, |
| "eval_steps_per_second": 0.173, |
| "eval_wer": 29.051360086819074, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 1746, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.383651560374272e+19, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
