| { |
| "best_global_step": 200, |
| "best_metric": 0.9943728018757327, |
| "best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200", |
| "epoch": 0.18757327080890973, |
| "eval_steps": 200, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00023446658851113716, |
| "grad_norm": 7.900483131408691, |
| "learning_rate": 0.0, |
| "loss": 1.2285, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.023446658851113716, |
| "grad_norm": 2.4035584926605225, |
| "learning_rate": 2.9015240328253227e-06, |
| "loss": 0.9217, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04689331770222743, |
| "grad_norm": 0.31396016478538513, |
| "learning_rate": 5.832356389214537e-06, |
| "loss": 0.073, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.04689331770222743, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1_macro": 0.24929461556548319, |
| "eval_f1_weighted": 0.9915671414895327, |
| "eval_loss": 0.04064385965466499, |
| "eval_runtime": 57.486, |
| "eval_samples_per_second": 148.384, |
| "eval_steps_per_second": 9.289, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.07033997655334115, |
| "grad_norm": 0.14905625581741333, |
| "learning_rate": 8.763188745603752e-06, |
| "loss": 0.0474, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.09378663540445487, |
| "grad_norm": 0.08281561732292175, |
| "learning_rate": 1.1694021101992966e-05, |
| "loss": 0.0334, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.09378663540445487, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1_macro": 0.24929461556548319, |
| "eval_f1_weighted": 0.9915671414895327, |
| "eval_loss": 0.04262762889266014, |
| "eval_runtime": 54.8606, |
| "eval_samples_per_second": 155.485, |
| "eval_steps_per_second": 9.734, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.11723329425556858, |
| "grad_norm": 0.04056438058614731, |
| "learning_rate": 1.4624853458382182e-05, |
| "loss": 0.04, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1406799531066823, |
| "grad_norm": 0.04737967997789383, |
| "learning_rate": 1.7555685814771398e-05, |
| "loss": 0.0502, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.1406799531066823, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1_macro": 0.24929461556548319, |
| "eval_f1_weighted": 0.9915671414895327, |
| "eval_loss": 0.04288283362984657, |
| "eval_runtime": 54.7704, |
| "eval_samples_per_second": 155.741, |
| "eval_steps_per_second": 9.75, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.16412661195779601, |
| "grad_norm": 0.14134405553340912, |
| "learning_rate": 2.048651817116061e-05, |
| "loss": 0.0605, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.18757327080890973, |
| "grad_norm": 0.11066514253616333, |
| "learning_rate": 2.3417350527549826e-05, |
| "loss": 0.0325, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.18757327080890973, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1_macro": 0.24929461556548319, |
| "eval_f1_weighted": 0.9915671414895327, |
| "eval_loss": 0.04036899656057358, |
| "eval_runtime": 54.8996, |
| "eval_samples_per_second": 155.375, |
| "eval_steps_per_second": 9.727, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 17060, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2525934167654400.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
