| { |
| "best_global_step": 1784, |
| "best_metric": 0.7424307052322987, |
| "best_model_checkpoint": "outputs/mbert-spam-multiclass/checkpoint-1784", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1784, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.718122661113739, |
| "learning_rate": 4.998771926094749e-05, |
| "loss": 0.4205, |
| "step": 446 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8846880907372401, |
| "eval_f1": 0.6497507877391984, |
| "eval_loss": 0.36673811078071594, |
| "eval_precision": 0.7950539055043409, |
| "eval_recall": 0.5966946689462213, |
| "eval_runtime": 1.8876, |
| "eval_samples_per_second": 840.735, |
| "eval_steps_per_second": 26.488, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 8.896832466125488, |
| "learning_rate": 4.995077872180951e-05, |
| "loss": 0.2976, |
| "step": 892 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8928796471329553, |
| "eval_f1": 0.7307096160459899, |
| "eval_loss": 0.34850800037384033, |
| "eval_precision": 0.8328975143146583, |
| "eval_recall": 0.6755418632791529, |
| "eval_runtime": 1.8873, |
| "eval_samples_per_second": 840.902, |
| "eval_steps_per_second": 26.493, |
| "step": 892 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.093507766723633, |
| "learning_rate": 4.988921477641713e-05, |
| "loss": 0.2378, |
| "step": 1338 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8651543793320731, |
| "eval_f1": 0.6932333947923072, |
| "eval_loss": 0.40883514285087585, |
| "eval_precision": 0.7921159351026835, |
| "eval_recall": 0.6868319709426316, |
| "eval_runtime": 1.8897, |
| "eval_samples_per_second": 839.824, |
| "eval_steps_per_second": 26.459, |
| "step": 1338 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 7.626230239868164, |
| "learning_rate": 4.980308818095173e-05, |
| "loss": 0.1903, |
| "step": 1784 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8764965343415249, |
| "eval_f1": 0.7424307052322987, |
| "eval_loss": 0.3517472445964813, |
| "eval_precision": 0.802800525730462, |
| "eval_recall": 0.7160022972277378, |
| "eval_runtime": 1.8913, |
| "eval_samples_per_second": 839.095, |
| "eval_steps_per_second": 26.437, |
| "step": 1784 |
| } |
| ], |
| "logging_steps": 446, |
| "max_steps": 44600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
