| { |
| "best_metric": 0.570550262928009, |
| "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-2785", |
| "epoch": 5.0, |
| "eval_steps": 100, |
| "global_step": 2785, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.1359150409698486, |
| "learning_rate": 4.5e-06, |
| "loss": 0.6958, |
| "step": 557 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5296762589928058, |
| "eval_f1": 0.5188592456301748, |
| "eval_loss": 0.6925909519195557, |
| "eval_precision": 0.5454545454545454, |
| "eval_recall": 0.49473684210526314, |
| "eval_runtime": 24.1607, |
| "eval_samples_per_second": 46.025, |
| "eval_steps_per_second": 2.897, |
| "step": 557 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 8.246417999267578, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.6676, |
| "step": 1114 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6519784172661871, |
| "eval_f1": 0.7160674981658107, |
| "eval_loss": 0.6172838807106018, |
| "eval_precision": 0.6153846153846154, |
| "eval_recall": 0.856140350877193, |
| "eval_runtime": 23.8527, |
| "eval_samples_per_second": 46.619, |
| "eval_steps_per_second": 2.935, |
| "step": 1114 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 68.80496215820312, |
| "learning_rate": 3.5e-06, |
| "loss": 0.5867, |
| "step": 1671 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6915467625899281, |
| "eval_f1": 0.6809302325581396, |
| "eval_loss": 0.5942487120628357, |
| "eval_precision": 0.7247524752475247, |
| "eval_recall": 0.6421052631578947, |
| "eval_runtime": 24.0034, |
| "eval_samples_per_second": 46.327, |
| "eval_steps_per_second": 2.916, |
| "step": 1671 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 15.448868751525879, |
| "learning_rate": 3e-06, |
| "loss": 0.5309, |
| "step": 2228 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7059352517985612, |
| "eval_f1": 0.7067264573991031, |
| "eval_loss": 0.5705930590629578, |
| "eval_precision": 0.7229357798165138, |
| "eval_recall": 0.6912280701754386, |
| "eval_runtime": 23.8606, |
| "eval_samples_per_second": 46.604, |
| "eval_steps_per_second": 2.934, |
| "step": 2228 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 36.05428695678711, |
| "learning_rate": 2.5e-06, |
| "loss": 0.4821, |
| "step": 2785 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7140287769784173, |
| "eval_f1": 0.741042345276873, |
| "eval_loss": 0.570550262928009, |
| "eval_precision": 0.6914893617021277, |
| "eval_recall": 0.7982456140350878, |
| "eval_runtime": 23.8434, |
| "eval_samples_per_second": 46.638, |
| "eval_steps_per_second": 2.936, |
| "step": 2785 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5570, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": 4.146162635446272e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
