| { | |
| "best_metric": 0.1501207798719406, | |
| "best_model_checkpoint": "/content/drive/MyDrive/RoBERTa/checkpoint-14545", | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 14545, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.497077941894531, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2489, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7945676465532061, | |
| "eval_f1": 0.7961558430656073, | |
| "eval_loss": 0.16617761552333832, | |
| "eval_precision": 0.801102553760894, | |
| "eval_recall": 0.7945676465532061, | |
| "eval_runtime": 46.2471, | |
| "eval_samples_per_second": 125.781, | |
| "eval_steps_per_second": 7.871, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.7504544258117676, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.165, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8066013408973698, | |
| "eval_f1": 0.806334324115106, | |
| "eval_loss": 0.15410974621772766, | |
| "eval_precision": 0.807004318007734, | |
| "eval_recall": 0.8066013408973698, | |
| "eval_runtime": 46.1274, | |
| "eval_samples_per_second": 126.107, | |
| "eval_steps_per_second": 7.891, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.142695426940918, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1479, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8038507821901324, | |
| "eval_f1": 0.8008391832785562, | |
| "eval_loss": 0.15494388341903687, | |
| "eval_precision": 0.8086474488952677, | |
| "eval_recall": 0.8038507821901324, | |
| "eval_runtime": 46.076, | |
| "eval_samples_per_second": 126.248, | |
| "eval_steps_per_second": 7.9, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 16.692214965820312, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1375, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8102114492006188, | |
| "eval_f1": 0.8090868438898687, | |
| "eval_loss": 0.15274302661418915, | |
| "eval_precision": 0.8111386977694952, | |
| "eval_recall": 0.8102114492006188, | |
| "eval_runtime": 46.1151, | |
| "eval_samples_per_second": 126.141, | |
| "eval_steps_per_second": 7.893, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 24.896465301513672, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.1289, | |
| "step": 14545 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8096957194430119, | |
| "eval_f1": 0.8100808721825671, | |
| "eval_loss": 0.1501207798719406, | |
| "eval_precision": 0.8116662168004147, | |
| "eval_recall": 0.8096957194430119, | |
| "eval_runtime": 46.0976, | |
| "eval_samples_per_second": 126.189, | |
| "eval_steps_per_second": 7.896, | |
| "step": 14545 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 29090, | |
| "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": 6.122024785926144e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |