| { | |
| "best_metric": 0.1460878551006317, | |
| "best_model_checkpoint": "/content/drive/MyDrive/RoBERTa/checkpoint-11636", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 11636, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.9410436153411865, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2361, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7993811242908716, | |
| "eval_f1": 0.8000383628284219, | |
| "eval_loss": 0.1618930995464325, | |
| "eval_precision": 0.801877689223025, | |
| "eval_recall": 0.7993811242908716, | |
| "eval_runtime": 100.7934, | |
| "eval_samples_per_second": 57.712, | |
| "eval_steps_per_second": 3.611, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.755303144454956, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1588, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8115867285542375, | |
| "eval_f1": 0.8119755242707591, | |
| "eval_loss": 0.14911070466041565, | |
| "eval_precision": 0.8130543725573091, | |
| "eval_recall": 0.8115867285542375, | |
| "eval_runtime": 100.747, | |
| "eval_samples_per_second": 57.739, | |
| "eval_steps_per_second": 3.613, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.666957139968872, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1425, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8151968368574867, | |
| "eval_f1": 0.8140299685788867, | |
| "eval_loss": 0.15050296485424042, | |
| "eval_precision": 0.8201423906704529, | |
| "eval_recall": 0.8151968368574867, | |
| "eval_runtime": 100.8777, | |
| "eval_samples_per_second": 57.664, | |
| "eval_steps_per_second": 3.608, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 3.600872278213501, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1322, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8182912154031288, | |
| "eval_f1": 0.8181033584717875, | |
| "eval_loss": 0.1460878551006317, | |
| "eval_precision": 0.8224312871560887, | |
| "eval_recall": 0.8182912154031288, | |
| "eval_runtime": 100.713, | |
| "eval_samples_per_second": 57.758, | |
| "eval_steps_per_second": 3.614, | |
| "step": 11636 | |
| } | |
| ], | |
| "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": 4.897619828740915e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |