{ "best_global_step": 200, "best_metric": 0.997965707643127, "best_model_checkpoint": "models/tinybert-enron\\checkpoint-200", "epoch": 0.21119324181626187, "eval_steps": 200, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05279831045406547, "grad_norm": 0.7054851055145264, "learning_rate": 3.878627968337731e-06, "loss": 0.6916, "step": 50 }, { "epoch": 0.10559662090813093, "grad_norm": 4.758987903594971, "learning_rate": 7.836411609498681e-06, "loss": 0.6419, "step": 100 }, { "epoch": 0.1583949313621964, "grad_norm": 2.878147602081299, "learning_rate": 1.179419525065963e-05, "loss": 0.4382, "step": 150 }, { "epoch": 0.21119324181626187, "grad_norm": 0.9188410639762878, "learning_rate": 1.575197889182058e-05, "loss": 0.2162, "step": 200 }, { "epoch": 0.21119324181626187, "eval_accuracy": 0.997920997920998, "eval_f1": 0.997965707643127, "eval_loss": 0.11409526318311691, "eval_precision": 0.9959396751740139, "eval_recall": 1.0, "eval_runtime": 77.9734, "eval_samples_per_second": 43.181, "eval_steps_per_second": 2.706, "step": 200 } ], "logging_steps": 50, "max_steps": 3788, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 200, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.0005 }, "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": 45884787916800.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }