{ "best_metric": 0.708745440947976, "best_model_checkpoint": "./run_seed_42/checkpoint-188", "epoch": 1.0, "eval_steps": 500, "global_step": 188, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.26595744680851063, "grad_norm": 4.2967529296875, "learning_rate": 1.754385964912281e-05, "loss": 0.9658, "step": 50 }, { "epoch": 0.5319148936170213, "grad_norm": 5.152985095977783, "learning_rate": 1.8303747534516768e-05, "loss": 0.8554, "step": 100 }, { "epoch": 0.7978723404255319, "grad_norm": 3.6444594860076904, "learning_rate": 1.6331360946745562e-05, "loss": 0.8136, "step": 150 }, { "epoch": 1.0, "eval_accuracy": 0.7245989304812834, "eval_f1_macro": 0.708745440947976, "eval_f1_weighted": 0.7325385090858103, "eval_loss": 0.7565225958824158, "eval_precision_macro": 0.7206246999350449, "eval_recall_macro": 0.7151010443712931, "eval_runtime": 0.826, "eval_samples_per_second": 452.773, "eval_steps_per_second": 14.527, "step": 188 } ], "logging_steps": 50, "max_steps": 564, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "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": 252646437079008.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }