{ "best_global_step": 2757, "best_metric": 0.8695398280390421, "best_model_checkpoint": "outputs/hate-speech-detection/sphobert/checkpoint-2757", "epoch": 3.0, "eval_steps": 500, "global_step": 2757, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.998911860718172, "grad_norm": 4.184622287750244, "learning_rate": 1.9996091589167148e-05, "loss": 0.4416, "step": 918 }, { "epoch": 1.0, "eval_accuracy": 0.8672093023255814, "eval_f1": 0.8518449095766703, "eval_loss": 0.3689223527908325, "eval_precision": 0.8462192542311449, "eval_recall": 0.8672093023255814, "eval_runtime": 38.1007, "eval_samples_per_second": 112.859, "eval_steps_per_second": 3.543, "step": 919 }, { "epoch": 1.997823721436344, "grad_norm": 6.81333589553833, "learning_rate": 1.9982377977480694e-05, "loss": 0.3299, "step": 1836 }, { "epoch": 2.0, "eval_accuracy": 0.8806976744186047, "eval_f1": 0.8616461626459706, "eval_loss": 0.3702216148376465, "eval_precision": 0.8647081088093735, "eval_recall": 0.8806976744186047, "eval_runtime": 40.0641, "eval_samples_per_second": 107.328, "eval_steps_per_second": 3.37, "step": 1838 }, { "epoch": 2.996735582154516, "grad_norm": 7.187419414520264, "learning_rate": 1.9958812963917564e-05, "loss": 0.2644, "step": 2754 }, { "epoch": 3.0, "eval_accuracy": 0.878139534883721, "eval_f1": 0.8695398280390421, "eval_loss": 0.3386484682559967, "eval_precision": 0.8660161855016026, "eval_recall": 0.878139534883721, "eval_runtime": 40.1821, "eval_samples_per_second": 107.013, "eval_steps_per_second": 3.36, "step": 2757 } ], "logging_steps": 918, "max_steps": 91900, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "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": 0.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }