{ "best_metric": 0.28317779302597046, "best_model_checkpoint": "./model_sentiment/checkpoint-1300", "epoch": 3.0, "eval_steps": 500, "global_step": 1950, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 7.652286529541016, "learning_rate": 1.866666666666667e-05, "loss": 0.4381, "step": 650 }, { "epoch": 1.0, "eval_accuracy": 0.7561327561327561, "eval_f1": 0.8001123753336142, "eval_f1_macro": 0.7961336354425609, "eval_loss": 0.3537029027938843, "eval_runtime": 6.6113, "eval_samples_per_second": 524.102, "eval_steps_per_second": 32.823, "step": 650 }, { "epoch": 2.0, "grad_norm": 13.353829383850098, "learning_rate": 1.7333333333333336e-05, "loss": 0.2336, "step": 1300 }, { "epoch": 2.0, "eval_accuracy": 0.8207792207792208, "eval_f1": 0.8560773480662983, "eval_f1_macro": 0.853074547088536, "eval_loss": 0.28317779302597046, "eval_runtime": 6.6046, "eval_samples_per_second": 524.635, "eval_steps_per_second": 32.856, "step": 1300 }, { "epoch": 3.0, "grad_norm": 29.17078971862793, "learning_rate": 1.6000000000000003e-05, "loss": 0.1322, "step": 1950 }, { "epoch": 3.0, "eval_accuracy": 0.8421356421356422, "eval_f1": 0.8724869182043515, "eval_f1_macro": 0.8692950229330473, "eval_loss": 0.2874596118927002, "eval_runtime": 6.5966, "eval_samples_per_second": 525.269, "eval_steps_per_second": 32.896, "step": 1950 } ], "logging_steps": 500, "max_steps": 9750, "num_input_tokens_seen": 0, "num_train_epochs": 15, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "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": 2050903312835328.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }