{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1900, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0526315789473684, "grad_norm": 4.899050235748291, "learning_rate": 3.686842105263158e-05, "loss": 0.4032, "step": 500 }, { "epoch": 2.1052631578947367, "grad_norm": 1.965386986732483, "learning_rate": 2.3710526315789475e-05, "loss": 0.1094, "step": 1000 }, { "epoch": 3.1578947368421053, "grad_norm": 0.382137268781662, "learning_rate": 1.055263157894737e-05, "loss": 0.0476, "step": 1500 } ], "logging_steps": 500, "max_steps": 1900, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }