{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09237875288683603, "eval_steps": 100, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04608294930875576, "grad_norm": 3.232759714126587, "learning_rate": 4.999735579817769e-05, "loss": 1.4008, "step": 10 }, { "epoch": 0.09237875288683603, "grad_norm": 2.0704426765441895, "learning_rate": 4.997598371650346e-05, "loss": 1.388, "step": 20 } ], "logging_steps": 10, "max_steps": 1080, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 47859389030400.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }