{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.9239653512993262, "grad_norm": 79.3982925415039, "learning_rate": 6.161538461538462e-06, "loss": -100.81, "step": 500 }, { "epoch": 3.846968238691049, "grad_norm": 95.40797424316406, "learning_rate": 2.3153846153846153e-06, "loss": -150.2456, "step": 1000 } ], "logging_steps": 500, "max_steps": 1300, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 2, "trial_name": null, "trial_params": null }