{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03571428571428571, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.017857142857142856, "grad_norm": 1.5585895776748657, "learning_rate": 5.9523809523809524e-05, "loss": 5.8862, "step": 25 }, { "epoch": 0.03571428571428571, "grad_norm": 3.964160680770874, "learning_rate": 9.941089837997055e-05, "loss": 4.952, "step": 50 } ], "logging_steps": 25, "max_steps": 1400, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 303138078720000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }