{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.01, "eval_steps": 0, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "grad_norm": 0.5258329510688782, "learning_rate": 0.0001, "loss": 3.1294, "step": 10 }, { "epoch": 0.01, "step": 10, "total_flos": 4810910442979328.0, "train_loss": 3.1294017791748048, "train_runtime": 82.5533, "train_samples_per_second": 4.845, "train_steps_per_second": 0.121 } ], "logging_steps": 10, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4810910442979328.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }