{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1597603594608088, "eval_steps": 500, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0798801797304044, "grad_norm": 0.669739842414856, "learning_rate": 3.6e-05, "loss": 1.3048, "step": 10 }, { "epoch": 0.1597603594608088, "grad_norm": 0.2995016872882843, "learning_rate": 7.6e-05, "loss": 1.1036, "step": 20 } ], "logging_steps": 10, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.1530833350078464e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }