{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 50, "global_step": 22, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.23054755043227665, "grad_norm": 18.841991424560547, "learning_rate": 8.181818181818183e-05, "loss": 3.3709, "step": 5 }, { "epoch": 0.4610951008645533, "grad_norm": 10.662392616271973, "learning_rate": 5.90909090909091e-05, "loss": 3.1199, "step": 10 }, { "epoch": 0.69164265129683, "grad_norm": 9.5862455368042, "learning_rate": 3.6363636363636364e-05, "loss": 2.9516, "step": 15 }, { "epoch": 0.9221902017291066, "grad_norm": 9.728779792785645, "learning_rate": 1.3636363636363637e-05, "loss": 2.8603, "step": 20 } ], "logging_steps": 5, "max_steps": 22, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.0250391773904896e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }