{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 7.64, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.64, "grad_norm": 0.2845379412174225, "learning_rate": 0.00014, "loss": 12.9949, "step": 10 }, { "epoch": 5.0, "grad_norm": 0.1813206523656845, "learning_rate": 7.333333333333333e-05, "loss": 0.1045, "step": 20 }, { "epoch": 7.64, "grad_norm": 0.08738444000482559, "learning_rate": 6.666666666666667e-06, "loss": 0.0656, "step": 30 } ], "logging_steps": 10, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 1.3267710279627571e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }