{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.992, "eval_steps": 500, "global_step": 31, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.064, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 2 }, { "epoch": 0.128, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 4 }, { "epoch": 0.192, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 6 }, { "epoch": 0.256, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 8 }, { "epoch": 0.32, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.384, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 12 }, { "epoch": 0.448, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 14 }, { "epoch": 0.512, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 16 }, { "epoch": 0.576, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 18 }, { "epoch": 0.64, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 20 }, { "epoch": 0.704, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 22 }, { "epoch": 0.768, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 24 }, { "epoch": 0.832, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 26 }, { "epoch": 0.896, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 28 }, { "epoch": 0.96, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 30 }, { "epoch": 0.992, "step": 31, "total_flos": 142541964023184.0, "train_loss": 0.0, "train_runtime": 77.075, "train_samples_per_second": 6.487, "train_steps_per_second": 0.402 } ], "logging_steps": 2, "max_steps": 31, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 142541964023184.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }