{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0006418871482157543, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00032094357410787714, "grad_norm": 11.735983848571777, "learning_rate": 1e-05, "loss": 177.875, "step": 1 }, { "epoch": 0.00032094357410787714, "eval_loss": 11.11240005493164, "eval_runtime": 11.8342, "eval_samples_per_second": 443.462, "eval_steps_per_second": 221.731, "step": 1 }, { "epoch": 0.0006418871482157543, "grad_norm": 12.970888137817383, "learning_rate": 2e-05, "loss": 177.8125, "step": 2 }, { "epoch": 0.0006418871482157543, "eval_loss": 11.11218547821045, "eval_runtime": 6.7783, "eval_samples_per_second": 774.239, "eval_steps_per_second": 387.119, "step": 2 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5976883200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }