{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006845798391237378, "eval_steps": 13, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006845798391237378, "eval_loss": NaN, "eval_runtime": 15.567, "eval_samples_per_second": 39.507, "eval_steps_per_second": 19.785, "step": 1 }, { "epoch": 0.0020537395173712133, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004107479034742427, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.00616121855211364, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 } ], "logging_steps": 3, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 162890557685760.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }