{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.023444544634806132, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0018034265103697023, "eval_loss": 1.5323797464370728, "eval_runtime": 15.1257, "eval_samples_per_second": 15.47, "eval_steps_per_second": 7.735, "step": 1 }, { "epoch": 0.009017132551848512, "grad_norm": 8.786983489990234, "learning_rate": 5e-05, "loss": 6.1675, "step": 5 }, { "epoch": 0.018034265103697024, "grad_norm": 7.997146129608154, "learning_rate": 0.0001, "loss": 5.5276, "step": 10 }, { "epoch": 0.018034265103697024, "eval_loss": 1.2454485893249512, "eval_runtime": 15.4977, "eval_samples_per_second": 15.099, "eval_steps_per_second": 7.55, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2322290133958656.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }