{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0024655212265968104, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012327606132984052, "grad_norm": 1.080862283706665, "learning_rate": 1e-05, "loss": 2.0853, "step": 1 }, { "epoch": 0.0012327606132984052, "eval_loss": 3.7710342407226562, "eval_runtime": 141.3112, "eval_samples_per_second": 9.674, "eval_steps_per_second": 4.84, "step": 1 }, { "epoch": 0.0024655212265968104, "grad_norm": 1.4210823774337769, "learning_rate": 2e-05, "loss": 2.5696, "step": 2 }, { "epoch": 0.0024655212265968104, "eval_loss": 3.7517523765563965, "eval_runtime": 42.0384, "eval_samples_per_second": 32.518, "eval_steps_per_second": 16.271, "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": 800155729133568.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }