{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.012752391073326248, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004250797024442083, "grad_norm": 0.7029209136962891, "learning_rate": 2e-05, "loss": 1.6147, "step": 1 }, { "epoch": 0.004250797024442083, "eval_loss": 1.5603886842727661, "eval_runtime": 2.3017, "eval_samples_per_second": 43.447, "eval_steps_per_second": 21.723, "step": 1 }, { "epoch": 0.008501594048884165, "grad_norm": 0.9273056983947754, "learning_rate": 4e-05, "loss": 1.5879, "step": 2 }, { "epoch": 0.012752391073326248, "grad_norm": 0.6883237361907959, "learning_rate": 6e-05, "loss": 1.6456, "step": 3 }, { "epoch": 0.012752391073326248, "eval_loss": 1.5593794584274292, "eval_runtime": 1.7995, "eval_samples_per_second": 55.572, "eval_steps_per_second": 27.786, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 76737593475072.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }