{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 10, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.2253111600875854, "learning_rate": 2e-05, "loss": 5.4883, "step": 1 }, { "epoch": 0.2, "grad_norm": 1.2487238645553589, "learning_rate": 1.9510565162951538e-05, "loss": 5.5898, "step": 2 }, { "epoch": 0.3, "grad_norm": 1.3708199262619019, "learning_rate": 1.8090169943749477e-05, "loss": 5.75, "step": 3 }, { "epoch": 0.4, "grad_norm": 1.2051873207092285, "learning_rate": 1.5877852522924733e-05, "loss": 5.4727, "step": 4 }, { "epoch": 0.5, "grad_norm": 1.3166049718856812, "learning_rate": 1.3090169943749475e-05, "loss": 5.5742, "step": 5 }, { "epoch": 0.6, "grad_norm": 1.307198166847229, "learning_rate": 1e-05, "loss": 5.4922, "step": 6 }, { "epoch": 0.7, "grad_norm": 1.3135805130004883, "learning_rate": 6.909830056250527e-06, "loss": 5.4414, "step": 7 }, { "epoch": 0.8, "grad_norm": 1.3186125755310059, "learning_rate": 4.12214747707527e-06, "loss": 5.4453, "step": 8 }, { "epoch": 0.9, "grad_norm": 1.2448387145996094, "learning_rate": 1.9098300562505266e-06, "loss": 5.4023, "step": 9 }, { "epoch": 1.0, "grad_norm": 1.2668588161468506, "learning_rate": 4.894348370484648e-07, "loss": 5.3672, "step": 10 }, { "epoch": 1.0, "eval_loss": 5.465277671813965, "eval_runtime": 0.2049, "eval_samples_per_second": 87.862, "eval_steps_per_second": 9.762, "step": 10 } ], "logging_steps": 1.0, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2207185924784128.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }