{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5505092210294522, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.055050922102945224, "grad_norm": 3.223727226257324, "learning_rate": 5.494505494505495e-05, "loss": 2.0113, "step": 100 }, { "epoch": 0.11010184420589045, "grad_norm": 2.7249491214752197, "learning_rate": 9.997006099836617e-05, "loss": 1.7306, "step": 200 }, { "epoch": 0.16515276630883569, "grad_norm": 2.2732579708099365, "learning_rate": 9.871874350577997e-05, "loss": 1.6522, "step": 300 }, { "epoch": 0.2202036884117809, "grad_norm": 2.5243077278137207, "learning_rate": 9.567205799555621e-05, "loss": 1.5667, "step": 400 }, { "epoch": 0.2752546105147261, "grad_norm": 2.2532739639282227, "learning_rate": 9.09422799766929e-05, "loss": 1.5134, "step": 500 }, { "epoch": 0.33030553261767137, "grad_norm": 2.3742384910583496, "learning_rate": 8.47037097610317e-05, "loss": 1.4548, "step": 600 }, { "epoch": 0.3853564547206166, "grad_norm": 2.96374773979187, "learning_rate": 7.718624920225358e-05, "loss": 1.4309, "step": 700 }, { "epoch": 0.4404073768235618, "grad_norm": 2.140960693359375, "learning_rate": 6.866692942410824e-05, "loss": 1.4181, "step": 800 }, { "epoch": 0.495458298926507, "grad_norm": 1.9198336601257324, "learning_rate": 5.9459701755408125e-05, "loss": 1.3413, "step": 900 }, { "epoch": 0.5505092210294522, "grad_norm": 1.8933072090148926, "learning_rate": 4.9903868093081854e-05, "loss": 1.3367, "step": 1000 } ], "logging_steps": 100, "max_steps": 1816, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.293567140023501e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }