{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 2060, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4854368932038835, "grad_norm": 1.1003823280334473, "learning_rate": 8.794946550048592e-05, "loss": 0.8551, "step": 250 }, { "epoch": 0.970873786407767, "grad_norm": 0.7180963158607483, "learning_rate": 7.580174927113704e-05, "loss": 0.4137, "step": 500 }, { "epoch": 1.4563106796116505, "grad_norm": 0.6523966789245605, "learning_rate": 6.365403304178815e-05, "loss": 0.3735, "step": 750 }, { "epoch": 1.941747572815534, "grad_norm": 0.6745087504386902, "learning_rate": 5.150631681243926e-05, "loss": 0.3583, "step": 1000 }, { "epoch": 2.4271844660194173, "grad_norm": 0.6706854104995728, "learning_rate": 3.9358600583090386e-05, "loss": 0.345, "step": 1250 }, { "epoch": 2.912621359223301, "grad_norm": 0.7672198414802551, "learning_rate": 2.72108843537415e-05, "loss": 0.333, "step": 1500 }, { "epoch": 3.3980582524271843, "grad_norm": 0.7942991256713867, "learning_rate": 1.5063168124392615e-05, "loss": 0.3142, "step": 1750 }, { "epoch": 3.883495145631068, "grad_norm": 0.7696407437324524, "learning_rate": 2.915451895043732e-06, "loss": 0.302, "step": 2000 }, { "epoch": 4.0, "step": 2060, "total_flos": 1.4445804612483994e+18, "train_loss": 0.40855656966422366, "train_runtime": 23649.5822, "train_samples_per_second": 22.298, "train_steps_per_second": 0.087 } ], "logging_steps": 250, "max_steps": 2060, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.4445804612483994e+18, "train_batch_size": 16, "trial_name": null, "trial_params": null }