{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.425531914893617, "global_step": 25000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 0.00014999965456413008, "loss": 0.6492, "step": 500 }, { "epoch": 0.02, "learning_rate": 0.0001499986182599296, "loss": 0.5432, "step": 1000 }, { "epoch": 0.03, "learning_rate": 0.00014999689109762647, "loss": 0.5137, "step": 1500 }, { "epoch": 0.03, "learning_rate": 0.00014999447309426713, "loss": 0.4986, "step": 2000 }, { "epoch": 0.04, "learning_rate": 0.00014999136427371623, "loss": 0.4877, "step": 2500 }, { "epoch": 0.05, "learning_rate": 0.0001499875646666566, "loss": 0.4785, "step": 3000 }, { "epoch": 0.06, "learning_rate": 0.00014998307431058887, "loss": 0.4702, "step": 3500 }, { "epoch": 0.07, "learning_rate": 0.00014997789324983099, "loss": 0.462, "step": 4000 }, { "epoch": 0.08, "learning_rate": 0.00014997202153551792, "loss": 0.454, "step": 4500 }, { "epoch": 0.09, "learning_rate": 0.0001499654592256012, "loss": 0.4466, "step": 5000 }, { "epoch": 0.09, "learning_rate": 0.0001499582063848481, "loss": 0.4398, "step": 5500 }, { "epoch": 0.1, "learning_rate": 0.00014995026308484122, "loss": 0.4341, "step": 6000 }, { "epoch": 0.11, "learning_rate": 0.00014994162940397778, "loss": 0.4288, "step": 6500 }, { "epoch": 0.12, "learning_rate": 0.00014993230542746872, "loss": 0.4247, "step": 7000 }, { "epoch": 0.13, "learning_rate": 0.00014992229124733788, "loss": 0.4207, "step": 7500 }, { "epoch": 0.14, "learning_rate": 0.0001499115869624212, "loss": 0.4175, "step": 8000 }, { "epoch": 0.14, "learning_rate": 0.00014990019267836565, "loss": 0.4146, "step": 8500 }, { "epoch": 0.15, "learning_rate": 0.00014988810850762824, "loss": 0.4122, "step": 9000 }, { "epoch": 0.16, "learning_rate": 0.00014987533456947482, "loss": 0.4097, "step": 9500 }, { "epoch": 0.17, "learning_rate": 0.000149861870989979, "loss": 0.4082, "step": 10000 }, { "epoch": 0.18, "learning_rate": 0.0001498477179020209, "loss": 0.406, "step": 10500 }, { "epoch": 0.19, "learning_rate": 0.00014983287544528573, "loss": 0.4042, "step": 11000 }, { "epoch": 0.2, "learning_rate": 0.0001498173755173638, "loss": 0.4026, "step": 11500 }, { "epoch": 0.2, "learning_rate": 0.0001498011561473246, "loss": 0.4014, "step": 12000 }, { "epoch": 0.21, "learning_rate": 0.00014978424786805407, "loss": 0.3999, "step": 12500 }, { "epoch": 0.22, "learning_rate": 0.00014976665084643018, "loss": 0.3985, "step": 13000 }, { "epoch": 0.23, "learning_rate": 0.00014974836525612832, "loss": 0.3971, "step": 13500 }, { "epoch": 0.24, "learning_rate": 0.00014972939127761998, "loss": 0.3961, "step": 14000 }, { "epoch": 0.25, "learning_rate": 0.0001497097290981706, "loss": 0.3949, "step": 14500 }, { "epoch": 0.26, "learning_rate": 0.00014968937891183796, "loss": 0.3938, "step": 15000 }, { "epoch": 0.26, "learning_rate": 0.00014966834091947024, "loss": 0.3927, "step": 15500 }, { "epoch": 0.27, "learning_rate": 0.0001496466594659672, "loss": 0.3924, "step": 16000 }, { "epoch": 0.28, "learning_rate": 0.00014962424786577448, "loss": 0.3908, "step": 16500 }, { "epoch": 0.29, "learning_rate": 0.00014960114910236375, "loss": 0.3898, "step": 17000 }, { "epoch": 0.3, "learning_rate": 0.0001495774116605143, "loss": 0.389, "step": 17500 }, { "epoch": 0.31, "learning_rate": 0.00014955294063453595, "loss": 0.3883, "step": 18000 }, { "epoch": 0.31, "learning_rate": 0.00014952778314911323, "loss": 0.3875, "step": 18500 }, { "epoch": 0.32, "learning_rate": 0.0001495019394525403, "loss": 0.3871, "step": 19000 }, { "epoch": 0.33, "learning_rate": 0.0001494755172845744, "loss": 0.3857, "step": 19500 }, { "epoch": 0.34, "learning_rate": 0.00014944830467991823, "loss": 0.3855, "step": 20000 }, { "epoch": 0.35, "learning_rate": 0.00014942040664853227, "loss": 0.3843, "step": 20500 }, { "epoch": 0.36, "learning_rate": 0.00014939182346575884, "loss": 0.3841, "step": 21000 }, { "epoch": 0.37, "learning_rate": 0.0001493625554137024, "loss": 0.3833, "step": 21500 }, { "epoch": 0.37, "learning_rate": 0.00014933266336950772, "loss": 0.3825, "step": 22000 }, { "epoch": 0.38, "learning_rate": 0.0001493020278205035, "loss": 0.3822, "step": 22500 }, { "epoch": 0.39, "learning_rate": 0.00014927070828846305, "loss": 0.3814, "step": 23000 }, { "epoch": 0.4, "learning_rate": 0.00014923870508249748, "loss": 0.3809, "step": 23500 }, { "epoch": 0.41, "learning_rate": 0.00014920601851846558, "loss": 0.3806, "step": 24000 }, { "epoch": 0.42, "learning_rate": 0.0001491727163396211, "loss": 0.3797, "step": 24500 }, { "epoch": 0.43, "learning_rate": 0.00014913866539908636, "loss": 0.3794, "step": 25000 } ], "max_steps": 500000, "num_train_epochs": 9, "total_flos": 0.0, "trial_name": null, "trial_params": null }