{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.953846153846154, "eval_steps": 500, "global_step": 144, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "learning_rate": 8.000000000000001e-06, "loss": 5.2885, "step": 2 }, { "epoch": 0.08, "learning_rate": 1.6000000000000003e-05, "loss": 4.3115, "step": 4 }, { "epoch": 0.12, "learning_rate": 1.999744599547812e-05, "loss": 3.1889, "step": 6 }, { "epoch": 0.16, "learning_rate": 1.99770217861636e-05, "loss": 2.2276, "step": 8 }, { "epoch": 0.21, "learning_rate": 1.9936215093023884e-05, "loss": 1.4245, "step": 10 }, { "epoch": 0.25, "learning_rate": 1.9875109281794828e-05, "loss": 0.9188, "step": 12 }, { "epoch": 0.29, "learning_rate": 1.9793829188147406e-05, "loss": 4.5676, "step": 14 }, { "epoch": 0.33, "learning_rate": 1.9692540862655587e-05, "loss": 3.4422, "step": 16 }, { "epoch": 0.37, "learning_rate": 1.9571451231564523e-05, "loss": 1.9053, "step": 18 }, { "epoch": 0.41, "learning_rate": 1.9430807674052092e-05, "loss": 1.1145, "step": 20 }, { "epoch": 0.45, "learning_rate": 1.9270897516847406e-05, "loss": 0.717, "step": 22 }, { "epoch": 0.49, "learning_rate": 1.9092047447238775e-05, "loss": 0.5241, "step": 24 }, { "epoch": 0.53, "learning_rate": 1.8894622845670282e-05, "loss": 3.1616, "step": 26 }, { "epoch": 0.57, "learning_rate": 1.86790270392905e-05, "loss": 1.4529, "step": 28 }, { "epoch": 0.62, "learning_rate": 1.8445700477978207e-05, "loss": 0.8347, "step": 30 }, { "epoch": 0.66, "learning_rate": 1.8195119834528535e-05, "loss": 0.4146, "step": 32 }, { "epoch": 0.7, "learning_rate": 1.792779703083777e-05, "loss": 0.2956, "step": 34 }, { "epoch": 0.74, "learning_rate": 1.764427819207624e-05, "loss": 0.2205, "step": 36 }, { "epoch": 0.78, "learning_rate": 1.734514253098589e-05, "loss": 1.6814, "step": 38 }, { "epoch": 0.82, "learning_rate": 1.7031001164581828e-05, "loss": 0.4792, "step": 40 }, { "epoch": 0.86, "learning_rate": 1.670249586567531e-05, "loss": 0.2038, "step": 42 }, { "epoch": 0.9, "learning_rate": 1.636029775176862e-05, "loss": 0.1199, "step": 44 }, { "epoch": 0.94, "learning_rate": 1.6005105914000508e-05, "loss": 0.0972, "step": 46 }, { "epoch": 0.98, "learning_rate": 1.5637645988943008e-05, "loss": 0.0947, "step": 48 }, { "epoch": 1.03, "learning_rate": 1.5258668676167548e-05, "loss": 0.6136, "step": 50 }, { "epoch": 1.07, "learning_rate": 1.48689482046087e-05, "loss": 0.3785, "step": 52 }, { "epoch": 1.11, "learning_rate": 1.4469280750858854e-05, "loss": 0.1075, "step": 54 }, { "epoch": 1.15, "learning_rate": 1.4060482812625055e-05, "loss": 0.0497, "step": 56 }, { "epoch": 1.19, "learning_rate": 1.3643389540670963e-05, "loss": 0.0431, "step": 58 }, { "epoch": 1.23, "learning_rate": 1.3218853032651719e-05, "loss": 0.0432, "step": 60 }, { "epoch": 1.27, "learning_rate": 1.2787740592327232e-05, "loss": 0.2216, "step": 62 }, { "epoch": 1.31, "learning_rate": 1.2350932957710322e-05, "loss": 0.1697, "step": 64 }, { "epoch": 1.35, "learning_rate": 1.1909322501769407e-05, "loss": 0.0716, "step": 66 }, { "epoch": 1.39, "learning_rate": 1.1463811409361667e-05, "loss": 0.0357, "step": 68 }, { "epoch": 1.44, "learning_rate": 1.1015309834121083e-05, "loss": 0.02, "step": 70 }, { "epoch": 1.48, "learning_rate": 1.05647340390667e-05, "loss": 0.0326, "step": 72 }, { "epoch": 1.52, "learning_rate": 1.01130045247298e-05, "loss": 0.1052, "step": 74 }, { "epoch": 1.56, "learning_rate": 9.661044148624038e-06, "loss": 0.061, "step": 76 }, { "epoch": 1.6, "learning_rate": 9.209776239900453e-06, "loss": 0.0387, "step": 78 }, { "epoch": 1.64, "learning_rate": 8.76012271303888e-06, "loss": 0.0186, "step": 80 }, { "epoch": 1.68, "learning_rate": 8.313002184429529e-06, "loss": 0.0249, "step": 82 }, { "epoch": 1.72, "learning_rate": 7.869328095692313e-06, "loss": 0.0319, "step": 84 }, { "epoch": 1.76, "learning_rate": 7.430006847567972e-06, "loss": 0.0586, "step": 86 }, { "epoch": 1.81, "learning_rate": 6.995935948193294e-06, "loss": 0.0917, "step": 88 }, { "epoch": 1.85, "learning_rate": 6.568002179543409e-06, "loss": 0.0284, "step": 90 }, { "epoch": 1.89, "learning_rate": 6.147079785787038e-06, "loss": 0.0158, "step": 92 }, { "epoch": 1.93, "learning_rate": 5.7340286872557515e-06, "loss": 0.0145, "step": 94 }, { "epoch": 1.97, "learning_rate": 5.329692723675994e-06, "loss": 0.0189, "step": 96 }, { "epoch": 2.01, "learning_rate": 4.934897930252887e-06, "loss": 0.03, "step": 98 }, { "epoch": 2.05, "learning_rate": 4.550450850127626e-06, "loss": 0.0605, "step": 100 }, { "epoch": 2.09, "learning_rate": 4.177136886656067e-06, "loss": 0.0348, "step": 102 }, { "epoch": 2.13, "learning_rate": 3.815718698874672e-06, "loss": 0.0191, "step": 104 }, { "epoch": 2.17, "learning_rate": 3.466934643431795e-06, "loss": 0.0174, "step": 106 }, { "epoch": 2.22, "learning_rate": 3.1314972661673572e-06, "loss": 0.0167, "step": 108 }, { "epoch": 2.26, "learning_rate": 2.8100918464225304e-06, "loss": 0.0295, "step": 110 }, { "epoch": 2.3, "learning_rate": 2.5033749970533015e-06, "loss": 0.0499, "step": 112 }, { "epoch": 2.34, "learning_rate": 2.211973323008041e-06, "loss": 0.0262, "step": 114 }, { "epoch": 2.38, "learning_rate": 1.936482141209486e-06, "loss": 0.0162, "step": 116 }, { "epoch": 2.42, "learning_rate": 1.6774642643563955e-06, "loss": 0.012, "step": 118 }, { "epoch": 2.46, "learning_rate": 1.4354488511294418e-06, "loss": 0.0198, "step": 120 }, { "epoch": 2.5, "learning_rate": 1.2109303251503434e-06, "loss": 0.0291, "step": 122 }, { "epoch": 2.54, "learning_rate": 1.0043673649027519e-06, "loss": 0.0534, "step": 124 }, { "epoch": 2.58, "learning_rate": 8.161819666783888e-07, "loss": 0.0224, "step": 126 }, { "epoch": 2.63, "learning_rate": 6.467585824627886e-07, "loss": 0.0184, "step": 128 }, { "epoch": 2.67, "learning_rate": 4.964433345219354e-07, "loss": 0.0157, "step": 130 }, { "epoch": 2.71, "learning_rate": 3.6554330829429716e-07, "loss": 0.0177, "step": 132 }, { "epoch": 2.75, "learning_rate": 2.5432592503288e-07, "loss": 0.0268, "step": 134 }, { "epoch": 2.79, "learning_rate": 1.630183954789233e-07, "loss": 0.0562, "step": 136 }, { "epoch": 2.83, "learning_rate": 9.180725568338045e-08, "loss": 0.0211, "step": 138 }, { "epoch": 2.87, "learning_rate": 4.083798592444899e-08, "loss": 0.0202, "step": 140 }, { "epoch": 2.91, "learning_rate": 1.0214713499706596e-08, "loss": 0.0142, "step": 142 }, { "epoch": 2.95, "learning_rate": 0.0, "loss": 0.0116, "step": 144 } ], "logging_steps": 2, "max_steps": 144, "num_train_epochs": 3, "save_steps": 500, "total_flos": 9993412315865088.0, "trial_name": null, "trial_params": null }