{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999818725641258,
  "eval_steps": 500,
  "global_step": 16548,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.999549488698767e-05,
      "loss": 0.9367,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998198117163414e-05,
      "loss": 0.8539,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.995946372440459e-05,
      "loss": 0.8563,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.99279506607906e-05,
      "loss": 0.8552,
      "step": 400
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9887453338385195e-05,
      "loss": 0.8377,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.98379863527895e-05,
      "loss": 0.8346,
      "step": 600
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9779567532352364e-05,
      "loss": 0.8338,
      "step": 700
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.971221793174483e-05,
      "loss": 0.8176,
      "step": 800
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9635961824371865e-05,
      "loss": 0.8297,
      "step": 900
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9550826693624e-05,
      "loss": 0.8337,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.945684322297207e-05,
      "loss": 0.8243,
      "step": 1100
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.935404528490858e-05,
      "loss": 0.8289,
      "step": 1200
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.924246992873982e-05,
      "loss": 0.818,
      "step": 1300
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9122157367232894e-05,
      "loss": 0.8361,
      "step": 1400
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.899315096212272e-05,
      "loss": 0.8055,
      "step": 1500
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.8855497208484046e-05,
      "loss": 0.8284,
      "step": 1600
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.8709245717974204e-05,
      "loss": 0.8214,
      "step": 1700
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.8554449200952635e-05,
      "loss": 0.8243,
      "step": 1800
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.8391163447483587e-05,
      "loss": 0.8191,
      "step": 1900
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.821944730722887e-05,
      "loss": 0.8106,
      "step": 2000
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.803936266823792e-05,
      "loss": 0.8217,
      "step": 2100
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.785097443464276e-05,
      "loss": 0.8071,
      "step": 2200
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.765435050326602e-05,
      "loss": 0.8164,
      "step": 2300
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.744956173915022e-05,
      "loss": 0.8264,
      "step": 2400
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7236681950017445e-05,
      "loss": 0.8183,
      "step": 2500
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.701578785966834e-05,
      "loss": 0.8035,
      "step": 2600
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.678695908033017e-05,
      "loss": 0.8019,
      "step": 2700
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.655027808396385e-05,
      "loss": 0.8084,
      "step": 2800
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.6305830172540295e-05,
      "loss": 0.8124,
      "step": 2900
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6053703447296826e-05,
      "loss": 0.8206,
      "step": 3000
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.579398877698471e-05,
      "loss": 0.8137,
      "step": 3100
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.55267797651192e-05,
      "loss": 0.803,
      "step": 3200
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.5252172716244e-05,
      "loss": 0.8108,
      "step": 3300
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.4970266601222243e-05,
      "loss": 0.8154,
      "step": 3400
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.4681163021566496e-05,
      "loss": 0.7998,
      "step": 3500
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.4384966172820644e-05,
      "loss": 0.8109,
      "step": 3600
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.40817828070069e-05,
      "loss": 0.8102,
      "step": 3700
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.377172219415136e-05,
      "loss": 0.8119,
      "step": 3800
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.345489608290216e-05,
      "loss": 0.8041,
      "step": 3900
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.313141866025423e-05,
      "loss": 0.8149,
      "step": 4000
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.280140651039522e-05,
      "loss": 0.8043,
      "step": 4100
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.246497857268759e-05,
      "loss": 0.7933,
      "step": 4200
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.2122256098801726e-05,
      "loss": 0.8022,
      "step": 4300
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.177336260901578e-05,
      "loss": 0.8083,
      "step": 4400
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.1418423847697786e-05,
      "loss": 0.8082,
      "step": 4500
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.105756773798633e-05,
      "loss": 0.7956,
      "step": 4600
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.0690924335685865e-05,
      "loss": 0.8072,
      "step": 4700
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.031862578239338e-05,
      "loss": 0.7954,
      "step": 4800
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.994080625787343e-05,
      "loss": 0.8025,
      "step": 4900
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.955760193169851e-05,
      "loss": 0.796,
      "step": 5000
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.9169150914172324e-05,
      "loss": 0.7924,
      "step": 5100
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.8775593206553575e-05,
      "loss": 0.8076,
      "step": 5200
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.837707065059823e-05,
      "loss": 0.7929,
      "step": 5300
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.79737268774385e-05,
      "loss": 0.7966,
      "step": 5400
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.756570725581684e-05,
      "loss": 0.812,
      "step": 5500
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.71531588396938e-05,
      "loss": 0.7952,
      "step": 5600
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.673623031524838e-05,
      "loss": 0.807,
      "step": 5700
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.6315071947290255e-05,
      "loss": 0.7919,
      "step": 5800
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.588983552510291e-05,
      "loss": 0.8051,
      "step": 5900
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.546067430773747e-05,
      "loss": 0.8067,
      "step": 6000
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.50277429687767e-05,
      "loss": 0.7982,
      "step": 6100
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.459119754058929e-05,
      "loss": 0.7965,
      "step": 6200
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.4151195358094365e-05,
      "loss": 0.7829,
      "step": 6300
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.370789500205656e-05,
      "loss": 0.7905,
      "step": 6400
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.326593563722561e-05,
      "loss": 0.7904,
      "step": 6500
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.281654834858534e-05,
      "loss": 0.7972,
      "step": 6600
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.236434390525093e-05,
      "loss": 0.7995,
      "step": 6700
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.190948528579214e-05,
      "loss": 0.7965,
      "step": 6800
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.1452136425367785e-05,
      "loss": 0.7956,
      "step": 6900
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.099246215664205e-05,
      "loss": 0.7894,
      "step": 7000
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.0530628150377295e-05,
      "loss": 0.8024,
      "step": 7100
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.0066800855724798e-05,
      "loss": 0.7726,
      "step": 7200
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.960114744023503e-05,
      "loss": 0.7881,
      "step": 7300
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.913383572960889e-05,
      "loss": 0.7993,
      "step": 7400
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.866503414721184e-05,
      "loss": 0.8094,
      "step": 7500
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.8194911653372613e-05,
      "loss": 0.7923,
      "step": 7600
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7723637684488356e-05,
      "loss": 0.8058,
      "step": 7700
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.725138209195824e-05,
      "loss": 0.7852,
      "step": 7800
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.677831508096747e-05,
      "loss": 0.7888,
      "step": 7900
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.630460714914379e-05,
      "loss": 0.8021,
      "step": 8000
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.5830429025108627e-05,
      "loss": 0.7901,
      "step": 8100
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5355951606944913e-05,
      "loss": 0.8147,
      "step": 8200
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.488134590060391e-05,
      "loss": 0.7986,
      "step": 8300
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.441152781437193e-05,
      "loss": 0.8005,
      "step": 8400
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.393717568838824e-05,
      "loss": 0.7923,
      "step": 8500
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.346320661389542e-05,
      "loss": 0.789,
      "step": 8600
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.2989791413633083e-05,
      "loss": 0.7746,
      "step": 8700
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.2517100710719537e-05,
      "loss": 0.7861,
      "step": 8800
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.2045304867157723e-05,
      "loss": 0.7853,
      "step": 8900
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.157457392243513e-05,
      "loss": 0.7903,
      "step": 9000
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.110507753224012e-05,
      "loss": 0.7986,
      "step": 9100
    },
    {
      "epoch": 1.67,
      "learning_rate": 2.0636984907316447e-05,
      "loss": 0.7961,
      "step": 9200
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.017046475247813e-05,
      "loss": 0.7958,
      "step": 9300
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.9705685205806772e-05,
      "loss": 0.7866,
      "step": 9400
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.9242813778053085e-05,
      "loss": 0.7816,
      "step": 9500
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.8782017292264426e-05,
      "loss": 0.7848,
      "step": 9600
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.8323461823660335e-05,
      "loss": 0.7935,
      "step": 9700
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.786731263977748e-05,
      "loss": 0.7978,
      "step": 9800
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.7413734140905783e-05,
      "loss": 0.7936,
      "step": 9900
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.696288980083704e-05,
      "loss": 0.7996,
      "step": 10000
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6514942107947466e-05,
      "loss": 0.7798,
      "step": 10100
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.6070052506635487e-05,
      "loss": 0.786,
      "step": 10200
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5628381339135647e-05,
      "loss": 0.7912,
      "step": 10300
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.5190087787729873e-05,
      "loss": 0.7767,
      "step": 10400
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.4755329817376672e-05,
      "loss": 0.7891,
      "step": 10500
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.4324264118779218e-05,
      "loss": 0.7885,
      "step": 10600
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.389704605191254e-05,
      "loss": 0.7969,
      "step": 10700
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.3473829590030412e-05,
      "loss": 0.788,
      "step": 10800
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.3054767264171989e-05,
      "loss": 0.7861,
      "step": 10900
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.2640010108188234e-05,
      "loss": 0.7864,
      "step": 11000
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.2229707604308002e-05,
      "loss": 0.7989,
      "step": 11100
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.1824007629263217e-05,
      "loss": 0.7764,
      "step": 11200
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.1423056400992816e-05,
      "loss": 0.7934,
      "step": 11300
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.1026998425944449e-05,
      "loss": 0.786,
      "step": 11400
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.0635976446993102e-05,
      "loss": 0.7922,
      "step": 11500
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.02501313919952e-05,
      "loss": 0.7842,
      "step": 11600
    },
    {
      "epoch": 2.12,
      "learning_rate": 9.869602322996985e-06,
      "loss": 0.7932,
      "step": 11700
    },
    {
      "epoch": 2.14,
      "learning_rate": 9.494526386115285e-06,
      "loss": 0.7754,
      "step": 11800
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.125038762108796e-06,
      "loss": 0.7921,
      "step": 11900
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.76127261765777e-06,
      "loss": 0.7935,
      "step": 12000
    },
    {
      "epoch": 2.19,
      "learning_rate": 8.403359057369443e-06,
      "loss": 0.7857,
      "step": 12100
    },
    {
      "epoch": 2.21,
      "learning_rate": 8.05142707652685e-06,
      "loss": 0.7884,
      "step": 12200
    },
    {
      "epoch": 2.23,
      "learning_rate": 7.705603514597697e-06,
      "loss": 0.7896,
      "step": 12300
    },
    {
      "epoch": 2.25,
      "learning_rate": 7.366013009520287e-06,
      "loss": 0.7823,
      "step": 12400
    },
    {
      "epoch": 2.27,
      "learning_rate": 7.032777952782879e-06,
      "loss": 0.7743,
      "step": 12500
    },
    {
      "epoch": 2.28,
      "learning_rate": 6.7060184453127065e-06,
      "loss": 0.7912,
      "step": 12600
    },
    {
      "epoch": 2.3,
      "learning_rate": 6.385852254190483e-06,
      "loss": 0.7814,
      "step": 12700
    },
    {
      "epoch": 2.32,
      "learning_rate": 6.072394770206108e-06,
      "loss": 0.7882,
      "step": 12800
    },
    {
      "epoch": 2.34,
      "learning_rate": 5.7657589662707655e-06,
      "loss": 0.7895,
      "step": 12900
    },
    {
      "epoch": 2.36,
      "learning_rate": 5.4660553567005e-06,
      "loss": 0.7872,
      "step": 13000
    },
    {
      "epoch": 2.37,
      "learning_rate": 5.173391957385812e-06,
      "loss": 0.7932,
      "step": 13100
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.887874246861776e-06,
      "loss": 0.7979,
      "step": 13200
    },
    {
      "epoch": 2.41,
      "learning_rate": 4.609605128292627e-06,
      "loss": 0.7816,
      "step": 13300
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.33868489238452e-06,
      "loss": 0.798,
      "step": 13400
    },
    {
      "epoch": 2.45,
      "learning_rate": 4.0752111812398825e-06,
      "loss": 0.7787,
      "step": 13500
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.819278953166247e-06,
      "loss": 0.7929,
      "step": 13600
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.570980448452507e-06,
      "loss": 0.7856,
      "step": 13700
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.3304051561246193e-06,
      "loss": 0.7891,
      "step": 13800
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.0976397816929847e-06,
      "loss": 0.7871,
      "step": 13900
    },
    {
      "epoch": 2.54,
      "learning_rate": 2.872768215902963e-06,
      "loss": 0.7771,
      "step": 14000
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.6558715044999407e-06,
      "loss": 0.7852,
      "step": 14100
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.4470278190196565e-06,
      "loss": 0.7848,
      "step": 14200
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.246312428614519e-06,
      "loss": 0.7832,
      "step": 14300
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.0537976729258834e-06,
      "loss": 0.7903,
      "step": 14400
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.8695529360122367e-06,
      "loss": 0.7787,
      "step": 14500
    },
    {
      "epoch": 2.65,
      "learning_rate": 1.6936446213425079e-06,
      "loss": 0.7867,
      "step": 14600
    },
    {
      "epoch": 2.66,
      "learning_rate": 1.5261361278636949e-06,
      "loss": 0.7915,
      "step": 14700
    },
    {
      "epoch": 2.68,
      "learning_rate": 1.367087827151284e-06,
      "loss": 0.7798,
      "step": 14800
    },
    {
      "epoch": 2.7,
      "learning_rate": 1.2165570416508038e-06,
      "loss": 0.78,
      "step": 14900
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.074598024018303e-06,
      "loss": 0.7942,
      "step": 15000
    },
    {
      "epoch": 2.74,
      "learning_rate": 9.412619375671838e-07,
      "loss": 0.7871,
      "step": 15100
    },
    {
      "epoch": 2.76,
      "learning_rate": 8.165968378284899e-07,
      "loss": 0.7874,
      "step": 15200
    },
    {
      "epoch": 2.77,
      "learning_rate": 7.006476552312597e-07,
      "loss": 0.8047,
      "step": 15300
    },
    {
      "epoch": 2.79,
      "learning_rate": 5.934561789092075e-07,
      "loss": 0.7972,
      "step": 15400
    },
    {
      "epoch": 2.81,
      "learning_rate": 4.950610416395052e-07,
      "loss": 0.7809,
      "step": 15500
    },
    {
      "epoch": 2.83,
      "learning_rate": 4.0549770591921944e-07,
      "loss": 0.7863,
      "step": 15600
    },
    {
      "epoch": 2.85,
      "learning_rate": 3.2479845118428556e-07,
      "loss": 0.7823,
      "step": 15700
    },
    {
      "epoch": 2.86,
      "learning_rate": 2.529923621757052e-07,
      "loss": 0.7795,
      "step": 15800
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.901053184571594e-07,
      "loss": 0.7921,
      "step": 15900
    },
    {
      "epoch": 2.9,
      "learning_rate": 1.361599850877665e-07,
      "loss": 0.7846,
      "step": 16000
    },
    {
      "epoch": 2.92,
      "learning_rate": 9.117580445338892e-08,
      "loss": 0.7781,
      "step": 16100
    },
    {
      "epoch": 2.94,
      "learning_rate": 5.5168989259429816e-08,
      "loss": 0.7865,
      "step": 16200
    },
    {
      "epoch": 2.95,
      "learning_rate": 2.81525166876212e-08,
      "loss": 0.7831,
      "step": 16300
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.01361237189318e-08,
      "loss": 0.7788,
      "step": 16400
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.1263036242797898e-09,
      "loss": 0.7937,
      "step": 16500
    },
    {
      "epoch": 3.0,
      "step": 16548,
      "total_flos": 1.4925620407412038e+20,
      "train_loss": 0.31137707696204203,
      "train_runtime": 269031.4999,
      "train_samples_per_second": 1.968,
      "train_steps_per_second": 0.062
    }
  ],
  "logging_steps": 100,
  "max_steps": 16548,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 1.4925620407412038e+20,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}