{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0729613733905579,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.988078206962327e-05,
      "loss": 1.7515,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.976156413924655e-05,
      "loss": 1.78,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.964234620886982e-05,
      "loss": 1.7268,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9523128278493086e-05,
      "loss": 1.6973,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.940391034811636e-05,
      "loss": 1.6927,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.928469241773963e-05,
      "loss": 1.6304,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.91654744873629e-05,
      "loss": 1.6876,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.904625655698618e-05,
      "loss": 1.6705,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.8927038626609446e-05,
      "loss": 1.671,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8807820696232716e-05,
      "loss": 1.6873,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.868860276585599e-05,
      "loss": 1.6374,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.856938483547926e-05,
      "loss": 1.6345,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.845016690510253e-05,
      "loss": 1.6681,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8330948974725806e-05,
      "loss": 1.6318,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8211731044349076e-05,
      "loss": 1.6623,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8092513113972345e-05,
      "loss": 1.6638,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.7973295183595614e-05,
      "loss": 1.5959,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.785407725321889e-05,
      "loss": 1.6736,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.773485932284216e-05,
      "loss": 1.6483,
      "step": 190
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.761564139246543e-05,
      "loss": 1.6607,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.74964234620887e-05,
      "loss": 1.6355,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7377205531711974e-05,
      "loss": 1.6412,
      "step": 220
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7257987601335244e-05,
      "loss": 1.6416,
      "step": 230
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.713876967095851e-05,
      "loss": 1.6822,
      "step": 240
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.701955174058178e-05,
      "loss": 1.6344,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.690033381020505e-05,
      "loss": 1.6217,
      "step": 260
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.678111587982833e-05,
      "loss": 1.6628,
      "step": 270
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.66618979494516e-05,
      "loss": 1.6067,
      "step": 280
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.6542680019074866e-05,
      "loss": 1.6526,
      "step": 290
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.642346208869814e-05,
      "loss": 1.637,
      "step": 300
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.630424415832141e-05,
      "loss": 1.6491,
      "step": 310
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.618502622794468e-05,
      "loss": 1.6213,
      "step": 320
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.606580829756796e-05,
      "loss": 1.6675,
      "step": 330
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.5946590367191226e-05,
      "loss": 1.5946,
      "step": 340
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5827372436814496e-05,
      "loss": 1.6309,
      "step": 350
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.570815450643777e-05,
      "loss": 1.6093,
      "step": 360
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.558893657606104e-05,
      "loss": 1.6171,
      "step": 370
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.546971864568431e-05,
      "loss": 1.6124,
      "step": 380
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5350500715307586e-05,
      "loss": 1.6322,
      "step": 390
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5231282784930856e-05,
      "loss": 1.6261,
      "step": 400
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5112064854554125e-05,
      "loss": 1.5778,
      "step": 410
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.49928469241774e-05,
      "loss": 1.6442,
      "step": 420
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.487362899380067e-05,
      "loss": 1.6189,
      "step": 430
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.475441106342394e-05,
      "loss": 1.6357,
      "step": 440
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.4635193133047216e-05,
      "loss": 1.6001,
      "step": 450
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.4515975202670485e-05,
      "loss": 1.6227,
      "step": 460
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.4396757272293754e-05,
      "loss": 1.6108,
      "step": 470
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.4277539341917024e-05,
      "loss": 1.6559,
      "step": 480
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.41583214115403e-05,
      "loss": 1.6107,
      "step": 490
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.403910348116357e-05,
      "loss": 1.6137,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.391988555078684e-05,
      "loss": 1.6333,
      "step": 510
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.3800667620410114e-05,
      "loss": 1.6256,
      "step": 520
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.3681449690033384e-05,
      "loss": 1.652,
      "step": 530
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.356223175965665e-05,
      "loss": 1.6325,
      "step": 540
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.344301382927993e-05,
      "loss": 1.6319,
      "step": 550
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.33237958989032e-05,
      "loss": 1.6378,
      "step": 560
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.320457796852647e-05,
      "loss": 1.6113,
      "step": 570
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.3085360038149744e-05,
      "loss": 1.5908,
      "step": 580
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.296614210777301e-05,
      "loss": 1.6292,
      "step": 590
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.284692417739628e-05,
      "loss": 1.6608,
      "step": 600
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.272770624701956e-05,
      "loss": 1.6125,
      "step": 610
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.260848831664283e-05,
      "loss": 1.597,
      "step": 620
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.24892703862661e-05,
      "loss": 1.6496,
      "step": 630
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.237005245588937e-05,
      "loss": 1.6096,
      "step": 640
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.225083452551264e-05,
      "loss": 1.634,
      "step": 650
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.213161659513591e-05,
      "loss": 1.6243,
      "step": 660
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.201239866475918e-05,
      "loss": 1.6428,
      "step": 670
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.189318073438245e-05,
      "loss": 1.6434,
      "step": 680
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.1773962804005726e-05,
      "loss": 1.6316,
      "step": 690
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.1654744873628996e-05,
      "loss": 1.627,
      "step": 700
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.1535526943252265e-05,
      "loss": 1.6344,
      "step": 710
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.1416309012875534e-05,
      "loss": 1.6445,
      "step": 720
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.129709108249881e-05,
      "loss": 1.637,
      "step": 730
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.117787315212208e-05,
      "loss": 1.6025,
      "step": 740
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.105865522174535e-05,
      "loss": 1.6254,
      "step": 750
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.0939437291368625e-05,
      "loss": 1.6274,
      "step": 760
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.0820219360991894e-05,
      "loss": 1.6329,
      "step": 770
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.0701001430615164e-05,
      "loss": 1.6436,
      "step": 780
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.058178350023844e-05,
      "loss": 1.6511,
      "step": 790
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.046256556986171e-05,
      "loss": 1.6011,
      "step": 800
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.034334763948498e-05,
      "loss": 1.6596,
      "step": 810
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.022412970910825e-05,
      "loss": 1.6009,
      "step": 820
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.0104911778731524e-05,
      "loss": 1.5909,
      "step": 830
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.998569384835479e-05,
      "loss": 1.6371,
      "step": 840
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.986647591797806e-05,
      "loss": 1.5722,
      "step": 850
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.974725798760134e-05,
      "loss": 1.6408,
      "step": 860
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.962804005722461e-05,
      "loss": 1.6413,
      "step": 870
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.950882212684788e-05,
      "loss": 1.6372,
      "step": 880
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.938960419647115e-05,
      "loss": 1.6492,
      "step": 890
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.927038626609442e-05,
      "loss": 1.667,
      "step": 900
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.915116833571769e-05,
      "loss": 1.626,
      "step": 910
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.903195040534097e-05,
      "loss": 1.5959,
      "step": 920
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.891273247496424e-05,
      "loss": 1.6026,
      "step": 930
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.8793514544587506e-05,
      "loss": 1.6449,
      "step": 940
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.867429661421078e-05,
      "loss": 1.6275,
      "step": 950
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.855507868383405e-05,
      "loss": 1.6155,
      "step": 960
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.843586075345732e-05,
      "loss": 1.6324,
      "step": 970
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.83166428230806e-05,
      "loss": 1.6119,
      "step": 980
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.8197424892703866e-05,
      "loss": 1.6156,
      "step": 990
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8078206962327136e-05,
      "loss": 1.5996,
      "step": 1000
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.795898903195041e-05,
      "loss": 1.6431,
      "step": 1010
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.783977110157368e-05,
      "loss": 1.6383,
      "step": 1020
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.772055317119695e-05,
      "loss": 1.6192,
      "step": 1030
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7601335240820226e-05,
      "loss": 1.5839,
      "step": 1040
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.7482117310443496e-05,
      "loss": 1.5957,
      "step": 1050
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.7362899380066765e-05,
      "loss": 1.6518,
      "step": 1060
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.724368144969004e-05,
      "loss": 1.6311,
      "step": 1070
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.712446351931331e-05,
      "loss": 1.6616,
      "step": 1080
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.700524558893658e-05,
      "loss": 1.6469,
      "step": 1090
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.688602765855985e-05,
      "loss": 1.6166,
      "step": 1100
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.676680972818312e-05,
      "loss": 1.6427,
      "step": 1110
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.6647591797806394e-05,
      "loss": 1.6341,
      "step": 1120
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.6528373867429664e-05,
      "loss": 1.628,
      "step": 1130
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.640915593705293e-05,
      "loss": 1.6182,
      "step": 1140
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.62899380066762e-05,
      "loss": 1.6392,
      "step": 1150
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.617072007629947e-05,
      "loss": 1.6185,
      "step": 1160
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.605150214592275e-05,
      "loss": 1.6146,
      "step": 1170
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.593228421554602e-05,
      "loss": 1.6151,
      "step": 1180
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.5813066285169286e-05,
      "loss": 1.6696,
      "step": 1190
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.569384835479256e-05,
      "loss": 1.6416,
      "step": 1200
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.557463042441583e-05,
      "loss": 1.6127,
      "step": 1210
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.54554124940391e-05,
      "loss": 1.6247,
      "step": 1220
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.533619456366238e-05,
      "loss": 1.6297,
      "step": 1230
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.5216976633285646e-05,
      "loss": 1.6354,
      "step": 1240
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.5097758702908915e-05,
      "loss": 1.6057,
      "step": 1250
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.497854077253219e-05,
      "loss": 1.6314,
      "step": 1260
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.485932284215546e-05,
      "loss": 1.6576,
      "step": 1270
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.474010491177873e-05,
      "loss": 1.6059,
      "step": 1280
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4620886981402006e-05,
      "loss": 1.6689,
      "step": 1290
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.4501669051025275e-05,
      "loss": 1.6505,
      "step": 1300
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.4382451120648545e-05,
      "loss": 1.5906,
      "step": 1310
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.426323319027182e-05,
      "loss": 1.6134,
      "step": 1320
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.414401525989509e-05,
      "loss": 1.6182,
      "step": 1330
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.402479732951836e-05,
      "loss": 1.6337,
      "step": 1340
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.3905579399141636e-05,
      "loss": 1.6436,
      "step": 1350
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.3786361468764905e-05,
      "loss": 1.6666,
      "step": 1360
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.3667143538388174e-05,
      "loss": 1.626,
      "step": 1370
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.354792560801145e-05,
      "loss": 1.5996,
      "step": 1380
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.342870767763472e-05,
      "loss": 1.6522,
      "step": 1390
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.330948974725799e-05,
      "loss": 1.6198,
      "step": 1400
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.3190271816881265e-05,
      "loss": 1.6077,
      "step": 1410
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.3071053886504534e-05,
      "loss": 1.6341,
      "step": 1420
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.2951835956127803e-05,
      "loss": 1.5617,
      "step": 1430
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.283261802575107e-05,
      "loss": 1.661,
      "step": 1440
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.271340009537435e-05,
      "loss": 1.601,
      "step": 1450
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.259418216499762e-05,
      "loss": 1.607,
      "step": 1460
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.247496423462089e-05,
      "loss": 1.642,
      "step": 1470
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.2355746304244164e-05,
      "loss": 1.6506,
      "step": 1480
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.223652837386743e-05,
      "loss": 1.6046,
      "step": 1490
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.21173104434907e-05,
      "loss": 1.6273,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4194,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 9.47879226680279e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}