{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.97191011235955,
  "eval_steps": 25,
  "global_step": 1775,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1404494382022472,
      "grad_norm": 1.0087393522262573,
      "learning_rate": 0.0001973018549747049,
      "loss": 1.3531,
      "step": 25
    },
    {
      "epoch": 0.2808988764044944,
      "grad_norm": 0.6913560032844543,
      "learning_rate": 0.0001944912872400225,
      "loss": 0.6347,
      "step": 50
    },
    {
      "epoch": 0.42134831460674155,
      "grad_norm": 0.5822920799255371,
      "learning_rate": 0.00019168071950534008,
      "loss": 0.6301,
      "step": 75
    },
    {
      "epoch": 0.5617977528089888,
      "grad_norm": 0.6517189741134644,
      "learning_rate": 0.00018887015177065767,
      "loss": 0.5746,
      "step": 100
    },
    {
      "epoch": 0.702247191011236,
      "grad_norm": 0.5613220930099487,
      "learning_rate": 0.00018605958403597526,
      "loss": 0.546,
      "step": 125
    },
    {
      "epoch": 0.8426966292134831,
      "grad_norm": 0.6231513023376465,
      "learning_rate": 0.00018324901630129288,
      "loss": 0.6111,
      "step": 150
    },
    {
      "epoch": 0.9831460674157303,
      "grad_norm": 0.5648068189620972,
      "learning_rate": 0.00018043844856661047,
      "loss": 0.4602,
      "step": 175
    },
    {
      "epoch": 1.1235955056179776,
      "grad_norm": 0.7641807794570923,
      "learning_rate": 0.00017762788083192804,
      "loss": 0.5375,
      "step": 200
    },
    {
      "epoch": 1.2640449438202248,
      "grad_norm": 0.8002265691757202,
      "learning_rate": 0.00017481731309724566,
      "loss": 0.384,
      "step": 225
    },
    {
      "epoch": 1.404494382022472,
      "grad_norm": 0.5983501672744751,
      "learning_rate": 0.00017200674536256325,
      "loss": 0.478,
      "step": 250
    },
    {
      "epoch": 1.5449438202247192,
      "grad_norm": 0.6597617268562317,
      "learning_rate": 0.00016919617762788084,
      "loss": 0.4276,
      "step": 275
    },
    {
      "epoch": 1.6853932584269664,
      "grad_norm": 0.6023315787315369,
      "learning_rate": 0.00016638560989319843,
      "loss": 0.3864,
      "step": 300
    },
    {
      "epoch": 1.8258426966292136,
      "grad_norm": 0.6361246705055237,
      "learning_rate": 0.00016357504215851602,
      "loss": 0.4311,
      "step": 325
    },
    {
      "epoch": 1.9662921348314608,
      "grad_norm": 0.5704653859138489,
      "learning_rate": 0.00016076447442383361,
      "loss": 0.3237,
      "step": 350
    },
    {
      "epoch": 2.106741573033708,
      "grad_norm": 0.6480958461761475,
      "learning_rate": 0.00015795390668915123,
      "loss": 0.3515,
      "step": 375
    },
    {
      "epoch": 2.247191011235955,
      "grad_norm": 0.6552001237869263,
      "learning_rate": 0.00015514333895446882,
      "loss": 0.2377,
      "step": 400
    },
    {
      "epoch": 2.3876404494382024,
      "grad_norm": 0.7502114176750183,
      "learning_rate": 0.0001523327712197864,
      "loss": 0.3069,
      "step": 425
    },
    {
      "epoch": 2.5280898876404496,
      "grad_norm": 0.7289499640464783,
      "learning_rate": 0.000149522203485104,
      "loss": 0.2973,
      "step": 450
    },
    {
      "epoch": 2.668539325842697,
      "grad_norm": 0.7269200682640076,
      "learning_rate": 0.0001467116357504216,
      "loss": 0.2612,
      "step": 475
    },
    {
      "epoch": 2.808988764044944,
      "grad_norm": 0.9184384346008301,
      "learning_rate": 0.0001439010680157392,
      "loss": 0.282,
      "step": 500
    },
    {
      "epoch": 2.949438202247191,
      "grad_norm": 0.6768775582313538,
      "learning_rate": 0.00014109050028105678,
      "loss": 0.2647,
      "step": 525
    },
    {
      "epoch": 3.0898876404494384,
      "grad_norm": 0.8616690039634705,
      "learning_rate": 0.00013827993254637437,
      "loss": 0.2385,
      "step": 550
    },
    {
      "epoch": 3.2303370786516856,
      "grad_norm": 0.5999014377593994,
      "learning_rate": 0.00013546936481169196,
      "loss": 0.1662,
      "step": 575
    },
    {
      "epoch": 3.370786516853933,
      "grad_norm": 0.5833967328071594,
      "learning_rate": 0.00013265879707700956,
      "loss": 0.2198,
      "step": 600
    },
    {
      "epoch": 3.51123595505618,
      "grad_norm": 0.694567084312439,
      "learning_rate": 0.00012984822934232717,
      "loss": 0.1762,
      "step": 625
    },
    {
      "epoch": 3.6516853932584272,
      "grad_norm": 0.6547160744667053,
      "learning_rate": 0.00012703766160764474,
      "loss": 0.2045,
      "step": 650
    },
    {
      "epoch": 3.7921348314606744,
      "grad_norm": 0.7818899750709534,
      "learning_rate": 0.00012422709387296233,
      "loss": 0.2029,
      "step": 675
    },
    {
      "epoch": 3.932584269662921,
      "grad_norm": 0.47738873958587646,
      "learning_rate": 0.00012141652613827993,
      "loss": 0.1734,
      "step": 700
    },
    {
      "epoch": 4.073033707865169,
      "grad_norm": 0.6599411368370056,
      "learning_rate": 0.00011860595840359754,
      "loss": 0.1773,
      "step": 725
    },
    {
      "epoch": 4.213483146067416,
      "grad_norm": 0.4201154410839081,
      "learning_rate": 0.00011579539066891512,
      "loss": 0.1276,
      "step": 750
    },
    {
      "epoch": 4.353932584269663,
      "grad_norm": 0.495446115732193,
      "learning_rate": 0.00011298482293423271,
      "loss": 0.146,
      "step": 775
    },
    {
      "epoch": 4.49438202247191,
      "grad_norm": 0.27687525749206543,
      "learning_rate": 0.00011017425519955031,
      "loss": 0.1302,
      "step": 800
    },
    {
      "epoch": 4.634831460674158,
      "grad_norm": 0.44135782122612,
      "learning_rate": 0.00010736368746486792,
      "loss": 0.157,
      "step": 825
    },
    {
      "epoch": 4.775280898876405,
      "grad_norm": 1.0475701093673706,
      "learning_rate": 0.00010455311973018551,
      "loss": 0.1463,
      "step": 850
    },
    {
      "epoch": 4.915730337078652,
      "grad_norm": 0.5669655799865723,
      "learning_rate": 0.00010174255199550309,
      "loss": 0.1427,
      "step": 875
    },
    {
      "epoch": 5.056179775280899,
      "grad_norm": 0.4750053286552429,
      "learning_rate": 9.893198426082069e-05,
      "loss": 0.137,
      "step": 900
    },
    {
      "epoch": 5.196629213483146,
      "grad_norm": 0.5436720252037048,
      "learning_rate": 9.612141652613828e-05,
      "loss": 0.1049,
      "step": 925
    },
    {
      "epoch": 5.337078651685394,
      "grad_norm": 0.9001078009605408,
      "learning_rate": 9.331084879145588e-05,
      "loss": 0.1214,
      "step": 950
    },
    {
      "epoch": 5.477528089887641,
      "grad_norm": 0.4534567892551422,
      "learning_rate": 9.050028105677347e-05,
      "loss": 0.1126,
      "step": 975
    },
    {
      "epoch": 5.617977528089888,
      "grad_norm": 0.5312709212303162,
      "learning_rate": 8.768971332209107e-05,
      "loss": 0.1134,
      "step": 1000
    },
    {
      "epoch": 5.758426966292134,
      "grad_norm": 0.4822239577770233,
      "learning_rate": 8.487914558740866e-05,
      "loss": 0.1171,
      "step": 1025
    },
    {
      "epoch": 5.898876404494382,
      "grad_norm": 1.4501484632492065,
      "learning_rate": 8.206857785272625e-05,
      "loss": 0.1189,
      "step": 1050
    },
    {
      "epoch": 6.03932584269663,
      "grad_norm": 0.40537115931510925,
      "learning_rate": 7.925801011804385e-05,
      "loss": 0.1166,
      "step": 1075
    },
    {
      "epoch": 6.179775280898877,
      "grad_norm": 0.5476611852645874,
      "learning_rate": 7.644744238336145e-05,
      "loss": 0.0919,
      "step": 1100
    },
    {
      "epoch": 6.320224719101123,
      "grad_norm": 0.2506895959377289,
      "learning_rate": 7.363687464867903e-05,
      "loss": 0.0974,
      "step": 1125
    },
    {
      "epoch": 6.460674157303371,
      "grad_norm": 0.3818029463291168,
      "learning_rate": 7.082630691399663e-05,
      "loss": 0.0999,
      "step": 1150
    },
    {
      "epoch": 6.601123595505618,
      "grad_norm": 0.4769856631755829,
      "learning_rate": 6.801573917931423e-05,
      "loss": 0.1042,
      "step": 1175
    },
    {
      "epoch": 6.741573033707866,
      "grad_norm": 0.2570767402648926,
      "learning_rate": 6.520517144463182e-05,
      "loss": 0.1067,
      "step": 1200
    },
    {
      "epoch": 6.882022471910112,
      "grad_norm": 0.39180973172187805,
      "learning_rate": 6.239460370994942e-05,
      "loss": 0.0967,
      "step": 1225
    },
    {
      "epoch": 7.022471910112359,
      "grad_norm": 0.4090649485588074,
      "learning_rate": 5.9584035975267006e-05,
      "loss": 0.1026,
      "step": 1250
    },
    {
      "epoch": 7.162921348314606,
      "grad_norm": 0.29195311665534973,
      "learning_rate": 5.6773468240584605e-05,
      "loss": 0.0831,
      "step": 1275
    },
    {
      "epoch": 7.303370786516854,
      "grad_norm": 0.4446125030517578,
      "learning_rate": 5.396290050590219e-05,
      "loss": 0.091,
      "step": 1300
    },
    {
      "epoch": 7.443820224719101,
      "grad_norm": 0.3004734516143799,
      "learning_rate": 5.115233277121979e-05,
      "loss": 0.0894,
      "step": 1325
    },
    {
      "epoch": 7.584269662921348,
      "grad_norm": 0.34026992321014404,
      "learning_rate": 4.8341765036537386e-05,
      "loss": 0.089,
      "step": 1350
    },
    {
      "epoch": 7.724719101123595,
      "grad_norm": 0.35366305708885193,
      "learning_rate": 4.553119730185498e-05,
      "loss": 0.0973,
      "step": 1375
    },
    {
      "epoch": 7.865168539325842,
      "grad_norm": 0.46121978759765625,
      "learning_rate": 4.272062956717257e-05,
      "loss": 0.0893,
      "step": 1400
    },
    {
      "epoch": 8.00561797752809,
      "grad_norm": 0.30849024653434753,
      "learning_rate": 3.991006183249017e-05,
      "loss": 0.0967,
      "step": 1425
    },
    {
      "epoch": 8.146067415730338,
      "grad_norm": 0.26774147152900696,
      "learning_rate": 3.709949409780776e-05,
      "loss": 0.0749,
      "step": 1450
    },
    {
      "epoch": 8.286516853932584,
      "grad_norm": 0.451695054769516,
      "learning_rate": 3.428892636312535e-05,
      "loss": 0.0822,
      "step": 1475
    },
    {
      "epoch": 8.426966292134832,
      "grad_norm": 0.3220645487308502,
      "learning_rate": 3.147835862844295e-05,
      "loss": 0.08,
      "step": 1500
    },
    {
      "epoch": 8.567415730337078,
      "grad_norm": 0.3273387551307678,
      "learning_rate": 2.8667790893760543e-05,
      "loss": 0.0847,
      "step": 1525
    },
    {
      "epoch": 8.707865168539326,
      "grad_norm": 0.3072643280029297,
      "learning_rate": 2.5857223159078137e-05,
      "loss": 0.0869,
      "step": 1550
    },
    {
      "epoch": 8.848314606741573,
      "grad_norm": 0.38988426327705383,
      "learning_rate": 2.304665542439573e-05,
      "loss": 0.0835,
      "step": 1575
    },
    {
      "epoch": 8.98876404494382,
      "grad_norm": 0.2914678156375885,
      "learning_rate": 2.0236087689713324e-05,
      "loss": 0.0929,
      "step": 1600
    },
    {
      "epoch": 9.129213483146067,
      "grad_norm": 0.2762880027294159,
      "learning_rate": 1.742551995503092e-05,
      "loss": 0.0742,
      "step": 1625
    },
    {
      "epoch": 9.269662921348315,
      "grad_norm": 0.33493509888648987,
      "learning_rate": 1.461495222034851e-05,
      "loss": 0.0791,
      "step": 1650
    },
    {
      "epoch": 9.410112359550562,
      "grad_norm": 0.3052024841308594,
      "learning_rate": 1.1804384485666105e-05,
      "loss": 0.075,
      "step": 1675
    },
    {
      "epoch": 9.55056179775281,
      "grad_norm": 0.38245493173599243,
      "learning_rate": 8.9938167509837e-06,
      "loss": 0.0795,
      "step": 1700
    },
    {
      "epoch": 9.691011235955056,
      "grad_norm": 0.2810506522655487,
      "learning_rate": 6.183249016301293e-06,
      "loss": 0.0814,
      "step": 1725
    },
    {
      "epoch": 9.831460674157304,
      "grad_norm": 0.34336212277412415,
      "learning_rate": 3.372681281618887e-06,
      "loss": 0.0774,
      "step": 1750
    },
    {
      "epoch": 9.97191011235955,
      "grad_norm": 0.3593064546585083,
      "learning_rate": 5.621135469364812e-07,
      "loss": 0.0837,
      "step": 1775
    }
  ],
  "logging_steps": 25,
  "max_steps": 1780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 25,
  "total_flos": 6273062618664960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}