{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7407407407407407,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 1.9547569751739502,
      "learning_rate": 5.205622071837585e-08,
      "loss": 0.213,
      "step": 10
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 2.578005313873291,
      "learning_rate": 1.041124414367517e-07,
      "loss": 0.2008,
      "step": 20
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 2.6108486652374268,
      "learning_rate": 1.5616866215512754e-07,
      "loss": 0.2183,
      "step": 30
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 2.8388636112213135,
      "learning_rate": 2.082248828735034e-07,
      "loss": 0.1992,
      "step": 40
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 3.057955026626587,
      "learning_rate": 2.6028110359187923e-07,
      "loss": 0.191,
      "step": 50
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 3.562337875366211,
      "learning_rate": 3.123373243102551e-07,
      "loss": 0.2146,
      "step": 60
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 2.5107476711273193,
      "learning_rate": 3.643935450286309e-07,
      "loss": 0.1965,
      "step": 70
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 3.556824207305908,
      "learning_rate": 4.164497657470068e-07,
      "loss": 0.2066,
      "step": 80
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 2.4915523529052734,
      "learning_rate": 4.633003643935451e-07,
      "loss": 0.1732,
      "step": 90
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 2.685553789138794,
      "learning_rate": 5.153565851119209e-07,
      "loss": 0.171,
      "step": 100
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 2.201007127761841,
      "learning_rate": 5.674128058302968e-07,
      "loss": 0.1896,
      "step": 110
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 2.432368040084839,
      "learning_rate": 6.194690265486726e-07,
      "loss": 0.1754,
      "step": 120
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 2.5078160762786865,
      "learning_rate": 6.715252472670485e-07,
      "loss": 0.1696,
      "step": 130
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 2.8419947624206543,
      "learning_rate": 7.235814679854243e-07,
      "loss": 0.171,
      "step": 140
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 1.7001116275787354,
      "learning_rate": 7.756376887038002e-07,
      "loss": 0.1851,
      "step": 150
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.28574275970459,
      "learning_rate": 8.27693909422176e-07,
      "loss": 0.1787,
      "step": 160
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 2.0533792972564697,
      "learning_rate": 8.797501301405519e-07,
      "loss": 0.1851,
      "step": 170
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.8994508981704712,
      "learning_rate": 9.318063508589277e-07,
      "loss": 0.1759,
      "step": 180
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 2.1839489936828613,
      "learning_rate": 9.838625715773036e-07,
      "loss": 0.1733,
      "step": 190
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 2.344303607940674,
      "learning_rate": 1.0359187922956794e-06,
      "loss": 0.1612,
      "step": 200
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 2.48638916015625,
      "learning_rate": 1.0879750130140553e-06,
      "loss": 0.1672,
      "step": 210
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 2.793229579925537,
      "learning_rate": 1.140031233732431e-06,
      "loss": 0.1726,
      "step": 220
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 2.6986732482910156,
      "learning_rate": 1.192087454450807e-06,
      "loss": 0.1652,
      "step": 230
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.5542423725128174,
      "learning_rate": 1.2441436751691828e-06,
      "loss": 0.1816,
      "step": 240
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 2.154715061187744,
      "learning_rate": 1.2961998958875587e-06,
      "loss": 0.1653,
      "step": 250
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 2.007305383682251,
      "learning_rate": 1.3482561166059347e-06,
      "loss": 0.1763,
      "step": 260
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.7739317417144775,
      "learning_rate": 1.4003123373243104e-06,
      "loss": 0.1534,
      "step": 270
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 2.1357200145721436,
      "learning_rate": 1.4523685580426864e-06,
      "loss": 0.1734,
      "step": 280
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 2.1542086601257324,
      "learning_rate": 1.5044247787610621e-06,
      "loss": 0.1671,
      "step": 290
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 2.20986008644104,
      "learning_rate": 1.556480999479438e-06,
      "loss": 0.1615,
      "step": 300
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 2.262831211090088,
      "learning_rate": 1.6085372201978138e-06,
      "loss": 0.1453,
      "step": 310
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.9716724157333374,
      "learning_rate": 1.6605934409161898e-06,
      "loss": 0.1688,
      "step": 320
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 2.058307647705078,
      "learning_rate": 1.7126496616345655e-06,
      "loss": 0.1494,
      "step": 330
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 2.354652166366577,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 0.1641,
      "step": 340
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 2.8483664989471436,
      "learning_rate": 1.8167621030713172e-06,
      "loss": 0.1545,
      "step": 350
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 3.0298044681549072,
      "learning_rate": 1.8688183237896931e-06,
      "loss": 0.1463,
      "step": 360
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 2.6635050773620605,
      "learning_rate": 1.920874544508069e-06,
      "loss": 0.1483,
      "step": 370
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 2.1750943660736084,
      "learning_rate": 1.972930765226445e-06,
      "loss": 0.1539,
      "step": 380
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 3.222320318222046,
      "learning_rate": 2.0249869859448206e-06,
      "loss": 0.1677,
      "step": 390
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 2.517885684967041,
      "learning_rate": 2.0770432066631967e-06,
      "loss": 0.1719,
      "step": 400
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 2.2146666049957275,
      "learning_rate": 2.1290994273815725e-06,
      "loss": 0.1445,
      "step": 410
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 1.9601733684539795,
      "learning_rate": 2.1811556480999482e-06,
      "loss": 0.1664,
      "step": 420
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 2.468904733657837,
      "learning_rate": 2.233211868818324e-06,
      "loss": 0.1486,
      "step": 430
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 1.9706175327301025,
      "learning_rate": 2.2852680895367e-06,
      "loss": 0.1408,
      "step": 440
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 1.9512994289398193,
      "learning_rate": 2.337324310255076e-06,
      "loss": 0.1659,
      "step": 450
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 2.83563494682312,
      "learning_rate": 2.3893805309734516e-06,
      "loss": 0.1686,
      "step": 460
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 3.0552988052368164,
      "learning_rate": 2.4414367516918273e-06,
      "loss": 0.1576,
      "step": 470
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.7302849292755127,
      "learning_rate": 2.4934929724102035e-06,
      "loss": 0.1447,
      "step": 480
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 2.417853593826294,
      "learning_rate": 2.5455491931285792e-06,
      "loss": 0.1581,
      "step": 490
    },
    {
      "execution_accuracy": 46.0,
      "selected_difficulty": "overall",
      "step": 500
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 2.8662281036376953,
      "learning_rate": 2.5976054138469546e-06,
      "loss": 0.1617,
      "step": 500
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 2.442883014678955,
      "learning_rate": 2.6496616345653307e-06,
      "loss": 0.1608,
      "step": 510
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 2.1168131828308105,
      "learning_rate": 2.7017178552837065e-06,
      "loss": 0.1438,
      "step": 520
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 3.455186605453491,
      "learning_rate": 2.7537740760020826e-06,
      "loss": 0.1661,
      "step": 530
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.615549325942993,
      "learning_rate": 2.805830296720458e-06,
      "loss": 0.1584,
      "step": 540
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 1.9767112731933594,
      "learning_rate": 2.857886517438834e-06,
      "loss": 0.1299,
      "step": 550
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 2.0110256671905518,
      "learning_rate": 2.90994273815721e-06,
      "loss": 0.1436,
      "step": 560
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 2.232252836227417,
      "learning_rate": 2.961998958875586e-06,
      "loss": 0.1476,
      "step": 570
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 2.556427240371704,
      "learning_rate": 3.0140551795939618e-06,
      "loss": 0.1411,
      "step": 580
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 1.7226930856704712,
      "learning_rate": 3.0661114003123375e-06,
      "loss": 0.1421,
      "step": 590
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.7159005403518677,
      "learning_rate": 3.1181676210307132e-06,
      "loss": 0.1451,
      "step": 600
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 2.398245334625244,
      "learning_rate": 3.1702238417490894e-06,
      "loss": 0.1537,
      "step": 610
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 2.5853817462921143,
      "learning_rate": 3.222280062467465e-06,
      "loss": 0.1506,
      "step": 620
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 2.438486337661743,
      "learning_rate": 3.274336283185841e-06,
      "loss": 0.1512,
      "step": 630
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.3523032665252686,
      "learning_rate": 3.3263925039042166e-06,
      "loss": 0.1489,
      "step": 640
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 2.763634443283081,
      "learning_rate": 3.3784487246225928e-06,
      "loss": 0.1518,
      "step": 650
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 2.588419198989868,
      "learning_rate": 3.4305049453409685e-06,
      "loss": 0.138,
      "step": 660
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 1.9856290817260742,
      "learning_rate": 3.4825611660593443e-06,
      "loss": 0.1549,
      "step": 670
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 1.7812482118606567,
      "learning_rate": 3.53461738677772e-06,
      "loss": 0.1288,
      "step": 680
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 2.1843719482421875,
      "learning_rate": 3.586673607496096e-06,
      "loss": 0.1311,
      "step": 690
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 2.653047561645508,
      "learning_rate": 3.638729828214472e-06,
      "loss": 0.1612,
      "step": 700
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 2.5062875747680664,
      "learning_rate": 3.690786048932848e-06,
      "loss": 0.1437,
      "step": 710
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.8424952030181885,
      "learning_rate": 3.7428422696512234e-06,
      "loss": 0.1368,
      "step": 720
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 2.2268905639648438,
      "learning_rate": 3.7948984903695995e-06,
      "loss": 0.1442,
      "step": 730
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 2.2701923847198486,
      "learning_rate": 3.846954711087975e-06,
      "loss": 0.1359,
      "step": 740
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 1.805020809173584,
      "learning_rate": 3.899010931806351e-06,
      "loss": 0.1414,
      "step": 750
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 2.4810807704925537,
      "learning_rate": 3.951067152524727e-06,
      "loss": 0.1504,
      "step": 760
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 2.313380002975464,
      "learning_rate": 4.003123373243103e-06,
      "loss": 0.1417,
      "step": 770
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 2.2919764518737793,
      "learning_rate": 4.055179593961479e-06,
      "loss": 0.1402,
      "step": 780
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 2.7147014141082764,
      "learning_rate": 4.107235814679855e-06,
      "loss": 0.1305,
      "step": 790
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.1526637077331543,
      "learning_rate": 4.15929203539823e-06,
      "loss": 0.1371,
      "step": 800
    },
    {
      "epoch": 0.375,
      "grad_norm": 2.168653726577759,
      "learning_rate": 4.211348256116606e-06,
      "loss": 0.1261,
      "step": 810
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 1.9278998374938965,
      "learning_rate": 4.263404476834982e-06,
      "loss": 0.1371,
      "step": 820
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 2.528472423553467,
      "learning_rate": 4.315460697553358e-06,
      "loss": 0.1343,
      "step": 830
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 1.9146366119384766,
      "learning_rate": 4.367516918271734e-06,
      "loss": 0.1287,
      "step": 840
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 2.0333926677703857,
      "learning_rate": 4.41957313899011e-06,
      "loss": 0.1226,
      "step": 850
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 1.8780897855758667,
      "learning_rate": 4.4716293597084854e-06,
      "loss": 0.1358,
      "step": 860
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 2.3289811611175537,
      "learning_rate": 4.523685580426862e-06,
      "loss": 0.1361,
      "step": 870
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 2.307506799697876,
      "learning_rate": 4.575741801145237e-06,
      "loss": 0.1347,
      "step": 880
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 2.4301393032073975,
      "learning_rate": 4.627798021863613e-06,
      "loss": 0.1407,
      "step": 890
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.1248655319213867,
      "learning_rate": 4.679854242581988e-06,
      "loss": 0.1359,
      "step": 900
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 2.7919039726257324,
      "learning_rate": 4.7319104633003646e-06,
      "loss": 0.1404,
      "step": 910
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 2.627920627593994,
      "learning_rate": 4.783966684018741e-06,
      "loss": 0.1347,
      "step": 920
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 1.7436546087265015,
      "learning_rate": 4.836022904737117e-06,
      "loss": 0.135,
      "step": 930
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 2.3651235103607178,
      "learning_rate": 4.888079125455492e-06,
      "loss": 0.1165,
      "step": 940
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 3.688002586364746,
      "learning_rate": 4.940135346173868e-06,
      "loss": 0.1289,
      "step": 950
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.553744077682495,
      "learning_rate": 4.992191566892244e-06,
      "loss": 0.1399,
      "step": 960
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 2.997828722000122,
      "learning_rate": 5.04424778761062e-06,
      "loss": 0.1115,
      "step": 970
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 1.8085178136825562,
      "learning_rate": 5.096304008328996e-06,
      "loss": 0.1144,
      "step": 980
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 3.0211071968078613,
      "learning_rate": 5.148360229047371e-06,
      "loss": 0.1432,
      "step": 990
    },
    {
      "execution_accuracy": 46.0,
      "selected_difficulty": "overall",
      "step": 1000
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 2.11688232421875,
      "learning_rate": 5.2004164497657475e-06,
      "loss": 0.136,
      "step": 1000
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 2.3399276733398438,
      "learning_rate": 5.252472670484124e-06,
      "loss": 0.1258,
      "step": 1010
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 2.1700856685638428,
      "learning_rate": 5.3045288912025e-06,
      "loss": 0.1278,
      "step": 1020
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 2.491363286972046,
      "learning_rate": 5.356585111920874e-06,
      "loss": 0.1278,
      "step": 1030
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 2.147585868835449,
      "learning_rate": 5.4086413326392505e-06,
      "loss": 0.1263,
      "step": 1040
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 2.3154337406158447,
      "learning_rate": 5.460697553357627e-06,
      "loss": 0.1231,
      "step": 1050
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 2.23714280128479,
      "learning_rate": 5.512753774076003e-06,
      "loss": 0.1396,
      "step": 1060
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 2.789081573486328,
      "learning_rate": 5.564809994794378e-06,
      "loss": 0.1505,
      "step": 1070
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.1684062480926514,
      "learning_rate": 5.616866215512754e-06,
      "loss": 0.128,
      "step": 1080
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 2.603804588317871,
      "learning_rate": 5.6689224362311304e-06,
      "loss": 0.1269,
      "step": 1090
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 1.6282514333724976,
      "learning_rate": 5.720978656949507e-06,
      "loss": 0.1201,
      "step": 1100
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 2.267298460006714,
      "learning_rate": 5.773034877667881e-06,
      "loss": 0.1294,
      "step": 1110
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 2.526259183883667,
      "learning_rate": 5.825091098386257e-06,
      "loss": 0.1263,
      "step": 1120
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 2.38616943359375,
      "learning_rate": 5.877147319104633e-06,
      "loss": 0.1436,
      "step": 1130
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 2.69435715675354,
      "learning_rate": 5.9292035398230096e-06,
      "loss": 0.1374,
      "step": 1140
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 2.2402076721191406,
      "learning_rate": 5.981259760541385e-06,
      "loss": 0.1208,
      "step": 1150
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 2.1587324142456055,
      "learning_rate": 6.033315981259761e-06,
      "loss": 0.1458,
      "step": 1160
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 2.2141196727752686,
      "learning_rate": 6.085372201978137e-06,
      "loss": 0.1193,
      "step": 1170
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 2.2879085540771484,
      "learning_rate": 6.137428422696513e-06,
      "loss": 0.1345,
      "step": 1180
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 3.161435604095459,
      "learning_rate": 6.189484643414888e-06,
      "loss": 0.1319,
      "step": 1190
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.313039779663086,
      "learning_rate": 6.241540864133264e-06,
      "loss": 0.1295,
      "step": 1200
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 3.2827019691467285,
      "learning_rate": 6.29359708485164e-06,
      "loss": 0.1335,
      "step": 1210
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 2.1369690895080566,
      "learning_rate": 6.345653305570016e-06,
      "loss": 0.1123,
      "step": 1220
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 2.3678247928619385,
      "learning_rate": 6.397709526288392e-06,
      "loss": 0.1271,
      "step": 1230
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 2.282134771347046,
      "learning_rate": 6.449765747006768e-06,
      "loss": 0.1078,
      "step": 1240
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 2.3011066913604736,
      "learning_rate": 6.501821967725144e-06,
      "loss": 0.1356,
      "step": 1250
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 2.669616460800171,
      "learning_rate": 6.55387818844352e-06,
      "loss": 0.1175,
      "step": 1260
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 2.568129777908325,
      "learning_rate": 6.605934409161895e-06,
      "loss": 0.1168,
      "step": 1270
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.9154844284057617,
      "learning_rate": 6.657990629880271e-06,
      "loss": 0.1235,
      "step": 1280
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 2.8254613876342773,
      "learning_rate": 6.710046850598647e-06,
      "loss": 0.1352,
      "step": 1290
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 1.9419591426849365,
      "learning_rate": 6.762103071317023e-06,
      "loss": 0.1196,
      "step": 1300
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 2.1100144386291504,
      "learning_rate": 6.814159292035398e-06,
      "loss": 0.1337,
      "step": 1310
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 2.0183956623077393,
      "learning_rate": 6.8662155127537746e-06,
      "loss": 0.1166,
      "step": 1320
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 2.0606720447540283,
      "learning_rate": 6.918271733472151e-06,
      "loss": 0.1265,
      "step": 1330
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 2.4177541732788086,
      "learning_rate": 6.970327954190527e-06,
      "loss": 0.1276,
      "step": 1340
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.064150810241699,
      "learning_rate": 7.022384174908901e-06,
      "loss": 0.1262,
      "step": 1350
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 1.9812283515930176,
      "learning_rate": 7.0744403956272775e-06,
      "loss": 0.1168,
      "step": 1360
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 2.5228352546691895,
      "learning_rate": 7.126496616345654e-06,
      "loss": 0.126,
      "step": 1370
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 2.5014448165893555,
      "learning_rate": 7.17855283706403e-06,
      "loss": 0.1275,
      "step": 1380
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 2.343454122543335,
      "learning_rate": 7.230609057782405e-06,
      "loss": 0.1288,
      "step": 1390
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 2.2527363300323486,
      "learning_rate": 7.282665278500781e-06,
      "loss": 0.1447,
      "step": 1400
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 2.631322145462036,
      "learning_rate": 7.3347214992191575e-06,
      "loss": 0.1411,
      "step": 1410
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 2.194526433944702,
      "learning_rate": 7.386777719937534e-06,
      "loss": 0.1314,
      "step": 1420
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 1.7892805337905884,
      "learning_rate": 7.438833940655908e-06,
      "loss": 0.1237,
      "step": 1430
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.414116621017456,
      "learning_rate": 7.490890161374284e-06,
      "loss": 0.1218,
      "step": 1440
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 1.8819609880447388,
      "learning_rate": 7.5429463820926605e-06,
      "loss": 0.1196,
      "step": 1450
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 2.459386110305786,
      "learning_rate": 7.595002602811037e-06,
      "loss": 0.1222,
      "step": 1460
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 2.1400787830352783,
      "learning_rate": 7.647058823529411e-06,
      "loss": 0.1227,
      "step": 1470
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 2.4179768562316895,
      "learning_rate": 7.699115044247788e-06,
      "loss": 0.1392,
      "step": 1480
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 2.1421689987182617,
      "learning_rate": 7.751171264966163e-06,
      "loss": 0.1367,
      "step": 1490
    },
    {
      "execution_accuracy": 45.0,
      "selected_difficulty": "overall",
      "step": 1500
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 2.1561977863311768,
      "learning_rate": 7.80322748568454e-06,
      "loss": 0.1308,
      "step": 1500
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 1.4436249732971191,
      "learning_rate": 7.855283706402916e-06,
      "loss": 0.1131,
      "step": 1510
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 2.2428104877471924,
      "learning_rate": 7.907339927121291e-06,
      "loss": 0.1187,
      "step": 1520
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 2.241523265838623,
      "learning_rate": 7.959396147839668e-06,
      "loss": 0.1129,
      "step": 1530
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 1.6972129344940186,
      "learning_rate": 8.011452368558043e-06,
      "loss": 0.1189,
      "step": 1540
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 2.174455165863037,
      "learning_rate": 8.063508589276419e-06,
      "loss": 0.1186,
      "step": 1550
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 2.057164430618286,
      "learning_rate": 8.115564809994794e-06,
      "loss": 0.1259,
      "step": 1560
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 2.4605278968811035,
      "learning_rate": 8.167621030713171e-06,
      "loss": 0.1237,
      "step": 1570
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 2.3143205642700195,
      "learning_rate": 8.219677251431546e-06,
      "loss": 0.1055,
      "step": 1580
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 2.437072992324829,
      "learning_rate": 8.271733472149922e-06,
      "loss": 0.1101,
      "step": 1590
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.146765947341919,
      "learning_rate": 8.323789692868299e-06,
      "loss": 0.1127,
      "step": 1600
    }
  ],
  "logging_steps": 10,
  "max_steps": 15068,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.821775221247181e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}