{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.2969624996185303,
      "epoch": 0.012861736334405145,
      "grad_norm": 1.222815990447998,
      "learning_rate": 0.0,
      "loss": 2.025021553039551,
      "mean_token_accuracy": 0.5397194549441338,
      "num_tokens": 128512.0,
      "step": 1
    },
    {
      "entropy": 1.3495921194553375,
      "epoch": 0.02572347266881029,
      "grad_norm": 1.2900104522705078,
      "learning_rate": 4.166666666666667e-06,
      "loss": 2.113243341445923,
      "mean_token_accuracy": 0.5239669531583786,
      "num_tokens": 258439.0,
      "step": 2
    },
    {
      "entropy": 1.4065107256174088,
      "epoch": 0.03858520900321544,
      "grad_norm": 1.1876918077468872,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.0984230041503906,
      "mean_token_accuracy": 0.525254875421524,
      "num_tokens": 387958.0,
      "step": 3
    },
    {
      "entropy": 1.4473730325698853,
      "epoch": 0.05144694533762058,
      "grad_norm": 0.995452880859375,
      "learning_rate": 1.25e-05,
      "loss": 2.0187673568725586,
      "mean_token_accuracy": 0.534252941608429,
      "num_tokens": 516779.0,
      "step": 4
    },
    {
      "entropy": 1.626717284321785,
      "epoch": 0.06430868167202572,
      "grad_norm": 0.6222253441810608,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.9110387563705444,
      "mean_token_accuracy": 0.5435223057866096,
      "num_tokens": 645829.0,
      "step": 5
    },
    {
      "entropy": 1.810067042708397,
      "epoch": 0.07717041800643087,
      "grad_norm": 0.42118003964424133,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.8789349794387817,
      "mean_token_accuracy": 0.5466088876128197,
      "num_tokens": 774435.0,
      "step": 6
    },
    {
      "entropy": 1.9707088768482208,
      "epoch": 0.09003215434083602,
      "grad_norm": 0.4645366072654724,
      "learning_rate": 2.5e-05,
      "loss": 1.8074758052825928,
      "mean_token_accuracy": 0.5567064955830574,
      "num_tokens": 903545.0,
      "step": 7
    },
    {
      "entropy": 1.9890314191579819,
      "epoch": 0.10289389067524116,
      "grad_norm": 0.5461070537567139,
      "learning_rate": 2.916666666666667e-05,
      "loss": 1.7440648078918457,
      "mean_token_accuracy": 0.5663307011127472,
      "num_tokens": 1033070.0,
      "step": 8
    },
    {
      "entropy": 1.968129649758339,
      "epoch": 0.1157556270096463,
      "grad_norm": 0.5405251383781433,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7069363594055176,
      "mean_token_accuracy": 0.5683588162064552,
      "num_tokens": 1162755.0,
      "step": 9
    },
    {
      "entropy": 1.8345413953065872,
      "epoch": 0.12861736334405144,
      "grad_norm": 0.42177239060401917,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.65086030960083,
      "mean_token_accuracy": 0.5773059874773026,
      "num_tokens": 1290164.0,
      "step": 10
    },
    {
      "entropy": 1.6431169360876083,
      "epoch": 0.1414790996784566,
      "grad_norm": 0.31144559383392334,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.582027792930603,
      "mean_token_accuracy": 0.5872198939323425,
      "num_tokens": 1419501.0,
      "step": 11
    },
    {
      "entropy": 1.544620230793953,
      "epoch": 0.15434083601286175,
      "grad_norm": 0.27825888991355896,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.5446865558624268,
      "mean_token_accuracy": 0.594700962305069,
      "num_tokens": 1547996.0,
      "step": 12
    },
    {
      "entropy": 1.4267793744802475,
      "epoch": 0.16720257234726688,
      "grad_norm": 0.2835897207260132,
      "learning_rate": 5e-05,
      "loss": 1.509974479675293,
      "mean_token_accuracy": 0.6006790399551392,
      "num_tokens": 1676937.0,
      "step": 13
    },
    {
      "entropy": 1.3972271531820297,
      "epoch": 0.18006430868167203,
      "grad_norm": 0.25854921340942383,
      "learning_rate": 4.9997496794168726e-05,
      "loss": 1.491778016090393,
      "mean_token_accuracy": 0.6045994758605957,
      "num_tokens": 1806013.0,
      "step": 14
    },
    {
      "entropy": 1.4395506381988525,
      "epoch": 0.19292604501607716,
      "grad_norm": 0.22095996141433716,
      "learning_rate": 4.998998767795805e-05,
      "loss": 1.4883487224578857,
      "mean_token_accuracy": 0.6050755307078362,
      "num_tokens": 1935387.0,
      "step": 15
    },
    {
      "entropy": 1.4550755470991135,
      "epoch": 0.2057877813504823,
      "grad_norm": 0.24221676588058472,
      "learning_rate": 4.9977474155117045e-05,
      "loss": 1.4858245849609375,
      "mean_token_accuracy": 0.6017315089702606,
      "num_tokens": 2065100.0,
      "step": 16
    },
    {
      "entropy": 1.4459427893161774,
      "epoch": 0.21864951768488747,
      "grad_norm": 0.25146999955177307,
      "learning_rate": 4.995995873155958e-05,
      "loss": 1.4274994134902954,
      "mean_token_accuracy": 0.6151479333639145,
      "num_tokens": 2194685.0,
      "step": 17
    },
    {
      "entropy": 1.4442210048437119,
      "epoch": 0.2315112540192926,
      "grad_norm": 0.2271786779165268,
      "learning_rate": 4.99374449148625e-05,
      "loss": 1.4092518091201782,
      "mean_token_accuracy": 0.6148851290345192,
      "num_tokens": 2324963.0,
      "step": 18
    },
    {
      "entropy": 1.4254360347986221,
      "epoch": 0.24437299035369775,
      "grad_norm": 0.18994390964508057,
      "learning_rate": 4.9909937213563165e-05,
      "loss": 1.3825007677078247,
      "mean_token_accuracy": 0.6199355497956276,
      "num_tokens": 2454343.0,
      "step": 19
    },
    {
      "entropy": 1.3843167871236801,
      "epoch": 0.2572347266881029,
      "grad_norm": 0.18420229852199554,
      "learning_rate": 4.987744113625665e-05,
      "loss": 1.3471739292144775,
      "mean_token_accuracy": 0.6283371672034264,
      "num_tokens": 2584405.0,
      "step": 20
    },
    {
      "entropy": 1.3585271686315536,
      "epoch": 0.27009646302250806,
      "grad_norm": 0.18983817100524902,
      "learning_rate": 4.9839963190492576e-05,
      "loss": 1.3283567428588867,
      "mean_token_accuracy": 0.6319968476891518,
      "num_tokens": 2709555.0,
      "step": 21
    },
    {
      "entropy": 1.3483584225177765,
      "epoch": 0.2829581993569132,
      "grad_norm": 0.18332050740718842,
      "learning_rate": 4.979751088147192e-05,
      "loss": 1.33201003074646,
      "mean_token_accuracy": 0.6298539489507675,
      "num_tokens": 2839191.0,
      "step": 22
    },
    {
      "entropy": 1.334426462650299,
      "epoch": 0.2958199356913183,
      "grad_norm": 0.16615396738052368,
      "learning_rate": 4.975009271054409e-05,
      "loss": 1.3058710098266602,
      "mean_token_accuracy": 0.6357970610260963,
      "num_tokens": 2968625.0,
      "step": 23
    },
    {
      "entropy": 1.3269707262516022,
      "epoch": 0.3086816720257235,
      "grad_norm": 0.16659598052501678,
      "learning_rate": 4.969771817350445e-05,
      "loss": 1.298633337020874,
      "mean_token_accuracy": 0.6390289217233658,
      "num_tokens": 3098193.0,
      "step": 24
    },
    {
      "entropy": 1.3264441937208176,
      "epoch": 0.3215434083601286,
      "grad_norm": 0.18099723756313324,
      "learning_rate": 4.9640397758692715e-05,
      "loss": 1.2919727563858032,
      "mean_token_accuracy": 0.6379936411976814,
      "num_tokens": 3226304.0,
      "step": 25
    },
    {
      "entropy": 1.2971351444721222,
      "epoch": 0.33440514469453375,
      "grad_norm": 0.16978149116039276,
      "learning_rate": 4.957814294489261e-05,
      "loss": 1.283421277999878,
      "mean_token_accuracy": 0.6396878883242607,
      "num_tokens": 3356150.0,
      "step": 26
    },
    {
      "entropy": 1.2420216798782349,
      "epoch": 0.34726688102893893,
      "grad_norm": 0.15654370188713074,
      "learning_rate": 4.9510966199033174e-05,
      "loss": 1.2411205768585205,
      "mean_token_accuracy": 0.6497687473893166,
      "num_tokens": 3485881.0,
      "step": 27
    },
    {
      "entropy": 1.2905446141958237,
      "epoch": 0.36012861736334406,
      "grad_norm": 0.15767726302146912,
      "learning_rate": 4.943888097369216e-05,
      "loss": 1.2969235181808472,
      "mean_token_accuracy": 0.6399867981672287,
      "num_tokens": 3614360.0,
      "step": 28
    },
    {
      "entropy": 1.2797959297895432,
      "epoch": 0.3729903536977492,
      "grad_norm": 0.1609920859336853,
      "learning_rate": 4.936190170440208e-05,
      "loss": 1.281036615371704,
      "mean_token_accuracy": 0.6414945125579834,
      "num_tokens": 3742757.0,
      "step": 29
    },
    {
      "entropy": 1.2370718121528625,
      "epoch": 0.3858520900321543,
      "grad_norm": 0.15289531648159027,
      "learning_rate": 4.928004380675941e-05,
      "loss": 1.2397706508636475,
      "mean_token_accuracy": 0.6485739275813103,
      "num_tokens": 3872361.0,
      "step": 30
    },
    {
      "entropy": 1.2661651074886322,
      "epoch": 0.3987138263665595,
      "grad_norm": 0.15539875626564026,
      "learning_rate": 4.9193323673337476e-05,
      "loss": 1.2545585632324219,
      "mean_token_accuracy": 0.646148107945919,
      "num_tokens": 4001029.0,
      "step": 31
    },
    {
      "entropy": 1.259293794631958,
      "epoch": 0.4115755627009646,
      "grad_norm": 0.15602311491966248,
      "learning_rate": 4.910175867040377e-05,
      "loss": 1.2386581897735596,
      "mean_token_accuracy": 0.6532392650842667,
      "num_tokens": 4129746.0,
      "step": 32
    },
    {
      "entropy": 1.2246208488941193,
      "epoch": 0.42443729903536975,
      "grad_norm": 0.15040729939937592,
      "learning_rate": 4.9005367134442235e-05,
      "loss": 1.2012075185775757,
      "mean_token_accuracy": 0.6605038940906525,
      "num_tokens": 4258908.0,
      "step": 33
    },
    {
      "entropy": 1.2688497006893158,
      "epoch": 0.43729903536977494,
      "grad_norm": 0.14351816475391388,
      "learning_rate": 4.890416836848127e-05,
      "loss": 1.2468310594558716,
      "mean_token_accuracy": 0.6454005613923073,
      "num_tokens": 4388837.0,
      "step": 34
    },
    {
      "entropy": 1.2282109707593918,
      "epoch": 0.45016077170418006,
      "grad_norm": 0.14232277870178223,
      "learning_rate": 4.8798182638228166e-05,
      "loss": 1.2170629501342773,
      "mean_token_accuracy": 0.6531817615032196,
      "num_tokens": 4518130.0,
      "step": 35
    },
    {
      "entropy": 1.2145698070526123,
      "epoch": 0.4630225080385852,
      "grad_norm": 0.14945274591445923,
      "learning_rate": 4.868743116801074e-05,
      "loss": 1.2234522104263306,
      "mean_token_accuracy": 0.6538028195500374,
      "num_tokens": 4647727.0,
      "step": 36
    },
    {
      "entropy": 1.2184867858886719,
      "epoch": 0.4758842443729904,
      "grad_norm": 0.14716529846191406,
      "learning_rate": 4.857193613652711e-05,
      "loss": 1.2205889225006104,
      "mean_token_accuracy": 0.6552813798189163,
      "num_tokens": 4776814.0,
      "step": 37
    },
    {
      "entropy": 1.2501244097948074,
      "epoch": 0.4887459807073955,
      "grad_norm": 0.13584738969802856,
      "learning_rate": 4.845172067240415e-05,
      "loss": 1.232811689376831,
      "mean_token_accuracy": 0.6496494188904762,
      "num_tokens": 4906642.0,
      "step": 38
    },
    {
      "entropy": 1.2297646403312683,
      "epoch": 0.5016077170418006,
      "grad_norm": 0.1445397287607193,
      "learning_rate": 4.8326808849565936e-05,
      "loss": 1.2179179191589355,
      "mean_token_accuracy": 0.6524648442864418,
      "num_tokens": 5035784.0,
      "step": 39
    },
    {
      "entropy": 1.2054394781589508,
      "epoch": 0.5144694533762058,
      "grad_norm": 0.1438300460577011,
      "learning_rate": 4.819722568241274e-05,
      "loss": 1.1902542114257812,
      "mean_token_accuracy": 0.6586381196975708,
      "num_tokens": 5163483.0,
      "step": 40
    },
    {
      "entropy": 1.1801835894584656,
      "epoch": 0.5273311897106109,
      "grad_norm": 0.13536524772644043,
      "learning_rate": 4.806299712081172e-05,
      "loss": 1.1734623908996582,
      "mean_token_accuracy": 0.6613527312874794,
      "num_tokens": 5289099.0,
      "step": 41
    },
    {
      "entropy": 1.2093226611614227,
      "epoch": 0.5401929260450161,
      "grad_norm": 0.13810646533966064,
      "learning_rate": 4.792415004490034e-05,
      "loss": 1.2002174854278564,
      "mean_token_accuracy": 0.6581337600946426,
      "num_tokens": 5414735.0,
      "step": 42
    },
    {
      "entropy": 1.1848722696304321,
      "epoch": 0.5530546623794212,
      "grad_norm": 0.1468912959098816,
      "learning_rate": 4.77807122597034e-05,
      "loss": 1.1885192394256592,
      "mean_token_accuracy": 0.6589618176221848,
      "num_tokens": 5543143.0,
      "step": 43
    },
    {
      "entropy": 1.181750476360321,
      "epoch": 0.5659163987138264,
      "grad_norm": 0.1429019272327423,
      "learning_rate": 4.7632712489564926e-05,
      "loss": 1.1800310611724854,
      "mean_token_accuracy": 0.6618404239416122,
      "num_tokens": 5671758.0,
      "step": 44
    },
    {
      "entropy": 1.223798543214798,
      "epoch": 0.5787781350482315,
      "grad_norm": 0.13423405587673187,
      "learning_rate": 4.748018037239592e-05,
      "loss": 1.2137880325317383,
      "mean_token_accuracy": 0.6538020968437195,
      "num_tokens": 5801203.0,
      "step": 45
    },
    {
      "entropy": 1.1596673130989075,
      "epoch": 0.5916398713826366,
      "grad_norm": 0.14085975289344788,
      "learning_rate": 4.732314645373921e-05,
      "loss": 1.1383979320526123,
      "mean_token_accuracy": 0.6676715686917305,
      "num_tokens": 5929286.0,
      "step": 46
    },
    {
      "entropy": 1.1791094541549683,
      "epoch": 0.6045016077170418,
      "grad_norm": 0.14022590219974518,
      "learning_rate": 4.7161642180652464e-05,
      "loss": 1.1624398231506348,
      "mean_token_accuracy": 0.6638200730085373,
      "num_tokens": 6055494.0,
      "step": 47
    },
    {
      "entropy": 1.17191481590271,
      "epoch": 0.617363344051447,
      "grad_norm": 0.14044098556041718,
      "learning_rate": 4.699569989541074e-05,
      "loss": 1.1661159992218018,
      "mean_token_accuracy": 0.6632223278284073,
      "num_tokens": 6184519.0,
      "step": 48
    },
    {
      "entropy": 1.1261081546545029,
      "epoch": 0.6302250803858521,
      "grad_norm": 0.13071966171264648,
      "learning_rate": 4.6825352829029705e-05,
      "loss": 1.1280871629714966,
      "mean_token_accuracy": 0.672090008854866,
      "num_tokens": 6313996.0,
      "step": 49
    },
    {
      "entropy": 1.108861967921257,
      "epoch": 0.6430868167202572,
      "grad_norm": 0.13524308800697327,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.1100517511367798,
      "mean_token_accuracy": 0.6758645325899124,
      "num_tokens": 6442914.0,
      "step": 50
    },
    {
      "entropy": 1.1622951924800873,
      "epoch": 0.6559485530546624,
      "grad_norm": 0.14350417256355286,
      "learning_rate": 4.647158168051066e-05,
      "loss": 1.1698243618011475,
      "mean_token_accuracy": 0.661836288869381,
      "num_tokens": 6569312.0,
      "step": 51
    },
    {
      "entropy": 1.1530523151159286,
      "epoch": 0.6688102893890675,
      "grad_norm": 0.13998498022556305,
      "learning_rate": 4.628822844333278e-05,
      "loss": 1.135171890258789,
      "mean_token_accuracy": 0.6697984710335732,
      "num_tokens": 6698149.0,
      "step": 52
    },
    {
      "entropy": 1.1557507067918777,
      "epoch": 0.6816720257234726,
      "grad_norm": 0.13826699554920197,
      "learning_rate": 4.6100612100748765e-05,
      "loss": 1.1333105564117432,
      "mean_token_accuracy": 0.6696186140179634,
      "num_tokens": 6827547.0,
      "step": 53
    },
    {
      "entropy": 1.1415271162986755,
      "epoch": 0.6945337620578779,
      "grad_norm": 0.14170631766319275,
      "learning_rate": 4.59087702241444e-05,
      "loss": 1.1154472827911377,
      "mean_token_accuracy": 0.6728732585906982,
      "num_tokens": 6956641.0,
      "step": 54
    },
    {
      "entropy": 1.133439689874649,
      "epoch": 0.707395498392283,
      "grad_norm": 0.19915136694908142,
      "learning_rate": 4.571274123109606e-05,
      "loss": 1.12148916721344,
      "mean_token_accuracy": 0.6721195057034492,
      "num_tokens": 7087072.0,
      "step": 55
    },
    {
      "entropy": 1.1475654691457748,
      "epoch": 0.7202572347266881,
      "grad_norm": 0.1380179524421692,
      "learning_rate": 4.551256437767719e-05,
      "loss": 1.147176742553711,
      "mean_token_accuracy": 0.6669263690710068,
      "num_tokens": 7217233.0,
      "step": 56
    },
    {
      "entropy": 1.1235886365175247,
      "epoch": 0.7331189710610932,
      "grad_norm": 0.14977428317070007,
      "learning_rate": 4.530827975059715e-05,
      "loss": 1.1248936653137207,
      "mean_token_accuracy": 0.6717223599553108,
      "num_tokens": 7345601.0,
      "step": 57
    },
    {
      "entropy": 1.0966329723596573,
      "epoch": 0.7459807073954984,
      "grad_norm": 0.13217344880104065,
      "learning_rate": 4.5099928259173516e-05,
      "loss": 1.0947030782699585,
      "mean_token_accuracy": 0.6786246225237846,
      "num_tokens": 7473430.0,
      "step": 58
    },
    {
      "entropy": 1.1365204900503159,
      "epoch": 0.7588424437299035,
      "grad_norm": 0.12866446375846863,
      "learning_rate": 4.488755162713975e-05,
      "loss": 1.126430869102478,
      "mean_token_accuracy": 0.6728999614715576,
      "num_tokens": 7602826.0,
      "step": 59
    },
    {
      "entropy": 1.1535387188196182,
      "epoch": 0.7717041800643086,
      "grad_norm": 0.1415134221315384,
      "learning_rate": 4.467119238428975e-05,
      "loss": 1.1418571472167969,
      "mean_token_accuracy": 0.6701028272509575,
      "num_tokens": 7732028.0,
      "step": 60
    },
    {
      "entropy": 1.1234214305877686,
      "epoch": 0.7845659163987139,
      "grad_norm": 0.14994795620441437,
      "learning_rate": 4.445089385796099e-05,
      "loss": 1.1106842756271362,
      "mean_token_accuracy": 0.6764309927821159,
      "num_tokens": 7860385.0,
      "step": 61
    },
    {
      "entropy": 1.0901593267917633,
      "epoch": 0.797427652733119,
      "grad_norm": 0.13637474179267883,
      "learning_rate": 4.422670016435792e-05,
      "loss": 1.0811570882797241,
      "mean_token_accuracy": 0.6831180602312088,
      "num_tokens": 7989531.0,
      "step": 62
    },
    {
      "entropy": 1.1060381978750229,
      "epoch": 0.8102893890675241,
      "grad_norm": 0.1306847780942917,
      "learning_rate": 4.3998656199717435e-05,
      "loss": 1.1069831848144531,
      "mean_token_accuracy": 0.6745292320847511,
      "num_tokens": 8118824.0,
      "step": 63
    },
    {
      "entropy": 1.1469190865755081,
      "epoch": 0.8231511254019293,
      "grad_norm": 0.14836829900741577,
      "learning_rate": 4.3766807631318106e-05,
      "loss": 1.1478967666625977,
      "mean_token_accuracy": 0.6674168556928635,
      "num_tokens": 8248122.0,
      "step": 64
    },
    {
      "entropy": 1.1051507145166397,
      "epoch": 0.8360128617363344,
      "grad_norm": 0.1413162350654602,
      "learning_rate": 4.353120088833501e-05,
      "loss": 1.0933685302734375,
      "mean_token_accuracy": 0.6783376038074493,
      "num_tokens": 8376429.0,
      "step": 65
    },
    {
      "entropy": 1.1381653249263763,
      "epoch": 0.8488745980707395,
      "grad_norm": 0.13279159367084503,
      "learning_rate": 4.329188315254196e-05,
      "loss": 1.1261053085327148,
      "mean_token_accuracy": 0.6716507449746132,
      "num_tokens": 8504687.0,
      "step": 66
    },
    {
      "entropy": 1.1401405185461044,
      "epoch": 0.8617363344051447,
      "grad_norm": 0.14999179542064667,
      "learning_rate": 4.3048902348863116e-05,
      "loss": 1.122992992401123,
      "mean_token_accuracy": 0.6721775308251381,
      "num_tokens": 8635119.0,
      "step": 67
    },
    {
      "entropy": 1.1104646772146225,
      "epoch": 0.8745980707395499,
      "grad_norm": 0.15244296193122864,
      "learning_rate": 4.280230713577564e-05,
      "loss": 1.0963469743728638,
      "mean_token_accuracy": 0.6784974113106728,
      "num_tokens": 8765133.0,
      "step": 68
    },
    {
      "entropy": 1.1325141787528992,
      "epoch": 0.887459807073955,
      "grad_norm": 0.13338243961334229,
      "learning_rate": 4.255214689556557e-05,
      "loss": 1.133899211883545,
      "mean_token_accuracy": 0.6714881733059883,
      "num_tokens": 8895437.0,
      "step": 69
    },
    {
      "entropy": 1.1021241694688797,
      "epoch": 0.9003215434083601,
      "grad_norm": 0.14672274887561798,
      "learning_rate": 4.229847172443866e-05,
      "loss": 1.1050517559051514,
      "mean_token_accuracy": 0.6782850474119186,
      "num_tokens": 9023472.0,
      "step": 70
    },
    {
      "entropy": 1.0665733218193054,
      "epoch": 0.9131832797427653,
      "grad_norm": 0.1326168030500412,
      "learning_rate": 4.204133242248832e-05,
      "loss": 1.0614970922470093,
      "mean_token_accuracy": 0.6890874728560448,
      "num_tokens": 9152924.0,
      "step": 71
    },
    {
      "entropy": 1.0804976969957352,
      "epoch": 0.9260450160771704,
      "grad_norm": 0.14258776605129242,
      "learning_rate": 4.1780780483522575e-05,
      "loss": 1.071770191192627,
      "mean_token_accuracy": 0.6831802353262901,
      "num_tokens": 9282930.0,
      "step": 72
    },
    {
      "entropy": 1.0698173642158508,
      "epoch": 0.9389067524115756,
      "grad_norm": 0.13697165250778198,
      "learning_rate": 4.151686808475204e-05,
      "loss": 1.057246208190918,
      "mean_token_accuracy": 0.6859329044818878,
      "num_tokens": 9410776.0,
      "step": 73
    },
    {
      "entropy": 1.0982066690921783,
      "epoch": 0.9517684887459807,
      "grad_norm": 0.14332003891468048,
      "learning_rate": 4.1249648076341165e-05,
      "loss": 1.08486008644104,
      "mean_token_accuracy": 0.6810793280601501,
      "num_tokens": 9539314.0,
      "step": 74
    },
    {
      "entropy": 1.1045535802841187,
      "epoch": 0.9646302250803859,
      "grad_norm": 0.14386016130447388,
      "learning_rate": 4.0979173970824626e-05,
      "loss": 1.1035948991775513,
      "mean_token_accuracy": 0.6733438894152641,
      "num_tokens": 9668102.0,
      "step": 75
    },
    {
      "entropy": 1.0924865305423737,
      "epoch": 0.977491961414791,
      "grad_norm": 0.13745297491550446,
      "learning_rate": 4.070549993239106e-05,
      "loss": 1.090521216392517,
      "mean_token_accuracy": 0.6789770871400833,
      "num_tokens": 9797707.0,
      "step": 76
    },
    {
      "entropy": 1.0984582901000977,
      "epoch": 0.9903536977491961,
      "grad_norm": 0.14490951597690582,
      "learning_rate": 4.0428680766036384e-05,
      "loss": 1.1076843738555908,
      "mean_token_accuracy": 0.6759174689650536,
      "num_tokens": 9927684.0,
      "step": 77
    },
    {
      "entropy": 1.0977885921796162,
      "epoch": 1.0,
      "grad_norm": 0.15585829317569733,
      "learning_rate": 4.0148771906588706e-05,
      "loss": 1.0940134525299072,
      "mean_token_accuracy": 0.6789492865403494,
      "num_tokens": 9998574.0,
      "step": 78
    }
  ],
  "logging_steps": 1,
  "max_steps": 234,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0574306065829069e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}