{
  "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": 1.327302247285843,
      "epoch": 0.012903225806451613,
      "grad_norm": 1.0468459129333496,
      "learning_rate": 0.0,
      "loss": 1.9516217708587646,
      "mean_token_accuracy": 0.5490271672606468,
      "num_tokens": 129656.0,
      "step": 1
    },
    {
      "entropy": 1.3267911523580551,
      "epoch": 0.025806451612903226,
      "grad_norm": 1.0235601663589478,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.9609016180038452,
      "mean_token_accuracy": 0.545955665409565,
      "num_tokens": 257608.0,
      "step": 2
    },
    {
      "entropy": 1.4163906574249268,
      "epoch": 0.03870967741935484,
      "grad_norm": 0.8620004057884216,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.9539512395858765,
      "mean_token_accuracy": 0.5437170788645744,
      "num_tokens": 385654.0,
      "step": 3
    },
    {
      "entropy": 1.5072677731513977,
      "epoch": 0.05161290322580645,
      "grad_norm": 0.6674020290374756,
      "learning_rate": 1.25e-05,
      "loss": 1.929893136024475,
      "mean_token_accuracy": 0.5428568199276924,
      "num_tokens": 513578.0,
      "step": 4
    },
    {
      "entropy": 1.5772784054279327,
      "epoch": 0.06451612903225806,
      "grad_norm": 0.44926103949546814,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.8096842765808105,
      "mean_token_accuracy": 0.5594104528427124,
      "num_tokens": 643891.0,
      "step": 5
    },
    {
      "entropy": 1.691362425684929,
      "epoch": 0.07741935483870968,
      "grad_norm": 0.3624405860900879,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.792994499206543,
      "mean_token_accuracy": 0.5583670735359192,
      "num_tokens": 773552.0,
      "step": 6
    },
    {
      "entropy": 1.7625758796930313,
      "epoch": 0.09032258064516129,
      "grad_norm": 0.32741692662239075,
      "learning_rate": 2.5e-05,
      "loss": 1.7421350479125977,
      "mean_token_accuracy": 0.565700501203537,
      "num_tokens": 902676.0,
      "step": 7
    },
    {
      "entropy": 1.816343978047371,
      "epoch": 0.1032258064516129,
      "grad_norm": 0.31979212164878845,
      "learning_rate": 2.916666666666667e-05,
      "loss": 1.7134227752685547,
      "mean_token_accuracy": 0.5680374577641487,
      "num_tokens": 1031062.0,
      "step": 8
    },
    {
      "entropy": 1.884494736790657,
      "epoch": 0.11612903225806452,
      "grad_norm": 0.3261905312538147,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.697797417640686,
      "mean_token_accuracy": 0.5728070959448814,
      "num_tokens": 1159144.0,
      "step": 9
    },
    {
      "entropy": 1.9154246598482132,
      "epoch": 0.12903225806451613,
      "grad_norm": 0.33981192111968994,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.691472053527832,
      "mean_token_accuracy": 0.5723336413502693,
      "num_tokens": 1286047.0,
      "step": 10
    },
    {
      "entropy": 1.8476576060056686,
      "epoch": 0.14193548387096774,
      "grad_norm": 0.3439367115497589,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.6031842231750488,
      "mean_token_accuracy": 0.5876904204487801,
      "num_tokens": 1414956.0,
      "step": 11
    },
    {
      "entropy": 1.7925567030906677,
      "epoch": 0.15483870967741936,
      "grad_norm": 0.3315640985965729,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.5772321224212646,
      "mean_token_accuracy": 0.5901090204715729,
      "num_tokens": 1544083.0,
      "step": 12
    },
    {
      "entropy": 1.6733195632696152,
      "epoch": 0.16774193548387098,
      "grad_norm": 0.2760685086250305,
      "learning_rate": 5e-05,
      "loss": 1.5256061553955078,
      "mean_token_accuracy": 0.5991538763046265,
      "num_tokens": 1673817.0,
      "step": 13
    },
    {
      "entropy": 1.4815043658018112,
      "epoch": 0.18064516129032257,
      "grad_norm": 0.23523160815238953,
      "learning_rate": 4.9997496794168726e-05,
      "loss": 1.4415483474731445,
      "mean_token_accuracy": 0.6162490248680115,
      "num_tokens": 1801770.0,
      "step": 14
    },
    {
      "entropy": 1.4159721434116364,
      "epoch": 0.1935483870967742,
      "grad_norm": 0.28664934635162354,
      "learning_rate": 4.998998767795805e-05,
      "loss": 1.4667837619781494,
      "mean_token_accuracy": 0.6101680621504784,
      "num_tokens": 1931723.0,
      "step": 15
    },
    {
      "entropy": 1.3478048890829086,
      "epoch": 0.2064516129032258,
      "grad_norm": 0.28385764360427856,
      "learning_rate": 4.9977474155117045e-05,
      "loss": 1.4278314113616943,
      "mean_token_accuracy": 0.6164416000247002,
      "num_tokens": 2061345.0,
      "step": 16
    },
    {
      "entropy": 1.3173148781061172,
      "epoch": 0.21935483870967742,
      "grad_norm": 0.24572592973709106,
      "learning_rate": 4.995995873155958e-05,
      "loss": 1.3927912712097168,
      "mean_token_accuracy": 0.6206158325076103,
      "num_tokens": 2190508.0,
      "step": 17
    },
    {
      "entropy": 1.3462176322937012,
      "epoch": 0.23225806451612904,
      "grad_norm": 0.2069179117679596,
      "learning_rate": 4.99374449148625e-05,
      "loss": 1.3792784214019775,
      "mean_token_accuracy": 0.6236012801527977,
      "num_tokens": 2318941.0,
      "step": 18
    },
    {
      "entropy": 1.39307202398777,
      "epoch": 0.24516129032258063,
      "grad_norm": 0.19426818192005157,
      "learning_rate": 4.9909937213563165e-05,
      "loss": 1.37335205078125,
      "mean_token_accuracy": 0.62324009090662,
      "num_tokens": 2448059.0,
      "step": 19
    },
    {
      "entropy": 1.420734629034996,
      "epoch": 0.25806451612903225,
      "grad_norm": 0.19838440418243408,
      "learning_rate": 4.987744113625665e-05,
      "loss": 1.370849370956421,
      "mean_token_accuracy": 0.6241574659943581,
      "num_tokens": 2577375.0,
      "step": 20
    },
    {
      "entropy": 1.371973842382431,
      "epoch": 0.2709677419354839,
      "grad_norm": 0.18288694322109222,
      "learning_rate": 4.9839963190492576e-05,
      "loss": 1.3033034801483154,
      "mean_token_accuracy": 0.6400853618979454,
      "num_tokens": 2707055.0,
      "step": 21
    },
    {
      "entropy": 1.3838643580675125,
      "epoch": 0.2838709677419355,
      "grad_norm": 0.18097883462905884,
      "learning_rate": 4.979751088147192e-05,
      "loss": 1.318864107131958,
      "mean_token_accuracy": 0.6351697221398354,
      "num_tokens": 2836471.0,
      "step": 22
    },
    {
      "entropy": 1.354823961853981,
      "epoch": 0.2967741935483871,
      "grad_norm": 0.16573207080364227,
      "learning_rate": 4.975009271054409e-05,
      "loss": 1.2960338592529297,
      "mean_token_accuracy": 0.6396285593509674,
      "num_tokens": 2967186.0,
      "step": 23
    },
    {
      "entropy": 1.356062889099121,
      "epoch": 0.3096774193548387,
      "grad_norm": 0.15834170579910278,
      "learning_rate": 4.969771817350445e-05,
      "loss": 1.311288595199585,
      "mean_token_accuracy": 0.638341523706913,
      "num_tokens": 3091283.0,
      "step": 24
    },
    {
      "entropy": 1.3014232963323593,
      "epoch": 0.3225806451612903,
      "grad_norm": 0.15633215010166168,
      "learning_rate": 4.9640397758692715e-05,
      "loss": 1.2794947624206543,
      "mean_token_accuracy": 0.6442421302199364,
      "num_tokens": 3221704.0,
      "step": 25
    },
    {
      "entropy": 1.2741473019123077,
      "epoch": 0.33548387096774196,
      "grad_norm": 0.16600695252418518,
      "learning_rate": 4.957814294489261e-05,
      "loss": 1.2685260772705078,
      "mean_token_accuracy": 0.6439810171723366,
      "num_tokens": 3351359.0,
      "step": 26
    },
    {
      "entropy": 1.2793954610824585,
      "epoch": 0.34838709677419355,
      "grad_norm": 0.1699378341436386,
      "learning_rate": 4.9510966199033174e-05,
      "loss": 1.299481749534607,
      "mean_token_accuracy": 0.6377060264348984,
      "num_tokens": 3480058.0,
      "step": 27
    },
    {
      "entropy": 1.2380398958921432,
      "epoch": 0.36129032258064514,
      "grad_norm": 0.1586979180574417,
      "learning_rate": 4.943888097369216e-05,
      "loss": 1.2551636695861816,
      "mean_token_accuracy": 0.6473096534609795,
      "num_tokens": 3610897.0,
      "step": 28
    },
    {
      "entropy": 1.25519198179245,
      "epoch": 0.3741935483870968,
      "grad_norm": 0.1537477672100067,
      "learning_rate": 4.936190170440208e-05,
      "loss": 1.2700082063674927,
      "mean_token_accuracy": 0.6448632478713989,
      "num_tokens": 3740627.0,
      "step": 29
    },
    {
      "entropy": 1.200623482465744,
      "epoch": 0.3870967741935484,
      "grad_norm": 0.1391288787126541,
      "learning_rate": 4.928004380675941e-05,
      "loss": 1.2029218673706055,
      "mean_token_accuracy": 0.6599779576063156,
      "num_tokens": 3869695.0,
      "step": 30
    },
    {
      "entropy": 1.222929760813713,
      "epoch": 0.4,
      "grad_norm": 0.14511308073997498,
      "learning_rate": 4.9193323673337476e-05,
      "loss": 1.2141369581222534,
      "mean_token_accuracy": 0.6561597287654877,
      "num_tokens": 3998221.0,
      "step": 31
    },
    {
      "entropy": 1.2850614041090012,
      "epoch": 0.4129032258064516,
      "grad_norm": 0.14675162732601166,
      "learning_rate": 4.910175867040377e-05,
      "loss": 1.260993242263794,
      "mean_token_accuracy": 0.6444773599505424,
      "num_tokens": 4127108.0,
      "step": 32
    },
    {
      "entropy": 1.2510194778442383,
      "epoch": 0.4258064516129032,
      "grad_norm": 0.14100538194179535,
      "learning_rate": 4.9005367134442235e-05,
      "loss": 1.2186331748962402,
      "mean_token_accuracy": 0.65362448990345,
      "num_tokens": 4256994.0,
      "step": 33
    },
    {
      "entropy": 1.223235473036766,
      "epoch": 0.43870967741935485,
      "grad_norm": 0.13875682651996613,
      "learning_rate": 4.890416836848127e-05,
      "loss": 1.203627586364746,
      "mean_token_accuracy": 0.6568410098552704,
      "num_tokens": 4385244.0,
      "step": 34
    },
    {
      "entropy": 1.1924351304769516,
      "epoch": 0.45161290322580644,
      "grad_norm": 0.13426443934440613,
      "learning_rate": 4.8798182638228166e-05,
      "loss": 1.1726880073547363,
      "mean_token_accuracy": 0.6638099774718285,
      "num_tokens": 4515175.0,
      "step": 35
    },
    {
      "entropy": 1.2145061641931534,
      "epoch": 0.4645161290322581,
      "grad_norm": 0.1369384229183197,
      "learning_rate": 4.868743116801074e-05,
      "loss": 1.2057712078094482,
      "mean_token_accuracy": 0.6585973352193832,
      "num_tokens": 4644464.0,
      "step": 36
    },
    {
      "entropy": 1.1699982434511185,
      "epoch": 0.4774193548387097,
      "grad_norm": 0.13203217089176178,
      "learning_rate": 4.857193613652711e-05,
      "loss": 1.1678709983825684,
      "mean_token_accuracy": 0.6651179119944572,
      "num_tokens": 4774388.0,
      "step": 37
    },
    {
      "entropy": 1.1900109350681305,
      "epoch": 0.49032258064516127,
      "grad_norm": 0.1409081071615219,
      "learning_rate": 4.845172067240415e-05,
      "loss": 1.196943998336792,
      "mean_token_accuracy": 0.6569633036851883,
      "num_tokens": 4903171.0,
      "step": 38
    },
    {
      "entropy": 1.1959572583436966,
      "epoch": 0.5032258064516129,
      "grad_norm": 0.13402387499809265,
      "learning_rate": 4.8326808849565936e-05,
      "loss": 1.204121470451355,
      "mean_token_accuracy": 0.6561899334192276,
      "num_tokens": 5033677.0,
      "step": 39
    },
    {
      "entropy": 1.1748242527246475,
      "epoch": 0.5161290322580645,
      "grad_norm": 0.13230547308921814,
      "learning_rate": 4.819722568241274e-05,
      "loss": 1.1755125522613525,
      "mean_token_accuracy": 0.6607141047716141,
      "num_tokens": 5163487.0,
      "step": 40
    },
    {
      "entropy": 1.1830326318740845,
      "epoch": 0.5290322580645161,
      "grad_norm": 0.13548049330711365,
      "learning_rate": 4.806299712081172e-05,
      "loss": 1.183053970336914,
      "mean_token_accuracy": 0.661345437169075,
      "num_tokens": 5292899.0,
      "step": 41
    },
    {
      "entropy": 1.180369421839714,
      "epoch": 0.5419354838709678,
      "grad_norm": 0.13295236229896545,
      "learning_rate": 4.792415004490034e-05,
      "loss": 1.1716046333312988,
      "mean_token_accuracy": 0.6627360582351685,
      "num_tokens": 5422025.0,
      "step": 42
    },
    {
      "entropy": 1.1974405944347382,
      "epoch": 0.5548387096774193,
      "grad_norm": 0.12952998280525208,
      "learning_rate": 4.77807122597034e-05,
      "loss": 1.1795024871826172,
      "mean_token_accuracy": 0.6590340510010719,
      "num_tokens": 5551149.0,
      "step": 43
    },
    {
      "entropy": 1.1339516341686249,
      "epoch": 0.567741935483871,
      "grad_norm": 0.13098949193954468,
      "learning_rate": 4.7632712489564926e-05,
      "loss": 1.1292296648025513,
      "mean_token_accuracy": 0.6728876158595085,
      "num_tokens": 5680701.0,
      "step": 44
    },
    {
      "entropy": 1.1452270299196243,
      "epoch": 0.5806451612903226,
      "grad_norm": 0.13148927688598633,
      "learning_rate": 4.748018037239592e-05,
      "loss": 1.1412042379379272,
      "mean_token_accuracy": 0.6679868176579475,
      "num_tokens": 5808493.0,
      "step": 45
    },
    {
      "entropy": 1.1565511226654053,
      "epoch": 0.5935483870967742,
      "grad_norm": 0.12716591358184814,
      "learning_rate": 4.732314645373921e-05,
      "loss": 1.147752046585083,
      "mean_token_accuracy": 0.6678735390305519,
      "num_tokens": 5938296.0,
      "step": 46
    },
    {
      "entropy": 1.1531172394752502,
      "epoch": 0.6064516129032258,
      "grad_norm": 0.13128802180290222,
      "learning_rate": 4.7161642180652464e-05,
      "loss": 1.137876033782959,
      "mean_token_accuracy": 0.6694907322525978,
      "num_tokens": 6067439.0,
      "step": 47
    },
    {
      "entropy": 1.1726240366697311,
      "epoch": 0.6193548387096774,
      "grad_norm": 0.1309962421655655,
      "learning_rate": 4.699569989541074e-05,
      "loss": 1.166740894317627,
      "mean_token_accuracy": 0.6635602861642838,
      "num_tokens": 6197510.0,
      "step": 48
    },
    {
      "entropy": 1.150630384683609,
      "epoch": 0.632258064516129,
      "grad_norm": 0.12693582475185394,
      "learning_rate": 4.6825352829029705e-05,
      "loss": 1.1487030982971191,
      "mean_token_accuracy": 0.667711079120636,
      "num_tokens": 6327768.0,
      "step": 49
    },
    {
      "entropy": 1.1061551421880722,
      "epoch": 0.6451612903225806,
      "grad_norm": 0.12342569977045059,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.107095718383789,
      "mean_token_accuracy": 0.6762828528881073,
      "num_tokens": 6455846.0,
      "step": 50
    },
    {
      "entropy": 1.1445851027965546,
      "epoch": 0.6580645161290323,
      "grad_norm": 0.1373581886291504,
      "learning_rate": 4.647158168051066e-05,
      "loss": 1.1354420185089111,
      "mean_token_accuracy": 0.6716547980904579,
      "num_tokens": 6585457.0,
      "step": 51
    },
    {
      "entropy": 1.1473966836929321,
      "epoch": 0.6709677419354839,
      "grad_norm": 0.1250847578048706,
      "learning_rate": 4.628822844333278e-05,
      "loss": 1.1474499702453613,
      "mean_token_accuracy": 0.6668257936835289,
      "num_tokens": 6716096.0,
      "step": 52
    },
    {
      "entropy": 1.1469789743423462,
      "epoch": 0.6838709677419355,
      "grad_norm": 0.1268235445022583,
      "learning_rate": 4.6100612100748765e-05,
      "loss": 1.14267897605896,
      "mean_token_accuracy": 0.6698051393032074,
      "num_tokens": 6844341.0,
      "step": 53
    },
    {
      "entropy": 1.1110682487487793,
      "epoch": 0.6967741935483871,
      "grad_norm": 0.12988688051700592,
      "learning_rate": 4.59087702241444e-05,
      "loss": 1.1135189533233643,
      "mean_token_accuracy": 0.6766636297106743,
      "num_tokens": 6971794.0,
      "step": 54
    },
    {
      "entropy": 1.1421085596084595,
      "epoch": 0.7096774193548387,
      "grad_norm": 0.1267767995595932,
      "learning_rate": 4.571274123109606e-05,
      "loss": 1.1490681171417236,
      "mean_token_accuracy": 0.6662089303135872,
      "num_tokens": 7100353.0,
      "step": 55
    },
    {
      "entropy": 1.1042888760566711,
      "epoch": 0.7225806451612903,
      "grad_norm": 0.12492457777261734,
      "learning_rate": 4.551256437767719e-05,
      "loss": 1.110184669494629,
      "mean_token_accuracy": 0.6747554019093513,
      "num_tokens": 7230177.0,
      "step": 56
    },
    {
      "entropy": 1.065716564655304,
      "epoch": 0.7354838709677419,
      "grad_norm": 0.12365498393774033,
      "learning_rate": 4.530827975059715e-05,
      "loss": 1.0647603273391724,
      "mean_token_accuracy": 0.6866239011287689,
      "num_tokens": 7359042.0,
      "step": 57
    },
    {
      "entropy": 1.0687381699681282,
      "epoch": 0.7483870967741936,
      "grad_norm": 0.12762895226478577,
      "learning_rate": 4.5099928259173516e-05,
      "loss": 1.0665113925933838,
      "mean_token_accuracy": 0.6885024607181549,
      "num_tokens": 7488137.0,
      "step": 58
    },
    {
      "entropy": 1.1023950427770615,
      "epoch": 0.7612903225806451,
      "grad_norm": 0.12779441475868225,
      "learning_rate": 4.488755162713975e-05,
      "loss": 1.0950183868408203,
      "mean_token_accuracy": 0.6785372719168663,
      "num_tokens": 7618282.0,
      "step": 59
    },
    {
      "entropy": 1.089103415608406,
      "epoch": 0.7741935483870968,
      "grad_norm": 0.12895165383815765,
      "learning_rate": 4.467119238428975e-05,
      "loss": 1.0878229141235352,
      "mean_token_accuracy": 0.6820144504308701,
      "num_tokens": 7748017.0,
      "step": 60
    },
    {
      "entropy": 1.0883491188287735,
      "epoch": 0.7870967741935484,
      "grad_norm": 0.13146434724330902,
      "learning_rate": 4.445089385796099e-05,
      "loss": 1.0844019651412964,
      "mean_token_accuracy": 0.6833582445979118,
      "num_tokens": 7876986.0,
      "step": 61
    },
    {
      "entropy": 1.1199355721473694,
      "epoch": 0.8,
      "grad_norm": 0.13159561157226562,
      "learning_rate": 4.422670016435792e-05,
      "loss": 1.1150472164154053,
      "mean_token_accuracy": 0.6756617501378059,
      "num_tokens": 8006794.0,
      "step": 62
    },
    {
      "entropy": 1.1050203889608383,
      "epoch": 0.8129032258064516,
      "grad_norm": 0.1264924556016922,
      "learning_rate": 4.3998656199717435e-05,
      "loss": 1.1043422222137451,
      "mean_token_accuracy": 0.6767379865050316,
      "num_tokens": 8135408.0,
      "step": 63
    },
    {
      "entropy": 1.1202740967273712,
      "epoch": 0.8258064516129032,
      "grad_norm": 0.12594330310821533,
      "learning_rate": 4.3766807631318106e-05,
      "loss": 1.1134419441223145,
      "mean_token_accuracy": 0.676059253513813,
      "num_tokens": 8265182.0,
      "step": 64
    },
    {
      "entropy": 1.1008555963635445,
      "epoch": 0.8387096774193549,
      "grad_norm": 0.14352354407310486,
      "learning_rate": 4.353120088833501e-05,
      "loss": 1.089049220085144,
      "mean_token_accuracy": 0.679233193397522,
      "num_tokens": 8395710.0,
      "step": 65
    },
    {
      "entropy": 1.09499129652977,
      "epoch": 0.8516129032258064,
      "grad_norm": 0.12506140768527985,
      "learning_rate": 4.329188315254196e-05,
      "loss": 1.0959919691085815,
      "mean_token_accuracy": 0.6772814318537712,
      "num_tokens": 8525026.0,
      "step": 66
    },
    {
      "entropy": 1.0806580409407616,
      "epoch": 0.864516129032258,
      "grad_norm": 0.12470545619726181,
      "learning_rate": 4.3048902348863116e-05,
      "loss": 1.077396273612976,
      "mean_token_accuracy": 0.6855179369449615,
      "num_tokens": 8655176.0,
      "step": 67
    },
    {
      "entropy": 1.0938902795314789,
      "epoch": 0.8774193548387097,
      "grad_norm": 0.1254391372203827,
      "learning_rate": 4.280230713577564e-05,
      "loss": 1.096771240234375,
      "mean_token_accuracy": 0.6798589378595352,
      "num_tokens": 8784950.0,
      "step": 68
    },
    {
      "entropy": 1.0837120488286018,
      "epoch": 0.8903225806451613,
      "grad_norm": 0.12564809620380402,
      "learning_rate": 4.255214689556557e-05,
      "loss": 1.0887655019760132,
      "mean_token_accuracy": 0.6802218705415726,
      "num_tokens": 8915424.0,
      "step": 69
    },
    {
      "entropy": 1.1309964209794998,
      "epoch": 0.9032258064516129,
      "grad_norm": 0.13434115052223206,
      "learning_rate": 4.229847172443866e-05,
      "loss": 1.1279692649841309,
      "mean_token_accuracy": 0.6699688509106636,
      "num_tokens": 9043958.0,
      "step": 70
    },
    {
      "entropy": 1.0794824212789536,
      "epoch": 0.9161290322580645,
      "grad_norm": 0.13104921579360962,
      "learning_rate": 4.204133242248832e-05,
      "loss": 1.0755493640899658,
      "mean_token_accuracy": 0.6832893788814545,
      "num_tokens": 9173238.0,
      "step": 71
    },
    {
      "entropy": 1.0700343400239944,
      "epoch": 0.9290322580645162,
      "grad_norm": 0.12627503275871277,
      "learning_rate": 4.1780780483522575e-05,
      "loss": 1.0692481994628906,
      "mean_token_accuracy": 0.6846828386187553,
      "num_tokens": 9303178.0,
      "step": 72
    },
    {
      "entropy": 1.0971452593803406,
      "epoch": 0.9419354838709677,
      "grad_norm": 0.1322394162416458,
      "learning_rate": 4.151686808475204e-05,
      "loss": 1.0987398624420166,
      "mean_token_accuracy": 0.6774289608001709,
      "num_tokens": 9432086.0,
      "step": 73
    },
    {
      "entropy": 1.1076685041189194,
      "epoch": 0.9548387096774194,
      "grad_norm": 0.13057094812393188,
      "learning_rate": 4.1249648076341165e-05,
      "loss": 1.1064797639846802,
      "mean_token_accuracy": 0.6764660328626633,
      "num_tokens": 9560333.0,
      "step": 74
    },
    {
      "entropy": 1.0812313556671143,
      "epoch": 0.967741935483871,
      "grad_norm": 0.12581738829612732,
      "learning_rate": 4.0979173970824626e-05,
      "loss": 1.077629566192627,
      "mean_token_accuracy": 0.6832556426525116,
      "num_tokens": 9689775.0,
      "step": 75
    },
    {
      "entropy": 1.067845843732357,
      "epoch": 0.9806451612903225,
      "grad_norm": 0.12489581108093262,
      "learning_rate": 4.070549993239106e-05,
      "loss": 1.0688203573226929,
      "mean_token_accuracy": 0.6856153085827827,
      "num_tokens": 9818901.0,
      "step": 76
    },
    {
      "entropy": 1.070682093501091,
      "epoch": 0.9935483870967742,
      "grad_norm": 0.13314804434776306,
      "learning_rate": 4.0428680766036384e-05,
      "loss": 1.0635384321212769,
      "mean_token_accuracy": 0.6840452700853348,
      "num_tokens": 9948460.0,
      "step": 77
    },
    {
      "entropy": 1.0606148540973663,
      "epoch": 1.0,
      "grad_norm": 0.16886763274669647,
      "learning_rate": 4.0148771906588706e-05,
      "loss": 1.0518985986709595,
      "mean_token_accuracy": 0.6878193020820618,
      "num_tokens": 9997067.0,
      "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": 1.085983676405121e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}