{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05731069560856795,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028655347804283973,
      "grad_norm": 7.381157047348097e-05,
      "learning_rate": 6.666666666666667e-06,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00028655347804283973,
      "eval_loss": 11.5,
      "eval_runtime": 1.0821,
      "eval_samples_per_second": 130.301,
      "eval_steps_per_second": 65.612,
      "step": 1
    },
    {
      "epoch": 0.0005731069560856795,
      "grad_norm": 6.596604362130165e-05,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0008596604341285192,
      "grad_norm": 0.00010368386574555188,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.001146213912171359,
      "grad_norm": 0.0001162872213171795,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0014327673902141988,
      "grad_norm": 7.124816329451278e-05,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0017193208682570384,
      "grad_norm": 6.46381449769251e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.002005874346299878,
      "grad_norm": 6.736363138770685e-05,
      "learning_rate": 4.666666666666667e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002292427824342718,
      "grad_norm": 8.684724161867052e-05,
      "learning_rate": 5.333333333333333e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0025789813023855577,
      "grad_norm": 0.00011209803051315248,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0028655347804283976,
      "grad_norm": 7.704443851253018e-05,
      "learning_rate": 6.666666666666667e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0031520882584712374,
      "grad_norm": 0.00012871134094893932,
      "learning_rate": 7.333333333333333e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.003438641736514077,
      "grad_norm": 9.129566024057567e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0037251952145569167,
      "grad_norm": 0.00016532166046090424,
      "learning_rate": 8.666666666666667e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.004011748692599756,
      "grad_norm": 4.0770170016912743e-05,
      "learning_rate": 9.333333333333334e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.004298302170642596,
      "grad_norm": 6.018530257279053e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.004584855648685436,
      "grad_norm": 0.00010712119546951726,
      "learning_rate": 0.00010666666666666667,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.004871409126728276,
      "grad_norm": 9.569038957124576e-05,
      "learning_rate": 0.00011333333333333334,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0051579626047711154,
      "grad_norm": 4.893005097983405e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.005444516082813955,
      "grad_norm": 6.882779416628182e-05,
      "learning_rate": 0.00012666666666666666,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.005731069560856795,
      "grad_norm": 0.00010898563778027892,
      "learning_rate": 0.00013333333333333334,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.006017623038899635,
      "grad_norm": 5.298621908877976e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.006304176516942475,
      "grad_norm": 8.256702130893245e-05,
      "learning_rate": 0.00014666666666666666,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.006590729994985314,
      "grad_norm": 7.129500590963289e-05,
      "learning_rate": 0.00015333333333333334,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.006877283473028154,
      "grad_norm": 6.098434096202254e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0071638369510709935,
      "grad_norm": 5.094590233056806e-05,
      "learning_rate": 0.0001666666666666667,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.007450390429113833,
      "grad_norm": 0.00010607678268570453,
      "learning_rate": 0.00017333333333333334,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.007736943907156673,
      "grad_norm": 0.00013629230670630932,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.008023497385199512,
      "grad_norm": 5.341317955753766e-05,
      "learning_rate": 0.0001866666666666667,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.008310050863242352,
      "grad_norm": 7.902220386313275e-05,
      "learning_rate": 0.00019333333333333333,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.008596604341285192,
      "grad_norm": 0.00012108004011679441,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.008883157819328032,
      "grad_norm": 0.0001192674899357371,
      "learning_rate": 0.00019999999546978955,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.009169711297370872,
      "grad_norm": 6.242323433980346e-05,
      "learning_rate": 0.00019999998187915854,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.009456264775413711,
      "grad_norm": 0.00010374305566074327,
      "learning_rate": 0.00019999995922810823,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.009742818253456551,
      "grad_norm": 7.662192365387455e-05,
      "learning_rate": 0.0001999999275166407,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.010029371731499391,
      "grad_norm": 5.456238068290986e-05,
      "learning_rate": 0.00019999988674475878,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.010315925209542231,
      "grad_norm": 5.168572533875704e-05,
      "learning_rate": 0.0001999998369124662,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.01060247868758507,
      "grad_norm": 8.381979569094256e-05,
      "learning_rate": 0.00019999977801976742,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.01088903216562791,
      "grad_norm": 0.00010368989751441404,
      "learning_rate": 0.0001999997100666678,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.01117558564367075,
      "grad_norm": 9.2031252279412e-05,
      "learning_rate": 0.00019999963305317354,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.01146213912171359,
      "grad_norm": 5.379249341785908e-05,
      "learning_rate": 0.0001999995469792916,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.01174869259975643,
      "grad_norm": 9.862228762358427e-05,
      "learning_rate": 0.00019999945184502973,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.01203524607779927,
      "grad_norm": 9.657383634475991e-05,
      "learning_rate": 0.0001999993476503966,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.01232179955584211,
      "grad_norm": 8.879863162292168e-05,
      "learning_rate": 0.00019999923439540163,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.01260835303388495,
      "grad_norm": 6.925352499820292e-05,
      "learning_rate": 0.00019999911208005508,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.012894906511927788,
      "grad_norm": 8.172217349056154e-05,
      "learning_rate": 0.00019999898070436806,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.013181459989970628,
      "grad_norm": 8.213800174416974e-05,
      "learning_rate": 0.00019999884026835246,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 6.044626570655964e-05,
      "learning_rate": 0.00019999869077202097,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.013754566946056307,
      "grad_norm": 6.844953168183565e-05,
      "learning_rate": 0.00019999853221538714,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.014041120424099147,
      "grad_norm": 0.00013352354289963841,
      "learning_rate": 0.00019999836459846538,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.014327673902141987,
      "grad_norm": 7.450298289768398e-05,
      "learning_rate": 0.00019999818792127086,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.014614227380184827,
      "grad_norm": 7.48366946936585e-05,
      "learning_rate": 0.00019999800218381956,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.014900780858227667,
      "grad_norm": 5.8166733651887625e-05,
      "learning_rate": 0.00019999780738612835,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.015187334336270506,
      "grad_norm": 8.82293243193999e-05,
      "learning_rate": 0.00019999760352821486,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.015473887814313346,
      "grad_norm": 8.331720164278522e-05,
      "learning_rate": 0.00019999739061009753,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.015760441292356184,
      "grad_norm": 0.00011742674541892484,
      "learning_rate": 0.00019999716863179572,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.016046994770399024,
      "grad_norm": 7.888959953561425e-05,
      "learning_rate": 0.0001999969375933295,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.016333548248441864,
      "grad_norm": 9.424455492990091e-05,
      "learning_rate": 0.00019999669749471978,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.016620101726484704,
      "grad_norm": 4.706982508650981e-05,
      "learning_rate": 0.00019999644833598837,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.016906655204527544,
      "grad_norm": 9.459713328396901e-05,
      "learning_rate": 0.00019999619011715778,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.017193208682570384,
      "grad_norm": 7.433071732521057e-05,
      "learning_rate": 0.0001999959228382515,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.017479762160613223,
      "grad_norm": 0.00013755627151113003,
      "learning_rate": 0.00019999564649929362,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.017766315638656063,
      "grad_norm": 7.515963079640642e-05,
      "learning_rate": 0.00019999536110030925,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.018052869116698903,
      "grad_norm": 9.297157521359622e-05,
      "learning_rate": 0.00019999506664132425,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.018339422594741743,
      "grad_norm": 6.67767963022925e-05,
      "learning_rate": 0.00019999476312236532,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.018625976072784583,
      "grad_norm": 0.00010362596367485821,
      "learning_rate": 0.00019999445054345993,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.018912529550827423,
      "grad_norm": 0.00010248312901239842,
      "learning_rate": 0.0001999941289046364,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.019199083028870263,
      "grad_norm": 0.00011670257663354278,
      "learning_rate": 0.00019999379820592386,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.019485636506913102,
      "grad_norm": 9.483767644269392e-05,
      "learning_rate": 0.00019999345844735227,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.019772189984955942,
      "grad_norm": 0.00012299351510591805,
      "learning_rate": 0.00019999310962895246,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.020058743462998782,
      "grad_norm": 0.00013893700088374317,
      "learning_rate": 0.000199992751750756,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.020345296941041622,
      "grad_norm": 0.00015965943748597056,
      "learning_rate": 0.0001999923848127953,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.020631850419084462,
      "grad_norm": 0.00010530438157729805,
      "learning_rate": 0.00019999200881510367,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.0209184038971273,
      "grad_norm": 0.00018572794215288013,
      "learning_rate": 0.0001999916237577151,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.02120495737517014,
      "grad_norm": 7.796911086188629e-05,
      "learning_rate": 0.00019999122964066453,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.02149151085321298,
      "grad_norm": 0.00011319840996293351,
      "learning_rate": 0.00019999082646398765,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.02177806433125582,
      "grad_norm": 8.448911103187129e-05,
      "learning_rate": 0.00019999041422772096,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.02206461780929866,
      "grad_norm": 0.00010140217636944726,
      "learning_rate": 0.00019998999293190185,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.0223511712873415,
      "grad_norm": 0.00012014622916467488,
      "learning_rate": 0.0001999895625765685,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.02263772476538434,
      "grad_norm": 0.00016250344924628735,
      "learning_rate": 0.0001999891231617599,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.02292427824342718,
      "grad_norm": 0.0001607730082469061,
      "learning_rate": 0.0001999886746875158,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.02321083172147002,
      "grad_norm": 9.321732068201527e-05,
      "learning_rate": 0.0001999882171538769,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.02349738519951286,
      "grad_norm": 8.782186341704801e-05,
      "learning_rate": 0.00019998775056088465,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.0237839386775557,
      "grad_norm": 0.0001984712143894285,
      "learning_rate": 0.0001999872749085813,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.02407049215559854,
      "grad_norm": 9.399009286426008e-05,
      "learning_rate": 0.00019998679019700994,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.02435704563364138,
      "grad_norm": 0.00010639801621437073,
      "learning_rate": 0.00019998629642621453,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.02464359911168422,
      "grad_norm": 0.0001523221581010148,
      "learning_rate": 0.00019998579359623974,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.02493015258972706,
      "grad_norm": 0.0002136339171556756,
      "learning_rate": 0.00019998528170713122,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.0252167060677699,
      "grad_norm": 0.0002231518883490935,
      "learning_rate": 0.00019998476075893526,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.025503259545812736,
      "grad_norm": 0.0003373888903297484,
      "learning_rate": 0.0001999842307516991,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.025789813023855575,
      "grad_norm": 0.0001387349038850516,
      "learning_rate": 0.0001999836916854708,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.026076366501898415,
      "grad_norm": 0.0001619431423023343,
      "learning_rate": 0.00019998314356029913,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.026362919979941255,
      "grad_norm": 0.00016960031643975526,
      "learning_rate": 0.00019998258637623378,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.026649473457984095,
      "grad_norm": 0.00013296969700604677,
      "learning_rate": 0.00019998202013332526,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 0.00015429664927069098,
      "learning_rate": 0.0001999814448316248,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.027222580414069775,
      "grad_norm": 0.00019981182413175702,
      "learning_rate": 0.00019998086047118464,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.027509133892112615,
      "grad_norm": 0.00020218861754983664,
      "learning_rate": 0.0001999802670520576,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.027795687370155454,
      "grad_norm": 0.0001801289909053594,
      "learning_rate": 0.00019997966457429756,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.028082240848198294,
      "grad_norm": 0.0003259029472246766,
      "learning_rate": 0.000199979053037959,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.00010903332440648228,
      "learning_rate": 0.0001999784324430974,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.028655347804283974,
      "grad_norm": 0.00010584478877717629,
      "learning_rate": 0.00019997780278976901,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.028941901282326814,
      "grad_norm": 0.00024283739912789315,
      "learning_rate": 0.0001999771640780308,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.029228454760369654,
      "grad_norm": 0.00020966072042938322,
      "learning_rate": 0.0001999765163079407,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.029515008238412493,
      "grad_norm": 0.00016458171012345701,
      "learning_rate": 0.00019997585947955737,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.029801561716455333,
      "grad_norm": 0.0002142781886504963,
      "learning_rate": 0.0001999751935929403,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.030088115194498173,
      "grad_norm": 0.00018552150868345052,
      "learning_rate": 0.0001999745186481499,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.030374668672541013,
      "grad_norm": 0.00021552396356128156,
      "learning_rate": 0.00019997383464524728,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.030661222150583853,
      "grad_norm": 0.00038846713141538203,
      "learning_rate": 0.00019997314158429438,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.030947775628626693,
      "grad_norm": 0.00019503093790262938,
      "learning_rate": 0.00019997243946535406,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.031234329106669532,
      "grad_norm": 0.0003047584614250809,
      "learning_rate": 0.00019997172828848986,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.03152088258471237,
      "grad_norm": 0.00025872603873722255,
      "learning_rate": 0.00019997100805376627,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.03180743606275521,
      "grad_norm": 0.0003769325849134475,
      "learning_rate": 0.00019997027876124854,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.03209398954079805,
      "grad_norm": 0.0004575467901304364,
      "learning_rate": 0.00019996954041100274,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.03238054301884089,
      "grad_norm": 0.0003370651975274086,
      "learning_rate": 0.00019996879300309575,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.03266709649688373,
      "grad_norm": 0.0002681570767890662,
      "learning_rate": 0.00019996803653759532,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.03295364997492657,
      "grad_norm": 0.0002245080249849707,
      "learning_rate": 0.00019996727101456995,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.03324020345296941,
      "grad_norm": 0.0002516446984373033,
      "learning_rate": 0.00019996649643408906,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.03352675693101225,
      "grad_norm": 0.000306058645946905,
      "learning_rate": 0.00019996571279622276,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.03381331040905509,
      "grad_norm": 0.0003231150913052261,
      "learning_rate": 0.0001999649201010421,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.03409986388709793,
      "grad_norm": 0.00030212162528187037,
      "learning_rate": 0.00019996411834861887,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.03438641736514077,
      "grad_norm": 0.0002937183016911149,
      "learning_rate": 0.00019996330753902574,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.03467297084318361,
      "grad_norm": 0.0003606914251577109,
      "learning_rate": 0.00019996248767233617,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.03495952432122645,
      "grad_norm": 0.0003355994704179466,
      "learning_rate": 0.00019996165874862443,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.03524607779926929,
      "grad_norm": 0.00034902329207398,
      "learning_rate": 0.0001999608207679656,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.03553263127731213,
      "grad_norm": 0.0002104766172124073,
      "learning_rate": 0.00019995997373043568,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.03581918475535497,
      "grad_norm": 0.00023777480237185955,
      "learning_rate": 0.00019995911763611132,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.036105738233397806,
      "grad_norm": 0.00029851359431631863,
      "learning_rate": 0.00019995825248507015,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.03639229171144065,
      "grad_norm": 0.0004646476882044226,
      "learning_rate": 0.00019995737827739057,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.036678845189483486,
      "grad_norm": 0.00029485157574526966,
      "learning_rate": 0.0001999564950131517,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.03696539866752633,
      "grad_norm": 0.0007383066695183516,
      "learning_rate": 0.00019995560269243367,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.037251952145569166,
      "grad_norm": 0.0003343581047374755,
      "learning_rate": 0.00019995470131531725,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.03753850562361201,
      "grad_norm": 0.0004639736143872142,
      "learning_rate": 0.00019995379088188418,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.037825059101654845,
      "grad_norm": 0.0007386133074760437,
      "learning_rate": 0.0001999528713922169,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.03811161257969769,
      "grad_norm": 0.0003995689039584249,
      "learning_rate": 0.0001999519428463987,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.038398166057740525,
      "grad_norm": 0.00027600504108704627,
      "learning_rate": 0.00019995100524451372,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.03868471953578337,
      "grad_norm": 0.00037365983007475734,
      "learning_rate": 0.00019995005858664696,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.038971273013826205,
      "grad_norm": 0.0006544017815031111,
      "learning_rate": 0.00019994910287288417,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.03925782649186905,
      "grad_norm": 0.0004640940751414746,
      "learning_rate": 0.0001999481381033119,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.039544379969911884,
      "grad_norm": 0.00038468436105176806,
      "learning_rate": 0.00019994716427801766,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.03983093344795473,
      "grad_norm": 0.0009553630952723324,
      "learning_rate": 0.0001999461813970896,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.040117486925997564,
      "grad_norm": 0.0002630364033393562,
      "learning_rate": 0.00019994518946061675,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.0002757444162853062,
      "learning_rate": 0.00019994418846868906,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.040690593882083244,
      "grad_norm": 0.00042787828715518117,
      "learning_rate": 0.00019994317842139716,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.04097714736012608,
      "grad_norm": 0.000318807055009529,
      "learning_rate": 0.0001999421593188326,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.041263700838168924,
      "grad_norm": 0.0007039292831905186,
      "learning_rate": 0.00019994113116108772,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.04155025431621176,
      "grad_norm": 0.0005391126614995301,
      "learning_rate": 0.00019994009394825568,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.0418368077942546,
      "grad_norm": 0.0006373688811436296,
      "learning_rate": 0.0001999390476804304,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.04212336127229744,
      "grad_norm": 0.00032521801767870784,
      "learning_rate": 0.00019993799235770674,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.04240991475034028,
      "grad_norm": 0.0004875020822510123,
      "learning_rate": 0.00019993692798018028,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.04269646822838312,
      "grad_norm": 0.0006042442400939763,
      "learning_rate": 0.00019993585454794748,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.04298302170642596,
      "grad_norm": 0.00043931492837145925,
      "learning_rate": 0.00019993477206110559,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.0432695751844688,
      "grad_norm": 0.00035808575921691954,
      "learning_rate": 0.00019993368051975268,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.04355612866251164,
      "grad_norm": 0.0004806216456927359,
      "learning_rate": 0.00019993257992398765,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.04384268214055448,
      "grad_norm": 0.00039719213964417577,
      "learning_rate": 0.0001999314702739102,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.04412923561859732,
      "grad_norm": 0.0004144109843764454,
      "learning_rate": 0.00019993035156962093,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.04441578909664016,
      "grad_norm": 0.0006228784914128482,
      "learning_rate": 0.00019992922381122113,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.044702342574683,
      "grad_norm": 0.0006269604782573879,
      "learning_rate": 0.00019992808699881303,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.04498889605272584,
      "grad_norm": 0.00046757658128626645,
      "learning_rate": 0.0001999269411324996,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.04527544953076868,
      "grad_norm": 0.00044586771400645375,
      "learning_rate": 0.00019992578621238466,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.04556200300881152,
      "grad_norm": 0.0005216663703322411,
      "learning_rate": 0.0001999246222385729,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.04584855648685436,
      "grad_norm": 0.00044177312520332634,
      "learning_rate": 0.00019992344921116972,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.0461351099648972,
      "grad_norm": 0.0010134356562048197,
      "learning_rate": 0.00019992226713028138,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.04642166344294004,
      "grad_norm": 0.0005053270142525434,
      "learning_rate": 0.00019992107599601508,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.04670821692098288,
      "grad_norm": 0.0008667529909871519,
      "learning_rate": 0.00019991987580847867,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.04699477039902572,
      "grad_norm": 0.0005064812139607966,
      "learning_rate": 0.00019991866656778092,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 0.00033950377837754786,
      "learning_rate": 0.00019991744827403137,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.0475678773551114,
      "grad_norm": 0.0006410735077224672,
      "learning_rate": 0.0001999162209273404,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.047854430833154236,
      "grad_norm": 0.0011909378226846457,
      "learning_rate": 0.0001999149845278192,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.04814098431119708,
      "grad_norm": 0.0009707885328680277,
      "learning_rate": 0.00019991373907557987,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.048427537789239916,
      "grad_norm": 0.0009485428454354405,
      "learning_rate": 0.0001999124845707352,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.04871409126728276,
      "grad_norm": 0.0008028754382394254,
      "learning_rate": 0.00019991122101339884,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.049000644745325596,
      "grad_norm": 0.0008805354009382427,
      "learning_rate": 0.00019990994840368527,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.04928719822336844,
      "grad_norm": 0.0005341559299267828,
      "learning_rate": 0.00019990866674170983,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.049573751701411276,
      "grad_norm": 0.0007721466827206314,
      "learning_rate": 0.00019990737602758863,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.04986030517945412,
      "grad_norm": 0.0012437815312296152,
      "learning_rate": 0.0001999060762614386,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.050146858657496955,
      "grad_norm": 0.0005417719949036837,
      "learning_rate": 0.00019990476744337753,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.0504334121355398,
      "grad_norm": 0.000531162484548986,
      "learning_rate": 0.00019990344957352397,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.050719965613582635,
      "grad_norm": 0.0010336303384974599,
      "learning_rate": 0.00019990212265199738,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.05100651909162547,
      "grad_norm": 0.0006930266390554607,
      "learning_rate": 0.00019990078667891792,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.051293072569668315,
      "grad_norm": 0.0005671161925420165,
      "learning_rate": 0.00019989944165440667,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.05157962604771115,
      "grad_norm": 0.0005927831516601145,
      "learning_rate": 0.00019989808757858547,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.051866179525753994,
      "grad_norm": 0.0014029775047674775,
      "learning_rate": 0.00019989672445157707,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.05215273300379683,
      "grad_norm": 0.0005633488181047142,
      "learning_rate": 0.0001998953522735049,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.052439286481839674,
      "grad_norm": 0.0008726881351321936,
      "learning_rate": 0.00019989397104449327,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.05272583995988251,
      "grad_norm": 0.0010581790702417493,
      "learning_rate": 0.00019989258076466744,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.053012393437925354,
      "grad_norm": 0.001107684918679297,
      "learning_rate": 0.00019989118143415327,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.05329894691596819,
      "grad_norm": 0.0003141145862173289,
      "learning_rate": 0.00019988977305307758,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.05358550039401103,
      "grad_norm": 0.0005039018578827381,
      "learning_rate": 0.00019988835562156798,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 0.0005364140379242599,
      "learning_rate": 0.00019988692913975288,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.05415860735009671,
      "grad_norm": 0.0011345255188643932,
      "learning_rate": 0.00019988549360776153,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.05444516082813955,
      "grad_norm": 0.0007594748749397695,
      "learning_rate": 0.00019988404902572402,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.05473171430618239,
      "grad_norm": 0.0011707482626661658,
      "learning_rate": 0.0001998825953937712,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.05501826778422523,
      "grad_norm": 0.0010088670533150434,
      "learning_rate": 0.0001998811327120348,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.05530482126226807,
      "grad_norm": 0.0010642173001542687,
      "learning_rate": 0.00019987966098064733,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.05559137474031091,
      "grad_norm": 0.0011455731000751257,
      "learning_rate": 0.00019987818019974216,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.05587792821835375,
      "grad_norm": 0.0006063128239475191,
      "learning_rate": 0.00019987669036945343,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.05616448169639659,
      "grad_norm": 0.00092441460583359,
      "learning_rate": 0.00019987519148991612,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.05645103517443943,
      "grad_norm": 0.0008765366510488093,
      "learning_rate": 0.00019987368356126604,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.0011625416809692979,
      "learning_rate": 0.00019987216658363984,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.05702414213052511,
      "grad_norm": 0.0007807817892171443,
      "learning_rate": 0.0001998706405571749,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.05731069560856795,
      "grad_norm": 0.001416051178239286,
      "learning_rate": 0.00019986910548200955,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.05731069560856795,
      "eval_loss": 11.5,
      "eval_runtime": 1.0416,
      "eval_samples_per_second": 135.365,
      "eval_steps_per_second": 68.162,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 10467,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1999837593600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}