{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2012072434607646,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002012072434607646,
      "grad_norm": 46.70955276489258,
      "learning_rate": 6.5e-06,
      "loss": 1.4376,
      "step": 1
    },
    {
      "epoch": 0.004024144869215292,
      "grad_norm": 25.710079193115234,
      "learning_rate": 1.3e-05,
      "loss": 1.2619,
      "step": 2
    },
    {
      "epoch": 0.006036217303822937,
      "grad_norm": 26.04344940185547,
      "learning_rate": 1.9499999999999996e-05,
      "loss": 1.2208,
      "step": 3
    },
    {
      "epoch": 0.008048289738430584,
      "grad_norm": 8.251016616821289,
      "learning_rate": 2.6e-05,
      "loss": 1.0171,
      "step": 4
    },
    {
      "epoch": 0.01006036217303823,
      "grad_norm": 4.199310302734375,
      "learning_rate": 3.25e-05,
      "loss": 0.9699,
      "step": 5
    },
    {
      "epoch": 0.012072434607645875,
      "grad_norm": 6.134476661682129,
      "learning_rate": 3.899999999999999e-05,
      "loss": 0.9899,
      "step": 6
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 4.348274230957031,
      "learning_rate": 4.5499999999999995e-05,
      "loss": 0.9959,
      "step": 7
    },
    {
      "epoch": 0.01609657947686117,
      "grad_norm": 3.9475340843200684,
      "learning_rate": 5.2e-05,
      "loss": 0.8857,
      "step": 8
    },
    {
      "epoch": 0.018108651911468814,
      "grad_norm": 3.1918065547943115,
      "learning_rate": 5.85e-05,
      "loss": 0.9008,
      "step": 9
    },
    {
      "epoch": 0.02012072434607646,
      "grad_norm": 2.7590606212615967,
      "learning_rate": 6.5e-05,
      "loss": 0.8703,
      "step": 10
    },
    {
      "epoch": 0.022132796780684104,
      "grad_norm": 3.0539116859436035,
      "learning_rate": 6.499932377117017e-05,
      "loss": 0.8258,
      "step": 11
    },
    {
      "epoch": 0.02414486921529175,
      "grad_norm": 2.821988344192505,
      "learning_rate": 6.499729511282135e-05,
      "loss": 0.9071,
      "step": 12
    },
    {
      "epoch": 0.026156941649899398,
      "grad_norm": 2.776759147644043,
      "learning_rate": 6.499391410937425e-05,
      "loss": 0.8496,
      "step": 13
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 2.897883176803589,
      "learning_rate": 6.498918090152627e-05,
      "loss": 0.8339,
      "step": 14
    },
    {
      "epoch": 0.030181086519114688,
      "grad_norm": 2.511650562286377,
      "learning_rate": 6.498309568624549e-05,
      "loss": 0.8398,
      "step": 15
    },
    {
      "epoch": 0.03219315895372234,
      "grad_norm": 2.69217848777771,
      "learning_rate": 6.497565871676255e-05,
      "loss": 0.8373,
      "step": 16
    },
    {
      "epoch": 0.03420523138832998,
      "grad_norm": 2.5202300548553467,
      "learning_rate": 6.496687030256012e-05,
      "loss": 0.8418,
      "step": 17
    },
    {
      "epoch": 0.03621730382293763,
      "grad_norm": 2.4313321113586426,
      "learning_rate": 6.495673080935999e-05,
      "loss": 0.8482,
      "step": 18
    },
    {
      "epoch": 0.03822937625754527,
      "grad_norm": 2.278684139251709,
      "learning_rate": 6.494524065910784e-05,
      "loss": 0.8059,
      "step": 19
    },
    {
      "epoch": 0.04024144869215292,
      "grad_norm": 2.2294907569885254,
      "learning_rate": 6.493240032995573e-05,
      "loss": 0.8085,
      "step": 20
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 2.446382999420166,
      "learning_rate": 6.491821035624218e-05,
      "loss": 0.8298,
      "step": 21
    },
    {
      "epoch": 0.04426559356136821,
      "grad_norm": 2.4150474071502686,
      "learning_rate": 6.490267132846992e-05,
      "loss": 0.9265,
      "step": 22
    },
    {
      "epoch": 0.04627766599597585,
      "grad_norm": 2.170037269592285,
      "learning_rate": 6.488578389328129e-05,
      "loss": 0.8323,
      "step": 23
    },
    {
      "epoch": 0.0482897384305835,
      "grad_norm": 2.010956287384033,
      "learning_rate": 6.486754875343145e-05,
      "loss": 0.8646,
      "step": 24
    },
    {
      "epoch": 0.05030181086519115,
      "grad_norm": 1.8752851486206055,
      "learning_rate": 6.484796666775895e-05,
      "loss": 0.8402,
      "step": 25
    },
    {
      "epoch": 0.052313883299798795,
      "grad_norm": 1.8610150814056396,
      "learning_rate": 6.482703845115434e-05,
      "loss": 0.8256,
      "step": 26
    },
    {
      "epoch": 0.05432595573440644,
      "grad_norm": 1.8047019243240356,
      "learning_rate": 6.480476497452613e-05,
      "loss": 0.819,
      "step": 27
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 1.6434446573257446,
      "learning_rate": 6.47811471647646e-05,
      "loss": 0.8671,
      "step": 28
    },
    {
      "epoch": 0.05835010060362173,
      "grad_norm": 1.5787513256072998,
      "learning_rate": 6.475618600470322e-05,
      "loss": 0.7992,
      "step": 29
    },
    {
      "epoch": 0.060362173038229376,
      "grad_norm": 1.4350961446762085,
      "learning_rate": 6.472988253307773e-05,
      "loss": 0.7524,
      "step": 30
    },
    {
      "epoch": 0.06237424547283702,
      "grad_norm": 1.391878604888916,
      "learning_rate": 6.470223784448298e-05,
      "loss": 0.7541,
      "step": 31
    },
    {
      "epoch": 0.06438631790744467,
      "grad_norm": 1.4117164611816406,
      "learning_rate": 6.467325308932728e-05,
      "loss": 0.7899,
      "step": 32
    },
    {
      "epoch": 0.06639839034205232,
      "grad_norm": 1.3123915195465088,
      "learning_rate": 6.464292947378462e-05,
      "loss": 0.7402,
      "step": 33
    },
    {
      "epoch": 0.06841046277665996,
      "grad_norm": 1.4149091243743896,
      "learning_rate": 6.46112682597444e-05,
      "loss": 0.8195,
      "step": 34
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 1.2951886653900146,
      "learning_rate": 6.457827076475899e-05,
      "loss": 0.7179,
      "step": 35
    },
    {
      "epoch": 0.07243460764587525,
      "grad_norm": 1.3390341997146606,
      "learning_rate": 6.454393836198883e-05,
      "loss": 0.7973,
      "step": 36
    },
    {
      "epoch": 0.0744466800804829,
      "grad_norm": 1.307084560394287,
      "learning_rate": 6.450827248014535e-05,
      "loss": 0.7591,
      "step": 37
    },
    {
      "epoch": 0.07645875251509054,
      "grad_norm": 1.3605775833129883,
      "learning_rate": 6.447127460343148e-05,
      "loss": 0.8085,
      "step": 38
    },
    {
      "epoch": 0.07847082494969819,
      "grad_norm": 1.4956183433532715,
      "learning_rate": 6.443294627147988e-05,
      "loss": 0.735,
      "step": 39
    },
    {
      "epoch": 0.08048289738430583,
      "grad_norm": 1.371940016746521,
      "learning_rate": 6.439328907928889e-05,
      "loss": 0.8025,
      "step": 40
    },
    {
      "epoch": 0.08249496981891348,
      "grad_norm": 1.4716073274612427,
      "learning_rate": 6.435230467715615e-05,
      "loss": 0.7381,
      "step": 41
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 1.3676444292068481,
      "learning_rate": 6.430999477060994e-05,
      "loss": 0.7601,
      "step": 42
    },
    {
      "epoch": 0.08651911468812877,
      "grad_norm": 1.5072672367095947,
      "learning_rate": 6.426636112033818e-05,
      "loss": 0.8209,
      "step": 43
    },
    {
      "epoch": 0.08853118712273642,
      "grad_norm": 1.3186477422714233,
      "learning_rate": 6.422140554211511e-05,
      "loss": 0.777,
      "step": 44
    },
    {
      "epoch": 0.09054325955734406,
      "grad_norm": 1.4689198732376099,
      "learning_rate": 6.417512990672591e-05,
      "loss": 0.871,
      "step": 45
    },
    {
      "epoch": 0.0925553319919517,
      "grad_norm": 1.287394642829895,
      "learning_rate": 6.412753613988862e-05,
      "loss": 0.7281,
      "step": 46
    },
    {
      "epoch": 0.09456740442655935,
      "grad_norm": 1.1629823446273804,
      "learning_rate": 6.407862622217414e-05,
      "loss": 0.715,
      "step": 47
    },
    {
      "epoch": 0.096579476861167,
      "grad_norm": 1.2146556377410889,
      "learning_rate": 6.402840218892381e-05,
      "loss": 0.6985,
      "step": 48
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 1.3280084133148193,
      "learning_rate": 6.397686613016466e-05,
      "loss": 0.8195,
      "step": 49
    },
    {
      "epoch": 0.1006036217303823,
      "grad_norm": 1.157867193222046,
      "learning_rate": 6.392402019052244e-05,
      "loss": 0.7529,
      "step": 50
    },
    {
      "epoch": 0.10261569416498995,
      "grad_norm": 1.1449801921844482,
      "learning_rate": 6.386986656913242e-05,
      "loss": 0.7834,
      "step": 51
    },
    {
      "epoch": 0.10462776659959759,
      "grad_norm": 1.2190605401992798,
      "learning_rate": 6.381440751954782e-05,
      "loss": 0.8203,
      "step": 52
    },
    {
      "epoch": 0.10663983903420524,
      "grad_norm": 1.2562769651412964,
      "learning_rate": 6.375764534964608e-05,
      "loss": 0.7338,
      "step": 53
    },
    {
      "epoch": 0.10865191146881288,
      "grad_norm": 1.1834882497787476,
      "learning_rate": 6.369958242153278e-05,
      "loss": 0.7489,
      "step": 54
    },
    {
      "epoch": 0.11066398390342053,
      "grad_norm": 1.2381786108016968,
      "learning_rate": 6.364022115144337e-05,
      "loss": 0.7537,
      "step": 55
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 1.256866693496704,
      "learning_rate": 6.357956400964259e-05,
      "loss": 0.7725,
      "step": 56
    },
    {
      "epoch": 0.11468812877263582,
      "grad_norm": 1.2332978248596191,
      "learning_rate": 6.351761352032171e-05,
      "loss": 0.774,
      "step": 57
    },
    {
      "epoch": 0.11670020120724346,
      "grad_norm": 1.3557363748550415,
      "learning_rate": 6.345437226149345e-05,
      "loss": 0.7877,
      "step": 58
    },
    {
      "epoch": 0.11871227364185111,
      "grad_norm": 1.1381844282150269,
      "learning_rate": 6.338984286488472e-05,
      "loss": 0.7152,
      "step": 59
    },
    {
      "epoch": 0.12072434607645875,
      "grad_norm": 1.147226095199585,
      "learning_rate": 6.332402801582716e-05,
      "loss": 0.7713,
      "step": 60
    },
    {
      "epoch": 0.1227364185110664,
      "grad_norm": 1.0942986011505127,
      "learning_rate": 6.325693045314524e-05,
      "loss": 0.7446,
      "step": 61
    },
    {
      "epoch": 0.12474849094567404,
      "grad_norm": 1.233619213104248,
      "learning_rate": 6.318855296904246e-05,
      "loss": 0.8107,
      "step": 62
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 1.1866984367370605,
      "learning_rate": 6.311889840898498e-05,
      "loss": 0.8206,
      "step": 63
    },
    {
      "epoch": 0.12877263581488935,
      "grad_norm": 1.176274061203003,
      "learning_rate": 6.304796967158343e-05,
      "loss": 0.7813,
      "step": 64
    },
    {
      "epoch": 0.13078470824949698,
      "grad_norm": 1.1214070320129395,
      "learning_rate": 6.297576970847205e-05,
      "loss": 0.6908,
      "step": 65
    },
    {
      "epoch": 0.13279678068410464,
      "grad_norm": 1.0725229978561401,
      "learning_rate": 6.290230152418603e-05,
      "loss": 0.756,
      "step": 66
    },
    {
      "epoch": 0.13480885311871227,
      "grad_norm": 1.1194369792938232,
      "learning_rate": 6.28275681760364e-05,
      "loss": 0.7766,
      "step": 67
    },
    {
      "epoch": 0.13682092555331993,
      "grad_norm": 1.090072512626648,
      "learning_rate": 6.275157277398282e-05,
      "loss": 0.7856,
      "step": 68
    },
    {
      "epoch": 0.13883299798792756,
      "grad_norm": 1.1602994203567505,
      "learning_rate": 6.267431848050418e-05,
      "loss": 0.7597,
      "step": 69
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 1.0984241962432861,
      "learning_rate": 6.259580851046697e-05,
      "loss": 0.7318,
      "step": 70
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.0639097690582275,
      "learning_rate": 6.251604613099149e-05,
      "loss": 0.7265,
      "step": 71
    },
    {
      "epoch": 0.1448692152917505,
      "grad_norm": 1.0951672792434692,
      "learning_rate": 6.243503466131597e-05,
      "loss": 0.7312,
      "step": 72
    },
    {
      "epoch": 0.14688128772635814,
      "grad_norm": 1.092551827430725,
      "learning_rate": 6.235277747265828e-05,
      "loss": 0.7556,
      "step": 73
    },
    {
      "epoch": 0.1488933601609658,
      "grad_norm": 1.1054296493530273,
      "learning_rate": 6.226927798807585e-05,
      "loss": 0.8489,
      "step": 74
    },
    {
      "epoch": 0.15090543259557343,
      "grad_norm": 1.0174497365951538,
      "learning_rate": 6.218453968232303e-05,
      "loss": 0.7104,
      "step": 75
    },
    {
      "epoch": 0.1529175050301811,
      "grad_norm": 1.146209716796875,
      "learning_rate": 6.209856608170663e-05,
      "loss": 0.7276,
      "step": 76
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 1.0379316806793213,
      "learning_rate": 6.201136076393911e-05,
      "loss": 0.7243,
      "step": 77
    },
    {
      "epoch": 0.15694164989939638,
      "grad_norm": 1.0034286975860596,
      "learning_rate": 6.192292735798967e-05,
      "loss": 0.7085,
      "step": 78
    },
    {
      "epoch": 0.158953722334004,
      "grad_norm": 1.0072968006134033,
      "learning_rate": 6.183326954393332e-05,
      "loss": 0.6865,
      "step": 79
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 1.0766922235488892,
      "learning_rate": 6.174239105279768e-05,
      "loss": 0.7628,
      "step": 80
    },
    {
      "epoch": 0.16297786720321933,
      "grad_norm": 1.014816403388977,
      "learning_rate": 6.16502956664077e-05,
      "loss": 0.7356,
      "step": 81
    },
    {
      "epoch": 0.16498993963782696,
      "grad_norm": 1.055881142616272,
      "learning_rate": 6.155698721722834e-05,
      "loss": 0.7763,
      "step": 82
    },
    {
      "epoch": 0.16700201207243462,
      "grad_norm": 1.0576510429382324,
      "learning_rate": 6.146246958820503e-05,
      "loss": 0.6852,
      "step": 83
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 1.2542794942855835,
      "learning_rate": 6.136674671260213e-05,
      "loss": 0.7956,
      "step": 84
    },
    {
      "epoch": 0.1710261569416499,
      "grad_norm": 1.0826421976089478,
      "learning_rate": 6.12698225738392e-05,
      "loss": 0.7285,
      "step": 85
    },
    {
      "epoch": 0.17303822937625754,
      "grad_norm": 1.0286874771118164,
      "learning_rate": 6.11717012053253e-05,
      "loss": 0.7363,
      "step": 86
    },
    {
      "epoch": 0.1750503018108652,
      "grad_norm": 1.1285161972045898,
      "learning_rate": 6.107238669029108e-05,
      "loss": 0.7807,
      "step": 87
    },
    {
      "epoch": 0.17706237424547283,
      "grad_norm": 2.394617795944214,
      "learning_rate": 6.0971883161618906e-05,
      "loss": 0.663,
      "step": 88
    },
    {
      "epoch": 0.1790744466800805,
      "grad_norm": 1.0971828699111938,
      "learning_rate": 6.0870194801670825e-05,
      "loss": 0.7331,
      "step": 89
    },
    {
      "epoch": 0.18108651911468812,
      "grad_norm": 1.0546624660491943,
      "learning_rate": 6.076732584211459e-05,
      "loss": 0.7244,
      "step": 90
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 1.0969500541687012,
      "learning_rate": 6.06632805637475e-05,
      "loss": 0.8122,
      "step": 91
    },
    {
      "epoch": 0.1851106639839034,
      "grad_norm": 1.0038318634033203,
      "learning_rate": 6.055806329631827e-05,
      "loss": 0.752,
      "step": 92
    },
    {
      "epoch": 0.18712273641851107,
      "grad_norm": 1.017544150352478,
      "learning_rate": 6.045167841834689e-05,
      "loss": 0.7629,
      "step": 93
    },
    {
      "epoch": 0.1891348088531187,
      "grad_norm": 1.0679768323898315,
      "learning_rate": 6.034413035694237e-05,
      "loss": 0.7533,
      "step": 94
    },
    {
      "epoch": 0.19114688128772636,
      "grad_norm": 1.1002590656280518,
      "learning_rate": 6.023542358761855e-05,
      "loss": 0.7566,
      "step": 95
    },
    {
      "epoch": 0.193158953722334,
      "grad_norm": 1.0083142518997192,
      "learning_rate": 6.01255626341078e-05,
      "loss": 0.6873,
      "step": 96
    },
    {
      "epoch": 0.19517102615694165,
      "grad_norm": 1.897566318511963,
      "learning_rate": 6.0014552068172866e-05,
      "loss": 0.8056,
      "step": 97
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 0.995782732963562,
      "learning_rate": 5.990239650941649e-05,
      "loss": 0.7062,
      "step": 98
    },
    {
      "epoch": 0.19919517102615694,
      "grad_norm": 0.9380747079849243,
      "learning_rate": 5.97891006250893e-05,
      "loss": 0.6674,
      "step": 99
    },
    {
      "epoch": 0.2012072434607646,
      "grad_norm": 1.0377370119094849,
      "learning_rate": 5.967466912989547e-05,
      "loss": 0.7425,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 497,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.60168918788096e+17,
  "train_batch_size": 15,
  "trial_name": null,
  "trial_params": null
}