{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9581589958158996,
  "eval_steps": 59,
  "global_step": 118,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 0.3126992881298065,
      "learning_rate": 2e-05,
      "loss": 2.4388,
      "step": 1
    },
    {
      "epoch": 0.016736401673640166,
      "eval_loss": 2.2736361026763916,
      "eval_runtime": 44.9772,
      "eval_samples_per_second": 37.419,
      "eval_steps_per_second": 0.8,
      "step": 1
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 0.31262004375457764,
      "learning_rate": 4e-05,
      "loss": 2.3915,
      "step": 2
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 0.3161173462867737,
      "learning_rate": 6e-05,
      "loss": 2.4118,
      "step": 3
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 0.32605665922164917,
      "learning_rate": 8e-05,
      "loss": 2.3872,
      "step": 4
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 0.32243478298187256,
      "learning_rate": 0.0001,
      "loss": 2.3368,
      "step": 5
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 0.3141494393348694,
      "learning_rate": 0.00012,
      "loss": 2.2966,
      "step": 6
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 0.330599308013916,
      "learning_rate": 0.00014,
      "loss": 2.2379,
      "step": 7
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 0.33452969789505005,
      "learning_rate": 0.00016,
      "loss": 2.1949,
      "step": 8
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 0.2835342288017273,
      "learning_rate": 0.00018,
      "loss": 2.156,
      "step": 9
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 0.23091256618499756,
      "learning_rate": 0.0002,
      "loss": 2.1109,
      "step": 10
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 0.2284015268087387,
      "learning_rate": 0.00019999033847063811,
      "loss": 2.0782,
      "step": 11
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 0.23981927335262299,
      "learning_rate": 0.00019996135574945544,
      "loss": 2.053,
      "step": 12
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 0.23807936906814575,
      "learning_rate": 0.00019991305743680013,
      "loss": 2.0294,
      "step": 13
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 0.20766477286815643,
      "learning_rate": 0.0001998454528653836,
      "loss": 1.9947,
      "step": 14
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 0.1892593652009964,
      "learning_rate": 0.00019975855509847686,
      "loss": 1.9643,
      "step": 15
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 0.19022946059703827,
      "learning_rate": 0.00019965238092738643,
      "loss": 1.9275,
      "step": 16
    },
    {
      "epoch": 0.28451882845188287,
      "grad_norm": 0.18370254337787628,
      "learning_rate": 0.00019952695086820975,
      "loss": 1.9512,
      "step": 17
    },
    {
      "epoch": 0.301255230125523,
      "grad_norm": 0.16774943470954895,
      "learning_rate": 0.0001993822891578708,
      "loss": 1.8883,
      "step": 18
    },
    {
      "epoch": 0.3179916317991632,
      "grad_norm": 0.17572854459285736,
      "learning_rate": 0.0001992184237494368,
      "loss": 1.938,
      "step": 19
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 0.21952244639396667,
      "learning_rate": 0.0001990353863067169,
      "loss": 1.8937,
      "step": 20
    },
    {
      "epoch": 0.3514644351464435,
      "grad_norm": 0.2579434812068939,
      "learning_rate": 0.0001988332121981436,
      "loss": 1.8797,
      "step": 21
    },
    {
      "epoch": 0.3682008368200837,
      "grad_norm": 0.29942768812179565,
      "learning_rate": 0.00019861194048993863,
      "loss": 1.8766,
      "step": 22
    },
    {
      "epoch": 0.38493723849372385,
      "grad_norm": 0.326593279838562,
      "learning_rate": 0.0001983716139385641,
      "loss": 1.8567,
      "step": 23
    },
    {
      "epoch": 0.401673640167364,
      "grad_norm": 0.2769831418991089,
      "learning_rate": 0.0001981122789824607,
      "loss": 1.839,
      "step": 24
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 0.2902805507183075,
      "learning_rate": 0.00019783398573307428,
      "loss": 1.8622,
      "step": 25
    },
    {
      "epoch": 0.4351464435146444,
      "grad_norm": 0.2152428776025772,
      "learning_rate": 0.00019753678796517282,
      "loss": 1.8393,
      "step": 26
    },
    {
      "epoch": 0.45188284518828453,
      "grad_norm": 0.1541067361831665,
      "learning_rate": 0.00019722074310645553,
      "loss": 1.8326,
      "step": 27
    },
    {
      "epoch": 0.4686192468619247,
      "grad_norm": 0.12413746118545532,
      "learning_rate": 0.00019688591222645607,
      "loss": 1.8079,
      "step": 28
    },
    {
      "epoch": 0.48535564853556484,
      "grad_norm": 0.11909659206867218,
      "learning_rate": 0.000196532360024742,
      "loss": 1.8044,
      "step": 29
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 0.16260313987731934,
      "learning_rate": 0.0001961601548184129,
      "loss": 1.7888,
      "step": 30
    },
    {
      "epoch": 0.5188284518828452,
      "grad_norm": 0.17894335091114044,
      "learning_rate": 0.00019576936852889936,
      "loss": 1.8263,
      "step": 31
    },
    {
      "epoch": 0.5355648535564853,
      "grad_norm": 0.21706554293632507,
      "learning_rate": 0.00019536007666806556,
      "loss": 1.8151,
      "step": 32
    },
    {
      "epoch": 0.5523012552301255,
      "grad_norm": 0.17296762764453888,
      "learning_rate": 0.0001949323583236181,
      "loss": 1.7901,
      "step": 33
    },
    {
      "epoch": 0.5690376569037657,
      "grad_norm": 0.1761002093553543,
      "learning_rate": 0.0001944862961438239,
      "loss": 1.8126,
      "step": 34
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 0.14914190769195557,
      "learning_rate": 0.00019402197632153992,
      "loss": 1.7797,
      "step": 35
    },
    {
      "epoch": 0.602510460251046,
      "grad_norm": 0.13111546635627747,
      "learning_rate": 0.00019353948857755803,
      "loss": 1.7916,
      "step": 36
    },
    {
      "epoch": 0.6192468619246861,
      "grad_norm": 0.12080994248390198,
      "learning_rate": 0.00019303892614326836,
      "loss": 1.7834,
      "step": 37
    },
    {
      "epoch": 0.6359832635983264,
      "grad_norm": 0.15622606873512268,
      "learning_rate": 0.00019252038574264405,
      "loss": 1.794,
      "step": 38
    },
    {
      "epoch": 0.6527196652719666,
      "grad_norm": 0.1345275640487671,
      "learning_rate": 0.00019198396757355118,
      "loss": 1.7554,
      "step": 39
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 0.18387249112129211,
      "learning_rate": 0.00019142977528838762,
      "loss": 1.7675,
      "step": 40
    },
    {
      "epoch": 0.6861924686192469,
      "grad_norm": 0.165897399187088,
      "learning_rate": 0.00019085791597405404,
      "loss": 1.7631,
      "step": 41
    },
    {
      "epoch": 0.702928870292887,
      "grad_norm": 0.13675889372825623,
      "learning_rate": 0.00019026850013126157,
      "loss": 1.754,
      "step": 42
    },
    {
      "epoch": 0.7196652719665272,
      "grad_norm": 0.16969387233257294,
      "learning_rate": 0.00018966164165317966,
      "loss": 1.745,
      "step": 43
    },
    {
      "epoch": 0.7364016736401674,
      "grad_norm": 0.16098380088806152,
      "learning_rate": 0.00018903745780342839,
      "loss": 1.7609,
      "step": 44
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 0.12338632345199585,
      "learning_rate": 0.0001883960691934196,
      "loss": 1.7584,
      "step": 45
    },
    {
      "epoch": 0.7698744769874477,
      "grad_norm": 0.1335158348083496,
      "learning_rate": 0.00018773759975905098,
      "loss": 1.7302,
      "step": 46
    },
    {
      "epoch": 0.7866108786610879,
      "grad_norm": 0.11967575550079346,
      "learning_rate": 0.00018706217673675811,
      "loss": 1.7323,
      "step": 47
    },
    {
      "epoch": 0.803347280334728,
      "grad_norm": 0.12446475774049759,
      "learning_rate": 0.0001863699306389282,
      "loss": 1.7217,
      "step": 48
    },
    {
      "epoch": 0.8200836820083682,
      "grad_norm": 0.13070392608642578,
      "learning_rate": 0.00018566099522868119,
      "loss": 1.7192,
      "step": 49
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 0.15041972696781158,
      "learning_rate": 0.00018493550749402278,
      "loss": 1.7386,
      "step": 50
    },
    {
      "epoch": 0.8535564853556485,
      "grad_norm": 0.12314204126596451,
      "learning_rate": 0.00018419360762137395,
      "loss": 1.7465,
      "step": 51
    },
    {
      "epoch": 0.8702928870292888,
      "grad_norm": 0.15009309351444244,
      "learning_rate": 0.00018343543896848273,
      "loss": 1.7216,
      "step": 52
    },
    {
      "epoch": 0.8870292887029289,
      "grad_norm": 0.12467087060213089,
      "learning_rate": 0.00018266114803672318,
      "loss": 1.7043,
      "step": 53
    },
    {
      "epoch": 0.9037656903765691,
      "grad_norm": 0.1297266036272049,
      "learning_rate": 0.00018187088444278674,
      "loss": 1.7069,
      "step": 54
    },
    {
      "epoch": 0.9205020920502092,
      "grad_norm": 0.1195509061217308,
      "learning_rate": 0.00018106480088977172,
      "loss": 1.7305,
      "step": 55
    },
    {
      "epoch": 0.9372384937238494,
      "grad_norm": 0.14450602233409882,
      "learning_rate": 0.00018024305313767646,
      "loss": 1.7171,
      "step": 56
    },
    {
      "epoch": 0.9539748953974896,
      "grad_norm": 0.16594989597797394,
      "learning_rate": 0.00017940579997330165,
      "loss": 1.7239,
      "step": 57
    },
    {
      "epoch": 0.9707112970711297,
      "grad_norm": 0.19210928678512573,
      "learning_rate": 0.00017855320317956784,
      "loss": 1.7081,
      "step": 58
    },
    {
      "epoch": 0.9874476987447699,
      "grad_norm": 0.16463987529277802,
      "learning_rate": 0.00017768542750425426,
      "loss": 1.7178,
      "step": 59
    },
    {
      "epoch": 0.9874476987447699,
      "eval_loss": 1.7365927696228027,
      "eval_runtime": 44.9816,
      "eval_samples_per_second": 37.415,
      "eval_steps_per_second": 0.8,
      "step": 59
    },
    {
      "epoch": 1.00418410041841,
      "grad_norm": 0.13954801857471466,
      "learning_rate": 0.0001768026406281642,
      "loss": 1.6905,
      "step": 60
    },
    {
      "epoch": 1.00418410041841,
      "grad_norm": 0.17747963964939117,
      "learning_rate": 0.00017590501313272415,
      "loss": 1.6864,
      "step": 61
    },
    {
      "epoch": 1.0209205020920502,
      "grad_norm": 0.1328994333744049,
      "learning_rate": 0.00017499271846702213,
      "loss": 1.6388,
      "step": 62
    },
    {
      "epoch": 1.0376569037656904,
      "grad_norm": 0.12811322510242462,
      "learning_rate": 0.00017406593291429217,
      "loss": 1.6821,
      "step": 63
    },
    {
      "epoch": 1.0543933054393306,
      "grad_norm": 0.1379721611738205,
      "learning_rate": 0.00017312483555785086,
      "loss": 1.6364,
      "step": 64
    },
    {
      "epoch": 1.0711297071129706,
      "grad_norm": 0.14301170408725739,
      "learning_rate": 0.00017216960824649303,
      "loss": 1.646,
      "step": 65
    },
    {
      "epoch": 1.0878661087866108,
      "grad_norm": 0.15547165274620056,
      "learning_rate": 0.00017120043555935298,
      "loss": 1.6625,
      "step": 66
    },
    {
      "epoch": 1.104602510460251,
      "grad_norm": 0.14291325211524963,
      "learning_rate": 0.0001702175047702382,
      "loss": 1.6392,
      "step": 67
    },
    {
      "epoch": 1.1213389121338913,
      "grad_norm": 0.14325812458992004,
      "learning_rate": 0.00016922100581144228,
      "loss": 1.6677,
      "step": 68
    },
    {
      "epoch": 1.1380753138075315,
      "grad_norm": 0.14328014850616455,
      "learning_rate": 0.00016821113123704424,
      "loss": 1.6182,
      "step": 69
    },
    {
      "epoch": 1.1548117154811715,
      "grad_norm": 0.16151900589466095,
      "learning_rate": 0.00016718807618570106,
      "loss": 1.6492,
      "step": 70
    },
    {
      "epoch": 1.1715481171548117,
      "grad_norm": 0.15649794042110443,
      "learning_rate": 0.00016615203834294119,
      "loss": 1.6334,
      "step": 71
    },
    {
      "epoch": 1.1882845188284519,
      "grad_norm": 0.15963214635849,
      "learning_rate": 0.00016510321790296525,
      "loss": 1.6203,
      "step": 72
    },
    {
      "epoch": 1.205020920502092,
      "grad_norm": 0.15893195569515228,
      "learning_rate": 0.00016404181752996289,
      "loss": 1.6408,
      "step": 73
    },
    {
      "epoch": 1.2217573221757323,
      "grad_norm": 0.16694918274879456,
      "learning_rate": 0.00016296804231895142,
      "loss": 1.633,
      "step": 74
    },
    {
      "epoch": 1.2384937238493725,
      "grad_norm": 0.15804418921470642,
      "learning_rate": 0.00016188209975614542,
      "loss": 1.6548,
      "step": 75
    },
    {
      "epoch": 1.2552301255230125,
      "grad_norm": 0.14725787937641144,
      "learning_rate": 0.00016078419967886402,
      "loss": 1.6158,
      "step": 76
    },
    {
      "epoch": 1.2719665271966527,
      "grad_norm": 0.15310946106910706,
      "learning_rate": 0.00015967455423498387,
      "loss": 1.664,
      "step": 77
    },
    {
      "epoch": 1.288702928870293,
      "grad_norm": 0.14741982519626617,
      "learning_rate": 0.00015855337784194577,
      "loss": 1.6494,
      "step": 78
    },
    {
      "epoch": 1.3054393305439331,
      "grad_norm": 0.1478704810142517,
      "learning_rate": 0.00015742088714532247,
      "loss": 1.6254,
      "step": 79
    },
    {
      "epoch": 1.3221757322175733,
      "grad_norm": 0.1895337849855423,
      "learning_rate": 0.00015627730097695638,
      "loss": 1.6018,
      "step": 80
    },
    {
      "epoch": 1.3389121338912133,
      "grad_norm": 0.19194994866847992,
      "learning_rate": 0.00015512284031267437,
      "loss": 1.6543,
      "step": 81
    },
    {
      "epoch": 1.3556485355648535,
      "grad_norm": 0.1553422063589096,
      "learning_rate": 0.00015395772822958845,
      "loss": 1.6429,
      "step": 82
    },
    {
      "epoch": 1.3723849372384938,
      "grad_norm": 0.19711142778396606,
      "learning_rate": 0.00015278218986299074,
      "loss": 1.624,
      "step": 83
    },
    {
      "epoch": 1.389121338912134,
      "grad_norm": 0.16961851716041565,
      "learning_rate": 0.0001515964523628501,
      "loss": 1.6097,
      "step": 84
    },
    {
      "epoch": 1.4058577405857742,
      "grad_norm": 0.20063763856887817,
      "learning_rate": 0.00015040074484992,
      "loss": 1.6171,
      "step": 85
    },
    {
      "epoch": 1.4225941422594142,
      "grad_norm": 0.16175565123558044,
      "learning_rate": 0.00014919529837146528,
      "loss": 1.6119,
      "step": 86
    },
    {
      "epoch": 1.4393305439330544,
      "grad_norm": 0.20445561408996582,
      "learning_rate": 0.00014798034585661695,
      "loss": 1.6089,
      "step": 87
    },
    {
      "epoch": 1.4560669456066946,
      "grad_norm": 0.17204363644123077,
      "learning_rate": 0.0001467561220713628,
      "loss": 1.6178,
      "step": 88
    },
    {
      "epoch": 1.4728033472803348,
      "grad_norm": 0.1780082732439041,
      "learning_rate": 0.0001455228635731839,
      "loss": 1.6172,
      "step": 89
    },
    {
      "epoch": 1.489539748953975,
      "grad_norm": 0.17321935296058655,
      "learning_rate": 0.00014428080866534396,
      "loss": 1.574,
      "step": 90
    },
    {
      "epoch": 1.506276150627615,
      "grad_norm": 0.1722816675901413,
      "learning_rate": 0.00014303019735084226,
      "loss": 1.6096,
      "step": 91
    },
    {
      "epoch": 1.5230125523012552,
      "grad_norm": 0.1621088981628418,
      "learning_rate": 0.00014177127128603745,
      "loss": 1.603,
      "step": 92
    },
    {
      "epoch": 1.5397489539748954,
      "grad_norm": 0.17485831677913666,
      "learning_rate": 0.0001405042737339524,
      "loss": 1.6105,
      "step": 93
    },
    {
      "epoch": 1.5564853556485354,
      "grad_norm": 0.16599352657794952,
      "learning_rate": 0.0001392294495172681,
      "loss": 1.632,
      "step": 94
    },
    {
      "epoch": 1.5732217573221758,
      "grad_norm": 0.1569545418024063,
      "learning_rate": 0.00013794704497101655,
      "loss": 1.608,
      "step": 95
    },
    {
      "epoch": 1.5899581589958158,
      "grad_norm": 0.15951111912727356,
      "learning_rate": 0.0001366573078949813,
      "loss": 1.5742,
      "step": 96
    },
    {
      "epoch": 1.606694560669456,
      "grad_norm": 0.1951216161251068,
      "learning_rate": 0.00013536048750581494,
      "loss": 1.5908,
      "step": 97
    },
    {
      "epoch": 1.6234309623430963,
      "grad_norm": 0.20315046608448029,
      "learning_rate": 0.00013405683438888282,
      "loss": 1.6081,
      "step": 98
    },
    {
      "epoch": 1.6401673640167362,
      "grad_norm": 0.16759882867336273,
      "learning_rate": 0.00013274660044984224,
      "loss": 1.6041,
      "step": 99
    },
    {
      "epoch": 1.6569037656903767,
      "grad_norm": 0.18749655783176422,
      "learning_rate": 0.00013143003886596669,
      "loss": 1.6002,
      "step": 100
    },
    {
      "epoch": 1.6736401673640167,
      "grad_norm": 0.1809973418712616,
      "learning_rate": 0.0001301074040372242,
      "loss": 1.6328,
      "step": 101
    },
    {
      "epoch": 1.6903765690376569,
      "grad_norm": 0.20419345796108246,
      "learning_rate": 0.00012877895153711935,
      "loss": 1.6017,
      "step": 102
    },
    {
      "epoch": 1.707112970711297,
      "grad_norm": 0.1926768571138382,
      "learning_rate": 0.0001274449380633089,
      "loss": 1.5793,
      "step": 103
    },
    {
      "epoch": 1.723849372384937,
      "grad_norm": 0.22891242802143097,
      "learning_rate": 0.00012610562138799978,
      "loss": 1.6306,
      "step": 104
    },
    {
      "epoch": 1.7405857740585775,
      "grad_norm": 0.17105843126773834,
      "learning_rate": 0.00012476126030813963,
      "loss": 1.5999,
      "step": 105
    },
    {
      "epoch": 1.7573221757322175,
      "grad_norm": 0.17857873439788818,
      "learning_rate": 0.0001234121145954094,
      "loss": 1.5867,
      "step": 106
    },
    {
      "epoch": 1.7740585774058577,
      "grad_norm": 0.1942574381828308,
      "learning_rate": 0.0001220584449460274,
      "loss": 1.5719,
      "step": 107
    },
    {
      "epoch": 1.790794979079498,
      "grad_norm": 0.18035678565502167,
      "learning_rate": 0.00012070051293037492,
      "loss": 1.5783,
      "step": 108
    },
    {
      "epoch": 1.8075313807531381,
      "grad_norm": 0.18351756036281586,
      "learning_rate": 0.00011933858094245281,
      "loss": 1.6121,
      "step": 109
    },
    {
      "epoch": 1.8242677824267783,
      "grad_norm": 0.17191624641418457,
      "learning_rate": 0.00011797291214917881,
      "loss": 1.5801,
      "step": 110
    },
    {
      "epoch": 1.8410041841004183,
      "grad_norm": 0.19317130744457245,
      "learning_rate": 0.00011660377043953588,
      "loss": 1.5928,
      "step": 111
    },
    {
      "epoch": 1.8577405857740585,
      "grad_norm": 0.1735094040632248,
      "learning_rate": 0.0001152314203735805,
      "loss": 1.5782,
      "step": 112
    },
    {
      "epoch": 1.8744769874476988,
      "grad_norm": 0.1757810264825821,
      "learning_rate": 0.0001138561271313219,
      "loss": 1.605,
      "step": 113
    },
    {
      "epoch": 1.891213389121339,
      "grad_norm": 0.20154766738414764,
      "learning_rate": 0.00011247815646148087,
      "loss": 1.5782,
      "step": 114
    },
    {
      "epoch": 1.9079497907949792,
      "grad_norm": 0.18075552582740784,
      "learning_rate": 0.00011109777463013915,
      "loss": 1.5905,
      "step": 115
    },
    {
      "epoch": 1.9246861924686192,
      "grad_norm": 0.1821986436843872,
      "learning_rate": 0.0001097152483692886,
      "loss": 1.5661,
      "step": 116
    },
    {
      "epoch": 1.9414225941422594,
      "grad_norm": 0.1858905404806137,
      "learning_rate": 0.00010833084482529048,
      "loss": 1.6245,
      "step": 117
    },
    {
      "epoch": 1.9581589958158996,
      "grad_norm": 0.19977439939975739,
      "learning_rate": 0.00010694483150725458,
      "loss": 1.5568,
      "step": 118
    },
    {
      "epoch": 1.9581589958158996,
      "eval_loss": 1.7031370401382446,
      "eval_runtime": 45.0796,
      "eval_samples_per_second": 37.334,
      "eval_steps_per_second": 0.799,
      "step": 118
    }
  ],
  "logging_steps": 1,
  "max_steps": 236,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 59,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.814736962945024e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}