{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 117,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.20494528114795685,
      "learning_rate": 1e-05,
      "loss": 2.944,
      "step": 1
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.564369261264801,
      "learning_rate": 9.998197638354428e-06,
      "loss": 2.7139,
      "step": 2
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.2275543510913849,
      "learning_rate": 9.992791852820709e-06,
      "loss": 3.002,
      "step": 3
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.1662287712097168,
      "learning_rate": 9.983786540671052e-06,
      "loss": 2.6937,
      "step": 4
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.30666545033454895,
      "learning_rate": 9.971188194237141e-06,
      "loss": 2.5144,
      "step": 5
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.22469215095043182,
      "learning_rate": 9.955005896229543e-06,
      "loss": 2.5842,
      "step": 6
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.2725427448749542,
      "learning_rate": 9.935251313189564e-06,
      "loss": 2.9155,
      "step": 7
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.19864390790462494,
      "learning_rate": 9.911938687078324e-06,
      "loss": 2.6917,
      "step": 8
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.15495699644088745,
      "learning_rate": 9.885084825009085e-06,
      "loss": 2.3191,
      "step": 9
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.7309098839759827,
      "learning_rate": 9.854709087130261e-06,
      "loss": 3.166,
      "step": 10
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.2202342301607132,
      "learning_rate": 9.820833372667813e-06,
      "loss": 3.0812,
      "step": 11
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.45190778374671936,
      "learning_rate": 9.783482104137127e-06,
      "loss": 2.6462,
      "step": 12
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.2022932767868042,
      "learning_rate": 9.742682209735727e-06,
      "loss": 2.9554,
      "step": 13
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.17690043151378632,
      "learning_rate": 9.698463103929542e-06,
      "loss": 2.5946,
      "step": 14
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.20987562835216522,
      "learning_rate": 9.650856666246693e-06,
      "loss": 2.4706,
      "step": 15
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.19785286486148834,
      "learning_rate": 9.599897218294122e-06,
      "loss": 2.5767,
      "step": 16
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.26647791266441345,
      "learning_rate": 9.54562149901362e-06,
      "loss": 3.1842,
      "step": 17
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.14869138598442078,
      "learning_rate": 9.488068638195072e-06,
      "loss": 2.7924,
      "step": 18
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.18388637900352478,
      "learning_rate": 9.427280128266049e-06,
      "loss": 2.779,
      "step": 19
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.16335400938987732,
      "learning_rate": 9.363299794378072e-06,
      "loss": 2.9099,
      "step": 20
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.3611254096031189,
      "learning_rate": 9.296173762811084e-06,
      "loss": 2.7484,
      "step": 21
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.22266459465026855,
      "learning_rate": 9.225950427718974e-06,
      "loss": 2.6731,
      "step": 22
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.2212408483028412,
      "learning_rate": 9.152680416240059e-06,
      "loss": 2.5159,
      "step": 23
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.24422743916511536,
      "learning_rate": 9.076416551997721e-06,
      "loss": 3.0238,
      "step": 24
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.17641104757785797,
      "learning_rate": 8.997213817017508e-06,
      "loss": 2.7511,
      "step": 25
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.17786549031734467,
      "learning_rate": 8.915129312088112e-06,
      "loss": 2.8246,
      "step": 26
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.19077053666114807,
      "learning_rate": 8.83022221559489e-06,
      "loss": 2.8039,
      "step": 27
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.16474156081676483,
      "learning_rate": 8.742553740855507e-06,
      "loss": 2.9055,
      "step": 28
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.16694943606853485,
      "learning_rate": 8.652187091988516e-06,
      "loss": 3.0026,
      "step": 29
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.18305574357509613,
      "learning_rate": 8.559187418346703e-06,
      "loss": 3.05,
      "step": 30
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.44106462597846985,
      "learning_rate": 8.463621767547998e-06,
      "loss": 2.3594,
      "step": 31
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.13298189640045166,
      "learning_rate": 8.36555903713785e-06,
      "loss": 2.7032,
      "step": 32
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.16964633762836456,
      "learning_rate": 8.265069924917925e-06,
      "loss": 3.0049,
      "step": 33
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.21558941900730133,
      "learning_rate": 8.162226877976886e-06,
      "loss": 2.5803,
      "step": 34
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.1849488765001297,
      "learning_rate": 8.057104040460062e-06,
      "loss": 2.2861,
      "step": 35
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.16992613673210144,
      "learning_rate": 7.949777200115617e-06,
      "loss": 2.5638,
      "step": 36
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.1811276227235794,
      "learning_rate": 7.84032373365578e-06,
      "loss": 2.7225,
      "step": 37
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.14251349866390228,
      "learning_rate": 7.728822550972523e-06,
      "loss": 2.5935,
      "step": 38
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20674623548984528,
      "learning_rate": 7.615354038247889e-06,
      "loss": 2.3489,
      "step": 39
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.16418299078941345,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.8806,
      "step": 40
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 0.42056992650032043,
      "learning_rate": 7.382843600106539e-06,
      "loss": 2.5225,
      "step": 41
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.1651465892791748,
      "learning_rate": 7.263969301848188e-06,
      "loss": 2.9385,
      "step": 42
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 0.11612721532583237,
      "learning_rate": 7.143462807015271e-06,
      "loss": 2.65,
      "step": 43
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.22792533040046692,
      "learning_rate": 7.021410994121525e-06,
      "loss": 2.4115,
      "step": 44
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.18955646455287933,
      "learning_rate": 6.897901855769483e-06,
      "loss": 2.5088,
      "step": 45
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 0.2061670422554016,
      "learning_rate": 6.773024435212678e-06,
      "loss": 2.8308,
      "step": 46
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 0.1557702273130417,
      "learning_rate": 6.646868762160399e-06,
      "loss": 2.6351,
      "step": 47
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.13028891384601593,
      "learning_rate": 6.519525787871235e-06,
      "loss": 2.2725,
      "step": 48
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.5919710993766785,
      "learning_rate": 6.391087319582264e-06,
      "loss": 2.9043,
      "step": 49
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.16268998384475708,
      "learning_rate": 6.261645954321109e-06,
      "loss": 3.0056,
      "step": 50
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.3303690552711487,
      "learning_rate": 6.131295012148613e-06,
      "loss": 2.4932,
      "step": 51
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.140819251537323,
      "learning_rate": 6.000128468880223e-06,
      "loss": 2.8989,
      "step": 52
    },
    {
      "epoch": 1.358974358974359,
      "grad_norm": 0.13831716775894165,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 2.5417,
      "step": 53
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.18448969721794128,
      "learning_rate": 5.735727354158581e-06,
      "loss": 2.4042,
      "step": 54
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.1544794738292694,
      "learning_rate": 5.6026834012766155e-06,
      "loss": 2.5227,
      "step": 55
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.22304964065551758,
      "learning_rate": 5.469204947015897e-06,
      "loss": 3.0919,
      "step": 56
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.1189192682504654,
      "learning_rate": 5.335388221955012e-06,
      "loss": 2.7538,
      "step": 57
    },
    {
      "epoch": 1.4871794871794872,
      "grad_norm": 0.14262886345386505,
      "learning_rate": 5.201329700547077e-06,
      "loss": 2.7141,
      "step": 58
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 0.12737467885017395,
      "learning_rate": 5.067126031566988e-06,
      "loss": 2.8652,
      "step": 59
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.2574975788593292,
      "learning_rate": 4.932873968433014e-06,
      "loss": 2.6555,
      "step": 60
    },
    {
      "epoch": 1.564102564102564,
      "grad_norm": 0.18790772557258606,
      "learning_rate": 4.798670299452926e-06,
      "loss": 2.6082,
      "step": 61
    },
    {
      "epoch": 1.5897435897435899,
      "grad_norm": 0.17647786438465118,
      "learning_rate": 4.664611778044988e-06,
      "loss": 2.4594,
      "step": 62
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.1943756341934204,
      "learning_rate": 4.530795052984104e-06,
      "loss": 2.9589,
      "step": 63
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.15042220056056976,
      "learning_rate": 4.397316598723385e-06,
      "loss": 2.7027,
      "step": 64
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.1804312914609909,
      "learning_rate": 4.264272645841419e-06,
      "loss": 2.7935,
      "step": 65
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.1711619645357132,
      "learning_rate": 4.131759111665349e-06,
      "loss": 2.7634,
      "step": 66
    },
    {
      "epoch": 1.717948717948718,
      "grad_norm": 0.13611891865730286,
      "learning_rate": 3.999871531119779e-06,
      "loss": 2.8654,
      "step": 67
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.13859815895557404,
      "learning_rate": 3.86870498785139e-06,
      "loss": 2.9677,
      "step": 68
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.17095635831356049,
      "learning_rate": 3.7383540456788915e-06,
      "loss": 3.006,
      "step": 69
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.33051353693008423,
      "learning_rate": 3.6089126804177373e-06,
      "loss": 2.2646,
      "step": 70
    },
    {
      "epoch": 1.8205128205128205,
      "grad_norm": 0.12325972318649292,
      "learning_rate": 3.480474212128766e-06,
      "loss": 2.6746,
      "step": 71
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.15464168787002563,
      "learning_rate": 3.3531312378396026e-06,
      "loss": 2.9761,
      "step": 72
    },
    {
      "epoch": 1.8717948717948718,
      "grad_norm": 0.1984647959470749,
      "learning_rate": 3.226975564787322e-06,
      "loss": 2.5415,
      "step": 73
    },
    {
      "epoch": 1.8974358974358974,
      "grad_norm": 0.17000555992126465,
      "learning_rate": 3.1020981442305187e-06,
      "loss": 2.2454,
      "step": 74
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.15753290057182312,
      "learning_rate": 2.978589005878476e-06,
      "loss": 2.535,
      "step": 75
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.16940346360206604,
      "learning_rate": 2.8565371929847286e-06,
      "loss": 2.6881,
      "step": 76
    },
    {
      "epoch": 1.9743589743589745,
      "grad_norm": 0.13065537810325623,
      "learning_rate": 2.736030698151815e-06,
      "loss": 2.5689,
      "step": 77
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.19400492310523987,
      "learning_rate": 2.6171563998934605e-06,
      "loss": 2.3126,
      "step": 78
    },
    {
      "epoch": 2.0256410256410255,
      "grad_norm": 0.1678439974784851,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 2.8647,
      "step": 79
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.36615338921546936,
      "learning_rate": 2.384645961752113e-06,
      "loss": 2.4473,
      "step": 80
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.15688776969909668,
      "learning_rate": 2.2711774490274767e-06,
      "loss": 2.9054,
      "step": 81
    },
    {
      "epoch": 2.1025641025641026,
      "grad_norm": 0.10982992500066757,
      "learning_rate": 2.159676266344222e-06,
      "loss": 2.6324,
      "step": 82
    },
    {
      "epoch": 2.128205128205128,
      "grad_norm": 0.21072708070278168,
      "learning_rate": 2.050222799884387e-06,
      "loss": 2.3846,
      "step": 83
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.18832428753376007,
      "learning_rate": 1.942895959539939e-06,
      "loss": 2.4825,
      "step": 84
    },
    {
      "epoch": 2.1794871794871793,
      "grad_norm": 0.20066532492637634,
      "learning_rate": 1.8377731220231144e-06,
      "loss": 2.7871,
      "step": 85
    },
    {
      "epoch": 2.2051282051282053,
      "grad_norm": 0.16142620146274567,
      "learning_rate": 1.7349300750820758e-06,
      "loss": 2.6139,
      "step": 86
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.1329987347126007,
      "learning_rate": 1.6344409628621482e-06,
      "loss": 2.2679,
      "step": 87
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.48261162638664246,
      "learning_rate": 1.5363782324520033e-06,
      "loss": 2.8223,
      "step": 88
    },
    {
      "epoch": 2.282051282051282,
      "grad_norm": 0.16861321032047272,
      "learning_rate": 1.4408125816532981e-06,
      "loss": 2.9918,
      "step": 89
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.30975234508514404,
      "learning_rate": 1.347812908011485e-06,
      "loss": 2.4583,
      "step": 90
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.5936061143875122,
      "learning_rate": 1.257446259144494e-06,
      "loss": 2.8887,
      "step": 91
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.14251480996608734,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 2.5273,
      "step": 92
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.1809547394514084,
      "learning_rate": 1.0848706879118893e-06,
      "loss": 2.3871,
      "step": 93
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 0.1559205800294876,
      "learning_rate": 1.0027861829824953e-06,
      "loss": 2.5071,
      "step": 94
    },
    {
      "epoch": 2.435897435897436,
      "grad_norm": 0.22356708347797394,
      "learning_rate": 9.235834480022788e-07,
      "loss": 3.0696,
      "step": 95
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.11708559095859528,
      "learning_rate": 8.473195837599419e-07,
      "loss": 2.741,
      "step": 96
    },
    {
      "epoch": 2.4871794871794872,
      "grad_norm": 0.13850131630897522,
      "learning_rate": 7.740495722810271e-07,
      "loss": 2.7068,
      "step": 97
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.127314954996109,
      "learning_rate": 7.03826237188916e-07,
      "loss": 2.8583,
      "step": 98
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.2526121437549591,
      "learning_rate": 6.367002056219285e-07,
      "loss": 2.6353,
      "step": 99
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.18439951539039612,
      "learning_rate": 5.727198717339511e-07,
      "loss": 2.5881,
      "step": 100
    },
    {
      "epoch": 2.58974358974359,
      "grad_norm": 0.17252342402935028,
      "learning_rate": 5.119313618049309e-07,
      "loss": 2.4458,
      "step": 101
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.19350160658359528,
      "learning_rate": 4.54378500986381e-07,
      "loss": 2.9525,
      "step": 102
    },
    {
      "epoch": 2.641025641025641,
      "grad_norm": 0.15075629949569702,
      "learning_rate": 4.001027817058789e-07,
      "loss": 2.7002,
      "step": 103
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.18015150725841522,
      "learning_rate": 3.49143333753309e-07,
      "loss": 2.79,
      "step": 104
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.17058293521404266,
      "learning_rate": 3.015368960704584e-07,
      "loss": 2.7456,
      "step": 105
    },
    {
      "epoch": 2.717948717948718,
      "grad_norm": 0.1371268630027771,
      "learning_rate": 2.573177902642726e-07,
      "loss": 2.8645,
      "step": 106
    },
    {
      "epoch": 2.7435897435897436,
      "grad_norm": 0.1372060924768448,
      "learning_rate": 2.1651789586287442e-07,
      "loss": 2.9625,
      "step": 107
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.17000600695610046,
      "learning_rate": 1.7916662733218848e-07,
      "loss": 3.005,
      "step": 108
    },
    {
      "epoch": 2.7948717948717947,
      "grad_norm": 0.3287239074707031,
      "learning_rate": 1.4529091286973994e-07,
      "loss": 2.2515,
      "step": 109
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.12300807982683182,
      "learning_rate": 1.1491517499091498e-07,
      "loss": 2.6743,
      "step": 110
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.15311472117900848,
      "learning_rate": 8.80613129216762e-08,
      "loss": 2.9753,
      "step": 111
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.20104099810123444,
      "learning_rate": 6.474868681043578e-08,
      "loss": 2.5298,
      "step": 112
    },
    {
      "epoch": 2.8974358974358974,
      "grad_norm": 0.17030330002307892,
      "learning_rate": 4.499410377045765e-08,
      "loss": 2.2434,
      "step": 113
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.1580314338207245,
      "learning_rate": 2.8811805762860578e-08,
      "loss": 2.5331,
      "step": 114
    },
    {
      "epoch": 2.948717948717949,
      "grad_norm": 0.1715579628944397,
      "learning_rate": 1.6213459328950355e-08,
      "loss": 2.688,
      "step": 115
    },
    {
      "epoch": 2.9743589743589745,
      "grad_norm": 0.1321800947189331,
      "learning_rate": 7.2081471792911914e-09,
      "loss": 2.5686,
      "step": 116
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.1928524672985077,
      "learning_rate": 1.8023616455731253e-09,
      "loss": 2.3083,
      "step": 117
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.5,
      "eval_runtime": 10.2576,
      "eval_samples_per_second": 0.097,
      "eval_steps_per_second": 0.097,
      "step": 117
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 117,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.029898068446413e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}