{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.6883277297019958,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.0565,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.5167361497879028,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8421,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.8402963876724243,
      "learning_rate": 3e-06,
      "loss": 1.1245,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.930655300617218,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.432,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.5283745527267456,
      "learning_rate": 5e-06,
      "loss": 0.941,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.1349669694900513,
      "learning_rate": 6e-06,
      "loss": 1.3429,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 1.173917293548584,
      "learning_rate": 7e-06,
      "loss": 0.9637,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.6507728099822998,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0163,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.6534399390220642,
      "learning_rate": 9e-06,
      "loss": 0.9108,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.8090460300445557,
      "learning_rate": 1e-05,
      "loss": 1.1224,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 1.183127760887146,
      "learning_rate": 9.999882372979835e-06,
      "loss": 1.1556,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.1587895154953003,
      "learning_rate": 9.999529497453782e-06,
      "loss": 0.9223,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.7878014445304871,
      "learning_rate": 9.998941390024924e-06,
      "loss": 1.0363,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 1.0422732830047607,
      "learning_rate": 9.998118078364186e-06,
      "loss": 1.1158,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.8618931174278259,
      "learning_rate": 9.99705960120905e-06,
      "loss": 1.1986,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.7314261198043823,
      "learning_rate": 9.99576600836172e-06,
      "loss": 0.9607,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.8001905679702759,
      "learning_rate": 9.994237360686784e-06,
      "loss": 1.3201,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.6340293288230896,
      "learning_rate": 9.992473730108354e-06,
      "loss": 0.8039,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 1.0305331945419312,
      "learning_rate": 9.990475199606672e-06,
      "loss": 0.987,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.5756571292877197,
      "learning_rate": 9.988241863214212e-06,
      "loss": 0.856,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.7210500836372375,
      "learning_rate": 9.985773826011256e-06,
      "loss": 0.9009,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.6321185231208801,
      "learning_rate": 9.98307120412095e-06,
      "loss": 0.9718,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.7177990078926086,
      "learning_rate": 9.980134124703837e-06,
      "loss": 1.0357,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.695940375328064,
      "learning_rate": 9.976962725951878e-06,
      "loss": 1.0613,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.7316240072250366,
      "learning_rate": 9.973557157081946e-06,
      "loss": 1.5432,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.1439138650894165,
      "learning_rate": 9.969917578328808e-06,
      "loss": 1.3765,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.7460082173347473,
      "learning_rate": 9.966044160937588e-06,
      "loss": 0.8814,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.6455249190330505,
      "learning_rate": 9.961937087155697e-06,
      "loss": 0.889,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.7218654155731201,
      "learning_rate": 9.957596550224285e-06,
      "loss": 1.1877,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.7643616795539856,
      "learning_rate": 9.953022754369115e-06,
      "loss": 1.133,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.4708094298839569,
      "learning_rate": 9.94821591479098e-06,
      "loss": 0.8308,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.5885545611381531,
      "learning_rate": 9.943176257655567e-06,
      "loss": 0.8915,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.7514286637306213,
      "learning_rate": 9.937904020082815e-06,
      "loss": 1.063,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.541725754737854,
      "learning_rate": 9.932399450135765e-06,
      "loss": 0.9508,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.5545334815979004,
      "learning_rate": 9.92666280680888e-06,
      "loss": 0.8066,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.47642382979393005,
      "learning_rate": 9.920694360015864e-06,
      "loss": 0.755,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.5091294050216675,
      "learning_rate": 9.914494390576958e-06,
      "loss": 0.7879,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.46325746178627014,
      "learning_rate": 9.908063190205739e-06,
      "loss": 0.83,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5515424609184265,
      "learning_rate": 9.901401061495379e-06,
      "loss": 0.8476,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.5145699977874756,
      "learning_rate": 9.894508317904418e-06,
      "loss": 0.9449,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.46632590889930725,
      "learning_rate": 9.88738528374201e-06,
      "loss": 0.9886,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.41940009593963623,
      "learning_rate": 9.880032294152673e-06,
      "loss": 0.7544,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.3798862099647522,
      "learning_rate": 9.872449695100503e-06,
      "loss": 0.77,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.571315348148346,
      "learning_rate": 9.864637843352916e-06,
      "loss": 1.1002,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.44546273350715637,
      "learning_rate": 9.856597106463847e-06,
      "loss": 0.8818,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.6359449028968811,
      "learning_rate": 9.848327862756466e-06,
      "loss": 0.8167,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.5933560729026794,
      "learning_rate": 9.839830501305371e-06,
      "loss": 0.873,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.36119118332862854,
      "learning_rate": 9.831105421918287e-06,
      "loss": 0.776,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.4318462312221527,
      "learning_rate": 9.822153035117246e-06,
      "loss": 0.7745,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.5515265464782715,
      "learning_rate": 9.812973762119282e-06,
      "loss": 1.0686,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.3906237781047821,
      "learning_rate": 9.803568034816606e-06,
      "loss": 0.7159,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3262993395328522,
      "learning_rate": 9.793936295756292e-06,
      "loss": 0.7008,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.43187564611434937,
      "learning_rate": 9.784078998119442e-06,
      "loss": 0.7201,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3680849075317383,
      "learning_rate": 9.773996605699876e-06,
      "loss": 1.0274,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.32845616340637207,
      "learning_rate": 9.763689592882307e-06,
      "loss": 0.6843,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.5680167078971863,
      "learning_rate": 9.753158444620013e-06,
      "loss": 1.1483,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.4027453660964966,
      "learning_rate": 9.742403656412033e-06,
      "loss": 0.6624,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.42083829641342163,
      "learning_rate": 9.73142573427984e-06,
      "loss": 0.8074,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.43723517656326294,
      "learning_rate": 9.720225194743544e-06,
      "loss": 0.7623,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.37138086557388306,
      "learning_rate": 9.70880256479758e-06,
      "loss": 0.7541,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.38942328095436096,
      "learning_rate": 9.697158381885915e-06,
      "loss": 0.7369,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.35463273525238037,
      "learning_rate": 9.685293193876766e-06,
      "loss": 0.6687,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.443660706281662,
      "learning_rate": 9.673207559036817e-06,
      "loss": 1.3078,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.42827773094177246,
      "learning_rate": 9.660902046004954e-06,
      "loss": 0.7356,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.6239178776741028,
      "learning_rate": 9.648377233765507e-06,
      "loss": 0.6916,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.40673717856407166,
      "learning_rate": 9.635633711621014e-06,
      "loss": 0.728,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.4105391800403595,
      "learning_rate": 9.622672079164487e-06,
      "loss": 0.811,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.37009334564208984,
      "learning_rate": 9.60949294625121e-06,
      "loss": 0.6723,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.37860628962516785,
      "learning_rate": 9.596096932970035e-06,
      "loss": 0.7644,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.36861270666122437,
      "learning_rate": 9.582484669614212e-06,
      "loss": 0.7353,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.3790634274482727,
      "learning_rate": 9.568656796651733e-06,
      "loss": 0.8376,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.5848673582077026,
      "learning_rate": 9.554613964695189e-06,
      "loss": 1.3309,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.3627384305000305,
      "learning_rate": 9.540356834471178e-06,
      "loss": 0.6774,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.37787535786628723,
      "learning_rate": 9.525886076789195e-06,
      "loss": 0.703,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.32273605465888977,
      "learning_rate": 9.511202372510083e-06,
      "loss": 0.7019,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.30288276076316833,
      "learning_rate": 9.496306412513989e-06,
      "loss": 0.7098,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.47629785537719727,
      "learning_rate": 9.481198897667875e-06,
      "loss": 0.8417,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.29766926169395447,
      "learning_rate": 9.465880538792519e-06,
      "loss": 0.6709,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.33883240818977356,
      "learning_rate": 9.450352056629083e-06,
      "loss": 0.6712,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.3106386959552765,
      "learning_rate": 9.434614181805203e-06,
      "loss": 0.6535,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.38624322414398193,
      "learning_rate": 9.418667654800607e-06,
      "loss": 0.7493,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.46079033613204956,
      "learning_rate": 9.402513225912273e-06,
      "loss": 1.1914,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.4166659414768219,
      "learning_rate": 9.386151655219137e-06,
      "loss": 1.1341,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.3459385931491852,
      "learning_rate": 9.369583712546322e-06,
      "loss": 1.1233,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.303739994764328,
      "learning_rate": 9.352810177428917e-06,
      "loss": 0.6361,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.31175675988197327,
      "learning_rate": 9.335831839075303e-06,
      "loss": 0.5938,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.3335458040237427,
      "learning_rate": 9.318649496330021e-06,
      "loss": 0.673,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.5561854839324951,
      "learning_rate": 9.30126395763618e-06,
      "loss": 1.0438,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.39674779772758484,
      "learning_rate": 9.283676040997426e-06,
      "loss": 1.2274,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.46839889883995056,
      "learning_rate": 9.265886573939448e-06,
      "loss": 1.0736,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.329444020986557,
      "learning_rate": 9.247896393471045e-06,
      "loss": 0.6996,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.37539413571357727,
      "learning_rate": 9.229706346044749e-06,
      "loss": 0.6772,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.3232697546482086,
      "learning_rate": 9.211317287516985e-06,
      "loss": 0.6433,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.4283379912376404,
      "learning_rate": 9.19273008310782e-06,
      "loss": 0.808,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.40039879083633423,
      "learning_rate": 9.173945607360238e-06,
      "loss": 0.6781,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.421421617269516,
      "learning_rate": 9.154964744099006e-06,
      "loss": 1.1649,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.37563416361808777,
      "learning_rate": 9.135788386389077e-06,
      "loss": 0.6748,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.34847089648246765,
      "learning_rate": 9.116417436493574e-06,
      "loss": 1.2002,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.38143283128738403,
      "learning_rate": 9.096852805831348e-06,
      "loss": 0.8034,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.43068060278892517,
      "learning_rate": 9.077095414934076e-06,
      "loss": 0.7409,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.4279479384422302,
      "learning_rate": 9.057146193402968e-06,
      "loss": 1.0627,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.4032224416732788,
      "learning_rate": 9.037006079865017e-06,
      "loss": 1.1393,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.36322587728500366,
      "learning_rate": 9.016676021928838e-06,
      "loss": 0.9575,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.42848172783851624,
      "learning_rate": 8.996156976140088e-06,
      "loss": 1.1044,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.38128426671028137,
      "learning_rate": 8.975449907936447e-06,
      "loss": 1.2012,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.8348135948181152,
      "learning_rate": 8.95455579160221e-06,
      "loss": 1.1161,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.599600613117218,
      "learning_rate": 8.933475610222435e-06,
      "loss": 0.8809,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.34604817628860474,
      "learning_rate": 8.91221035563669e-06,
      "loss": 1.1079,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.6436942219734192,
      "learning_rate": 8.890761028392385e-06,
      "loss": 1.136,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.44971659779548645,
      "learning_rate": 8.869128637697702e-06,
      "loss": 0.8062,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.3893284201622009,
      "learning_rate": 8.847314201374102e-06,
      "loss": 0.7011,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.39437901973724365,
      "learning_rate": 8.82531874580844e-06,
      "loss": 0.6845,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.39099910855293274,
      "learning_rate": 8.803143305904676e-06,
      "loss": 0.6957,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.3814919590950012,
      "learning_rate": 8.780788925035178e-06,
      "loss": 0.8374,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.31528154015541077,
      "learning_rate": 8.758256654991627e-06,
      "loss": 0.601,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.45662426948547363,
      "learning_rate": 8.735547555935538e-06,
      "loss": 0.7883,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3865978419780731,
      "learning_rate": 8.712662696348371e-06,
      "loss": 0.6754,
      "step": 117
    }
  ],
  "logging_steps": 1,
  "max_steps": 468,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 117,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.3510580656472064e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}