{
  "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": 0.15355850756168365,
      "learning_rate": 2e-05,
      "loss": 1.4892,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.1224861666560173,
      "learning_rate": 4e-05,
      "loss": 1.1445,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.1645984649658203,
      "learning_rate": 6e-05,
      "loss": 1.5538,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.125856414437294,
      "learning_rate": 8e-05,
      "loss": 1.7634,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.1726977378129959,
      "learning_rate": 0.0001,
      "loss": 1.4105,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.18316921591758728,
      "learning_rate": 0.00012,
      "loss": 1.8364,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.17618055641651154,
      "learning_rate": 0.00014,
      "loss": 1.3885,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.17036275565624237,
      "learning_rate": 0.00016,
      "loss": 1.3574,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.18832312524318695,
      "learning_rate": 0.00018,
      "loss": 1.2256,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.22157786786556244,
      "learning_rate": 0.0002,
      "loss": 1.515,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.21728643774986267,
      "learning_rate": 0.0001999976474595967,
      "loss": 1.4505,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.16113220155239105,
      "learning_rate": 0.00019999058994907564,
      "loss": 1.132,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.1798534393310547,
      "learning_rate": 0.00019997882780049847,
      "loss": 1.2355,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.19335126876831055,
      "learning_rate": 0.0001999623615672837,
      "loss": 1.4485,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.14973561465740204,
      "learning_rate": 0.00019994119202418098,
      "loss": 1.4852,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.1763419359922409,
      "learning_rate": 0.00019991532016723439,
      "loss": 1.0831,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.148220494389534,
      "learning_rate": 0.00019988474721373568,
      "loss": 1.5454,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.1581086665391922,
      "learning_rate": 0.00019984947460216707,
      "loss": 0.9387,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.1937003880739212,
      "learning_rate": 0.00019980950399213344,
      "loss": 1.1612,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.15193545818328857,
      "learning_rate": 0.00019976483726428422,
      "loss": 0.9678,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.17265811562538147,
      "learning_rate": 0.0001997154765202251,
      "loss": 1.0147,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.16466519236564636,
      "learning_rate": 0.00019966142408241901,
      "loss": 1.1492,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.17746295034885406,
      "learning_rate": 0.00019960268249407675,
      "loss": 1.2277,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.1838495433330536,
      "learning_rate": 0.00019953925451903756,
      "loss": 1.1559,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.1542479395866394,
      "learning_rate": 0.0001994711431416389,
      "loss": 1.855,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.1788703054189682,
      "learning_rate": 0.00019939835156657616,
      "loss": 1.6273,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.15661294758319855,
      "learning_rate": 0.00019932088321875172,
      "loss": 1.0783,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.1869712620973587,
      "learning_rate": 0.00019923874174311394,
      "loss": 0.9181,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.14521349966526031,
      "learning_rate": 0.0001991519310044857,
      "loss": 1.4428,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.17194955050945282,
      "learning_rate": 0.00019906045508738228,
      "loss": 1.3213,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.14739835262298584,
      "learning_rate": 0.0001989643182958196,
      "loss": 0.9933,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.17825335264205933,
      "learning_rate": 0.00019886352515311134,
      "loss": 1.034,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.16200387477874756,
      "learning_rate": 0.0001987580804016563,
      "loss": 1.3064,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.170911967754364,
      "learning_rate": 0.00019864798900271532,
      "loss": 1.2321,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.16599859297275543,
      "learning_rate": 0.0001985332561361776,
      "loss": 0.9447,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.14686603844165802,
      "learning_rate": 0.00019841388720031727,
      "loss": 0.8823,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.1870049089193344,
      "learning_rate": 0.00019828988781153917,
      "loss": 1.1041,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.1619299054145813,
      "learning_rate": 0.00019816126380411476,
      "loss": 0.9918,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.18731147050857544,
      "learning_rate": 0.00019802802122990758,
      "loss": 1.0642,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.17905616760253906,
      "learning_rate": 0.00019789016635808837,
      "loss": 1.0877,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.15318270027637482,
      "learning_rate": 0.00019774770567484022,
      "loss": 1.2165,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.14854711294174194,
      "learning_rate": 0.00019760064588305345,
      "loss": 0.9812,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.15519340336322784,
      "learning_rate": 0.00019744899390201006,
      "loss": 0.9977,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.1589617133140564,
      "learning_rate": 0.0001972927568670583,
      "loss": 1.4097,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.17286093533039093,
      "learning_rate": 0.00019713194212927696,
      "loss": 1.1385,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.19325074553489685,
      "learning_rate": 0.00019696655725512933,
      "loss": 0.9997,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.18447531759738922,
      "learning_rate": 0.00019679661002610743,
      "loss": 1.0873,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.16223366558551788,
      "learning_rate": 0.00019662210843836574,
      "loss": 0.99,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.1919640749692917,
      "learning_rate": 0.0001964430607023449,
      "loss": 1.0171,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.22606882452964783,
      "learning_rate": 0.00019625947524238563,
      "loss": 1.4172,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.17758312821388245,
      "learning_rate": 0.00019607136069633212,
      "loss": 0.9964,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.16785483062267303,
      "learning_rate": 0.0001958787259151258,
      "loss": 0.9883,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.19499914348125458,
      "learning_rate": 0.00019568157996238884,
      "loss": 1.0293,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.15674076974391937,
      "learning_rate": 0.0001954799321139975,
      "loss": 1.3643,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.16759538650512695,
      "learning_rate": 0.00019527379185764612,
      "loss": 0.8998,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.20853222906589508,
      "learning_rate": 0.00019506316889240027,
      "loss": 1.4597,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.18584011495113373,
      "learning_rate": 0.00019484807312824067,
      "loss": 0.8848,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.24146708846092224,
      "learning_rate": 0.0001946285146855968,
      "loss": 1.0529,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.20457321405410767,
      "learning_rate": 0.0001944045038948709,
      "loss": 0.9917,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.21354275941848755,
      "learning_rate": 0.00019417605129595157,
      "loss": 0.9096,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.2198089212179184,
      "learning_rate": 0.0001939431676377183,
      "loss": 0.9228,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.18545866012573242,
      "learning_rate": 0.0001937058638775353,
      "loss": 0.8399,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.1578792780637741,
      "learning_rate": 0.00019346415118073632,
      "loss": 1.6315,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.23443493247032166,
      "learning_rate": 0.00019321804092009906,
      "loss": 1.0905,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.20623010396957397,
      "learning_rate": 0.00019296754467531014,
      "loss": 0.9367,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.24046015739440918,
      "learning_rate": 0.00019271267423242024,
      "loss": 0.9195,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.22675752639770508,
      "learning_rate": 0.00019245344158328972,
      "loss": 1.1275,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.22297680377960205,
      "learning_rate": 0.0001921898589250242,
      "loss": 0.9244,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.21324071288108826,
      "learning_rate": 0.0001919219386594007,
      "loss": 0.9706,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.21497191488742828,
      "learning_rate": 0.00019164969339228422,
      "loss": 1.0559,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.2526251971721649,
      "learning_rate": 0.00019137313593303463,
      "loss": 1.0632,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.19590331614017487,
      "learning_rate": 0.00019109227929390378,
      "loss": 1.8134,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.21532683074474335,
      "learning_rate": 0.00019080713668942356,
      "loss": 0.9466,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.2264883816242218,
      "learning_rate": 0.00019051772153578389,
      "loss": 0.8941,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.22985824942588806,
      "learning_rate": 0.00019022404745020163,
      "loss": 0.8991,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.19453634321689606,
      "learning_rate": 0.00018992612825027976,
      "loss": 0.9837,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.2547195851802826,
      "learning_rate": 0.0001896239779533575,
      "loss": 1.1035,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.20812910795211792,
      "learning_rate": 0.00018931761077585035,
      "loss": 0.8916,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.2176084816455841,
      "learning_rate": 0.00018900704113258165,
      "loss": 0.8826,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2221064418554306,
      "learning_rate": 0.00018869228363610404,
      "loss": 0.9069,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.2675364911556244,
      "learning_rate": 0.00018837335309601213,
      "loss": 1.035,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.1994653195142746,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.5854,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.20346811413764954,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.4788,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.22119802236557007,
      "learning_rate": 0.00018739167425092644,
      "loss": 1.4946,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.2174052894115448,
      "learning_rate": 0.00018705620354857833,
      "loss": 0.8667,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.2322807013988495,
      "learning_rate": 0.00018671663678150607,
      "loss": 0.861,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.22151263058185577,
      "learning_rate": 0.0001863729899266004,
      "loss": 0.8966,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.243766650557518,
      "learning_rate": 0.0001860252791527236,
      "loss": 1.2998,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.19212521612644196,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.5215,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.20964723825454712,
      "learning_rate": 0.00018531773147878895,
      "loss": 1.4717,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.24561531841754913,
      "learning_rate": 0.0001849579278694209,
      "loss": 0.9569,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.23924781382083893,
      "learning_rate": 0.00018459412692089494,
      "loss": 0.9441,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.2302614450454712,
      "learning_rate": 0.0001842263457503397,
      "loss": 0.8417,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.24661926925182343,
      "learning_rate": 0.00018385460166215638,
      "loss": 1.1297,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.24925513565540314,
      "learning_rate": 0.00018347891214720477,
      "loss": 0.8999,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.19934344291687012,
      "learning_rate": 0.00018309929488198012,
      "loss": 1.4818,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.24845215678215027,
      "learning_rate": 0.00018271576772778154,
      "loss": 0.9454,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.22845034301280975,
      "learning_rate": 0.00018232834872987147,
      "loss": 1.5063,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.2563302516937256,
      "learning_rate": 0.00018193705611662696,
      "loss": 0.9946,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.30030304193496704,
      "learning_rate": 0.0001815419082986815,
      "loss": 1.0936,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.22599591314792633,
      "learning_rate": 0.00018114292386805936,
      "loss": 1.346,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.20411820709705353,
      "learning_rate": 0.00018074012159730032,
      "loss": 1.5147,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.20635190606117249,
      "learning_rate": 0.00018033352043857675,
      "loss": 1.1425,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.22327086329460144,
      "learning_rate": 0.00017992313952280172,
      "loss": 1.4435,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.2183496206998825,
      "learning_rate": 0.00017950899815872892,
      "loss": 1.5659,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.31636252999305725,
      "learning_rate": 0.00017909111583204422,
      "loss": 1.4703,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.3305496275424957,
      "learning_rate": 0.0001786695122044487,
      "loss": 1.0904,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.22857435047626495,
      "learning_rate": 0.0001782442071127338,
      "loss": 1.3801,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.31968221068382263,
      "learning_rate": 0.0001778152205678477,
      "loss": 1.4907,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.27950960397720337,
      "learning_rate": 0.00017738257275395404,
      "loss": 1.0864,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.2740281820297241,
      "learning_rate": 0.00017694628402748202,
      "loss": 0.9241,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.26951318979263306,
      "learning_rate": 0.0001765063749161688,
      "loss": 0.9894,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.2811899781227112,
      "learning_rate": 0.00017606286611809353,
      "loss": 0.9659,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.23854824900627136,
      "learning_rate": 0.00017561577850070355,
      "loss": 1.0623,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.21959957480430603,
      "learning_rate": 0.00017516513309983253,
      "loss": 0.8671,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.3096697926521301,
      "learning_rate": 0.00017471095111871074,
      "loss": 1.0756,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.23363932967185974,
      "learning_rate": 0.0001742532539269674,
      "loss": 0.8988,
      "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": 7.59834818421719e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}