{
  "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": 0.25262296199798584,
      "learning_rate": 2e-05,
      "loss": 1.288,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.2176843136548996,
      "learning_rate": 4e-05,
      "loss": 0.9905,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.2575605809688568,
      "learning_rate": 6e-05,
      "loss": 1.3014,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.1782544106245041,
      "learning_rate": 8e-05,
      "loss": 1.5081,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.33221080899238586,
      "learning_rate": 0.0001,
      "loss": 1.1328,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.28970077633857727,
      "learning_rate": 0.00012,
      "loss": 1.4862,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.32833603024482727,
      "learning_rate": 0.00014,
      "loss": 1.0591,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.35267820954322815,
      "learning_rate": 0.00016,
      "loss": 1.0766,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.402508020401001,
      "learning_rate": 0.00018,
      "loss": 0.9063,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.316371351480484,
      "learning_rate": 0.0002,
      "loss": 1.1015,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.32572099566459656,
      "learning_rate": 0.0001999976474595967,
      "loss": 1.08,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.18087100982666016,
      "learning_rate": 0.00019999058994907564,
      "loss": 0.8118,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.30534857511520386,
      "learning_rate": 0.00019997882780049847,
      "loss": 0.9287,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.332878053188324,
      "learning_rate": 0.0001999623615672837,
      "loss": 1.0165,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.17985212802886963,
      "learning_rate": 0.00019994119202418098,
      "loss": 1.1294,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.17866399884223938,
      "learning_rate": 0.00019991532016723439,
      "loss": 0.8047,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.10377021133899689,
      "learning_rate": 0.00019988474721373568,
      "loss": 1.193,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.11353971809148788,
      "learning_rate": 0.00019984947460216707,
      "loss": 0.6695,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.12540249526500702,
      "learning_rate": 0.00019980950399213344,
      "loss": 0.7988,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.11810794472694397,
      "learning_rate": 0.00019976483726428422,
      "loss": 0.6776,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.15847349166870117,
      "learning_rate": 0.0001997154765202251,
      "loss": 0.6852,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.13485313951969147,
      "learning_rate": 0.00019966142408241901,
      "loss": 0.7981,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.1381629854440689,
      "learning_rate": 0.00019960268249407675,
      "loss": 0.8672,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.18560636043548584,
      "learning_rate": 0.00019953925451903756,
      "loss": 0.8382,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.11415428668260574,
      "learning_rate": 0.0001994711431416389,
      "loss": 1.4257,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.1419740468263626,
      "learning_rate": 0.00019939835156657616,
      "loss": 1.2219,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.1541571021080017,
      "learning_rate": 0.00019932088321875172,
      "loss": 0.7459,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.16184499859809875,
      "learning_rate": 0.00019923874174311394,
      "loss": 0.66,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.13992361724376678,
      "learning_rate": 0.0001991519310044857,
      "loss": 1.0709,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.1397615224123001,
      "learning_rate": 0.00019906045508738228,
      "loss": 0.9601,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.15078146755695343,
      "learning_rate": 0.0001989643182958196,
      "loss": 0.678,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.18909209966659546,
      "learning_rate": 0.00019886352515311134,
      "loss": 0.7399,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.149637833237648,
      "learning_rate": 0.0001987580804016563,
      "loss": 0.9793,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.14903782308101654,
      "learning_rate": 0.00019864798900271532,
      "loss": 0.8615,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.13387615978717804,
      "learning_rate": 0.0001985332561361776,
      "loss": 0.6926,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.11794736236333847,
      "learning_rate": 0.00019841388720031727,
      "loss": 0.6114,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.14885829389095306,
      "learning_rate": 0.00019828988781153917,
      "loss": 0.7201,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.15518176555633545,
      "learning_rate": 0.00019816126380411476,
      "loss": 0.7263,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.13227546215057373,
      "learning_rate": 0.00019802802122990758,
      "loss": 0.7479,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.15872053802013397,
      "learning_rate": 0.00019789016635808837,
      "loss": 0.7847,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.13838137686252594,
      "learning_rate": 0.00019774770567484022,
      "loss": 0.9159,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.11419806629419327,
      "learning_rate": 0.00019760064588305345,
      "loss": 0.6802,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.12754102051258087,
      "learning_rate": 0.00019744899390201006,
      "loss": 0.7116,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.12221560627222061,
      "learning_rate": 0.0001972927568670583,
      "loss": 1.0765,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.1402164101600647,
      "learning_rate": 0.00019713194212927696,
      "loss": 0.83,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.14776213467121124,
      "learning_rate": 0.00019696655725512933,
      "loss": 0.7333,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.14819088578224182,
      "learning_rate": 0.00019679661002610743,
      "loss": 0.8153,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.12451574206352234,
      "learning_rate": 0.00019662210843836574,
      "loss": 0.7028,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.14047390222549438,
      "learning_rate": 0.0001964430607023449,
      "loss": 0.6932,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.1826234757900238,
      "learning_rate": 0.00019625947524238563,
      "loss": 0.9923,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.14018255472183228,
      "learning_rate": 0.00019607136069633212,
      "loss": 0.6738,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.13014380633831024,
      "learning_rate": 0.0001958787259151258,
      "loss": 0.6896,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.1482684463262558,
      "learning_rate": 0.00019568157996238884,
      "loss": 0.6597,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.12220227718353271,
      "learning_rate": 0.0001954799321139975,
      "loss": 0.9904,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.1338455229997635,
      "learning_rate": 0.00019527379185764612,
      "loss": 0.6457,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.17472369968891144,
      "learning_rate": 0.00019506316889240027,
      "loss": 1.134,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.14439380168914795,
      "learning_rate": 0.00019484807312824067,
      "loss": 0.6166,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.18377861380577087,
      "learning_rate": 0.0001946285146855968,
      "loss": 0.7602,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.159800723195076,
      "learning_rate": 0.0001944045038948709,
      "loss": 0.7342,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.17464005947113037,
      "learning_rate": 0.00019417605129595157,
      "loss": 0.6698,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.16266022622585297,
      "learning_rate": 0.0001939431676377183,
      "loss": 0.6718,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.14515793323516846,
      "learning_rate": 0.0001937058638775353,
      "loss": 0.6268,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.12234693765640259,
      "learning_rate": 0.00019346415118073632,
      "loss": 1.2523,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.17767716944217682,
      "learning_rate": 0.00019321804092009906,
      "loss": 0.7257,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.16069312393665314,
      "learning_rate": 0.00019296754467531014,
      "loss": 0.6947,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.18852359056472778,
      "learning_rate": 0.00019271267423242024,
      "loss": 0.6933,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.1703113317489624,
      "learning_rate": 0.00019245344158328972,
      "loss": 0.7734,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.1587096005678177,
      "learning_rate": 0.0001921898589250242,
      "loss": 0.6607,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.15161314606666565,
      "learning_rate": 0.0001919219386594007,
      "loss": 0.7139,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.15223422646522522,
      "learning_rate": 0.00019164969339228422,
      "loss": 0.7178,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.18094822764396667,
      "learning_rate": 0.00019137313593303463,
      "loss": 0.7735,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.13845407962799072,
      "learning_rate": 0.00019109227929390378,
      "loss": 1.3756,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.15550608932971954,
      "learning_rate": 0.00019080713668942356,
      "loss": 0.6475,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.16042666137218475,
      "learning_rate": 0.00019051772153578389,
      "loss": 0.6748,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.17203615605831146,
      "learning_rate": 0.00019022404745020163,
      "loss": 0.6711,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.14476130902767181,
      "learning_rate": 0.00018992612825027976,
      "loss": 0.7195,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.18853308260440826,
      "learning_rate": 0.0001896239779533575,
      "loss": 0.8027,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1497141271829605,
      "learning_rate": 0.00018931761077585035,
      "loss": 0.6621,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.16902165114879608,
      "learning_rate": 0.00018900704113258165,
      "loss": 0.6437,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.1600257009267807,
      "learning_rate": 0.00018869228363610404,
      "loss": 0.6308,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.18659566342830658,
      "learning_rate": 0.00018837335309601213,
      "loss": 0.7028,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.14221739768981934,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.2147,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.13898412883281708,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.1227,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.16075965762138367,
      "learning_rate": 0.00018739167425092644,
      "loss": 1.1104,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.1688220500946045,
      "learning_rate": 0.00018705620354857833,
      "loss": 0.6213,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.15251010656356812,
      "learning_rate": 0.00018671663678150607,
      "loss": 0.6059,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.14779676496982574,
      "learning_rate": 0.0001863729899266004,
      "loss": 0.6402,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.16805744171142578,
      "learning_rate": 0.0001860252791527236,
      "loss": 1.0025,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.13870711624622345,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.1969,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.1410149782896042,
      "learning_rate": 0.00018531773147878895,
      "loss": 1.0952,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.16514992713928223,
      "learning_rate": 0.0001849579278694209,
      "loss": 0.6968,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.16152970492839813,
      "learning_rate": 0.00018459412692089494,
      "loss": 0.6271,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.1401905119419098,
      "learning_rate": 0.0001842263457503397,
      "loss": 0.5867,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.2006424516439438,
      "learning_rate": 0.00018385460166215638,
      "loss": 0.7979,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.17356745898723602,
      "learning_rate": 0.00018347891214720477,
      "loss": 0.6557,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.13943414390087128,
      "learning_rate": 0.00018309929488198012,
      "loss": 1.1329,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.16562946140766144,
      "learning_rate": 0.00018271576772778154,
      "loss": 0.6571,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.1551978886127472,
      "learning_rate": 0.00018232834872987147,
      "loss": 1.1503,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.1753336638212204,
      "learning_rate": 0.00018193705611662696,
      "loss": 0.7613,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.21526718139648438,
      "learning_rate": 0.0001815419082986815,
      "loss": 0.7481,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.15033215284347534,
      "learning_rate": 0.00018114292386805936,
      "loss": 1.0287,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.15260834991931915,
      "learning_rate": 0.00018074012159730032,
      "loss": 1.1275,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.14884799718856812,
      "learning_rate": 0.00018033352043857675,
      "loss": 0.9348,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.1598692387342453,
      "learning_rate": 0.00017992313952280172,
      "loss": 1.0837,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.17874813079833984,
      "learning_rate": 0.00017950899815872892,
      "loss": 1.1863,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.2233838587999344,
      "learning_rate": 0.00017909111583204422,
      "loss": 1.0691,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.2679513990879059,
      "learning_rate": 0.0001786695122044487,
      "loss": 0.8508,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.16150496900081635,
      "learning_rate": 0.0001782442071127338,
      "loss": 1.0845,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.23054973781108856,
      "learning_rate": 0.0001778152205678477,
      "loss": 1.0911,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.2072819173336029,
      "learning_rate": 0.00017738257275395404,
      "loss": 0.7793,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.18355989456176758,
      "learning_rate": 0.00017694628402748202,
      "loss": 0.6947,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.17697495222091675,
      "learning_rate": 0.0001765063749161688,
      "loss": 0.7191,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.1893756091594696,
      "learning_rate": 0.00017606286611809353,
      "loss": 0.7089,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.175858274102211,
      "learning_rate": 0.00017561577850070355,
      "loss": 0.8156,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.1497766226530075,
      "learning_rate": 0.00017516513309983253,
      "loss": 0.6113,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.2035011351108551,
      "learning_rate": 0.00017471095111871074,
      "loss": 0.7514,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.19679343700408936,
      "learning_rate": 0.0001742532539269674,
      "loss": 0.6778,
      "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": 1.535518996294533e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}