{
  "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": 0.8597566485404968,
      "learning_rate": 2e-05,
      "loss": 1.0565,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.6099331378936768,
      "learning_rate": 4e-05,
      "loss": 0.8421,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.976015031337738,
      "learning_rate": 6e-05,
      "loss": 1.1244,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.2120051383972168,
      "learning_rate": 8e-05,
      "loss": 1.4274,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.7949010133743286,
      "learning_rate": 0.0001,
      "loss": 0.9262,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.1617588996887207,
      "learning_rate": 0.00012,
      "loss": 1.3036,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.7767685055732727,
      "learning_rate": 0.00014,
      "loss": 0.8809,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.4965355098247528,
      "learning_rate": 0.00016,
      "loss": 0.8728,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.4307010769844055,
      "learning_rate": 0.00018,
      "loss": 0.7268,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.5121279358863831,
      "learning_rate": 0.0002,
      "loss": 0.9179,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.5783049464225769,
      "learning_rate": 0.0001999976474595967,
      "loss": 0.8706,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.407270610332489,
      "learning_rate": 0.00019999058994907564,
      "loss": 0.706,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.4507271647453308,
      "learning_rate": 0.00019997882780049847,
      "loss": 0.8007,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.4835984706878662,
      "learning_rate": 0.0001999623615672837,
      "loss": 0.8741,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.35001033544540405,
      "learning_rate": 0.00019994119202418098,
      "loss": 1.0107,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.34652167558670044,
      "learning_rate": 0.00019991532016723439,
      "loss": 0.7135,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.3886638581752777,
      "learning_rate": 0.00019988474721373568,
      "loss": 1.0932,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.44986358284950256,
      "learning_rate": 0.00019984947460216707,
      "loss": 0.5826,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.38238662481307983,
      "learning_rate": 0.00019980950399213344,
      "loss": 0.7045,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.2608371675014496,
      "learning_rate": 0.00019976483726428422,
      "loss": 0.5967,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.3465232253074646,
      "learning_rate": 0.0001997154765202251,
      "loss": 0.6187,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.32362625002861023,
      "learning_rate": 0.00019966142408241901,
      "loss": 0.6944,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.3342239260673523,
      "learning_rate": 0.00019960268249407675,
      "loss": 0.7556,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3412131667137146,
      "learning_rate": 0.00019953925451903756,
      "loss": 0.7405,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.44964078068733215,
      "learning_rate": 0.0001994711431416389,
      "loss": 1.3261,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.3409959077835083,
      "learning_rate": 0.00019939835156657616,
      "loss": 1.1328,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3522396981716156,
      "learning_rate": 0.00019932088321875172,
      "loss": 0.6525,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.32580652832984924,
      "learning_rate": 0.00019923874174311394,
      "loss": 0.5873,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.28162461519241333,
      "learning_rate": 0.0001991519310044857,
      "loss": 0.9859,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.3276708424091339,
      "learning_rate": 0.00019906045508738228,
      "loss": 0.8892,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.3066442906856537,
      "learning_rate": 0.0001989643182958196,
      "loss": 0.612,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3192179203033447,
      "learning_rate": 0.00019886352515311134,
      "loss": 0.6572,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.3197144567966461,
      "learning_rate": 0.0001987580804016563,
      "loss": 0.8862,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.3386269807815552,
      "learning_rate": 0.00019864798900271532,
      "loss": 0.7647,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.2944129705429077,
      "learning_rate": 0.0001985332561361776,
      "loss": 0.6034,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.2859589457511902,
      "learning_rate": 0.00019841388720031727,
      "loss": 0.5716,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.33579686284065247,
      "learning_rate": 0.00019828988781153917,
      "loss": 0.6174,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.3010195195674896,
      "learning_rate": 0.00019816126380411476,
      "loss": 0.6273,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.28635373711586,
      "learning_rate": 0.00019802802122990758,
      "loss": 0.6698,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.32364264130592346,
      "learning_rate": 0.00019789016635808837,
      "loss": 0.7271,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.27588221430778503,
      "learning_rate": 0.00019774770567484022,
      "loss": 0.8396,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.26630881428718567,
      "learning_rate": 0.00019760064588305345,
      "loss": 0.6031,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.2740603983402252,
      "learning_rate": 0.00019744899390201006,
      "loss": 0.6341,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.2932704985141754,
      "learning_rate": 0.0001972927568670583,
      "loss": 0.9879,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.3053448796272278,
      "learning_rate": 0.00019713194212927696,
      "loss": 0.7197,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.30776503682136536,
      "learning_rate": 0.00019696655725512933,
      "loss": 0.6701,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.31533047556877136,
      "learning_rate": 0.00019679661002610743,
      "loss": 0.7483,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.2600354254245758,
      "learning_rate": 0.00019662210843836574,
      "loss": 0.6361,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.29985320568084717,
      "learning_rate": 0.0001964430607023449,
      "loss": 0.6284,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.3829474449157715,
      "learning_rate": 0.00019625947524238563,
      "loss": 0.8927,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.29532748460769653,
      "learning_rate": 0.00019607136069633212,
      "loss": 0.5987,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.2676311731338501,
      "learning_rate": 0.0001958787259151258,
      "loss": 0.6036,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.34333693981170654,
      "learning_rate": 0.00019568157996238884,
      "loss": 0.5933,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2540273368358612,
      "learning_rate": 0.0001954799321139975,
      "loss": 0.8985,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.24644608795642853,
      "learning_rate": 0.00019527379185764612,
      "loss": 0.5539,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.37965652346611023,
      "learning_rate": 0.00019506316889240027,
      "loss": 1.0166,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.2802373766899109,
      "learning_rate": 0.00019484807312824067,
      "loss": 0.5285,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.3936748802661896,
      "learning_rate": 0.0001946285146855968,
      "loss": 0.6576,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.29837948083877563,
      "learning_rate": 0.0001944045038948709,
      "loss": 0.6493,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.2878054082393646,
      "learning_rate": 0.00019417605129595157,
      "loss": 0.6055,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.31146562099456787,
      "learning_rate": 0.0001939431676377183,
      "loss": 0.6076,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.26937177777290344,
      "learning_rate": 0.0001937058638775353,
      "loss": 0.5893,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.27157649397850037,
      "learning_rate": 0.00019346415118073632,
      "loss": 1.1555,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.4730302691459656,
      "learning_rate": 0.00019321804092009906,
      "loss": 0.6345,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.2813616693019867,
      "learning_rate": 0.00019296754467531014,
      "loss": 0.5973,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.3468441069126129,
      "learning_rate": 0.00019271267423242024,
      "loss": 0.6335,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.3037238121032715,
      "learning_rate": 0.00019245344158328972,
      "loss": 0.677,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.2790398597717285,
      "learning_rate": 0.0001921898589250242,
      "loss": 0.5703,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.288515567779541,
      "learning_rate": 0.0001919219386594007,
      "loss": 0.6514,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.2876873016357422,
      "learning_rate": 0.00019164969339228422,
      "loss": 0.6443,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.32371172308921814,
      "learning_rate": 0.00019137313593303463,
      "loss": 0.7022,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.2753008008003235,
      "learning_rate": 0.00019109227929390378,
      "loss": 1.2197,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.26767146587371826,
      "learning_rate": 0.00019080713668942356,
      "loss": 0.5784,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.2762153148651123,
      "learning_rate": 0.00019051772153578389,
      "loss": 0.5991,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.28386157751083374,
      "learning_rate": 0.00019022404745020163,
      "loss": 0.6117,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.24532322585582733,
      "learning_rate": 0.00018992612825027976,
      "loss": 0.6231,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.32852908968925476,
      "learning_rate": 0.0001896239779533575,
      "loss": 0.7321,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.24348995089530945,
      "learning_rate": 0.00018931761077585035,
      "loss": 0.589,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.25331753492355347,
      "learning_rate": 0.00018900704113258165,
      "loss": 0.5817,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2514454126358032,
      "learning_rate": 0.00018869228363610404,
      "loss": 0.5693,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.28637388348579407,
      "learning_rate": 0.00018837335309601213,
      "loss": 0.6363,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.2514885663986206,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.1033,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.2492385059595108,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.045,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.287953644990921,
      "learning_rate": 0.00018739167425092644,
      "loss": 1.0097,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.2525361478328705,
      "learning_rate": 0.00018705620354857833,
      "loss": 0.5465,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.2608508765697479,
      "learning_rate": 0.00018671663678150607,
      "loss": 0.5291,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.25817644596099854,
      "learning_rate": 0.0001863729899266004,
      "loss": 0.5783,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.32855451107025146,
      "learning_rate": 0.0001860252791527236,
      "loss": 0.926,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.25011545419692993,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.12,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.24932663142681122,
      "learning_rate": 0.00018531773147878895,
      "loss": 0.9743,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.2763610780239105,
      "learning_rate": 0.0001849579278694209,
      "loss": 0.6299,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.27096471190452576,
      "learning_rate": 0.00018459412692089494,
      "loss": 0.5782,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.246726855635643,
      "learning_rate": 0.0001842263457503397,
      "loss": 0.5432,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.3436436951160431,
      "learning_rate": 0.00018385460166215638,
      "loss": 0.7304,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.31473803520202637,
      "learning_rate": 0.00018347891214720477,
      "loss": 0.5874,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.23026835918426514,
      "learning_rate": 0.00018309929488198012,
      "loss": 1.0413,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.2863934338092804,
      "learning_rate": 0.00018271576772778154,
      "loss": 0.5917,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.2771088182926178,
      "learning_rate": 0.00018232834872987147,
      "loss": 1.089,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.33394113183021545,
      "learning_rate": 0.00018193705611662696,
      "loss": 0.6941,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.3389004170894623,
      "learning_rate": 0.0001815419082986815,
      "loss": 0.6486,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.2511347830295563,
      "learning_rate": 0.00018114292386805936,
      "loss": 0.952,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.28700685501098633,
      "learning_rate": 0.00018074012159730032,
      "loss": 0.9952,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.2681572437286377,
      "learning_rate": 0.00018033352043857675,
      "loss": 0.8697,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.28524017333984375,
      "learning_rate": 0.00017992313952280172,
      "loss": 0.9502,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.28100305795669556,
      "learning_rate": 0.00017950899815872892,
      "loss": 1.0808,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.37970542907714844,
      "learning_rate": 0.00017909111583204422,
      "loss": 0.9715,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.4127101004123688,
      "learning_rate": 0.0001786695122044487,
      "loss": 0.7508,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3084346354007721,
      "learning_rate": 0.0001782442071127338,
      "loss": 0.9778,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.4070857763290405,
      "learning_rate": 0.0001778152205678477,
      "loss": 1.0079,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.35972508788108826,
      "learning_rate": 0.00017738257275395404,
      "loss": 0.6978,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.3087528347969055,
      "learning_rate": 0.00017694628402748202,
      "loss": 0.6223,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.30665698647499084,
      "learning_rate": 0.0001765063749161688,
      "loss": 0.6312,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.3046605587005615,
      "learning_rate": 0.00017606286611809353,
      "loss": 0.6267,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.30426326394081116,
      "learning_rate": 0.00017561577850070355,
      "loss": 0.7445,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.23966537415981293,
      "learning_rate": 0.00017516513309983253,
      "loss": 0.526,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.3334603011608124,
      "learning_rate": 0.00017471095111871074,
      "loss": 0.6664,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2775772511959076,
      "learning_rate": 0.0001742532539269674,
      "loss": 0.5718,
      "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
}