{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01987918725974739,
  "eval_steps": 500,
  "global_step": 181,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010982976386600769,
      "grad_norm": 18.411802291870117,
      "learning_rate": 0.0,
      "loss": 0.3251,
      "step": 1
    },
    {
      "epoch": 0.00021965952773201537,
      "grad_norm": 14.977940559387207,
      "learning_rate": 5.2631578947368416e-08,
      "loss": 0.3606,
      "step": 2
    },
    {
      "epoch": 0.00032948929159802305,
      "grad_norm": 14.84136962890625,
      "learning_rate": 1.0526315789473683e-07,
      "loss": 0.2777,
      "step": 3
    },
    {
      "epoch": 0.00043931905546403075,
      "grad_norm": 15.656201362609863,
      "learning_rate": 1.5789473684210525e-07,
      "loss": 0.293,
      "step": 4
    },
    {
      "epoch": 0.0005491488193300384,
      "grad_norm": 11.50175666809082,
      "learning_rate": 2.1052631578947366e-07,
      "loss": 0.271,
      "step": 5
    },
    {
      "epoch": 0.0006589785831960461,
      "grad_norm": 13.30196762084961,
      "learning_rate": 2.631578947368421e-07,
      "loss": 0.3014,
      "step": 6
    },
    {
      "epoch": 0.0007688083470620538,
      "grad_norm": 18.187772750854492,
      "learning_rate": 3.157894736842105e-07,
      "loss": 0.2838,
      "step": 7
    },
    {
      "epoch": 0.0008786381109280615,
      "grad_norm": 12.342240333557129,
      "learning_rate": 3.684210526315789e-07,
      "loss": 0.2961,
      "step": 8
    },
    {
      "epoch": 0.0009884678747940692,
      "grad_norm": 12.453307151794434,
      "learning_rate": 4.2105263157894733e-07,
      "loss": 0.2727,
      "step": 9
    },
    {
      "epoch": 0.001098297638660077,
      "grad_norm": 13.236316680908203,
      "learning_rate": 4.7368421052631574e-07,
      "loss": 0.2777,
      "step": 10
    },
    {
      "epoch": 0.0012081274025260845,
      "grad_norm": 9.186564445495605,
      "learning_rate": 5.263157894736842e-07,
      "loss": 0.2362,
      "step": 11
    },
    {
      "epoch": 0.0013179571663920922,
      "grad_norm": 14.68601131439209,
      "learning_rate": 5.789473684210526e-07,
      "loss": 0.3246,
      "step": 12
    },
    {
      "epoch": 0.0014277869302581,
      "grad_norm": 12.118836402893066,
      "learning_rate": 6.31578947368421e-07,
      "loss": 0.2334,
      "step": 13
    },
    {
      "epoch": 0.0015376166941241077,
      "grad_norm": 9.764254570007324,
      "learning_rate": 6.842105263157895e-07,
      "loss": 0.2382,
      "step": 14
    },
    {
      "epoch": 0.0016474464579901153,
      "grad_norm": 7.129339694976807,
      "learning_rate": 7.368421052631578e-07,
      "loss": 0.2399,
      "step": 15
    },
    {
      "epoch": 0.001757276221856123,
      "grad_norm": 6.999264717102051,
      "learning_rate": 7.894736842105263e-07,
      "loss": 0.1915,
      "step": 16
    },
    {
      "epoch": 0.0018671059857221306,
      "grad_norm": 6.912661075592041,
      "learning_rate": 8.421052631578947e-07,
      "loss": 0.1996,
      "step": 17
    },
    {
      "epoch": 0.0019769357495881385,
      "grad_norm": 6.077408313751221,
      "learning_rate": 8.947368421052631e-07,
      "loss": 0.1915,
      "step": 18
    },
    {
      "epoch": 0.002086765513454146,
      "grad_norm": 4.185582160949707,
      "learning_rate": 9.473684210526315e-07,
      "loss": 0.176,
      "step": 19
    },
    {
      "epoch": 0.002196595277320154,
      "grad_norm": 2.6936287879943848,
      "learning_rate": 1e-06,
      "loss": 0.1309,
      "step": 20
    },
    {
      "epoch": 0.0023064250411861617,
      "grad_norm": 3.5675835609436035,
      "learning_rate": 1e-06,
      "loss": 0.1515,
      "step": 21
    },
    {
      "epoch": 0.002416254805052169,
      "grad_norm": 2.7305240631103516,
      "learning_rate": 1e-06,
      "loss": 0.132,
      "step": 22
    },
    {
      "epoch": 0.002526084568918177,
      "grad_norm": 2.0667977333068848,
      "learning_rate": 1e-06,
      "loss": 0.107,
      "step": 23
    },
    {
      "epoch": 0.0026359143327841844,
      "grad_norm": 2.3355114459991455,
      "learning_rate": 1e-06,
      "loss": 0.1252,
      "step": 24
    },
    {
      "epoch": 0.0027457440966501922,
      "grad_norm": 2.30021333694458,
      "learning_rate": 1e-06,
      "loss": 0.1262,
      "step": 25
    },
    {
      "epoch": 0.0028555738605162,
      "grad_norm": 2.639949083328247,
      "learning_rate": 1e-06,
      "loss": 0.1611,
      "step": 26
    },
    {
      "epoch": 0.0029654036243822075,
      "grad_norm": 2.6157100200653076,
      "learning_rate": 1e-06,
      "loss": 0.1133,
      "step": 27
    },
    {
      "epoch": 0.0030752333882482154,
      "grad_norm": 2.25714373588562,
      "learning_rate": 1e-06,
      "loss": 0.1175,
      "step": 28
    },
    {
      "epoch": 0.003185063152114223,
      "grad_norm": 2.413874864578247,
      "learning_rate": 1e-06,
      "loss": 0.1335,
      "step": 29
    },
    {
      "epoch": 0.0032948929159802307,
      "grad_norm": 2.9752049446105957,
      "learning_rate": 1e-06,
      "loss": 0.1549,
      "step": 30
    },
    {
      "epoch": 0.003404722679846238,
      "grad_norm": 2.191883087158203,
      "learning_rate": 1e-06,
      "loss": 0.1072,
      "step": 31
    },
    {
      "epoch": 0.003514552443712246,
      "grad_norm": 2.182326078414917,
      "learning_rate": 1e-06,
      "loss": 0.1322,
      "step": 32
    },
    {
      "epoch": 0.003624382207578254,
      "grad_norm": 2.0499420166015625,
      "learning_rate": 1e-06,
      "loss": 0.1252,
      "step": 33
    },
    {
      "epoch": 0.0037342119714442613,
      "grad_norm": 2.898209571838379,
      "learning_rate": 1e-06,
      "loss": 0.1564,
      "step": 34
    },
    {
      "epoch": 0.003844041735310269,
      "grad_norm": 2.6807024478912354,
      "learning_rate": 1e-06,
      "loss": 0.1215,
      "step": 35
    },
    {
      "epoch": 0.003953871499176277,
      "grad_norm": 2.6628167629241943,
      "learning_rate": 1e-06,
      "loss": 0.125,
      "step": 36
    },
    {
      "epoch": 0.004063701263042284,
      "grad_norm": 2.3685622215270996,
      "learning_rate": 1e-06,
      "loss": 0.1423,
      "step": 37
    },
    {
      "epoch": 0.004173531026908292,
      "grad_norm": 2.0525412559509277,
      "learning_rate": 1e-06,
      "loss": 0.1321,
      "step": 38
    },
    {
      "epoch": 0.0042833607907743,
      "grad_norm": 2.064305305480957,
      "learning_rate": 1e-06,
      "loss": 0.1139,
      "step": 39
    },
    {
      "epoch": 0.004393190554640308,
      "grad_norm": 2.255208969116211,
      "learning_rate": 1e-06,
      "loss": 0.1075,
      "step": 40
    },
    {
      "epoch": 0.004503020318506315,
      "grad_norm": 2.1674306392669678,
      "learning_rate": 1e-06,
      "loss": 0.1231,
      "step": 41
    },
    {
      "epoch": 0.004612850082372323,
      "grad_norm": 2.1255414485931396,
      "learning_rate": 1e-06,
      "loss": 0.149,
      "step": 42
    },
    {
      "epoch": 0.004722679846238331,
      "grad_norm": 1.9542911052703857,
      "learning_rate": 1e-06,
      "loss": 0.1406,
      "step": 43
    },
    {
      "epoch": 0.004832509610104338,
      "grad_norm": 2.3152379989624023,
      "learning_rate": 1e-06,
      "loss": 0.122,
      "step": 44
    },
    {
      "epoch": 0.004942339373970346,
      "grad_norm": 2.2259297370910645,
      "learning_rate": 1e-06,
      "loss": 0.1273,
      "step": 45
    },
    {
      "epoch": 0.005052169137836354,
      "grad_norm": 2.1162829399108887,
      "learning_rate": 1e-06,
      "loss": 0.1071,
      "step": 46
    },
    {
      "epoch": 0.005161998901702361,
      "grad_norm": 2.2870123386383057,
      "learning_rate": 1e-06,
      "loss": 0.1222,
      "step": 47
    },
    {
      "epoch": 0.005271828665568369,
      "grad_norm": 2.1178293228149414,
      "learning_rate": 1e-06,
      "loss": 0.1128,
      "step": 48
    },
    {
      "epoch": 0.005381658429434377,
      "grad_norm": 2.811563730239868,
      "learning_rate": 1e-06,
      "loss": 0.113,
      "step": 49
    },
    {
      "epoch": 0.0054914881933003845,
      "grad_norm": 1.9846251010894775,
      "learning_rate": 1e-06,
      "loss": 0.1083,
      "step": 50
    },
    {
      "epoch": 0.005601317957166392,
      "grad_norm": 4.522186279296875,
      "learning_rate": 1e-06,
      "loss": 0.1283,
      "step": 51
    },
    {
      "epoch": 0.0057111477210324,
      "grad_norm": 1.9514762163162231,
      "learning_rate": 1e-06,
      "loss": 0.117,
      "step": 52
    },
    {
      "epoch": 0.005820977484898408,
      "grad_norm": 1.644494652748108,
      "learning_rate": 1e-06,
      "loss": 0.1097,
      "step": 53
    },
    {
      "epoch": 0.005930807248764415,
      "grad_norm": 2.26704740524292,
      "learning_rate": 1e-06,
      "loss": 0.0996,
      "step": 54
    },
    {
      "epoch": 0.0060406370126304225,
      "grad_norm": 1.8278131484985352,
      "learning_rate": 1e-06,
      "loss": 0.1175,
      "step": 55
    },
    {
      "epoch": 0.006150466776496431,
      "grad_norm": 2.9004828929901123,
      "learning_rate": 1e-06,
      "loss": 0.118,
      "step": 56
    },
    {
      "epoch": 0.006260296540362438,
      "grad_norm": 2.1837573051452637,
      "learning_rate": 1e-06,
      "loss": 0.1052,
      "step": 57
    },
    {
      "epoch": 0.006370126304228446,
      "grad_norm": 2.207904577255249,
      "learning_rate": 1e-06,
      "loss": 0.1057,
      "step": 58
    },
    {
      "epoch": 0.006479956068094454,
      "grad_norm": 1.937738060951233,
      "learning_rate": 1e-06,
      "loss": 0.1377,
      "step": 59
    },
    {
      "epoch": 0.006589785831960461,
      "grad_norm": 1.8323129415512085,
      "learning_rate": 1e-06,
      "loss": 0.0962,
      "step": 60
    },
    {
      "epoch": 0.006699615595826469,
      "grad_norm": 1.9134773015975952,
      "learning_rate": 1e-06,
      "loss": 0.0991,
      "step": 61
    },
    {
      "epoch": 0.006809445359692476,
      "grad_norm": 2.54829478263855,
      "learning_rate": 1e-06,
      "loss": 0.1199,
      "step": 62
    },
    {
      "epoch": 0.0069192751235584845,
      "grad_norm": 2.0665552616119385,
      "learning_rate": 1e-06,
      "loss": 0.1242,
      "step": 63
    },
    {
      "epoch": 0.007029104887424492,
      "grad_norm": 1.9088149070739746,
      "learning_rate": 1e-06,
      "loss": 0.1187,
      "step": 64
    },
    {
      "epoch": 0.007138934651290499,
      "grad_norm": 1.6347726583480835,
      "learning_rate": 1e-06,
      "loss": 0.1087,
      "step": 65
    },
    {
      "epoch": 0.007248764415156508,
      "grad_norm": 1.8846579790115356,
      "learning_rate": 1e-06,
      "loss": 0.115,
      "step": 66
    },
    {
      "epoch": 0.007358594179022515,
      "grad_norm": 2.108840227127075,
      "learning_rate": 1e-06,
      "loss": 0.1296,
      "step": 67
    },
    {
      "epoch": 0.0074684239428885225,
      "grad_norm": 2.0860307216644287,
      "learning_rate": 1e-06,
      "loss": 0.1088,
      "step": 68
    },
    {
      "epoch": 0.007578253706754531,
      "grad_norm": 2.0085508823394775,
      "learning_rate": 1e-06,
      "loss": 0.1208,
      "step": 69
    },
    {
      "epoch": 0.007688083470620538,
      "grad_norm": 1.8251607418060303,
      "learning_rate": 1e-06,
      "loss": 0.1112,
      "step": 70
    },
    {
      "epoch": 0.007797913234486546,
      "grad_norm": 1.9405887126922607,
      "learning_rate": 1e-06,
      "loss": 0.1014,
      "step": 71
    },
    {
      "epoch": 0.007907742998352554,
      "grad_norm": 2.248020887374878,
      "learning_rate": 1e-06,
      "loss": 0.107,
      "step": 72
    },
    {
      "epoch": 0.008017572762218561,
      "grad_norm": 1.9570263624191284,
      "learning_rate": 1e-06,
      "loss": 0.1071,
      "step": 73
    },
    {
      "epoch": 0.008127402526084569,
      "grad_norm": 2.1239218711853027,
      "learning_rate": 1e-06,
      "loss": 0.133,
      "step": 74
    },
    {
      "epoch": 0.008237232289950576,
      "grad_norm": 1.7767431735992432,
      "learning_rate": 1e-06,
      "loss": 0.102,
      "step": 75
    },
    {
      "epoch": 0.008347062053816584,
      "grad_norm": 2.4217135906219482,
      "learning_rate": 1e-06,
      "loss": 0.1004,
      "step": 76
    },
    {
      "epoch": 0.008456891817682591,
      "grad_norm": 1.89665687084198,
      "learning_rate": 1e-06,
      "loss": 0.1241,
      "step": 77
    },
    {
      "epoch": 0.0085667215815486,
      "grad_norm": 1.431766152381897,
      "learning_rate": 1e-06,
      "loss": 0.0849,
      "step": 78
    },
    {
      "epoch": 0.008676551345414608,
      "grad_norm": 2.6968767642974854,
      "learning_rate": 1e-06,
      "loss": 0.1129,
      "step": 79
    },
    {
      "epoch": 0.008786381109280615,
      "grad_norm": 1.8317389488220215,
      "learning_rate": 1e-06,
      "loss": 0.1033,
      "step": 80
    },
    {
      "epoch": 0.008896210873146623,
      "grad_norm": 2.0611159801483154,
      "learning_rate": 1e-06,
      "loss": 0.1075,
      "step": 81
    },
    {
      "epoch": 0.00900604063701263,
      "grad_norm": 2.4678268432617188,
      "learning_rate": 1e-06,
      "loss": 0.0914,
      "step": 82
    },
    {
      "epoch": 0.009115870400878637,
      "grad_norm": 2.097642183303833,
      "learning_rate": 1e-06,
      "loss": 0.1033,
      "step": 83
    },
    {
      "epoch": 0.009225700164744647,
      "grad_norm": 1.9599785804748535,
      "learning_rate": 1e-06,
      "loss": 0.1063,
      "step": 84
    },
    {
      "epoch": 0.009335529928610654,
      "grad_norm": 1.938198447227478,
      "learning_rate": 1e-06,
      "loss": 0.0968,
      "step": 85
    },
    {
      "epoch": 0.009445359692476661,
      "grad_norm": 2.0601954460144043,
      "learning_rate": 1e-06,
      "loss": 0.1077,
      "step": 86
    },
    {
      "epoch": 0.009555189456342669,
      "grad_norm": 1.9235936403274536,
      "learning_rate": 1e-06,
      "loss": 0.1218,
      "step": 87
    },
    {
      "epoch": 0.009665019220208676,
      "grad_norm": 1.6672967672348022,
      "learning_rate": 1e-06,
      "loss": 0.0982,
      "step": 88
    },
    {
      "epoch": 0.009774848984074684,
      "grad_norm": 1.9302681684494019,
      "learning_rate": 1e-06,
      "loss": 0.1124,
      "step": 89
    },
    {
      "epoch": 0.009884678747940691,
      "grad_norm": 2.2827959060668945,
      "learning_rate": 1e-06,
      "loss": 0.1178,
      "step": 90
    },
    {
      "epoch": 0.0099945085118067,
      "grad_norm": 1.8714021444320679,
      "learning_rate": 1e-06,
      "loss": 0.0984,
      "step": 91
    },
    {
      "epoch": 0.010104338275672708,
      "grad_norm": 2.1995835304260254,
      "learning_rate": 1e-06,
      "loss": 0.1319,
      "step": 92
    },
    {
      "epoch": 0.010214168039538715,
      "grad_norm": 1.92769455909729,
      "learning_rate": 1e-06,
      "loss": 0.1026,
      "step": 93
    },
    {
      "epoch": 0.010323997803404723,
      "grad_norm": 1.9699769020080566,
      "learning_rate": 1e-06,
      "loss": 0.1189,
      "step": 94
    },
    {
      "epoch": 0.01043382756727073,
      "grad_norm": 2.7029881477355957,
      "learning_rate": 1e-06,
      "loss": 0.1282,
      "step": 95
    },
    {
      "epoch": 0.010543657331136738,
      "grad_norm": 1.6077944040298462,
      "learning_rate": 1e-06,
      "loss": 0.1096,
      "step": 96
    },
    {
      "epoch": 0.010653487095002745,
      "grad_norm": 2.0745413303375244,
      "learning_rate": 1e-06,
      "loss": 0.1154,
      "step": 97
    },
    {
      "epoch": 0.010763316858868754,
      "grad_norm": 1.8612251281738281,
      "learning_rate": 1e-06,
      "loss": 0.1014,
      "step": 98
    },
    {
      "epoch": 0.010873146622734762,
      "grad_norm": 1.8795632123947144,
      "learning_rate": 1e-06,
      "loss": 0.1029,
      "step": 99
    },
    {
      "epoch": 0.010982976386600769,
      "grad_norm": 1.8857154846191406,
      "learning_rate": 1e-06,
      "loss": 0.1014,
      "step": 100
    },
    {
      "epoch": 0.011092806150466776,
      "grad_norm": 1.87457275390625,
      "learning_rate": 1e-06,
      "loss": 0.1047,
      "step": 101
    },
    {
      "epoch": 0.011202635914332784,
      "grad_norm": 2.02274489402771,
      "learning_rate": 1e-06,
      "loss": 0.117,
      "step": 102
    },
    {
      "epoch": 0.011312465678198791,
      "grad_norm": 2.1100752353668213,
      "learning_rate": 1e-06,
      "loss": 0.1116,
      "step": 103
    },
    {
      "epoch": 0.0114222954420648,
      "grad_norm": 2.1528773307800293,
      "learning_rate": 1e-06,
      "loss": 0.1147,
      "step": 104
    },
    {
      "epoch": 0.011532125205930808,
      "grad_norm": 5.85520076751709,
      "learning_rate": 1e-06,
      "loss": 0.1089,
      "step": 105
    },
    {
      "epoch": 0.011641954969796815,
      "grad_norm": 2.007204532623291,
      "learning_rate": 1e-06,
      "loss": 0.1244,
      "step": 106
    },
    {
      "epoch": 0.011751784733662823,
      "grad_norm": 1.9761431217193604,
      "learning_rate": 1e-06,
      "loss": 0.104,
      "step": 107
    },
    {
      "epoch": 0.01186161449752883,
      "grad_norm": 1.6352622509002686,
      "learning_rate": 1e-06,
      "loss": 0.1098,
      "step": 108
    },
    {
      "epoch": 0.011971444261394838,
      "grad_norm": 1.898520588874817,
      "learning_rate": 1e-06,
      "loss": 0.1122,
      "step": 109
    },
    {
      "epoch": 0.012081274025260845,
      "grad_norm": 1.6044663190841675,
      "learning_rate": 1e-06,
      "loss": 0.1044,
      "step": 110
    },
    {
      "epoch": 0.012191103789126854,
      "grad_norm": 1.7996292114257812,
      "learning_rate": 1e-06,
      "loss": 0.1107,
      "step": 111
    },
    {
      "epoch": 0.012300933552992862,
      "grad_norm": 1.949839472770691,
      "learning_rate": 1e-06,
      "loss": 0.1345,
      "step": 112
    },
    {
      "epoch": 0.012410763316858869,
      "grad_norm": 1.7750391960144043,
      "learning_rate": 1e-06,
      "loss": 0.1023,
      "step": 113
    },
    {
      "epoch": 0.012520593080724876,
      "grad_norm": 1.8512459993362427,
      "learning_rate": 1e-06,
      "loss": 0.0921,
      "step": 114
    },
    {
      "epoch": 0.012630422844590884,
      "grad_norm": 1.8420369625091553,
      "learning_rate": 1e-06,
      "loss": 0.0949,
      "step": 115
    },
    {
      "epoch": 0.012740252608456891,
      "grad_norm": 1.885312795639038,
      "learning_rate": 1e-06,
      "loss": 0.1118,
      "step": 116
    },
    {
      "epoch": 0.012850082372322899,
      "grad_norm": 2.293736457824707,
      "learning_rate": 1e-06,
      "loss": 0.1227,
      "step": 117
    },
    {
      "epoch": 0.012959912136188908,
      "grad_norm": 1.9772549867630005,
      "learning_rate": 1e-06,
      "loss": 0.1212,
      "step": 118
    },
    {
      "epoch": 0.013069741900054915,
      "grad_norm": 2.280238151550293,
      "learning_rate": 1e-06,
      "loss": 0.1192,
      "step": 119
    },
    {
      "epoch": 0.013179571663920923,
      "grad_norm": 1.9888858795166016,
      "learning_rate": 1e-06,
      "loss": 0.1027,
      "step": 120
    },
    {
      "epoch": 0.01328940142778693,
      "grad_norm": 1.5730584859848022,
      "learning_rate": 1e-06,
      "loss": 0.0913,
      "step": 121
    },
    {
      "epoch": 0.013399231191652938,
      "grad_norm": 1.7493692636489868,
      "learning_rate": 1e-06,
      "loss": 0.097,
      "step": 122
    },
    {
      "epoch": 0.013509060955518945,
      "grad_norm": 2.1915624141693115,
      "learning_rate": 1e-06,
      "loss": 0.1217,
      "step": 123
    },
    {
      "epoch": 0.013618890719384952,
      "grad_norm": 2.0627121925354004,
      "learning_rate": 1e-06,
      "loss": 0.1138,
      "step": 124
    },
    {
      "epoch": 0.013728720483250962,
      "grad_norm": 1.8700608015060425,
      "learning_rate": 1e-06,
      "loss": 0.0957,
      "step": 125
    },
    {
      "epoch": 0.013838550247116969,
      "grad_norm": 4.867977142333984,
      "learning_rate": 1e-06,
      "loss": 0.1143,
      "step": 126
    },
    {
      "epoch": 0.013948380010982976,
      "grad_norm": 1.6484566926956177,
      "learning_rate": 1e-06,
      "loss": 0.0883,
      "step": 127
    },
    {
      "epoch": 0.014058209774848984,
      "grad_norm": 1.7756706476211548,
      "learning_rate": 1e-06,
      "loss": 0.0992,
      "step": 128
    },
    {
      "epoch": 0.014168039538714991,
      "grad_norm": 23.05768394470215,
      "learning_rate": 1e-06,
      "loss": 0.0779,
      "step": 129
    },
    {
      "epoch": 0.014277869302580999,
      "grad_norm": 1.8049583435058594,
      "learning_rate": 1e-06,
      "loss": 0.1014,
      "step": 130
    },
    {
      "epoch": 0.014387699066447008,
      "grad_norm": 1.9289432764053345,
      "learning_rate": 1e-06,
      "loss": 0.0958,
      "step": 131
    },
    {
      "epoch": 0.014497528830313015,
      "grad_norm": 1.9363269805908203,
      "learning_rate": 1e-06,
      "loss": 0.1306,
      "step": 132
    },
    {
      "epoch": 0.014607358594179023,
      "grad_norm": 1.7127413749694824,
      "learning_rate": 1e-06,
      "loss": 0.1015,
      "step": 133
    },
    {
      "epoch": 0.01471718835804503,
      "grad_norm": 2.036144733428955,
      "learning_rate": 1e-06,
      "loss": 0.1002,
      "step": 134
    },
    {
      "epoch": 0.014827018121911038,
      "grad_norm": 2.464301347732544,
      "learning_rate": 1e-06,
      "loss": 0.1119,
      "step": 135
    },
    {
      "epoch": 0.014936847885777045,
      "grad_norm": 1.9304972887039185,
      "learning_rate": 1e-06,
      "loss": 0.1148,
      "step": 136
    },
    {
      "epoch": 0.015046677649643053,
      "grad_norm": 1.6702697277069092,
      "learning_rate": 1e-06,
      "loss": 0.1113,
      "step": 137
    },
    {
      "epoch": 0.015156507413509062,
      "grad_norm": 1.804840326309204,
      "learning_rate": 1e-06,
      "loss": 0.0956,
      "step": 138
    },
    {
      "epoch": 0.015266337177375069,
      "grad_norm": 1.7338131666183472,
      "learning_rate": 1e-06,
      "loss": 0.107,
      "step": 139
    },
    {
      "epoch": 0.015376166941241077,
      "grad_norm": 1.8909966945648193,
      "learning_rate": 1e-06,
      "loss": 0.093,
      "step": 140
    },
    {
      "epoch": 0.015485996705107084,
      "grad_norm": 1.957493543624878,
      "learning_rate": 1e-06,
      "loss": 0.0968,
      "step": 141
    },
    {
      "epoch": 0.015595826468973091,
      "grad_norm": 2.450575590133667,
      "learning_rate": 1e-06,
      "loss": 0.1133,
      "step": 142
    },
    {
      "epoch": 0.0157056562328391,
      "grad_norm": 2.1446874141693115,
      "learning_rate": 1e-06,
      "loss": 0.1388,
      "step": 143
    },
    {
      "epoch": 0.015815485996705108,
      "grad_norm": 2.1485435962677,
      "learning_rate": 1e-06,
      "loss": 0.1315,
      "step": 144
    },
    {
      "epoch": 0.015925315760571115,
      "grad_norm": 2.152599573135376,
      "learning_rate": 1e-06,
      "loss": 0.1326,
      "step": 145
    },
    {
      "epoch": 0.016035145524437123,
      "grad_norm": 1.9794915914535522,
      "learning_rate": 1e-06,
      "loss": 0.1277,
      "step": 146
    },
    {
      "epoch": 0.01614497528830313,
      "grad_norm": 1.7658240795135498,
      "learning_rate": 1e-06,
      "loss": 0.1031,
      "step": 147
    },
    {
      "epoch": 0.016254805052169138,
      "grad_norm": 1.8528263568878174,
      "learning_rate": 1e-06,
      "loss": 0.0952,
      "step": 148
    },
    {
      "epoch": 0.016364634816035145,
      "grad_norm": 1.5647423267364502,
      "learning_rate": 1e-06,
      "loss": 0.1088,
      "step": 149
    },
    {
      "epoch": 0.016474464579901153,
      "grad_norm": 2.419384717941284,
      "learning_rate": 1e-06,
      "loss": 0.0967,
      "step": 150
    },
    {
      "epoch": 0.01658429434376716,
      "grad_norm": 1.5838412046432495,
      "learning_rate": 1e-06,
      "loss": 0.0839,
      "step": 151
    },
    {
      "epoch": 0.016694124107633167,
      "grad_norm": 2.1404707431793213,
      "learning_rate": 1e-06,
      "loss": 0.1142,
      "step": 152
    },
    {
      "epoch": 0.016803953871499175,
      "grad_norm": 1.6462748050689697,
      "learning_rate": 1e-06,
      "loss": 0.0947,
      "step": 153
    },
    {
      "epoch": 0.016913783635365182,
      "grad_norm": 2.057058811187744,
      "learning_rate": 1e-06,
      "loss": 0.1123,
      "step": 154
    },
    {
      "epoch": 0.017023613399231193,
      "grad_norm": 1.7520567178726196,
      "learning_rate": 1e-06,
      "loss": 0.1008,
      "step": 155
    },
    {
      "epoch": 0.0171334431630972,
      "grad_norm": 2.039196014404297,
      "learning_rate": 1e-06,
      "loss": 0.1322,
      "step": 156
    },
    {
      "epoch": 0.017243272926963208,
      "grad_norm": 1.8729941844940186,
      "learning_rate": 1e-06,
      "loss": 0.102,
      "step": 157
    },
    {
      "epoch": 0.017353102690829215,
      "grad_norm": 1.9198112487792969,
      "learning_rate": 1e-06,
      "loss": 0.1141,
      "step": 158
    },
    {
      "epoch": 0.017462932454695223,
      "grad_norm": 1.690664529800415,
      "learning_rate": 1e-06,
      "loss": 0.0938,
      "step": 159
    },
    {
      "epoch": 0.01757276221856123,
      "grad_norm": 2.284759044647217,
      "learning_rate": 1e-06,
      "loss": 0.1171,
      "step": 160
    },
    {
      "epoch": 0.017682591982427238,
      "grad_norm": 1.7743721008300781,
      "learning_rate": 1e-06,
      "loss": 0.0976,
      "step": 161
    },
    {
      "epoch": 0.017792421746293245,
      "grad_norm": 2.1249804496765137,
      "learning_rate": 1e-06,
      "loss": 0.0904,
      "step": 162
    },
    {
      "epoch": 0.017902251510159253,
      "grad_norm": 3.607625722885132,
      "learning_rate": 1e-06,
      "loss": 0.1277,
      "step": 163
    },
    {
      "epoch": 0.01801208127402526,
      "grad_norm": 1.950108289718628,
      "learning_rate": 1e-06,
      "loss": 0.1016,
      "step": 164
    },
    {
      "epoch": 0.018121911037891267,
      "grad_norm": 1.6242471933364868,
      "learning_rate": 1e-06,
      "loss": 0.0919,
      "step": 165
    },
    {
      "epoch": 0.018231740801757275,
      "grad_norm": 2.4311513900756836,
      "learning_rate": 1e-06,
      "loss": 0.1112,
      "step": 166
    },
    {
      "epoch": 0.018341570565623282,
      "grad_norm": 1.5507546663284302,
      "learning_rate": 1e-06,
      "loss": 0.0981,
      "step": 167
    },
    {
      "epoch": 0.018451400329489293,
      "grad_norm": 1.9630911350250244,
      "learning_rate": 1e-06,
      "loss": 0.1087,
      "step": 168
    },
    {
      "epoch": 0.0185612300933553,
      "grad_norm": 1.6163691282272339,
      "learning_rate": 1e-06,
      "loss": 0.092,
      "step": 169
    },
    {
      "epoch": 0.018671059857221308,
      "grad_norm": 1.647873878479004,
      "learning_rate": 1e-06,
      "loss": 0.0867,
      "step": 170
    },
    {
      "epoch": 0.018780889621087316,
      "grad_norm": 2.0003228187561035,
      "learning_rate": 1e-06,
      "loss": 0.1166,
      "step": 171
    },
    {
      "epoch": 0.018890719384953323,
      "grad_norm": 2.019808053970337,
      "learning_rate": 1e-06,
      "loss": 0.1139,
      "step": 172
    },
    {
      "epoch": 0.01900054914881933,
      "grad_norm": 1.6541454792022705,
      "learning_rate": 1e-06,
      "loss": 0.0857,
      "step": 173
    },
    {
      "epoch": 0.019110378912685338,
      "grad_norm": 2.194434642791748,
      "learning_rate": 1e-06,
      "loss": 0.0919,
      "step": 174
    },
    {
      "epoch": 0.019220208676551345,
      "grad_norm": 2.8449411392211914,
      "learning_rate": 1e-06,
      "loss": 0.113,
      "step": 175
    },
    {
      "epoch": 0.019330038440417353,
      "grad_norm": 2.208855152130127,
      "learning_rate": 1e-06,
      "loss": 0.0964,
      "step": 176
    },
    {
      "epoch": 0.01943986820428336,
      "grad_norm": 1.9803837537765503,
      "learning_rate": 1e-06,
      "loss": 0.0968,
      "step": 177
    },
    {
      "epoch": 0.019549697968149368,
      "grad_norm": 1.8835409879684448,
      "learning_rate": 1e-06,
      "loss": 0.1059,
      "step": 178
    },
    {
      "epoch": 0.019659527732015375,
      "grad_norm": 2.523775339126587,
      "learning_rate": 1e-06,
      "loss": 0.1217,
      "step": 179
    },
    {
      "epoch": 0.019769357495881382,
      "grad_norm": 2.160933494567871,
      "learning_rate": 1e-06,
      "loss": 0.0974,
      "step": 180
    },
    {
      "epoch": 0.01987918725974739,
      "grad_norm": 1.6890003681182861,
      "learning_rate": 1e-06,
      "loss": 0.0856,
      "step": 181
    },
    {
      "epoch": 0.01987918725974739,
      "step": 181,
      "total_flos": 0.0,
      "train_loss": 0.05325274675755211,
      "train_runtime": 2257.3022,
      "train_samples_per_second": 1.283,
      "train_steps_per_second": 0.08
    }
  ],
  "logging_steps": 1,
  "max_steps": 181,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 91,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}