{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07501875468867217,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007501875468867217,
      "grad_norm": 1.3280349969863892,
      "learning_rate": 1e-05,
      "loss": 2.2383,
      "step": 1
    },
    {
      "epoch": 0.0007501875468867217,
      "eval_loss": 2.0136821269989014,
      "eval_runtime": 103.2644,
      "eval_samples_per_second": 43.481,
      "eval_steps_per_second": 1.365,
      "step": 1
    },
    {
      "epoch": 0.0015003750937734434,
      "grad_norm": 0.8275195360183716,
      "learning_rate": 2e-05,
      "loss": 1.5301,
      "step": 2
    },
    {
      "epoch": 0.002250562640660165,
      "grad_norm": 0.9605063796043396,
      "learning_rate": 3e-05,
      "loss": 2.1497,
      "step": 3
    },
    {
      "epoch": 0.003000750187546887,
      "grad_norm": 1.0736336708068848,
      "learning_rate": 4e-05,
      "loss": 1.9107,
      "step": 4
    },
    {
      "epoch": 0.0037509377344336083,
      "grad_norm": 1.2186498641967773,
      "learning_rate": 5e-05,
      "loss": 1.9314,
      "step": 5
    },
    {
      "epoch": 0.00450112528132033,
      "grad_norm": 1.3287383317947388,
      "learning_rate": 6e-05,
      "loss": 1.9111,
      "step": 6
    },
    {
      "epoch": 0.005251312828207052,
      "grad_norm": 1.0373561382293701,
      "learning_rate": 7e-05,
      "loss": 1.647,
      "step": 7
    },
    {
      "epoch": 0.006001500375093774,
      "grad_norm": 1.397292137145996,
      "learning_rate": 8e-05,
      "loss": 1.7292,
      "step": 8
    },
    {
      "epoch": 0.006751687921980495,
      "grad_norm": 1.3358120918273926,
      "learning_rate": 9e-05,
      "loss": 1.8251,
      "step": 9
    },
    {
      "epoch": 0.006751687921980495,
      "eval_loss": 1.6242059469223022,
      "eval_runtime": 101.8731,
      "eval_samples_per_second": 44.074,
      "eval_steps_per_second": 1.384,
      "step": 9
    },
    {
      "epoch": 0.007501875468867217,
      "grad_norm": 1.0473986864089966,
      "learning_rate": 0.0001,
      "loss": 1.5298,
      "step": 10
    },
    {
      "epoch": 0.008252063015753939,
      "grad_norm": 1.5843597650527954,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8032,
      "step": 11
    },
    {
      "epoch": 0.00900225056264066,
      "grad_norm": 1.9067630767822266,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.3697,
      "step": 12
    },
    {
      "epoch": 0.009752438109527382,
      "grad_norm": 1.6097503900527954,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.4249,
      "step": 13
    },
    {
      "epoch": 0.010502625656414103,
      "grad_norm": 1.6491360664367676,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3823,
      "step": 14
    },
    {
      "epoch": 0.011252813203300824,
      "grad_norm": 1.6188210248947144,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5574,
      "step": 15
    },
    {
      "epoch": 0.012003000750187547,
      "grad_norm": 0.9108206629753113,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2524,
      "step": 16
    },
    {
      "epoch": 0.012753188297074268,
      "grad_norm": 1.0216554403305054,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.4649,
      "step": 17
    },
    {
      "epoch": 0.01350337584396099,
      "grad_norm": 0.7486273646354675,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.313,
      "step": 18
    },
    {
      "epoch": 0.01350337584396099,
      "eval_loss": 1.375331163406372,
      "eval_runtime": 101.8813,
      "eval_samples_per_second": 44.071,
      "eval_steps_per_second": 1.384,
      "step": 18
    },
    {
      "epoch": 0.014253563390847712,
      "grad_norm": 0.8785766959190369,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5243,
      "step": 19
    },
    {
      "epoch": 0.015003750937734433,
      "grad_norm": 1.0122979879379272,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.509,
      "step": 20
    },
    {
      "epoch": 0.015753938484621154,
      "grad_norm": 0.8695924282073975,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.1527,
      "step": 21
    },
    {
      "epoch": 0.016504126031507877,
      "grad_norm": 0.887084424495697,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.647,
      "step": 22
    },
    {
      "epoch": 0.0172543135783946,
      "grad_norm": 0.8445745706558228,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.4299,
      "step": 23
    },
    {
      "epoch": 0.01800450112528132,
      "grad_norm": 0.6971724629402161,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4398,
      "step": 24
    },
    {
      "epoch": 0.018754688672168042,
      "grad_norm": 0.8376932144165039,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2993,
      "step": 25
    },
    {
      "epoch": 0.019504876219054765,
      "grad_norm": 0.7465542554855347,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3123,
      "step": 26
    },
    {
      "epoch": 0.020255063765941484,
      "grad_norm": 0.9306272268295288,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.1982,
      "step": 27
    },
    {
      "epoch": 0.020255063765941484,
      "eval_loss": 1.2671202421188354,
      "eval_runtime": 101.9784,
      "eval_samples_per_second": 44.029,
      "eval_steps_per_second": 1.383,
      "step": 27
    },
    {
      "epoch": 0.021005251312828207,
      "grad_norm": 0.8331791162490845,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2495,
      "step": 28
    },
    {
      "epoch": 0.02175543885971493,
      "grad_norm": 0.7449824810028076,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1467,
      "step": 29
    },
    {
      "epoch": 0.02250562640660165,
      "grad_norm": 0.7697576880455017,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1848,
      "step": 30
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.8151161074638367,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.4536,
      "step": 31
    },
    {
      "epoch": 0.024006001500375095,
      "grad_norm": 1.033082127571106,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.3566,
      "step": 32
    },
    {
      "epoch": 0.024756189047261814,
      "grad_norm": 1.1058353185653687,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.1636,
      "step": 33
    },
    {
      "epoch": 0.025506376594148537,
      "grad_norm": 0.7640313506126404,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.0794,
      "step": 34
    },
    {
      "epoch": 0.02625656414103526,
      "grad_norm": 0.8580933809280396,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4723,
      "step": 35
    },
    {
      "epoch": 0.02700675168792198,
      "grad_norm": 0.8849585652351379,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.2334,
      "step": 36
    },
    {
      "epoch": 0.02700675168792198,
      "eval_loss": 1.2054572105407715,
      "eval_runtime": 102.0785,
      "eval_samples_per_second": 43.986,
      "eval_steps_per_second": 1.381,
      "step": 36
    },
    {
      "epoch": 0.0277569392348087,
      "grad_norm": 0.684136688709259,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0061,
      "step": 37
    },
    {
      "epoch": 0.028507126781695424,
      "grad_norm": 1.4281845092773438,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.5218,
      "step": 38
    },
    {
      "epoch": 0.029257314328582147,
      "grad_norm": 0.8635900020599365,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2753,
      "step": 39
    },
    {
      "epoch": 0.030007501875468866,
      "grad_norm": 0.9380740523338318,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2604,
      "step": 40
    },
    {
      "epoch": 0.03075768942235559,
      "grad_norm": 0.813073992729187,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.1825,
      "step": 41
    },
    {
      "epoch": 0.03150787696924231,
      "grad_norm": 0.7898310422897339,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8984,
      "step": 42
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.8174970149993896,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.1029,
      "step": 43
    },
    {
      "epoch": 0.033008252063015754,
      "grad_norm": 0.8050629496574402,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0702,
      "step": 44
    },
    {
      "epoch": 0.03375843960990248,
      "grad_norm": 0.8709306120872498,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.0744,
      "step": 45
    },
    {
      "epoch": 0.03375843960990248,
      "eval_loss": 1.1697427034378052,
      "eval_runtime": 101.921,
      "eval_samples_per_second": 44.054,
      "eval_steps_per_second": 1.383,
      "step": 45
    },
    {
      "epoch": 0.0345086271567892,
      "grad_norm": 0.7574114203453064,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.933,
      "step": 46
    },
    {
      "epoch": 0.035258814703675916,
      "grad_norm": 0.9223089814186096,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.1576,
      "step": 47
    },
    {
      "epoch": 0.03600900225056264,
      "grad_norm": 0.9843670725822449,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4228,
      "step": 48
    },
    {
      "epoch": 0.03675918979744936,
      "grad_norm": 0.8700153231620789,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.1176,
      "step": 49
    },
    {
      "epoch": 0.037509377344336084,
      "grad_norm": 0.8566334843635559,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0468,
      "step": 50
    },
    {
      "epoch": 0.03825956489122281,
      "grad_norm": 0.9160157442092896,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.2192,
      "step": 51
    },
    {
      "epoch": 0.03900975243810953,
      "grad_norm": 0.8719275593757629,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.122,
      "step": 52
    },
    {
      "epoch": 0.03975993998499625,
      "grad_norm": 0.8951583504676819,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.1081,
      "step": 53
    },
    {
      "epoch": 0.04051012753188297,
      "grad_norm": 0.9064164757728577,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3942,
      "step": 54
    },
    {
      "epoch": 0.04051012753188297,
      "eval_loss": 1.143883466720581,
      "eval_runtime": 102.0427,
      "eval_samples_per_second": 44.001,
      "eval_steps_per_second": 1.382,
      "step": 54
    },
    {
      "epoch": 0.04126031507876969,
      "grad_norm": 0.9431135654449463,
      "learning_rate": 5e-05,
      "loss": 1.0718,
      "step": 55
    },
    {
      "epoch": 0.042010502625656414,
      "grad_norm": 0.711380124092102,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8391,
      "step": 56
    },
    {
      "epoch": 0.04276069017254314,
      "grad_norm": 0.7991424798965454,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0982,
      "step": 57
    },
    {
      "epoch": 0.04351087771942986,
      "grad_norm": 1.1488597393035889,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.322,
      "step": 58
    },
    {
      "epoch": 0.04426106526631658,
      "grad_norm": 0.914455235004425,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.1224,
      "step": 59
    },
    {
      "epoch": 0.0450112528132033,
      "grad_norm": 0.7701334357261658,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.0476,
      "step": 60
    },
    {
      "epoch": 0.04576144036009002,
      "grad_norm": 0.8613665699958801,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0711,
      "step": 61
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.6381407976150513,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.1379,
      "step": 62
    },
    {
      "epoch": 0.047261815453863466,
      "grad_norm": 0.8371841311454773,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9863,
      "step": 63
    },
    {
      "epoch": 0.047261815453863466,
      "eval_loss": 1.1274592876434326,
      "eval_runtime": 102.6127,
      "eval_samples_per_second": 43.757,
      "eval_steps_per_second": 1.374,
      "step": 63
    },
    {
      "epoch": 0.04801200300075019,
      "grad_norm": 0.8599445819854736,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1032,
      "step": 64
    },
    {
      "epoch": 0.04876219054763691,
      "grad_norm": 0.8590635061264038,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.1514,
      "step": 65
    },
    {
      "epoch": 0.04951237809452363,
      "grad_norm": 0.9228536486625671,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0695,
      "step": 66
    },
    {
      "epoch": 0.05026256564141035,
      "grad_norm": 0.9740797877311707,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.9148,
      "step": 67
    },
    {
      "epoch": 0.05101275318829707,
      "grad_norm": 0.8204237222671509,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3028,
      "step": 68
    },
    {
      "epoch": 0.051762940735183796,
      "grad_norm": 0.9011926054954529,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0154,
      "step": 69
    },
    {
      "epoch": 0.05251312828207052,
      "grad_norm": 0.9710061550140381,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.2003,
      "step": 70
    },
    {
      "epoch": 0.05326331582895724,
      "grad_norm": 1.0523173809051514,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.2007,
      "step": 71
    },
    {
      "epoch": 0.05401350337584396,
      "grad_norm": 0.7311878800392151,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.1174,
      "step": 72
    },
    {
      "epoch": 0.05401350337584396,
      "eval_loss": 1.115315318107605,
      "eval_runtime": 102.0472,
      "eval_samples_per_second": 43.999,
      "eval_steps_per_second": 1.382,
      "step": 72
    },
    {
      "epoch": 0.05476369092273068,
      "grad_norm": 0.810351550579071,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9258,
      "step": 73
    },
    {
      "epoch": 0.0555138784696174,
      "grad_norm": 0.8039197325706482,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0235,
      "step": 74
    },
    {
      "epoch": 0.056264066016504126,
      "grad_norm": 1.1314038038253784,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0,
      "step": 75
    },
    {
      "epoch": 0.05701425356339085,
      "grad_norm": 1.0105289220809937,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0618,
      "step": 76
    },
    {
      "epoch": 0.05776444111027757,
      "grad_norm": 0.9906763434410095,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.3966,
      "step": 77
    },
    {
      "epoch": 0.058514628657164294,
      "grad_norm": 1.0615285634994507,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.119,
      "step": 78
    },
    {
      "epoch": 0.05926481620405101,
      "grad_norm": 1.4000828266143799,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.3671,
      "step": 79
    },
    {
      "epoch": 0.06001500375093773,
      "grad_norm": 1.228930115699768,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.2806,
      "step": 80
    },
    {
      "epoch": 0.060765191297824456,
      "grad_norm": 0.9001653790473938,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.2502,
      "step": 81
    },
    {
      "epoch": 0.060765191297824456,
      "eval_loss": 1.1089634895324707,
      "eval_runtime": 101.9954,
      "eval_samples_per_second": 44.022,
      "eval_steps_per_second": 1.382,
      "step": 81
    },
    {
      "epoch": 0.06151537884471118,
      "grad_norm": 1.1187061071395874,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3192,
      "step": 82
    },
    {
      "epoch": 0.0622655663915979,
      "grad_norm": 0.9319303035736084,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.1843,
      "step": 83
    },
    {
      "epoch": 0.06301575393848462,
      "grad_norm": 0.8874063491821289,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9317,
      "step": 84
    },
    {
      "epoch": 0.06376594148537135,
      "grad_norm": 0.9671034812927246,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0485,
      "step": 85
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 0.9318347573280334,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.011,
      "step": 86
    },
    {
      "epoch": 0.06526631657914479,
      "grad_norm": 1.0970379114151,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0897,
      "step": 87
    },
    {
      "epoch": 0.06601650412603151,
      "grad_norm": 0.9756683707237244,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1833,
      "step": 88
    },
    {
      "epoch": 0.06676669167291822,
      "grad_norm": 1.1624336242675781,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.3335,
      "step": 89
    },
    {
      "epoch": 0.06751687921980495,
      "grad_norm": 0.9813941717147827,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0293,
      "step": 90
    },
    {
      "epoch": 0.06751687921980495,
      "eval_loss": 1.1063300371170044,
      "eval_runtime": 102.9191,
      "eval_samples_per_second": 43.626,
      "eval_steps_per_second": 1.37,
      "step": 90
    },
    {
      "epoch": 0.06826706676669167,
      "grad_norm": 0.882434606552124,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0447,
      "step": 91
    },
    {
      "epoch": 0.0690172543135784,
      "grad_norm": 1.0112385749816895,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.7567,
      "step": 92
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 1.1317676305770874,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.1961,
      "step": 93
    },
    {
      "epoch": 0.07051762940735183,
      "grad_norm": 0.9738214015960693,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.043,
      "step": 94
    },
    {
      "epoch": 0.07126781695423856,
      "grad_norm": 0.9306845664978027,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.4558,
      "step": 95
    },
    {
      "epoch": 0.07201800450112528,
      "grad_norm": 1.0271937847137451,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1143,
      "step": 96
    },
    {
      "epoch": 0.072768192048012,
      "grad_norm": 1.1768940687179565,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0726,
      "step": 97
    },
    {
      "epoch": 0.07351837959489872,
      "grad_norm": 1.0005249977111816,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.1317,
      "step": 98
    },
    {
      "epoch": 0.07426856714178545,
      "grad_norm": 0.7808559536933899,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8203,
      "step": 99
    },
    {
      "epoch": 0.07426856714178545,
      "eval_loss": 1.105713129043579,
      "eval_runtime": 102.0398,
      "eval_samples_per_second": 44.002,
      "eval_steps_per_second": 1.382,
      "step": 99
    },
    {
      "epoch": 0.07501875468867217,
      "grad_norm": 0.8602554798126221,
      "learning_rate": 0.0,
      "loss": 1.0806,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.690889286044877e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}