{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00832639467110741,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.326394671107411e-05,
      "grad_norm": 0.6871480941772461,
      "learning_rate": 1e-05,
      "loss": 1.1197,
      "step": 1
    },
    {
      "epoch": 8.326394671107411e-05,
      "eval_loss": 1.2025511264801025,
      "eval_runtime": 1873.6459,
      "eval_samples_per_second": 5.398,
      "eval_steps_per_second": 0.675,
      "step": 1
    },
    {
      "epoch": 0.00016652789342214822,
      "grad_norm": 0.6065630912780762,
      "learning_rate": 2e-05,
      "loss": 1.4157,
      "step": 2
    },
    {
      "epoch": 0.0002497918401332223,
      "grad_norm": 0.6395959854125977,
      "learning_rate": 3e-05,
      "loss": 1.0421,
      "step": 3
    },
    {
      "epoch": 0.00033305578684429644,
      "grad_norm": 0.7535728812217712,
      "learning_rate": 4e-05,
      "loss": 0.8854,
      "step": 4
    },
    {
      "epoch": 0.00041631973355537054,
      "grad_norm": 0.8002839684486389,
      "learning_rate": 5e-05,
      "loss": 1.1319,
      "step": 5
    },
    {
      "epoch": 0.0004995836802664446,
      "grad_norm": 0.7185359597206116,
      "learning_rate": 6e-05,
      "loss": 1.1534,
      "step": 6
    },
    {
      "epoch": 0.0005828476269775188,
      "grad_norm": 0.7994174957275391,
      "learning_rate": 7e-05,
      "loss": 1.1366,
      "step": 7
    },
    {
      "epoch": 0.0006661115736885929,
      "grad_norm": 0.9843465089797974,
      "learning_rate": 8e-05,
      "loss": 1.2944,
      "step": 8
    },
    {
      "epoch": 0.000749375520399667,
      "grad_norm": 1.1043306589126587,
      "learning_rate": 9e-05,
      "loss": 1.1426,
      "step": 9
    },
    {
      "epoch": 0.000749375520399667,
      "eval_loss": 1.0168187618255615,
      "eval_runtime": 1879.978,
      "eval_samples_per_second": 5.38,
      "eval_steps_per_second": 0.673,
      "step": 9
    },
    {
      "epoch": 0.0008326394671107411,
      "grad_norm": 0.7300062775611877,
      "learning_rate": 0.0001,
      "loss": 0.8043,
      "step": 10
    },
    {
      "epoch": 0.0009159034138218152,
      "grad_norm": 0.5794069170951843,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8879,
      "step": 11
    },
    {
      "epoch": 0.0009991673605328892,
      "grad_norm": 0.656294047832489,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8947,
      "step": 12
    },
    {
      "epoch": 0.0010824313072439634,
      "grad_norm": 0.6405145525932312,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.7168,
      "step": 13
    },
    {
      "epoch": 0.0011656952539550376,
      "grad_norm": 0.7153993248939514,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8198,
      "step": 14
    },
    {
      "epoch": 0.0012489592006661116,
      "grad_norm": 0.6253563761711121,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9583,
      "step": 15
    },
    {
      "epoch": 0.0013322231473771858,
      "grad_norm": 0.9064929485321045,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7007,
      "step": 16
    },
    {
      "epoch": 0.0014154870940882597,
      "grad_norm": 0.6331225633621216,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6507,
      "step": 17
    },
    {
      "epoch": 0.001498751040799334,
      "grad_norm": 0.6313807964324951,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.8009,
      "step": 18
    },
    {
      "epoch": 0.001498751040799334,
      "eval_loss": 0.7656639218330383,
      "eval_runtime": 1878.3063,
      "eval_samples_per_second": 5.385,
      "eval_steps_per_second": 0.673,
      "step": 18
    },
    {
      "epoch": 0.001582014987510408,
      "grad_norm": 0.5964687466621399,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8406,
      "step": 19
    },
    {
      "epoch": 0.0016652789342214821,
      "grad_norm": 0.8008723855018616,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7004,
      "step": 20
    },
    {
      "epoch": 0.0017485428809325561,
      "grad_norm": 0.7248008251190186,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.6875,
      "step": 21
    },
    {
      "epoch": 0.0018318068276436303,
      "grad_norm": 0.6736342906951904,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.761,
      "step": 22
    },
    {
      "epoch": 0.0019150707743547043,
      "grad_norm": 0.7091475129127502,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1793,
      "step": 23
    },
    {
      "epoch": 0.0019983347210657783,
      "grad_norm": 0.6263002753257751,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7844,
      "step": 24
    },
    {
      "epoch": 0.0020815986677768525,
      "grad_norm": 0.8400290608406067,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7321,
      "step": 25
    },
    {
      "epoch": 0.0021648626144879267,
      "grad_norm": 0.43379339575767517,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4609,
      "step": 26
    },
    {
      "epoch": 0.002248126561199001,
      "grad_norm": 0.6223347783088684,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7268,
      "step": 27
    },
    {
      "epoch": 0.002248126561199001,
      "eval_loss": 0.6873729825019836,
      "eval_runtime": 1878.2535,
      "eval_samples_per_second": 5.385,
      "eval_steps_per_second": 0.673,
      "step": 27
    },
    {
      "epoch": 0.002331390507910075,
      "grad_norm": 0.5511863827705383,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8827,
      "step": 28
    },
    {
      "epoch": 0.002414654454621149,
      "grad_norm": 0.5144586563110352,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.614,
      "step": 29
    },
    {
      "epoch": 0.002497918401332223,
      "grad_norm": 0.45852169394493103,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.8406,
      "step": 30
    },
    {
      "epoch": 0.0025811823480432973,
      "grad_norm": 0.5173745155334473,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.5123,
      "step": 31
    },
    {
      "epoch": 0.0026644462947543715,
      "grad_norm": 0.5404499769210815,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7068,
      "step": 32
    },
    {
      "epoch": 0.0027477102414654453,
      "grad_norm": 0.510198175907135,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7882,
      "step": 33
    },
    {
      "epoch": 0.0028309741881765195,
      "grad_norm": 0.4509652853012085,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.6486,
      "step": 34
    },
    {
      "epoch": 0.0029142381348875937,
      "grad_norm": 0.5206254720687866,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.4552,
      "step": 35
    },
    {
      "epoch": 0.002997502081598668,
      "grad_norm": 0.5085834860801697,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4236,
      "step": 36
    },
    {
      "epoch": 0.002997502081598668,
      "eval_loss": 0.6540737152099609,
      "eval_runtime": 1876.5825,
      "eval_samples_per_second": 5.39,
      "eval_steps_per_second": 0.674,
      "step": 36
    },
    {
      "epoch": 0.0030807660283097417,
      "grad_norm": 0.8389857411384583,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3498,
      "step": 37
    },
    {
      "epoch": 0.003164029975020816,
      "grad_norm": 0.6714943647384644,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6599,
      "step": 38
    },
    {
      "epoch": 0.00324729392173189,
      "grad_norm": 0.5501314401626587,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.5868,
      "step": 39
    },
    {
      "epoch": 0.0033305578684429643,
      "grad_norm": 0.5625066757202148,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6431,
      "step": 40
    },
    {
      "epoch": 0.0034138218151540385,
      "grad_norm": 0.536219596862793,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7902,
      "step": 41
    },
    {
      "epoch": 0.0034970857618651123,
      "grad_norm": 0.5107579827308655,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3753,
      "step": 42
    },
    {
      "epoch": 0.0035803497085761865,
      "grad_norm": 0.5040971040725708,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.8633,
      "step": 43
    },
    {
      "epoch": 0.0036636136552872607,
      "grad_norm": 0.713556706905365,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6374,
      "step": 44
    },
    {
      "epoch": 0.003746877601998335,
      "grad_norm": 0.5780977606773376,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9586,
      "step": 45
    },
    {
      "epoch": 0.003746877601998335,
      "eval_loss": 0.638473391532898,
      "eval_runtime": 1875.0259,
      "eval_samples_per_second": 5.394,
      "eval_steps_per_second": 0.675,
      "step": 45
    },
    {
      "epoch": 0.0038301415487094087,
      "grad_norm": 0.5278427600860596,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2688,
      "step": 46
    },
    {
      "epoch": 0.003913405495420483,
      "grad_norm": 0.5301978588104248,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6102,
      "step": 47
    },
    {
      "epoch": 0.003996669442131557,
      "grad_norm": 0.526614248752594,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8452,
      "step": 48
    },
    {
      "epoch": 0.004079933388842631,
      "grad_norm": 0.6380936503410339,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.5953,
      "step": 49
    },
    {
      "epoch": 0.004163197335553705,
      "grad_norm": 0.6241381764411926,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7052,
      "step": 50
    },
    {
      "epoch": 0.004246461282264779,
      "grad_norm": 0.5144871473312378,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6276,
      "step": 51
    },
    {
      "epoch": 0.0043297252289758534,
      "grad_norm": 0.7938607931137085,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6172,
      "step": 52
    },
    {
      "epoch": 0.004412989175686928,
      "grad_norm": 0.559364378452301,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.9424,
      "step": 53
    },
    {
      "epoch": 0.004496253122398002,
      "grad_norm": 0.5549708604812622,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5619,
      "step": 54
    },
    {
      "epoch": 0.004496253122398002,
      "eval_loss": 0.6263570785522461,
      "eval_runtime": 1874.081,
      "eval_samples_per_second": 5.397,
      "eval_steps_per_second": 0.675,
      "step": 54
    },
    {
      "epoch": 0.004579517069109076,
      "grad_norm": 0.6072118282318115,
      "learning_rate": 5e-05,
      "loss": 0.5964,
      "step": 55
    },
    {
      "epoch": 0.00466278101582015,
      "grad_norm": 0.5688763856887817,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7724,
      "step": 56
    },
    {
      "epoch": 0.004746044962531224,
      "grad_norm": 0.6150090098381042,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.6189,
      "step": 57
    },
    {
      "epoch": 0.004829308909242298,
      "grad_norm": 0.5213116407394409,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.6805,
      "step": 58
    },
    {
      "epoch": 0.004912572855953372,
      "grad_norm": 0.47878560423851013,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.625,
      "step": 59
    },
    {
      "epoch": 0.004995836802664446,
      "grad_norm": 0.6849039793014526,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7203,
      "step": 60
    },
    {
      "epoch": 0.00507910074937552,
      "grad_norm": 0.5728254914283752,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.8075,
      "step": 61
    },
    {
      "epoch": 0.005162364696086595,
      "grad_norm": 0.7572735548019409,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5874,
      "step": 62
    },
    {
      "epoch": 0.005245628642797669,
      "grad_norm": 0.6589543223381042,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.5797,
      "step": 63
    },
    {
      "epoch": 0.005245628642797669,
      "eval_loss": 0.6163843274116516,
      "eval_runtime": 1874.0277,
      "eval_samples_per_second": 5.397,
      "eval_steps_per_second": 0.675,
      "step": 63
    },
    {
      "epoch": 0.005328892589508743,
      "grad_norm": 0.5503858327865601,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6858,
      "step": 64
    },
    {
      "epoch": 0.005412156536219817,
      "grad_norm": 0.4466218948364258,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7072,
      "step": 65
    },
    {
      "epoch": 0.005495420482930891,
      "grad_norm": 0.676203727722168,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6532,
      "step": 66
    },
    {
      "epoch": 0.005578684429641965,
      "grad_norm": 0.5970198512077332,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4029,
      "step": 67
    },
    {
      "epoch": 0.005661948376353039,
      "grad_norm": 0.59070885181427,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6509,
      "step": 68
    },
    {
      "epoch": 0.005745212323064113,
      "grad_norm": 0.5007186532020569,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7345,
      "step": 69
    },
    {
      "epoch": 0.005828476269775187,
      "grad_norm": 0.549541175365448,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.492,
      "step": 70
    },
    {
      "epoch": 0.005911740216486262,
      "grad_norm": 0.6607359051704407,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5709,
      "step": 71
    },
    {
      "epoch": 0.005995004163197336,
      "grad_norm": 0.4524803161621094,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.843,
      "step": 72
    },
    {
      "epoch": 0.005995004163197336,
      "eval_loss": 0.6111176013946533,
      "eval_runtime": 1875.3753,
      "eval_samples_per_second": 5.393,
      "eval_steps_per_second": 0.675,
      "step": 72
    },
    {
      "epoch": 0.00607826810990841,
      "grad_norm": 0.5329728126525879,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7755,
      "step": 73
    },
    {
      "epoch": 0.006161532056619483,
      "grad_norm": 0.5134813189506531,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.5342,
      "step": 74
    },
    {
      "epoch": 0.0062447960033305576,
      "grad_norm": 0.47925451397895813,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9089,
      "step": 75
    },
    {
      "epoch": 0.006328059950041632,
      "grad_norm": 0.5378401875495911,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7044,
      "step": 76
    },
    {
      "epoch": 0.006411323896752706,
      "grad_norm": 0.5078656673431396,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7109,
      "step": 77
    },
    {
      "epoch": 0.00649458784346378,
      "grad_norm": 0.7006959319114685,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.431,
      "step": 78
    },
    {
      "epoch": 0.006577851790174854,
      "grad_norm": 0.5978702306747437,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.5518,
      "step": 79
    },
    {
      "epoch": 0.006661115736885929,
      "grad_norm": 0.5336026549339294,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.55,
      "step": 80
    },
    {
      "epoch": 0.006744379683597003,
      "grad_norm": 0.4496859312057495,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6881,
      "step": 81
    },
    {
      "epoch": 0.006744379683597003,
      "eval_loss": 0.607624351978302,
      "eval_runtime": 1874.8035,
      "eval_samples_per_second": 5.395,
      "eval_steps_per_second": 0.675,
      "step": 81
    },
    {
      "epoch": 0.006827643630308077,
      "grad_norm": 0.5448951125144958,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7178,
      "step": 82
    },
    {
      "epoch": 0.00691090757701915,
      "grad_norm": 0.5171974301338196,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.7393,
      "step": 83
    },
    {
      "epoch": 0.0069941715237302245,
      "grad_norm": 0.3583661615848541,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.5103,
      "step": 84
    },
    {
      "epoch": 0.007077435470441299,
      "grad_norm": 0.5829033851623535,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6899,
      "step": 85
    },
    {
      "epoch": 0.007160699417152373,
      "grad_norm": 0.5309457182884216,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6061,
      "step": 86
    },
    {
      "epoch": 0.007243963363863447,
      "grad_norm": 0.8489606976509094,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4233,
      "step": 87
    },
    {
      "epoch": 0.007327227310574521,
      "grad_norm": 0.6375559568405151,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6815,
      "step": 88
    },
    {
      "epoch": 0.0074104912572855956,
      "grad_norm": 0.6630268096923828,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.6326,
      "step": 89
    },
    {
      "epoch": 0.00749375520399667,
      "grad_norm": 0.45221108198165894,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4865,
      "step": 90
    },
    {
      "epoch": 0.00749375520399667,
      "eval_loss": 0.6059922575950623,
      "eval_runtime": 1878.4027,
      "eval_samples_per_second": 5.384,
      "eval_steps_per_second": 0.673,
      "step": 90
    },
    {
      "epoch": 0.007577019150707744,
      "grad_norm": 0.5124365091323853,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5778,
      "step": 91
    },
    {
      "epoch": 0.007660283097418817,
      "grad_norm": 0.8342736959457397,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.609,
      "step": 92
    },
    {
      "epoch": 0.0077435470441298915,
      "grad_norm": 0.4861484467983246,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4582,
      "step": 93
    },
    {
      "epoch": 0.007826810990840967,
      "grad_norm": 0.4907625913619995,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7756,
      "step": 94
    },
    {
      "epoch": 0.00791007493755204,
      "grad_norm": 0.49000653624534607,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.4203,
      "step": 95
    },
    {
      "epoch": 0.007993338884263113,
      "grad_norm": 0.6092959046363831,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.524,
      "step": 96
    },
    {
      "epoch": 0.008076602830974187,
      "grad_norm": 0.5685826539993286,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.5168,
      "step": 97
    },
    {
      "epoch": 0.008159866777685262,
      "grad_norm": 0.7407828569412231,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7229,
      "step": 98
    },
    {
      "epoch": 0.008243130724396336,
      "grad_norm": 0.5559101104736328,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8751,
      "step": 99
    },
    {
      "epoch": 0.008243130724396336,
      "eval_loss": 0.6056489944458008,
      "eval_runtime": 1877.0661,
      "eval_samples_per_second": 5.388,
      "eval_steps_per_second": 0.674,
      "step": 99
    },
    {
      "epoch": 0.00832639467110741,
      "grad_norm": 0.5634000301361084,
      "learning_rate": 0.0,
      "loss": 0.3409,
      "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": 1.1602201751322624e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}