{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14154281670205238,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014154281670205238,
      "grad_norm": 18.013778686523438,
      "learning_rate": 1e-05,
      "loss": 10.9884,
      "step": 1
    },
    {
      "epoch": 0.0014154281670205238,
      "eval_loss": 11.335967063903809,
      "eval_runtime": 127.8442,
      "eval_samples_per_second": 4.654,
      "eval_steps_per_second": 0.587,
      "step": 1
    },
    {
      "epoch": 0.0028308563340410475,
      "grad_norm": 17.465604782104492,
      "learning_rate": 2e-05,
      "loss": 11.6695,
      "step": 2
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 17.163856506347656,
      "learning_rate": 3e-05,
      "loss": 10.5079,
      "step": 3
    },
    {
      "epoch": 0.005661712668082095,
      "grad_norm": 14.109235763549805,
      "learning_rate": 4e-05,
      "loss": 11.4578,
      "step": 4
    },
    {
      "epoch": 0.007077140835102618,
      "grad_norm": 15.552477836608887,
      "learning_rate": 5e-05,
      "loss": 9.7975,
      "step": 5
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 13.720661163330078,
      "learning_rate": 6e-05,
      "loss": 9.5652,
      "step": 6
    },
    {
      "epoch": 0.009907997169143666,
      "grad_norm": 14.205248832702637,
      "learning_rate": 7e-05,
      "loss": 9.7105,
      "step": 7
    },
    {
      "epoch": 0.01132342533616419,
      "grad_norm": 16.87137222290039,
      "learning_rate": 8e-05,
      "loss": 7.3195,
      "step": 8
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 21.546878814697266,
      "learning_rate": 9e-05,
      "loss": 4.2201,
      "step": 9
    },
    {
      "epoch": 0.012738853503184714,
      "eval_loss": 3.523077964782715,
      "eval_runtime": 127.1731,
      "eval_samples_per_second": 4.679,
      "eval_steps_per_second": 0.59,
      "step": 9
    },
    {
      "epoch": 0.014154281670205236,
      "grad_norm": 25.0731201171875,
      "learning_rate": 0.0001,
      "loss": 3.5148,
      "step": 10
    },
    {
      "epoch": 0.01556970983722576,
      "grad_norm": 20.35257911682129,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.1071,
      "step": 11
    },
    {
      "epoch": 0.016985138004246284,
      "grad_norm": 14.014211654663086,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4957,
      "step": 12
    },
    {
      "epoch": 0.01840056617126681,
      "grad_norm": 7.595372676849365,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1848,
      "step": 13
    },
    {
      "epoch": 0.019815994338287332,
      "grad_norm": 6.6889848709106445,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.5921,
      "step": 14
    },
    {
      "epoch": 0.021231422505307854,
      "grad_norm": 12.184597969055176,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1347,
      "step": 15
    },
    {
      "epoch": 0.02264685067232838,
      "grad_norm": 9.233231544494629,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6222,
      "step": 16
    },
    {
      "epoch": 0.024062278839348902,
      "grad_norm": 5.808018207550049,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.3068,
      "step": 17
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 3.670421838760376,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2605,
      "step": 18
    },
    {
      "epoch": 0.025477707006369428,
      "eval_loss": 0.2632092833518982,
      "eval_runtime": 128.0046,
      "eval_samples_per_second": 4.648,
      "eval_steps_per_second": 0.586,
      "step": 18
    },
    {
      "epoch": 0.02689313517338995,
      "grad_norm": 3.4510953426361084,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2908,
      "step": 19
    },
    {
      "epoch": 0.028308563340410473,
      "grad_norm": 5.750612735748291,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2289,
      "step": 20
    },
    {
      "epoch": 0.029723991507430998,
      "grad_norm": 1.479280710220337,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1128,
      "step": 21
    },
    {
      "epoch": 0.03113941967445152,
      "grad_norm": 2.3032033443450928,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1502,
      "step": 22
    },
    {
      "epoch": 0.03255484784147204,
      "grad_norm": 1.0339311361312866,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1578,
      "step": 23
    },
    {
      "epoch": 0.03397027600849257,
      "grad_norm": 1.6400504112243652,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1038,
      "step": 24
    },
    {
      "epoch": 0.035385704175513094,
      "grad_norm": 3.0625715255737305,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1778,
      "step": 25
    },
    {
      "epoch": 0.03680113234253362,
      "grad_norm": 2.3699939250946045,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.143,
      "step": 26
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": 2.2926950454711914,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1596,
      "step": 27
    },
    {
      "epoch": 0.03821656050955414,
      "eval_loss": 0.20281900465488434,
      "eval_runtime": 127.1194,
      "eval_samples_per_second": 4.681,
      "eval_steps_per_second": 0.59,
      "step": 27
    },
    {
      "epoch": 0.039631988676574664,
      "grad_norm": 3.758871555328369,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1926,
      "step": 28
    },
    {
      "epoch": 0.04104741684359519,
      "grad_norm": 1.8953357934951782,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.134,
      "step": 29
    },
    {
      "epoch": 0.04246284501061571,
      "grad_norm": 0.5549580454826355,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1117,
      "step": 30
    },
    {
      "epoch": 0.043878273177636234,
      "grad_norm": 1.1810989379882812,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1069,
      "step": 31
    },
    {
      "epoch": 0.04529370134465676,
      "grad_norm": 3.1690216064453125,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1625,
      "step": 32
    },
    {
      "epoch": 0.04670912951167728,
      "grad_norm": 1.049263596534729,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1153,
      "step": 33
    },
    {
      "epoch": 0.048124557678697805,
      "grad_norm": 2.511300563812256,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.128,
      "step": 34
    },
    {
      "epoch": 0.04953998584571833,
      "grad_norm": 1.8151744604110718,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1393,
      "step": 35
    },
    {
      "epoch": 0.050955414012738856,
      "grad_norm": 3.0959160327911377,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.162,
      "step": 36
    },
    {
      "epoch": 0.050955414012738856,
      "eval_loss": 0.11191724240779877,
      "eval_runtime": 127.0939,
      "eval_samples_per_second": 4.682,
      "eval_steps_per_second": 0.59,
      "step": 36
    },
    {
      "epoch": 0.052370842179759375,
      "grad_norm": 1.4394816160202026,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1308,
      "step": 37
    },
    {
      "epoch": 0.0537862703467799,
      "grad_norm": 2.1883745193481445,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1825,
      "step": 38
    },
    {
      "epoch": 0.055201698513800426,
      "grad_norm": 2.7608649730682373,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1724,
      "step": 39
    },
    {
      "epoch": 0.056617126680820945,
      "grad_norm": 4.084112167358398,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2077,
      "step": 40
    },
    {
      "epoch": 0.05803255484784147,
      "grad_norm": 2.417600631713867,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1452,
      "step": 41
    },
    {
      "epoch": 0.059447983014861996,
      "grad_norm": 2.287311315536499,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1342,
      "step": 42
    },
    {
      "epoch": 0.06086341118188252,
      "grad_norm": 1.036487102508545,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1302,
      "step": 43
    },
    {
      "epoch": 0.06227883934890304,
      "grad_norm": 2.3799216747283936,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1295,
      "step": 44
    },
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 0.44193577766418457,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1292,
      "step": 45
    },
    {
      "epoch": 0.06369426751592357,
      "eval_loss": 0.11066457629203796,
      "eval_runtime": 127.0622,
      "eval_samples_per_second": 4.683,
      "eval_steps_per_second": 0.59,
      "step": 45
    },
    {
      "epoch": 0.06510969568294409,
      "grad_norm": 0.2613424062728882,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0994,
      "step": 46
    },
    {
      "epoch": 0.06652512384996462,
      "grad_norm": 0.5390338897705078,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1016,
      "step": 47
    },
    {
      "epoch": 0.06794055201698514,
      "grad_norm": 1.7200884819030762,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1325,
      "step": 48
    },
    {
      "epoch": 0.06935598018400566,
      "grad_norm": 3.1017560958862305,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1629,
      "step": 49
    },
    {
      "epoch": 0.07077140835102619,
      "grad_norm": 0.32497769594192505,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0913,
      "step": 50
    },
    {
      "epoch": 0.07218683651804671,
      "grad_norm": 1.8043497800827026,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1411,
      "step": 51
    },
    {
      "epoch": 0.07360226468506724,
      "grad_norm": 0.7669022679328918,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1089,
      "step": 52
    },
    {
      "epoch": 0.07501769285208776,
      "grad_norm": 0.8200987577438354,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1072,
      "step": 53
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": 1.5350964069366455,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.1279,
      "step": 54
    },
    {
      "epoch": 0.07643312101910828,
      "eval_loss": 0.10821533203125,
      "eval_runtime": 127.087,
      "eval_samples_per_second": 4.682,
      "eval_steps_per_second": 0.59,
      "step": 54
    },
    {
      "epoch": 0.07784854918612881,
      "grad_norm": 0.5155397057533264,
      "learning_rate": 5e-05,
      "loss": 0.1156,
      "step": 55
    },
    {
      "epoch": 0.07926397735314933,
      "grad_norm": 0.41658011078834534,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1141,
      "step": 56
    },
    {
      "epoch": 0.08067940552016985,
      "grad_norm": 0.986137330532074,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1358,
      "step": 57
    },
    {
      "epoch": 0.08209483368719038,
      "grad_norm": 1.5772260427474976,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1149,
      "step": 58
    },
    {
      "epoch": 0.0835102618542109,
      "grad_norm": 1.9692206382751465,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.146,
      "step": 59
    },
    {
      "epoch": 0.08492569002123142,
      "grad_norm": 0.8698508739471436,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1009,
      "step": 60
    },
    {
      "epoch": 0.08634111818825195,
      "grad_norm": 2.1218152046203613,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1416,
      "step": 61
    },
    {
      "epoch": 0.08775654635527247,
      "grad_norm": 1.7425721883773804,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1384,
      "step": 62
    },
    {
      "epoch": 0.08917197452229299,
      "grad_norm": 2.9890897274017334,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1707,
      "step": 63
    },
    {
      "epoch": 0.08917197452229299,
      "eval_loss": 0.1412888765335083,
      "eval_runtime": 127.0555,
      "eval_samples_per_second": 4.683,
      "eval_steps_per_second": 0.59,
      "step": 63
    },
    {
      "epoch": 0.09058740268931352,
      "grad_norm": 3.2205963134765625,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1843,
      "step": 64
    },
    {
      "epoch": 0.09200283085633404,
      "grad_norm": 0.5274741053581238,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0972,
      "step": 65
    },
    {
      "epoch": 0.09341825902335456,
      "grad_norm": 1.1009308099746704,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1413,
      "step": 66
    },
    {
      "epoch": 0.09483368719037509,
      "grad_norm": 1.007982611656189,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1176,
      "step": 67
    },
    {
      "epoch": 0.09624911535739561,
      "grad_norm": 1.1018102169036865,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1269,
      "step": 68
    },
    {
      "epoch": 0.09766454352441614,
      "grad_norm": 0.3432563841342926,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0989,
      "step": 69
    },
    {
      "epoch": 0.09907997169143666,
      "grad_norm": 2.0502262115478516,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1301,
      "step": 70
    },
    {
      "epoch": 0.10049539985845718,
      "grad_norm": 0.684442937374115,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0976,
      "step": 71
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 1.1942218542099,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1241,
      "step": 72
    },
    {
      "epoch": 0.10191082802547771,
      "eval_loss": 0.10807202756404877,
      "eval_runtime": 127.0721,
      "eval_samples_per_second": 4.682,
      "eval_steps_per_second": 0.59,
      "step": 72
    },
    {
      "epoch": 0.10332625619249823,
      "grad_norm": 1.5802924633026123,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1139,
      "step": 73
    },
    {
      "epoch": 0.10474168435951875,
      "grad_norm": 0.271753191947937,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1051,
      "step": 74
    },
    {
      "epoch": 0.10615711252653928,
      "grad_norm": 1.833114504814148,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1629,
      "step": 75
    },
    {
      "epoch": 0.1075725406935598,
      "grad_norm": 0.7451173663139343,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1308,
      "step": 76
    },
    {
      "epoch": 0.10898796886058032,
      "grad_norm": 0.8794470429420471,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1099,
      "step": 77
    },
    {
      "epoch": 0.11040339702760085,
      "grad_norm": 1.5756449699401855,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.121,
      "step": 78
    },
    {
      "epoch": 0.11181882519462137,
      "grad_norm": 1.5091930627822876,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1289,
      "step": 79
    },
    {
      "epoch": 0.11323425336164189,
      "grad_norm": 0.8172638416290283,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0927,
      "step": 80
    },
    {
      "epoch": 0.11464968152866242,
      "grad_norm": 0.6090733408927917,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1133,
      "step": 81
    },
    {
      "epoch": 0.11464968152866242,
      "eval_loss": 0.10955800116062164,
      "eval_runtime": 127.1359,
      "eval_samples_per_second": 4.68,
      "eval_steps_per_second": 0.59,
      "step": 81
    },
    {
      "epoch": 0.11606510969568294,
      "grad_norm": 0.45214489102363586,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.098,
      "step": 82
    },
    {
      "epoch": 0.11748053786270347,
      "grad_norm": 0.7153350114822388,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0853,
      "step": 83
    },
    {
      "epoch": 0.11889596602972399,
      "grad_norm": 0.5856150984764099,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0897,
      "step": 84
    },
    {
      "epoch": 0.12031139419674451,
      "grad_norm": 0.5094517469406128,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1127,
      "step": 85
    },
    {
      "epoch": 0.12172682236376504,
      "grad_norm": 2.3627333641052246,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1412,
      "step": 86
    },
    {
      "epoch": 0.12314225053078556,
      "grad_norm": 0.7735049724578857,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1132,
      "step": 87
    },
    {
      "epoch": 0.12455767869780608,
      "grad_norm": 0.5762856602668762,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1129,
      "step": 88
    },
    {
      "epoch": 0.1259731068648266,
      "grad_norm": 1.0163521766662598,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1242,
      "step": 89
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 0.4653487205505371,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1007,
      "step": 90
    },
    {
      "epoch": 0.12738853503184713,
      "eval_loss": 0.10906722396612167,
      "eval_runtime": 127.0759,
      "eval_samples_per_second": 4.682,
      "eval_steps_per_second": 0.59,
      "step": 90
    },
    {
      "epoch": 0.12880396319886767,
      "grad_norm": 1.58189857006073,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1539,
      "step": 91
    },
    {
      "epoch": 0.13021939136588817,
      "grad_norm": 1.1043466329574585,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1043,
      "step": 92
    },
    {
      "epoch": 0.1316348195329087,
      "grad_norm": 1.41648530960083,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1185,
      "step": 93
    },
    {
      "epoch": 0.13305024769992924,
      "grad_norm": 0.4491123557090759,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1167,
      "step": 94
    },
    {
      "epoch": 0.13446567586694974,
      "grad_norm": 2.0084850788116455,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1225,
      "step": 95
    },
    {
      "epoch": 0.13588110403397027,
      "grad_norm": 0.3125413656234741,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1013,
      "step": 96
    },
    {
      "epoch": 0.1372965322009908,
      "grad_norm": 0.47210630774497986,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0968,
      "step": 97
    },
    {
      "epoch": 0.1387119603680113,
      "grad_norm": 0.8656429052352905,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1112,
      "step": 98
    },
    {
      "epoch": 0.14012738853503184,
      "grad_norm": 0.3149074912071228,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0945,
      "step": 99
    },
    {
      "epoch": 0.14012738853503184,
      "eval_loss": 0.10777448117733002,
      "eval_runtime": 127.1053,
      "eval_samples_per_second": 4.681,
      "eval_steps_per_second": 0.59,
      "step": 99
    },
    {
      "epoch": 0.14154281670205238,
      "grad_norm": 0.4153774678707123,
      "learning_rate": 0.0,
      "loss": 0.0999,
      "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": 1.4132952751826534e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}