{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.031070374398011497,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031070374398011494,
      "grad_norm": 0.41790682077407837,
      "learning_rate": 1e-05,
      "loss": 0.3706,
      "step": 1
    },
    {
      "epoch": 0.00031070374398011494,
      "eval_loss": 0.5521897673606873,
      "eval_runtime": 476.997,
      "eval_samples_per_second": 5.683,
      "eval_steps_per_second": 0.711,
      "step": 1
    },
    {
      "epoch": 0.0006214074879602299,
      "grad_norm": 0.9188364744186401,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 2
    },
    {
      "epoch": 0.0009321112319403449,
      "grad_norm": 0.48639437556266785,
      "learning_rate": 3e-05,
      "loss": 0.4176,
      "step": 3
    },
    {
      "epoch": 0.0012428149759204598,
      "grad_norm": 0.45980286598205566,
      "learning_rate": 4e-05,
      "loss": 0.3546,
      "step": 4
    },
    {
      "epoch": 0.0015535187199005747,
      "grad_norm": 0.8268013000488281,
      "learning_rate": 5e-05,
      "loss": 0.7585,
      "step": 5
    },
    {
      "epoch": 0.0018642224638806897,
      "grad_norm": 0.4426511824131012,
      "learning_rate": 6e-05,
      "loss": 0.2954,
      "step": 6
    },
    {
      "epoch": 0.0021749262078608047,
      "grad_norm": 0.6053217053413391,
      "learning_rate": 7e-05,
      "loss": 0.5119,
      "step": 7
    },
    {
      "epoch": 0.0024856299518409195,
      "grad_norm": 0.44315120577812195,
      "learning_rate": 8e-05,
      "loss": 0.2999,
      "step": 8
    },
    {
      "epoch": 0.0027963336958210347,
      "grad_norm": 0.5531988143920898,
      "learning_rate": 9e-05,
      "loss": 0.406,
      "step": 9
    },
    {
      "epoch": 0.0027963336958210347,
      "eval_loss": 0.4063211977481842,
      "eval_runtime": 476.8353,
      "eval_samples_per_second": 5.685,
      "eval_steps_per_second": 0.711,
      "step": 9
    },
    {
      "epoch": 0.0031070374398011495,
      "grad_norm": 0.5760719180107117,
      "learning_rate": 0.0001,
      "loss": 0.3408,
      "step": 10
    },
    {
      "epoch": 0.0034177411837812647,
      "grad_norm": 0.3422175645828247,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.3512,
      "step": 11
    },
    {
      "epoch": 0.0037284449277613795,
      "grad_norm": 0.6977759003639221,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3214,
      "step": 12
    },
    {
      "epoch": 0.004039148671741494,
      "grad_norm": 0.5818986892700195,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3384,
      "step": 13
    },
    {
      "epoch": 0.0043498524157216095,
      "grad_norm": 0.3300100266933441,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3199,
      "step": 14
    },
    {
      "epoch": 0.004660556159701725,
      "grad_norm": 0.7036962509155273,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2575,
      "step": 15
    },
    {
      "epoch": 0.004971259903681839,
      "grad_norm": 0.9844618439674377,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3385,
      "step": 16
    },
    {
      "epoch": 0.005281963647661954,
      "grad_norm": 0.6180463433265686,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.28,
      "step": 17
    },
    {
      "epoch": 0.005592667391642069,
      "grad_norm": 0.32857397198677063,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1648,
      "step": 18
    },
    {
      "epoch": 0.005592667391642069,
      "eval_loss": 0.24664728343486786,
      "eval_runtime": 476.6652,
      "eval_samples_per_second": 5.687,
      "eval_steps_per_second": 0.711,
      "step": 18
    },
    {
      "epoch": 0.005903371135622185,
      "grad_norm": 0.3222501575946808,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1621,
      "step": 19
    },
    {
      "epoch": 0.006214074879602299,
      "grad_norm": 0.2679303288459778,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1456,
      "step": 20
    },
    {
      "epoch": 0.006524778623582414,
      "grad_norm": 0.27220985293388367,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1968,
      "step": 21
    },
    {
      "epoch": 0.006835482367562529,
      "grad_norm": 0.18961292505264282,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1115,
      "step": 22
    },
    {
      "epoch": 0.007146186111542644,
      "grad_norm": 0.3951137363910675,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1629,
      "step": 23
    },
    {
      "epoch": 0.007456889855522759,
      "grad_norm": 0.619987428188324,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2825,
      "step": 24
    },
    {
      "epoch": 0.007767593599502874,
      "grad_norm": 0.4849282503128052,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1851,
      "step": 25
    },
    {
      "epoch": 0.008078297343482988,
      "grad_norm": 0.34269535541534424,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1632,
      "step": 26
    },
    {
      "epoch": 0.008389001087463105,
      "grad_norm": 0.3975559175014496,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1247,
      "step": 27
    },
    {
      "epoch": 0.008389001087463105,
      "eval_loss": 0.185841903090477,
      "eval_runtime": 476.7059,
      "eval_samples_per_second": 5.687,
      "eval_steps_per_second": 0.711,
      "step": 27
    },
    {
      "epoch": 0.008699704831443219,
      "grad_norm": 0.34876108169555664,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1416,
      "step": 28
    },
    {
      "epoch": 0.009010408575423333,
      "grad_norm": 0.37794193625450134,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1579,
      "step": 29
    },
    {
      "epoch": 0.00932111231940345,
      "grad_norm": 0.47456857562065125,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2242,
      "step": 30
    },
    {
      "epoch": 0.009631816063383564,
      "grad_norm": 0.5491670966148376,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1729,
      "step": 31
    },
    {
      "epoch": 0.009942519807363678,
      "grad_norm": 0.30028006434440613,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1175,
      "step": 32
    },
    {
      "epoch": 0.010253223551343794,
      "grad_norm": 0.2186529040336609,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1144,
      "step": 33
    },
    {
      "epoch": 0.010563927295323908,
      "grad_norm": 0.2727157473564148,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1292,
      "step": 34
    },
    {
      "epoch": 0.010874631039304023,
      "grad_norm": 0.7948876619338989,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1344,
      "step": 35
    },
    {
      "epoch": 0.011185334783284139,
      "grad_norm": 0.5991654396057129,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1465,
      "step": 36
    },
    {
      "epoch": 0.011185334783284139,
      "eval_loss": 0.1456374228000641,
      "eval_runtime": 476.6381,
      "eval_samples_per_second": 5.688,
      "eval_steps_per_second": 0.711,
      "step": 36
    },
    {
      "epoch": 0.011496038527264253,
      "grad_norm": 0.39887380599975586,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1494,
      "step": 37
    },
    {
      "epoch": 0.01180674227124437,
      "grad_norm": 0.43696069717407227,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1529,
      "step": 38
    },
    {
      "epoch": 0.012117446015224484,
      "grad_norm": 0.5842476487159729,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1245,
      "step": 39
    },
    {
      "epoch": 0.012428149759204598,
      "grad_norm": 0.28087949752807617,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2125,
      "step": 40
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.5370662212371826,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0815,
      "step": 41
    },
    {
      "epoch": 0.013049557247164828,
      "grad_norm": 0.3173500895500183,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0959,
      "step": 42
    },
    {
      "epoch": 0.013360260991144943,
      "grad_norm": 0.47975385189056396,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0892,
      "step": 43
    },
    {
      "epoch": 0.013670964735125059,
      "grad_norm": 0.5914775133132935,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1415,
      "step": 44
    },
    {
      "epoch": 0.013981668479105173,
      "grad_norm": 0.25946399569511414,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0765,
      "step": 45
    },
    {
      "epoch": 0.013981668479105173,
      "eval_loss": 0.12117481976747513,
      "eval_runtime": 476.5823,
      "eval_samples_per_second": 5.688,
      "eval_steps_per_second": 0.711,
      "step": 45
    },
    {
      "epoch": 0.014292372223085287,
      "grad_norm": 0.3228887617588043,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1105,
      "step": 46
    },
    {
      "epoch": 0.014603075967065404,
      "grad_norm": 0.5414590239524841,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1508,
      "step": 47
    },
    {
      "epoch": 0.014913779711045518,
      "grad_norm": 0.4692119359970093,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1244,
      "step": 48
    },
    {
      "epoch": 0.015224483455025632,
      "grad_norm": 0.5145476460456848,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0949,
      "step": 49
    },
    {
      "epoch": 0.015535187199005748,
      "grad_norm": 0.3916400969028473,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0687,
      "step": 50
    },
    {
      "epoch": 0.015845890942985864,
      "grad_norm": 0.3204256296157837,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1,
      "step": 51
    },
    {
      "epoch": 0.016156594686965977,
      "grad_norm": 0.31012028455734253,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0815,
      "step": 52
    },
    {
      "epoch": 0.016467298430946093,
      "grad_norm": 0.3400692343711853,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0901,
      "step": 53
    },
    {
      "epoch": 0.01677800217492621,
      "grad_norm": 0.3835544288158417,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0983,
      "step": 54
    },
    {
      "epoch": 0.01677800217492621,
      "eval_loss": 0.1074644923210144,
      "eval_runtime": 476.89,
      "eval_samples_per_second": 5.685,
      "eval_steps_per_second": 0.711,
      "step": 54
    },
    {
      "epoch": 0.01708870591890632,
      "grad_norm": 0.29666757583618164,
      "learning_rate": 5e-05,
      "loss": 0.0944,
      "step": 55
    },
    {
      "epoch": 0.017399409662886438,
      "grad_norm": 0.427259236574173,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0895,
      "step": 56
    },
    {
      "epoch": 0.017710113406866554,
      "grad_norm": 0.5842662453651428,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1279,
      "step": 57
    },
    {
      "epoch": 0.018020817150846666,
      "grad_norm": 0.3031122386455536,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0649,
      "step": 58
    },
    {
      "epoch": 0.018331520894826783,
      "grad_norm": 0.6648306250572205,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1514,
      "step": 59
    },
    {
      "epoch": 0.0186422246388069,
      "grad_norm": 0.515338122844696,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1075,
      "step": 60
    },
    {
      "epoch": 0.01895292838278701,
      "grad_norm": 0.42272016406059265,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2258,
      "step": 61
    },
    {
      "epoch": 0.019263632126767127,
      "grad_norm": 0.3235437870025635,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0793,
      "step": 62
    },
    {
      "epoch": 0.019574335870747243,
      "grad_norm": 0.7144022583961487,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2682,
      "step": 63
    },
    {
      "epoch": 0.019574335870747243,
      "eval_loss": 0.09928452968597412,
      "eval_runtime": 476.7575,
      "eval_samples_per_second": 5.686,
      "eval_steps_per_second": 0.711,
      "step": 63
    },
    {
      "epoch": 0.019885039614727356,
      "grad_norm": 0.3919568955898285,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0866,
      "step": 64
    },
    {
      "epoch": 0.020195743358707472,
      "grad_norm": 0.2596946656703949,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1011,
      "step": 65
    },
    {
      "epoch": 0.020506447102687588,
      "grad_norm": 0.619389533996582,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2114,
      "step": 66
    },
    {
      "epoch": 0.0208171508466677,
      "grad_norm": 0.5929703116416931,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1019,
      "step": 67
    },
    {
      "epoch": 0.021127854590647817,
      "grad_norm": 0.2772235870361328,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0602,
      "step": 68
    },
    {
      "epoch": 0.021438558334627933,
      "grad_norm": 0.6497057676315308,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1489,
      "step": 69
    },
    {
      "epoch": 0.021749262078608046,
      "grad_norm": 0.3832882344722748,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0773,
      "step": 70
    },
    {
      "epoch": 0.02205996582258816,
      "grad_norm": 0.2511863112449646,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.112,
      "step": 71
    },
    {
      "epoch": 0.022370669566568278,
      "grad_norm": 0.7245559096336365,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.153,
      "step": 72
    },
    {
      "epoch": 0.022370669566568278,
      "eval_loss": 0.09493355453014374,
      "eval_runtime": 476.8146,
      "eval_samples_per_second": 5.686,
      "eval_steps_per_second": 0.711,
      "step": 72
    },
    {
      "epoch": 0.022681373310548394,
      "grad_norm": 0.31734803318977356,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.048,
      "step": 73
    },
    {
      "epoch": 0.022992077054528506,
      "grad_norm": 0.42933279275894165,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1131,
      "step": 74
    },
    {
      "epoch": 0.023302780798508622,
      "grad_norm": 0.30525970458984375,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0717,
      "step": 75
    },
    {
      "epoch": 0.02361348454248874,
      "grad_norm": 0.40439170598983765,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1148,
      "step": 76
    },
    {
      "epoch": 0.02392418828646885,
      "grad_norm": 0.628427267074585,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0704,
      "step": 77
    },
    {
      "epoch": 0.024234892030448967,
      "grad_norm": 0.5532355308532715,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0994,
      "step": 78
    },
    {
      "epoch": 0.024545595774429083,
      "grad_norm": 0.18102148175239563,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0508,
      "step": 79
    },
    {
      "epoch": 0.024856299518409196,
      "grad_norm": 0.28862491250038147,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0626,
      "step": 80
    },
    {
      "epoch": 0.025167003262389312,
      "grad_norm": 0.44811418652534485,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0762,
      "step": 81
    },
    {
      "epoch": 0.025167003262389312,
      "eval_loss": 0.09211050719022751,
      "eval_runtime": 476.7462,
      "eval_samples_per_second": 5.686,
      "eval_steps_per_second": 0.711,
      "step": 81
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.2729843854904175,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0549,
      "step": 82
    },
    {
      "epoch": 0.02578841075034954,
      "grad_norm": 0.4627554416656494,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1649,
      "step": 83
    },
    {
      "epoch": 0.026099114494329657,
      "grad_norm": 0.2735048234462738,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0503,
      "step": 84
    },
    {
      "epoch": 0.026409818238309773,
      "grad_norm": 0.45912477374076843,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0694,
      "step": 85
    },
    {
      "epoch": 0.026720521982289885,
      "grad_norm": 0.2504335641860962,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0768,
      "step": 86
    },
    {
      "epoch": 0.02703122572627,
      "grad_norm": 0.5822497010231018,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0832,
      "step": 87
    },
    {
      "epoch": 0.027341929470250118,
      "grad_norm": 0.4059930443763733,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0662,
      "step": 88
    },
    {
      "epoch": 0.02765263321423023,
      "grad_norm": 0.3446873724460602,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0653,
      "step": 89
    },
    {
      "epoch": 0.027963336958210346,
      "grad_norm": 0.5446871519088745,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1038,
      "step": 90
    },
    {
      "epoch": 0.027963336958210346,
      "eval_loss": 0.0907156765460968,
      "eval_runtime": 476.7657,
      "eval_samples_per_second": 5.686,
      "eval_steps_per_second": 0.711,
      "step": 90
    },
    {
      "epoch": 0.028274040702190462,
      "grad_norm": 0.28611159324645996,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0804,
      "step": 91
    },
    {
      "epoch": 0.028584744446170575,
      "grad_norm": 0.526472270488739,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0755,
      "step": 92
    },
    {
      "epoch": 0.02889544819015069,
      "grad_norm": 0.2932213842868805,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1271,
      "step": 93
    },
    {
      "epoch": 0.029206151934130807,
      "grad_norm": 0.4505036771297455,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0581,
      "step": 94
    },
    {
      "epoch": 0.02951685567811092,
      "grad_norm": 0.37807580828666687,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0832,
      "step": 95
    },
    {
      "epoch": 0.029827559422091036,
      "grad_norm": 0.41597023606300354,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1158,
      "step": 96
    },
    {
      "epoch": 0.030138263166071152,
      "grad_norm": 0.5798332095146179,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.3012,
      "step": 97
    },
    {
      "epoch": 0.030448966910051264,
      "grad_norm": 0.22657930850982666,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0659,
      "step": 98
    },
    {
      "epoch": 0.03075967065403138,
      "grad_norm": 0.23417678475379944,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0867,
      "step": 99
    },
    {
      "epoch": 0.03075967065403138,
      "eval_loss": 0.09054123610258102,
      "eval_runtime": 476.6412,
      "eval_samples_per_second": 5.688,
      "eval_steps_per_second": 0.711,
      "step": 99
    },
    {
      "epoch": 0.031070374398011497,
      "grad_norm": 0.29348117113113403,
      "learning_rate": 0.0,
      "loss": 0.07,
      "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": 4.5274515111936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}