{
  "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": 0.3979324400424957,
      "learning_rate": 1e-05,
      "loss": 0.3706,
      "step": 1
    },
    {
      "epoch": 0.00031070374398011494,
      "eval_loss": 0.5521897673606873,
      "eval_runtime": 478.798,
      "eval_samples_per_second": 5.662,
      "eval_steps_per_second": 0.708,
      "step": 1
    },
    {
      "epoch": 0.0006214074879602299,
      "grad_norm": 0.8664864897727966,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 2
    },
    {
      "epoch": 0.0009321112319403449,
      "grad_norm": 0.4651488661766052,
      "learning_rate": 3e-05,
      "loss": 0.4161,
      "step": 3
    },
    {
      "epoch": 0.0012428149759204598,
      "grad_norm": 0.4391263425350189,
      "learning_rate": 4e-05,
      "loss": 0.3542,
      "step": 4
    },
    {
      "epoch": 0.0015535187199005747,
      "grad_norm": 0.7842640280723572,
      "learning_rate": 5e-05,
      "loss": 0.76,
      "step": 5
    },
    {
      "epoch": 0.0018642224638806897,
      "grad_norm": 0.41998252272605896,
      "learning_rate": 6e-05,
      "loss": 0.2956,
      "step": 6
    },
    {
      "epoch": 0.0021749262078608047,
      "grad_norm": 0.5816775560379028,
      "learning_rate": 7e-05,
      "loss": 0.5142,
      "step": 7
    },
    {
      "epoch": 0.0024856299518409195,
      "grad_norm": 0.42541053891181946,
      "learning_rate": 8e-05,
      "loss": 0.3005,
      "step": 8
    },
    {
      "epoch": 0.0027963336958210347,
      "grad_norm": 0.5307878851890564,
      "learning_rate": 9e-05,
      "loss": 0.4065,
      "step": 9
    },
    {
      "epoch": 0.0027963336958210347,
      "eval_loss": 0.4081890881061554,
      "eval_runtime": 478.547,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 9
    },
    {
      "epoch": 0.0031070374398011495,
      "grad_norm": 0.5609463453292847,
      "learning_rate": 0.0001,
      "loss": 0.343,
      "step": 10
    },
    {
      "epoch": 0.0034177411837812647,
      "grad_norm": 0.3241025507450104,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.3513,
      "step": 11
    },
    {
      "epoch": 0.0037284449277613795,
      "grad_norm": 0.618793785572052,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3196,
      "step": 12
    },
    {
      "epoch": 0.004039148671741494,
      "grad_norm": 0.5527074337005615,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3386,
      "step": 13
    },
    {
      "epoch": 0.0043498524157216095,
      "grad_norm": 0.3217713534832001,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3191,
      "step": 14
    },
    {
      "epoch": 0.004660556159701725,
      "grad_norm": 0.6587296724319458,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2569,
      "step": 15
    },
    {
      "epoch": 0.004971259903681839,
      "grad_norm": 0.9640960693359375,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3398,
      "step": 16
    },
    {
      "epoch": 0.005281963647661954,
      "grad_norm": 0.6162159442901611,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2824,
      "step": 17
    },
    {
      "epoch": 0.005592667391642069,
      "grad_norm": 0.3180422782897949,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1648,
      "step": 18
    },
    {
      "epoch": 0.005592667391642069,
      "eval_loss": 0.24653799831867218,
      "eval_runtime": 478.527,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 18
    },
    {
      "epoch": 0.005903371135622185,
      "grad_norm": 0.31329768896102905,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1629,
      "step": 19
    },
    {
      "epoch": 0.006214074879602299,
      "grad_norm": 0.2654910087585449,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1454,
      "step": 20
    },
    {
      "epoch": 0.006524778623582414,
      "grad_norm": 0.2714911997318268,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1977,
      "step": 21
    },
    {
      "epoch": 0.006835482367562529,
      "grad_norm": 0.18957370519638062,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1122,
      "step": 22
    },
    {
      "epoch": 0.007146186111542644,
      "grad_norm": 0.38467055559158325,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1625,
      "step": 23
    },
    {
      "epoch": 0.007456889855522759,
      "grad_norm": 0.626914381980896,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2835,
      "step": 24
    },
    {
      "epoch": 0.007767593599502874,
      "grad_norm": 0.48199400305747986,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1861,
      "step": 25
    },
    {
      "epoch": 0.008078297343482988,
      "grad_norm": 0.33903753757476807,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1635,
      "step": 26
    },
    {
      "epoch": 0.008389001087463105,
      "grad_norm": 0.3818158209323883,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1259,
      "step": 27
    },
    {
      "epoch": 0.008389001087463105,
      "eval_loss": 0.18625223636627197,
      "eval_runtime": 478.5196,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 27
    },
    {
      "epoch": 0.008699704831443219,
      "grad_norm": 0.3403395712375641,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1403,
      "step": 28
    },
    {
      "epoch": 0.009010408575423333,
      "grad_norm": 0.3787979185581207,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.159,
      "step": 29
    },
    {
      "epoch": 0.00932111231940345,
      "grad_norm": 0.46852102875709534,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2222,
      "step": 30
    },
    {
      "epoch": 0.009631816063383564,
      "grad_norm": 0.5512856841087341,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1744,
      "step": 31
    },
    {
      "epoch": 0.009942519807363678,
      "grad_norm": 0.2995116114616394,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.119,
      "step": 32
    },
    {
      "epoch": 0.010253223551343794,
      "grad_norm": 0.2171677201986313,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1134,
      "step": 33
    },
    {
      "epoch": 0.010563927295323908,
      "grad_norm": 0.2736062705516815,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1293,
      "step": 34
    },
    {
      "epoch": 0.010874631039304023,
      "grad_norm": 0.7495072484016418,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1346,
      "step": 35
    },
    {
      "epoch": 0.011185334783284139,
      "grad_norm": 0.5948975086212158,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.144,
      "step": 36
    },
    {
      "epoch": 0.011185334783284139,
      "eval_loss": 0.14601945877075195,
      "eval_runtime": 478.5299,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 36
    },
    {
      "epoch": 0.011496038527264253,
      "grad_norm": 0.4023019075393677,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1502,
      "step": 37
    },
    {
      "epoch": 0.01180674227124437,
      "grad_norm": 0.43612515926361084,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.153,
      "step": 38
    },
    {
      "epoch": 0.012117446015224484,
      "grad_norm": 0.6205630898475647,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1269,
      "step": 39
    },
    {
      "epoch": 0.012428149759204598,
      "grad_norm": 0.29479214549064636,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2117,
      "step": 40
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.5156003832817078,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0794,
      "step": 41
    },
    {
      "epoch": 0.013049557247164828,
      "grad_norm": 0.31090861558914185,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0933,
      "step": 42
    },
    {
      "epoch": 0.013360260991144943,
      "grad_norm": 0.4626767039299011,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0868,
      "step": 43
    },
    {
      "epoch": 0.013670964735125059,
      "grad_norm": 0.5885339379310608,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1403,
      "step": 44
    },
    {
      "epoch": 0.013981668479105173,
      "grad_norm": 0.29251593351364136,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.078,
      "step": 45
    },
    {
      "epoch": 0.013981668479105173,
      "eval_loss": 0.12018238008022308,
      "eval_runtime": 478.5318,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 45
    },
    {
      "epoch": 0.014292372223085287,
      "grad_norm": 0.32098764181137085,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1104,
      "step": 46
    },
    {
      "epoch": 0.014603075967065404,
      "grad_norm": 0.5425329804420471,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1494,
      "step": 47
    },
    {
      "epoch": 0.014913779711045518,
      "grad_norm": 0.40288758277893066,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.123,
      "step": 48
    },
    {
      "epoch": 0.015224483455025632,
      "grad_norm": 0.5317268967628479,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0999,
      "step": 49
    },
    {
      "epoch": 0.015535187199005748,
      "grad_norm": 0.3459482789039612,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0676,
      "step": 50
    },
    {
      "epoch": 0.015845890942985864,
      "grad_norm": 0.33869612216949463,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1034,
      "step": 51
    },
    {
      "epoch": 0.016156594686965977,
      "grad_norm": 0.3105941414833069,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0806,
      "step": 52
    },
    {
      "epoch": 0.016467298430946093,
      "grad_norm": 0.34324607253074646,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0889,
      "step": 53
    },
    {
      "epoch": 0.01677800217492621,
      "grad_norm": 0.38898375630378723,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0993,
      "step": 54
    },
    {
      "epoch": 0.01677800217492621,
      "eval_loss": 0.10659828037023544,
      "eval_runtime": 478.6444,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.708,
      "step": 54
    },
    {
      "epoch": 0.01708870591890632,
      "grad_norm": 0.30846843123435974,
      "learning_rate": 5e-05,
      "loss": 0.097,
      "step": 55
    },
    {
      "epoch": 0.017399409662886438,
      "grad_norm": 0.4181019961833954,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0903,
      "step": 56
    },
    {
      "epoch": 0.017710113406866554,
      "grad_norm": 0.528732180595398,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1247,
      "step": 57
    },
    {
      "epoch": 0.018020817150846666,
      "grad_norm": 0.33058804273605347,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0668,
      "step": 58
    },
    {
      "epoch": 0.018331520894826783,
      "grad_norm": 0.6249443292617798,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1474,
      "step": 59
    },
    {
      "epoch": 0.0186422246388069,
      "grad_norm": 0.48911044001579285,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1056,
      "step": 60
    },
    {
      "epoch": 0.01895292838278701,
      "grad_norm": 0.42180556058883667,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2277,
      "step": 61
    },
    {
      "epoch": 0.019263632126767127,
      "grad_norm": 0.29567211866378784,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0761,
      "step": 62
    },
    {
      "epoch": 0.019574335870747243,
      "grad_norm": 0.6346483826637268,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2634,
      "step": 63
    },
    {
      "epoch": 0.019574335870747243,
      "eval_loss": 0.09913559257984161,
      "eval_runtime": 478.65,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.708,
      "step": 63
    },
    {
      "epoch": 0.019885039614727356,
      "grad_norm": 0.4134097695350647,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0839,
      "step": 64
    },
    {
      "epoch": 0.020195743358707472,
      "grad_norm": 0.2704060971736908,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1007,
      "step": 65
    },
    {
      "epoch": 0.020506447102687588,
      "grad_norm": 0.5956614017486572,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2097,
      "step": 66
    },
    {
      "epoch": 0.0208171508466677,
      "grad_norm": 0.6127525568008423,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0984,
      "step": 67
    },
    {
      "epoch": 0.021127854590647817,
      "grad_norm": 0.26547056436538696,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0601,
      "step": 68
    },
    {
      "epoch": 0.021438558334627933,
      "grad_norm": 0.6513274312019348,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.145,
      "step": 69
    },
    {
      "epoch": 0.021749262078608046,
      "grad_norm": 0.3579119145870209,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0754,
      "step": 70
    },
    {
      "epoch": 0.02205996582258816,
      "grad_norm": 0.25781944394111633,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1109,
      "step": 71
    },
    {
      "epoch": 0.022370669566568278,
      "grad_norm": 0.7353035807609558,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.153,
      "step": 72
    },
    {
      "epoch": 0.022370669566568278,
      "eval_loss": 0.09439601004123688,
      "eval_runtime": 478.6405,
      "eval_samples_per_second": 5.664,
      "eval_steps_per_second": 0.708,
      "step": 72
    },
    {
      "epoch": 0.022681373310548394,
      "grad_norm": 0.42085394263267517,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0514,
      "step": 73
    },
    {
      "epoch": 0.022992077054528506,
      "grad_norm": 0.44704753160476685,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.116,
      "step": 74
    },
    {
      "epoch": 0.023302780798508622,
      "grad_norm": 0.3115587830543518,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0713,
      "step": 75
    },
    {
      "epoch": 0.02361348454248874,
      "grad_norm": 0.38487324118614197,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1164,
      "step": 76
    },
    {
      "epoch": 0.02392418828646885,
      "grad_norm": 0.5476064682006836,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0682,
      "step": 77
    },
    {
      "epoch": 0.024234892030448967,
      "grad_norm": 0.5468012690544128,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0986,
      "step": 78
    },
    {
      "epoch": 0.024545595774429083,
      "grad_norm": 0.18167272210121155,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0497,
      "step": 79
    },
    {
      "epoch": 0.024856299518409196,
      "grad_norm": 0.2906138300895691,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0629,
      "step": 80
    },
    {
      "epoch": 0.025167003262389312,
      "grad_norm": 0.4465659260749817,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0762,
      "step": 81
    },
    {
      "epoch": 0.025167003262389312,
      "eval_loss": 0.09172177314758301,
      "eval_runtime": 478.5611,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 81
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.26898109912872314,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0526,
      "step": 82
    },
    {
      "epoch": 0.02578841075034954,
      "grad_norm": 0.5038782954216003,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1666,
      "step": 83
    },
    {
      "epoch": 0.026099114494329657,
      "grad_norm": 0.2767373025417328,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0521,
      "step": 84
    },
    {
      "epoch": 0.026409818238309773,
      "grad_norm": 0.5038904547691345,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0702,
      "step": 85
    },
    {
      "epoch": 0.026720521982289885,
      "grad_norm": 0.263021856546402,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0777,
      "step": 86
    },
    {
      "epoch": 0.02703122572627,
      "grad_norm": 0.5625424385070801,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0838,
      "step": 87
    },
    {
      "epoch": 0.027341929470250118,
      "grad_norm": 0.4216459095478058,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0653,
      "step": 88
    },
    {
      "epoch": 0.02765263321423023,
      "grad_norm": 0.3736090660095215,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0643,
      "step": 89
    },
    {
      "epoch": 0.027963336958210346,
      "grad_norm": 0.5854941606521606,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1054,
      "step": 90
    },
    {
      "epoch": 0.027963336958210346,
      "eval_loss": 0.09043664485216141,
      "eval_runtime": 478.5777,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 90
    },
    {
      "epoch": 0.028274040702190462,
      "grad_norm": 0.2925987243652344,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0793,
      "step": 91
    },
    {
      "epoch": 0.028584744446170575,
      "grad_norm": 0.5664364099502563,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0755,
      "step": 92
    },
    {
      "epoch": 0.02889544819015069,
      "grad_norm": 0.29245734214782715,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1267,
      "step": 93
    },
    {
      "epoch": 0.029206151934130807,
      "grad_norm": 0.45084962248802185,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0548,
      "step": 94
    },
    {
      "epoch": 0.02951685567811092,
      "grad_norm": 0.39742884039878845,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0825,
      "step": 95
    },
    {
      "epoch": 0.029827559422091036,
      "grad_norm": 0.4094812273979187,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1132,
      "step": 96
    },
    {
      "epoch": 0.030138263166071152,
      "grad_norm": 0.5582484006881714,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.3011,
      "step": 97
    },
    {
      "epoch": 0.030448966910051264,
      "grad_norm": 0.26959139108657837,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0663,
      "step": 98
    },
    {
      "epoch": 0.03075967065403138,
      "grad_norm": 0.22900760173797607,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0863,
      "step": 99
    },
    {
      "epoch": 0.03075967065403138,
      "eval_loss": 0.09016219526529312,
      "eval_runtime": 478.5425,
      "eval_samples_per_second": 5.665,
      "eval_steps_per_second": 0.708,
      "step": 99
    },
    {
      "epoch": 0.031070374398011497,
      "grad_norm": 0.30340513586997986,
      "learning_rate": 0.0,
      "loss": 0.0709,
      "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
}