{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2442002442002442,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002442002442002442,
      "grad_norm": 4.003821849822998,
      "learning_rate": 1e-05,
      "loss": 3.5448,
      "step": 1
    },
    {
      "epoch": 0.002442002442002442,
      "eval_loss": 3.4570086002349854,
      "eval_runtime": 17.1854,
      "eval_samples_per_second": 20.075,
      "eval_steps_per_second": 2.56,
      "step": 1
    },
    {
      "epoch": 0.004884004884004884,
      "grad_norm": 4.212690353393555,
      "learning_rate": 2e-05,
      "loss": 3.29,
      "step": 2
    },
    {
      "epoch": 0.007326007326007326,
      "grad_norm": 3.684267282485962,
      "learning_rate": 3e-05,
      "loss": 3.2101,
      "step": 3
    },
    {
      "epoch": 0.009768009768009768,
      "grad_norm": 4.348191738128662,
      "learning_rate": 4e-05,
      "loss": 3.6773,
      "step": 4
    },
    {
      "epoch": 0.01221001221001221,
      "grad_norm": 3.9922070503234863,
      "learning_rate": 5e-05,
      "loss": 3.4306,
      "step": 5
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 3.5863325595855713,
      "learning_rate": 6e-05,
      "loss": 3.3782,
      "step": 6
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 3.6543312072753906,
      "learning_rate": 7e-05,
      "loss": 3.2914,
      "step": 7
    },
    {
      "epoch": 0.019536019536019536,
      "grad_norm": 2.883704900741577,
      "learning_rate": 8e-05,
      "loss": 2.8062,
      "step": 8
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 2.7370340824127197,
      "learning_rate": 9e-05,
      "loss": 2.8026,
      "step": 9
    },
    {
      "epoch": 0.02197802197802198,
      "eval_loss": 2.863778591156006,
      "eval_runtime": 17.1862,
      "eval_samples_per_second": 20.074,
      "eval_steps_per_second": 2.56,
      "step": 9
    },
    {
      "epoch": 0.02442002442002442,
      "grad_norm": 3.3165810108184814,
      "learning_rate": 0.0001,
      "loss": 2.9095,
      "step": 10
    },
    {
      "epoch": 0.026862026862026864,
      "grad_norm": 3.8215725421905518,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.8289,
      "step": 11
    },
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 3.539818286895752,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2962,
      "step": 12
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 3.0036020278930664,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.569,
      "step": 13
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 3.063443422317505,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6549,
      "step": 14
    },
    {
      "epoch": 0.03663003663003663,
      "grad_norm": 2.7809972763061523,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.7653,
      "step": 15
    },
    {
      "epoch": 0.03907203907203907,
      "grad_norm": 2.9072892665863037,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.6655,
      "step": 16
    },
    {
      "epoch": 0.04151404151404151,
      "grad_norm": 2.6445059776306152,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.7984,
      "step": 17
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 2.6554043292999268,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6775,
      "step": 18
    },
    {
      "epoch": 0.04395604395604396,
      "eval_loss": 2.5405185222625732,
      "eval_runtime": 17.192,
      "eval_samples_per_second": 20.067,
      "eval_steps_per_second": 2.559,
      "step": 18
    },
    {
      "epoch": 0.0463980463980464,
      "grad_norm": 2.496406316757202,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.4901,
      "step": 19
    },
    {
      "epoch": 0.04884004884004884,
      "grad_norm": 2.5684244632720947,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.7073,
      "step": 20
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 2.4029531478881836,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.1923,
      "step": 21
    },
    {
      "epoch": 0.05372405372405373,
      "grad_norm": 2.1948258876800537,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.4754,
      "step": 22
    },
    {
      "epoch": 0.05616605616605617,
      "grad_norm": 2.6035783290863037,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.8365,
      "step": 23
    },
    {
      "epoch": 0.05860805860805861,
      "grad_norm": 2.6996240615844727,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.1656,
      "step": 24
    },
    {
      "epoch": 0.06105006105006105,
      "grad_norm": 2.1867291927337646,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.509,
      "step": 25
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 2.629974842071533,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.4488,
      "step": 26
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.655991554260254,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.2719,
      "step": 27
    },
    {
      "epoch": 0.06593406593406594,
      "eval_loss": 2.3683769702911377,
      "eval_runtime": 17.208,
      "eval_samples_per_second": 20.049,
      "eval_steps_per_second": 2.557,
      "step": 27
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 2.4463114738464355,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4659,
      "step": 28
    },
    {
      "epoch": 0.07081807081807082,
      "grad_norm": 2.276737928390503,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.4116,
      "step": 29
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 2.5003745555877686,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1826,
      "step": 30
    },
    {
      "epoch": 0.0757020757020757,
      "grad_norm": 2.833949565887451,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.4994,
      "step": 31
    },
    {
      "epoch": 0.07814407814407814,
      "grad_norm": 2.667140007019043,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.4033,
      "step": 32
    },
    {
      "epoch": 0.08058608058608059,
      "grad_norm": 2.864898920059204,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.1158,
      "step": 33
    },
    {
      "epoch": 0.08302808302808302,
      "grad_norm": 3.267824172973633,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.0373,
      "step": 34
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 2.865539789199829,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.4525,
      "step": 35
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 2.8213765621185303,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.3295,
      "step": 36
    },
    {
      "epoch": 0.08791208791208792,
      "eval_loss": 2.2654080390930176,
      "eval_runtime": 17.1512,
      "eval_samples_per_second": 20.115,
      "eval_steps_per_second": 2.565,
      "step": 36
    },
    {
      "epoch": 0.09035409035409035,
      "grad_norm": 2.6522955894470215,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0216,
      "step": 37
    },
    {
      "epoch": 0.0927960927960928,
      "grad_norm": 2.883388042449951,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2312,
      "step": 38
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 2.54302978515625,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.3645,
      "step": 39
    },
    {
      "epoch": 0.09768009768009768,
      "grad_norm": 2.6332242488861084,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2103,
      "step": 40
    },
    {
      "epoch": 0.10012210012210013,
      "grad_norm": 2.973139762878418,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3439,
      "step": 41
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.7934212684631348,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.1581,
      "step": 42
    },
    {
      "epoch": 0.10500610500610501,
      "grad_norm": 2.8419196605682373,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.3719,
      "step": 43
    },
    {
      "epoch": 0.10744810744810745,
      "grad_norm": 2.6125094890594482,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.1408,
      "step": 44
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 2.8555796146392822,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.3435,
      "step": 45
    },
    {
      "epoch": 0.10989010989010989,
      "eval_loss": 2.1842544078826904,
      "eval_runtime": 17.2121,
      "eval_samples_per_second": 20.044,
      "eval_steps_per_second": 2.556,
      "step": 45
    },
    {
      "epoch": 0.11233211233211234,
      "grad_norm": 3.3376097679138184,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1704,
      "step": 46
    },
    {
      "epoch": 0.11477411477411477,
      "grad_norm": 3.228142499923706,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.2675,
      "step": 47
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 3.246316432952881,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2922,
      "step": 48
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 3.411884307861328,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1232,
      "step": 49
    },
    {
      "epoch": 0.1221001221001221,
      "grad_norm": 2.7644128799438477,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.9756,
      "step": 50
    },
    {
      "epoch": 0.12454212454212454,
      "grad_norm": 2.9831814765930176,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.1691,
      "step": 51
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 2.948953628540039,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.2066,
      "step": 52
    },
    {
      "epoch": 0.12942612942612944,
      "grad_norm": 3.319122552871704,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.0857,
      "step": 53
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 3.127619743347168,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.9764,
      "step": 54
    },
    {
      "epoch": 0.13186813186813187,
      "eval_loss": 2.127415180206299,
      "eval_runtime": 17.2075,
      "eval_samples_per_second": 20.049,
      "eval_steps_per_second": 2.557,
      "step": 54
    },
    {
      "epoch": 0.1343101343101343,
      "grad_norm": 3.369476795196533,
      "learning_rate": 5e-05,
      "loss": 2.194,
      "step": 55
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 3.0237653255462646,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.1449,
      "step": 56
    },
    {
      "epoch": 0.1391941391941392,
      "grad_norm": 2.8375723361968994,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.2385,
      "step": 57
    },
    {
      "epoch": 0.14163614163614163,
      "grad_norm": 3.1608798503875732,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7792,
      "step": 58
    },
    {
      "epoch": 0.14407814407814407,
      "grad_norm": 3.247514247894287,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.1278,
      "step": 59
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 3.289715051651001,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.3176,
      "step": 60
    },
    {
      "epoch": 0.14896214896214896,
      "grad_norm": 3.2936837673187256,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.072,
      "step": 61
    },
    {
      "epoch": 0.1514041514041514,
      "grad_norm": 3.1719565391540527,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.916,
      "step": 62
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 2.834185838699341,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.0461,
      "step": 63
    },
    {
      "epoch": 0.15384615384615385,
      "eval_loss": 2.0899388790130615,
      "eval_runtime": 17.2055,
      "eval_samples_per_second": 20.052,
      "eval_steps_per_second": 2.557,
      "step": 63
    },
    {
      "epoch": 0.1562881562881563,
      "grad_norm": 3.3529248237609863,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0755,
      "step": 64
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 3.64978289604187,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.2543,
      "step": 65
    },
    {
      "epoch": 0.16117216117216118,
      "grad_norm": 2.9989237785339355,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.9864,
      "step": 66
    },
    {
      "epoch": 0.16361416361416362,
      "grad_norm": 3.2978744506835938,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1456,
      "step": 67
    },
    {
      "epoch": 0.16605616605616605,
      "grad_norm": 3.1260225772857666,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1197,
      "step": 68
    },
    {
      "epoch": 0.1684981684981685,
      "grad_norm": 2.8456709384918213,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.1985,
      "step": 69
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 3.1655471324920654,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1985,
      "step": 70
    },
    {
      "epoch": 0.17338217338217338,
      "grad_norm": 3.4631283283233643,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.0562,
      "step": 71
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 2.9049081802368164,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.0665,
      "step": 72
    },
    {
      "epoch": 0.17582417582417584,
      "eval_loss": 2.0659754276275635,
      "eval_runtime": 17.2028,
      "eval_samples_per_second": 20.055,
      "eval_steps_per_second": 2.558,
      "step": 72
    },
    {
      "epoch": 0.17826617826617827,
      "grad_norm": 3.1705820560455322,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.2104,
      "step": 73
    },
    {
      "epoch": 0.1807081807081807,
      "grad_norm": 3.19238543510437,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8963,
      "step": 74
    },
    {
      "epoch": 0.18315018315018314,
      "grad_norm": 2.8358798027038574,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.1482,
      "step": 75
    },
    {
      "epoch": 0.1855921855921856,
      "grad_norm": 3.2111284732818604,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.0634,
      "step": 76
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 3.5797221660614014,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8014,
      "step": 77
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.0201733112335205,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.0404,
      "step": 78
    },
    {
      "epoch": 0.19291819291819293,
      "grad_norm": 3.203850507736206,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.1296,
      "step": 79
    },
    {
      "epoch": 0.19536019536019536,
      "grad_norm": 2.728576898574829,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.9965,
      "step": 80
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 3.051905632019043,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.2437,
      "step": 81
    },
    {
      "epoch": 0.1978021978021978,
      "eval_loss": 2.0485291481018066,
      "eval_runtime": 17.19,
      "eval_samples_per_second": 20.07,
      "eval_steps_per_second": 2.56,
      "step": 81
    },
    {
      "epoch": 0.20024420024420025,
      "grad_norm": 3.3389062881469727,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.0766,
      "step": 82
    },
    {
      "epoch": 0.2026862026862027,
      "grad_norm": 3.4000632762908936,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.0668,
      "step": 83
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 3.469282627105713,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.9469,
      "step": 84
    },
    {
      "epoch": 0.20757020757020758,
      "grad_norm": 3.1487700939178467,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.0561,
      "step": 85
    },
    {
      "epoch": 0.21001221001221002,
      "grad_norm": 3.3516573905944824,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.4972,
      "step": 86
    },
    {
      "epoch": 0.21245421245421245,
      "grad_norm": 3.0450797080993652,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.0687,
      "step": 87
    },
    {
      "epoch": 0.2148962148962149,
      "grad_norm": 3.4229252338409424,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1243,
      "step": 88
    },
    {
      "epoch": 0.21733821733821734,
      "grad_norm": 3.3112401962280273,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.0881,
      "step": 89
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 2.852926015853882,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.0004,
      "step": 90
    },
    {
      "epoch": 0.21978021978021978,
      "eval_loss": 2.040705919265747,
      "eval_runtime": 17.1884,
      "eval_samples_per_second": 20.072,
      "eval_steps_per_second": 2.56,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.144771099090576,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.2776,
      "step": 91
    },
    {
      "epoch": 0.22466422466422467,
      "grad_norm": 2.85107159614563,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1482,
      "step": 92
    },
    {
      "epoch": 0.2271062271062271,
      "grad_norm": 3.379453182220459,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.0163,
      "step": 93
    },
    {
      "epoch": 0.22954822954822954,
      "grad_norm": 3.250808000564575,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.114,
      "step": 94
    },
    {
      "epoch": 0.231990231990232,
      "grad_norm": 3.544097423553467,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.875,
      "step": 95
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 3.2743308544158936,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.9819,
      "step": 96
    },
    {
      "epoch": 0.23687423687423687,
      "grad_norm": 3.108639717102051,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.3488,
      "step": 97
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 3.2740273475646973,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.3454,
      "step": 98
    },
    {
      "epoch": 0.24175824175824176,
      "grad_norm": 2.951927661895752,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.0124,
      "step": 99
    },
    {
      "epoch": 0.24175824175824176,
      "eval_loss": 2.0391764640808105,
      "eval_runtime": 17.1917,
      "eval_samples_per_second": 20.068,
      "eval_steps_per_second": 2.559,
      "step": 99
    },
    {
      "epoch": 0.2442002442002442,
      "grad_norm": 3.4022247791290283,
      "learning_rate": 0.0,
      "loss": 2.0964,
      "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": 1.96755069075456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}