{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.91324200913242,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0091324200913242,
      "grad_norm": 1.084800362586975,
      "learning_rate": 1e-05,
      "loss": 2.8326,
      "step": 1
    },
    {
      "epoch": 0.0091324200913242,
      "eval_loss": 2.798067092895508,
      "eval_runtime": 21.5901,
      "eval_samples_per_second": 4.308,
      "eval_steps_per_second": 0.556,
      "step": 1
    },
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 1.2182632684707642,
      "learning_rate": 2e-05,
      "loss": 2.9614,
      "step": 2
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 1.6452730894088745,
      "learning_rate": 3e-05,
      "loss": 2.8599,
      "step": 3
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.8521353006362915,
      "learning_rate": 4e-05,
      "loss": 2.8872,
      "step": 4
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 1.6193654537200928,
      "learning_rate": 5e-05,
      "loss": 2.9812,
      "step": 5
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.8667663335800171,
      "learning_rate": 6e-05,
      "loss": 2.6056,
      "step": 6
    },
    {
      "epoch": 0.0639269406392694,
      "grad_norm": 0.769944965839386,
      "learning_rate": 7e-05,
      "loss": 2.6849,
      "step": 7
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.6952024698257446,
      "learning_rate": 8e-05,
      "loss": 2.8224,
      "step": 8
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 0.5516144037246704,
      "learning_rate": 9e-05,
      "loss": 2.7377,
      "step": 9
    },
    {
      "epoch": 0.0821917808219178,
      "eval_loss": 2.5981481075286865,
      "eval_runtime": 20.8343,
      "eval_samples_per_second": 4.464,
      "eval_steps_per_second": 0.576,
      "step": 9
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.42393094301223755,
      "learning_rate": 0.0001,
      "loss": 2.6221,
      "step": 10
    },
    {
      "epoch": 0.1004566210045662,
      "grad_norm": 0.6319543123245239,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.6145,
      "step": 11
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.5436657071113586,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.7166,
      "step": 12
    },
    {
      "epoch": 0.1187214611872146,
      "grad_norm": 0.8254231214523315,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.7582,
      "step": 13
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 0.8472221493721008,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6982,
      "step": 14
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.8218504786491394,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.6974,
      "step": 15
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.5962392687797546,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.6403,
      "step": 16
    },
    {
      "epoch": 0.1552511415525114,
      "grad_norm": 0.5021297931671143,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2763,
      "step": 17
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.5453546643257141,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6802,
      "step": 18
    },
    {
      "epoch": 0.1643835616438356,
      "eval_loss": 2.4870386123657227,
      "eval_runtime": 20.8336,
      "eval_samples_per_second": 4.464,
      "eval_steps_per_second": 0.576,
      "step": 18
    },
    {
      "epoch": 0.1735159817351598,
      "grad_norm": 0.4549436867237091,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.527,
      "step": 19
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.5642745494842529,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2381,
      "step": 20
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.6105585694313049,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.6864,
      "step": 21
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 0.5239546298980713,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.5988,
      "step": 22
    },
    {
      "epoch": 0.2100456621004566,
      "grad_norm": 0.42599719762802124,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.6572,
      "step": 23
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.44432634115219116,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.4072,
      "step": 24
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 0.35761409997940063,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.4447,
      "step": 25
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 0.5584380626678467,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.6289,
      "step": 26
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.4284055233001709,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3918,
      "step": 27
    },
    {
      "epoch": 0.2465753424657534,
      "eval_loss": 2.4019358158111572,
      "eval_runtime": 20.8512,
      "eval_samples_per_second": 4.46,
      "eval_steps_per_second": 0.576,
      "step": 27
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 0.4879898130893707,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.1281,
      "step": 28
    },
    {
      "epoch": 0.2648401826484018,
      "grad_norm": 0.41476884484291077,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.1886,
      "step": 29
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.44141650199890137,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.358,
      "step": 30
    },
    {
      "epoch": 0.2831050228310502,
      "grad_norm": 0.4332883358001709,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.3373,
      "step": 31
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.3508234918117523,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.3777,
      "step": 32
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.45701152086257935,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.1395,
      "step": 33
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 0.46137839555740356,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2298,
      "step": 34
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 0.44093969464302063,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.1593,
      "step": 35
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.39953914284706116,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.428,
      "step": 36
    },
    {
      "epoch": 0.3287671232876712,
      "eval_loss": 2.3425583839416504,
      "eval_runtime": 20.8286,
      "eval_samples_per_second": 4.465,
      "eval_steps_per_second": 0.576,
      "step": 36
    },
    {
      "epoch": 0.3378995433789954,
      "grad_norm": 0.5955489873886108,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.3129,
      "step": 37
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 0.4501381814479828,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.1981,
      "step": 38
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.5031882524490356,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.135,
      "step": 39
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.4565059244632721,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3784,
      "step": 40
    },
    {
      "epoch": 0.3744292237442922,
      "grad_norm": 0.499051958322525,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.4311,
      "step": 41
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.4589824676513672,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.2253,
      "step": 42
    },
    {
      "epoch": 0.3926940639269406,
      "grad_norm": 0.5880911946296692,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.631,
      "step": 43
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 0.5631856918334961,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.276,
      "step": 44
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.49337872862815857,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.4768,
      "step": 45
    },
    {
      "epoch": 0.410958904109589,
      "eval_loss": 2.3006603717803955,
      "eval_runtime": 20.8313,
      "eval_samples_per_second": 4.464,
      "eval_steps_per_second": 0.576,
      "step": 45
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 0.5138399004936218,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1801,
      "step": 46
    },
    {
      "epoch": 0.4292237442922374,
      "grad_norm": 0.5627867579460144,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.7648,
      "step": 47
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.4585358500480652,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.347,
      "step": 48
    },
    {
      "epoch": 0.4474885844748858,
      "grad_norm": 0.46846991777420044,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.4827,
      "step": 49
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.46761196851730347,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.4759,
      "step": 50
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.6463755369186401,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.6691,
      "step": 51
    },
    {
      "epoch": 0.4748858447488584,
      "grad_norm": 0.5370874404907227,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.9535,
      "step": 52
    },
    {
      "epoch": 0.4840182648401826,
      "grad_norm": 0.5238595604896545,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.3709,
      "step": 53
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.397002637386322,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.2094,
      "step": 54
    },
    {
      "epoch": 0.4931506849315068,
      "eval_loss": 2.2663588523864746,
      "eval_runtime": 20.8487,
      "eval_samples_per_second": 4.461,
      "eval_steps_per_second": 0.576,
      "step": 54
    },
    {
      "epoch": 0.502283105022831,
      "grad_norm": 0.5351884365081787,
      "learning_rate": 5e-05,
      "loss": 2.3405,
      "step": 55
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 0.5713867545127869,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.3341,
      "step": 56
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.5104215741157532,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.362,
      "step": 57
    },
    {
      "epoch": 0.5296803652968036,
      "grad_norm": 0.539503812789917,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.2757,
      "step": 58
    },
    {
      "epoch": 0.5388127853881278,
      "grad_norm": 0.621566116809845,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2117,
      "step": 59
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.6480065584182739,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.3927,
      "step": 60
    },
    {
      "epoch": 0.5570776255707762,
      "grad_norm": 0.714128851890564,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.292,
      "step": 61
    },
    {
      "epoch": 0.5662100456621004,
      "grad_norm": 0.6220545172691345,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.5397,
      "step": 62
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.5826694369316101,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.4353,
      "step": 63
    },
    {
      "epoch": 0.5753424657534246,
      "eval_loss": 2.2431254386901855,
      "eval_runtime": 20.8407,
      "eval_samples_per_second": 4.462,
      "eval_steps_per_second": 0.576,
      "step": 63
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 0.566975474357605,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.3431,
      "step": 64
    },
    {
      "epoch": 0.593607305936073,
      "grad_norm": 0.5798670649528503,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.3806,
      "step": 65
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.6358705759048462,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.2348,
      "step": 66
    },
    {
      "epoch": 0.6118721461187214,
      "grad_norm": 0.550161600112915,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.0631,
      "step": 67
    },
    {
      "epoch": 0.6210045662100456,
      "grad_norm": 0.5509560108184814,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.3087,
      "step": 68
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.5989461541175842,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.3166,
      "step": 69
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.5471036434173584,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.3823,
      "step": 70
    },
    {
      "epoch": 0.6484018264840182,
      "grad_norm": 0.7197486758232117,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.3573,
      "step": 71
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.6207011342048645,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9111,
      "step": 72
    },
    {
      "epoch": 0.6575342465753424,
      "eval_loss": 2.227933406829834,
      "eval_runtime": 20.8452,
      "eval_samples_per_second": 4.461,
      "eval_steps_per_second": 0.576,
      "step": 72
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.7113797068595886,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0437,
      "step": 73
    },
    {
      "epoch": 0.6757990867579908,
      "grad_norm": 0.515771746635437,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.3436,
      "step": 74
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.5890393257141113,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.3986,
      "step": 75
    },
    {
      "epoch": 0.6940639269406392,
      "grad_norm": 0.5468965768814087,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.9288,
      "step": 76
    },
    {
      "epoch": 0.7031963470319634,
      "grad_norm": 0.4898984432220459,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.0482,
      "step": 77
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.6228100657463074,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.903,
      "step": 78
    },
    {
      "epoch": 0.7214611872146118,
      "grad_norm": 0.6375327110290527,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.49,
      "step": 79
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.5555298328399658,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.5199,
      "step": 80
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": 0.6126773953437805,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.4759,
      "step": 81
    },
    {
      "epoch": 0.7397260273972602,
      "eval_loss": 2.2166996002197266,
      "eval_runtime": 20.8348,
      "eval_samples_per_second": 4.464,
      "eval_steps_per_second": 0.576,
      "step": 81
    },
    {
      "epoch": 0.7488584474885844,
      "grad_norm": 0.5838559865951538,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1914,
      "step": 82
    },
    {
      "epoch": 0.7579908675799086,
      "grad_norm": 0.7605540156364441,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.1758,
      "step": 83
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.6348507404327393,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.2758,
      "step": 84
    },
    {
      "epoch": 0.776255707762557,
      "grad_norm": 0.5870646834373474,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.3142,
      "step": 85
    },
    {
      "epoch": 0.7853881278538812,
      "grad_norm": 0.5460823774337769,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.2798,
      "step": 86
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": 0.6042826175689697,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.2346,
      "step": 87
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 0.5716707706451416,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1999,
      "step": 88
    },
    {
      "epoch": 0.8127853881278538,
      "grad_norm": 0.550568699836731,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.0574,
      "step": 89
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.5823182463645935,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.9946,
      "step": 90
    },
    {
      "epoch": 0.821917808219178,
      "eval_loss": 2.2124736309051514,
      "eval_runtime": 20.813,
      "eval_samples_per_second": 4.468,
      "eval_steps_per_second": 0.577,
      "step": 90
    },
    {
      "epoch": 0.8310502283105022,
      "grad_norm": 0.5822633504867554,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0597,
      "step": 91
    },
    {
      "epoch": 0.8401826484018264,
      "grad_norm": 0.5779334306716919,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.2442,
      "step": 92
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": 0.5636650323867798,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.2871,
      "step": 93
    },
    {
      "epoch": 0.8584474885844748,
      "grad_norm": 0.6365733742713928,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2949,
      "step": 94
    },
    {
      "epoch": 0.867579908675799,
      "grad_norm": 0.8823941946029663,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.2909,
      "step": 95
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.507706880569458,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.2422,
      "step": 96
    },
    {
      "epoch": 0.8858447488584474,
      "grad_norm": 0.8357117772102356,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.2351,
      "step": 97
    },
    {
      "epoch": 0.8949771689497716,
      "grad_norm": 0.694574236869812,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.3319,
      "step": 98
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": 0.47206035256385803,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.2751,
      "step": 99
    },
    {
      "epoch": 0.9041095890410958,
      "eval_loss": 2.2115933895111084,
      "eval_runtime": 20.8491,
      "eval_samples_per_second": 4.461,
      "eval_steps_per_second": 0.576,
      "step": 99
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.864282488822937,
      "learning_rate": 0.0,
      "loss": 2.3232,
      "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": 1.483774567120896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}