{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.057653502450273855,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005765350245027386,
      "grad_norm": 0.37003085017204285,
      "learning_rate": 1e-05,
      "loss": 0.7974,
      "step": 1
    },
    {
      "epoch": 0.0005765350245027386,
      "eval_loss": 0.8378480076789856,
      "eval_runtime": 364.6071,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.502,
      "step": 1
    },
    {
      "epoch": 0.0011530700490054772,
      "grad_norm": 0.4608853757381439,
      "learning_rate": 2e-05,
      "loss": 0.902,
      "step": 2
    },
    {
      "epoch": 0.0017296050735082155,
      "grad_norm": 0.38606587052345276,
      "learning_rate": 3e-05,
      "loss": 0.7769,
      "step": 3
    },
    {
      "epoch": 0.0023061400980109543,
      "grad_norm": 0.3839559555053711,
      "learning_rate": 4e-05,
      "loss": 0.6454,
      "step": 4
    },
    {
      "epoch": 0.0028826751225136927,
      "grad_norm": 0.3978426456451416,
      "learning_rate": 5e-05,
      "loss": 0.7626,
      "step": 5
    },
    {
      "epoch": 0.003459210147016431,
      "grad_norm": 0.41355010867118835,
      "learning_rate": 6e-05,
      "loss": 0.7875,
      "step": 6
    },
    {
      "epoch": 0.00403574517151917,
      "grad_norm": 0.3894678056240082,
      "learning_rate": 7e-05,
      "loss": 0.7629,
      "step": 7
    },
    {
      "epoch": 0.004612280196021909,
      "grad_norm": 0.3983372449874878,
      "learning_rate": 8e-05,
      "loss": 0.7176,
      "step": 8
    },
    {
      "epoch": 0.0051888152205246466,
      "grad_norm": 0.39030584692955017,
      "learning_rate": 9e-05,
      "loss": 0.7723,
      "step": 9
    },
    {
      "epoch": 0.0051888152205246466,
      "eval_loss": 0.789570152759552,
      "eval_runtime": 364.6308,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.502,
      "step": 9
    },
    {
      "epoch": 0.005765350245027385,
      "grad_norm": 0.32367318868637085,
      "learning_rate": 0.0001,
      "loss": 0.7582,
      "step": 10
    },
    {
      "epoch": 0.006341885269530124,
      "grad_norm": 0.3000706136226654,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.7372,
      "step": 11
    },
    {
      "epoch": 0.006918420294032862,
      "grad_norm": 0.37174996733665466,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.004,
      "step": 12
    },
    {
      "epoch": 0.007494955318535601,
      "grad_norm": 0.5804224014282227,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.873,
      "step": 13
    },
    {
      "epoch": 0.00807149034303834,
      "grad_norm": 0.5187421441078186,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9452,
      "step": 14
    },
    {
      "epoch": 0.008648025367541078,
      "grad_norm": 0.38242048025131226,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.8002,
      "step": 15
    },
    {
      "epoch": 0.009224560392043817,
      "grad_norm": 0.3651973605155945,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6972,
      "step": 16
    },
    {
      "epoch": 0.009801095416546555,
      "grad_norm": 0.2555687427520752,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6669,
      "step": 17
    },
    {
      "epoch": 0.010377630441049293,
      "grad_norm": 0.3022112250328064,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.722,
      "step": 18
    },
    {
      "epoch": 0.010377630441049293,
      "eval_loss": 0.7508166432380676,
      "eval_runtime": 364.5311,
      "eval_samples_per_second": 4.008,
      "eval_steps_per_second": 0.502,
      "step": 18
    },
    {
      "epoch": 0.010954165465552033,
      "grad_norm": 0.26917049288749695,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5684,
      "step": 19
    },
    {
      "epoch": 0.01153070049005477,
      "grad_norm": 0.2615295350551605,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6792,
      "step": 20
    },
    {
      "epoch": 0.012107235514557509,
      "grad_norm": 0.32459720969200134,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0269,
      "step": 21
    },
    {
      "epoch": 0.012683770539060248,
      "grad_norm": 0.3132142424583435,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.725,
      "step": 22
    },
    {
      "epoch": 0.013260305563562986,
      "grad_norm": 0.248282328248024,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.6729,
      "step": 23
    },
    {
      "epoch": 0.013836840588065724,
      "grad_norm": 0.3106798231601715,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9266,
      "step": 24
    },
    {
      "epoch": 0.014413375612568464,
      "grad_norm": 0.28047069907188416,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7819,
      "step": 25
    },
    {
      "epoch": 0.014989910637071202,
      "grad_norm": 0.2894701361656189,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.6512,
      "step": 26
    },
    {
      "epoch": 0.015566445661573941,
      "grad_norm": 0.27698245644569397,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.9993,
      "step": 27
    },
    {
      "epoch": 0.015566445661573941,
      "eval_loss": 0.7369452714920044,
      "eval_runtime": 364.6583,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.502,
      "step": 27
    },
    {
      "epoch": 0.01614298068607668,
      "grad_norm": 0.2213415801525116,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5782,
      "step": 28
    },
    {
      "epoch": 0.01671951571057942,
      "grad_norm": 0.24280491471290588,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8991,
      "step": 29
    },
    {
      "epoch": 0.017296050735082155,
      "grad_norm": 0.2960163354873657,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7063,
      "step": 30
    },
    {
      "epoch": 0.017872585759584895,
      "grad_norm": 0.31063902378082275,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6707,
      "step": 31
    },
    {
      "epoch": 0.018449120784087635,
      "grad_norm": 0.3026576638221741,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7804,
      "step": 32
    },
    {
      "epoch": 0.01902565580859037,
      "grad_norm": 0.3448016047477722,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.6608,
      "step": 33
    },
    {
      "epoch": 0.01960219083309311,
      "grad_norm": 0.29537856578826904,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7379,
      "step": 34
    },
    {
      "epoch": 0.02017872585759585,
      "grad_norm": 0.26168203353881836,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6782,
      "step": 35
    },
    {
      "epoch": 0.020755260882098586,
      "grad_norm": 0.31830257177352905,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7171,
      "step": 36
    },
    {
      "epoch": 0.020755260882098586,
      "eval_loss": 0.7282043099403381,
      "eval_runtime": 364.6188,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.502,
      "step": 36
    },
    {
      "epoch": 0.021331795906601326,
      "grad_norm": 0.2763126790523529,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7177,
      "step": 37
    },
    {
      "epoch": 0.021908330931104066,
      "grad_norm": 0.2710229456424713,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.9052,
      "step": 38
    },
    {
      "epoch": 0.022484865955606802,
      "grad_norm": 0.24854080379009247,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.55,
      "step": 39
    },
    {
      "epoch": 0.02306140098010954,
      "grad_norm": 0.2228298783302307,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6573,
      "step": 40
    },
    {
      "epoch": 0.02363793600461228,
      "grad_norm": 0.27724236249923706,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7139,
      "step": 41
    },
    {
      "epoch": 0.024214471029115017,
      "grad_norm": 0.2727970778942108,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8087,
      "step": 42
    },
    {
      "epoch": 0.024791006053617757,
      "grad_norm": 0.2884417474269867,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.8424,
      "step": 43
    },
    {
      "epoch": 0.025367541078120497,
      "grad_norm": 0.2760305404663086,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.8116,
      "step": 44
    },
    {
      "epoch": 0.025944076102623233,
      "grad_norm": 0.25933367013931274,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.6274,
      "step": 45
    },
    {
      "epoch": 0.025944076102623233,
      "eval_loss": 0.7213953733444214,
      "eval_runtime": 364.6375,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.502,
      "step": 45
    },
    {
      "epoch": 0.026520611127125972,
      "grad_norm": 0.27154043316841125,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8194,
      "step": 46
    },
    {
      "epoch": 0.027097146151628712,
      "grad_norm": 0.2734670341014862,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6864,
      "step": 47
    },
    {
      "epoch": 0.02767368117613145,
      "grad_norm": 0.35416772961616516,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7526,
      "step": 48
    },
    {
      "epoch": 0.028250216200634188,
      "grad_norm": 0.2307697981595993,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6646,
      "step": 49
    },
    {
      "epoch": 0.028826751225136928,
      "grad_norm": 0.24104607105255127,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7292,
      "step": 50
    },
    {
      "epoch": 0.029403286249639667,
      "grad_norm": 0.2737148106098175,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.578,
      "step": 51
    },
    {
      "epoch": 0.029979821274142403,
      "grad_norm": 0.25250449776649475,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7965,
      "step": 52
    },
    {
      "epoch": 0.030556356298645143,
      "grad_norm": 0.2679482698440552,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.5666,
      "step": 53
    },
    {
      "epoch": 0.031132891323147883,
      "grad_norm": 0.23697395622730255,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.793,
      "step": 54
    },
    {
      "epoch": 0.031132891323147883,
      "eval_loss": 0.7161357998847961,
      "eval_runtime": 364.7647,
      "eval_samples_per_second": 4.005,
      "eval_steps_per_second": 0.502,
      "step": 54
    },
    {
      "epoch": 0.03170942634765062,
      "grad_norm": 0.24478928744792938,
      "learning_rate": 5e-05,
      "loss": 0.7117,
      "step": 55
    },
    {
      "epoch": 0.03228596137215336,
      "grad_norm": 0.24072794616222382,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7469,
      "step": 56
    },
    {
      "epoch": 0.032862496396656095,
      "grad_norm": 0.2506271302700043,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.5882,
      "step": 57
    },
    {
      "epoch": 0.03343903142115884,
      "grad_norm": 0.25327742099761963,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.8655,
      "step": 58
    },
    {
      "epoch": 0.034015566445661574,
      "grad_norm": 0.2883288264274597,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.6904,
      "step": 59
    },
    {
      "epoch": 0.03459210147016431,
      "grad_norm": 0.31384822726249695,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6982,
      "step": 60
    },
    {
      "epoch": 0.035168636494667053,
      "grad_norm": 0.2190999835729599,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.537,
      "step": 61
    },
    {
      "epoch": 0.03574517151916979,
      "grad_norm": 0.2678523361682892,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.603,
      "step": 62
    },
    {
      "epoch": 0.036321706543672526,
      "grad_norm": 0.2452000230550766,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.6418,
      "step": 63
    },
    {
      "epoch": 0.036321706543672526,
      "eval_loss": 0.7111778259277344,
      "eval_runtime": 364.5252,
      "eval_samples_per_second": 4.008,
      "eval_steps_per_second": 0.502,
      "step": 63
    },
    {
      "epoch": 0.03689824156817527,
      "grad_norm": 0.26516154408454895,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6853,
      "step": 64
    },
    {
      "epoch": 0.037474776592678005,
      "grad_norm": 0.24883601069450378,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7509,
      "step": 65
    },
    {
      "epoch": 0.03805131161718074,
      "grad_norm": 0.2416902482509613,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7731,
      "step": 66
    },
    {
      "epoch": 0.038627846641683485,
      "grad_norm": 0.3510083556175232,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.772,
      "step": 67
    },
    {
      "epoch": 0.03920438166618622,
      "grad_norm": 0.2844652831554413,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6466,
      "step": 68
    },
    {
      "epoch": 0.03978091669068896,
      "grad_norm": 0.38679516315460205,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7163,
      "step": 69
    },
    {
      "epoch": 0.0403574517151917,
      "grad_norm": 0.26089876890182495,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8,
      "step": 70
    },
    {
      "epoch": 0.040933986739694436,
      "grad_norm": 0.2750791907310486,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.6986,
      "step": 71
    },
    {
      "epoch": 0.04151052176419717,
      "grad_norm": 0.2476816475391388,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6961,
      "step": 72
    },
    {
      "epoch": 0.04151052176419717,
      "eval_loss": 0.7084031105041504,
      "eval_runtime": 364.4857,
      "eval_samples_per_second": 4.008,
      "eval_steps_per_second": 0.502,
      "step": 72
    },
    {
      "epoch": 0.042087056788699916,
      "grad_norm": 0.2966419756412506,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4958,
      "step": 73
    },
    {
      "epoch": 0.04266359181320265,
      "grad_norm": 0.4231601357460022,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6412,
      "step": 74
    },
    {
      "epoch": 0.04324012683770539,
      "grad_norm": 0.30261847376823425,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.6129,
      "step": 75
    },
    {
      "epoch": 0.04381666186220813,
      "grad_norm": 0.2374476194381714,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.5682,
      "step": 76
    },
    {
      "epoch": 0.04439319688671087,
      "grad_norm": 0.25753456354141235,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.5805,
      "step": 77
    },
    {
      "epoch": 0.044969731911213603,
      "grad_norm": 0.2336205244064331,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.5953,
      "step": 78
    },
    {
      "epoch": 0.04554626693571635,
      "grad_norm": 0.30540937185287476,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.6858,
      "step": 79
    },
    {
      "epoch": 0.04612280196021908,
      "grad_norm": 0.2815301716327667,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.8478,
      "step": 80
    },
    {
      "epoch": 0.04669933698472182,
      "grad_norm": 0.23606453835964203,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.726,
      "step": 81
    },
    {
      "epoch": 0.04669933698472182,
      "eval_loss": 0.7066140174865723,
      "eval_runtime": 364.442,
      "eval_samples_per_second": 4.009,
      "eval_steps_per_second": 0.502,
      "step": 81
    },
    {
      "epoch": 0.04727587200922456,
      "grad_norm": 0.264173299074173,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7206,
      "step": 82
    },
    {
      "epoch": 0.0478524070337273,
      "grad_norm": 0.259550541639328,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6457,
      "step": 83
    },
    {
      "epoch": 0.048428942058230035,
      "grad_norm": 0.25564852356910706,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.5842,
      "step": 84
    },
    {
      "epoch": 0.04900547708273278,
      "grad_norm": 0.2507416307926178,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6966,
      "step": 85
    },
    {
      "epoch": 0.049582012107235514,
      "grad_norm": 0.22969740629196167,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6032,
      "step": 86
    },
    {
      "epoch": 0.05015854713173825,
      "grad_norm": 0.2480449229478836,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6458,
      "step": 87
    },
    {
      "epoch": 0.05073508215624099,
      "grad_norm": 0.24502995610237122,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6293,
      "step": 88
    },
    {
      "epoch": 0.05131161718074373,
      "grad_norm": 0.2702799141407013,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.5813,
      "step": 89
    },
    {
      "epoch": 0.051888152205246466,
      "grad_norm": 0.2640494704246521,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.8735,
      "step": 90
    },
    {
      "epoch": 0.051888152205246466,
      "eval_loss": 0.7058947682380676,
      "eval_runtime": 364.3775,
      "eval_samples_per_second": 4.01,
      "eval_steps_per_second": 0.502,
      "step": 90
    },
    {
      "epoch": 0.05246468722974921,
      "grad_norm": 0.23920738697052002,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6639,
      "step": 91
    },
    {
      "epoch": 0.053041222254251945,
      "grad_norm": 0.2456059753894806,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.694,
      "step": 92
    },
    {
      "epoch": 0.05361775727875468,
      "grad_norm": 0.2731674909591675,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.8057,
      "step": 93
    },
    {
      "epoch": 0.054194292303257424,
      "grad_norm": 0.2577863931655884,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.5574,
      "step": 94
    },
    {
      "epoch": 0.05477082732776016,
      "grad_norm": 0.22670993208885193,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.6183,
      "step": 95
    },
    {
      "epoch": 0.0553473623522629,
      "grad_norm": 0.2563611567020416,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7729,
      "step": 96
    },
    {
      "epoch": 0.05592389737676564,
      "grad_norm": 0.26697584986686707,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.8254,
      "step": 97
    },
    {
      "epoch": 0.056500432401268376,
      "grad_norm": 0.23468847572803497,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7771,
      "step": 98
    },
    {
      "epoch": 0.05707696742577112,
      "grad_norm": 0.2329586148262024,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.6909,
      "step": 99
    },
    {
      "epoch": 0.05707696742577112,
      "eval_loss": 0.7057739496231079,
      "eval_runtime": 364.6184,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.502,
      "step": 99
    },
    {
      "epoch": 0.057653502450273855,
      "grad_norm": 0.28871598839759827,
      "learning_rate": 0.0,
      "loss": 0.7902,
      "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": 1.483775372427264e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}