{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009961647656522389,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.961647656522389e-05,
      "grad_norm": 0.3764162063598633,
      "learning_rate": 1e-05,
      "loss": 1.6077,
      "step": 1
    },
    {
      "epoch": 9.961647656522389e-05,
      "eval_loss": 1.0737049579620361,
      "eval_runtime": 1971.4732,
      "eval_samples_per_second": 4.288,
      "eval_steps_per_second": 0.536,
      "step": 1
    },
    {
      "epoch": 0.00019923295313044778,
      "grad_norm": 0.4798222482204437,
      "learning_rate": 2e-05,
      "loss": 2.0602,
      "step": 2
    },
    {
      "epoch": 0.0002988494296956717,
      "grad_norm": 0.471971333026886,
      "learning_rate": 3e-05,
      "loss": 2.213,
      "step": 3
    },
    {
      "epoch": 0.00039846590626089557,
      "grad_norm": 0.5088309049606323,
      "learning_rate": 4e-05,
      "loss": 2.2241,
      "step": 4
    },
    {
      "epoch": 0.0004980823828261194,
      "grad_norm": 0.637701153755188,
      "learning_rate": 5e-05,
      "loss": 2.3129,
      "step": 5
    },
    {
      "epoch": 0.0005976988593913434,
      "grad_norm": 0.5900222659111023,
      "learning_rate": 6e-05,
      "loss": 2.3504,
      "step": 6
    },
    {
      "epoch": 0.0006973153359565673,
      "grad_norm": 0.4763854146003723,
      "learning_rate": 7e-05,
      "loss": 1.8135,
      "step": 7
    },
    {
      "epoch": 0.0007969318125217911,
      "grad_norm": 0.5983641147613525,
      "learning_rate": 8e-05,
      "loss": 2.1851,
      "step": 8
    },
    {
      "epoch": 0.000896548289087015,
      "grad_norm": 0.7559554576873779,
      "learning_rate": 9e-05,
      "loss": 2.2561,
      "step": 9
    },
    {
      "epoch": 0.000896548289087015,
      "eval_loss": 1.0239731073379517,
      "eval_runtime": 1983.1293,
      "eval_samples_per_second": 4.263,
      "eval_steps_per_second": 0.533,
      "step": 9
    },
    {
      "epoch": 0.0009961647656522388,
      "grad_norm": 0.7414022088050842,
      "learning_rate": 0.0001,
      "loss": 2.321,
      "step": 10
    },
    {
      "epoch": 0.0010957812422174628,
      "grad_norm": 0.6791929006576538,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9623,
      "step": 11
    },
    {
      "epoch": 0.0011953977187826868,
      "grad_norm": 0.787407398223877,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0065,
      "step": 12
    },
    {
      "epoch": 0.0012950141953479105,
      "grad_norm": 0.7576856017112732,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.9836,
      "step": 13
    },
    {
      "epoch": 0.0013946306719131345,
      "grad_norm": 0.7433531880378723,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.0257,
      "step": 14
    },
    {
      "epoch": 0.0014942471484783583,
      "grad_norm": 1.1988621950149536,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.9823,
      "step": 15
    },
    {
      "epoch": 0.0015938636250435823,
      "grad_norm": 1.3264309167861938,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0327,
      "step": 16
    },
    {
      "epoch": 0.001693480101608806,
      "grad_norm": 1.1322566270828247,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.8481,
      "step": 17
    },
    {
      "epoch": 0.00179309657817403,
      "grad_norm": 0.8317338824272156,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7525,
      "step": 18
    },
    {
      "epoch": 0.00179309657817403,
      "eval_loss": 0.8562144637107849,
      "eval_runtime": 1982.5376,
      "eval_samples_per_second": 4.264,
      "eval_steps_per_second": 0.533,
      "step": 18
    },
    {
      "epoch": 0.0018927130547392538,
      "grad_norm": 0.7076705098152161,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5928,
      "step": 19
    },
    {
      "epoch": 0.0019923295313044776,
      "grad_norm": 0.7870856523513794,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5674,
      "step": 20
    },
    {
      "epoch": 0.0020919460078697018,
      "grad_norm": 0.9307458400726318,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5335,
      "step": 21
    },
    {
      "epoch": 0.0021915624844349255,
      "grad_norm": 0.9218393564224243,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6571,
      "step": 22
    },
    {
      "epoch": 0.0022911789610001493,
      "grad_norm": 0.7083066701889038,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.4193,
      "step": 23
    },
    {
      "epoch": 0.0023907954375653735,
      "grad_norm": 0.6554067730903625,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4356,
      "step": 24
    },
    {
      "epoch": 0.0024904119141305973,
      "grad_norm": 0.7899258732795715,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5535,
      "step": 25
    },
    {
      "epoch": 0.002590028390695821,
      "grad_norm": 0.7197738289833069,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5874,
      "step": 26
    },
    {
      "epoch": 0.002689644867261045,
      "grad_norm": 0.6915492415428162,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.4368,
      "step": 27
    },
    {
      "epoch": 0.002689644867261045,
      "eval_loss": 0.8158602118492126,
      "eval_runtime": 1982.4997,
      "eval_samples_per_second": 4.264,
      "eval_steps_per_second": 0.533,
      "step": 27
    },
    {
      "epoch": 0.002789261343826269,
      "grad_norm": 0.7694994211196899,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4071,
      "step": 28
    },
    {
      "epoch": 0.002888877820391493,
      "grad_norm": 0.6930390000343323,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2322,
      "step": 29
    },
    {
      "epoch": 0.0029884942969567166,
      "grad_norm": 0.8376277089118958,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7066,
      "step": 30
    },
    {
      "epoch": 0.0030881107735219403,
      "grad_norm": 0.8401179313659668,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.4075,
      "step": 31
    },
    {
      "epoch": 0.0031877272500871645,
      "grad_norm": 0.6120941638946533,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2898,
      "step": 32
    },
    {
      "epoch": 0.0032873437266523883,
      "grad_norm": 0.7408422231674194,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4385,
      "step": 33
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 0.8187410831451416,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6469,
      "step": 34
    },
    {
      "epoch": 0.0034865766797828363,
      "grad_norm": 0.9299861788749695,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8522,
      "step": 35
    },
    {
      "epoch": 0.00358619315634806,
      "grad_norm": 0.6361233592033386,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.801,
      "step": 36
    },
    {
      "epoch": 0.00358619315634806,
      "eval_loss": 0.7981658577919006,
      "eval_runtime": 1981.0,
      "eval_samples_per_second": 4.268,
      "eval_steps_per_second": 0.534,
      "step": 36
    },
    {
      "epoch": 0.003685809632913284,
      "grad_norm": 0.6598179936408997,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5102,
      "step": 37
    },
    {
      "epoch": 0.0037854261094785076,
      "grad_norm": 0.7499687075614929,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.657,
      "step": 38
    },
    {
      "epoch": 0.0038850425860437318,
      "grad_norm": 0.9739256501197815,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.8125,
      "step": 39
    },
    {
      "epoch": 0.003984659062608955,
      "grad_norm": 0.7461879253387451,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5476,
      "step": 40
    },
    {
      "epoch": 0.004084275539174179,
      "grad_norm": 0.6482231616973877,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.6514,
      "step": 41
    },
    {
      "epoch": 0.0041838920157394035,
      "grad_norm": 0.6921175718307495,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7081,
      "step": 42
    },
    {
      "epoch": 0.004283508492304627,
      "grad_norm": 0.6822366714477539,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4533,
      "step": 43
    },
    {
      "epoch": 0.004383124968869851,
      "grad_norm": 0.7140436768531799,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6157,
      "step": 44
    },
    {
      "epoch": 0.004482741445435075,
      "grad_norm": 0.7993573546409607,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5638,
      "step": 45
    },
    {
      "epoch": 0.004482741445435075,
      "eval_loss": 0.7814497351646423,
      "eval_runtime": 1981.9691,
      "eval_samples_per_second": 4.265,
      "eval_steps_per_second": 0.533,
      "step": 45
    },
    {
      "epoch": 0.004582357922000299,
      "grad_norm": 0.8172252774238586,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6437,
      "step": 46
    },
    {
      "epoch": 0.004681974398565523,
      "grad_norm": 0.7211968302726746,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4087,
      "step": 47
    },
    {
      "epoch": 0.004781590875130747,
      "grad_norm": 0.5860567092895508,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.3838,
      "step": 48
    },
    {
      "epoch": 0.00488120735169597,
      "grad_norm": 0.8529565334320068,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8087,
      "step": 49
    },
    {
      "epoch": 0.0049808238282611945,
      "grad_norm": 0.722075879573822,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.6567,
      "step": 50
    },
    {
      "epoch": 0.005080440304826418,
      "grad_norm": 0.8188619017601013,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.6396,
      "step": 51
    },
    {
      "epoch": 0.005180056781391642,
      "grad_norm": 0.79249507188797,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5557,
      "step": 52
    },
    {
      "epoch": 0.005279673257956866,
      "grad_norm": 0.6785992383956909,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.3073,
      "step": 53
    },
    {
      "epoch": 0.00537928973452209,
      "grad_norm": 0.97710782289505,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.7284,
      "step": 54
    },
    {
      "epoch": 0.00537928973452209,
      "eval_loss": 0.7754528522491455,
      "eval_runtime": 1981.7331,
      "eval_samples_per_second": 4.266,
      "eval_steps_per_second": 0.533,
      "step": 54
    },
    {
      "epoch": 0.005478906211087314,
      "grad_norm": 0.6769554615020752,
      "learning_rate": 5e-05,
      "loss": 1.4189,
      "step": 55
    },
    {
      "epoch": 0.005578522687652538,
      "grad_norm": 0.7661912441253662,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.7372,
      "step": 56
    },
    {
      "epoch": 0.005678139164217761,
      "grad_norm": 0.6592562794685364,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4502,
      "step": 57
    },
    {
      "epoch": 0.005777755640782986,
      "grad_norm": 0.7503229975700378,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7161,
      "step": 58
    },
    {
      "epoch": 0.00587737211734821,
      "grad_norm": 0.732617974281311,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.7657,
      "step": 59
    },
    {
      "epoch": 0.005976988593913433,
      "grad_norm": 1.082809329032898,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6904,
      "step": 60
    },
    {
      "epoch": 0.006076605070478657,
      "grad_norm": 0.7891655564308167,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.44,
      "step": 61
    },
    {
      "epoch": 0.006176221547043881,
      "grad_norm": 0.6875162124633789,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.4152,
      "step": 62
    },
    {
      "epoch": 0.006275838023609105,
      "grad_norm": 0.9231224656105042,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.5762,
      "step": 63
    },
    {
      "epoch": 0.006275838023609105,
      "eval_loss": 0.770641028881073,
      "eval_runtime": 1982.7582,
      "eval_samples_per_second": 4.264,
      "eval_steps_per_second": 0.533,
      "step": 63
    },
    {
      "epoch": 0.006375454500174329,
      "grad_norm": 0.7868038415908813,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5909,
      "step": 64
    },
    {
      "epoch": 0.006475070976739552,
      "grad_norm": 0.7078908681869507,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.3516,
      "step": 65
    },
    {
      "epoch": 0.006574687453304777,
      "grad_norm": 0.6930572986602783,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4509,
      "step": 66
    },
    {
      "epoch": 0.006674303929870001,
      "grad_norm": 0.8317136764526367,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.7793,
      "step": 67
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 0.8354675769805908,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.7312,
      "step": 68
    },
    {
      "epoch": 0.006873536883000448,
      "grad_norm": 0.7719464302062988,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8397,
      "step": 69
    },
    {
      "epoch": 0.0069731533595656725,
      "grad_norm": 0.7388513088226318,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5045,
      "step": 70
    },
    {
      "epoch": 0.007072769836130896,
      "grad_norm": 0.8662011623382568,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8403,
      "step": 71
    },
    {
      "epoch": 0.00717238631269612,
      "grad_norm": 0.9247857332229614,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6341,
      "step": 72
    },
    {
      "epoch": 0.00717238631269612,
      "eval_loss": 0.7679572105407715,
      "eval_runtime": 1983.463,
      "eval_samples_per_second": 4.262,
      "eval_steps_per_second": 0.533,
      "step": 72
    },
    {
      "epoch": 0.007272002789261343,
      "grad_norm": 0.6822766661643982,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.341,
      "step": 73
    },
    {
      "epoch": 0.007371619265826568,
      "grad_norm": 0.8702826499938965,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6741,
      "step": 74
    },
    {
      "epoch": 0.007471235742391792,
      "grad_norm": 0.6422632932662964,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3527,
      "step": 75
    },
    {
      "epoch": 0.007570852218957015,
      "grad_norm": 0.8617198467254639,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.4376,
      "step": 76
    },
    {
      "epoch": 0.007670468695522239,
      "grad_norm": 0.8097233772277832,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.4977,
      "step": 77
    },
    {
      "epoch": 0.0077700851720874636,
      "grad_norm": 0.6698528528213501,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.2981,
      "step": 78
    },
    {
      "epoch": 0.007869701648652687,
      "grad_norm": 0.9840778708457947,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4803,
      "step": 79
    },
    {
      "epoch": 0.00796931812521791,
      "grad_norm": 0.89268958568573,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8106,
      "step": 80
    },
    {
      "epoch": 0.008068934601783135,
      "grad_norm": 0.7866905927658081,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6302,
      "step": 81
    },
    {
      "epoch": 0.008068934601783135,
      "eval_loss": 0.7663864493370056,
      "eval_runtime": 1983.5768,
      "eval_samples_per_second": 4.262,
      "eval_steps_per_second": 0.533,
      "step": 81
    },
    {
      "epoch": 0.008168551078348359,
      "grad_norm": 0.6179813742637634,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2949,
      "step": 82
    },
    {
      "epoch": 0.008268167554913582,
      "grad_norm": 0.5955004692077637,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.3741,
      "step": 83
    },
    {
      "epoch": 0.008367784031478807,
      "grad_norm": 0.6240610480308533,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3025,
      "step": 84
    },
    {
      "epoch": 0.00846740050804403,
      "grad_norm": 0.7150053977966309,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4859,
      "step": 85
    },
    {
      "epoch": 0.008567016984609254,
      "grad_norm": 0.7417619228363037,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.4521,
      "step": 86
    },
    {
      "epoch": 0.008666633461174479,
      "grad_norm": 0.6979576945304871,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5195,
      "step": 87
    },
    {
      "epoch": 0.008766249937739702,
      "grad_norm": 0.7996464371681213,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6097,
      "step": 88
    },
    {
      "epoch": 0.008865866414304925,
      "grad_norm": 0.7870691418647766,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.6533,
      "step": 89
    },
    {
      "epoch": 0.00896548289087015,
      "grad_norm": 0.6725627183914185,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.3191,
      "step": 90
    },
    {
      "epoch": 0.00896548289087015,
      "eval_loss": 0.7657433152198792,
      "eval_runtime": 1983.6936,
      "eval_samples_per_second": 4.262,
      "eval_steps_per_second": 0.533,
      "step": 90
    },
    {
      "epoch": 0.009065099367435374,
      "grad_norm": 0.7659081816673279,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6397,
      "step": 91
    },
    {
      "epoch": 0.009164715844000597,
      "grad_norm": 0.6460014581680298,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3172,
      "step": 92
    },
    {
      "epoch": 0.009264332320565822,
      "grad_norm": 0.665287435054779,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.2986,
      "step": 93
    },
    {
      "epoch": 0.009363948797131046,
      "grad_norm": 0.7975252866744995,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.6436,
      "step": 94
    },
    {
      "epoch": 0.009463565273696269,
      "grad_norm": 0.6706257462501526,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.5118,
      "step": 95
    },
    {
      "epoch": 0.009563181750261494,
      "grad_norm": 0.7847915291786194,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.3296,
      "step": 96
    },
    {
      "epoch": 0.009662798226826717,
      "grad_norm": 0.6760066747665405,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.5437,
      "step": 97
    },
    {
      "epoch": 0.00976241470339194,
      "grad_norm": 0.6760746836662292,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4752,
      "step": 98
    },
    {
      "epoch": 0.009862031179957166,
      "grad_norm": 0.6780611872673035,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4912,
      "step": 99
    },
    {
      "epoch": 0.009862031179957166,
      "eval_loss": 0.7656309604644775,
      "eval_runtime": 1983.1932,
      "eval_samples_per_second": 4.263,
      "eval_steps_per_second": 0.533,
      "step": 99
    },
    {
      "epoch": 0.009961647656522389,
      "grad_norm": 0.7122662663459778,
      "learning_rate": 0.0,
      "loss": 1.5126,
      "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": 1.2886094823555072e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}