{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25906735751295334,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025906735751295338,
      "grad_norm": 3.7401230335235596,
      "learning_rate": 1e-05,
      "loss": 3.0666,
      "step": 1
    },
    {
      "epoch": 0.0025906735751295338,
      "eval_loss": 4.18491792678833,
      "eval_runtime": 35.7075,
      "eval_samples_per_second": 9.102,
      "eval_steps_per_second": 1.148,
      "step": 1
    },
    {
      "epoch": 0.0051813471502590676,
      "grad_norm": 4.653674125671387,
      "learning_rate": 2e-05,
      "loss": 4.1643,
      "step": 2
    },
    {
      "epoch": 0.007772020725388601,
      "grad_norm": 5.061185836791992,
      "learning_rate": 3e-05,
      "loss": 3.7233,
      "step": 3
    },
    {
      "epoch": 0.010362694300518135,
      "grad_norm": 4.979389667510986,
      "learning_rate": 4e-05,
      "loss": 4.6052,
      "step": 4
    },
    {
      "epoch": 0.012953367875647668,
      "grad_norm": 4.482627868652344,
      "learning_rate": 5e-05,
      "loss": 3.4867,
      "step": 5
    },
    {
      "epoch": 0.015544041450777202,
      "grad_norm": 6.006535053253174,
      "learning_rate": 6e-05,
      "loss": 3.7069,
      "step": 6
    },
    {
      "epoch": 0.018134715025906734,
      "grad_norm": 4.89888334274292,
      "learning_rate": 7e-05,
      "loss": 3.9644,
      "step": 7
    },
    {
      "epoch": 0.02072538860103627,
      "grad_norm": 5.465033531188965,
      "learning_rate": 8e-05,
      "loss": 3.3032,
      "step": 8
    },
    {
      "epoch": 0.023316062176165803,
      "grad_norm": 4.801088809967041,
      "learning_rate": 9e-05,
      "loss": 2.0563,
      "step": 9
    },
    {
      "epoch": 0.023316062176165803,
      "eval_loss": 3.25215744972229,
      "eval_runtime": 35.2692,
      "eval_samples_per_second": 9.215,
      "eval_steps_per_second": 1.162,
      "step": 9
    },
    {
      "epoch": 0.025906735751295335,
      "grad_norm": 8.266736030578613,
      "learning_rate": 0.0001,
      "loss": 3.6629,
      "step": 10
    },
    {
      "epoch": 0.02849740932642487,
      "grad_norm": 4.273421287536621,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.7825,
      "step": 11
    },
    {
      "epoch": 0.031088082901554404,
      "grad_norm": 9.370466232299805,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.9157,
      "step": 12
    },
    {
      "epoch": 0.03367875647668394,
      "grad_norm": 5.781856536865234,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.4527,
      "step": 13
    },
    {
      "epoch": 0.03626943005181347,
      "grad_norm": 7.081896781921387,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.0791,
      "step": 14
    },
    {
      "epoch": 0.038860103626943004,
      "grad_norm": 9.198928833007812,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.8983,
      "step": 15
    },
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 7.364632606506348,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0986,
      "step": 16
    },
    {
      "epoch": 0.04404145077720207,
      "grad_norm": 5.105291366577148,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.4194,
      "step": 17
    },
    {
      "epoch": 0.046632124352331605,
      "grad_norm": 7.902851104736328,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.5238,
      "step": 18
    },
    {
      "epoch": 0.046632124352331605,
      "eval_loss": 2.1568806171417236,
      "eval_runtime": 35.3004,
      "eval_samples_per_second": 9.207,
      "eval_steps_per_second": 1.161,
      "step": 18
    },
    {
      "epoch": 0.04922279792746114,
      "grad_norm": 7.482724666595459,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0681,
      "step": 19
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 6.279477119445801,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.0164,
      "step": 20
    },
    {
      "epoch": 0.054404145077720206,
      "grad_norm": 6.212917804718018,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.9994,
      "step": 21
    },
    {
      "epoch": 0.05699481865284974,
      "grad_norm": 5.9393815994262695,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.2696,
      "step": 22
    },
    {
      "epoch": 0.05958549222797927,
      "grad_norm": 6.2451171875,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.0264,
      "step": 23
    },
    {
      "epoch": 0.06217616580310881,
      "grad_norm": 4.755683898925781,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7309,
      "step": 24
    },
    {
      "epoch": 0.06476683937823834,
      "grad_norm": 5.793985366821289,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.432,
      "step": 25
    },
    {
      "epoch": 0.06735751295336788,
      "grad_norm": 6.06044864654541,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6466,
      "step": 26
    },
    {
      "epoch": 0.06994818652849741,
      "grad_norm": 5.624882698059082,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5609,
      "step": 27
    },
    {
      "epoch": 0.06994818652849741,
      "eval_loss": 1.9685734510421753,
      "eval_runtime": 35.2965,
      "eval_samples_per_second": 9.208,
      "eval_steps_per_second": 1.162,
      "step": 27
    },
    {
      "epoch": 0.07253886010362694,
      "grad_norm": 5.412827968597412,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9472,
      "step": 28
    },
    {
      "epoch": 0.07512953367875648,
      "grad_norm": 8.074312210083008,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8224,
      "step": 29
    },
    {
      "epoch": 0.07772020725388601,
      "grad_norm": 10.367136001586914,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7846,
      "step": 30
    },
    {
      "epoch": 0.08031088082901554,
      "grad_norm": 5.971827507019043,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.8626,
      "step": 31
    },
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 6.0518975257873535,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.9026,
      "step": 32
    },
    {
      "epoch": 0.08549222797927461,
      "grad_norm": 7.365506172180176,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.6508,
      "step": 33
    },
    {
      "epoch": 0.08808290155440414,
      "grad_norm": 7.813849925994873,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2382,
      "step": 34
    },
    {
      "epoch": 0.09067357512953368,
      "grad_norm": 6.097650527954102,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8182,
      "step": 35
    },
    {
      "epoch": 0.09326424870466321,
      "grad_norm": 8.286858558654785,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0077,
      "step": 36
    },
    {
      "epoch": 0.09326424870466321,
      "eval_loss": 1.8582597970962524,
      "eval_runtime": 35.2881,
      "eval_samples_per_second": 9.21,
      "eval_steps_per_second": 1.162,
      "step": 36
    },
    {
      "epoch": 0.09585492227979274,
      "grad_norm": 7.306047439575195,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.754,
      "step": 37
    },
    {
      "epoch": 0.09844559585492228,
      "grad_norm": 8.38849925994873,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.59,
      "step": 38
    },
    {
      "epoch": 0.10103626943005181,
      "grad_norm": 5.015171527862549,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.272,
      "step": 39
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 7.593957901000977,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.1336,
      "step": 40
    },
    {
      "epoch": 0.10621761658031088,
      "grad_norm": 9.562592506408691,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.4349,
      "step": 41
    },
    {
      "epoch": 0.10880829015544041,
      "grad_norm": 7.189981937408447,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.827,
      "step": 42
    },
    {
      "epoch": 0.11139896373056994,
      "grad_norm": 5.631102561950684,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.5876,
      "step": 43
    },
    {
      "epoch": 0.11398963730569948,
      "grad_norm": 5.808564186096191,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7378,
      "step": 44
    },
    {
      "epoch": 0.11658031088082901,
      "grad_norm": 6.575247764587402,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.4891,
      "step": 45
    },
    {
      "epoch": 0.11658031088082901,
      "eval_loss": 1.8105183839797974,
      "eval_runtime": 35.2968,
      "eval_samples_per_second": 9.208,
      "eval_steps_per_second": 1.162,
      "step": 45
    },
    {
      "epoch": 0.11917098445595854,
      "grad_norm": 6.088664531707764,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4166,
      "step": 46
    },
    {
      "epoch": 0.12176165803108809,
      "grad_norm": 5.614904403686523,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6618,
      "step": 47
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 5.483867645263672,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.0089,
      "step": 48
    },
    {
      "epoch": 0.12694300518134716,
      "grad_norm": 5.806712627410889,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3856,
      "step": 49
    },
    {
      "epoch": 0.12953367875647667,
      "grad_norm": 6.254551410675049,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0932,
      "step": 50
    },
    {
      "epoch": 0.13212435233160622,
      "grad_norm": 7.465367317199707,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.5789,
      "step": 51
    },
    {
      "epoch": 0.13471502590673576,
      "grad_norm": 6.681556224822998,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.2189,
      "step": 52
    },
    {
      "epoch": 0.13730569948186527,
      "grad_norm": 5.871731281280518,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.9786,
      "step": 53
    },
    {
      "epoch": 0.13989637305699482,
      "grad_norm": 5.125665664672852,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0465,
      "step": 54
    },
    {
      "epoch": 0.13989637305699482,
      "eval_loss": 1.7822543382644653,
      "eval_runtime": 35.2945,
      "eval_samples_per_second": 9.208,
      "eval_steps_per_second": 1.162,
      "step": 54
    },
    {
      "epoch": 0.14248704663212436,
      "grad_norm": 4.874420642852783,
      "learning_rate": 5e-05,
      "loss": 1.4988,
      "step": 55
    },
    {
      "epoch": 0.14507772020725387,
      "grad_norm": 8.843067169189453,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.158,
      "step": 56
    },
    {
      "epoch": 0.14766839378238342,
      "grad_norm": 6.586634159088135,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.3119,
      "step": 57
    },
    {
      "epoch": 0.15025906735751296,
      "grad_norm": 5.651390552520752,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.6922,
      "step": 58
    },
    {
      "epoch": 0.15284974093264247,
      "grad_norm": 6.231300354003906,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.2431,
      "step": 59
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 4.043275356292725,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4424,
      "step": 60
    },
    {
      "epoch": 0.15803108808290156,
      "grad_norm": 4.617724895477295,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.4586,
      "step": 61
    },
    {
      "epoch": 0.16062176165803108,
      "grad_norm": 6.494050025939941,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.1089,
      "step": 62
    },
    {
      "epoch": 0.16321243523316062,
      "grad_norm": 5.432744026184082,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.7376,
      "step": 63
    },
    {
      "epoch": 0.16321243523316062,
      "eval_loss": 1.765604019165039,
      "eval_runtime": 35.2977,
      "eval_samples_per_second": 9.207,
      "eval_steps_per_second": 1.162,
      "step": 63
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 5.5120463371276855,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.711,
      "step": 64
    },
    {
      "epoch": 0.16839378238341968,
      "grad_norm": 8.615033149719238,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6806,
      "step": 65
    },
    {
      "epoch": 0.17098445595854922,
      "grad_norm": 5.7851457595825195,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.6872,
      "step": 66
    },
    {
      "epoch": 0.17357512953367876,
      "grad_norm": 5.352823734283447,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.6242,
      "step": 67
    },
    {
      "epoch": 0.17616580310880828,
      "grad_norm": 5.25345516204834,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5811,
      "step": 68
    },
    {
      "epoch": 0.17875647668393782,
      "grad_norm": 5.170534133911133,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.0783,
      "step": 69
    },
    {
      "epoch": 0.18134715025906736,
      "grad_norm": 6.311948776245117,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.062,
      "step": 70
    },
    {
      "epoch": 0.18393782383419688,
      "grad_norm": 5.581143379211426,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8589,
      "step": 71
    },
    {
      "epoch": 0.18652849740932642,
      "grad_norm": 5.393500328063965,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.7363,
      "step": 72
    },
    {
      "epoch": 0.18652849740932642,
      "eval_loss": 1.7536301612854004,
      "eval_runtime": 35.2875,
      "eval_samples_per_second": 9.21,
      "eval_steps_per_second": 1.162,
      "step": 72
    },
    {
      "epoch": 0.18911917098445596,
      "grad_norm": 5.37123441696167,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.9177,
      "step": 73
    },
    {
      "epoch": 0.19170984455958548,
      "grad_norm": 6.34086799621582,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.1225,
      "step": 74
    },
    {
      "epoch": 0.19430051813471502,
      "grad_norm": 7.714578151702881,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3644,
      "step": 75
    },
    {
      "epoch": 0.19689119170984457,
      "grad_norm": 4.742852687835693,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.7323,
      "step": 76
    },
    {
      "epoch": 0.19948186528497408,
      "grad_norm": 5.983976364135742,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.0531,
      "step": 77
    },
    {
      "epoch": 0.20207253886010362,
      "grad_norm": 4.984601020812988,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.7742,
      "step": 78
    },
    {
      "epoch": 0.20466321243523317,
      "grad_norm": 4.635814666748047,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.6767,
      "step": 79
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 4.99966287612915,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.2725,
      "step": 80
    },
    {
      "epoch": 0.20984455958549222,
      "grad_norm": 5.62561559677124,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.2132,
      "step": 81
    },
    {
      "epoch": 0.20984455958549222,
      "eval_loss": 1.7448948621749878,
      "eval_runtime": 35.2914,
      "eval_samples_per_second": 9.209,
      "eval_steps_per_second": 1.162,
      "step": 81
    },
    {
      "epoch": 0.21243523316062177,
      "grad_norm": 4.649908065795898,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8946,
      "step": 82
    },
    {
      "epoch": 0.21502590673575128,
      "grad_norm": 5.773758411407471,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.0471,
      "step": 83
    },
    {
      "epoch": 0.21761658031088082,
      "grad_norm": 4.992987632751465,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.2634,
      "step": 84
    },
    {
      "epoch": 0.22020725388601037,
      "grad_norm": 5.054306983947754,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.606,
      "step": 85
    },
    {
      "epoch": 0.22279792746113988,
      "grad_norm": 7.253666877746582,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.7227,
      "step": 86
    },
    {
      "epoch": 0.22538860103626943,
      "grad_norm": 6.778452396392822,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.8102,
      "step": 87
    },
    {
      "epoch": 0.22797927461139897,
      "grad_norm": 6.862227439880371,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.7802,
      "step": 88
    },
    {
      "epoch": 0.23056994818652848,
      "grad_norm": 7.059535503387451,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.9549,
      "step": 89
    },
    {
      "epoch": 0.23316062176165803,
      "grad_norm": 5.250755310058594,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.3474,
      "step": 90
    },
    {
      "epoch": 0.23316062176165803,
      "eval_loss": 1.7410351037979126,
      "eval_runtime": 35.2927,
      "eval_samples_per_second": 9.209,
      "eval_steps_per_second": 1.162,
      "step": 90
    },
    {
      "epoch": 0.23575129533678757,
      "grad_norm": 5.2854766845703125,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5383,
      "step": 91
    },
    {
      "epoch": 0.23834196891191708,
      "grad_norm": 7.203006267547607,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4815,
      "step": 92
    },
    {
      "epoch": 0.24093264248704663,
      "grad_norm": 4.856672286987305,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.4639,
      "step": 93
    },
    {
      "epoch": 0.24352331606217617,
      "grad_norm": 5.998774528503418,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.4536,
      "step": 94
    },
    {
      "epoch": 0.24611398963730569,
      "grad_norm": 5.14902925491333,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.2994,
      "step": 95
    },
    {
      "epoch": 0.24870466321243523,
      "grad_norm": 4.489436149597168,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.1281,
      "step": 96
    },
    {
      "epoch": 0.25129533678756477,
      "grad_norm": 5.765980243682861,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.5997,
      "step": 97
    },
    {
      "epoch": 0.2538860103626943,
      "grad_norm": 7.2586212158203125,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.8729,
      "step": 98
    },
    {
      "epoch": 0.25647668393782386,
      "grad_norm": 5.121305465698242,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.135,
      "step": 99
    },
    {
      "epoch": 0.25647668393782386,
      "eval_loss": 1.7404252290725708,
      "eval_runtime": 35.2941,
      "eval_samples_per_second": 9.208,
      "eval_steps_per_second": 1.162,
      "step": 99
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 6.39724063873291,
      "learning_rate": 0.0,
      "loss": 2.012,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}