{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01013273887931908,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001013273887931908,
      "grad_norm": 18.065086364746094,
      "learning_rate": 1e-05,
      "loss": 16.6968,
      "step": 1
    },
    {
      "epoch": 0.0001013273887931908,
      "eval_loss": 16.862133026123047,
      "eval_runtime": 910.0751,
      "eval_samples_per_second": 9.132,
      "eval_steps_per_second": 1.142,
      "step": 1
    },
    {
      "epoch": 0.0002026547775863816,
      "grad_norm": 19.527385711669922,
      "learning_rate": 2e-05,
      "loss": 17.5056,
      "step": 2
    },
    {
      "epoch": 0.0003039821663795724,
      "grad_norm": 18.436649322509766,
      "learning_rate": 3e-05,
      "loss": 16.8749,
      "step": 3
    },
    {
      "epoch": 0.0004053095551727632,
      "grad_norm": 20.10441017150879,
      "learning_rate": 4e-05,
      "loss": 17.0225,
      "step": 4
    },
    {
      "epoch": 0.000506636943965954,
      "grad_norm": 21.448444366455078,
      "learning_rate": 5e-05,
      "loss": 16.6387,
      "step": 5
    },
    {
      "epoch": 0.0006079643327591448,
      "grad_norm": 23.05156135559082,
      "learning_rate": 6e-05,
      "loss": 15.373,
      "step": 6
    },
    {
      "epoch": 0.0007092917215523356,
      "grad_norm": 28.821434020996094,
      "learning_rate": 7e-05,
      "loss": 13.9355,
      "step": 7
    },
    {
      "epoch": 0.0008106191103455264,
      "grad_norm": 27.994274139404297,
      "learning_rate": 8e-05,
      "loss": 11.7677,
      "step": 8
    },
    {
      "epoch": 0.0009119464991387172,
      "grad_norm": 28.988418579101562,
      "learning_rate": 9e-05,
      "loss": 8.8509,
      "step": 9
    },
    {
      "epoch": 0.0009119464991387172,
      "eval_loss": 6.098950386047363,
      "eval_runtime": 910.8237,
      "eval_samples_per_second": 9.125,
      "eval_steps_per_second": 1.141,
      "step": 9
    },
    {
      "epoch": 0.001013273887931908,
      "grad_norm": 29.230281829833984,
      "learning_rate": 0.0001,
      "loss": 6.0279,
      "step": 10
    },
    {
      "epoch": 0.0011146012767250988,
      "grad_norm": 23.10491180419922,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.936,
      "step": 11
    },
    {
      "epoch": 0.0012159286655182896,
      "grad_norm": 16.272106170654297,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1306,
      "step": 12
    },
    {
      "epoch": 0.0013172560543114804,
      "grad_norm": 7.049140930175781,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3879,
      "step": 13
    },
    {
      "epoch": 0.0014185834431046712,
      "grad_norm": 1.3865737915039062,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0468,
      "step": 14
    },
    {
      "epoch": 0.001519910831897862,
      "grad_norm": 0.16824091970920563,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0061,
      "step": 15
    },
    {
      "epoch": 0.0016212382206910528,
      "grad_norm": 0.054334599524736404,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0016,
      "step": 16
    },
    {
      "epoch": 0.0017225656094842436,
      "grad_norm": 0.5172011256217957,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0063,
      "step": 17
    },
    {
      "epoch": 0.0018238929982774344,
      "grad_norm": 0.05042453482747078,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0009,
      "step": 18
    },
    {
      "epoch": 0.0018238929982774344,
      "eval_loss": 0.001392049714922905,
      "eval_runtime": 910.5203,
      "eval_samples_per_second": 9.128,
      "eval_steps_per_second": 1.141,
      "step": 18
    },
    {
      "epoch": 0.0019252203870706252,
      "grad_norm": 0.026352200657129288,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0006,
      "step": 19
    },
    {
      "epoch": 0.002026547775863816,
      "grad_norm": 0.016916528344154358,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0004,
      "step": 20
    },
    {
      "epoch": 0.0021278751646570068,
      "grad_norm": 0.025508670136332512,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0004,
      "step": 21
    },
    {
      "epoch": 0.0022292025534501976,
      "grad_norm": 0.014257045462727547,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0003,
      "step": 22
    },
    {
      "epoch": 0.0023305299422433884,
      "grad_norm": 0.013771199621260166,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0003,
      "step": 23
    },
    {
      "epoch": 0.002431857331036579,
      "grad_norm": 0.013078059069812298,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0002,
      "step": 24
    },
    {
      "epoch": 0.00253318471982977,
      "grad_norm": 0.011078037321567535,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0002,
      "step": 25
    },
    {
      "epoch": 0.0026345121086229608,
      "grad_norm": 0.009111849591135979,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0002,
      "step": 26
    },
    {
      "epoch": 0.0027358394974161516,
      "grad_norm": 0.007235573139041662,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0001,
      "step": 27
    },
    {
      "epoch": 0.0027358394974161516,
      "eval_loss": 0.0002121519937645644,
      "eval_runtime": 909.9954,
      "eval_samples_per_second": 9.133,
      "eval_steps_per_second": 1.142,
      "step": 27
    },
    {
      "epoch": 0.0028371668862093424,
      "grad_norm": 0.005932696163654327,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0001,
      "step": 28
    },
    {
      "epoch": 0.002938494275002533,
      "grad_norm": 0.028776858001947403,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0002,
      "step": 29
    },
    {
      "epoch": 0.003039821663795724,
      "grad_norm": 0.0039496226236224174,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.0031411490525889148,
      "grad_norm": 0.0031183729879558086,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.0032424764413821056,
      "grad_norm": 0.0021235900931060314,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0001,
      "step": 32
    },
    {
      "epoch": 0.0033438038301752964,
      "grad_norm": 0.001924128970131278,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.003445131218968487,
      "grad_norm": 0.045619312673807144,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.003546458607761678,
      "grad_norm": 0.0013390559470281005,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0036477859965548688,
      "grad_norm": 0.0013533019227907062,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0036477859965548688,
      "eval_loss": 0.00013809023948851973,
      "eval_runtime": 909.7784,
      "eval_samples_per_second": 9.135,
      "eval_steps_per_second": 1.142,
      "step": 36
    },
    {
      "epoch": 0.0037491133853480595,
      "grad_norm": 0.0012198821641504765,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0038504407741412503,
      "grad_norm": 0.001205620588734746,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.003951768162934442,
      "grad_norm": 0.0010990527225658298,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.004053095551727632,
      "grad_norm": 0.001103319926187396,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.004154422940520823,
      "grad_norm": 0.002035663230344653,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0042557503293140135,
      "grad_norm": 0.0011256610741838813,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.004357077718107205,
      "grad_norm": 0.0011186710326001048,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.004458405106900395,
      "grad_norm": 0.001320298295468092,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.004559732495693586,
      "grad_norm": 0.0011717890156432986,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.004559732495693586,
      "eval_loss": 6.609158299397677e-05,
      "eval_runtime": 909.7829,
      "eval_samples_per_second": 9.135,
      "eval_steps_per_second": 1.142,
      "step": 45
    },
    {
      "epoch": 0.004661059884486777,
      "grad_norm": 0.0012935634003952146,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.004762387273279968,
      "grad_norm": 0.0009132419945672154,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.004863714662073158,
      "grad_norm": 0.0018957024440169334,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.00496504205086635,
      "grad_norm": 0.0008707873639650643,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.00506636943965954,
      "grad_norm": 0.0011261776089668274,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.005167696828452731,
      "grad_norm": 0.0010706789325922728,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.0052690242172459215,
      "grad_norm": 0.0008777298498898745,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.005370351606039113,
      "grad_norm": 0.0007904967060312629,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.005471678994832303,
      "grad_norm": 0.0009741680114530027,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.005471678994832303,
      "eval_loss": 4.508355414145626e-05,
      "eval_runtime": 909.3496,
      "eval_samples_per_second": 9.139,
      "eval_steps_per_second": 1.143,
      "step": 54
    },
    {
      "epoch": 0.005573006383625494,
      "grad_norm": 0.0007645328296348453,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.005674333772418685,
      "grad_norm": 0.0007385151111520827,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.005775661161211876,
      "grad_norm": 0.0013896574964746833,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.005876988550005066,
      "grad_norm": 0.0007003318169154227,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.0059783159387982576,
      "grad_norm": 0.0006799364346079528,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.006079643327591448,
      "grad_norm": 0.0005815947079099715,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.006180970716384639,
      "grad_norm": 0.0006344603025354445,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.0062822981051778295,
      "grad_norm": 0.0006664209067821503,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.006383625493971021,
      "grad_norm": 0.0005522060673683882,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.006383625493971021,
      "eval_loss": 3.897623537341133e-05,
      "eval_runtime": 910.073,
      "eval_samples_per_second": 9.132,
      "eval_steps_per_second": 1.142,
      "step": 63
    },
    {
      "epoch": 0.006484952882764211,
      "grad_norm": 0.0006067636422812939,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.006586280271557402,
      "grad_norm": 0.000596160942222923,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.006687607660350593,
      "grad_norm": 0.0007353340624831617,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.006788935049143784,
      "grad_norm": 0.0006642314838245511,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.006890262437936974,
      "grad_norm": 0.0005714757717214525,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.0069915898267301655,
      "grad_norm": 0.00058308697771281,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.007092917215523356,
      "grad_norm": 0.0004924508975818753,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.007194244604316547,
      "grad_norm": 0.0005918579990975559,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.0072955719931097375,
      "grad_norm": 0.00047563898260705173,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0072955719931097375,
      "eval_loss": 4.1060800867853686e-05,
      "eval_runtime": 909.4758,
      "eval_samples_per_second": 9.138,
      "eval_steps_per_second": 1.142,
      "step": 72
    },
    {
      "epoch": 0.007396899381902929,
      "grad_norm": 0.0005259711178950965,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.007498226770696119,
      "grad_norm": 0.0005420084926299751,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.00759955415948931,
      "grad_norm": 0.0004860495973844081,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.007700881548282501,
      "grad_norm": 0.0004998171934857965,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.007802208937075692,
      "grad_norm": 0.0006128872628323734,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.007903536325868883,
      "grad_norm": 0.0005098230321891606,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.008004863714662074,
      "grad_norm": 0.0004762745520565659,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.008106191103455264,
      "grad_norm": 0.0004520942165981978,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.008207518492248454,
      "grad_norm": 0.0005275892908684909,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.008207518492248454,
      "eval_loss": 4.220239497954026e-05,
      "eval_runtime": 910.4375,
      "eval_samples_per_second": 9.129,
      "eval_steps_per_second": 1.141,
      "step": 81
    },
    {
      "epoch": 0.008308845881041646,
      "grad_norm": 0.00043567438842728734,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.008410173269834837,
      "grad_norm": 0.0004816035507246852,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.008511500658628027,
      "grad_norm": 0.0005054061184637249,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.008612828047421217,
      "grad_norm": 0.00044693483505398035,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.00871415543621441,
      "grad_norm": 0.000529658398590982,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.0088154828250076,
      "grad_norm": 0.002676603151485324,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.00891681021380079,
      "grad_norm": 0.00046323458082042634,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.00901813760259398,
      "grad_norm": 0.0004469167906790972,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.009119464991387173,
      "grad_norm": 0.00048288522521033883,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.009119464991387173,
      "eval_loss": 4.202386844553985e-05,
      "eval_runtime": 909.1536,
      "eval_samples_per_second": 9.141,
      "eval_steps_per_second": 1.143,
      "step": 90
    },
    {
      "epoch": 0.009220792380180363,
      "grad_norm": 0.00044704313040710986,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.009322119768973553,
      "grad_norm": 0.0004466854443307966,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.009423447157766744,
      "grad_norm": 0.00046623233356513083,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.009524774546559936,
      "grad_norm": 0.00042636101716198027,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.009626101935353126,
      "grad_norm": 0.0005625992780551314,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.009727429324146317,
      "grad_norm": 0.0005262286285869777,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.009828756712939507,
      "grad_norm": 0.0004594066122081131,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.0099300841017327,
      "grad_norm": 0.0004715861286967993,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.01003141149052589,
      "grad_norm": 0.0004536711785476655,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.01003141149052589,
      "eval_loss": 4.104103209101595e-05,
      "eval_runtime": 909.6345,
      "eval_samples_per_second": 9.137,
      "eval_steps_per_second": 1.142,
      "step": 99
    },
    {
      "epoch": 0.01013273887931908,
      "grad_norm": 8.957590103149414,
      "learning_rate": 0.0,
      "loss": 0.0842,
      "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
}