{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7299270072992701,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0072992700729927005,
      "grad_norm": 0.5759531855583191,
      "learning_rate": 1e-05,
      "loss": 2.5578,
      "step": 1
    },
    {
      "epoch": 0.0072992700729927005,
      "eval_loss": 2.5493626594543457,
      "eval_runtime": 3.9453,
      "eval_samples_per_second": 29.402,
      "eval_steps_per_second": 3.802,
      "step": 1
    },
    {
      "epoch": 0.014598540145985401,
      "grad_norm": 0.4575677216053009,
      "learning_rate": 2e-05,
      "loss": 2.4742,
      "step": 2
    },
    {
      "epoch": 0.021897810218978103,
      "grad_norm": 0.4650042653083801,
      "learning_rate": 3e-05,
      "loss": 2.5112,
      "step": 3
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 0.5823487043380737,
      "learning_rate": 4e-05,
      "loss": 2.5448,
      "step": 4
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 0.4799887239933014,
      "learning_rate": 5e-05,
      "loss": 2.5753,
      "step": 5
    },
    {
      "epoch": 0.043795620437956206,
      "grad_norm": 0.576637864112854,
      "learning_rate": 6e-05,
      "loss": 2.5572,
      "step": 6
    },
    {
      "epoch": 0.051094890510948905,
      "grad_norm": 0.500969648361206,
      "learning_rate": 7e-05,
      "loss": 2.4998,
      "step": 7
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 0.48866644501686096,
      "learning_rate": 8e-05,
      "loss": 2.4528,
      "step": 8
    },
    {
      "epoch": 0.06569343065693431,
      "grad_norm": 0.45695871114730835,
      "learning_rate": 9e-05,
      "loss": 2.4748,
      "step": 9
    },
    {
      "epoch": 0.06569343065693431,
      "eval_loss": 2.4808189868927,
      "eval_runtime": 3.3274,
      "eval_samples_per_second": 34.862,
      "eval_steps_per_second": 4.508,
      "step": 9
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.5332048535346985,
      "learning_rate": 0.0001,
      "loss": 2.2931,
      "step": 10
    },
    {
      "epoch": 0.08029197080291971,
      "grad_norm": 0.5480175614356995,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.4459,
      "step": 11
    },
    {
      "epoch": 0.08759124087591241,
      "grad_norm": 0.5366429090499878,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3188,
      "step": 12
    },
    {
      "epoch": 0.0948905109489051,
      "grad_norm": 0.5494810938835144,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.3401,
      "step": 13
    },
    {
      "epoch": 0.10218978102189781,
      "grad_norm": 0.536588728427887,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.2276,
      "step": 14
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 0.578070342540741,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.2032,
      "step": 15
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.5455062985420227,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.1968,
      "step": 16
    },
    {
      "epoch": 0.12408759124087591,
      "grad_norm": 0.6033762097358704,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.0457,
      "step": 17
    },
    {
      "epoch": 0.13138686131386862,
      "grad_norm": 0.5091367363929749,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0457,
      "step": 18
    },
    {
      "epoch": 0.13138686131386862,
      "eval_loss": 2.0244650840759277,
      "eval_runtime": 3.3259,
      "eval_samples_per_second": 34.878,
      "eval_steps_per_second": 4.51,
      "step": 18
    },
    {
      "epoch": 0.1386861313868613,
      "grad_norm": 0.6819591522216797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0456,
      "step": 19
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 0.5838029980659485,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.1287,
      "step": 20
    },
    {
      "epoch": 0.15328467153284672,
      "grad_norm": 0.5925353765487671,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8451,
      "step": 21
    },
    {
      "epoch": 0.16058394160583941,
      "grad_norm": 0.5294898152351379,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7995,
      "step": 22
    },
    {
      "epoch": 0.1678832116788321,
      "grad_norm": 0.5663394331932068,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7454,
      "step": 23
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 0.5861549973487854,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.8476,
      "step": 24
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 0.5432003736495972,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7331,
      "step": 25
    },
    {
      "epoch": 0.1897810218978102,
      "grad_norm": 0.5292729735374451,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6665,
      "step": 26
    },
    {
      "epoch": 0.19708029197080293,
      "grad_norm": 0.604349672794342,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5397,
      "step": 27
    },
    {
      "epoch": 0.19708029197080293,
      "eval_loss": 1.55046546459198,
      "eval_runtime": 3.3307,
      "eval_samples_per_second": 34.828,
      "eval_steps_per_second": 4.504,
      "step": 27
    },
    {
      "epoch": 0.20437956204379562,
      "grad_norm": 0.612851619720459,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5245,
      "step": 28
    },
    {
      "epoch": 0.2116788321167883,
      "grad_norm": 0.5950889587402344,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.3849,
      "step": 29
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 0.5285123586654663,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4316,
      "step": 30
    },
    {
      "epoch": 0.22627737226277372,
      "grad_norm": 0.5811218023300171,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.3643,
      "step": 31
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.6191416382789612,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.3797,
      "step": 32
    },
    {
      "epoch": 0.24087591240875914,
      "grad_norm": 0.6147345304489136,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.3354,
      "step": 33
    },
    {
      "epoch": 0.24817518248175183,
      "grad_norm": 0.6098886132240295,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.2501,
      "step": 34
    },
    {
      "epoch": 0.25547445255474455,
      "grad_norm": 0.6387662887573242,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2498,
      "step": 35
    },
    {
      "epoch": 0.26277372262773724,
      "grad_norm": 0.6446758508682251,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1279,
      "step": 36
    },
    {
      "epoch": 0.26277372262773724,
      "eval_loss": 1.0792505741119385,
      "eval_runtime": 3.3273,
      "eval_samples_per_second": 34.863,
      "eval_steps_per_second": 4.508,
      "step": 36
    },
    {
      "epoch": 0.27007299270072993,
      "grad_norm": 0.6810407638549805,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0696,
      "step": 37
    },
    {
      "epoch": 0.2773722627737226,
      "grad_norm": 0.7299973964691162,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.0278,
      "step": 38
    },
    {
      "epoch": 0.2846715328467153,
      "grad_norm": 0.9009426236152649,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.9941,
      "step": 39
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.881585419178009,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8963,
      "step": 40
    },
    {
      "epoch": 0.29927007299270075,
      "grad_norm": 0.7808435559272766,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8841,
      "step": 41
    },
    {
      "epoch": 0.30656934306569344,
      "grad_norm": 0.7895486950874329,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8795,
      "step": 42
    },
    {
      "epoch": 0.31386861313868614,
      "grad_norm": 0.7057706117630005,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7984,
      "step": 43
    },
    {
      "epoch": 0.32116788321167883,
      "grad_norm": 0.8553966879844666,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.7712,
      "step": 44
    },
    {
      "epoch": 0.3284671532846715,
      "grad_norm": 0.7784386277198792,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.6806,
      "step": 45
    },
    {
      "epoch": 0.3284671532846715,
      "eval_loss": 0.6408138871192932,
      "eval_runtime": 3.3252,
      "eval_samples_per_second": 34.885,
      "eval_steps_per_second": 4.511,
      "step": 45
    },
    {
      "epoch": 0.3357664233576642,
      "grad_norm": 0.8031398057937622,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6404,
      "step": 46
    },
    {
      "epoch": 0.34306569343065696,
      "grad_norm": 0.7656677961349487,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.5158,
      "step": 47
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 0.750630259513855,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5667,
      "step": 48
    },
    {
      "epoch": 0.35766423357664234,
      "grad_norm": 0.832373321056366,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.5518,
      "step": 49
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 1.1414823532104492,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.5022,
      "step": 50
    },
    {
      "epoch": 0.3722627737226277,
      "grad_norm": 0.8492874503135681,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.4418,
      "step": 51
    },
    {
      "epoch": 0.3795620437956204,
      "grad_norm": 0.7709046602249146,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.3382,
      "step": 52
    },
    {
      "epoch": 0.38686131386861317,
      "grad_norm": 0.7917667627334595,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3708,
      "step": 53
    },
    {
      "epoch": 0.39416058394160586,
      "grad_norm": 0.6456604599952698,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.3194,
      "step": 54
    },
    {
      "epoch": 0.39416058394160586,
      "eval_loss": 0.2983303666114807,
      "eval_runtime": 3.3312,
      "eval_samples_per_second": 34.822,
      "eval_steps_per_second": 4.503,
      "step": 54
    },
    {
      "epoch": 0.40145985401459855,
      "grad_norm": 0.6997843980789185,
      "learning_rate": 5e-05,
      "loss": 0.3086,
      "step": 55
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 0.7327139973640442,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2994,
      "step": 56
    },
    {
      "epoch": 0.41605839416058393,
      "grad_norm": 0.5769990086555481,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2329,
      "step": 57
    },
    {
      "epoch": 0.4233576642335766,
      "grad_norm": 0.6165249347686768,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2371,
      "step": 58
    },
    {
      "epoch": 0.4306569343065693,
      "grad_norm": 0.6056733131408691,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2217,
      "step": 59
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 0.6416125297546387,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1895,
      "step": 60
    },
    {
      "epoch": 0.44525547445255476,
      "grad_norm": 0.6404258012771606,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1652,
      "step": 61
    },
    {
      "epoch": 0.45255474452554745,
      "grad_norm": 0.5605882406234741,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1647,
      "step": 62
    },
    {
      "epoch": 0.45985401459854014,
      "grad_norm": 0.5275187492370605,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.129,
      "step": 63
    },
    {
      "epoch": 0.45985401459854014,
      "eval_loss": 0.13693049550056458,
      "eval_runtime": 3.3295,
      "eval_samples_per_second": 34.84,
      "eval_steps_per_second": 4.505,
      "step": 63
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 0.49548661708831787,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.129,
      "step": 64
    },
    {
      "epoch": 0.4744525547445255,
      "grad_norm": 0.3914906680583954,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1175,
      "step": 65
    },
    {
      "epoch": 0.48175182481751827,
      "grad_norm": 0.41363123059272766,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1176,
      "step": 66
    },
    {
      "epoch": 0.48905109489051096,
      "grad_norm": 0.4557228088378906,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1208,
      "step": 67
    },
    {
      "epoch": 0.49635036496350365,
      "grad_norm": 0.4289744198322296,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1057,
      "step": 68
    },
    {
      "epoch": 0.5036496350364964,
      "grad_norm": 0.39465251564979553,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1006,
      "step": 69
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 0.34635651111602783,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0931,
      "step": 70
    },
    {
      "epoch": 0.5182481751824818,
      "grad_norm": 0.27340167760849,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0751,
      "step": 71
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 0.4173787236213684,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0944,
      "step": 72
    },
    {
      "epoch": 0.5255474452554745,
      "eval_loss": 0.08399030566215515,
      "eval_runtime": 3.3264,
      "eval_samples_per_second": 34.872,
      "eval_steps_per_second": 4.509,
      "step": 72
    },
    {
      "epoch": 0.5328467153284672,
      "grad_norm": 0.36685168743133545,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0896,
      "step": 73
    },
    {
      "epoch": 0.5401459854014599,
      "grad_norm": 0.38893231749534607,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0866,
      "step": 74
    },
    {
      "epoch": 0.5474452554744526,
      "grad_norm": 0.7083960771560669,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1027,
      "step": 75
    },
    {
      "epoch": 0.5547445255474452,
      "grad_norm": 0.26822802424430847,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0691,
      "step": 76
    },
    {
      "epoch": 0.5620437956204379,
      "grad_norm": 0.3321515917778015,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0858,
      "step": 77
    },
    {
      "epoch": 0.5693430656934306,
      "grad_norm": 0.2608104944229126,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0614,
      "step": 78
    },
    {
      "epoch": 0.5766423357664233,
      "grad_norm": 0.3555421829223633,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0754,
      "step": 79
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.26505646109580994,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0671,
      "step": 80
    },
    {
      "epoch": 0.5912408759124088,
      "grad_norm": 0.2878665328025818,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0727,
      "step": 81
    },
    {
      "epoch": 0.5912408759124088,
      "eval_loss": 0.06520013511180878,
      "eval_runtime": 3.3311,
      "eval_samples_per_second": 34.823,
      "eval_steps_per_second": 4.503,
      "step": 81
    },
    {
      "epoch": 0.5985401459854015,
      "grad_norm": 0.2670612633228302,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0617,
      "step": 82
    },
    {
      "epoch": 0.6058394160583942,
      "grad_norm": 0.26891815662384033,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0681,
      "step": 83
    },
    {
      "epoch": 0.6131386861313869,
      "grad_norm": 0.2797491252422333,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0596,
      "step": 84
    },
    {
      "epoch": 0.6204379562043796,
      "grad_norm": 0.3638363480567932,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0703,
      "step": 85
    },
    {
      "epoch": 0.6277372262773723,
      "grad_norm": 0.3013610243797302,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0691,
      "step": 86
    },
    {
      "epoch": 0.635036496350365,
      "grad_norm": 0.29810383915901184,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0587,
      "step": 87
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 0.23804855346679688,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0608,
      "step": 88
    },
    {
      "epoch": 0.6496350364963503,
      "grad_norm": 0.2316129356622696,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.055,
      "step": 89
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 0.24306073784828186,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0524,
      "step": 90
    },
    {
      "epoch": 0.656934306569343,
      "eval_loss": 0.05965128540992737,
      "eval_runtime": 3.329,
      "eval_samples_per_second": 34.845,
      "eval_steps_per_second": 4.506,
      "step": 90
    },
    {
      "epoch": 0.6642335766423357,
      "grad_norm": 0.2617510259151459,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0661,
      "step": 91
    },
    {
      "epoch": 0.6715328467153284,
      "grad_norm": 0.3330131769180298,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0639,
      "step": 92
    },
    {
      "epoch": 0.6788321167883211,
      "grad_norm": 0.3344978988170624,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0611,
      "step": 93
    },
    {
      "epoch": 0.6861313868613139,
      "grad_norm": 0.32943710684776306,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.063,
      "step": 94
    },
    {
      "epoch": 0.6934306569343066,
      "grad_norm": 0.22557362914085388,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0562,
      "step": 95
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 0.2720947563648224,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0626,
      "step": 96
    },
    {
      "epoch": 0.708029197080292,
      "grad_norm": 0.24434538185596466,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0581,
      "step": 97
    },
    {
      "epoch": 0.7153284671532847,
      "grad_norm": 0.2425081729888916,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0564,
      "step": 98
    },
    {
      "epoch": 0.7226277372262774,
      "grad_norm": 0.23129865527153015,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0518,
      "step": 99
    },
    {
      "epoch": 0.7226277372262774,
      "eval_loss": 0.05876779928803444,
      "eval_runtime": 3.3257,
      "eval_samples_per_second": 34.88,
      "eval_steps_per_second": 4.51,
      "step": 99
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.29011285305023193,
      "learning_rate": 0.0,
      "loss": 0.0555,
      "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": 1.02936877203456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}