{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006587615283267457,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.587615283267457e-05,
      "grad_norm": 6.192081928253174,
      "learning_rate": 1e-05,
      "loss": 12.3252,
      "step": 1
    },
    {
      "epoch": 6.587615283267457e-05,
      "eval_loss": 12.318095207214355,
      "eval_runtime": 184.4228,
      "eval_samples_per_second": 69.319,
      "eval_steps_per_second": 8.665,
      "step": 1
    },
    {
      "epoch": 0.00013175230566534913,
      "grad_norm": 6.010153770446777,
      "learning_rate": 2e-05,
      "loss": 12.2193,
      "step": 2
    },
    {
      "epoch": 0.0001976284584980237,
      "grad_norm": 5.602427959442139,
      "learning_rate": 3e-05,
      "loss": 12.4322,
      "step": 3
    },
    {
      "epoch": 0.00026350461133069827,
      "grad_norm": 5.586225509643555,
      "learning_rate": 4e-05,
      "loss": 12.0126,
      "step": 4
    },
    {
      "epoch": 0.00032938076416337287,
      "grad_norm": 5.574303150177002,
      "learning_rate": 5e-05,
      "loss": 12.1146,
      "step": 5
    },
    {
      "epoch": 0.0003952569169960474,
      "grad_norm": 5.685383319854736,
      "learning_rate": 6e-05,
      "loss": 12.0445,
      "step": 6
    },
    {
      "epoch": 0.000461133069828722,
      "grad_norm": 6.527904987335205,
      "learning_rate": 7e-05,
      "loss": 12.0914,
      "step": 7
    },
    {
      "epoch": 0.0005270092226613965,
      "grad_norm": 5.289760589599609,
      "learning_rate": 8e-05,
      "loss": 10.8712,
      "step": 8
    },
    {
      "epoch": 0.0005928853754940712,
      "grad_norm": 6.140544414520264,
      "learning_rate": 9e-05,
      "loss": 11.6504,
      "step": 9
    },
    {
      "epoch": 0.0005928853754940712,
      "eval_loss": 11.612039566040039,
      "eval_runtime": 184.6499,
      "eval_samples_per_second": 69.234,
      "eval_steps_per_second": 8.654,
      "step": 9
    },
    {
      "epoch": 0.0006587615283267457,
      "grad_norm": 6.362745761871338,
      "learning_rate": 0.0001,
      "loss": 11.7407,
      "step": 10
    },
    {
      "epoch": 0.0007246376811594203,
      "grad_norm": 5.845798015594482,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.0677,
      "step": 11
    },
    {
      "epoch": 0.0007905138339920949,
      "grad_norm": 6.456894397735596,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.3561,
      "step": 12
    },
    {
      "epoch": 0.0008563899868247694,
      "grad_norm": 5.976311206817627,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.7305,
      "step": 13
    },
    {
      "epoch": 0.000922266139657444,
      "grad_norm": 5.910308361053467,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.7511,
      "step": 14
    },
    {
      "epoch": 0.0009881422924901185,
      "grad_norm": 5.393200397491455,
      "learning_rate": 9.924038765061042e-05,
      "loss": 9.8402,
      "step": 15
    },
    {
      "epoch": 0.001054018445322793,
      "grad_norm": 6.385056495666504,
      "learning_rate": 9.890738003669029e-05,
      "loss": 9.648,
      "step": 16
    },
    {
      "epoch": 0.0011198945981554676,
      "grad_norm": 6.098160266876221,
      "learning_rate": 9.851478631379982e-05,
      "loss": 9.3232,
      "step": 17
    },
    {
      "epoch": 0.0011857707509881424,
      "grad_norm": 6.31523323059082,
      "learning_rate": 9.806308479691595e-05,
      "loss": 8.8209,
      "step": 18
    },
    {
      "epoch": 0.0011857707509881424,
      "eval_loss": 8.577109336853027,
      "eval_runtime": 184.3733,
      "eval_samples_per_second": 69.338,
      "eval_steps_per_second": 8.667,
      "step": 18
    },
    {
      "epoch": 0.001251646903820817,
      "grad_norm": 6.199258804321289,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.415,
      "step": 19
    },
    {
      "epoch": 0.0013175230566534915,
      "grad_norm": 6.069029331207275,
      "learning_rate": 9.698463103929542e-05,
      "loss": 7.9969,
      "step": 20
    },
    {
      "epoch": 0.001383399209486166,
      "grad_norm": 6.013519763946533,
      "learning_rate": 9.635919272833938e-05,
      "loss": 8.2204,
      "step": 21
    },
    {
      "epoch": 0.0014492753623188406,
      "grad_norm": 6.165053367614746,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.5931,
      "step": 22
    },
    {
      "epoch": 0.0015151515151515152,
      "grad_norm": 6.0091753005981445,
      "learning_rate": 9.493970231495835e-05,
      "loss": 6.9307,
      "step": 23
    },
    {
      "epoch": 0.0015810276679841897,
      "grad_norm": 6.555554389953613,
      "learning_rate": 9.414737964294636e-05,
      "loss": 6.9404,
      "step": 24
    },
    {
      "epoch": 0.0016469038208168643,
      "grad_norm": 6.848858833312988,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.8355,
      "step": 25
    },
    {
      "epoch": 0.0017127799736495388,
      "grad_norm": 6.512882709503174,
      "learning_rate": 9.24024048078213e-05,
      "loss": 5.8496,
      "step": 26
    },
    {
      "epoch": 0.0017786561264822134,
      "grad_norm": 6.7052001953125,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.7517,
      "step": 27
    },
    {
      "epoch": 0.0017786561264822134,
      "eval_loss": 5.528936862945557,
      "eval_runtime": 184.5038,
      "eval_samples_per_second": 69.289,
      "eval_steps_per_second": 8.661,
      "step": 27
    },
    {
      "epoch": 0.001844532279314888,
      "grad_norm": 6.696857929229736,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.744,
      "step": 28
    },
    {
      "epoch": 0.0019104084321475627,
      "grad_norm": 6.88131046295166,
      "learning_rate": 8.940053768033609e-05,
      "loss": 5.3715,
      "step": 29
    },
    {
      "epoch": 0.001976284584980237,
      "grad_norm": 7.05979061126709,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.748,
      "step": 30
    },
    {
      "epoch": 0.002042160737812912,
      "grad_norm": 7.165943145751953,
      "learning_rate": 8.715724127386972e-05,
      "loss": 4.3262,
      "step": 31
    },
    {
      "epoch": 0.002108036890645586,
      "grad_norm": 6.821268081665039,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.4215,
      "step": 32
    },
    {
      "epoch": 0.002173913043478261,
      "grad_norm": 5.98926305770874,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.6921,
      "step": 33
    },
    {
      "epoch": 0.0022397891963109352,
      "grad_norm": 5.945371150970459,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.7048,
      "step": 34
    },
    {
      "epoch": 0.00230566534914361,
      "grad_norm": 4.138054847717285,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.308,
      "step": 35
    },
    {
      "epoch": 0.0023715415019762848,
      "grad_norm": 4.569094181060791,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.4081,
      "step": 36
    },
    {
      "epoch": 0.0023715415019762848,
      "eval_loss": 3.0261588096618652,
      "eval_runtime": 184.3164,
      "eval_samples_per_second": 69.359,
      "eval_steps_per_second": 8.67,
      "step": 36
    },
    {
      "epoch": 0.002437417654808959,
      "grad_norm": 3.269929885864258,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.8406,
      "step": 37
    },
    {
      "epoch": 0.002503293807641634,
      "grad_norm": 3.704793930053711,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.7271,
      "step": 38
    },
    {
      "epoch": 0.002569169960474308,
      "grad_norm": 5.287662029266357,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.0801,
      "step": 39
    },
    {
      "epoch": 0.002635046113306983,
      "grad_norm": 3.6738574504852295,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.5241,
      "step": 40
    },
    {
      "epoch": 0.0027009222661396573,
      "grad_norm": 3.433509111404419,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.4624,
      "step": 41
    },
    {
      "epoch": 0.002766798418972332,
      "grad_norm": 3.7118277549743652,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.7331,
      "step": 42
    },
    {
      "epoch": 0.0028326745718050064,
      "grad_norm": 4.565731525421143,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.8115,
      "step": 43
    },
    {
      "epoch": 0.002898550724637681,
      "grad_norm": 2.9661378860473633,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0928,
      "step": 44
    },
    {
      "epoch": 0.0029644268774703555,
      "grad_norm": 3.1142585277557373,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0762,
      "step": 45
    },
    {
      "epoch": 0.0029644268774703555,
      "eval_loss": 2.1579360961914062,
      "eval_runtime": 184.323,
      "eval_samples_per_second": 69.356,
      "eval_steps_per_second": 8.67,
      "step": 45
    },
    {
      "epoch": 0.0030303030303030303,
      "grad_norm": 5.064971446990967,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2238,
      "step": 46
    },
    {
      "epoch": 0.003096179183135705,
      "grad_norm": 4.904120922088623,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1618,
      "step": 47
    },
    {
      "epoch": 0.0031620553359683794,
      "grad_norm": 3.264500141143799,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8662,
      "step": 48
    },
    {
      "epoch": 0.003227931488801054,
      "grad_norm": 3.768419027328491,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.7912,
      "step": 49
    },
    {
      "epoch": 0.0032938076416337285,
      "grad_norm": 3.241663694381714,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.68,
      "step": 50
    },
    {
      "epoch": 0.0033596837944664033,
      "grad_norm": 3.5803892612457275,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.7835,
      "step": 51
    },
    {
      "epoch": 0.0034255599472990776,
      "grad_norm": 3.1176340579986572,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5672,
      "step": 52
    },
    {
      "epoch": 0.0034914361001317524,
      "grad_norm": 2.987795114517212,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.4914,
      "step": 53
    },
    {
      "epoch": 0.0035573122529644267,
      "grad_norm": 6.246347427368164,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5927,
      "step": 54
    },
    {
      "epoch": 0.0035573122529644267,
      "eval_loss": 1.4257876873016357,
      "eval_runtime": 184.4229,
      "eval_samples_per_second": 69.319,
      "eval_steps_per_second": 8.665,
      "step": 54
    },
    {
      "epoch": 0.0036231884057971015,
      "grad_norm": 3.4647183418273926,
      "learning_rate": 5e-05,
      "loss": 1.4436,
      "step": 55
    },
    {
      "epoch": 0.003689064558629776,
      "grad_norm": 3.349560499191284,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.3829,
      "step": 56
    },
    {
      "epoch": 0.0037549407114624506,
      "grad_norm": 3.176090955734253,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.2451,
      "step": 57
    },
    {
      "epoch": 0.0038208168642951254,
      "grad_norm": 3.0225908756256104,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3579,
      "step": 58
    },
    {
      "epoch": 0.0038866930171277997,
      "grad_norm": 2.4458398818969727,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.101,
      "step": 59
    },
    {
      "epoch": 0.003952569169960474,
      "grad_norm": 3.876741886138916,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.3687,
      "step": 60
    },
    {
      "epoch": 0.004018445322793149,
      "grad_norm": 3.945711374282837,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.1523,
      "step": 61
    },
    {
      "epoch": 0.004084321475625824,
      "grad_norm": 3.1722943782806396,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9701,
      "step": 62
    },
    {
      "epoch": 0.004150197628458498,
      "grad_norm": 4.902099609375,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9159,
      "step": 63
    },
    {
      "epoch": 0.004150197628458498,
      "eval_loss": 1.0228184461593628,
      "eval_runtime": 184.3336,
      "eval_samples_per_second": 69.353,
      "eval_steps_per_second": 8.669,
      "step": 63
    },
    {
      "epoch": 0.004216073781291172,
      "grad_norm": 2.736250400543213,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9313,
      "step": 64
    },
    {
      "epoch": 0.004281949934123847,
      "grad_norm": 2.595193862915039,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.9,
      "step": 65
    },
    {
      "epoch": 0.004347826086956522,
      "grad_norm": 1.9990233182907104,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.8328,
      "step": 66
    },
    {
      "epoch": 0.0044137022397891966,
      "grad_norm": 4.0702223777771,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.0872,
      "step": 67
    },
    {
      "epoch": 0.0044795783926218705,
      "grad_norm": 1.7851134538650513,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8029,
      "step": 68
    },
    {
      "epoch": 0.004545454545454545,
      "grad_norm": 2.5434176921844482,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.835,
      "step": 69
    },
    {
      "epoch": 0.00461133069828722,
      "grad_norm": 3.252372980117798,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8726,
      "step": 70
    },
    {
      "epoch": 0.004677206851119895,
      "grad_norm": 1.7027548551559448,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7541,
      "step": 71
    },
    {
      "epoch": 0.0047430830039525695,
      "grad_norm": 2.5379581451416016,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.8231,
      "step": 72
    },
    {
      "epoch": 0.0047430830039525695,
      "eval_loss": 0.8483124375343323,
      "eval_runtime": 184.3066,
      "eval_samples_per_second": 69.363,
      "eval_steps_per_second": 8.67,
      "step": 72
    },
    {
      "epoch": 0.0048089591567852434,
      "grad_norm": 1.877734899520874,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7158,
      "step": 73
    },
    {
      "epoch": 0.004874835309617918,
      "grad_norm": 1.7974519729614258,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7645,
      "step": 74
    },
    {
      "epoch": 0.004940711462450593,
      "grad_norm": 4.693776607513428,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0939,
      "step": 75
    },
    {
      "epoch": 0.005006587615283268,
      "grad_norm": 2.774831533432007,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7907,
      "step": 76
    },
    {
      "epoch": 0.005072463768115942,
      "grad_norm": 1.4862602949142456,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6863,
      "step": 77
    },
    {
      "epoch": 0.005138339920948616,
      "grad_norm": 2.5560407638549805,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.7421,
      "step": 78
    },
    {
      "epoch": 0.005204216073781291,
      "grad_norm": 3.1836204528808594,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7768,
      "step": 79
    },
    {
      "epoch": 0.005270092226613966,
      "grad_norm": 1.9725606441497803,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7135,
      "step": 80
    },
    {
      "epoch": 0.005335968379446641,
      "grad_norm": 1.8420541286468506,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7451,
      "step": 81
    },
    {
      "epoch": 0.005335968379446641,
      "eval_loss": 0.7732530832290649,
      "eval_runtime": 184.4371,
      "eval_samples_per_second": 69.314,
      "eval_steps_per_second": 8.664,
      "step": 81
    },
    {
      "epoch": 0.005401844532279315,
      "grad_norm": 1.9438694715499878,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7781,
      "step": 82
    },
    {
      "epoch": 0.005467720685111989,
      "grad_norm": 1.7922385931015015,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6667,
      "step": 83
    },
    {
      "epoch": 0.005533596837944664,
      "grad_norm": 1.500645637512207,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.6971,
      "step": 84
    },
    {
      "epoch": 0.005599472990777339,
      "grad_norm": 3.3169381618499756,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7024,
      "step": 85
    },
    {
      "epoch": 0.005665349143610013,
      "grad_norm": 2.3479697704315186,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6829,
      "step": 86
    },
    {
      "epoch": 0.005731225296442688,
      "grad_norm": 1.7033846378326416,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6208,
      "step": 87
    },
    {
      "epoch": 0.005797101449275362,
      "grad_norm": 2.391817569732666,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.7019,
      "step": 88
    },
    {
      "epoch": 0.005862977602108037,
      "grad_norm": 2.0309882164001465,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7454,
      "step": 89
    },
    {
      "epoch": 0.005928853754940711,
      "grad_norm": 2.8557684421539307,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.763,
      "step": 90
    },
    {
      "epoch": 0.005928853754940711,
      "eval_loss": 0.748928427696228,
      "eval_runtime": 184.3653,
      "eval_samples_per_second": 69.341,
      "eval_steps_per_second": 8.668,
      "step": 90
    },
    {
      "epoch": 0.005994729907773386,
      "grad_norm": 1.738196611404419,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6203,
      "step": 91
    },
    {
      "epoch": 0.006060606060606061,
      "grad_norm": 3.5670719146728516,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.8929,
      "step": 92
    },
    {
      "epoch": 0.006126482213438735,
      "grad_norm": 2.1231579780578613,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.6805,
      "step": 93
    },
    {
      "epoch": 0.00619235836627141,
      "grad_norm": 1.6460092067718506,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7208,
      "step": 94
    },
    {
      "epoch": 0.006258234519104084,
      "grad_norm": 3.6686792373657227,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.7887,
      "step": 95
    },
    {
      "epoch": 0.006324110671936759,
      "grad_norm": 2.6409358978271484,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7277,
      "step": 96
    },
    {
      "epoch": 0.006389986824769434,
      "grad_norm": 1.6902509927749634,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.5849,
      "step": 97
    },
    {
      "epoch": 0.006455862977602108,
      "grad_norm": 1.3296384811401367,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.5937,
      "step": 98
    },
    {
      "epoch": 0.006521739130434782,
      "grad_norm": 3.772615671157837,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8282,
      "step": 99
    },
    {
      "epoch": 0.006521739130434782,
      "eval_loss": 0.7452791929244995,
      "eval_runtime": 184.1886,
      "eval_samples_per_second": 69.407,
      "eval_steps_per_second": 8.676,
      "step": 99
    },
    {
      "epoch": 0.006587615283267457,
      "grad_norm": 1.7011206150054932,
      "learning_rate": 0.0,
      "loss": 0.6518,
      "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": 2047854394736640.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}