{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021308331557639035,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021308331557639036,
      "grad_norm": 1.4914582967758179,
      "learning_rate": 1e-05,
      "loss": 2.9025,
      "step": 1
    },
    {
      "epoch": 0.00021308331557639036,
      "eval_loss": 3.0053186416625977,
      "eval_runtime": 481.0243,
      "eval_samples_per_second": 8.216,
      "eval_steps_per_second": 1.027,
      "step": 1
    },
    {
      "epoch": 0.0004261666311527807,
      "grad_norm": 1.2396098375320435,
      "learning_rate": 2e-05,
      "loss": 2.8422,
      "step": 2
    },
    {
      "epoch": 0.0006392499467291711,
      "grad_norm": 1.7862789630889893,
      "learning_rate": 3e-05,
      "loss": 2.9618,
      "step": 3
    },
    {
      "epoch": 0.0008523332623055614,
      "grad_norm": 1.4219273328781128,
      "learning_rate": 4e-05,
      "loss": 2.9024,
      "step": 4
    },
    {
      "epoch": 0.001065416577881952,
      "grad_norm": 1.5405254364013672,
      "learning_rate": 5e-05,
      "loss": 2.8993,
      "step": 5
    },
    {
      "epoch": 0.0012784998934583422,
      "grad_norm": 1.578925371170044,
      "learning_rate": 6e-05,
      "loss": 2.9408,
      "step": 6
    },
    {
      "epoch": 0.0014915832090347326,
      "grad_norm": 1.885631799697876,
      "learning_rate": 7e-05,
      "loss": 2.9361,
      "step": 7
    },
    {
      "epoch": 0.0017046665246111229,
      "grad_norm": 1.7301489114761353,
      "learning_rate": 8e-05,
      "loss": 2.776,
      "step": 8
    },
    {
      "epoch": 0.0019177498401875134,
      "grad_norm": 1.9182066917419434,
      "learning_rate": 9e-05,
      "loss": 2.7626,
      "step": 9
    },
    {
      "epoch": 0.0019177498401875134,
      "eval_loss": 2.742213487625122,
      "eval_runtime": 484.7163,
      "eval_samples_per_second": 8.153,
      "eval_steps_per_second": 1.019,
      "step": 9
    },
    {
      "epoch": 0.002130833155763904,
      "grad_norm": 1.6169171333312988,
      "learning_rate": 0.0001,
      "loss": 2.5475,
      "step": 10
    },
    {
      "epoch": 0.002343916471340294,
      "grad_norm": 1.6501270532608032,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.6424,
      "step": 11
    },
    {
      "epoch": 0.0025569997869166845,
      "grad_norm": 1.6458073854446411,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.7299,
      "step": 12
    },
    {
      "epoch": 0.002770083102493075,
      "grad_norm": 2.196349859237671,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.3784,
      "step": 13
    },
    {
      "epoch": 0.002983166418069465,
      "grad_norm": 2.144585132598877,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.4827,
      "step": 14
    },
    {
      "epoch": 0.0031962497336458554,
      "grad_norm": 2.0523390769958496,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4431,
      "step": 15
    },
    {
      "epoch": 0.0034093330492222457,
      "grad_norm": 2.20808744430542,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.6465,
      "step": 16
    },
    {
      "epoch": 0.0036224163647986364,
      "grad_norm": 2.1431615352630615,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.7287,
      "step": 17
    },
    {
      "epoch": 0.0038354996803750267,
      "grad_norm": 2.179090738296509,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4462,
      "step": 18
    },
    {
      "epoch": 0.0038354996803750267,
      "eval_loss": 2.446166753768921,
      "eval_runtime": 484.7504,
      "eval_samples_per_second": 8.153,
      "eval_steps_per_second": 1.019,
      "step": 18
    },
    {
      "epoch": 0.004048582995951417,
      "grad_norm": 1.9910677671432495,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5489,
      "step": 19
    },
    {
      "epoch": 0.004261666311527808,
      "grad_norm": 1.7879835367202759,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3464,
      "step": 20
    },
    {
      "epoch": 0.004474749627104198,
      "grad_norm": 1.7158172130584717,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.3559,
      "step": 21
    },
    {
      "epoch": 0.004687832942680588,
      "grad_norm": 1.5184911489486694,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.583,
      "step": 22
    },
    {
      "epoch": 0.004900916258256978,
      "grad_norm": 1.3161325454711914,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.4803,
      "step": 23
    },
    {
      "epoch": 0.005113999573833369,
      "grad_norm": 1.6111788749694824,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3079,
      "step": 24
    },
    {
      "epoch": 0.005327082889409759,
      "grad_norm": 1.6040608882904053,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3188,
      "step": 25
    },
    {
      "epoch": 0.00554016620498615,
      "grad_norm": 1.7765617370605469,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.1691,
      "step": 26
    },
    {
      "epoch": 0.00575324952056254,
      "grad_norm": 1.7104406356811523,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3399,
      "step": 27
    },
    {
      "epoch": 0.00575324952056254,
      "eval_loss": 2.3587300777435303,
      "eval_runtime": 485.0287,
      "eval_samples_per_second": 8.148,
      "eval_steps_per_second": 1.018,
      "step": 27
    },
    {
      "epoch": 0.00596633283613893,
      "grad_norm": 1.2958590984344482,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.336,
      "step": 28
    },
    {
      "epoch": 0.006179416151715321,
      "grad_norm": 1.8951802253723145,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.5203,
      "step": 29
    },
    {
      "epoch": 0.006392499467291711,
      "grad_norm": 1.4188854694366455,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.5081,
      "step": 30
    },
    {
      "epoch": 0.0066055827828681015,
      "grad_norm": 1.756216287612915,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.2355,
      "step": 31
    },
    {
      "epoch": 0.006818666098444491,
      "grad_norm": 1.6971544027328491,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2753,
      "step": 32
    },
    {
      "epoch": 0.007031749414020882,
      "grad_norm": 1.730682611465454,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.2489,
      "step": 33
    },
    {
      "epoch": 0.007244832729597273,
      "grad_norm": 1.500222086906433,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.5747,
      "step": 34
    },
    {
      "epoch": 0.007457916045173663,
      "grad_norm": 1.689780592918396,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.4923,
      "step": 35
    },
    {
      "epoch": 0.0076709993607500535,
      "grad_norm": 1.5094739198684692,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.3113,
      "step": 36
    },
    {
      "epoch": 0.0076709993607500535,
      "eval_loss": 2.3216378688812256,
      "eval_runtime": 485.2683,
      "eval_samples_per_second": 8.144,
      "eval_steps_per_second": 1.018,
      "step": 36
    },
    {
      "epoch": 0.007884082676326443,
      "grad_norm": 1.8050920963287354,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1219,
      "step": 37
    },
    {
      "epoch": 0.008097165991902834,
      "grad_norm": 1.7702151536941528,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.3288,
      "step": 38
    },
    {
      "epoch": 0.008310249307479225,
      "grad_norm": 1.9148733615875244,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.2052,
      "step": 39
    },
    {
      "epoch": 0.008523332623055616,
      "grad_norm": 1.9198733568191528,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0524,
      "step": 40
    },
    {
      "epoch": 0.008736415938632005,
      "grad_norm": 1.6441048383712769,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3595,
      "step": 41
    },
    {
      "epoch": 0.008949499254208395,
      "grad_norm": 1.6988778114318848,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.2509,
      "step": 42
    },
    {
      "epoch": 0.009162582569784786,
      "grad_norm": 1.6815834045410156,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.285,
      "step": 43
    },
    {
      "epoch": 0.009375665885361177,
      "grad_norm": 1.5567946434020996,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.2638,
      "step": 44
    },
    {
      "epoch": 0.009588749200937566,
      "grad_norm": 1.5238242149353027,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.455,
      "step": 45
    },
    {
      "epoch": 0.009588749200937566,
      "eval_loss": 2.2901864051818848,
      "eval_runtime": 484.6308,
      "eval_samples_per_second": 8.155,
      "eval_steps_per_second": 1.019,
      "step": 45
    },
    {
      "epoch": 0.009801832516513957,
      "grad_norm": 1.698690414428711,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5036,
      "step": 46
    },
    {
      "epoch": 0.010014915832090347,
      "grad_norm": 1.5626423358917236,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.3447,
      "step": 47
    },
    {
      "epoch": 0.010227999147666738,
      "grad_norm": 1.6634929180145264,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2132,
      "step": 48
    },
    {
      "epoch": 0.010441082463243129,
      "grad_norm": 1.5750799179077148,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.4226,
      "step": 49
    },
    {
      "epoch": 0.010654165778819518,
      "grad_norm": 1.4968082904815674,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.3799,
      "step": 50
    },
    {
      "epoch": 0.010867249094395908,
      "grad_norm": 1.7488001585006714,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.0902,
      "step": 51
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 1.5967189073562622,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.3407,
      "step": 52
    },
    {
      "epoch": 0.01129341572554869,
      "grad_norm": 1.6917262077331543,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.4421,
      "step": 53
    },
    {
      "epoch": 0.01150649904112508,
      "grad_norm": 1.5144695043563843,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.1417,
      "step": 54
    },
    {
      "epoch": 0.01150649904112508,
      "eval_loss": 2.2762832641601562,
      "eval_runtime": 485.0012,
      "eval_samples_per_second": 8.148,
      "eval_steps_per_second": 1.019,
      "step": 54
    },
    {
      "epoch": 0.01171958235670147,
      "grad_norm": 2.0978071689605713,
      "learning_rate": 5e-05,
      "loss": 2.368,
      "step": 55
    },
    {
      "epoch": 0.01193266567227786,
      "grad_norm": 1.3823351860046387,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.2761,
      "step": 56
    },
    {
      "epoch": 0.012145748987854251,
      "grad_norm": 1.401353120803833,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.4411,
      "step": 57
    },
    {
      "epoch": 0.012358832303430642,
      "grad_norm": 1.5619628429412842,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.4282,
      "step": 58
    },
    {
      "epoch": 0.012571915619007033,
      "grad_norm": 1.6720349788665771,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.1992,
      "step": 59
    },
    {
      "epoch": 0.012784998934583422,
      "grad_norm": 1.9900810718536377,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.189,
      "step": 60
    },
    {
      "epoch": 0.012998082250159812,
      "grad_norm": 1.8609704971313477,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.3073,
      "step": 61
    },
    {
      "epoch": 0.013211165565736203,
      "grad_norm": 1.6070359945297241,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.2932,
      "step": 62
    },
    {
      "epoch": 0.013424248881312594,
      "grad_norm": 1.7144007682800293,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.3884,
      "step": 63
    },
    {
      "epoch": 0.013424248881312594,
      "eval_loss": 2.262110948562622,
      "eval_runtime": 484.8431,
      "eval_samples_per_second": 8.151,
      "eval_steps_per_second": 1.019,
      "step": 63
    },
    {
      "epoch": 0.013637332196888983,
      "grad_norm": 1.6447594165802002,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.4163,
      "step": 64
    },
    {
      "epoch": 0.013850415512465374,
      "grad_norm": 1.65079927444458,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.2708,
      "step": 65
    },
    {
      "epoch": 0.014063498828041764,
      "grad_norm": 1.7811284065246582,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.1705,
      "step": 66
    },
    {
      "epoch": 0.014276582143618155,
      "grad_norm": 1.7202013731002808,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.3249,
      "step": 67
    },
    {
      "epoch": 0.014489665459194546,
      "grad_norm": 1.7483406066894531,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.2645,
      "step": 68
    },
    {
      "epoch": 0.014702748774770935,
      "grad_norm": 2.087839126586914,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.1354,
      "step": 69
    },
    {
      "epoch": 0.014915832090347326,
      "grad_norm": 1.6836611032485962,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.2473,
      "step": 70
    },
    {
      "epoch": 0.015128915405923716,
      "grad_norm": 1.3222910165786743,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.1784,
      "step": 71
    },
    {
      "epoch": 0.015341998721500107,
      "grad_norm": 1.6349443197250366,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.0551,
      "step": 72
    },
    {
      "epoch": 0.015341998721500107,
      "eval_loss": 2.254314422607422,
      "eval_runtime": 484.9695,
      "eval_samples_per_second": 8.149,
      "eval_steps_per_second": 1.019,
      "step": 72
    },
    {
      "epoch": 0.015555082037076498,
      "grad_norm": 1.65912926197052,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.325,
      "step": 73
    },
    {
      "epoch": 0.015768165352652887,
      "grad_norm": 1.8558361530303955,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.5441,
      "step": 74
    },
    {
      "epoch": 0.015981248668229277,
      "grad_norm": 1.7904530763626099,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.2417,
      "step": 75
    },
    {
      "epoch": 0.016194331983805668,
      "grad_norm": 1.606557011604309,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.32,
      "step": 76
    },
    {
      "epoch": 0.01640741529938206,
      "grad_norm": 1.6703760623931885,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.5816,
      "step": 77
    },
    {
      "epoch": 0.01662049861495845,
      "grad_norm": 1.63593590259552,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.3473,
      "step": 78
    },
    {
      "epoch": 0.01683358193053484,
      "grad_norm": 1.9115629196166992,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.2544,
      "step": 79
    },
    {
      "epoch": 0.01704666524611123,
      "grad_norm": 1.720870018005371,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.1917,
      "step": 80
    },
    {
      "epoch": 0.01725974856168762,
      "grad_norm": 1.7113711833953857,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.0777,
      "step": 81
    },
    {
      "epoch": 0.01725974856168762,
      "eval_loss": 2.248765468597412,
      "eval_runtime": 484.7178,
      "eval_samples_per_second": 8.153,
      "eval_steps_per_second": 1.019,
      "step": 81
    },
    {
      "epoch": 0.01747283187726401,
      "grad_norm": 1.6351940631866455,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.3214,
      "step": 82
    },
    {
      "epoch": 0.0176859151928404,
      "grad_norm": 1.4796867370605469,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.2755,
      "step": 83
    },
    {
      "epoch": 0.01789899850841679,
      "grad_norm": 1.394295334815979,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.4346,
      "step": 84
    },
    {
      "epoch": 0.01811208182399318,
      "grad_norm": 1.846497654914856,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1393,
      "step": 85
    },
    {
      "epoch": 0.018325165139569572,
      "grad_norm": 1.752183198928833,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.4348,
      "step": 86
    },
    {
      "epoch": 0.018538248455145963,
      "grad_norm": 1.6644121408462524,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.3184,
      "step": 87
    },
    {
      "epoch": 0.018751331770722354,
      "grad_norm": 1.5804589986801147,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.839,
      "step": 88
    },
    {
      "epoch": 0.018964415086298744,
      "grad_norm": 1.5491611957550049,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.3984,
      "step": 89
    },
    {
      "epoch": 0.01917749840187513,
      "grad_norm": 1.6144686937332153,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.0352,
      "step": 90
    },
    {
      "epoch": 0.01917749840187513,
      "eval_loss": 2.2463996410369873,
      "eval_runtime": 484.6085,
      "eval_samples_per_second": 8.155,
      "eval_steps_per_second": 1.019,
      "step": 90
    },
    {
      "epoch": 0.019390581717451522,
      "grad_norm": 1.871982455253601,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.2682,
      "step": 91
    },
    {
      "epoch": 0.019603665033027913,
      "grad_norm": 1.5905784368515015,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1101,
      "step": 92
    },
    {
      "epoch": 0.019816748348604304,
      "grad_norm": 1.4988384246826172,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.4955,
      "step": 93
    },
    {
      "epoch": 0.020029831664180694,
      "grad_norm": 1.6045547723770142,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.488,
      "step": 94
    },
    {
      "epoch": 0.020242914979757085,
      "grad_norm": 1.3878628015518188,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.138,
      "step": 95
    },
    {
      "epoch": 0.020455998295333476,
      "grad_norm": 1.6201906204223633,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.426,
      "step": 96
    },
    {
      "epoch": 0.020669081610909867,
      "grad_norm": 1.7183762788772583,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.1243,
      "step": 97
    },
    {
      "epoch": 0.020882164926486257,
      "grad_norm": 1.3840333223342896,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.3035,
      "step": 98
    },
    {
      "epoch": 0.021095248242062648,
      "grad_norm": 1.535163402557373,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.306,
      "step": 99
    },
    {
      "epoch": 0.021095248242062648,
      "eval_loss": 2.2457332611083984,
      "eval_runtime": 484.4586,
      "eval_samples_per_second": 8.158,
      "eval_steps_per_second": 1.02,
      "step": 99
    },
    {
      "epoch": 0.021308331557639035,
      "grad_norm": 1.3996747732162476,
      "learning_rate": 0.0,
      "loss": 2.4191,
      "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
}