{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.29069767441860467,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029069767441860465,
      "grad_norm": 0.6269262433052063,
      "learning_rate": 1e-05,
      "loss": 0.4149,
      "step": 1
    },
    {
      "epoch": 0.0029069767441860465,
      "eval_loss": 0.32177430391311646,
      "eval_runtime": 32.1501,
      "eval_samples_per_second": 9.02,
      "eval_steps_per_second": 1.151,
      "step": 1
    },
    {
      "epoch": 0.005813953488372093,
      "grad_norm": 0.40142378211021423,
      "learning_rate": 2e-05,
      "loss": 0.2732,
      "step": 2
    },
    {
      "epoch": 0.00872093023255814,
      "grad_norm": 0.3893200755119324,
      "learning_rate": 3e-05,
      "loss": 0.2537,
      "step": 3
    },
    {
      "epoch": 0.011627906976744186,
      "grad_norm": 0.44946348667144775,
      "learning_rate": 4e-05,
      "loss": 0.2946,
      "step": 4
    },
    {
      "epoch": 0.014534883720930232,
      "grad_norm": 0.46690016984939575,
      "learning_rate": 5e-05,
      "loss": 0.2881,
      "step": 5
    },
    {
      "epoch": 0.01744186046511628,
      "grad_norm": 0.4786141812801361,
      "learning_rate": 6e-05,
      "loss": 0.2854,
      "step": 6
    },
    {
      "epoch": 0.020348837209302327,
      "grad_norm": 0.637237548828125,
      "learning_rate": 7e-05,
      "loss": 0.3118,
      "step": 7
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.35781624913215637,
      "learning_rate": 8e-05,
      "loss": 0.2149,
      "step": 8
    },
    {
      "epoch": 0.02616279069767442,
      "grad_norm": 0.4675982594490051,
      "learning_rate": 9e-05,
      "loss": 0.1809,
      "step": 9
    },
    {
      "epoch": 0.02616279069767442,
      "eval_loss": 0.18669699132442474,
      "eval_runtime": 31.781,
      "eval_samples_per_second": 9.125,
      "eval_steps_per_second": 1.164,
      "step": 9
    },
    {
      "epoch": 0.029069767441860465,
      "grad_norm": 1.1234859228134155,
      "learning_rate": 0.0001,
      "loss": 0.1509,
      "step": 10
    },
    {
      "epoch": 0.03197674418604651,
      "grad_norm": 0.597476601600647,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.1963,
      "step": 11
    },
    {
      "epoch": 0.03488372093023256,
      "grad_norm": 0.45688414573669434,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0975,
      "step": 12
    },
    {
      "epoch": 0.0377906976744186,
      "grad_norm": 0.43219056725502014,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0719,
      "step": 13
    },
    {
      "epoch": 0.040697674418604654,
      "grad_norm": 0.5428093075752258,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1036,
      "step": 14
    },
    {
      "epoch": 0.0436046511627907,
      "grad_norm": 0.7716228365898132,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.081,
      "step": 15
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.8211978673934937,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1221,
      "step": 16
    },
    {
      "epoch": 0.04941860465116279,
      "grad_norm": 0.9486254453659058,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1489,
      "step": 17
    },
    {
      "epoch": 0.05232558139534884,
      "grad_norm": 0.5020085573196411,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1001,
      "step": 18
    },
    {
      "epoch": 0.05232558139534884,
      "eval_loss": 0.06299833208322525,
      "eval_runtime": 31.8162,
      "eval_samples_per_second": 9.115,
      "eval_steps_per_second": 1.163,
      "step": 18
    },
    {
      "epoch": 0.055232558139534885,
      "grad_norm": 0.3962463140487671,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0522,
      "step": 19
    },
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 0.774312436580658,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1395,
      "step": 20
    },
    {
      "epoch": 0.061046511627906974,
      "grad_norm": 0.4788380265235901,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0497,
      "step": 21
    },
    {
      "epoch": 0.06395348837209303,
      "grad_norm": 0.4114557206630707,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0671,
      "step": 22
    },
    {
      "epoch": 0.06686046511627906,
      "grad_norm": 0.18382249772548676,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0168,
      "step": 23
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.30654194951057434,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0493,
      "step": 24
    },
    {
      "epoch": 0.07267441860465117,
      "grad_norm": 0.5613061189651489,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0914,
      "step": 25
    },
    {
      "epoch": 0.0755813953488372,
      "grad_norm": 0.46508359909057617,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0782,
      "step": 26
    },
    {
      "epoch": 0.07848837209302326,
      "grad_norm": 0.4454496204853058,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0576,
      "step": 27
    },
    {
      "epoch": 0.07848837209302326,
      "eval_loss": 0.05647557973861694,
      "eval_runtime": 31.8519,
      "eval_samples_per_second": 9.105,
      "eval_steps_per_second": 1.162,
      "step": 27
    },
    {
      "epoch": 0.08139534883720931,
      "grad_norm": 0.9659534692764282,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.101,
      "step": 28
    },
    {
      "epoch": 0.08430232558139535,
      "grad_norm": 0.36201971769332886,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0491,
      "step": 29
    },
    {
      "epoch": 0.0872093023255814,
      "grad_norm": 0.45469900965690613,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0489,
      "step": 30
    },
    {
      "epoch": 0.09011627906976744,
      "grad_norm": 0.31370460987091064,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0514,
      "step": 31
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.4985674321651459,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1133,
      "step": 32
    },
    {
      "epoch": 0.09593023255813954,
      "grad_norm": 0.4283120334148407,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0705,
      "step": 33
    },
    {
      "epoch": 0.09883720930232558,
      "grad_norm": 0.42796996235847473,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0309,
      "step": 34
    },
    {
      "epoch": 0.10174418604651163,
      "grad_norm": 0.30421769618988037,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0499,
      "step": 35
    },
    {
      "epoch": 0.10465116279069768,
      "grad_norm": 0.42994582653045654,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0659,
      "step": 36
    },
    {
      "epoch": 0.10465116279069768,
      "eval_loss": 0.04967455193400383,
      "eval_runtime": 31.8478,
      "eval_samples_per_second": 9.106,
      "eval_steps_per_second": 1.162,
      "step": 36
    },
    {
      "epoch": 0.10755813953488372,
      "grad_norm": 0.250835657119751,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0337,
      "step": 37
    },
    {
      "epoch": 0.11046511627906977,
      "grad_norm": 0.28204551339149475,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0348,
      "step": 38
    },
    {
      "epoch": 0.11337209302325581,
      "grad_norm": 0.30669015645980835,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0415,
      "step": 39
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.3696398437023163,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0438,
      "step": 40
    },
    {
      "epoch": 0.11918604651162791,
      "grad_norm": 0.3825896978378296,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0457,
      "step": 41
    },
    {
      "epoch": 0.12209302325581395,
      "grad_norm": 0.5122129917144775,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0688,
      "step": 42
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.2742997407913208,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0301,
      "step": 43
    },
    {
      "epoch": 0.12790697674418605,
      "grad_norm": 0.2424289584159851,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0279,
      "step": 44
    },
    {
      "epoch": 0.1308139534883721,
      "grad_norm": 0.2966480255126953,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0617,
      "step": 45
    },
    {
      "epoch": 0.1308139534883721,
      "eval_loss": 0.04850827157497406,
      "eval_runtime": 31.8294,
      "eval_samples_per_second": 9.111,
      "eval_steps_per_second": 1.162,
      "step": 45
    },
    {
      "epoch": 0.13372093023255813,
      "grad_norm": 0.7979899048805237,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0336,
      "step": 46
    },
    {
      "epoch": 0.13662790697674418,
      "grad_norm": 0.32393476366996765,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0464,
      "step": 47
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.34652408957481384,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0269,
      "step": 48
    },
    {
      "epoch": 0.14244186046511628,
      "grad_norm": 0.41564905643463135,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0573,
      "step": 49
    },
    {
      "epoch": 0.14534883720930233,
      "grad_norm": 0.25396621227264404,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.038,
      "step": 50
    },
    {
      "epoch": 0.14825581395348839,
      "grad_norm": 0.33711540699005127,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0418,
      "step": 51
    },
    {
      "epoch": 0.1511627906976744,
      "grad_norm": 0.38511842489242554,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0372,
      "step": 52
    },
    {
      "epoch": 0.15406976744186046,
      "grad_norm": 0.3456517457962036,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0533,
      "step": 53
    },
    {
      "epoch": 0.1569767441860465,
      "grad_norm": 0.5780833959579468,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0845,
      "step": 54
    },
    {
      "epoch": 0.1569767441860465,
      "eval_loss": 0.04621773585677147,
      "eval_runtime": 31.8453,
      "eval_samples_per_second": 9.107,
      "eval_steps_per_second": 1.162,
      "step": 54
    },
    {
      "epoch": 0.15988372093023256,
      "grad_norm": 0.4145897924900055,
      "learning_rate": 5e-05,
      "loss": 0.0737,
      "step": 55
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.3511849045753479,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0634,
      "step": 56
    },
    {
      "epoch": 0.16569767441860464,
      "grad_norm": 0.4212923049926758,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0872,
      "step": 57
    },
    {
      "epoch": 0.1686046511627907,
      "grad_norm": 0.37725627422332764,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0438,
      "step": 58
    },
    {
      "epoch": 0.17151162790697674,
      "grad_norm": 0.43850046396255493,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0856,
      "step": 59
    },
    {
      "epoch": 0.1744186046511628,
      "grad_norm": 0.24517984688282013,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0228,
      "step": 60
    },
    {
      "epoch": 0.17732558139534885,
      "grad_norm": 0.45141902565956116,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0624,
      "step": 61
    },
    {
      "epoch": 0.18023255813953487,
      "grad_norm": 0.2519844174385071,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0363,
      "step": 62
    },
    {
      "epoch": 0.18313953488372092,
      "grad_norm": 0.3177478611469269,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0589,
      "step": 63
    },
    {
      "epoch": 0.18313953488372092,
      "eval_loss": 0.0444461964070797,
      "eval_runtime": 31.8213,
      "eval_samples_per_second": 9.113,
      "eval_steps_per_second": 1.163,
      "step": 63
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.2350810170173645,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0268,
      "step": 64
    },
    {
      "epoch": 0.18895348837209303,
      "grad_norm": 0.19069309532642365,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0257,
      "step": 65
    },
    {
      "epoch": 0.19186046511627908,
      "grad_norm": 0.34234821796417236,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0603,
      "step": 66
    },
    {
      "epoch": 0.19476744186046513,
      "grad_norm": 0.2891956865787506,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0559,
      "step": 67
    },
    {
      "epoch": 0.19767441860465115,
      "grad_norm": 0.3088008463382721,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0634,
      "step": 68
    },
    {
      "epoch": 0.2005813953488372,
      "grad_norm": 0.42435476183891296,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0449,
      "step": 69
    },
    {
      "epoch": 0.20348837209302326,
      "grad_norm": 0.3041639029979706,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0342,
      "step": 70
    },
    {
      "epoch": 0.2063953488372093,
      "grad_norm": 0.2714124023914337,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0559,
      "step": 71
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.27597737312316895,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0394,
      "step": 72
    },
    {
      "epoch": 0.20930232558139536,
      "eval_loss": 0.04371662437915802,
      "eval_runtime": 31.8731,
      "eval_samples_per_second": 9.099,
      "eval_steps_per_second": 1.161,
      "step": 72
    },
    {
      "epoch": 0.21220930232558138,
      "grad_norm": 0.27406489849090576,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.042,
      "step": 73
    },
    {
      "epoch": 0.21511627906976744,
      "grad_norm": 0.30766603350639343,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0433,
      "step": 74
    },
    {
      "epoch": 0.2180232558139535,
      "grad_norm": 0.2573796510696411,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0331,
      "step": 75
    },
    {
      "epoch": 0.22093023255813954,
      "grad_norm": 0.19937089085578918,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0324,
      "step": 76
    },
    {
      "epoch": 0.2238372093023256,
      "grad_norm": 0.20462292432785034,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0236,
      "step": 77
    },
    {
      "epoch": 0.22674418604651161,
      "grad_norm": 0.28567931056022644,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0276,
      "step": 78
    },
    {
      "epoch": 0.22965116279069767,
      "grad_norm": 0.4329880475997925,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0775,
      "step": 79
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.4729216992855072,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0266,
      "step": 80
    },
    {
      "epoch": 0.23546511627906977,
      "grad_norm": 0.19957783818244934,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0197,
      "step": 81
    },
    {
      "epoch": 0.23546511627906977,
      "eval_loss": 0.04431019350886345,
      "eval_runtime": 31.87,
      "eval_samples_per_second": 9.099,
      "eval_steps_per_second": 1.161,
      "step": 81
    },
    {
      "epoch": 0.23837209302325582,
      "grad_norm": 0.3341924846172333,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0913,
      "step": 82
    },
    {
      "epoch": 0.24127906976744187,
      "grad_norm": 0.18140165507793427,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0353,
      "step": 83
    },
    {
      "epoch": 0.2441860465116279,
      "grad_norm": 0.2153806984424591,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0243,
      "step": 84
    },
    {
      "epoch": 0.24709302325581395,
      "grad_norm": 0.2617124617099762,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0446,
      "step": 85
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09424830228090286,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0089,
      "step": 86
    },
    {
      "epoch": 0.25290697674418605,
      "grad_norm": 0.25709268450737,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0519,
      "step": 87
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.5080177783966064,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0525,
      "step": 88
    },
    {
      "epoch": 0.25872093023255816,
      "grad_norm": 0.39113932847976685,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0497,
      "step": 89
    },
    {
      "epoch": 0.2616279069767442,
      "grad_norm": 0.22805412113666534,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0343,
      "step": 90
    },
    {
      "epoch": 0.2616279069767442,
      "eval_loss": 0.044002652168273926,
      "eval_runtime": 31.8503,
      "eval_samples_per_second": 9.105,
      "eval_steps_per_second": 1.162,
      "step": 90
    },
    {
      "epoch": 0.26453488372093026,
      "grad_norm": 0.24416109919548035,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0488,
      "step": 91
    },
    {
      "epoch": 0.26744186046511625,
      "grad_norm": 0.2086295783519745,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0329,
      "step": 92
    },
    {
      "epoch": 0.2703488372093023,
      "grad_norm": 0.20100471377372742,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0207,
      "step": 93
    },
    {
      "epoch": 0.27325581395348836,
      "grad_norm": 0.28016161918640137,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0322,
      "step": 94
    },
    {
      "epoch": 0.2761627906976744,
      "grad_norm": 0.32431530952453613,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0382,
      "step": 95
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.2922443449497223,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0363,
      "step": 96
    },
    {
      "epoch": 0.2819767441860465,
      "grad_norm": 0.34880465269088745,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0443,
      "step": 97
    },
    {
      "epoch": 0.28488372093023256,
      "grad_norm": 0.882049560546875,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0361,
      "step": 98
    },
    {
      "epoch": 0.2877906976744186,
      "grad_norm": 0.5549324750900269,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0871,
      "step": 99
    },
    {
      "epoch": 0.2877906976744186,
      "eval_loss": 0.043825071305036545,
      "eval_runtime": 31.844,
      "eval_samples_per_second": 9.107,
      "eval_steps_per_second": 1.162,
      "step": 99
    },
    {
      "epoch": 0.29069767441860467,
      "grad_norm": 0.2323886752128601,
      "learning_rate": 0.0,
      "loss": 0.0321,
      "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": 7.530155928138547e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}