{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16680567139282734,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016680567139282735,
      "grad_norm": 6.4218597412109375,
      "learning_rate": 1e-05,
      "loss": 8.8157,
      "step": 1
    },
    {
      "epoch": 0.0016680567139282735,
      "eval_loss": 10.53897476196289,
      "eval_runtime": 5.0335,
      "eval_samples_per_second": 100.327,
      "eval_steps_per_second": 12.715,
      "step": 1
    },
    {
      "epoch": 0.003336113427856547,
      "grad_norm": 8.344048500061035,
      "learning_rate": 2e-05,
      "loss": 9.9237,
      "step": 2
    },
    {
      "epoch": 0.0050041701417848205,
      "grad_norm": 5.752366065979004,
      "learning_rate": 3e-05,
      "loss": 10.2868,
      "step": 3
    },
    {
      "epoch": 0.006672226855713094,
      "grad_norm": 12.08169174194336,
      "learning_rate": 4e-05,
      "loss": 11.6577,
      "step": 4
    },
    {
      "epoch": 0.008340283569641367,
      "grad_norm": 7.6307902336120605,
      "learning_rate": 5e-05,
      "loss": 11.6049,
      "step": 5
    },
    {
      "epoch": 0.010008340283569641,
      "grad_norm": 13.488511085510254,
      "learning_rate": 6e-05,
      "loss": 11.6571,
      "step": 6
    },
    {
      "epoch": 0.011676396997497914,
      "grad_norm": 6.870922565460205,
      "learning_rate": 7e-05,
      "loss": 10.9165,
      "step": 7
    },
    {
      "epoch": 0.013344453711426188,
      "grad_norm": 6.744866371154785,
      "learning_rate": 8e-05,
      "loss": 9.6312,
      "step": 8
    },
    {
      "epoch": 0.015012510425354461,
      "grad_norm": 8.185052871704102,
      "learning_rate": 9e-05,
      "loss": 9.159,
      "step": 9
    },
    {
      "epoch": 0.015012510425354461,
      "eval_loss": 9.887859344482422,
      "eval_runtime": 4.3895,
      "eval_samples_per_second": 115.047,
      "eval_steps_per_second": 14.58,
      "step": 9
    },
    {
      "epoch": 0.016680567139282735,
      "grad_norm": 9.440922737121582,
      "learning_rate": 0.0001,
      "loss": 10.1835,
      "step": 10
    },
    {
      "epoch": 0.01834862385321101,
      "grad_norm": 5.682453155517578,
      "learning_rate": 9.99695413509548e-05,
      "loss": 9.355,
      "step": 11
    },
    {
      "epoch": 0.020016680567139282,
      "grad_norm": 5.6532368659973145,
      "learning_rate": 9.987820251299122e-05,
      "loss": 9.1637,
      "step": 12
    },
    {
      "epoch": 0.021684737281067557,
      "grad_norm": 8.35978889465332,
      "learning_rate": 9.972609476841367e-05,
      "loss": 8.5444,
      "step": 13
    },
    {
      "epoch": 0.02335279399499583,
      "grad_norm": 7.7980217933654785,
      "learning_rate": 9.951340343707852e-05,
      "loss": 9.1922,
      "step": 14
    },
    {
      "epoch": 0.025020850708924104,
      "grad_norm": 7.174959659576416,
      "learning_rate": 9.924038765061042e-05,
      "loss": 9.0129,
      "step": 15
    },
    {
      "epoch": 0.026688907422852376,
      "grad_norm": 5.547351837158203,
      "learning_rate": 9.890738003669029e-05,
      "loss": 7.7701,
      "step": 16
    },
    {
      "epoch": 0.02835696413678065,
      "grad_norm": 5.53154993057251,
      "learning_rate": 9.851478631379982e-05,
      "loss": 7.7904,
      "step": 17
    },
    {
      "epoch": 0.030025020850708923,
      "grad_norm": 5.278870105743408,
      "learning_rate": 9.806308479691595e-05,
      "loss": 8.5489,
      "step": 18
    },
    {
      "epoch": 0.030025020850708923,
      "eval_loss": 7.729805946350098,
      "eval_runtime": 4.3901,
      "eval_samples_per_second": 115.03,
      "eval_steps_per_second": 14.578,
      "step": 18
    },
    {
      "epoch": 0.0316930775646372,
      "grad_norm": 6.058969497680664,
      "learning_rate": 9.755282581475769e-05,
      "loss": 7.761,
      "step": 19
    },
    {
      "epoch": 0.03336113427856547,
      "grad_norm": 4.8587822914123535,
      "learning_rate": 9.698463103929542e-05,
      "loss": 7.8479,
      "step": 20
    },
    {
      "epoch": 0.03502919099249374,
      "grad_norm": 8.1661376953125,
      "learning_rate": 9.635919272833938e-05,
      "loss": 8.6839,
      "step": 21
    },
    {
      "epoch": 0.03669724770642202,
      "grad_norm": 5.563140392303467,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.5815,
      "step": 22
    },
    {
      "epoch": 0.03836530442035029,
      "grad_norm": 6.0711350440979,
      "learning_rate": 9.493970231495835e-05,
      "loss": 7.1114,
      "step": 23
    },
    {
      "epoch": 0.040033361134278564,
      "grad_norm": 4.127212047576904,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.8192,
      "step": 24
    },
    {
      "epoch": 0.041701417848206836,
      "grad_norm": 6.469174861907959,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.9953,
      "step": 25
    },
    {
      "epoch": 0.043369474562135114,
      "grad_norm": 5.392281532287598,
      "learning_rate": 9.24024048078213e-05,
      "loss": 6.2443,
      "step": 26
    },
    {
      "epoch": 0.045037531276063386,
      "grad_norm": 6.442398548126221,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.6431,
      "step": 27
    },
    {
      "epoch": 0.045037531276063386,
      "eval_loss": 5.766228675842285,
      "eval_runtime": 4.4386,
      "eval_samples_per_second": 113.776,
      "eval_steps_per_second": 14.419,
      "step": 27
    },
    {
      "epoch": 0.04670558798999166,
      "grad_norm": 5.939089775085449,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.7104,
      "step": 28
    },
    {
      "epoch": 0.04837364470391994,
      "grad_norm": 5.219799041748047,
      "learning_rate": 8.940053768033609e-05,
      "loss": 5.1013,
      "step": 29
    },
    {
      "epoch": 0.05004170141784821,
      "grad_norm": 5.86526346206665,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.5001,
      "step": 30
    },
    {
      "epoch": 0.05170975813177648,
      "grad_norm": 5.6979899406433105,
      "learning_rate": 8.715724127386972e-05,
      "loss": 5.0218,
      "step": 31
    },
    {
      "epoch": 0.05337781484570475,
      "grad_norm": 6.7155022621154785,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.7259,
      "step": 32
    },
    {
      "epoch": 0.05504587155963303,
      "grad_norm": 6.724297523498535,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.4075,
      "step": 33
    },
    {
      "epoch": 0.0567139282735613,
      "grad_norm": 5.889575004577637,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.9336,
      "step": 34
    },
    {
      "epoch": 0.058381984987489574,
      "grad_norm": 5.748373031616211,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.9889,
      "step": 35
    },
    {
      "epoch": 0.060050041701417846,
      "grad_norm": 6.093235492706299,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.6407,
      "step": 36
    },
    {
      "epoch": 0.060050041701417846,
      "eval_loss": 3.569064140319824,
      "eval_runtime": 4.3989,
      "eval_samples_per_second": 114.802,
      "eval_steps_per_second": 14.549,
      "step": 36
    },
    {
      "epoch": 0.061718098415346125,
      "grad_norm": 8.288016319274902,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.3482,
      "step": 37
    },
    {
      "epoch": 0.0633861551292744,
      "grad_norm": 8.288249015808105,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.2973,
      "step": 38
    },
    {
      "epoch": 0.06505421184320268,
      "grad_norm": 12.118824005126953,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.3757,
      "step": 39
    },
    {
      "epoch": 0.06672226855713094,
      "grad_norm": 16.755817413330078,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.218,
      "step": 40
    },
    {
      "epoch": 0.06839032527105922,
      "grad_norm": 5.772495269775391,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.7063,
      "step": 41
    },
    {
      "epoch": 0.07005838198498748,
      "grad_norm": 7.338413715362549,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.9268,
      "step": 42
    },
    {
      "epoch": 0.07172643869891576,
      "grad_norm": 6.612784385681152,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.4539,
      "step": 43
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": 7.984735012054443,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.1338,
      "step": 44
    },
    {
      "epoch": 0.0750625521267723,
      "grad_norm": 4.620100021362305,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0016,
      "step": 45
    },
    {
      "epoch": 0.0750625521267723,
      "eval_loss": 2.5487208366394043,
      "eval_runtime": 4.4053,
      "eval_samples_per_second": 114.634,
      "eval_steps_per_second": 14.528,
      "step": 45
    },
    {
      "epoch": 0.07673060884070058,
      "grad_norm": 3.504941463470459,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1658,
      "step": 46
    },
    {
      "epoch": 0.07839866555462886,
      "grad_norm": 4.470401763916016,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.5759,
      "step": 47
    },
    {
      "epoch": 0.08006672226855713,
      "grad_norm": 6.22830057144165,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.4302,
      "step": 48
    },
    {
      "epoch": 0.0817347789824854,
      "grad_norm": 5.181815147399902,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.5107,
      "step": 49
    },
    {
      "epoch": 0.08340283569641367,
      "grad_norm": 8.078532218933105,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.5161,
      "step": 50
    },
    {
      "epoch": 0.08507089241034195,
      "grad_norm": 5.465274333953857,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.5525,
      "step": 51
    },
    {
      "epoch": 0.08673894912427023,
      "grad_norm": 3.293487787246704,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.0532,
      "step": 52
    },
    {
      "epoch": 0.0884070058381985,
      "grad_norm": 2.6559829711914062,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8814,
      "step": 53
    },
    {
      "epoch": 0.09007506255212677,
      "grad_norm": 2.6199533939361572,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.838,
      "step": 54
    },
    {
      "epoch": 0.09007506255212677,
      "eval_loss": 1.9475644826889038,
      "eval_runtime": 4.4657,
      "eval_samples_per_second": 113.085,
      "eval_steps_per_second": 14.332,
      "step": 54
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 3.225780963897705,
      "learning_rate": 5e-05,
      "loss": 1.9229,
      "step": 55
    },
    {
      "epoch": 0.09341117597998332,
      "grad_norm": 3.074723958969116,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.8347,
      "step": 56
    },
    {
      "epoch": 0.0950792326939116,
      "grad_norm": 3.197967290878296,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.7263,
      "step": 57
    },
    {
      "epoch": 0.09674728940783987,
      "grad_norm": 4.160449504852295,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.0481,
      "step": 58
    },
    {
      "epoch": 0.09841534612176814,
      "grad_norm": 3.7194972038269043,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.8318,
      "step": 59
    },
    {
      "epoch": 0.10008340283569642,
      "grad_norm": 2.449399709701538,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5901,
      "step": 60
    },
    {
      "epoch": 0.10175145954962468,
      "grad_norm": 3.4351389408111572,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5641,
      "step": 61
    },
    {
      "epoch": 0.10341951626355296,
      "grad_norm": 3.361947774887085,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.578,
      "step": 62
    },
    {
      "epoch": 0.10508757297748124,
      "grad_norm": 3.230473279953003,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.669,
      "step": 63
    },
    {
      "epoch": 0.10508757297748124,
      "eval_loss": 1.5358057022094727,
      "eval_runtime": 4.3922,
      "eval_samples_per_second": 114.977,
      "eval_steps_per_second": 14.571,
      "step": 63
    },
    {
      "epoch": 0.1067556296914095,
      "grad_norm": 2.4203217029571533,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4209,
      "step": 64
    },
    {
      "epoch": 0.10842368640533778,
      "grad_norm": 2.566002130508423,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.56,
      "step": 65
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 2.262228012084961,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1765,
      "step": 66
    },
    {
      "epoch": 0.11175979983319433,
      "grad_norm": 3.0135338306427,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4756,
      "step": 67
    },
    {
      "epoch": 0.1134278565471226,
      "grad_norm": 2.6408193111419678,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5436,
      "step": 68
    },
    {
      "epoch": 0.11509591326105087,
      "grad_norm": 2.683082103729248,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.5177,
      "step": 69
    },
    {
      "epoch": 0.11676396997497915,
      "grad_norm": 3.316333293914795,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5634,
      "step": 70
    },
    {
      "epoch": 0.11843202668890743,
      "grad_norm": 2.793429136276245,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.3015,
      "step": 71
    },
    {
      "epoch": 0.12010008340283569,
      "grad_norm": 2.920193910598755,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.1048,
      "step": 72
    },
    {
      "epoch": 0.12010008340283569,
      "eval_loss": 1.251120924949646,
      "eval_runtime": 4.3942,
      "eval_samples_per_second": 114.923,
      "eval_steps_per_second": 14.565,
      "step": 72
    },
    {
      "epoch": 0.12176814011676397,
      "grad_norm": 4.115492343902588,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2124,
      "step": 73
    },
    {
      "epoch": 0.12343619683069225,
      "grad_norm": 2.110515594482422,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0832,
      "step": 74
    },
    {
      "epoch": 0.12510425354462051,
      "grad_norm": 2.922022819519043,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0819,
      "step": 75
    },
    {
      "epoch": 0.1267723102585488,
      "grad_norm": 3.2596352100372314,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.4257,
      "step": 76
    },
    {
      "epoch": 0.12844036697247707,
      "grad_norm": 3.483473777770996,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.3465,
      "step": 77
    },
    {
      "epoch": 0.13010842368640535,
      "grad_norm": 2.079091787338257,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0071,
      "step": 78
    },
    {
      "epoch": 0.1317764804003336,
      "grad_norm": 2.954646587371826,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.2336,
      "step": 79
    },
    {
      "epoch": 0.13344453711426188,
      "grad_norm": 3.4457616806030273,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.4788,
      "step": 80
    },
    {
      "epoch": 0.13511259382819016,
      "grad_norm": 1.9960256814956665,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.0899,
      "step": 81
    },
    {
      "epoch": 0.13511259382819016,
      "eval_loss": 1.0880334377288818,
      "eval_runtime": 4.4371,
      "eval_samples_per_second": 113.813,
      "eval_steps_per_second": 14.424,
      "step": 81
    },
    {
      "epoch": 0.13678065054211844,
      "grad_norm": 2.532301187515259,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.021,
      "step": 82
    },
    {
      "epoch": 0.13844870725604672,
      "grad_norm": 2.122875690460205,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.97,
      "step": 83
    },
    {
      "epoch": 0.14011676396997497,
      "grad_norm": 1.9642120599746704,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9546,
      "step": 84
    },
    {
      "epoch": 0.14178482068390325,
      "grad_norm": 2.8794195652008057,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.179,
      "step": 85
    },
    {
      "epoch": 0.14345287739783152,
      "grad_norm": 2.5818090438842773,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.076,
      "step": 86
    },
    {
      "epoch": 0.1451209341117598,
      "grad_norm": 2.238755702972412,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.968,
      "step": 87
    },
    {
      "epoch": 0.14678899082568808,
      "grad_norm": 2.656874179840088,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.9599,
      "step": 88
    },
    {
      "epoch": 0.14845704753961636,
      "grad_norm": 2.070028305053711,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0208,
      "step": 89
    },
    {
      "epoch": 0.1501251042535446,
      "grad_norm": 2.119825601577759,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0384,
      "step": 90
    },
    {
      "epoch": 0.1501251042535446,
      "eval_loss": 1.014533519744873,
      "eval_runtime": 4.3775,
      "eval_samples_per_second": 115.364,
      "eval_steps_per_second": 14.62,
      "step": 90
    },
    {
      "epoch": 0.1517931609674729,
      "grad_norm": 2.214562177658081,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9634,
      "step": 91
    },
    {
      "epoch": 0.15346121768140117,
      "grad_norm": 4.23738956451416,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.9777,
      "step": 92
    },
    {
      "epoch": 0.15512927439532945,
      "grad_norm": 4.1537628173828125,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.0151,
      "step": 93
    },
    {
      "epoch": 0.15679733110925773,
      "grad_norm": 5.1043500900268555,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0603,
      "step": 94
    },
    {
      "epoch": 0.15846538782318598,
      "grad_norm": 2.0667572021484375,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.9537,
      "step": 95
    },
    {
      "epoch": 0.16013344453711426,
      "grad_norm": 2.5994327068328857,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.9878,
      "step": 96
    },
    {
      "epoch": 0.16180150125104253,
      "grad_norm": 2.356971502304077,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.9275,
      "step": 97
    },
    {
      "epoch": 0.1634695579649708,
      "grad_norm": 2.4719834327697754,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.0936,
      "step": 98
    },
    {
      "epoch": 0.1651376146788991,
      "grad_norm": 1.9262813329696655,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8934,
      "step": 99
    },
    {
      "epoch": 0.1651376146788991,
      "eval_loss": 1.00246000289917,
      "eval_runtime": 4.3721,
      "eval_samples_per_second": 115.505,
      "eval_steps_per_second": 14.638,
      "step": 99
    },
    {
      "epoch": 0.16680567139282734,
      "grad_norm": 2.25650691986084,
      "learning_rate": 0.0,
      "loss": 0.9096,
      "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": 1388375860838400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}