{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006207517303454483,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.207517303454484e-05,
      "grad_norm": 8.319231033325195,
      "learning_rate": 1e-05,
      "loss": 3.376,
      "step": 1
    },
    {
      "epoch": 6.207517303454484e-05,
      "eval_loss": 3.6641039848327637,
      "eval_runtime": 2234.5572,
      "eval_samples_per_second": 6.071,
      "eval_steps_per_second": 0.759,
      "step": 1
    },
    {
      "epoch": 0.00012415034606908968,
      "grad_norm": 16.260986328125,
      "learning_rate": 2e-05,
      "loss": 4.4623,
      "step": 2
    },
    {
      "epoch": 0.0001862255191036345,
      "grad_norm": 10.607361793518066,
      "learning_rate": 3e-05,
      "loss": 3.5527,
      "step": 3
    },
    {
      "epoch": 0.00024830069213817936,
      "grad_norm": 9.623229026794434,
      "learning_rate": 4e-05,
      "loss": 3.8722,
      "step": 4
    },
    {
      "epoch": 0.00031037586517272415,
      "grad_norm": 11.056772232055664,
      "learning_rate": 5e-05,
      "loss": 3.2705,
      "step": 5
    },
    {
      "epoch": 0.000372451038207269,
      "grad_norm": 9.194046974182129,
      "learning_rate": 6e-05,
      "loss": 2.9016,
      "step": 6
    },
    {
      "epoch": 0.00043452621124181383,
      "grad_norm": 9.070704460144043,
      "learning_rate": 7e-05,
      "loss": 2.413,
      "step": 7
    },
    {
      "epoch": 0.0004966013842763587,
      "grad_norm": 8.438094139099121,
      "learning_rate": 8e-05,
      "loss": 2.0059,
      "step": 8
    },
    {
      "epoch": 0.0005586765573109035,
      "grad_norm": 6.488578796386719,
      "learning_rate": 9e-05,
      "loss": 1.2815,
      "step": 9
    },
    {
      "epoch": 0.0005586765573109035,
      "eval_loss": 0.877297580242157,
      "eval_runtime": 2238.6868,
      "eval_samples_per_second": 6.06,
      "eval_steps_per_second": 0.758,
      "step": 9
    },
    {
      "epoch": 0.0006207517303454483,
      "grad_norm": 4.686011791229248,
      "learning_rate": 0.0001,
      "loss": 0.9778,
      "step": 10
    },
    {
      "epoch": 0.0006828269033799932,
      "grad_norm": 3.337484836578369,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.6582,
      "step": 11
    },
    {
      "epoch": 0.000744902076414538,
      "grad_norm": 4.096186637878418,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3817,
      "step": 12
    },
    {
      "epoch": 0.0008069772494490829,
      "grad_norm": 3.6979470252990723,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.401,
      "step": 13
    },
    {
      "epoch": 0.0008690524224836277,
      "grad_norm": 3.9787817001342773,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3926,
      "step": 14
    },
    {
      "epoch": 0.0009311275955181726,
      "grad_norm": 2.9579179286956787,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4016,
      "step": 15
    },
    {
      "epoch": 0.0009932027685527174,
      "grad_norm": 3.684504270553589,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3088,
      "step": 16
    },
    {
      "epoch": 0.0010552779415872622,
      "grad_norm": 3.4828040599823,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.4045,
      "step": 17
    },
    {
      "epoch": 0.001117353114621807,
      "grad_norm": 2.041842222213745,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3169,
      "step": 18
    },
    {
      "epoch": 0.001117353114621807,
      "eval_loss": 0.29961079359054565,
      "eval_runtime": 2236.1553,
      "eval_samples_per_second": 6.067,
      "eval_steps_per_second": 0.758,
      "step": 18
    },
    {
      "epoch": 0.0011794282876563518,
      "grad_norm": 1.8513263463974,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.188,
      "step": 19
    },
    {
      "epoch": 0.0012415034606908966,
      "grad_norm": 1.9141404628753662,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2901,
      "step": 20
    },
    {
      "epoch": 0.0013035786337254416,
      "grad_norm": 2.310896158218384,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.2405,
      "step": 21
    },
    {
      "epoch": 0.0013656538067599864,
      "grad_norm": 2.9560153484344482,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2803,
      "step": 22
    },
    {
      "epoch": 0.0014277289797945312,
      "grad_norm": 2.5063514709472656,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2212,
      "step": 23
    },
    {
      "epoch": 0.001489804152829076,
      "grad_norm": 2.2873716354370117,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2478,
      "step": 24
    },
    {
      "epoch": 0.0015518793258636207,
      "grad_norm": 1.8756879568099976,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.232,
      "step": 25
    },
    {
      "epoch": 0.0016139544988981657,
      "grad_norm": 1.3680589199066162,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1827,
      "step": 26
    },
    {
      "epoch": 0.0016760296719327105,
      "grad_norm": 1.4772603511810303,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2457,
      "step": 27
    },
    {
      "epoch": 0.0016760296719327105,
      "eval_loss": 0.22593805193901062,
      "eval_runtime": 2235.9505,
      "eval_samples_per_second": 6.067,
      "eval_steps_per_second": 0.759,
      "step": 27
    },
    {
      "epoch": 0.0017381048449672553,
      "grad_norm": 1.2929972410202026,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2264,
      "step": 28
    },
    {
      "epoch": 0.0018001800180018,
      "grad_norm": 1.3302463293075562,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1391,
      "step": 29
    },
    {
      "epoch": 0.001862255191036345,
      "grad_norm": 0.9539820551872253,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1643,
      "step": 30
    },
    {
      "epoch": 0.00192433036407089,
      "grad_norm": 0.9900975227355957,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1359,
      "step": 31
    },
    {
      "epoch": 0.001986405537105435,
      "grad_norm": 1.4312468767166138,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1985,
      "step": 32
    },
    {
      "epoch": 0.0020484807101399795,
      "grad_norm": 1.6667448282241821,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2468,
      "step": 33
    },
    {
      "epoch": 0.0021105558831745245,
      "grad_norm": 1.0572471618652344,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1263,
      "step": 34
    },
    {
      "epoch": 0.002172631056209069,
      "grad_norm": 3.2816107273101807,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3581,
      "step": 35
    },
    {
      "epoch": 0.002234706229243614,
      "grad_norm": 2.523805618286133,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2526,
      "step": 36
    },
    {
      "epoch": 0.002234706229243614,
      "eval_loss": 0.21156874299049377,
      "eval_runtime": 2237.0996,
      "eval_samples_per_second": 6.064,
      "eval_steps_per_second": 0.758,
      "step": 36
    },
    {
      "epoch": 0.002296781402278159,
      "grad_norm": 3.9887495040893555,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2342,
      "step": 37
    },
    {
      "epoch": 0.0023588565753127036,
      "grad_norm": 1.690777063369751,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1865,
      "step": 38
    },
    {
      "epoch": 0.0024209317483472486,
      "grad_norm": 1.2107099294662476,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2207,
      "step": 39
    },
    {
      "epoch": 0.002483006921381793,
      "grad_norm": 1.3409606218338013,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1569,
      "step": 40
    },
    {
      "epoch": 0.002545082094416338,
      "grad_norm": 1.289309024810791,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.244,
      "step": 41
    },
    {
      "epoch": 0.002607157267450883,
      "grad_norm": 2.0155889987945557,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1858,
      "step": 42
    },
    {
      "epoch": 0.0026692324404854278,
      "grad_norm": 0.8973231911659241,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2317,
      "step": 43
    },
    {
      "epoch": 0.0027313076135199728,
      "grad_norm": 1.0135549306869507,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2102,
      "step": 44
    },
    {
      "epoch": 0.0027933827865545173,
      "grad_norm": 0.92349773645401,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1488,
      "step": 45
    },
    {
      "epoch": 0.0027933827865545173,
      "eval_loss": 0.19819892942905426,
      "eval_runtime": 2233.7344,
      "eval_samples_per_second": 6.073,
      "eval_steps_per_second": 0.759,
      "step": 45
    },
    {
      "epoch": 0.0028554579595890623,
      "grad_norm": 0.9457359313964844,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1637,
      "step": 46
    },
    {
      "epoch": 0.0029175331326236073,
      "grad_norm": 0.9686256647109985,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1819,
      "step": 47
    },
    {
      "epoch": 0.002979608305658152,
      "grad_norm": 1.1132407188415527,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2255,
      "step": 48
    },
    {
      "epoch": 0.003041683478692697,
      "grad_norm": 1.1518503427505493,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1877,
      "step": 49
    },
    {
      "epoch": 0.0031037586517272415,
      "grad_norm": 1.2734315395355225,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2391,
      "step": 50
    },
    {
      "epoch": 0.0031658338247617865,
      "grad_norm": 1.2569520473480225,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1754,
      "step": 51
    },
    {
      "epoch": 0.0032279089977963315,
      "grad_norm": 1.7715020179748535,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.29,
      "step": 52
    },
    {
      "epoch": 0.003289984170830876,
      "grad_norm": 1.2020207643508911,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1658,
      "step": 53
    },
    {
      "epoch": 0.003352059343865421,
      "grad_norm": 2.004467010498047,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2749,
      "step": 54
    },
    {
      "epoch": 0.003352059343865421,
      "eval_loss": 0.21678975224494934,
      "eval_runtime": 2232.1043,
      "eval_samples_per_second": 6.078,
      "eval_steps_per_second": 0.76,
      "step": 54
    },
    {
      "epoch": 0.003414134516899966,
      "grad_norm": 2.041341781616211,
      "learning_rate": 5e-05,
      "loss": 0.2153,
      "step": 55
    },
    {
      "epoch": 0.0034762096899345106,
      "grad_norm": 1.0738224983215332,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1612,
      "step": 56
    },
    {
      "epoch": 0.0035382848629690556,
      "grad_norm": 1.7214465141296387,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1676,
      "step": 57
    },
    {
      "epoch": 0.0036003600360036,
      "grad_norm": 1.4918973445892334,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1992,
      "step": 58
    },
    {
      "epoch": 0.003662435209038145,
      "grad_norm": 0.84410160779953,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0932,
      "step": 59
    },
    {
      "epoch": 0.00372451038207269,
      "grad_norm": 0.7239692211151123,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1256,
      "step": 60
    },
    {
      "epoch": 0.0037865855551072348,
      "grad_norm": 1.6752794981002808,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1966,
      "step": 61
    },
    {
      "epoch": 0.00384866072814178,
      "grad_norm": 1.7520849704742432,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2017,
      "step": 62
    },
    {
      "epoch": 0.003910735901176325,
      "grad_norm": 0.9484265446662903,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1794,
      "step": 63
    },
    {
      "epoch": 0.003910735901176325,
      "eval_loss": 0.18492011725902557,
      "eval_runtime": 2231.8143,
      "eval_samples_per_second": 6.078,
      "eval_steps_per_second": 0.76,
      "step": 63
    },
    {
      "epoch": 0.00397281107421087,
      "grad_norm": 1.4519840478897095,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1941,
      "step": 64
    },
    {
      "epoch": 0.004034886247245414,
      "grad_norm": 1.5735831260681152,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2795,
      "step": 65
    },
    {
      "epoch": 0.004096961420279959,
      "grad_norm": 1.0735223293304443,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1403,
      "step": 66
    },
    {
      "epoch": 0.004159036593314504,
      "grad_norm": 1.3041222095489502,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2024,
      "step": 67
    },
    {
      "epoch": 0.004221111766349049,
      "grad_norm": 1.0717079639434814,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1959,
      "step": 68
    },
    {
      "epoch": 0.004283186939383594,
      "grad_norm": 1.3034825325012207,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1763,
      "step": 69
    },
    {
      "epoch": 0.004345262112418138,
      "grad_norm": 0.5857073664665222,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0986,
      "step": 70
    },
    {
      "epoch": 0.004407337285452683,
      "grad_norm": 1.0117828845977783,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1772,
      "step": 71
    },
    {
      "epoch": 0.004469412458487228,
      "grad_norm": 1.0879490375518799,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1431,
      "step": 72
    },
    {
      "epoch": 0.004469412458487228,
      "eval_loss": 0.17801569402217865,
      "eval_runtime": 2232.7696,
      "eval_samples_per_second": 6.076,
      "eval_steps_per_second": 0.76,
      "step": 72
    },
    {
      "epoch": 0.004531487631521773,
      "grad_norm": 1.0074281692504883,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1842,
      "step": 73
    },
    {
      "epoch": 0.004593562804556318,
      "grad_norm": 1.2354624271392822,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.19,
      "step": 74
    },
    {
      "epoch": 0.004655637977590862,
      "grad_norm": 0.9586347341537476,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1884,
      "step": 75
    },
    {
      "epoch": 0.004717713150625407,
      "grad_norm": 0.5349669456481934,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1454,
      "step": 76
    },
    {
      "epoch": 0.004779788323659952,
      "grad_norm": 0.8816052079200745,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1014,
      "step": 77
    },
    {
      "epoch": 0.004841863496694497,
      "grad_norm": 1.5665334463119507,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1759,
      "step": 78
    },
    {
      "epoch": 0.004903938669729042,
      "grad_norm": 1.1516512632369995,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2133,
      "step": 79
    },
    {
      "epoch": 0.004966013842763586,
      "grad_norm": 0.9246344566345215,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1827,
      "step": 80
    },
    {
      "epoch": 0.005028089015798131,
      "grad_norm": 0.7256326675415039,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0897,
      "step": 81
    },
    {
      "epoch": 0.005028089015798131,
      "eval_loss": 0.17462599277496338,
      "eval_runtime": 2236.3863,
      "eval_samples_per_second": 6.066,
      "eval_steps_per_second": 0.758,
      "step": 81
    },
    {
      "epoch": 0.005090164188832676,
      "grad_norm": 1.1471014022827148,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1784,
      "step": 82
    },
    {
      "epoch": 0.005152239361867221,
      "grad_norm": 0.6445525288581848,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1625,
      "step": 83
    },
    {
      "epoch": 0.005214314534901766,
      "grad_norm": 0.9093417525291443,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1404,
      "step": 84
    },
    {
      "epoch": 0.0052763897079363105,
      "grad_norm": 0.9778578281402588,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1453,
      "step": 85
    },
    {
      "epoch": 0.0053384648809708555,
      "grad_norm": 1.2823891639709473,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2318,
      "step": 86
    },
    {
      "epoch": 0.0054005400540054005,
      "grad_norm": 0.6436693668365479,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1107,
      "step": 87
    },
    {
      "epoch": 0.0054626152270399455,
      "grad_norm": 1.4560965299606323,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2796,
      "step": 88
    },
    {
      "epoch": 0.0055246904000744905,
      "grad_norm": 0.8489173054695129,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1177,
      "step": 89
    },
    {
      "epoch": 0.005586765573109035,
      "grad_norm": 0.9858618974685669,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1779,
      "step": 90
    },
    {
      "epoch": 0.005586765573109035,
      "eval_loss": 0.17215199768543243,
      "eval_runtime": 2237.2776,
      "eval_samples_per_second": 6.064,
      "eval_steps_per_second": 0.758,
      "step": 90
    },
    {
      "epoch": 0.00564884074614358,
      "grad_norm": 1.120463490486145,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2531,
      "step": 91
    },
    {
      "epoch": 0.005710915919178125,
      "grad_norm": 1.1673436164855957,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1362,
      "step": 92
    },
    {
      "epoch": 0.00577299109221267,
      "grad_norm": 1.2356417179107666,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2066,
      "step": 93
    },
    {
      "epoch": 0.005835066265247215,
      "grad_norm": 0.9142425656318665,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1632,
      "step": 94
    },
    {
      "epoch": 0.005897141438281759,
      "grad_norm": 0.9412080645561218,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1884,
      "step": 95
    },
    {
      "epoch": 0.005959216611316304,
      "grad_norm": 1.1272531747817993,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1681,
      "step": 96
    },
    {
      "epoch": 0.006021291784350849,
      "grad_norm": 1.020373821258545,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2634,
      "step": 97
    },
    {
      "epoch": 0.006083366957385394,
      "grad_norm": 0.8609936833381653,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1496,
      "step": 98
    },
    {
      "epoch": 0.006145442130419939,
      "grad_norm": 0.7480646967887878,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2058,
      "step": 99
    },
    {
      "epoch": 0.006145442130419939,
      "eval_loss": 0.17152301967144012,
      "eval_runtime": 2237.397,
      "eval_samples_per_second": 6.063,
      "eval_steps_per_second": 0.758,
      "step": 99
    },
    {
      "epoch": 0.006207517303454483,
      "grad_norm": 0.8420364260673523,
      "learning_rate": 0.0,
      "loss": 0.173,
      "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": 1.1091214889228698e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}