{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15071590052750566,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015071590052750565,
      "grad_norm": 0.7864943742752075,
      "learning_rate": 1e-05,
      "loss": 0.5102,
      "step": 1
    },
    {
      "epoch": 0.0015071590052750565,
      "eval_loss": 0.5028060078620911,
      "eval_runtime": 123.6309,
      "eval_samples_per_second": 4.522,
      "eval_steps_per_second": 0.566,
      "step": 1
    },
    {
      "epoch": 0.003014318010550113,
      "grad_norm": 0.6568166613578796,
      "learning_rate": 2e-05,
      "loss": 0.455,
      "step": 2
    },
    {
      "epoch": 0.00452147701582517,
      "grad_norm": 0.5635665059089661,
      "learning_rate": 3e-05,
      "loss": 0.4053,
      "step": 3
    },
    {
      "epoch": 0.006028636021100226,
      "grad_norm": 0.7057203650474548,
      "learning_rate": 4e-05,
      "loss": 0.5003,
      "step": 4
    },
    {
      "epoch": 0.007535795026375283,
      "grad_norm": 1.4039517641067505,
      "learning_rate": 5e-05,
      "loss": 0.4817,
      "step": 5
    },
    {
      "epoch": 0.00904295403165034,
      "grad_norm": 1.3611491918563843,
      "learning_rate": 6e-05,
      "loss": 0.5256,
      "step": 6
    },
    {
      "epoch": 0.010550113036925395,
      "grad_norm": 0.933882474899292,
      "learning_rate": 7e-05,
      "loss": 0.5931,
      "step": 7
    },
    {
      "epoch": 0.012057272042200452,
      "grad_norm": 1.0020099878311157,
      "learning_rate": 8e-05,
      "loss": 0.5128,
      "step": 8
    },
    {
      "epoch": 0.013564431047475508,
      "grad_norm": 0.7827029824256897,
      "learning_rate": 9e-05,
      "loss": 0.5025,
      "step": 9
    },
    {
      "epoch": 0.013564431047475508,
      "eval_loss": 0.37673527002334595,
      "eval_runtime": 123.5959,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 9
    },
    {
      "epoch": 0.015071590052750565,
      "grad_norm": 0.7502973079681396,
      "learning_rate": 0.0001,
      "loss": 0.3596,
      "step": 10
    },
    {
      "epoch": 0.016578749058025623,
      "grad_norm": 0.8659213781356812,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.3821,
      "step": 11
    },
    {
      "epoch": 0.01808590806330068,
      "grad_norm": 0.6731705069541931,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3327,
      "step": 12
    },
    {
      "epoch": 0.019593067068575734,
      "grad_norm": 0.8304461240768433,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.2444,
      "step": 13
    },
    {
      "epoch": 0.02110022607385079,
      "grad_norm": 1.0592200756072998,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.2108,
      "step": 14
    },
    {
      "epoch": 0.02260738507912585,
      "grad_norm": 0.5523332953453064,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1363,
      "step": 15
    },
    {
      "epoch": 0.024114544084400905,
      "grad_norm": 0.7820104360580444,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2449,
      "step": 16
    },
    {
      "epoch": 0.02562170308967596,
      "grad_norm": 0.7897171378135681,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2552,
      "step": 17
    },
    {
      "epoch": 0.027128862094951016,
      "grad_norm": 0.49348121881484985,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1448,
      "step": 18
    },
    {
      "epoch": 0.027128862094951016,
      "eval_loss": 0.21509040892124176,
      "eval_runtime": 123.6098,
      "eval_samples_per_second": 4.522,
      "eval_steps_per_second": 0.566,
      "step": 18
    },
    {
      "epoch": 0.028636021100226075,
      "grad_norm": 0.5062901377677917,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1737,
      "step": 19
    },
    {
      "epoch": 0.03014318010550113,
      "grad_norm": 0.39385759830474854,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1268,
      "step": 20
    },
    {
      "epoch": 0.031650339110776186,
      "grad_norm": 0.7342726588249207,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.2666,
      "step": 21
    },
    {
      "epoch": 0.033157498116051246,
      "grad_norm": 1.1756455898284912,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5072,
      "step": 22
    },
    {
      "epoch": 0.0346646571213263,
      "grad_norm": 0.6300706267356873,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2077,
      "step": 23
    },
    {
      "epoch": 0.03617181612660136,
      "grad_norm": 0.4381844699382782,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1014,
      "step": 24
    },
    {
      "epoch": 0.037678975131876416,
      "grad_norm": 0.6207946538925171,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1978,
      "step": 25
    },
    {
      "epoch": 0.03918613413715147,
      "grad_norm": 0.3882005214691162,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1296,
      "step": 26
    },
    {
      "epoch": 0.04069329314242653,
      "grad_norm": 0.4310823082923889,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1181,
      "step": 27
    },
    {
      "epoch": 0.04069329314242653,
      "eval_loss": 0.18763834238052368,
      "eval_runtime": 123.6029,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 27
    },
    {
      "epoch": 0.04220045214770158,
      "grad_norm": 0.5565463304519653,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2201,
      "step": 28
    },
    {
      "epoch": 0.04370761115297664,
      "grad_norm": 0.3672766387462616,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0876,
      "step": 29
    },
    {
      "epoch": 0.0452147701582517,
      "grad_norm": 0.3959539234638214,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0997,
      "step": 30
    },
    {
      "epoch": 0.04672192916352675,
      "grad_norm": 0.38439688086509705,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1038,
      "step": 31
    },
    {
      "epoch": 0.04822908816880181,
      "grad_norm": 0.6091885566711426,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1196,
      "step": 32
    },
    {
      "epoch": 0.04973624717407687,
      "grad_norm": 0.4755226671695709,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1388,
      "step": 33
    },
    {
      "epoch": 0.05124340617935192,
      "grad_norm": 0.504368007183075,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1114,
      "step": 34
    },
    {
      "epoch": 0.05275056518462698,
      "grad_norm": 0.35794878005981445,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0983,
      "step": 35
    },
    {
      "epoch": 0.05425772418990203,
      "grad_norm": 0.5445522665977478,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1758,
      "step": 36
    },
    {
      "epoch": 0.05425772418990203,
      "eval_loss": 0.17182248830795288,
      "eval_runtime": 123.5947,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 36
    },
    {
      "epoch": 0.05576488319517709,
      "grad_norm": 0.563473105430603,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0778,
      "step": 37
    },
    {
      "epoch": 0.05727204220045215,
      "grad_norm": 0.7104746699333191,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2217,
      "step": 38
    },
    {
      "epoch": 0.0587792012057272,
      "grad_norm": 0.3592125177383423,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0769,
      "step": 39
    },
    {
      "epoch": 0.06028636021100226,
      "grad_norm": 0.3523983061313629,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0896,
      "step": 40
    },
    {
      "epoch": 0.06179351921627732,
      "grad_norm": 0.31311479210853577,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0581,
      "step": 41
    },
    {
      "epoch": 0.06330067822155237,
      "grad_norm": 0.44165709614753723,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0845,
      "step": 42
    },
    {
      "epoch": 0.06480783722682742,
      "grad_norm": 1.0613696575164795,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.266,
      "step": 43
    },
    {
      "epoch": 0.06631499623210249,
      "grad_norm": 0.5340938568115234,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1391,
      "step": 44
    },
    {
      "epoch": 0.06782215523737754,
      "grad_norm": 0.46894630789756775,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0675,
      "step": 45
    },
    {
      "epoch": 0.06782215523737754,
      "eval_loss": 0.15676920115947723,
      "eval_runtime": 123.5469,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.567,
      "step": 45
    },
    {
      "epoch": 0.0693293142426526,
      "grad_norm": 0.3855697810649872,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0871,
      "step": 46
    },
    {
      "epoch": 0.07083647324792766,
      "grad_norm": 3.673552989959717,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.34,
      "step": 47
    },
    {
      "epoch": 0.07234363225320271,
      "grad_norm": 0.46040230989456177,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0978,
      "step": 48
    },
    {
      "epoch": 0.07385079125847777,
      "grad_norm": 0.4494129717350006,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1389,
      "step": 49
    },
    {
      "epoch": 0.07535795026375283,
      "grad_norm": 0.6942574977874756,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2822,
      "step": 50
    },
    {
      "epoch": 0.07686510926902788,
      "grad_norm": 0.7992674708366394,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2198,
      "step": 51
    },
    {
      "epoch": 0.07837226827430294,
      "grad_norm": 0.5225107669830322,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1998,
      "step": 52
    },
    {
      "epoch": 0.07987942727957799,
      "grad_norm": 0.5572648048400879,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1562,
      "step": 53
    },
    {
      "epoch": 0.08138658628485305,
      "grad_norm": 0.6357726454734802,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.1094,
      "step": 54
    },
    {
      "epoch": 0.08138658628485305,
      "eval_loss": 0.15196655690670013,
      "eval_runtime": 123.5572,
      "eval_samples_per_second": 4.524,
      "eval_steps_per_second": 0.567,
      "step": 54
    },
    {
      "epoch": 0.0828937452901281,
      "grad_norm": 0.5080541372299194,
      "learning_rate": 5e-05,
      "loss": 0.1882,
      "step": 55
    },
    {
      "epoch": 0.08440090429540316,
      "grad_norm": 0.5046006441116333,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1819,
      "step": 56
    },
    {
      "epoch": 0.08590806330067823,
      "grad_norm": 0.6285750865936279,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1142,
      "step": 57
    },
    {
      "epoch": 0.08741522230595328,
      "grad_norm": 0.6299275755882263,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1164,
      "step": 58
    },
    {
      "epoch": 0.08892238131122833,
      "grad_norm": 0.37507885694503784,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1564,
      "step": 59
    },
    {
      "epoch": 0.0904295403165034,
      "grad_norm": 0.546333372592926,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1532,
      "step": 60
    },
    {
      "epoch": 0.09193669932177845,
      "grad_norm": 0.5628113150596619,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1439,
      "step": 61
    },
    {
      "epoch": 0.0934438583270535,
      "grad_norm": 0.31105494499206543,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0802,
      "step": 62
    },
    {
      "epoch": 0.09495101733232857,
      "grad_norm": 0.2998591661453247,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0895,
      "step": 63
    },
    {
      "epoch": 0.09495101733232857,
      "eval_loss": 0.14642611145973206,
      "eval_runtime": 123.5866,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 63
    },
    {
      "epoch": 0.09645817633760362,
      "grad_norm": 0.34861132502555847,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0748,
      "step": 64
    },
    {
      "epoch": 0.09796533534287867,
      "grad_norm": 0.3098653256893158,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.085,
      "step": 65
    },
    {
      "epoch": 0.09947249434815374,
      "grad_norm": 2.6786906719207764,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3102,
      "step": 66
    },
    {
      "epoch": 0.10097965335342879,
      "grad_norm": 0.4055371582508087,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0964,
      "step": 67
    },
    {
      "epoch": 0.10248681235870384,
      "grad_norm": 0.38335639238357544,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0683,
      "step": 68
    },
    {
      "epoch": 0.1039939713639789,
      "grad_norm": 0.5514392852783203,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1355,
      "step": 69
    },
    {
      "epoch": 0.10550113036925396,
      "grad_norm": 0.4799521267414093,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1633,
      "step": 70
    },
    {
      "epoch": 0.10700828937452901,
      "grad_norm": 0.7698957324028015,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.354,
      "step": 71
    },
    {
      "epoch": 0.10851544837980406,
      "grad_norm": 0.33936837315559387,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0471,
      "step": 72
    },
    {
      "epoch": 0.10851544837980406,
      "eval_loss": 0.14258287847042084,
      "eval_runtime": 123.5915,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 72
    },
    {
      "epoch": 0.11002260738507913,
      "grad_norm": 0.3643311560153961,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1008,
      "step": 73
    },
    {
      "epoch": 0.11152976639035418,
      "grad_norm": 0.6503349542617798,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2444,
      "step": 74
    },
    {
      "epoch": 0.11303692539562923,
      "grad_norm": 0.3921027183532715,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1735,
      "step": 75
    },
    {
      "epoch": 0.1145440844009043,
      "grad_norm": 0.364891916513443,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.07,
      "step": 76
    },
    {
      "epoch": 0.11605124340617935,
      "grad_norm": 0.5485689640045166,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.23,
      "step": 77
    },
    {
      "epoch": 0.1175584024114544,
      "grad_norm": 0.6924117803573608,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0649,
      "step": 78
    },
    {
      "epoch": 0.11906556141672947,
      "grad_norm": 0.40422847867012024,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1353,
      "step": 79
    },
    {
      "epoch": 0.12057272042200452,
      "grad_norm": 0.3907949924468994,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0656,
      "step": 80
    },
    {
      "epoch": 0.12207987942727958,
      "grad_norm": 0.4222213327884674,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0848,
      "step": 81
    },
    {
      "epoch": 0.12207987942727958,
      "eval_loss": 0.14018893241882324,
      "eval_runtime": 123.5822,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 0.566,
      "step": 81
    },
    {
      "epoch": 0.12358703843255464,
      "grad_norm": 0.6123594045639038,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1254,
      "step": 82
    },
    {
      "epoch": 0.12509419743782968,
      "grad_norm": 0.3415692448616028,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0581,
      "step": 83
    },
    {
      "epoch": 0.12660135644310475,
      "grad_norm": 0.6530345678329468,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1209,
      "step": 84
    },
    {
      "epoch": 0.1281085154483798,
      "grad_norm": 1.1032772064208984,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2231,
      "step": 85
    },
    {
      "epoch": 0.12961567445365485,
      "grad_norm": 0.5108954310417175,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0894,
      "step": 86
    },
    {
      "epoch": 0.13112283345892992,
      "grad_norm": 2.216198444366455,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0951,
      "step": 87
    },
    {
      "epoch": 0.13262999246420498,
      "grad_norm": 0.738016664981842,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2348,
      "step": 88
    },
    {
      "epoch": 0.13413715146948002,
      "grad_norm": 0.3426017761230469,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1023,
      "step": 89
    },
    {
      "epoch": 0.1356443104747551,
      "grad_norm": 0.5057233572006226,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1386,
      "step": 90
    },
    {
      "epoch": 0.1356443104747551,
      "eval_loss": 0.140176922082901,
      "eval_runtime": 123.5635,
      "eval_samples_per_second": 4.524,
      "eval_steps_per_second": 0.567,
      "step": 90
    },
    {
      "epoch": 0.13715146948003015,
      "grad_norm": 0.47616341710090637,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1072,
      "step": 91
    },
    {
      "epoch": 0.1386586284853052,
      "grad_norm": 3.395482063293457,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2067,
      "step": 92
    },
    {
      "epoch": 0.14016578749058026,
      "grad_norm": 0.8365815281867981,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1928,
      "step": 93
    },
    {
      "epoch": 0.14167294649585532,
      "grad_norm": 0.963044285774231,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1393,
      "step": 94
    },
    {
      "epoch": 0.14318010550113036,
      "grad_norm": 0.3439726233482361,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0857,
      "step": 95
    },
    {
      "epoch": 0.14468726450640543,
      "grad_norm": 0.44376206398010254,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1651,
      "step": 96
    },
    {
      "epoch": 0.1461944235116805,
      "grad_norm": 0.4902697801589966,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0953,
      "step": 97
    },
    {
      "epoch": 0.14770158251695553,
      "grad_norm": 0.3958795666694641,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0834,
      "step": 98
    },
    {
      "epoch": 0.1492087415222306,
      "grad_norm": 2.75736141204834,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4029,
      "step": 99
    },
    {
      "epoch": 0.1492087415222306,
      "eval_loss": 0.13978636264801025,
      "eval_runtime": 123.6077,
      "eval_samples_per_second": 4.522,
      "eval_steps_per_second": 0.566,
      "step": 99
    },
    {
      "epoch": 0.15071590052750566,
      "grad_norm": 0.4361518323421478,
      "learning_rate": 0.0,
      "loss": 0.1838,
      "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": 1.4800651307030938e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}