{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11363636363636363,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011363636363636363,
      "grad_norm": 0.5031628012657166,
      "learning_rate": 1e-05,
      "loss": 1.6175,
      "step": 1
    },
    {
      "epoch": 0.0011363636363636363,
      "eval_loss": 1.7302374839782715,
      "eval_runtime": 88.1623,
      "eval_samples_per_second": 8.405,
      "eval_steps_per_second": 1.055,
      "step": 1
    },
    {
      "epoch": 0.0022727272727272726,
      "grad_norm": 0.4654340147972107,
      "learning_rate": 2e-05,
      "loss": 2.1047,
      "step": 2
    },
    {
      "epoch": 0.003409090909090909,
      "grad_norm": 0.5036187171936035,
      "learning_rate": 3e-05,
      "loss": 1.7235,
      "step": 3
    },
    {
      "epoch": 0.004545454545454545,
      "grad_norm": 0.41818612813949585,
      "learning_rate": 4e-05,
      "loss": 1.3914,
      "step": 4
    },
    {
      "epoch": 0.005681818181818182,
      "grad_norm": 0.4234386086463928,
      "learning_rate": 5e-05,
      "loss": 2.0059,
      "step": 5
    },
    {
      "epoch": 0.006818181818181818,
      "grad_norm": 0.45015767216682434,
      "learning_rate": 6e-05,
      "loss": 1.6938,
      "step": 6
    },
    {
      "epoch": 0.007954545454545454,
      "grad_norm": 0.4883180856704712,
      "learning_rate": 7e-05,
      "loss": 1.866,
      "step": 7
    },
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 0.8753936886787415,
      "learning_rate": 8e-05,
      "loss": 1.735,
      "step": 8
    },
    {
      "epoch": 0.010227272727272727,
      "grad_norm": 0.43279698491096497,
      "learning_rate": 9e-05,
      "loss": 1.1927,
      "step": 9
    },
    {
      "epoch": 0.010227272727272727,
      "eval_loss": 1.6918625831604004,
      "eval_runtime": 87.4761,
      "eval_samples_per_second": 8.471,
      "eval_steps_per_second": 1.063,
      "step": 9
    },
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 0.5074693560600281,
      "learning_rate": 0.0001,
      "loss": 1.6828,
      "step": 10
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.5221801996231079,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9807,
      "step": 11
    },
    {
      "epoch": 0.013636363636363636,
      "grad_norm": 1.1368098258972168,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5947,
      "step": 12
    },
    {
      "epoch": 0.014772727272727272,
      "grad_norm": 0.7387529611587524,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7278,
      "step": 13
    },
    {
      "epoch": 0.015909090909090907,
      "grad_norm": 0.5394375920295715,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3158,
      "step": 14
    },
    {
      "epoch": 0.017045454545454544,
      "grad_norm": 0.4821315109729767,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.822,
      "step": 15
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.38951918482780457,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.5332,
      "step": 16
    },
    {
      "epoch": 0.019318181818181818,
      "grad_norm": 0.7511935234069824,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.5436,
      "step": 17
    },
    {
      "epoch": 0.020454545454545454,
      "grad_norm": 0.6894105672836304,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9722,
      "step": 18
    },
    {
      "epoch": 0.020454545454545454,
      "eval_loss": 1.539093017578125,
      "eval_runtime": 87.4243,
      "eval_samples_per_second": 8.476,
      "eval_steps_per_second": 1.064,
      "step": 18
    },
    {
      "epoch": 0.02159090909090909,
      "grad_norm": 0.5717121362686157,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3682,
      "step": 19
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.49914515018463135,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5274,
      "step": 20
    },
    {
      "epoch": 0.023863636363636365,
      "grad_norm": 0.5184929370880127,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.4419,
      "step": 21
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.8946555852890015,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7122,
      "step": 22
    },
    {
      "epoch": 0.026136363636363635,
      "grad_norm": 0.6487534046173096,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.5038,
      "step": 23
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 0.6374855637550354,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5951,
      "step": 24
    },
    {
      "epoch": 0.028409090909090908,
      "grad_norm": 0.7161133289337158,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6346,
      "step": 25
    },
    {
      "epoch": 0.029545454545454545,
      "grad_norm": 0.48917874693870544,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.154,
      "step": 26
    },
    {
      "epoch": 0.03068181818181818,
      "grad_norm": 0.6666057705879211,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.778,
      "step": 27
    },
    {
      "epoch": 0.03068181818181818,
      "eval_loss": 1.4715248346328735,
      "eval_runtime": 87.4639,
      "eval_samples_per_second": 8.472,
      "eval_steps_per_second": 1.063,
      "step": 27
    },
    {
      "epoch": 0.031818181818181815,
      "grad_norm": 0.5019454956054688,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7373,
      "step": 28
    },
    {
      "epoch": 0.03295454545454545,
      "grad_norm": 0.514089047908783,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.9394,
      "step": 29
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 0.4315960705280304,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6312,
      "step": 30
    },
    {
      "epoch": 0.035227272727272725,
      "grad_norm": 0.6210121512413025,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6856,
      "step": 31
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.86749267578125,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6499,
      "step": 32
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.5921334624290466,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.5508,
      "step": 33
    },
    {
      "epoch": 0.038636363636363635,
      "grad_norm": 0.5376932621002197,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.0017,
      "step": 34
    },
    {
      "epoch": 0.03977272727272727,
      "grad_norm": 0.762406587600708,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.372,
      "step": 35
    },
    {
      "epoch": 0.04090909090909091,
      "grad_norm": 0.5415381193161011,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5537,
      "step": 36
    },
    {
      "epoch": 0.04090909090909091,
      "eval_loss": 1.4426989555358887,
      "eval_runtime": 87.3876,
      "eval_samples_per_second": 8.479,
      "eval_steps_per_second": 1.064,
      "step": 36
    },
    {
      "epoch": 0.042045454545454546,
      "grad_norm": 0.7806885242462158,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5561,
      "step": 37
    },
    {
      "epoch": 0.04318181818181818,
      "grad_norm": 0.7586813569068909,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.3102,
      "step": 38
    },
    {
      "epoch": 0.04431818181818182,
      "grad_norm": 0.6596840620040894,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2605,
      "step": 39
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.5476572513580322,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4152,
      "step": 40
    },
    {
      "epoch": 0.04659090909090909,
      "grad_norm": 0.6413193345069885,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.8048,
      "step": 41
    },
    {
      "epoch": 0.04772727272727273,
      "grad_norm": 0.4673216938972473,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.6345,
      "step": 42
    },
    {
      "epoch": 0.048863636363636366,
      "grad_norm": 0.5007254481315613,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.247,
      "step": 43
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5497366189956665,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7314,
      "step": 44
    },
    {
      "epoch": 0.05113636363636364,
      "grad_norm": 0.4534544348716736,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.3849,
      "step": 45
    },
    {
      "epoch": 0.05113636363636364,
      "eval_loss": 1.4240630865097046,
      "eval_runtime": 87.401,
      "eval_samples_per_second": 8.478,
      "eval_steps_per_second": 1.064,
      "step": 45
    },
    {
      "epoch": 0.05227272727272727,
      "grad_norm": 0.4592258036136627,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7077,
      "step": 46
    },
    {
      "epoch": 0.053409090909090906,
      "grad_norm": 0.6697846055030823,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6171,
      "step": 47
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.5928575396537781,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.7667,
      "step": 48
    },
    {
      "epoch": 0.05568181818181818,
      "grad_norm": 0.6087995767593384,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.4706,
      "step": 49
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 0.728308379650116,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.9524,
      "step": 50
    },
    {
      "epoch": 0.05795454545454545,
      "grad_norm": 0.45047634840011597,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.4548,
      "step": 51
    },
    {
      "epoch": 0.05909090909090909,
      "grad_norm": 1.1415973901748657,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2522,
      "step": 52
    },
    {
      "epoch": 0.060227272727272727,
      "grad_norm": 0.5474623441696167,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.5022,
      "step": 53
    },
    {
      "epoch": 0.06136363636363636,
      "grad_norm": 0.5780206322669983,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3892,
      "step": 54
    },
    {
      "epoch": 0.06136363636363636,
      "eval_loss": 1.4119524955749512,
      "eval_runtime": 87.4373,
      "eval_samples_per_second": 8.475,
      "eval_steps_per_second": 1.064,
      "step": 54
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.5161088109016418,
      "learning_rate": 5e-05,
      "loss": 1.3492,
      "step": 55
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 0.461467981338501,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.5803,
      "step": 56
    },
    {
      "epoch": 0.06477272727272727,
      "grad_norm": 0.7066351771354675,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4825,
      "step": 57
    },
    {
      "epoch": 0.0659090909090909,
      "grad_norm": 0.7307711839675903,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7179,
      "step": 58
    },
    {
      "epoch": 0.06704545454545455,
      "grad_norm": 0.383287250995636,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.4907,
      "step": 59
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.7558887004852295,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5637,
      "step": 60
    },
    {
      "epoch": 0.06931818181818182,
      "grad_norm": 0.34086090326309204,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5766,
      "step": 61
    },
    {
      "epoch": 0.07045454545454545,
      "grad_norm": 0.6929436922073364,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.5548,
      "step": 62
    },
    {
      "epoch": 0.0715909090909091,
      "grad_norm": 0.4506044089794159,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.7352,
      "step": 63
    },
    {
      "epoch": 0.0715909090909091,
      "eval_loss": 1.4060667753219604,
      "eval_runtime": 87.4035,
      "eval_samples_per_second": 8.478,
      "eval_steps_per_second": 1.064,
      "step": 63
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.47386038303375244,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4088,
      "step": 64
    },
    {
      "epoch": 0.07386363636363637,
      "grad_norm": 0.8597636818885803,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0096,
      "step": 65
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.5897632241249084,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.6263,
      "step": 66
    },
    {
      "epoch": 0.07613636363636364,
      "grad_norm": 0.800680935382843,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4472,
      "step": 67
    },
    {
      "epoch": 0.07727272727272727,
      "grad_norm": 0.8336355090141296,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.4691,
      "step": 68
    },
    {
      "epoch": 0.07840909090909091,
      "grad_norm": 0.8036491870880127,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.573,
      "step": 69
    },
    {
      "epoch": 0.07954545454545454,
      "grad_norm": 0.551456093788147,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8588,
      "step": 70
    },
    {
      "epoch": 0.08068181818181819,
      "grad_norm": 0.5478857755661011,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8197,
      "step": 71
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 1.3312339782714844,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.9631,
      "step": 72
    },
    {
      "epoch": 0.08181818181818182,
      "eval_loss": 1.4008089303970337,
      "eval_runtime": 87.397,
      "eval_samples_per_second": 8.479,
      "eval_steps_per_second": 1.064,
      "step": 72
    },
    {
      "epoch": 0.08295454545454546,
      "grad_norm": 0.47865477204322815,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.6158,
      "step": 73
    },
    {
      "epoch": 0.08409090909090909,
      "grad_norm": 0.5435898900032043,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6159,
      "step": 74
    },
    {
      "epoch": 0.08522727272727272,
      "grad_norm": 0.589959442615509,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.1458,
      "step": 75
    },
    {
      "epoch": 0.08636363636363636,
      "grad_norm": 0.6192647218704224,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.3072,
      "step": 76
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.555339515209198,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.7459,
      "step": 77
    },
    {
      "epoch": 0.08863636363636364,
      "grad_norm": 0.402619868516922,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3941,
      "step": 78
    },
    {
      "epoch": 0.08977272727272727,
      "grad_norm": 0.4111030697822571,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.1667,
      "step": 79
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.6310803294181824,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.5854,
      "step": 80
    },
    {
      "epoch": 0.09204545454545454,
      "grad_norm": 0.4028031527996063,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.4636,
      "step": 81
    },
    {
      "epoch": 0.09204545454545454,
      "eval_loss": 1.3986175060272217,
      "eval_runtime": 87.4361,
      "eval_samples_per_second": 8.475,
      "eval_steps_per_second": 1.064,
      "step": 81
    },
    {
      "epoch": 0.09318181818181819,
      "grad_norm": 0.5828585624694824,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.9201,
      "step": 82
    },
    {
      "epoch": 0.09431818181818181,
      "grad_norm": 0.5383720397949219,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.3849,
      "step": 83
    },
    {
      "epoch": 0.09545454545454546,
      "grad_norm": 0.5691014528274536,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9816,
      "step": 84
    },
    {
      "epoch": 0.09659090909090909,
      "grad_norm": 0.4643211364746094,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5215,
      "step": 85
    },
    {
      "epoch": 0.09772727272727273,
      "grad_norm": 0.5514132380485535,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0381,
      "step": 86
    },
    {
      "epoch": 0.09886363636363636,
      "grad_norm": 0.3321930766105652,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0676,
      "step": 87
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.7636975646018982,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.4628,
      "step": 88
    },
    {
      "epoch": 0.10113636363636364,
      "grad_norm": 0.6969127655029297,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4346,
      "step": 89
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 0.6535035371780396,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2264,
      "step": 90
    },
    {
      "epoch": 0.10227272727272728,
      "eval_loss": 1.3976737260818481,
      "eval_runtime": 87.4171,
      "eval_samples_per_second": 8.477,
      "eval_steps_per_second": 1.064,
      "step": 90
    },
    {
      "epoch": 0.10340909090909091,
      "grad_norm": 0.4957861006259918,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5694,
      "step": 91
    },
    {
      "epoch": 0.10454545454545454,
      "grad_norm": 0.5834468007087708,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.157,
      "step": 92
    },
    {
      "epoch": 0.10568181818181818,
      "grad_norm": 0.6812298893928528,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.6588,
      "step": 93
    },
    {
      "epoch": 0.10681818181818181,
      "grad_norm": 0.46779105067253113,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.7968,
      "step": 94
    },
    {
      "epoch": 0.10795454545454546,
      "grad_norm": 0.5582041144371033,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.7294,
      "step": 95
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.5326647758483887,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.5638,
      "step": 96
    },
    {
      "epoch": 0.11022727272727273,
      "grad_norm": 0.5757723450660706,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.5188,
      "step": 97
    },
    {
      "epoch": 0.11136363636363636,
      "grad_norm": 0.8716908693313599,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.819,
      "step": 98
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.588882327079773,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.8313,
      "step": 99
    },
    {
      "epoch": 0.1125,
      "eval_loss": 1.3972293138504028,
      "eval_runtime": 87.4494,
      "eval_samples_per_second": 8.473,
      "eval_steps_per_second": 1.063,
      "step": 99
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.522475004196167,
      "learning_rate": 0.0,
      "loss": 1.5229,
      "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": 7.470363520794624e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}