{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.73972602739726,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 0.34039291739463806,
      "learning_rate": 1e-05,
      "loss": 0.7873,
      "step": 1
    },
    {
      "epoch": 0.0273972602739726,
      "eval_loss": 0.7825180888175964,
      "eval_runtime": 3.7233,
      "eval_samples_per_second": 33.035,
      "eval_steps_per_second": 1.074,
      "step": 1
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.33236923813819885,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 2
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 0.3145294487476349,
      "learning_rate": 3e-05,
      "loss": 0.7692,
      "step": 3
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.3200077712535858,
      "learning_rate": 4e-05,
      "loss": 0.8006,
      "step": 4
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.35172683000564575,
      "learning_rate": 5e-05,
      "loss": 0.7617,
      "step": 5
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.3168494403362274,
      "learning_rate": 6e-05,
      "loss": 0.6911,
      "step": 6
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.3026105463504791,
      "learning_rate": 7e-05,
      "loss": 0.7288,
      "step": 7
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.23557651042938232,
      "learning_rate": 8e-05,
      "loss": 0.6837,
      "step": 8
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.2609310746192932,
      "learning_rate": 9e-05,
      "loss": 0.7528,
      "step": 9
    },
    {
      "epoch": 0.2465753424657534,
      "eval_loss": 0.7097108364105225,
      "eval_runtime": 3.7358,
      "eval_samples_per_second": 32.925,
      "eval_steps_per_second": 1.071,
      "step": 9
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.38081562519073486,
      "learning_rate": 0.0001,
      "loss": 0.6966,
      "step": 10
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.3591172993183136,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.7356,
      "step": 11
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.2671995460987091,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6586,
      "step": 12
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.23940521478652954,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.6827,
      "step": 13
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.1851789802312851,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.6027,
      "step": 14
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.1938449591398239,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6249,
      "step": 15
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.20314064621925354,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6649,
      "step": 16
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.20224684476852417,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6648,
      "step": 17
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.1758587509393692,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6387,
      "step": 18
    },
    {
      "epoch": 0.4931506849315068,
      "eval_loss": 0.641433835029602,
      "eval_runtime": 3.7417,
      "eval_samples_per_second": 32.873,
      "eval_steps_per_second": 1.069,
      "step": 18
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.17420168220996857,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5897,
      "step": 19
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.16646286845207214,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6144,
      "step": 20
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.17843681573867798,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.5987,
      "step": 21
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.17376701533794403,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6542,
      "step": 22
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.17084181308746338,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.6578,
      "step": 23
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.17303168773651123,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6007,
      "step": 24
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.17795169353485107,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6037,
      "step": 25
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.18882305920124054,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.6477,
      "step": 26
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": 0.17540940642356873,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5942,
      "step": 27
    },
    {
      "epoch": 0.7397260273972602,
      "eval_loss": 0.6050936579704285,
      "eval_runtime": 3.7452,
      "eval_samples_per_second": 32.842,
      "eval_steps_per_second": 1.068,
      "step": 27
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.15383704006671906,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5708,
      "step": 28
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": 0.1529732495546341,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.5649,
      "step": 29
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.17093701660633087,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5892,
      "step": 30
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": 0.16270044445991516,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6012,
      "step": 31
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.16807973384857178,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6265,
      "step": 32
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": 0.17066408693790436,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.6891,
      "step": 33
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.16887181997299194,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.5854,
      "step": 34
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.151829794049263,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.5384,
      "step": 35
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.1556522399187088,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5408,
      "step": 36
    },
    {
      "epoch": 0.9863013698630136,
      "eval_loss": 0.581146240234375,
      "eval_runtime": 3.7475,
      "eval_samples_per_second": 32.822,
      "eval_steps_per_second": 1.067,
      "step": 36
    },
    {
      "epoch": 1.0136986301369864,
      "grad_norm": 0.24949964880943298,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0727,
      "step": 37
    },
    {
      "epoch": 1.0410958904109588,
      "grad_norm": 0.15431559085845947,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.5255,
      "step": 38
    },
    {
      "epoch": 1.0684931506849316,
      "grad_norm": 0.16149845719337463,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.5169,
      "step": 39
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.17814257740974426,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5936,
      "step": 40
    },
    {
      "epoch": 1.1232876712328768,
      "grad_norm": 0.17237083613872528,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5709,
      "step": 41
    },
    {
      "epoch": 1.1506849315068493,
      "grad_norm": 0.16471445560455322,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5481,
      "step": 42
    },
    {
      "epoch": 1.178082191780822,
      "grad_norm": 0.16372527182102203,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6038,
      "step": 43
    },
    {
      "epoch": 1.2054794520547945,
      "grad_norm": 0.16758929193019867,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5288,
      "step": 44
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.18296092748641968,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5391,
      "step": 45
    },
    {
      "epoch": 1.2328767123287672,
      "eval_loss": 0.563045859336853,
      "eval_runtime": 3.7488,
      "eval_samples_per_second": 32.81,
      "eval_steps_per_second": 1.067,
      "step": 45
    },
    {
      "epoch": 1.2602739726027397,
      "grad_norm": 0.17584213614463806,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4915,
      "step": 46
    },
    {
      "epoch": 1.2876712328767124,
      "grad_norm": 0.1747244894504547,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.5201,
      "step": 47
    },
    {
      "epoch": 1.3150684931506849,
      "grad_norm": 0.1775994747877121,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5486,
      "step": 48
    },
    {
      "epoch": 1.3424657534246576,
      "grad_norm": 0.18910668790340424,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.5333,
      "step": 49
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.18840499222278595,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.5564,
      "step": 50
    },
    {
      "epoch": 1.3972602739726028,
      "grad_norm": 0.19617432355880737,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6264,
      "step": 51
    },
    {
      "epoch": 1.4246575342465753,
      "grad_norm": 0.16905656456947327,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4914,
      "step": 52
    },
    {
      "epoch": 1.452054794520548,
      "grad_norm": 0.19357207417488098,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.5915,
      "step": 53
    },
    {
      "epoch": 1.4794520547945205,
      "grad_norm": 0.1903381496667862,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5207,
      "step": 54
    },
    {
      "epoch": 1.4794520547945205,
      "eval_loss": 0.5485405921936035,
      "eval_runtime": 3.7239,
      "eval_samples_per_second": 33.03,
      "eval_steps_per_second": 1.074,
      "step": 54
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.17761348187923431,
      "learning_rate": 5e-05,
      "loss": 0.5346,
      "step": 55
    },
    {
      "epoch": 1.5342465753424657,
      "grad_norm": 0.18968743085861206,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.5365,
      "step": 56
    },
    {
      "epoch": 1.5616438356164384,
      "grad_norm": 0.1862426996231079,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.5685,
      "step": 57
    },
    {
      "epoch": 1.589041095890411,
      "grad_norm": 0.1861899346113205,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.5087,
      "step": 58
    },
    {
      "epoch": 1.6164383561643836,
      "grad_norm": 0.20097282528877258,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.5512,
      "step": 59
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.19234813749790192,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.5802,
      "step": 60
    },
    {
      "epoch": 1.6712328767123288,
      "grad_norm": 0.1840270459651947,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.5111,
      "step": 61
    },
    {
      "epoch": 1.6986301369863015,
      "grad_norm": 0.1915348917245865,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5219,
      "step": 62
    },
    {
      "epoch": 1.726027397260274,
      "grad_norm": 0.1915121227502823,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.5399,
      "step": 63
    },
    {
      "epoch": 1.726027397260274,
      "eval_loss": 0.5395578742027283,
      "eval_runtime": 3.7376,
      "eval_samples_per_second": 32.909,
      "eval_steps_per_second": 1.07,
      "step": 63
    },
    {
      "epoch": 1.7534246575342465,
      "grad_norm": 0.20380911231040955,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5214,
      "step": 64
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.20791220664978027,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.5881,
      "step": 65
    },
    {
      "epoch": 1.808219178082192,
      "grad_norm": 0.20161592960357666,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.5263,
      "step": 66
    },
    {
      "epoch": 1.8356164383561644,
      "grad_norm": 0.18923571705818176,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.5327,
      "step": 67
    },
    {
      "epoch": 1.8630136986301369,
      "grad_norm": 0.19650258123874664,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.5184,
      "step": 68
    },
    {
      "epoch": 1.8904109589041096,
      "grad_norm": 0.19661547243595123,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.5911,
      "step": 69
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.20530207455158234,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5041,
      "step": 70
    },
    {
      "epoch": 1.9452054794520548,
      "grad_norm": 0.21102431416511536,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5269,
      "step": 71
    },
    {
      "epoch": 1.9726027397260273,
      "grad_norm": 0.19871897995471954,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5147,
      "step": 72
    },
    {
      "epoch": 1.9726027397260273,
      "eval_loss": 0.5325475335121155,
      "eval_runtime": 3.8106,
      "eval_samples_per_second": 32.279,
      "eval_steps_per_second": 1.05,
      "step": 72
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3174644410610199,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7421,
      "step": 73
    },
    {
      "epoch": 2.0273972602739727,
      "grad_norm": 0.19568274915218353,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6202,
      "step": 74
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.20575644075870514,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4887,
      "step": 75
    },
    {
      "epoch": 2.0821917808219177,
      "grad_norm": 0.1924329251050949,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.5011,
      "step": 76
    },
    {
      "epoch": 2.1095890410958904,
      "grad_norm": 0.20766966044902802,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.5311,
      "step": 77
    },
    {
      "epoch": 2.136986301369863,
      "grad_norm": 0.194940447807312,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.438,
      "step": 78
    },
    {
      "epoch": 2.1643835616438354,
      "grad_norm": 0.19695548713207245,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.506,
      "step": 79
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.2021200954914093,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.4969,
      "step": 80
    },
    {
      "epoch": 2.219178082191781,
      "grad_norm": 0.20260506868362427,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4825,
      "step": 81
    },
    {
      "epoch": 2.219178082191781,
      "eval_loss": 0.5286130905151367,
      "eval_runtime": 3.7501,
      "eval_samples_per_second": 32.799,
      "eval_steps_per_second": 1.067,
      "step": 81
    },
    {
      "epoch": 2.2465753424657535,
      "grad_norm": 0.200306698679924,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5857,
      "step": 82
    },
    {
      "epoch": 2.2739726027397262,
      "grad_norm": 0.19307281076908112,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.4812,
      "step": 83
    },
    {
      "epoch": 2.3013698630136985,
      "grad_norm": 0.19841904938220978,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.505,
      "step": 84
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.21751321852207184,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5608,
      "step": 85
    },
    {
      "epoch": 2.356164383561644,
      "grad_norm": 0.21146072447299957,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.4821,
      "step": 86
    },
    {
      "epoch": 2.383561643835616,
      "grad_norm": 0.2212534099817276,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.5162,
      "step": 87
    },
    {
      "epoch": 2.410958904109589,
      "grad_norm": 0.21350644528865814,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.51,
      "step": 88
    },
    {
      "epoch": 2.4383561643835616,
      "grad_norm": 0.18542467057704926,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.4835,
      "step": 89
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.21330738067626953,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4642,
      "step": 90
    },
    {
      "epoch": 2.4657534246575343,
      "eval_loss": 0.526906430721283,
      "eval_runtime": 3.7465,
      "eval_samples_per_second": 32.831,
      "eval_steps_per_second": 1.068,
      "step": 90
    },
    {
      "epoch": 2.493150684931507,
      "grad_norm": 0.21417373418807983,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5203,
      "step": 91
    },
    {
      "epoch": 2.5205479452054793,
      "grad_norm": 0.2159249186515808,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.5275,
      "step": 92
    },
    {
      "epoch": 2.547945205479452,
      "grad_norm": 0.1969815343618393,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4667,
      "step": 93
    },
    {
      "epoch": 2.5753424657534247,
      "grad_norm": 0.2035369873046875,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.5494,
      "step": 94
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.19194987416267395,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.4834,
      "step": 95
    },
    {
      "epoch": 2.6301369863013697,
      "grad_norm": 0.20009766519069672,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4848,
      "step": 96
    },
    {
      "epoch": 2.6575342465753424,
      "grad_norm": 0.22390450537204742,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.5222,
      "step": 97
    },
    {
      "epoch": 2.684931506849315,
      "grad_norm": 0.19695667922496796,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.4638,
      "step": 98
    },
    {
      "epoch": 2.712328767123288,
      "grad_norm": 0.21116042137145996,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.5376,
      "step": 99
    },
    {
      "epoch": 2.712328767123288,
      "eval_loss": 0.5265399217605591,
      "eval_runtime": 3.7835,
      "eval_samples_per_second": 32.509,
      "eval_steps_per_second": 1.057,
      "step": 99
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.22835801541805267,
      "learning_rate": 0.0,
      "loss": 0.4968,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.935098268483584e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}