{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5952380952380952,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005952380952380952,
      "grad_norm": 1.8847510814666748,
      "learning_rate": 1e-05,
      "loss": 3.4453,
      "step": 1
    },
    {
      "epoch": 0.005952380952380952,
      "eval_loss": 3.4847054481506348,
      "eval_runtime": 0.7278,
      "eval_samples_per_second": 776.315,
      "eval_steps_per_second": 24.732,
      "step": 1
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 1.8967914581298828,
      "learning_rate": 2e-05,
      "loss": 3.5233,
      "step": 2
    },
    {
      "epoch": 0.017857142857142856,
      "grad_norm": 1.9609869718551636,
      "learning_rate": 3e-05,
      "loss": 3.4954,
      "step": 3
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 1.975792646408081,
      "learning_rate": 4e-05,
      "loss": 3.4817,
      "step": 4
    },
    {
      "epoch": 0.02976190476190476,
      "grad_norm": 1.9651564359664917,
      "learning_rate": 5e-05,
      "loss": 3.476,
      "step": 5
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 2.0456418991088867,
      "learning_rate": 6e-05,
      "loss": 3.4424,
      "step": 6
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 1.925234317779541,
      "learning_rate": 7e-05,
      "loss": 3.3821,
      "step": 7
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 1.7819530963897705,
      "learning_rate": 8e-05,
      "loss": 3.2534,
      "step": 8
    },
    {
      "epoch": 0.05357142857142857,
      "grad_norm": 1.7863258123397827,
      "learning_rate": 9e-05,
      "loss": 3.1961,
      "step": 9
    },
    {
      "epoch": 0.05357142857142857,
      "eval_loss": 3.0999181270599365,
      "eval_runtime": 0.729,
      "eval_samples_per_second": 775.008,
      "eval_steps_per_second": 24.691,
      "step": 9
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 1.722019076347351,
      "learning_rate": 0.0001,
      "loss": 3.1102,
      "step": 10
    },
    {
      "epoch": 0.06547619047619048,
      "grad_norm": 1.6802176237106323,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.0669,
      "step": 11
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.68272864818573,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.7909,
      "step": 12
    },
    {
      "epoch": 0.07738095238095238,
      "grad_norm": 1.5962737798690796,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6373,
      "step": 13
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.5708441734313965,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.5206,
      "step": 14
    },
    {
      "epoch": 0.08928571428571429,
      "grad_norm": 1.5052292346954346,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4557,
      "step": 15
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.5192614793777466,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3104,
      "step": 16
    },
    {
      "epoch": 0.10119047619047619,
      "grad_norm": 1.5247867107391357,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.275,
      "step": 17
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 1.5035266876220703,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1103,
      "step": 18
    },
    {
      "epoch": 0.10714285714285714,
      "eval_loss": 2.022083282470703,
      "eval_runtime": 0.7263,
      "eval_samples_per_second": 777.939,
      "eval_steps_per_second": 24.784,
      "step": 18
    },
    {
      "epoch": 0.1130952380952381,
      "grad_norm": 1.5212229490280151,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9887,
      "step": 19
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 1.5906459093093872,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.9476,
      "step": 20
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.7577109336853027,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.7878,
      "step": 21
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 1.9069538116455078,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7624,
      "step": 22
    },
    {
      "epoch": 0.13690476190476192,
      "grad_norm": 2.0785834789276123,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6126,
      "step": 23
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.226637363433838,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4719,
      "step": 24
    },
    {
      "epoch": 0.1488095238095238,
      "grad_norm": 3.0561819076538086,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4277,
      "step": 25
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 2.925053834915161,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3428,
      "step": 26
    },
    {
      "epoch": 0.16071428571428573,
      "grad_norm": 2.3791446685791016,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3196,
      "step": 27
    },
    {
      "epoch": 0.16071428571428573,
      "eval_loss": 1.1837644577026367,
      "eval_runtime": 0.749,
      "eval_samples_per_second": 754.302,
      "eval_steps_per_second": 24.031,
      "step": 27
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.918161392211914,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.078,
      "step": 28
    },
    {
      "epoch": 0.17261904761904762,
      "grad_norm": 1.787397027015686,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.0918,
      "step": 29
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.718632459640503,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.0613,
      "step": 30
    },
    {
      "epoch": 0.18452380952380953,
      "grad_norm": 1.6407841444015503,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.9426,
      "step": 31
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.6310867071151733,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9499,
      "step": 32
    },
    {
      "epoch": 0.19642857142857142,
      "grad_norm": 1.6535135507583618,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8009,
      "step": 33
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 1.7860593795776367,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.698,
      "step": 34
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 1.6134707927703857,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6973,
      "step": 35
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.5818922519683838,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6982,
      "step": 36
    },
    {
      "epoch": 0.21428571428571427,
      "eval_loss": 0.591748058795929,
      "eval_runtime": 0.7267,
      "eval_samples_per_second": 777.438,
      "eval_steps_per_second": 24.768,
      "step": 36
    },
    {
      "epoch": 0.22023809523809523,
      "grad_norm": 1.3319734334945679,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6164,
      "step": 37
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 1.2683157920837402,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.5391,
      "step": 38
    },
    {
      "epoch": 0.23214285714285715,
      "grad_norm": 1.0097771883010864,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.49,
      "step": 39
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.0080583095550537,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4928,
      "step": 40
    },
    {
      "epoch": 0.24404761904761904,
      "grad_norm": 0.8241538405418396,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.4672,
      "step": 41
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.8907387852668762,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.4678,
      "step": 42
    },
    {
      "epoch": 0.25595238095238093,
      "grad_norm": 0.8545511364936829,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3988,
      "step": 43
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.8012543320655823,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.4446,
      "step": 44
    },
    {
      "epoch": 0.26785714285714285,
      "grad_norm": 0.6742522716522217,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3976,
      "step": 45
    },
    {
      "epoch": 0.26785714285714285,
      "eval_loss": 0.393344908952713,
      "eval_runtime": 0.731,
      "eval_samples_per_second": 772.887,
      "eval_steps_per_second": 24.623,
      "step": 45
    },
    {
      "epoch": 0.27380952380952384,
      "grad_norm": 0.6675676107406616,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3466,
      "step": 46
    },
    {
      "epoch": 0.27976190476190477,
      "grad_norm": 0.7589141726493835,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3242,
      "step": 47
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.872429370880127,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3272,
      "step": 48
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 0.5737527012825012,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.3232,
      "step": 49
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.8787867426872253,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3176,
      "step": 50
    },
    {
      "epoch": 0.30357142857142855,
      "grad_norm": 0.8264537453651428,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2985,
      "step": 51
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.6697880029678345,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.335,
      "step": 52
    },
    {
      "epoch": 0.31547619047619047,
      "grad_norm": 0.6313273310661316,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3323,
      "step": 53
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.7156944274902344,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2925,
      "step": 54
    },
    {
      "epoch": 0.32142857142857145,
      "eval_loss": 0.30814456939697266,
      "eval_runtime": 0.7272,
      "eval_samples_per_second": 776.911,
      "eval_steps_per_second": 24.751,
      "step": 54
    },
    {
      "epoch": 0.3273809523809524,
      "grad_norm": 0.8110126852989197,
      "learning_rate": 5e-05,
      "loss": 0.2934,
      "step": 55
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5642712712287903,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3237,
      "step": 56
    },
    {
      "epoch": 0.3392857142857143,
      "grad_norm": 0.5082366466522217,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2284,
      "step": 57
    },
    {
      "epoch": 0.34523809523809523,
      "grad_norm": 0.5590605735778809,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2723,
      "step": 58
    },
    {
      "epoch": 0.35119047619047616,
      "grad_norm": 0.7834331393241882,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2732,
      "step": 59
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.5841456651687622,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2316,
      "step": 60
    },
    {
      "epoch": 0.3630952380952381,
      "grad_norm": 0.5144384503364563,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2676,
      "step": 61
    },
    {
      "epoch": 0.36904761904761907,
      "grad_norm": 0.5047840476036072,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2311,
      "step": 62
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5553379058837891,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2693,
      "step": 63
    },
    {
      "epoch": 0.375,
      "eval_loss": 0.2591702938079834,
      "eval_runtime": 0.7281,
      "eval_samples_per_second": 776.028,
      "eval_steps_per_second": 24.723,
      "step": 63
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.5578157901763916,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2313,
      "step": 64
    },
    {
      "epoch": 0.3869047619047619,
      "grad_norm": 0.5519534945487976,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1994,
      "step": 65
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.5156115889549255,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2438,
      "step": 66
    },
    {
      "epoch": 0.39880952380952384,
      "grad_norm": 0.5865421891212463,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2964,
      "step": 67
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.4177829921245575,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2274,
      "step": 68
    },
    {
      "epoch": 0.4107142857142857,
      "grad_norm": 0.442807674407959,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2507,
      "step": 69
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.4709461033344269,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2241,
      "step": 70
    },
    {
      "epoch": 0.4226190476190476,
      "grad_norm": 0.36320897936820984,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.203,
      "step": 71
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.4016166031360626,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2008,
      "step": 72
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 0.2299022376537323,
      "eval_runtime": 0.725,
      "eval_samples_per_second": 779.359,
      "eval_steps_per_second": 24.829,
      "step": 72
    },
    {
      "epoch": 0.43452380952380953,
      "grad_norm": 0.5135464668273926,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2505,
      "step": 73
    },
    {
      "epoch": 0.44047619047619047,
      "grad_norm": 0.4497532844543457,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2021,
      "step": 74
    },
    {
      "epoch": 0.44642857142857145,
      "grad_norm": 0.44834592938423157,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1972,
      "step": 75
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.4646625518798828,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2428,
      "step": 76
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 0.43261802196502686,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1961,
      "step": 77
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.4902274012565613,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1893,
      "step": 78
    },
    {
      "epoch": 0.47023809523809523,
      "grad_norm": 0.36820879578590393,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1857,
      "step": 79
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.40407320857048035,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1762,
      "step": 80
    },
    {
      "epoch": 0.48214285714285715,
      "grad_norm": 0.42008960247039795,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2245,
      "step": 81
    },
    {
      "epoch": 0.48214285714285715,
      "eval_loss": 0.2156299650669098,
      "eval_runtime": 0.731,
      "eval_samples_per_second": 772.964,
      "eval_steps_per_second": 24.625,
      "step": 81
    },
    {
      "epoch": 0.4880952380952381,
      "grad_norm": 0.5599027872085571,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2199,
      "step": 82
    },
    {
      "epoch": 0.49404761904761907,
      "grad_norm": 0.49288442730903625,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2179,
      "step": 83
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.385234534740448,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1945,
      "step": 84
    },
    {
      "epoch": 0.5059523809523809,
      "grad_norm": 0.5592166185379028,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2251,
      "step": 85
    },
    {
      "epoch": 0.5119047619047619,
      "grad_norm": 0.39405468106269836,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2158,
      "step": 86
    },
    {
      "epoch": 0.5178571428571429,
      "grad_norm": 0.5080683827400208,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2302,
      "step": 87
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.45728829503059387,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1862,
      "step": 88
    },
    {
      "epoch": 0.5297619047619048,
      "grad_norm": 0.3771636188030243,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2153,
      "step": 89
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.43016037344932556,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.266,
      "step": 90
    },
    {
      "epoch": 0.5357142857142857,
      "eval_loss": 0.21077343821525574,
      "eval_runtime": 0.7276,
      "eval_samples_per_second": 776.507,
      "eval_steps_per_second": 24.738,
      "step": 90
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 0.5915383100509644,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2349,
      "step": 91
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.37992358207702637,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1927,
      "step": 92
    },
    {
      "epoch": 0.5535714285714286,
      "grad_norm": 0.4356793463230133,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2227,
      "step": 93
    },
    {
      "epoch": 0.5595238095238095,
      "grad_norm": 0.5157723426818848,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2807,
      "step": 94
    },
    {
      "epoch": 0.5654761904761905,
      "grad_norm": 0.4171281158924103,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1941,
      "step": 95
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.44283267855644226,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2501,
      "step": 96
    },
    {
      "epoch": 0.5773809523809523,
      "grad_norm": 0.3836650252342224,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1853,
      "step": 97
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.40736451745033264,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1831,
      "step": 98
    },
    {
      "epoch": 0.5892857142857143,
      "grad_norm": 0.40472492575645447,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1468,
      "step": 99
    },
    {
      "epoch": 0.5892857142857143,
      "eval_loss": 0.20941224694252014,
      "eval_runtime": 0.7248,
      "eval_samples_per_second": 779.517,
      "eval_steps_per_second": 24.834,
      "step": 99
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.3667122721672058,
      "learning_rate": 0.0,
      "loss": 0.1555,
      "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": 5553503443353600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}