{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3527336860670194,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003527336860670194,
      "grad_norm": 24.732351303100586,
      "learning_rate": 1e-05,
      "loss": 12.7829,
      "step": 1
    },
    {
      "epoch": 0.003527336860670194,
      "eval_loss": 6.23192834854126,
      "eval_runtime": 37.6613,
      "eval_samples_per_second": 6.346,
      "eval_steps_per_second": 0.797,
      "step": 1
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 25.1240234375,
      "learning_rate": 2e-05,
      "loss": 12.1045,
      "step": 2
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 25.76141357421875,
      "learning_rate": 3e-05,
      "loss": 12.4319,
      "step": 3
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 24.581771850585938,
      "learning_rate": 4e-05,
      "loss": 12.3229,
      "step": 4
    },
    {
      "epoch": 0.01763668430335097,
      "grad_norm": 25.8974552154541,
      "learning_rate": 5e-05,
      "loss": 11.0399,
      "step": 5
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 25.636842727661133,
      "learning_rate": 6e-05,
      "loss": 10.5125,
      "step": 6
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 22.79175567626953,
      "learning_rate": 7e-05,
      "loss": 8.734,
      "step": 7
    },
    {
      "epoch": 0.02821869488536155,
      "grad_norm": 21.83588218688965,
      "learning_rate": 8e-05,
      "loss": 6.1147,
      "step": 8
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 13.920812606811523,
      "learning_rate": 9e-05,
      "loss": 3.7133,
      "step": 9
    },
    {
      "epoch": 0.031746031746031744,
      "eval_loss": 0.9912834763526917,
      "eval_runtime": 37.6592,
      "eval_samples_per_second": 6.346,
      "eval_steps_per_second": 0.797,
      "step": 9
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": 10.068586349487305,
      "learning_rate": 0.0001,
      "loss": 2.0718,
      "step": 10
    },
    {
      "epoch": 0.03880070546737213,
      "grad_norm": 6.6233954429626465,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.2433,
      "step": 11
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 6.429514408111572,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8386,
      "step": 12
    },
    {
      "epoch": 0.04585537918871252,
      "grad_norm": 5.240244388580322,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.6355,
      "step": 13
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 6.982906341552734,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.7284,
      "step": 14
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 5.769637584686279,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.696,
      "step": 15
    },
    {
      "epoch": 0.0564373897707231,
      "grad_norm": 5.077568054199219,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3887,
      "step": 16
    },
    {
      "epoch": 0.059964726631393295,
      "grad_norm": 4.646890640258789,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6242,
      "step": 17
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 11.119400024414062,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9408,
      "step": 18
    },
    {
      "epoch": 0.06349206349206349,
      "eval_loss": 0.24564185738563538,
      "eval_runtime": 37.6951,
      "eval_samples_per_second": 6.34,
      "eval_steps_per_second": 0.796,
      "step": 18
    },
    {
      "epoch": 0.06701940035273368,
      "grad_norm": 3.4085452556610107,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2693,
      "step": 19
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": 3.222567081451416,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3019,
      "step": 20
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.951718807220459,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3,
      "step": 21
    },
    {
      "epoch": 0.07760141093474426,
      "grad_norm": 3.150925397872925,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1912,
      "step": 22
    },
    {
      "epoch": 0.08112874779541446,
      "grad_norm": 4.397229194641113,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.3351,
      "step": 23
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 7.507371425628662,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6114,
      "step": 24
    },
    {
      "epoch": 0.08818342151675485,
      "grad_norm": 3.729475736618042,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1746,
      "step": 25
    },
    {
      "epoch": 0.09171075837742504,
      "grad_norm": 6.209860801696777,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4217,
      "step": 26
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 3.53015398979187,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5429,
      "step": 27
    },
    {
      "epoch": 0.09523809523809523,
      "eval_loss": 0.20255467295646667,
      "eval_runtime": 37.758,
      "eval_samples_per_second": 6.33,
      "eval_steps_per_second": 0.795,
      "step": 27
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 5.110671520233154,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6216,
      "step": 28
    },
    {
      "epoch": 0.10229276895943562,
      "grad_norm": 3.3714725971221924,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.6694,
      "step": 29
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 3.7595903873443604,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.501,
      "step": 30
    },
    {
      "epoch": 0.10934744268077601,
      "grad_norm": 1.5534464120864868,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4787,
      "step": 31
    },
    {
      "epoch": 0.1128747795414462,
      "grad_norm": 2.566434383392334,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.4139,
      "step": 32
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 1.6924530267715454,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3849,
      "step": 33
    },
    {
      "epoch": 0.11992945326278659,
      "grad_norm": 2.9056317806243896,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4179,
      "step": 34
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 1.0968977212905884,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1236,
      "step": 35
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 2.9626941680908203,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1803,
      "step": 36
    },
    {
      "epoch": 0.12698412698412698,
      "eval_loss": 0.18621611595153809,
      "eval_runtime": 37.6672,
      "eval_samples_per_second": 6.345,
      "eval_steps_per_second": 0.796,
      "step": 36
    },
    {
      "epoch": 0.13051146384479717,
      "grad_norm": 2.800790548324585,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6245,
      "step": 37
    },
    {
      "epoch": 0.13403880070546736,
      "grad_norm": 5.40810489654541,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8681,
      "step": 38
    },
    {
      "epoch": 0.13756613756613756,
      "grad_norm": 3.697223663330078,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3298,
      "step": 39
    },
    {
      "epoch": 0.14109347442680775,
      "grad_norm": 2.458991765975952,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3142,
      "step": 40
    },
    {
      "epoch": 0.14462081128747795,
      "grad_norm": 2.7322099208831787,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.3204,
      "step": 41
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 6.406352519989014,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.4234,
      "step": 42
    },
    {
      "epoch": 0.15167548500881833,
      "grad_norm": 5.081075191497803,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3333,
      "step": 43
    },
    {
      "epoch": 0.15520282186948853,
      "grad_norm": 3.3342695236206055,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3729,
      "step": 44
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 3.7283213138580322,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2785,
      "step": 45
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 0.11118412762880325,
      "eval_runtime": 37.6674,
      "eval_samples_per_second": 6.345,
      "eval_steps_per_second": 0.796,
      "step": 45
    },
    {
      "epoch": 0.16225749559082892,
      "grad_norm": 8.65853500366211,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4655,
      "step": 46
    },
    {
      "epoch": 0.1657848324514991,
      "grad_norm": 9.64456558227539,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3942,
      "step": 47
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 4.117836952209473,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3577,
      "step": 48
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 4.200088977813721,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.3752,
      "step": 49
    },
    {
      "epoch": 0.1763668430335097,
      "grad_norm": 4.15980339050293,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2969,
      "step": 50
    },
    {
      "epoch": 0.17989417989417988,
      "grad_norm": 9.53512191772461,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6029,
      "step": 51
    },
    {
      "epoch": 0.18342151675485008,
      "grad_norm": 3.098203182220459,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1674,
      "step": 52
    },
    {
      "epoch": 0.18694885361552027,
      "grad_norm": 5.761476993560791,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3695,
      "step": 53
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.4099481105804443,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5525,
      "step": 54
    },
    {
      "epoch": 0.19047619047619047,
      "eval_loss": 0.10475945472717285,
      "eval_runtime": 37.7225,
      "eval_samples_per_second": 6.336,
      "eval_steps_per_second": 0.795,
      "step": 54
    },
    {
      "epoch": 0.19400352733686066,
      "grad_norm": 3.259533643722534,
      "learning_rate": 5e-05,
      "loss": 0.2256,
      "step": 55
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 3.9592463970184326,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.5181,
      "step": 56
    },
    {
      "epoch": 0.20105820105820105,
      "grad_norm": 3.4747936725616455,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.4554,
      "step": 57
    },
    {
      "epoch": 0.20458553791887124,
      "grad_norm": 1.4295612573623657,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1801,
      "step": 58
    },
    {
      "epoch": 0.20811287477954143,
      "grad_norm": 2.1647229194641113,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1908,
      "step": 59
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 3.4215903282165527,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3586,
      "step": 60
    },
    {
      "epoch": 0.21516754850088182,
      "grad_norm": 2.3255903720855713,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2312,
      "step": 61
    },
    {
      "epoch": 0.21869488536155202,
      "grad_norm": 3.3858463764190674,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.294,
      "step": 62
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 4.583118438720703,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.469,
      "step": 63
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 0.11342418938875198,
      "eval_runtime": 37.6648,
      "eval_samples_per_second": 6.345,
      "eval_steps_per_second": 0.797,
      "step": 63
    },
    {
      "epoch": 0.2257495590828924,
      "grad_norm": 2.167945384979248,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2766,
      "step": 64
    },
    {
      "epoch": 0.2292768959435626,
      "grad_norm": 4.23003625869751,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.4786,
      "step": 65
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 2.1028635501861572,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1599,
      "step": 66
    },
    {
      "epoch": 0.23633156966490299,
      "grad_norm": 2.2224302291870117,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2536,
      "step": 67
    },
    {
      "epoch": 0.23985890652557318,
      "grad_norm": 1.0066758394241333,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0962,
      "step": 68
    },
    {
      "epoch": 0.24338624338624337,
      "grad_norm": 2.389492988586426,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.3528,
      "step": 69
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.8155355453491211,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0832,
      "step": 70
    },
    {
      "epoch": 0.25044091710758376,
      "grad_norm": 2.6937882900238037,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1585,
      "step": 71
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 2.682079315185547,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2465,
      "step": 72
    },
    {
      "epoch": 0.25396825396825395,
      "eval_loss": 0.11077579855918884,
      "eval_runtime": 37.6536,
      "eval_samples_per_second": 6.347,
      "eval_steps_per_second": 0.797,
      "step": 72
    },
    {
      "epoch": 0.25749559082892415,
      "grad_norm": 2.9206907749176025,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.243,
      "step": 73
    },
    {
      "epoch": 0.26102292768959434,
      "grad_norm": 3.7066774368286133,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1554,
      "step": 74
    },
    {
      "epoch": 0.26455026455026454,
      "grad_norm": 2.460815191268921,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1775,
      "step": 75
    },
    {
      "epoch": 0.26807760141093473,
      "grad_norm": 2.312260389328003,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2314,
      "step": 76
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 5.711832523345947,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6443,
      "step": 77
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 1.8561723232269287,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0904,
      "step": 78
    },
    {
      "epoch": 0.2786596119929453,
      "grad_norm": 4.764100551605225,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.4073,
      "step": 79
    },
    {
      "epoch": 0.2821869488536155,
      "grad_norm": 7.698202610015869,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.8285,
      "step": 80
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.3542370796203613,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.3216,
      "step": 81
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 0.1273738294839859,
      "eval_runtime": 37.6563,
      "eval_samples_per_second": 6.347,
      "eval_steps_per_second": 0.797,
      "step": 81
    },
    {
      "epoch": 0.2892416225749559,
      "grad_norm": 1.7140568494796753,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2145,
      "step": 82
    },
    {
      "epoch": 0.2927689594356261,
      "grad_norm": 5.036262512207031,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2936,
      "step": 83
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 3.415752649307251,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2426,
      "step": 84
    },
    {
      "epoch": 0.2998236331569665,
      "grad_norm": 4.9717535972595215,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3977,
      "step": 85
    },
    {
      "epoch": 0.30335097001763667,
      "grad_norm": 4.338818073272705,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2631,
      "step": 86
    },
    {
      "epoch": 0.30687830687830686,
      "grad_norm": 2.277334690093994,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2695,
      "step": 87
    },
    {
      "epoch": 0.31040564373897706,
      "grad_norm": 3.494274139404297,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2478,
      "step": 88
    },
    {
      "epoch": 0.31393298059964725,
      "grad_norm": 2.0326128005981445,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1626,
      "step": 89
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.125136375427246,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.3441,
      "step": 90
    },
    {
      "epoch": 0.31746031746031744,
      "eval_loss": 0.09313661605119705,
      "eval_runtime": 37.6783,
      "eval_samples_per_second": 6.343,
      "eval_steps_per_second": 0.796,
      "step": 90
    },
    {
      "epoch": 0.32098765432098764,
      "grad_norm": 0.8155926465988159,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.101,
      "step": 91
    },
    {
      "epoch": 0.32451499118165783,
      "grad_norm": 1.1524417400360107,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0992,
      "step": 92
    },
    {
      "epoch": 0.328042328042328,
      "grad_norm": 2.5966567993164062,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1509,
      "step": 93
    },
    {
      "epoch": 0.3315696649029982,
      "grad_norm": 4.279085159301758,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3135,
      "step": 94
    },
    {
      "epoch": 0.3350970017636684,
      "grad_norm": 2.5114855766296387,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2901,
      "step": 95
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 3.0181519985198975,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2685,
      "step": 96
    },
    {
      "epoch": 0.3421516754850088,
      "grad_norm": 2.5745158195495605,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1457,
      "step": 97
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 3.473428726196289,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3729,
      "step": 98
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 3.5403099060058594,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2323,
      "step": 99
    },
    {
      "epoch": 0.3492063492063492,
      "eval_loss": 0.0885021910071373,
      "eval_runtime": 37.6512,
      "eval_samples_per_second": 6.348,
      "eval_steps_per_second": 0.797,
      "step": 99
    },
    {
      "epoch": 0.3527336860670194,
      "grad_norm": 4.210207462310791,
      "learning_rate": 0.0,
      "loss": 0.2794,
      "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": 1.2695579394048e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}