{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1718213058419244,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001718213058419244,
      "grad_norm": 1.4552257061004639,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.9747,
      "step": 1
    },
    {
      "epoch": 0.001718213058419244,
      "eval_loss": 2.9044692516326904,
      "eval_runtime": 54.1075,
      "eval_samples_per_second": 9.056,
      "eval_steps_per_second": 1.146,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 1.601818323135376,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.9211,
      "step": 2
    },
    {
      "epoch": 0.005154639175257732,
      "grad_norm": 1.3512325286865234,
      "learning_rate": 6e-06,
      "loss": 2.8581,
      "step": 3
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 1.0799566507339478,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.9037,
      "step": 4
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 1.1190871000289917,
      "learning_rate": 1e-05,
      "loss": 2.61,
      "step": 5
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 1.4691556692123413,
      "learning_rate": 1.2e-05,
      "loss": 2.8907,
      "step": 6
    },
    {
      "epoch": 0.012027491408934709,
      "grad_norm": 1.3452229499816895,
      "learning_rate": 1.4e-05,
      "loss": 2.9439,
      "step": 7
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 1.4221925735473633,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.9711,
      "step": 8
    },
    {
      "epoch": 0.015463917525773196,
      "grad_norm": 1.5153411626815796,
      "learning_rate": 1.8e-05,
      "loss": 2.8293,
      "step": 9
    },
    {
      "epoch": 0.015463917525773196,
      "eval_loss": 2.867755651473999,
      "eval_runtime": 53.9342,
      "eval_samples_per_second": 9.085,
      "eval_steps_per_second": 1.15,
      "step": 9
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.8503870964050293,
      "learning_rate": 2e-05,
      "loss": 3.026,
      "step": 10
    },
    {
      "epoch": 0.018900343642611683,
      "grad_norm": 1.2147204875946045,
      "learning_rate": 1.999390827019096e-05,
      "loss": 2.6945,
      "step": 11
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 1.7642078399658203,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 2.8923,
      "step": 12
    },
    {
      "epoch": 0.022336769759450172,
      "grad_norm": 1.2980129718780518,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 2.7393,
      "step": 13
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 1.3925917148590088,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 2.5535,
      "step": 14
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 1.5147944688796997,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 2.8511,
      "step": 15
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 1.2164130210876465,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 2.8437,
      "step": 16
    },
    {
      "epoch": 0.029209621993127148,
      "grad_norm": 1.0631439685821533,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 2.6763,
      "step": 17
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 1.086801290512085,
      "learning_rate": 1.961261695938319e-05,
      "loss": 2.6049,
      "step": 18
    },
    {
      "epoch": 0.030927835051546393,
      "eval_loss": 2.658050060272217,
      "eval_runtime": 53.9151,
      "eval_samples_per_second": 9.088,
      "eval_steps_per_second": 1.15,
      "step": 18
    },
    {
      "epoch": 0.03264604810996564,
      "grad_norm": 0.8783615827560425,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 2.4608,
      "step": 19
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 1.0227434635162354,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 2.62,
      "step": 20
    },
    {
      "epoch": 0.03608247422680412,
      "grad_norm": 0.9718742966651917,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 2.6886,
      "step": 21
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 0.915580153465271,
      "learning_rate": 1.913545457642601e-05,
      "loss": 2.6012,
      "step": 22
    },
    {
      "epoch": 0.03951890034364261,
      "grad_norm": 1.0638337135314941,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 2.6491,
      "step": 23
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.9384369850158691,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 2.5368,
      "step": 24
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 0.9130814075469971,
      "learning_rate": 1.866025403784439e-05,
      "loss": 2.3225,
      "step": 25
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 0.9184699058532715,
      "learning_rate": 1.848048096156426e-05,
      "loss": 2.4329,
      "step": 26
    },
    {
      "epoch": 0.04639175257731959,
      "grad_norm": 0.8856079578399658,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 2.5287,
      "step": 27
    },
    {
      "epoch": 0.04639175257731959,
      "eval_loss": 2.5378904342651367,
      "eval_runtime": 53.9895,
      "eval_samples_per_second": 9.076,
      "eval_steps_per_second": 1.148,
      "step": 27
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 0.8450868129730225,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 2.4979,
      "step": 28
    },
    {
      "epoch": 0.04982817869415808,
      "grad_norm": 0.7719012498855591,
      "learning_rate": 1.788010753606722e-05,
      "loss": 2.4681,
      "step": 29
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.9072224497795105,
      "learning_rate": 1.766044443118978e-05,
      "loss": 2.4365,
      "step": 30
    },
    {
      "epoch": 0.05326460481099656,
      "grad_norm": 0.7823221683502197,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 2.5295,
      "step": 31
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.7898750901222229,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 2.3923,
      "step": 32
    },
    {
      "epoch": 0.05670103092783505,
      "grad_norm": 0.8035944104194641,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 2.5298,
      "step": 33
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 0.8627927899360657,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 2.4673,
      "step": 34
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 0.8033456802368164,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 2.5981,
      "step": 35
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.8485693335533142,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 2.5288,
      "step": 36
    },
    {
      "epoch": 0.061855670103092786,
      "eval_loss": 2.4429104328155518,
      "eval_runtime": 53.9031,
      "eval_samples_per_second": 9.09,
      "eval_steps_per_second": 1.15,
      "step": 36
    },
    {
      "epoch": 0.06357388316151202,
      "grad_norm": 0.9421496987342834,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 2.5437,
      "step": 37
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 0.8354393839836121,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 2.4454,
      "step": 38
    },
    {
      "epoch": 0.06701030927835051,
      "grad_norm": 0.7670913338661194,
      "learning_rate": 1.529919264233205e-05,
      "loss": 2.4182,
      "step": 39
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.7763900756835938,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.3541,
      "step": 40
    },
    {
      "epoch": 0.070446735395189,
      "grad_norm": 0.8617604970932007,
      "learning_rate": 1.469471562785891e-05,
      "loss": 2.5271,
      "step": 41
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 0.9598429799079895,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 2.4375,
      "step": 42
    },
    {
      "epoch": 0.07388316151202749,
      "grad_norm": 0.9671466946601868,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 2.3714,
      "step": 43
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.9174774289131165,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 2.4412,
      "step": 44
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.7222942113876343,
      "learning_rate": 1.342020143325669e-05,
      "loss": 2.4793,
      "step": 45
    },
    {
      "epoch": 0.07731958762886598,
      "eval_loss": 2.3874599933624268,
      "eval_runtime": 53.8778,
      "eval_samples_per_second": 9.095,
      "eval_steps_per_second": 1.151,
      "step": 45
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 0.8627158999443054,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 2.3258,
      "step": 46
    },
    {
      "epoch": 0.08075601374570447,
      "grad_norm": 0.871549129486084,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 2.4123,
      "step": 47
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.8606653213500977,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 2.2999,
      "step": 48
    },
    {
      "epoch": 0.08419243986254296,
      "grad_norm": 0.79212886095047,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 2.3249,
      "step": 49
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 0.7536124587059021,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 2.4682,
      "step": 50
    },
    {
      "epoch": 0.08762886597938144,
      "grad_norm": 0.8749776482582092,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 2.4948,
      "step": 51
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.8494153618812561,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 2.2526,
      "step": 52
    },
    {
      "epoch": 0.09106529209621993,
      "grad_norm": 0.8222371935844421,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 2.3296,
      "step": 53
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.8096013069152832,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 2.3362,
      "step": 54
    },
    {
      "epoch": 0.09278350515463918,
      "eval_loss": 2.347243070602417,
      "eval_runtime": 54.0253,
      "eval_samples_per_second": 9.07,
      "eval_steps_per_second": 1.148,
      "step": 54
    },
    {
      "epoch": 0.09450171821305842,
      "grad_norm": 0.7850937843322754,
      "learning_rate": 1e-05,
      "loss": 2.3294,
      "step": 55
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.8678675293922424,
      "learning_rate": 9.651005032974994e-06,
      "loss": 2.3613,
      "step": 56
    },
    {
      "epoch": 0.0979381443298969,
      "grad_norm": 0.8474549651145935,
      "learning_rate": 9.302435262558748e-06,
      "loss": 2.2918,
      "step": 57
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 0.801964282989502,
      "learning_rate": 8.954715367323468e-06,
      "loss": 2.2381,
      "step": 58
    },
    {
      "epoch": 0.1013745704467354,
      "grad_norm": 0.8996317982673645,
      "learning_rate": 8.60826899039935e-06,
      "loss": 2.3592,
      "step": 59
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.9154346585273743,
      "learning_rate": 8.263518223330698e-06,
      "loss": 2.2233,
      "step": 60
    },
    {
      "epoch": 0.10481099656357389,
      "grad_norm": 0.8557789921760559,
      "learning_rate": 7.92088309182241e-06,
      "loss": 2.2071,
      "step": 61
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 0.8039612770080566,
      "learning_rate": 7.580781044003324e-06,
      "loss": 2.377,
      "step": 62
    },
    {
      "epoch": 0.10824742268041238,
      "grad_norm": 0.7728231549263,
      "learning_rate": 7.243626441830009e-06,
      "loss": 2.3457,
      "step": 63
    },
    {
      "epoch": 0.10824742268041238,
      "eval_loss": 2.322047233581543,
      "eval_runtime": 53.9766,
      "eval_samples_per_second": 9.078,
      "eval_steps_per_second": 1.149,
      "step": 63
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.8466572761535645,
      "learning_rate": 6.909830056250527e-06,
      "loss": 2.412,
      "step": 64
    },
    {
      "epoch": 0.11168384879725086,
      "grad_norm": 0.917604923248291,
      "learning_rate": 6.579798566743314e-06,
      "loss": 2.4045,
      "step": 65
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.9224315881729126,
      "learning_rate": 6.25393406584088e-06,
      "loss": 2.1501,
      "step": 66
    },
    {
      "epoch": 0.11512027491408934,
      "grad_norm": 0.837670624256134,
      "learning_rate": 5.932633569242e-06,
      "loss": 2.277,
      "step": 67
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.882990837097168,
      "learning_rate": 5.616288532109225e-06,
      "loss": 2.3712,
      "step": 68
    },
    {
      "epoch": 0.11855670103092783,
      "grad_norm": 0.8681703209877014,
      "learning_rate": 5.305284372141095e-06,
      "loss": 2.4016,
      "step": 69
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.9175694584846497,
      "learning_rate": 5.000000000000003e-06,
      "loss": 2.1803,
      "step": 70
    },
    {
      "epoch": 0.12199312714776632,
      "grad_norm": 0.8295563459396362,
      "learning_rate": 4.700807357667953e-06,
      "loss": 2.3304,
      "step": 71
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.8171641826629639,
      "learning_rate": 4.408070965292534e-06,
      "loss": 2.3101,
      "step": 72
    },
    {
      "epoch": 0.12371134020618557,
      "eval_loss": 2.3061485290527344,
      "eval_runtime": 53.9613,
      "eval_samples_per_second": 9.081,
      "eval_steps_per_second": 1.149,
      "step": 72
    },
    {
      "epoch": 0.1254295532646048,
      "grad_norm": 0.8037437796592712,
      "learning_rate": 4.12214747707527e-06,
      "loss": 2.3567,
      "step": 73
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 0.9995263814926147,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 2.3716,
      "step": 74
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 0.9321764707565308,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 2.3856,
      "step": 75
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.9107049703598022,
      "learning_rate": 3.308693936411421e-06,
      "loss": 2.1619,
      "step": 76
    },
    {
      "epoch": 0.1323024054982818,
      "grad_norm": 0.886493980884552,
      "learning_rate": 3.0534162954100264e-06,
      "loss": 2.364,
      "step": 77
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.8511906266212463,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 2.3702,
      "step": 78
    },
    {
      "epoch": 0.13573883161512026,
      "grad_norm": 0.8737676739692688,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 2.3266,
      "step": 79
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.9273460507392883,
      "learning_rate": 2.339555568810221e-06,
      "loss": 2.4682,
      "step": 80
    },
    {
      "epoch": 0.13917525773195877,
      "grad_norm": 0.9046407341957092,
      "learning_rate": 2.119892463932781e-06,
      "loss": 2.3845,
      "step": 81
    },
    {
      "epoch": 0.13917525773195877,
      "eval_loss": 2.2980504035949707,
      "eval_runtime": 53.8703,
      "eval_samples_per_second": 9.096,
      "eval_steps_per_second": 1.151,
      "step": 81
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.9387871623039246,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 2.2462,
      "step": 82
    },
    {
      "epoch": 0.14261168384879724,
      "grad_norm": 0.9409812688827515,
      "learning_rate": 1.709624274449584e-06,
      "loss": 2.2848,
      "step": 83
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.7702521681785583,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 2.1991,
      "step": 84
    },
    {
      "epoch": 0.14604810996563575,
      "grad_norm": 1.0706955194473267,
      "learning_rate": 1.339745962155613e-06,
      "loss": 2.3964,
      "step": 85
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 1.0983765125274658,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 2.2446,
      "step": 86
    },
    {
      "epoch": 0.14948453608247422,
      "grad_norm": 0.9635602831840515,
      "learning_rate": 1.012059537008332e-06,
      "loss": 2.4293,
      "step": 87
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.7959424257278442,
      "learning_rate": 8.645454235739903e-07,
      "loss": 2.3489,
      "step": 88
    },
    {
      "epoch": 0.15292096219931273,
      "grad_norm": 0.8272770643234253,
      "learning_rate": 7.281614543321269e-07,
      "loss": 2.3465,
      "step": 89
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.8438785672187805,
      "learning_rate": 6.030737921409169e-07,
      "loss": 2.3952,
      "step": 90
    },
    {
      "epoch": 0.15463917525773196,
      "eval_loss": 2.294905424118042,
      "eval_runtime": 53.8933,
      "eval_samples_per_second": 9.092,
      "eval_steps_per_second": 1.15,
      "step": 90
    },
    {
      "epoch": 0.1563573883161512,
      "grad_norm": 0.7433553338050842,
      "learning_rate": 4.894348370484648e-07,
      "loss": 2.2177,
      "step": 91
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.8562928438186646,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 2.2728,
      "step": 92
    },
    {
      "epoch": 0.15979381443298968,
      "grad_norm": 0.8268380165100098,
      "learning_rate": 2.970427372400353e-07,
      "loss": 2.1367,
      "step": 93
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 0.8015822172164917,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 2.2379,
      "step": 94
    },
    {
      "epoch": 0.16323024054982818,
      "grad_norm": 0.9183565378189087,
      "learning_rate": 1.519224698779198e-07,
      "loss": 2.3487,
      "step": 95
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.8422606587409973,
      "learning_rate": 9.731931258429638e-08,
      "loss": 2.2636,
      "step": 96
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.7898986339569092,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 2.3046,
      "step": 97
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.8091641068458557,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 2.2416,
      "step": 98
    },
    {
      "epoch": 0.17010309278350516,
      "grad_norm": 0.8988981246948242,
      "learning_rate": 6.091729809042379e-09,
      "loss": 2.2703,
      "step": 99
    },
    {
      "epoch": 0.17010309278350516,
      "eval_loss": 2.294187545776367,
      "eval_runtime": 53.8764,
      "eval_samples_per_second": 9.095,
      "eval_steps_per_second": 1.151,
      "step": 99
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 1.0704481601715088,
      "learning_rate": 0.0,
      "loss": 2.1572,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}