{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.102880658436214,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00102880658436214,
      "grad_norm": 0.025219934061169624,
      "learning_rate": 1e-05,
      "loss": 10.3752,
      "step": 1
    },
    {
      "epoch": 0.00102880658436214,
      "eval_loss": 10.375638961791992,
      "eval_runtime": 3.4609,
      "eval_samples_per_second": 236.643,
      "eval_steps_per_second": 29.761,
      "step": 1
    },
    {
      "epoch": 0.00205761316872428,
      "grad_norm": 0.02738805301487446,
      "learning_rate": 2e-05,
      "loss": 10.377,
      "step": 2
    },
    {
      "epoch": 0.0030864197530864196,
      "grad_norm": 0.026469284668564796,
      "learning_rate": 3e-05,
      "loss": 10.3742,
      "step": 3
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 0.02698007971048355,
      "learning_rate": 4e-05,
      "loss": 10.3783,
      "step": 4
    },
    {
      "epoch": 0.0051440329218107,
      "grad_norm": 0.02839619107544422,
      "learning_rate": 5e-05,
      "loss": 10.374,
      "step": 5
    },
    {
      "epoch": 0.006172839506172839,
      "grad_norm": 0.029380450025200844,
      "learning_rate": 6e-05,
      "loss": 10.3777,
      "step": 6
    },
    {
      "epoch": 0.00720164609053498,
      "grad_norm": 0.024871516972780228,
      "learning_rate": 7e-05,
      "loss": 10.3754,
      "step": 7
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 0.028594117611646652,
      "learning_rate": 8e-05,
      "loss": 10.3687,
      "step": 8
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 0.02646900713443756,
      "learning_rate": 9e-05,
      "loss": 10.3764,
      "step": 9
    },
    {
      "epoch": 0.009259259259259259,
      "eval_loss": 10.375298500061035,
      "eval_runtime": 4.7508,
      "eval_samples_per_second": 172.393,
      "eval_steps_per_second": 21.681,
      "step": 9
    },
    {
      "epoch": 0.0102880658436214,
      "grad_norm": 0.030630815774202347,
      "learning_rate": 0.0001,
      "loss": 10.3748,
      "step": 10
    },
    {
      "epoch": 0.01131687242798354,
      "grad_norm": 0.02231612056493759,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3753,
      "step": 11
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 0.03500870242714882,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3749,
      "step": 12
    },
    {
      "epoch": 0.013374485596707819,
      "grad_norm": 0.03169140964746475,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3728,
      "step": 13
    },
    {
      "epoch": 0.01440329218106996,
      "grad_norm": 0.033007316291332245,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3752,
      "step": 14
    },
    {
      "epoch": 0.015432098765432098,
      "grad_norm": 0.027678297832608223,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3716,
      "step": 15
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 0.028717216104269028,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3719,
      "step": 16
    },
    {
      "epoch": 0.01748971193415638,
      "grad_norm": 0.024401096627116203,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3713,
      "step": 17
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.03191472589969635,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.379,
      "step": 18
    },
    {
      "epoch": 0.018518518518518517,
      "eval_loss": 10.374419212341309,
      "eval_runtime": 4.6532,
      "eval_samples_per_second": 176.007,
      "eval_steps_per_second": 22.135,
      "step": 18
    },
    {
      "epoch": 0.01954732510288066,
      "grad_norm": 0.026906833052635193,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3749,
      "step": 19
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 0.024135004729032516,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3714,
      "step": 20
    },
    {
      "epoch": 0.021604938271604937,
      "grad_norm": 0.030134005472064018,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3771,
      "step": 21
    },
    {
      "epoch": 0.02263374485596708,
      "grad_norm": 0.02962920069694519,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3719,
      "step": 22
    },
    {
      "epoch": 0.023662551440329218,
      "grad_norm": 0.02854999154806137,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.373,
      "step": 23
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.026968492195010185,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3742,
      "step": 24
    },
    {
      "epoch": 0.0257201646090535,
      "grad_norm": 0.03159381076693535,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.374,
      "step": 25
    },
    {
      "epoch": 0.026748971193415638,
      "grad_norm": 0.028679387643933296,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3742,
      "step": 26
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 0.027246227487921715,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.373,
      "step": 27
    },
    {
      "epoch": 0.027777777777777776,
      "eval_loss": 10.373526573181152,
      "eval_runtime": 4.4408,
      "eval_samples_per_second": 184.426,
      "eval_steps_per_second": 23.194,
      "step": 27
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 0.02638566493988037,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3752,
      "step": 28
    },
    {
      "epoch": 0.029835390946502057,
      "grad_norm": 0.029429133981466293,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3752,
      "step": 29
    },
    {
      "epoch": 0.030864197530864196,
      "grad_norm": 0.028540797531604767,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3752,
      "step": 30
    },
    {
      "epoch": 0.03189300411522634,
      "grad_norm": 0.026979394257068634,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3744,
      "step": 31
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 0.03402787446975708,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3702,
      "step": 32
    },
    {
      "epoch": 0.033950617283950615,
      "grad_norm": 0.03517807647585869,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3777,
      "step": 33
    },
    {
      "epoch": 0.03497942386831276,
      "grad_norm": 0.028791263699531555,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.37,
      "step": 34
    },
    {
      "epoch": 0.0360082304526749,
      "grad_norm": 0.027155417948961258,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.374,
      "step": 35
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.033103760331869125,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3683,
      "step": 36
    },
    {
      "epoch": 0.037037037037037035,
      "eval_loss": 10.372629165649414,
      "eval_runtime": 4.6687,
      "eval_samples_per_second": 175.422,
      "eval_steps_per_second": 22.062,
      "step": 36
    },
    {
      "epoch": 0.03806584362139918,
      "grad_norm": 0.03502420708537102,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.371,
      "step": 37
    },
    {
      "epoch": 0.03909465020576132,
      "grad_norm": 0.03081183321774006,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3732,
      "step": 38
    },
    {
      "epoch": 0.040123456790123455,
      "grad_norm": 0.02784951776266098,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3758,
      "step": 39
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.03854544833302498,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3658,
      "step": 40
    },
    {
      "epoch": 0.04218106995884774,
      "grad_norm": 0.027156542986631393,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3731,
      "step": 41
    },
    {
      "epoch": 0.043209876543209874,
      "grad_norm": 0.03118831478059292,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3659,
      "step": 42
    },
    {
      "epoch": 0.044238683127572016,
      "grad_norm": 0.03406394273042679,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3682,
      "step": 43
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 0.03691929578781128,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3734,
      "step": 44
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 0.03526577353477478,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3724,
      "step": 45
    },
    {
      "epoch": 0.046296296296296294,
      "eval_loss": 10.37172794342041,
      "eval_runtime": 4.6525,
      "eval_samples_per_second": 176.035,
      "eval_steps_per_second": 22.139,
      "step": 45
    },
    {
      "epoch": 0.047325102880658436,
      "grad_norm": 0.038986314088106155,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3734,
      "step": 46
    },
    {
      "epoch": 0.04835390946502058,
      "grad_norm": 0.033386219292879105,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3747,
      "step": 47
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.03682396188378334,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3702,
      "step": 48
    },
    {
      "epoch": 0.050411522633744855,
      "grad_norm": 0.035510748624801636,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3708,
      "step": 49
    },
    {
      "epoch": 0.051440329218107,
      "grad_norm": 0.02855323627591133,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3743,
      "step": 50
    },
    {
      "epoch": 0.05246913580246913,
      "grad_norm": 0.033705513924360275,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3749,
      "step": 51
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 0.03999943658709526,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3671,
      "step": 52
    },
    {
      "epoch": 0.05452674897119342,
      "grad_norm": 0.043624721467494965,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3708,
      "step": 53
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.036783572286367416,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3684,
      "step": 54
    },
    {
      "epoch": 0.05555555555555555,
      "eval_loss": 10.370903015136719,
      "eval_runtime": 4.3048,
      "eval_samples_per_second": 190.254,
      "eval_steps_per_second": 23.927,
      "step": 54
    },
    {
      "epoch": 0.056584362139917695,
      "grad_norm": 0.036852557212114334,
      "learning_rate": 5e-05,
      "loss": 10.3715,
      "step": 55
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.036059990525245667,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3685,
      "step": 56
    },
    {
      "epoch": 0.05864197530864197,
      "grad_norm": 0.04546878859400749,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3685,
      "step": 57
    },
    {
      "epoch": 0.059670781893004114,
      "grad_norm": 0.045334216207265854,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3677,
      "step": 58
    },
    {
      "epoch": 0.060699588477366256,
      "grad_norm": 0.046929437667131424,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3717,
      "step": 59
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 0.041340090334415436,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3723,
      "step": 60
    },
    {
      "epoch": 0.06275720164609054,
      "grad_norm": 0.042488716542720795,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3692,
      "step": 61
    },
    {
      "epoch": 0.06378600823045268,
      "grad_norm": 0.03854437917470932,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3682,
      "step": 62
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 0.03789610043168068,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3731,
      "step": 63
    },
    {
      "epoch": 0.06481481481481481,
      "eval_loss": 10.370210647583008,
      "eval_runtime": 4.6613,
      "eval_samples_per_second": 175.703,
      "eval_steps_per_second": 22.097,
      "step": 63
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.044738225638866425,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3694,
      "step": 64
    },
    {
      "epoch": 0.0668724279835391,
      "grad_norm": 0.040270205587148666,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3669,
      "step": 65
    },
    {
      "epoch": 0.06790123456790123,
      "grad_norm": 0.04272771254181862,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3651,
      "step": 66
    },
    {
      "epoch": 0.06893004115226338,
      "grad_norm": 0.043519698083400726,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3693,
      "step": 67
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 0.03874226659536362,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3727,
      "step": 68
    },
    {
      "epoch": 0.07098765432098765,
      "grad_norm": 0.05196073278784752,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3709,
      "step": 69
    },
    {
      "epoch": 0.0720164609053498,
      "grad_norm": 0.04321382939815521,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3718,
      "step": 70
    },
    {
      "epoch": 0.07304526748971193,
      "grad_norm": 0.046473391354084015,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3715,
      "step": 71
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.04274188354611397,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3679,
      "step": 72
    },
    {
      "epoch": 0.07407407407407407,
      "eval_loss": 10.369702339172363,
      "eval_runtime": 4.6514,
      "eval_samples_per_second": 176.078,
      "eval_steps_per_second": 22.144,
      "step": 72
    },
    {
      "epoch": 0.07510288065843622,
      "grad_norm": 0.03789234161376953,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3722,
      "step": 73
    },
    {
      "epoch": 0.07613168724279835,
      "grad_norm": 0.04123846814036369,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3666,
      "step": 74
    },
    {
      "epoch": 0.07716049382716049,
      "grad_norm": 0.043930958956480026,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3657,
      "step": 75
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 0.04726821556687355,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3692,
      "step": 76
    },
    {
      "epoch": 0.07921810699588477,
      "grad_norm": 0.04689066484570503,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3695,
      "step": 77
    },
    {
      "epoch": 0.08024691358024691,
      "grad_norm": 0.05402266979217529,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.37,
      "step": 78
    },
    {
      "epoch": 0.08127572016460906,
      "grad_norm": 0.04493223875761032,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3684,
      "step": 79
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.058183249086141586,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3659,
      "step": 80
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.04858890920877457,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3681,
      "step": 81
    },
    {
      "epoch": 0.08333333333333333,
      "eval_loss": 10.369402885437012,
      "eval_runtime": 4.4593,
      "eval_samples_per_second": 183.661,
      "eval_steps_per_second": 23.098,
      "step": 81
    },
    {
      "epoch": 0.08436213991769548,
      "grad_norm": 0.04888492077589035,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3731,
      "step": 82
    },
    {
      "epoch": 0.08539094650205761,
      "grad_norm": 0.04856285825371742,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3696,
      "step": 83
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 0.053031668066978455,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.371,
      "step": 84
    },
    {
      "epoch": 0.0874485596707819,
      "grad_norm": 0.04873763024806976,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3726,
      "step": 85
    },
    {
      "epoch": 0.08847736625514403,
      "grad_norm": 0.06068224832415581,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3666,
      "step": 86
    },
    {
      "epoch": 0.08950617283950617,
      "grad_norm": 0.05208251252770424,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3692,
      "step": 87
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.044392600655555725,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.369,
      "step": 88
    },
    {
      "epoch": 0.09156378600823045,
      "grad_norm": 0.05065758153796196,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3688,
      "step": 89
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.04816662147641182,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3699,
      "step": 90
    },
    {
      "epoch": 0.09259259259259259,
      "eval_loss": 10.36927318572998,
      "eval_runtime": 4.7104,
      "eval_samples_per_second": 173.872,
      "eval_steps_per_second": 21.867,
      "step": 90
    },
    {
      "epoch": 0.09362139917695474,
      "grad_norm": 0.040740616619586945,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3726,
      "step": 91
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 0.04884503409266472,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3637,
      "step": 92
    },
    {
      "epoch": 0.09567901234567901,
      "grad_norm": 0.045312654227018356,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3682,
      "step": 93
    },
    {
      "epoch": 0.09670781893004116,
      "grad_norm": 0.03917687013745308,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3687,
      "step": 94
    },
    {
      "epoch": 0.09773662551440329,
      "grad_norm": 0.04869252070784569,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3677,
      "step": 95
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.03939636051654816,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3654,
      "step": 96
    },
    {
      "epoch": 0.09979423868312758,
      "grad_norm": 0.04943367838859558,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.366,
      "step": 97
    },
    {
      "epoch": 0.10082304526748971,
      "grad_norm": 0.04062531515955925,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3703,
      "step": 98
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 0.04285578057169914,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3704,
      "step": 99
    },
    {
      "epoch": 0.10185185185185185,
      "eval_loss": 10.369248390197754,
      "eval_runtime": 4.5585,
      "eval_samples_per_second": 179.666,
      "eval_steps_per_second": 22.595,
      "step": 99
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 0.04049593210220337,
      "learning_rate": 0.0,
      "loss": 10.3727,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}