{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42643923240938164,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0042643923240938165,
      "grad_norm": 7.626420021057129,
      "learning_rate": 1e-05,
      "loss": 9.2005,
      "step": 1
    },
    {
      "epoch": 0.0042643923240938165,
      "eval_loss": 9.354655265808105,
      "eval_runtime": 10.9069,
      "eval_samples_per_second": 18.154,
      "eval_steps_per_second": 2.292,
      "step": 1
    },
    {
      "epoch": 0.008528784648187633,
      "grad_norm": 7.393431186676025,
      "learning_rate": 2e-05,
      "loss": 8.9266,
      "step": 2
    },
    {
      "epoch": 0.01279317697228145,
      "grad_norm": 7.272058963775635,
      "learning_rate": 3e-05,
      "loss": 9.4696,
      "step": 3
    },
    {
      "epoch": 0.017057569296375266,
      "grad_norm": 10.772072792053223,
      "learning_rate": 4e-05,
      "loss": 11.2647,
      "step": 4
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 8.580413818359375,
      "learning_rate": 5e-05,
      "loss": 9.7654,
      "step": 5
    },
    {
      "epoch": 0.0255863539445629,
      "grad_norm": 9.248568534851074,
      "learning_rate": 6e-05,
      "loss": 8.5883,
      "step": 6
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 8.970481872558594,
      "learning_rate": 7e-05,
      "loss": 7.5433,
      "step": 7
    },
    {
      "epoch": 0.03411513859275053,
      "grad_norm": 10.121480941772461,
      "learning_rate": 8e-05,
      "loss": 6.8674,
      "step": 8
    },
    {
      "epoch": 0.03837953091684435,
      "grad_norm": 11.635675430297852,
      "learning_rate": 9e-05,
      "loss": 6.0336,
      "step": 9
    },
    {
      "epoch": 0.03837953091684435,
      "eval_loss": 4.590646266937256,
      "eval_runtime": 10.2707,
      "eval_samples_per_second": 19.278,
      "eval_steps_per_second": 2.434,
      "step": 9
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 11.507807731628418,
      "learning_rate": 0.0001,
      "loss": 3.8999,
      "step": 10
    },
    {
      "epoch": 0.046908315565031986,
      "grad_norm": 11.984554290771484,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9669,
      "step": 11
    },
    {
      "epoch": 0.0511727078891258,
      "grad_norm": 9.42959976196289,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4079,
      "step": 12
    },
    {
      "epoch": 0.05543710021321962,
      "grad_norm": 5.841305255889893,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.3327,
      "step": 13
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 6.157541751861572,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1392,
      "step": 14
    },
    {
      "epoch": 0.06396588486140725,
      "grad_norm": 6.445117950439453,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7064,
      "step": 15
    },
    {
      "epoch": 0.06823027718550106,
      "grad_norm": 4.604715347290039,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7297,
      "step": 16
    },
    {
      "epoch": 0.07249466950959488,
      "grad_norm": 3.6460418701171875,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.5352,
      "step": 17
    },
    {
      "epoch": 0.0767590618336887,
      "grad_norm": 5.081651210784912,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.5846,
      "step": 18
    },
    {
      "epoch": 0.0767590618336887,
      "eval_loss": 0.5904957056045532,
      "eval_runtime": 10.272,
      "eval_samples_per_second": 19.276,
      "eval_steps_per_second": 2.434,
      "step": 18
    },
    {
      "epoch": 0.08102345415778252,
      "grad_norm": 6.522241115570068,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5412,
      "step": 19
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.6669106483459473,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.49,
      "step": 20
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 9.843894958496094,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.4774,
      "step": 21
    },
    {
      "epoch": 0.09381663113006397,
      "grad_norm": 12.477444648742676,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8002,
      "step": 22
    },
    {
      "epoch": 0.09808102345415778,
      "grad_norm": 2.9123220443725586,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5487,
      "step": 23
    },
    {
      "epoch": 0.1023454157782516,
      "grad_norm": 3.2394492626190186,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.563,
      "step": 24
    },
    {
      "epoch": 0.10660980810234541,
      "grad_norm": 2.013288974761963,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4545,
      "step": 25
    },
    {
      "epoch": 0.11087420042643924,
      "grad_norm": 2.242678642272949,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4828,
      "step": 26
    },
    {
      "epoch": 0.11513859275053305,
      "grad_norm": 3.301732301712036,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5155,
      "step": 27
    },
    {
      "epoch": 0.11513859275053305,
      "eval_loss": 0.47521042823791504,
      "eval_runtime": 10.2818,
      "eval_samples_per_second": 19.257,
      "eval_steps_per_second": 2.431,
      "step": 27
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 6.40436315536499,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4565,
      "step": 28
    },
    {
      "epoch": 0.12366737739872068,
      "grad_norm": 1.839121699333191,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.4901,
      "step": 29
    },
    {
      "epoch": 0.1279317697228145,
      "grad_norm": 3.2513206005096436,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4915,
      "step": 30
    },
    {
      "epoch": 0.13219616204690832,
      "grad_norm": 3.136847972869873,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4709,
      "step": 31
    },
    {
      "epoch": 0.13646055437100213,
      "grad_norm": 7.7169294357299805,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.362,
      "step": 32
    },
    {
      "epoch": 0.14072494669509594,
      "grad_norm": 4.151850700378418,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4048,
      "step": 33
    },
    {
      "epoch": 0.14498933901918976,
      "grad_norm": 2.1074740886688232,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4591,
      "step": 34
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 3.01412296295166,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.4848,
      "step": 35
    },
    {
      "epoch": 0.1535181236673774,
      "grad_norm": 1.6540210247039795,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3455,
      "step": 36
    },
    {
      "epoch": 0.1535181236673774,
      "eval_loss": 0.46294257044792175,
      "eval_runtime": 10.278,
      "eval_samples_per_second": 19.264,
      "eval_steps_per_second": 2.432,
      "step": 36
    },
    {
      "epoch": 0.15778251599147122,
      "grad_norm": 6.573389053344727,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5752,
      "step": 37
    },
    {
      "epoch": 0.16204690831556504,
      "grad_norm": 2.1863722801208496,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.4337,
      "step": 38
    },
    {
      "epoch": 0.16631130063965885,
      "grad_norm": 2.0309736728668213,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3555,
      "step": 39
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 2.8576529026031494,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3864,
      "step": 40
    },
    {
      "epoch": 0.17484008528784648,
      "grad_norm": 6.763268947601318,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5615,
      "step": 41
    },
    {
      "epoch": 0.1791044776119403,
      "grad_norm": 5.373194217681885,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5298,
      "step": 42
    },
    {
      "epoch": 0.18336886993603413,
      "grad_norm": 3.1446313858032227,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6005,
      "step": 43
    },
    {
      "epoch": 0.18763326226012794,
      "grad_norm": 3.919086217880249,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5317,
      "step": 44
    },
    {
      "epoch": 0.19189765458422176,
      "grad_norm": 3.238208770751953,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4672,
      "step": 45
    },
    {
      "epoch": 0.19189765458422176,
      "eval_loss": 0.45284032821655273,
      "eval_runtime": 10.2761,
      "eval_samples_per_second": 19.268,
      "eval_steps_per_second": 2.433,
      "step": 45
    },
    {
      "epoch": 0.19616204690831557,
      "grad_norm": 1.8225382566452026,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3382,
      "step": 46
    },
    {
      "epoch": 0.20042643923240938,
      "grad_norm": 3.1441404819488525,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.5518,
      "step": 47
    },
    {
      "epoch": 0.2046908315565032,
      "grad_norm": 1.9129095077514648,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5483,
      "step": 48
    },
    {
      "epoch": 0.208955223880597,
      "grad_norm": 1.4173413515090942,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.4976,
      "step": 49
    },
    {
      "epoch": 0.21321961620469082,
      "grad_norm": 1.7645654678344727,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.4223,
      "step": 50
    },
    {
      "epoch": 0.21748400852878466,
      "grad_norm": 2.758833408355713,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.3897,
      "step": 51
    },
    {
      "epoch": 0.22174840085287847,
      "grad_norm": 1.5845016241073608,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4511,
      "step": 52
    },
    {
      "epoch": 0.2260127931769723,
      "grad_norm": 1.5579299926757812,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.477,
      "step": 53
    },
    {
      "epoch": 0.2302771855010661,
      "grad_norm": 2.5025551319122314,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4295,
      "step": 54
    },
    {
      "epoch": 0.2302771855010661,
      "eval_loss": 0.45656469464302063,
      "eval_runtime": 10.3078,
      "eval_samples_per_second": 19.209,
      "eval_steps_per_second": 2.425,
      "step": 54
    },
    {
      "epoch": 0.2345415778251599,
      "grad_norm": 2.2095389366149902,
      "learning_rate": 5e-05,
      "loss": 0.4678,
      "step": 55
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 2.579927921295166,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4832,
      "step": 56
    },
    {
      "epoch": 0.24307036247334754,
      "grad_norm": 5.3822431564331055,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.4564,
      "step": 57
    },
    {
      "epoch": 0.24733475479744135,
      "grad_norm": 2.7342562675476074,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.4626,
      "step": 58
    },
    {
      "epoch": 0.2515991471215352,
      "grad_norm": 1.588128685951233,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.3156,
      "step": 59
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 2.154703378677368,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.481,
      "step": 60
    },
    {
      "epoch": 0.2601279317697228,
      "grad_norm": 1.9552626609802246,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.4017,
      "step": 61
    },
    {
      "epoch": 0.26439232409381663,
      "grad_norm": 2.0230414867401123,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.3645,
      "step": 62
    },
    {
      "epoch": 0.26865671641791045,
      "grad_norm": 1.755893588066101,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.4127,
      "step": 63
    },
    {
      "epoch": 0.26865671641791045,
      "eval_loss": 0.43372291326522827,
      "eval_runtime": 10.2799,
      "eval_samples_per_second": 19.261,
      "eval_steps_per_second": 2.432,
      "step": 63
    },
    {
      "epoch": 0.27292110874200426,
      "grad_norm": 2.2485551834106445,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3189,
      "step": 64
    },
    {
      "epoch": 0.2771855010660981,
      "grad_norm": 1.3965363502502441,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.3366,
      "step": 65
    },
    {
      "epoch": 0.2814498933901919,
      "grad_norm": 1.3492567539215088,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3823,
      "step": 66
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.6632083654403687,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.3844,
      "step": 67
    },
    {
      "epoch": 0.2899786780383795,
      "grad_norm": 1.879550576210022,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.4101,
      "step": 68
    },
    {
      "epoch": 0.2942430703624733,
      "grad_norm": 1.3813761472702026,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.3181,
      "step": 69
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 1.4394125938415527,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4275,
      "step": 70
    },
    {
      "epoch": 0.302771855010661,
      "grad_norm": 1.6453180313110352,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.406,
      "step": 71
    },
    {
      "epoch": 0.3070362473347548,
      "grad_norm": 2.2891740798950195,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.4582,
      "step": 72
    },
    {
      "epoch": 0.3070362473347548,
      "eval_loss": 0.42013365030288696,
      "eval_runtime": 10.2772,
      "eval_samples_per_second": 19.266,
      "eval_steps_per_second": 2.433,
      "step": 72
    },
    {
      "epoch": 0.31130063965884863,
      "grad_norm": 1.596182107925415,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3626,
      "step": 73
    },
    {
      "epoch": 0.31556503198294245,
      "grad_norm": 1.9961284399032593,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.4155,
      "step": 74
    },
    {
      "epoch": 0.31982942430703626,
      "grad_norm": 3.454941511154175,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.3384,
      "step": 75
    },
    {
      "epoch": 0.32409381663113007,
      "grad_norm": 2.230226993560791,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4053,
      "step": 76
    },
    {
      "epoch": 0.3283582089552239,
      "grad_norm": 2.071410655975342,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2676,
      "step": 77
    },
    {
      "epoch": 0.3326226012793177,
      "grad_norm": 2.1903834342956543,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3557,
      "step": 78
    },
    {
      "epoch": 0.3368869936034115,
      "grad_norm": 1.414023518562317,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3895,
      "step": 79
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 2.7078359127044678,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.4453,
      "step": 80
    },
    {
      "epoch": 0.34541577825159914,
      "grad_norm": 3.0554823875427246,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4786,
      "step": 81
    },
    {
      "epoch": 0.34541577825159914,
      "eval_loss": 0.3989747166633606,
      "eval_runtime": 10.3092,
      "eval_samples_per_second": 19.206,
      "eval_steps_per_second": 2.425,
      "step": 81
    },
    {
      "epoch": 0.34968017057569295,
      "grad_norm": 2.796588897705078,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3151,
      "step": 82
    },
    {
      "epoch": 0.35394456289978676,
      "grad_norm": 2.060140371322632,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.3486,
      "step": 83
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 2.0628552436828613,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.5163,
      "step": 84
    },
    {
      "epoch": 0.3624733475479744,
      "grad_norm": 2.8777129650115967,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5624,
      "step": 85
    },
    {
      "epoch": 0.36673773987206826,
      "grad_norm": 2.5616040229797363,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6318,
      "step": 86
    },
    {
      "epoch": 0.37100213219616207,
      "grad_norm": 2.548530340194702,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.3601,
      "step": 87
    },
    {
      "epoch": 0.3752665245202559,
      "grad_norm": 2.070634126663208,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5104,
      "step": 88
    },
    {
      "epoch": 0.3795309168443497,
      "grad_norm": 1.8933154344558716,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.3162,
      "step": 89
    },
    {
      "epoch": 0.3837953091684435,
      "grad_norm": 5.129238128662109,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2426,
      "step": 90
    },
    {
      "epoch": 0.3837953091684435,
      "eval_loss": 0.39163798093795776,
      "eval_runtime": 10.2858,
      "eval_samples_per_second": 19.25,
      "eval_steps_per_second": 2.431,
      "step": 90
    },
    {
      "epoch": 0.3880597014925373,
      "grad_norm": 1.3959840536117554,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2662,
      "step": 91
    },
    {
      "epoch": 0.39232409381663114,
      "grad_norm": 1.5999782085418701,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4021,
      "step": 92
    },
    {
      "epoch": 0.39658848614072495,
      "grad_norm": 1.681472659111023,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.323,
      "step": 93
    },
    {
      "epoch": 0.40085287846481876,
      "grad_norm": 1.872139811515808,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3603,
      "step": 94
    },
    {
      "epoch": 0.4051172707889126,
      "grad_norm": 1.6787221431732178,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.3002,
      "step": 95
    },
    {
      "epoch": 0.4093816631130064,
      "grad_norm": 1.6023163795471191,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4431,
      "step": 96
    },
    {
      "epoch": 0.4136460554371002,
      "grad_norm": 5.4748125076293945,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.6219,
      "step": 97
    },
    {
      "epoch": 0.417910447761194,
      "grad_norm": 3.0397448539733887,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3617,
      "step": 98
    },
    {
      "epoch": 0.42217484008528783,
      "grad_norm": 2.4502100944519043,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4726,
      "step": 99
    },
    {
      "epoch": 0.42217484008528783,
      "eval_loss": 0.3900476396083832,
      "eval_runtime": 10.2861,
      "eval_samples_per_second": 19.249,
      "eval_steps_per_second": 2.43,
      "step": 99
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 2.7998695373535156,
      "learning_rate": 0.0,
      "loss": 0.591,
      "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": 7.455967199782502e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}