{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 13616,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007344536812195604,
      "grad_norm": 143.0,
      "learning_rate": 1.98e-06,
      "loss": 10.0764,
      "step": 100
    },
    {
      "epoch": 0.014689073624391208,
      "grad_norm": 8.9375,
      "learning_rate": 3.980000000000001e-06,
      "loss": 5.2006,
      "step": 200
    },
    {
      "epoch": 0.02203361043658681,
      "grad_norm": 4.3125,
      "learning_rate": 5.98e-06,
      "loss": 0.1298,
      "step": 300
    },
    {
      "epoch": 0.029378147248782415,
      "grad_norm": 0.388671875,
      "learning_rate": 7.980000000000002e-06,
      "loss": 0.0782,
      "step": 400
    },
    {
      "epoch": 0.03672268406097802,
      "grad_norm": 0.267578125,
      "learning_rate": 9.980000000000001e-06,
      "loss": 0.0587,
      "step": 500
    },
    {
      "epoch": 0.04406722087317362,
      "grad_norm": 0.291015625,
      "learning_rate": 1.198e-05,
      "loss": 0.0435,
      "step": 600
    },
    {
      "epoch": 0.05141175768536922,
      "grad_norm": 0.205078125,
      "learning_rate": 1.398e-05,
      "loss": 0.0347,
      "step": 700
    },
    {
      "epoch": 0.05875629449756483,
      "grad_norm": 0.162109375,
      "learning_rate": 1.5980000000000003e-05,
      "loss": 0.0298,
      "step": 800
    },
    {
      "epoch": 0.06610083130976042,
      "grad_norm": 0.1904296875,
      "learning_rate": 1.798e-05,
      "loss": 0.028,
      "step": 900
    },
    {
      "epoch": 0.07344536812195604,
      "grad_norm": 0.1611328125,
      "learning_rate": 1.9980000000000002e-05,
      "loss": 0.0255,
      "step": 1000
    },
    {
      "epoch": 0.07344536812195604,
      "eval_loss": 0.2227211892604828,
      "eval_runtime": 5094.624,
      "eval_samples_per_second": 3.571,
      "eval_steps_per_second": 1.786,
      "step": 1000
    },
    {
      "epoch": 0.08078990493415164,
      "grad_norm": 0.5078125,
      "learning_rate": 1.9843056436271404e-05,
      "loss": 0.0249,
      "step": 1100
    },
    {
      "epoch": 0.08813444174634724,
      "grad_norm": 0.177734375,
      "learning_rate": 1.9684527584020294e-05,
      "loss": 0.0235,
      "step": 1200
    },
    {
      "epoch": 0.09547897855854284,
      "grad_norm": 0.171875,
      "learning_rate": 1.9525998731769185e-05,
      "loss": 0.0241,
      "step": 1300
    },
    {
      "epoch": 0.10282351537073844,
      "grad_norm": 0.1669921875,
      "learning_rate": 1.9367469879518076e-05,
      "loss": 0.0227,
      "step": 1400
    },
    {
      "epoch": 0.11016805218293405,
      "grad_norm": 0.263671875,
      "learning_rate": 1.9208941027266967e-05,
      "loss": 0.0209,
      "step": 1500
    },
    {
      "epoch": 0.11751258899512966,
      "grad_norm": 0.17578125,
      "learning_rate": 1.9050412175015854e-05,
      "loss": 0.0209,
      "step": 1600
    },
    {
      "epoch": 0.12485712580732526,
      "grad_norm": 0.2353515625,
      "learning_rate": 1.8891883322764745e-05,
      "loss": 0.0208,
      "step": 1700
    },
    {
      "epoch": 0.13220166261952085,
      "grad_norm": 0.171875,
      "learning_rate": 1.8733354470513636e-05,
      "loss": 0.0205,
      "step": 1800
    },
    {
      "epoch": 0.13954619943171648,
      "grad_norm": 0.17578125,
      "learning_rate": 1.8574825618262527e-05,
      "loss": 0.0206,
      "step": 1900
    },
    {
      "epoch": 0.14689073624391208,
      "grad_norm": 0.28515625,
      "learning_rate": 1.8416296766011418e-05,
      "loss": 0.0223,
      "step": 2000
    },
    {
      "epoch": 0.14689073624391208,
      "eval_loss": 0.21734359860420227,
      "eval_runtime": 5086.7715,
      "eval_samples_per_second": 3.577,
      "eval_steps_per_second": 1.789,
      "step": 2000
    },
    {
      "epoch": 0.15423527305610768,
      "grad_norm": 0.1669921875,
      "learning_rate": 1.8257767913760305e-05,
      "loss": 0.0189,
      "step": 2100
    },
    {
      "epoch": 0.16157980986830328,
      "grad_norm": 0.177734375,
      "learning_rate": 1.8099239061509196e-05,
      "loss": 0.0189,
      "step": 2200
    },
    {
      "epoch": 0.16892434668049888,
      "grad_norm": 0.15234375,
      "learning_rate": 1.7940710209258087e-05,
      "loss": 0.0192,
      "step": 2300
    },
    {
      "epoch": 0.17626888349269448,
      "grad_norm": 0.123046875,
      "learning_rate": 1.7782181357006974e-05,
      "loss": 0.0197,
      "step": 2400
    },
    {
      "epoch": 0.18361342030489008,
      "grad_norm": 0.1708984375,
      "learning_rate": 1.7623652504755865e-05,
      "loss": 0.0191,
      "step": 2500
    },
    {
      "epoch": 0.19095795711708569,
      "grad_norm": 0.21484375,
      "learning_rate": 1.7465123652504756e-05,
      "loss": 0.019,
      "step": 2600
    },
    {
      "epoch": 0.1983024939292813,
      "grad_norm": 0.1337890625,
      "learning_rate": 1.7306594800253647e-05,
      "loss": 0.0187,
      "step": 2700
    },
    {
      "epoch": 0.2056470307414769,
      "grad_norm": 0.2373046875,
      "learning_rate": 1.7148065948002538e-05,
      "loss": 0.019,
      "step": 2800
    },
    {
      "epoch": 0.2129915675536725,
      "grad_norm": 0.1708984375,
      "learning_rate": 1.698953709575143e-05,
      "loss": 0.0178,
      "step": 2900
    },
    {
      "epoch": 0.2203361043658681,
      "grad_norm": 0.12890625,
      "learning_rate": 1.6831008243500316e-05,
      "loss": 0.0188,
      "step": 3000
    },
    {
      "epoch": 0.2203361043658681,
      "eval_loss": 0.2142712026834488,
      "eval_runtime": 5079.9516,
      "eval_samples_per_second": 3.582,
      "eval_steps_per_second": 1.791,
      "step": 3000
    },
    {
      "epoch": 0.2276806411780637,
      "grad_norm": 0.2353515625,
      "learning_rate": 1.6672479391249207e-05,
      "loss": 0.0192,
      "step": 3100
    },
    {
      "epoch": 0.23502517799025932,
      "grad_norm": 0.16796875,
      "learning_rate": 1.6513950538998098e-05,
      "loss": 0.0187,
      "step": 3200
    },
    {
      "epoch": 0.24236971480245492,
      "grad_norm": 0.1923828125,
      "learning_rate": 1.635542168674699e-05,
      "loss": 0.0178,
      "step": 3300
    },
    {
      "epoch": 0.24971425161465052,
      "grad_norm": 0.36328125,
      "learning_rate": 1.619689283449588e-05,
      "loss": 0.0185,
      "step": 3400
    },
    {
      "epoch": 0.2570587884268461,
      "grad_norm": 0.224609375,
      "learning_rate": 1.603836398224477e-05,
      "loss": 0.018,
      "step": 3500
    },
    {
      "epoch": 0.2644033252390417,
      "grad_norm": 0.12353515625,
      "learning_rate": 1.587983512999366e-05,
      "loss": 0.0185,
      "step": 3600
    },
    {
      "epoch": 0.2717478620512373,
      "grad_norm": 0.2578125,
      "learning_rate": 1.572130627774255e-05,
      "loss": 0.0185,
      "step": 3700
    },
    {
      "epoch": 0.27909239886343296,
      "grad_norm": 0.169921875,
      "learning_rate": 1.556277742549144e-05,
      "loss": 0.0185,
      "step": 3800
    },
    {
      "epoch": 0.28643693567562856,
      "grad_norm": 0.345703125,
      "learning_rate": 1.540424857324033e-05,
      "loss": 0.0188,
      "step": 3900
    },
    {
      "epoch": 0.29378147248782416,
      "grad_norm": 0.1494140625,
      "learning_rate": 1.5245719720989221e-05,
      "loss": 0.0179,
      "step": 4000
    },
    {
      "epoch": 0.29378147248782416,
      "eval_loss": 0.21290630102157593,
      "eval_runtime": 5080.5527,
      "eval_samples_per_second": 3.581,
      "eval_steps_per_second": 1.791,
      "step": 4000
    },
    {
      "epoch": 0.30112600930001976,
      "grad_norm": 0.171875,
      "learning_rate": 1.508719086873811e-05,
      "loss": 0.0182,
      "step": 4100
    },
    {
      "epoch": 0.30847054611221536,
      "grad_norm": 0.1474609375,
      "learning_rate": 1.4928662016487001e-05,
      "loss": 0.0164,
      "step": 4200
    },
    {
      "epoch": 0.31581508292441096,
      "grad_norm": 0.1484375,
      "learning_rate": 1.4770133164235892e-05,
      "loss": 0.0188,
      "step": 4300
    },
    {
      "epoch": 0.32315961973660656,
      "grad_norm": 0.18359375,
      "learning_rate": 1.4611604311984781e-05,
      "loss": 0.0188,
      "step": 4400
    },
    {
      "epoch": 0.33050415654880216,
      "grad_norm": 0.169921875,
      "learning_rate": 1.4453075459733672e-05,
      "loss": 0.0179,
      "step": 4500
    },
    {
      "epoch": 0.33784869336099776,
      "grad_norm": 0.12158203125,
      "learning_rate": 1.4294546607482563e-05,
      "loss": 0.0192,
      "step": 4600
    },
    {
      "epoch": 0.34519323017319337,
      "grad_norm": 0.134765625,
      "learning_rate": 1.4136017755231453e-05,
      "loss": 0.0178,
      "step": 4700
    },
    {
      "epoch": 0.35253776698538897,
      "grad_norm": 0.2099609375,
      "learning_rate": 1.3977488902980343e-05,
      "loss": 0.0184,
      "step": 4800
    },
    {
      "epoch": 0.35988230379758457,
      "grad_norm": 0.16015625,
      "learning_rate": 1.3818960050729233e-05,
      "loss": 0.0167,
      "step": 4900
    },
    {
      "epoch": 0.36722684060978017,
      "grad_norm": 0.171875,
      "learning_rate": 1.3660431198478124e-05,
      "loss": 0.0171,
      "step": 5000
    },
    {
      "epoch": 0.36722684060978017,
      "eval_loss": 0.21267807483673096,
      "eval_runtime": 5084.9884,
      "eval_samples_per_second": 3.578,
      "eval_steps_per_second": 1.789,
      "step": 5000
    },
    {
      "epoch": 0.37457137742197577,
      "grad_norm": 0.353515625,
      "learning_rate": 1.3501902346227013e-05,
      "loss": 0.017,
      "step": 5100
    },
    {
      "epoch": 0.38191591423417137,
      "grad_norm": 0.12109375,
      "learning_rate": 1.3343373493975904e-05,
      "loss": 0.0191,
      "step": 5200
    },
    {
      "epoch": 0.389260451046367,
      "grad_norm": 0.232421875,
      "learning_rate": 1.3184844641724795e-05,
      "loss": 0.018,
      "step": 5300
    },
    {
      "epoch": 0.3966049878585626,
      "grad_norm": 0.1435546875,
      "learning_rate": 1.3026315789473684e-05,
      "loss": 0.0185,
      "step": 5400
    },
    {
      "epoch": 0.4039495246707582,
      "grad_norm": 0.1318359375,
      "learning_rate": 1.2867786937222575e-05,
      "loss": 0.0178,
      "step": 5500
    },
    {
      "epoch": 0.4112940614829538,
      "grad_norm": 0.1572265625,
      "learning_rate": 1.2709258084971466e-05,
      "loss": 0.0169,
      "step": 5600
    },
    {
      "epoch": 0.4186385982951494,
      "grad_norm": 0.21484375,
      "learning_rate": 1.2550729232720355e-05,
      "loss": 0.0167,
      "step": 5700
    },
    {
      "epoch": 0.425983135107345,
      "grad_norm": 0.1416015625,
      "learning_rate": 1.2392200380469246e-05,
      "loss": 0.0171,
      "step": 5800
    },
    {
      "epoch": 0.4333276719195406,
      "grad_norm": 0.232421875,
      "learning_rate": 1.2233671528218137e-05,
      "loss": 0.0173,
      "step": 5900
    },
    {
      "epoch": 0.4406722087317362,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.2075142675967026e-05,
      "loss": 0.0169,
      "step": 6000
    },
    {
      "epoch": 0.4406722087317362,
      "eval_loss": 0.21243031322956085,
      "eval_runtime": 5083.7144,
      "eval_samples_per_second": 3.579,
      "eval_steps_per_second": 1.79,
      "step": 6000
    },
    {
      "epoch": 0.4480167455439318,
      "grad_norm": 0.181640625,
      "learning_rate": 1.1916613823715917e-05,
      "loss": 0.0171,
      "step": 6100
    },
    {
      "epoch": 0.4553612823561274,
      "grad_norm": 0.134765625,
      "learning_rate": 1.1758084971464808e-05,
      "loss": 0.0171,
      "step": 6200
    },
    {
      "epoch": 0.46270581916832304,
      "grad_norm": 0.06689453125,
      "learning_rate": 1.1599556119213697e-05,
      "loss": 0.0174,
      "step": 6300
    },
    {
      "epoch": 0.47005035598051864,
      "grad_norm": 0.1328125,
      "learning_rate": 1.1441027266962588e-05,
      "loss": 0.0163,
      "step": 6400
    },
    {
      "epoch": 0.47739489279271424,
      "grad_norm": 0.1787109375,
      "learning_rate": 1.1282498414711478e-05,
      "loss": 0.0162,
      "step": 6500
    },
    {
      "epoch": 0.48473942960490984,
      "grad_norm": 0.1708984375,
      "learning_rate": 1.1123969562460368e-05,
      "loss": 0.0187,
      "step": 6600
    },
    {
      "epoch": 0.49208396641710545,
      "grad_norm": 0.1787109375,
      "learning_rate": 1.0965440710209258e-05,
      "loss": 0.0189,
      "step": 6700
    },
    {
      "epoch": 0.49942850322930105,
      "grad_norm": 0.2734375,
      "learning_rate": 1.080691185795815e-05,
      "loss": 0.0178,
      "step": 6800
    },
    {
      "epoch": 0.5067730400414966,
      "grad_norm": 0.1044921875,
      "learning_rate": 1.0648383005707038e-05,
      "loss": 0.0164,
      "step": 6900
    },
    {
      "epoch": 0.5141175768536922,
      "grad_norm": 0.1875,
      "learning_rate": 1.048985415345593e-05,
      "loss": 0.0188,
      "step": 7000
    },
    {
      "epoch": 0.5141175768536922,
      "eval_loss": 0.21181385219097137,
      "eval_runtime": 5094.3602,
      "eval_samples_per_second": 3.572,
      "eval_steps_per_second": 1.786,
      "step": 7000
    },
    {
      "epoch": 0.5214621136658878,
      "grad_norm": 0.16796875,
      "learning_rate": 1.033132530120482e-05,
      "loss": 0.0174,
      "step": 7100
    },
    {
      "epoch": 0.5288066504780834,
      "grad_norm": 0.1640625,
      "learning_rate": 1.0172796448953711e-05,
      "loss": 0.0167,
      "step": 7200
    },
    {
      "epoch": 0.536151187290279,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.00142675967026e-05,
      "loss": 0.0157,
      "step": 7300
    },
    {
      "epoch": 0.5434957241024746,
      "grad_norm": 0.1357421875,
      "learning_rate": 9.855738744451491e-06,
      "loss": 0.0172,
      "step": 7400
    },
    {
      "epoch": 0.5508402609146702,
      "grad_norm": 0.1669921875,
      "learning_rate": 9.697209892200382e-06,
      "loss": 0.0178,
      "step": 7500
    },
    {
      "epoch": 0.5581847977268659,
      "grad_norm": 0.1435546875,
      "learning_rate": 9.538681039949271e-06,
      "loss": 0.016,
      "step": 7600
    },
    {
      "epoch": 0.5655293345390615,
      "grad_norm": 0.1259765625,
      "learning_rate": 9.380152187698162e-06,
      "loss": 0.0173,
      "step": 7700
    },
    {
      "epoch": 0.5728738713512571,
      "grad_norm": 0.1923828125,
      "learning_rate": 9.221623335447053e-06,
      "loss": 0.0177,
      "step": 7800
    },
    {
      "epoch": 0.5802184081634527,
      "grad_norm": 0.1494140625,
      "learning_rate": 9.063094483195942e-06,
      "loss": 0.0173,
      "step": 7900
    },
    {
      "epoch": 0.5875629449756483,
      "grad_norm": 0.1484375,
      "learning_rate": 8.904565630944833e-06,
      "loss": 0.017,
      "step": 8000
    },
    {
      "epoch": 0.5875629449756483,
      "eval_loss": 0.2121034562587738,
      "eval_runtime": 5101.0988,
      "eval_samples_per_second": 3.567,
      "eval_steps_per_second": 1.784,
      "step": 8000
    },
    {
      "epoch": 0.5949074817878439,
      "grad_norm": 0.1494140625,
      "learning_rate": 8.746036778693723e-06,
      "loss": 0.0173,
      "step": 8100
    },
    {
      "epoch": 0.6022520186000395,
      "grad_norm": 0.119140625,
      "learning_rate": 8.587507926442613e-06,
      "loss": 0.0176,
      "step": 8200
    },
    {
      "epoch": 0.6095965554122351,
      "grad_norm": 0.1982421875,
      "learning_rate": 8.428979074191503e-06,
      "loss": 0.0179,
      "step": 8300
    },
    {
      "epoch": 0.6169410922244307,
      "grad_norm": 0.1279296875,
      "learning_rate": 8.270450221940394e-06,
      "loss": 0.0166,
      "step": 8400
    },
    {
      "epoch": 0.6242856290366263,
      "grad_norm": 0.1005859375,
      "learning_rate": 8.111921369689283e-06,
      "loss": 0.0164,
      "step": 8500
    },
    {
      "epoch": 0.6316301658488219,
      "grad_norm": 0.1474609375,
      "learning_rate": 7.953392517438174e-06,
      "loss": 0.018,
      "step": 8600
    },
    {
      "epoch": 0.6389747026610175,
      "grad_norm": 0.162109375,
      "learning_rate": 7.794863665187065e-06,
      "loss": 0.017,
      "step": 8700
    },
    {
      "epoch": 0.6463192394732131,
      "grad_norm": 0.1416015625,
      "learning_rate": 7.636334812935954e-06,
      "loss": 0.0178,
      "step": 8800
    },
    {
      "epoch": 0.6536637762854087,
      "grad_norm": 0.2265625,
      "learning_rate": 7.477805960684845e-06,
      "loss": 0.0174,
      "step": 8900
    },
    {
      "epoch": 0.6610083130976043,
      "grad_norm": 0.109375,
      "learning_rate": 7.319277108433736e-06,
      "loss": 0.0172,
      "step": 9000
    },
    {
      "epoch": 0.6610083130976043,
      "eval_loss": 0.21184413135051727,
      "eval_runtime": 5098.1011,
      "eval_samples_per_second": 3.569,
      "eval_steps_per_second": 1.785,
      "step": 9000
    },
    {
      "epoch": 0.6683528499097999,
      "grad_norm": 0.236328125,
      "learning_rate": 7.160748256182626e-06,
      "loss": 0.0184,
      "step": 9100
    },
    {
      "epoch": 0.6756973867219955,
      "grad_norm": 0.166015625,
      "learning_rate": 7.002219403931516e-06,
      "loss": 0.0171,
      "step": 9200
    },
    {
      "epoch": 0.6830419235341911,
      "grad_norm": 0.1103515625,
      "learning_rate": 6.843690551680407e-06,
      "loss": 0.0157,
      "step": 9300
    },
    {
      "epoch": 0.6903864603463867,
      "grad_norm": 0.1806640625,
      "learning_rate": 6.685161699429297e-06,
      "loss": 0.0173,
      "step": 9400
    },
    {
      "epoch": 0.6977309971585823,
      "grad_norm": 0.2138671875,
      "learning_rate": 6.526632847178187e-06,
      "loss": 0.0174,
      "step": 9500
    },
    {
      "epoch": 0.7050755339707779,
      "grad_norm": 0.1396484375,
      "learning_rate": 6.3681039949270775e-06,
      "loss": 0.0171,
      "step": 9600
    },
    {
      "epoch": 0.7124200707829735,
      "grad_norm": 0.1259765625,
      "learning_rate": 6.2095751426759675e-06,
      "loss": 0.0178,
      "step": 9700
    },
    {
      "epoch": 0.7197646075951691,
      "grad_norm": 0.1396484375,
      "learning_rate": 6.051046290424858e-06,
      "loss": 0.017,
      "step": 9800
    },
    {
      "epoch": 0.7271091444073647,
      "grad_norm": 0.1943359375,
      "learning_rate": 5.892517438173748e-06,
      "loss": 0.0178,
      "step": 9900
    },
    {
      "epoch": 0.7344536812195603,
      "grad_norm": 0.142578125,
      "learning_rate": 5.733988585922638e-06,
      "loss": 0.0177,
      "step": 10000
    },
    {
      "epoch": 0.7344536812195603,
      "eval_loss": 0.21181750297546387,
      "eval_runtime": 5085.6428,
      "eval_samples_per_second": 3.578,
      "eval_steps_per_second": 1.789,
      "step": 10000
    },
    {
      "epoch": 0.7417982180317559,
      "grad_norm": 0.20703125,
      "learning_rate": 5.575459733671529e-06,
      "loss": 0.017,
      "step": 10100
    },
    {
      "epoch": 0.7491427548439515,
      "grad_norm": 0.205078125,
      "learning_rate": 5.416930881420419e-06,
      "loss": 0.0162,
      "step": 10200
    },
    {
      "epoch": 0.7564872916561471,
      "grad_norm": 0.1787109375,
      "learning_rate": 5.258402029169309e-06,
      "loss": 0.017,
      "step": 10300
    },
    {
      "epoch": 0.7638318284683427,
      "grad_norm": 0.1171875,
      "learning_rate": 5.0998731769182e-06,
      "loss": 0.017,
      "step": 10400
    },
    {
      "epoch": 0.7711763652805383,
      "grad_norm": 0.058349609375,
      "learning_rate": 4.94134432466709e-06,
      "loss": 0.0174,
      "step": 10500
    },
    {
      "epoch": 0.778520902092734,
      "grad_norm": 0.11767578125,
      "learning_rate": 4.78281547241598e-06,
      "loss": 0.0174,
      "step": 10600
    },
    {
      "epoch": 0.7858654389049295,
      "grad_norm": 0.12451171875,
      "learning_rate": 4.624286620164871e-06,
      "loss": 0.0186,
      "step": 10700
    },
    {
      "epoch": 0.7932099757171251,
      "grad_norm": 0.1533203125,
      "learning_rate": 4.465757767913761e-06,
      "loss": 0.0172,
      "step": 10800
    },
    {
      "epoch": 0.8005545125293207,
      "grad_norm": 0.181640625,
      "learning_rate": 4.307228915662651e-06,
      "loss": 0.0169,
      "step": 10900
    },
    {
      "epoch": 0.8078990493415164,
      "grad_norm": 0.1396484375,
      "learning_rate": 4.148700063411541e-06,
      "loss": 0.0177,
      "step": 11000
    },
    {
      "epoch": 0.8078990493415164,
      "eval_loss": 0.21184377372264862,
      "eval_runtime": 5085.8047,
      "eval_samples_per_second": 3.578,
      "eval_steps_per_second": 1.789,
      "step": 11000
    },
    {
      "epoch": 0.815243586153712,
      "grad_norm": 0.09716796875,
      "learning_rate": 3.990171211160432e-06,
      "loss": 0.0172,
      "step": 11100
    },
    {
      "epoch": 0.8225881229659076,
      "grad_norm": 0.1923828125,
      "learning_rate": 3.831642358909322e-06,
      "loss": 0.018,
      "step": 11200
    },
    {
      "epoch": 0.8299326597781032,
      "grad_norm": 0.09326171875,
      "learning_rate": 3.673113506658212e-06,
      "loss": 0.0173,
      "step": 11300
    },
    {
      "epoch": 0.8372771965902988,
      "grad_norm": 0.1484375,
      "learning_rate": 3.514584654407102e-06,
      "loss": 0.0184,
      "step": 11400
    },
    {
      "epoch": 0.8446217334024944,
      "grad_norm": 0.244140625,
      "learning_rate": 3.3560558021559925e-06,
      "loss": 0.0168,
      "step": 11500
    },
    {
      "epoch": 0.85196627021469,
      "grad_norm": 0.126953125,
      "learning_rate": 3.197526949904883e-06,
      "loss": 0.0198,
      "step": 11600
    },
    {
      "epoch": 0.8593108070268856,
      "grad_norm": 0.30078125,
      "learning_rate": 3.038998097653773e-06,
      "loss": 0.0179,
      "step": 11700
    },
    {
      "epoch": 0.8666553438390812,
      "grad_norm": 0.2373046875,
      "learning_rate": 2.8804692454026633e-06,
      "loss": 0.0166,
      "step": 11800
    },
    {
      "epoch": 0.8739998806512768,
      "grad_norm": 0.177734375,
      "learning_rate": 2.7219403931515537e-06,
      "loss": 0.0166,
      "step": 11900
    },
    {
      "epoch": 0.8813444174634724,
      "grad_norm": 0.1953125,
      "learning_rate": 2.563411540900444e-06,
      "loss": 0.0163,
      "step": 12000
    },
    {
      "epoch": 0.8813444174634724,
      "eval_loss": 0.21183837950229645,
      "eval_runtime": 5098.0372,
      "eval_samples_per_second": 3.569,
      "eval_steps_per_second": 1.785,
      "step": 12000
    },
    {
      "epoch": 0.888688954275668,
      "grad_norm": 0.142578125,
      "learning_rate": 2.404882688649334e-06,
      "loss": 0.0179,
      "step": 12100
    },
    {
      "epoch": 0.8960334910878636,
      "grad_norm": 0.109375,
      "learning_rate": 2.2463538363982245e-06,
      "loss": 0.0171,
      "step": 12200
    },
    {
      "epoch": 0.9033780279000592,
      "grad_norm": 0.1513671875,
      "learning_rate": 2.087824984147115e-06,
      "loss": 0.0167,
      "step": 12300
    },
    {
      "epoch": 0.9107225647122548,
      "grad_norm": 0.17578125,
      "learning_rate": 1.9292961318960054e-06,
      "loss": 0.0177,
      "step": 12400
    },
    {
      "epoch": 0.9180671015244504,
      "grad_norm": 0.1904296875,
      "learning_rate": 1.7707672796448956e-06,
      "loss": 0.0174,
      "step": 12500
    },
    {
      "epoch": 0.9254116383366461,
      "grad_norm": 0.10009765625,
      "learning_rate": 1.6122384273937858e-06,
      "loss": 0.0173,
      "step": 12600
    },
    {
      "epoch": 0.9327561751488417,
      "grad_norm": 0.1337890625,
      "learning_rate": 1.453709575142676e-06,
      "loss": 0.017,
      "step": 12700
    },
    {
      "epoch": 0.9401007119610373,
      "grad_norm": 0.07080078125,
      "learning_rate": 1.2951807228915664e-06,
      "loss": 0.0173,
      "step": 12800
    },
    {
      "epoch": 0.9474452487732329,
      "grad_norm": 0.0830078125,
      "learning_rate": 1.1366518706404566e-06,
      "loss": 0.0187,
      "step": 12900
    },
    {
      "epoch": 0.9547897855854285,
      "grad_norm": 0.12890625,
      "learning_rate": 9.78123018389347e-07,
      "loss": 0.0177,
      "step": 13000
    },
    {
      "epoch": 0.9547897855854285,
      "eval_loss": 0.21184059977531433,
      "eval_runtime": 5091.2698,
      "eval_samples_per_second": 3.574,
      "eval_steps_per_second": 1.787,
      "step": 13000
    },
    {
      "epoch": 0.9621343223976241,
      "grad_norm": 0.1962890625,
      "learning_rate": 8.195941661382373e-07,
      "loss": 0.0175,
      "step": 13100
    },
    {
      "epoch": 0.9694788592098197,
      "grad_norm": 0.1806640625,
      "learning_rate": 6.610653138871275e-07,
      "loss": 0.017,
      "step": 13200
    },
    {
      "epoch": 0.9768233960220153,
      "grad_norm": 0.125,
      "learning_rate": 5.025364616360178e-07,
      "loss": 0.0174,
      "step": 13300
    },
    {
      "epoch": 0.9841679328342109,
      "grad_norm": 0.177734375,
      "learning_rate": 3.440076093849081e-07,
      "loss": 0.0157,
      "step": 13400
    },
    {
      "epoch": 0.9915124696464065,
      "grad_norm": 0.13671875,
      "learning_rate": 1.8547875713379836e-07,
      "loss": 0.018,
      "step": 13500
    },
    {
      "epoch": 0.9988570064586021,
      "grad_norm": 0.1533203125,
      "learning_rate": 2.6949904882688653e-08,
      "loss": 0.0177,
      "step": 13600
    }
  ],
  "logging_steps": 100,
  "max_steps": 13616,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.58162749078908e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}