{
  "best_global_step": 52000,
  "best_metric": 0.9908199660129274,
  "best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-52000",
  "epoch": 2.048,
  "eval_steps": 4000,
  "global_step": 64000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 1.3923053741455078,
      "learning_rate": 3.96e-06,
      "loss": 0.685,
      "step": 100
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.665050983428955,
      "learning_rate": 7.960000000000002e-06,
      "loss": 0.6654,
      "step": 200
    },
    {
      "epoch": 0.0096,
      "grad_norm": 3.1655123233795166,
      "learning_rate": 1.196e-05,
      "loss": 0.6169,
      "step": 300
    },
    {
      "epoch": 0.0128,
      "grad_norm": 3.3807435035705566,
      "learning_rate": 1.5960000000000003e-05,
      "loss": 0.4635,
      "step": 400
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.7963143587112427,
      "learning_rate": 1.9960000000000002e-05,
      "loss": 0.2886,
      "step": 500
    },
    {
      "epoch": 0.0192,
      "grad_norm": 1.5362155437469482,
      "learning_rate": 1.9987287319422154e-05,
      "loss": 0.2605,
      "step": 600
    },
    {
      "epoch": 0.0224,
      "grad_norm": 3.649484395980835,
      "learning_rate": 1.9974446227929375e-05,
      "loss": 0.2194,
      "step": 700
    },
    {
      "epoch": 0.0256,
      "grad_norm": 1.402876377105713,
      "learning_rate": 1.99616051364366e-05,
      "loss": 0.2367,
      "step": 800
    },
    {
      "epoch": 0.0288,
      "grad_norm": 2.708932399749756,
      "learning_rate": 1.994876404494382e-05,
      "loss": 0.2061,
      "step": 900
    },
    {
      "epoch": 0.032,
      "grad_norm": 2.4827463626861572,
      "learning_rate": 1.9935922953451046e-05,
      "loss": 0.1892,
      "step": 1000
    },
    {
      "epoch": 0.0352,
      "grad_norm": 0.9402571320533752,
      "learning_rate": 1.9923081861958268e-05,
      "loss": 0.1819,
      "step": 1100
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.8088085055351257,
      "learning_rate": 1.9910240770465493e-05,
      "loss": 0.1894,
      "step": 1200
    },
    {
      "epoch": 0.0416,
      "grad_norm": 2.8913955688476562,
      "learning_rate": 1.9897399678972714e-05,
      "loss": 0.1733,
      "step": 1300
    },
    {
      "epoch": 0.0448,
      "grad_norm": 1.9755029678344727,
      "learning_rate": 1.988455858747994e-05,
      "loss": 0.1748,
      "step": 1400
    },
    {
      "epoch": 0.048,
      "grad_norm": 2.659393310546875,
      "learning_rate": 1.987171749598716e-05,
      "loss": 0.1557,
      "step": 1500
    },
    {
      "epoch": 0.0512,
      "grad_norm": 10.118029594421387,
      "learning_rate": 1.9858876404494382e-05,
      "loss": 0.1702,
      "step": 1600
    },
    {
      "epoch": 0.0544,
      "grad_norm": 3.736616373062134,
      "learning_rate": 1.9846035313001607e-05,
      "loss": 0.1694,
      "step": 1700
    },
    {
      "epoch": 0.0576,
      "grad_norm": 4.140033721923828,
      "learning_rate": 1.9833194221508828e-05,
      "loss": 0.1615,
      "step": 1800
    },
    {
      "epoch": 0.0608,
      "grad_norm": 4.504345893859863,
      "learning_rate": 1.9820353130016053e-05,
      "loss": 0.1425,
      "step": 1900
    },
    {
      "epoch": 0.064,
      "grad_norm": 5.786899089813232,
      "learning_rate": 1.9807512038523274e-05,
      "loss": 0.1588,
      "step": 2000
    },
    {
      "epoch": 0.0672,
      "grad_norm": 9.956130027770996,
      "learning_rate": 1.97946709470305e-05,
      "loss": 0.1399,
      "step": 2100
    },
    {
      "epoch": 0.0704,
      "grad_norm": 11.86201286315918,
      "learning_rate": 1.978182985553772e-05,
      "loss": 0.173,
      "step": 2200
    },
    {
      "epoch": 0.0736,
      "grad_norm": 0.6308254599571228,
      "learning_rate": 1.9768988764044946e-05,
      "loss": 0.1428,
      "step": 2300
    },
    {
      "epoch": 0.0768,
      "grad_norm": 3.123718023300171,
      "learning_rate": 1.9756147672552167e-05,
      "loss": 0.1365,
      "step": 2400
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.8000500202178955,
      "learning_rate": 1.9743306581059392e-05,
      "loss": 0.1528,
      "step": 2500
    },
    {
      "epoch": 0.0832,
      "grad_norm": 2.9149184226989746,
      "learning_rate": 1.9730465489566613e-05,
      "loss": 0.1568,
      "step": 2600
    },
    {
      "epoch": 0.0864,
      "grad_norm": 8.345555305480957,
      "learning_rate": 1.9717624398073838e-05,
      "loss": 0.139,
      "step": 2700
    },
    {
      "epoch": 0.0896,
      "grad_norm": 1.785736322402954,
      "learning_rate": 1.970478330658106e-05,
      "loss": 0.1509,
      "step": 2800
    },
    {
      "epoch": 0.0928,
      "grad_norm": 5.256857872009277,
      "learning_rate": 1.9691942215088284e-05,
      "loss": 0.1284,
      "step": 2900
    },
    {
      "epoch": 0.096,
      "grad_norm": 2.305225133895874,
      "learning_rate": 1.967910112359551e-05,
      "loss": 0.1249,
      "step": 3000
    },
    {
      "epoch": 0.0992,
      "grad_norm": 1.1149404048919678,
      "learning_rate": 1.966626003210273e-05,
      "loss": 0.1223,
      "step": 3100
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.24498392641544342,
      "learning_rate": 1.9653418940609955e-05,
      "loss": 0.1415,
      "step": 3200
    },
    {
      "epoch": 0.1056,
      "grad_norm": 3.027209520339966,
      "learning_rate": 1.9640577849117177e-05,
      "loss": 0.133,
      "step": 3300
    },
    {
      "epoch": 0.1088,
      "grad_norm": 10.783885955810547,
      "learning_rate": 1.9627736757624402e-05,
      "loss": 0.1309,
      "step": 3400
    },
    {
      "epoch": 0.112,
      "grad_norm": 7.116244316101074,
      "learning_rate": 1.9614895666131623e-05,
      "loss": 0.1056,
      "step": 3500
    },
    {
      "epoch": 0.1152,
      "grad_norm": 8.193492889404297,
      "learning_rate": 1.9602054574638848e-05,
      "loss": 0.1201,
      "step": 3600
    },
    {
      "epoch": 0.1184,
      "grad_norm": 0.9174596071243286,
      "learning_rate": 1.958921348314607e-05,
      "loss": 0.12,
      "step": 3700
    },
    {
      "epoch": 0.1216,
      "grad_norm": 3.436502695083618,
      "learning_rate": 1.957637239165329e-05,
      "loss": 0.1257,
      "step": 3800
    },
    {
      "epoch": 0.1248,
      "grad_norm": 9.131117820739746,
      "learning_rate": 1.9563531300160516e-05,
      "loss": 0.1139,
      "step": 3900
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.3150777518749237,
      "learning_rate": 1.9550690208667737e-05,
      "loss": 0.1381,
      "step": 4000
    },
    {
      "epoch": 0.128,
      "eval_accuracy": 0.9586,
      "eval_f1": 0.9586218246722099,
      "eval_loss": 0.1626722663640976,
      "eval_precision": 0.9598553600795934,
      "eval_recall": 0.9586,
      "eval_runtime": 815.7025,
      "eval_samples_per_second": 122.594,
      "eval_steps_per_second": 7.662,
      "step": 4000
    },
    {
      "epoch": 0.1312,
      "grad_norm": 8.65023422241211,
      "learning_rate": 1.9537849117174962e-05,
      "loss": 0.1026,
      "step": 4100
    },
    {
      "epoch": 0.1344,
      "grad_norm": 8.46996784210205,
      "learning_rate": 1.9525008025682183e-05,
      "loss": 0.1251,
      "step": 4200
    },
    {
      "epoch": 0.1376,
      "grad_norm": 6.439260959625244,
      "learning_rate": 1.9512166934189408e-05,
      "loss": 0.1338,
      "step": 4300
    },
    {
      "epoch": 0.1408,
      "grad_norm": 1.012399435043335,
      "learning_rate": 1.949932584269663e-05,
      "loss": 0.1164,
      "step": 4400
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.33647093176841736,
      "learning_rate": 1.9486484751203855e-05,
      "loss": 0.1156,
      "step": 4500
    },
    {
      "epoch": 0.1472,
      "grad_norm": 7.39678955078125,
      "learning_rate": 1.9473643659711076e-05,
      "loss": 0.1013,
      "step": 4600
    },
    {
      "epoch": 0.1504,
      "grad_norm": 4.556000709533691,
      "learning_rate": 1.94608025682183e-05,
      "loss": 0.1038,
      "step": 4700
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.5087370276451111,
      "learning_rate": 1.9447961476725522e-05,
      "loss": 0.1319,
      "step": 4800
    },
    {
      "epoch": 0.1568,
      "grad_norm": 4.385759353637695,
      "learning_rate": 1.9435120385232747e-05,
      "loss": 0.1229,
      "step": 4900
    },
    {
      "epoch": 0.16,
      "grad_norm": 5.46568489074707,
      "learning_rate": 1.942227929373997e-05,
      "loss": 0.1234,
      "step": 5000
    },
    {
      "epoch": 0.1632,
      "grad_norm": 3.3565216064453125,
      "learning_rate": 1.9409438202247193e-05,
      "loss": 0.1007,
      "step": 5100
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.17969129979610443,
      "learning_rate": 1.9396597110754415e-05,
      "loss": 0.108,
      "step": 5200
    },
    {
      "epoch": 0.1696,
      "grad_norm": 8.49416732788086,
      "learning_rate": 1.938375601926164e-05,
      "loss": 0.1105,
      "step": 5300
    },
    {
      "epoch": 0.1728,
      "grad_norm": 6.072606086730957,
      "learning_rate": 1.937091492776886e-05,
      "loss": 0.1082,
      "step": 5400
    },
    {
      "epoch": 0.176,
      "grad_norm": 1.2361280918121338,
      "learning_rate": 1.9358073836276086e-05,
      "loss": 0.0966,
      "step": 5500
    },
    {
      "epoch": 0.1792,
      "grad_norm": 6.232377052307129,
      "learning_rate": 1.9345232744783307e-05,
      "loss": 0.1151,
      "step": 5600
    },
    {
      "epoch": 0.1824,
      "grad_norm": 0.6630802154541016,
      "learning_rate": 1.9332391653290532e-05,
      "loss": 0.104,
      "step": 5700
    },
    {
      "epoch": 0.1856,
      "grad_norm": 0.2744814157485962,
      "learning_rate": 1.9319550561797754e-05,
      "loss": 0.104,
      "step": 5800
    },
    {
      "epoch": 0.1888,
      "grad_norm": 0.37808698415756226,
      "learning_rate": 1.930670947030498e-05,
      "loss": 0.1183,
      "step": 5900
    },
    {
      "epoch": 0.192,
      "grad_norm": 11.47230052947998,
      "learning_rate": 1.9293868378812203e-05,
      "loss": 0.1258,
      "step": 6000
    },
    {
      "epoch": 0.1952,
      "grad_norm": 7.168028354644775,
      "learning_rate": 1.928102728731942e-05,
      "loss": 0.1117,
      "step": 6100
    },
    {
      "epoch": 0.1984,
      "grad_norm": 0.11318526417016983,
      "learning_rate": 1.9268186195826646e-05,
      "loss": 0.1004,
      "step": 6200
    },
    {
      "epoch": 0.2016,
      "grad_norm": 9.405433654785156,
      "learning_rate": 1.9255345104333868e-05,
      "loss": 0.1195,
      "step": 6300
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.507453978061676,
      "learning_rate": 1.9242504012841092e-05,
      "loss": 0.0987,
      "step": 6400
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.15791097283363342,
      "learning_rate": 1.9229662921348314e-05,
      "loss": 0.1156,
      "step": 6500
    },
    {
      "epoch": 0.2112,
      "grad_norm": 5.216452121734619,
      "learning_rate": 1.921682182985554e-05,
      "loss": 0.1375,
      "step": 6600
    },
    {
      "epoch": 0.2144,
      "grad_norm": 0.6168243885040283,
      "learning_rate": 1.9203980738362764e-05,
      "loss": 0.1086,
      "step": 6700
    },
    {
      "epoch": 0.2176,
      "grad_norm": 2.949383497238159,
      "learning_rate": 1.9191139646869985e-05,
      "loss": 0.0957,
      "step": 6800
    },
    {
      "epoch": 0.2208,
      "grad_norm": 9.519874572753906,
      "learning_rate": 1.917829855537721e-05,
      "loss": 0.0935,
      "step": 6900
    },
    {
      "epoch": 0.224,
      "grad_norm": 7.931914329528809,
      "learning_rate": 1.916545746388443e-05,
      "loss": 0.1335,
      "step": 7000
    },
    {
      "epoch": 0.2272,
      "grad_norm": 8.498374938964844,
      "learning_rate": 1.9152616372391656e-05,
      "loss": 0.1025,
      "step": 7100
    },
    {
      "epoch": 0.2304,
      "grad_norm": 5.054536819458008,
      "learning_rate": 1.9139775280898878e-05,
      "loss": 0.1165,
      "step": 7200
    },
    {
      "epoch": 0.2336,
      "grad_norm": 0.17365020513534546,
      "learning_rate": 1.9126934189406102e-05,
      "loss": 0.0996,
      "step": 7300
    },
    {
      "epoch": 0.2368,
      "grad_norm": 2.247058629989624,
      "learning_rate": 1.9114093097913324e-05,
      "loss": 0.1009,
      "step": 7400
    },
    {
      "epoch": 0.24,
      "grad_norm": 15.367574691772461,
      "learning_rate": 1.910125200642055e-05,
      "loss": 0.1082,
      "step": 7500
    },
    {
      "epoch": 0.2432,
      "grad_norm": 6.72482967376709,
      "learning_rate": 1.908841091492777e-05,
      "loss": 0.1308,
      "step": 7600
    },
    {
      "epoch": 0.2464,
      "grad_norm": 0.051803406327962875,
      "learning_rate": 1.9075569823434995e-05,
      "loss": 0.1031,
      "step": 7700
    },
    {
      "epoch": 0.2496,
      "grad_norm": 9.355685234069824,
      "learning_rate": 1.9062728731942216e-05,
      "loss": 0.1012,
      "step": 7800
    },
    {
      "epoch": 0.2528,
      "grad_norm": 2.047060012817383,
      "learning_rate": 1.904988764044944e-05,
      "loss": 0.1249,
      "step": 7900
    },
    {
      "epoch": 0.256,
      "grad_norm": 4.134668350219727,
      "learning_rate": 1.9037046548956663e-05,
      "loss": 0.0821,
      "step": 8000
    },
    {
      "epoch": 0.256,
      "eval_accuracy": 0.97609,
      "eval_f1": 0.9760920422665103,
      "eval_loss": 0.10814645141363144,
      "eval_precision": 0.9761013685233434,
      "eval_recall": 0.97609,
      "eval_runtime": 817.6077,
      "eval_samples_per_second": 122.308,
      "eval_steps_per_second": 7.644,
      "step": 8000
    },
    {
      "epoch": 0.2592,
      "grad_norm": 6.723151206970215,
      "learning_rate": 1.9024205457463887e-05,
      "loss": 0.0799,
      "step": 8100
    },
    {
      "epoch": 0.2624,
      "grad_norm": 1.805972933769226,
      "learning_rate": 1.901136436597111e-05,
      "loss": 0.1211,
      "step": 8200
    },
    {
      "epoch": 0.2656,
      "grad_norm": 11.118502616882324,
      "learning_rate": 1.8998523274478334e-05,
      "loss": 0.0916,
      "step": 8300
    },
    {
      "epoch": 0.2688,
      "grad_norm": 2.3953633308410645,
      "learning_rate": 1.8985682182985555e-05,
      "loss": 0.0878,
      "step": 8400
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.10008874535560608,
      "learning_rate": 1.8972841091492777e-05,
      "loss": 0.0868,
      "step": 8500
    },
    {
      "epoch": 0.2752,
      "grad_norm": 0.06934285163879395,
      "learning_rate": 1.896e-05,
      "loss": 0.1155,
      "step": 8600
    },
    {
      "epoch": 0.2784,
      "grad_norm": 0.3781879246234894,
      "learning_rate": 1.8947158908507223e-05,
      "loss": 0.0988,
      "step": 8700
    },
    {
      "epoch": 0.2816,
      "grad_norm": 9.6624174118042,
      "learning_rate": 1.8934317817014448e-05,
      "loss": 0.1072,
      "step": 8800
    },
    {
      "epoch": 0.2848,
      "grad_norm": 0.09044591337442398,
      "learning_rate": 1.892147672552167e-05,
      "loss": 0.1085,
      "step": 8900
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.0671633929014206,
      "learning_rate": 1.8908635634028894e-05,
      "loss": 0.1081,
      "step": 9000
    },
    {
      "epoch": 0.2912,
      "grad_norm": 8.130873680114746,
      "learning_rate": 1.8895794542536115e-05,
      "loss": 0.0968,
      "step": 9100
    },
    {
      "epoch": 0.2944,
      "grad_norm": 1.2537904977798462,
      "learning_rate": 1.888295345104334e-05,
      "loss": 0.0877,
      "step": 9200
    },
    {
      "epoch": 0.2976,
      "grad_norm": 6.084417819976807,
      "learning_rate": 1.887011235955056e-05,
      "loss": 0.1022,
      "step": 9300
    },
    {
      "epoch": 0.3008,
      "grad_norm": 6.140512943267822,
      "learning_rate": 1.8857271268057787e-05,
      "loss": 0.1016,
      "step": 9400
    },
    {
      "epoch": 0.304,
      "grad_norm": 1.7347182035446167,
      "learning_rate": 1.8844430176565008e-05,
      "loss": 0.092,
      "step": 9500
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.6796423196792603,
      "learning_rate": 1.8831589085072233e-05,
      "loss": 0.1172,
      "step": 9600
    },
    {
      "epoch": 0.3104,
      "grad_norm": 10.664779663085938,
      "learning_rate": 1.8818747993579454e-05,
      "loss": 0.0808,
      "step": 9700
    },
    {
      "epoch": 0.3136,
      "grad_norm": 0.4076235294342041,
      "learning_rate": 1.880590690208668e-05,
      "loss": 0.0836,
      "step": 9800
    },
    {
      "epoch": 0.3168,
      "grad_norm": 9.418440818786621,
      "learning_rate": 1.8793065810593904e-05,
      "loss": 0.0675,
      "step": 9900
    },
    {
      "epoch": 0.32,
      "grad_norm": 9.2078857421875,
      "learning_rate": 1.8780224719101125e-05,
      "loss": 0.0686,
      "step": 10000
    },
    {
      "epoch": 0.3232,
      "grad_norm": 0.47173646092414856,
      "learning_rate": 1.876738362760835e-05,
      "loss": 0.1096,
      "step": 10100
    },
    {
      "epoch": 0.3264,
      "grad_norm": 4.5297322273254395,
      "learning_rate": 1.875454253611557e-05,
      "loss": 0.098,
      "step": 10200
    },
    {
      "epoch": 0.3296,
      "grad_norm": 5.099269866943359,
      "learning_rate": 1.8741701444622796e-05,
      "loss": 0.1063,
      "step": 10300
    },
    {
      "epoch": 0.3328,
      "grad_norm": 2.588848114013672,
      "learning_rate": 1.8728860353130018e-05,
      "loss": 0.0989,
      "step": 10400
    },
    {
      "epoch": 0.336,
      "grad_norm": 4.629786968231201,
      "learning_rate": 1.8716019261637243e-05,
      "loss": 0.1018,
      "step": 10500
    },
    {
      "epoch": 0.3392,
      "grad_norm": 11.187308311462402,
      "learning_rate": 1.8703178170144464e-05,
      "loss": 0.0864,
      "step": 10600
    },
    {
      "epoch": 0.3424,
      "grad_norm": 2.476482391357422,
      "learning_rate": 1.869033707865169e-05,
      "loss": 0.0744,
      "step": 10700
    },
    {
      "epoch": 0.3456,
      "grad_norm": 17.418149948120117,
      "learning_rate": 1.867749598715891e-05,
      "loss": 0.1189,
      "step": 10800
    },
    {
      "epoch": 0.3488,
      "grad_norm": 11.753310203552246,
      "learning_rate": 1.8664654895666132e-05,
      "loss": 0.0832,
      "step": 10900
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.41917338967323303,
      "learning_rate": 1.8651813804173357e-05,
      "loss": 0.1063,
      "step": 11000
    },
    {
      "epoch": 0.3552,
      "grad_norm": 14.072111129760742,
      "learning_rate": 1.8638972712680578e-05,
      "loss": 0.1061,
      "step": 11100
    },
    {
      "epoch": 0.3584,
      "grad_norm": 2.6141397953033447,
      "learning_rate": 1.8626131621187803e-05,
      "loss": 0.0934,
      "step": 11200
    },
    {
      "epoch": 0.3616,
      "grad_norm": 3.1363914012908936,
      "learning_rate": 1.8613290529695024e-05,
      "loss": 0.0879,
      "step": 11300
    },
    {
      "epoch": 0.3648,
      "grad_norm": 4.260811805725098,
      "learning_rate": 1.860044943820225e-05,
      "loss": 0.092,
      "step": 11400
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.2677570879459381,
      "learning_rate": 1.858760834670947e-05,
      "loss": 0.1202,
      "step": 11500
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.056061357259750366,
      "learning_rate": 1.8574767255216696e-05,
      "loss": 0.0773,
      "step": 11600
    },
    {
      "epoch": 0.3744,
      "grad_norm": 7.95279598236084,
      "learning_rate": 1.8561926163723917e-05,
      "loss": 0.0749,
      "step": 11700
    },
    {
      "epoch": 0.3776,
      "grad_norm": 7.4200873374938965,
      "learning_rate": 1.8549085072231142e-05,
      "loss": 0.1054,
      "step": 11800
    },
    {
      "epoch": 0.3808,
      "grad_norm": 0.8819625973701477,
      "learning_rate": 1.8536243980738363e-05,
      "loss": 0.0998,
      "step": 11900
    },
    {
      "epoch": 0.384,
      "grad_norm": 6.32806396484375,
      "learning_rate": 1.8523402889245588e-05,
      "loss": 0.0667,
      "step": 12000
    },
    {
      "epoch": 0.384,
      "eval_accuracy": 0.97856,
      "eval_f1": 0.97856556986665,
      "eval_loss": 0.1008467897772789,
      "eval_precision": 0.9786554480535211,
      "eval_recall": 0.97856,
      "eval_runtime": 822.182,
      "eval_samples_per_second": 121.628,
      "eval_steps_per_second": 7.602,
      "step": 12000
    },
    {
      "epoch": 0.3872,
      "grad_norm": 11.900330543518066,
      "learning_rate": 1.851056179775281e-05,
      "loss": 0.0958,
      "step": 12100
    },
    {
      "epoch": 0.3904,
      "grad_norm": 18.242124557495117,
      "learning_rate": 1.8497720706260034e-05,
      "loss": 0.075,
      "step": 12200
    },
    {
      "epoch": 0.3936,
      "grad_norm": 0.0790882408618927,
      "learning_rate": 1.8484879614767256e-05,
      "loss": 0.071,
      "step": 12300
    },
    {
      "epoch": 0.3968,
      "grad_norm": 16.233280181884766,
      "learning_rate": 1.847203852327448e-05,
      "loss": 0.1109,
      "step": 12400
    },
    {
      "epoch": 0.4,
      "grad_norm": 12.048758506774902,
      "learning_rate": 1.8459197431781702e-05,
      "loss": 0.0703,
      "step": 12500
    },
    {
      "epoch": 0.4032,
      "grad_norm": 9.086562156677246,
      "learning_rate": 1.8446356340288927e-05,
      "loss": 0.0706,
      "step": 12600
    },
    {
      "epoch": 0.4064,
      "grad_norm": 9.871477127075195,
      "learning_rate": 1.843351524879615e-05,
      "loss": 0.0745,
      "step": 12700
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.7136130928993225,
      "learning_rate": 1.8420674157303373e-05,
      "loss": 0.0544,
      "step": 12800
    },
    {
      "epoch": 0.4128,
      "grad_norm": 10.892882347106934,
      "learning_rate": 1.8407833065810598e-05,
      "loss": 0.1109,
      "step": 12900
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.3350844383239746,
      "learning_rate": 1.839499197431782e-05,
      "loss": 0.0898,
      "step": 13000
    },
    {
      "epoch": 0.4192,
      "grad_norm": 11.215353012084961,
      "learning_rate": 1.838215088282504e-05,
      "loss": 0.0963,
      "step": 13100
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.2309681475162506,
      "learning_rate": 1.8369309791332262e-05,
      "loss": 0.0785,
      "step": 13200
    },
    {
      "epoch": 0.4256,
      "grad_norm": 0.0822586640715599,
      "learning_rate": 1.8356468699839487e-05,
      "loss": 0.0736,
      "step": 13300
    },
    {
      "epoch": 0.4288,
      "grad_norm": 0.6296452283859253,
      "learning_rate": 1.834362760834671e-05,
      "loss": 0.1064,
      "step": 13400
    },
    {
      "epoch": 0.432,
      "grad_norm": 7.989764213562012,
      "learning_rate": 1.8330786516853933e-05,
      "loss": 0.0885,
      "step": 13500
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.04016461223363876,
      "learning_rate": 1.8317945425361158e-05,
      "loss": 0.0574,
      "step": 13600
    },
    {
      "epoch": 0.4384,
      "grad_norm": 0.03219222649931908,
      "learning_rate": 1.830510433386838e-05,
      "loss": 0.0742,
      "step": 13700
    },
    {
      "epoch": 0.4416,
      "grad_norm": 11.071674346923828,
      "learning_rate": 1.8292263242375605e-05,
      "loss": 0.0968,
      "step": 13800
    },
    {
      "epoch": 0.4448,
      "grad_norm": 22.920804977416992,
      "learning_rate": 1.8279422150882826e-05,
      "loss": 0.0782,
      "step": 13900
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.05693759024143219,
      "learning_rate": 1.826658105939005e-05,
      "loss": 0.0538,
      "step": 14000
    },
    {
      "epoch": 0.4512,
      "grad_norm": 0.08659256994724274,
      "learning_rate": 1.8253739967897272e-05,
      "loss": 0.0699,
      "step": 14100
    },
    {
      "epoch": 0.4544,
      "grad_norm": 3.1322948932647705,
      "learning_rate": 1.8240898876404497e-05,
      "loss": 0.0841,
      "step": 14200
    },
    {
      "epoch": 0.4576,
      "grad_norm": 0.025594089180231094,
      "learning_rate": 1.822805778491172e-05,
      "loss": 0.1108,
      "step": 14300
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.5694848299026489,
      "learning_rate": 1.8215216693418943e-05,
      "loss": 0.0705,
      "step": 14400
    },
    {
      "epoch": 0.464,
      "grad_norm": 5.643801212310791,
      "learning_rate": 1.8202375601926165e-05,
      "loss": 0.0773,
      "step": 14500
    },
    {
      "epoch": 0.4672,
      "grad_norm": 1.6325165033340454,
      "learning_rate": 1.818953451043339e-05,
      "loss": 0.1244,
      "step": 14600
    },
    {
      "epoch": 0.4704,
      "grad_norm": 0.04731294512748718,
      "learning_rate": 1.817669341894061e-05,
      "loss": 0.0523,
      "step": 14700
    },
    {
      "epoch": 0.4736,
      "grad_norm": 9.385772705078125,
      "learning_rate": 1.8163852327447836e-05,
      "loss": 0.0739,
      "step": 14800
    },
    {
      "epoch": 0.4768,
      "grad_norm": 0.04752274602651596,
      "learning_rate": 1.8151011235955057e-05,
      "loss": 0.0636,
      "step": 14900
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4523526430130005,
      "learning_rate": 1.8138170144462282e-05,
      "loss": 0.0907,
      "step": 15000
    },
    {
      "epoch": 0.4832,
      "grad_norm": 0.10660147666931152,
      "learning_rate": 1.8125329052969504e-05,
      "loss": 0.1093,
      "step": 15100
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.024508710950613022,
      "learning_rate": 1.811248796147673e-05,
      "loss": 0.0562,
      "step": 15200
    },
    {
      "epoch": 0.4896,
      "grad_norm": 4.832937240600586,
      "learning_rate": 1.809964686998395e-05,
      "loss": 0.0694,
      "step": 15300
    },
    {
      "epoch": 0.4928,
      "grad_norm": 12.76455020904541,
      "learning_rate": 1.808680577849117e-05,
      "loss": 0.0525,
      "step": 15400
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.244754359126091,
      "learning_rate": 1.8073964686998396e-05,
      "loss": 0.0632,
      "step": 15500
    },
    {
      "epoch": 0.4992,
      "grad_norm": 19.315397262573242,
      "learning_rate": 1.8061123595505618e-05,
      "loss": 0.0794,
      "step": 15600
    },
    {
      "epoch": 0.5024,
      "grad_norm": 0.05077612027525902,
      "learning_rate": 1.8048282504012842e-05,
      "loss": 0.0848,
      "step": 15700
    },
    {
      "epoch": 0.5056,
      "grad_norm": 0.33186858892440796,
      "learning_rate": 1.8035441412520064e-05,
      "loss": 0.0894,
      "step": 15800
    },
    {
      "epoch": 0.5088,
      "grad_norm": 0.26919984817504883,
      "learning_rate": 1.802260032102729e-05,
      "loss": 0.0801,
      "step": 15900
    },
    {
      "epoch": 0.512,
      "grad_norm": 3.566136121749878,
      "learning_rate": 1.800975922953451e-05,
      "loss": 0.0754,
      "step": 16000
    },
    {
      "epoch": 0.512,
      "eval_accuracy": 0.98201,
      "eval_f1": 0.9820134202589396,
      "eval_loss": 0.07791993767023087,
      "eval_precision": 0.9820579125315673,
      "eval_recall": 0.98201,
      "eval_runtime": 823.0886,
      "eval_samples_per_second": 121.494,
      "eval_steps_per_second": 7.593,
      "step": 16000
    },
    {
      "epoch": 0.5152,
      "grad_norm": 8.349530220031738,
      "learning_rate": 1.7996918138041735e-05,
      "loss": 0.0724,
      "step": 16100
    },
    {
      "epoch": 0.5184,
      "grad_norm": 0.05041235312819481,
      "learning_rate": 1.7984077046548956e-05,
      "loss": 0.0428,
      "step": 16200
    },
    {
      "epoch": 0.5216,
      "grad_norm": 0.3858475685119629,
      "learning_rate": 1.797123595505618e-05,
      "loss": 0.0569,
      "step": 16300
    },
    {
      "epoch": 0.5248,
      "grad_norm": 8.561657905578613,
      "learning_rate": 1.7958394863563403e-05,
      "loss": 0.0758,
      "step": 16400
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.025413183495402336,
      "learning_rate": 1.7945553772070628e-05,
      "loss": 0.0548,
      "step": 16500
    },
    {
      "epoch": 0.5312,
      "grad_norm": 0.010517638176679611,
      "learning_rate": 1.7932712680577852e-05,
      "loss": 0.0706,
      "step": 16600
    },
    {
      "epoch": 0.5344,
      "grad_norm": 0.08805025368928909,
      "learning_rate": 1.7919871589085074e-05,
      "loss": 0.077,
      "step": 16700
    },
    {
      "epoch": 0.5376,
      "grad_norm": 5.7931342124938965,
      "learning_rate": 1.79070304975923e-05,
      "loss": 0.0669,
      "step": 16800
    },
    {
      "epoch": 0.5408,
      "grad_norm": 0.07078564912080765,
      "learning_rate": 1.789418940609952e-05,
      "loss": 0.1069,
      "step": 16900
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.9886382818222046,
      "learning_rate": 1.7881348314606745e-05,
      "loss": 0.0501,
      "step": 17000
    },
    {
      "epoch": 0.5472,
      "grad_norm": 6.3300065994262695,
      "learning_rate": 1.7868507223113966e-05,
      "loss": 0.0744,
      "step": 17100
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.18114350736141205,
      "learning_rate": 1.785566613162119e-05,
      "loss": 0.0782,
      "step": 17200
    },
    {
      "epoch": 0.5536,
      "grad_norm": 0.2821557819843292,
      "learning_rate": 1.7842825040128413e-05,
      "loss": 0.0477,
      "step": 17300
    },
    {
      "epoch": 0.5568,
      "grad_norm": 17.2164306640625,
      "learning_rate": 1.7829983948635637e-05,
      "loss": 0.0522,
      "step": 17400
    },
    {
      "epoch": 0.56,
      "grad_norm": 11.891914367675781,
      "learning_rate": 1.781714285714286e-05,
      "loss": 0.0859,
      "step": 17500
    },
    {
      "epoch": 0.5632,
      "grad_norm": 12.457894325256348,
      "learning_rate": 1.7804301765650084e-05,
      "loss": 0.0561,
      "step": 17600
    },
    {
      "epoch": 0.5664,
      "grad_norm": 1.845371961593628,
      "learning_rate": 1.7791460674157305e-05,
      "loss": 0.0598,
      "step": 17700
    },
    {
      "epoch": 0.5696,
      "grad_norm": 5.928323268890381,
      "learning_rate": 1.7778619582664527e-05,
      "loss": 0.0591,
      "step": 17800
    },
    {
      "epoch": 0.5728,
      "grad_norm": 0.10898735374212265,
      "learning_rate": 1.776577849117175e-05,
      "loss": 0.068,
      "step": 17900
    },
    {
      "epoch": 0.576,
      "grad_norm": 8.659664154052734,
      "learning_rate": 1.7752937399678973e-05,
      "loss": 0.0672,
      "step": 18000
    },
    {
      "epoch": 0.5792,
      "grad_norm": 0.1051400676369667,
      "learning_rate": 1.7740096308186198e-05,
      "loss": 0.0845,
      "step": 18100
    },
    {
      "epoch": 0.5824,
      "grad_norm": 2.4647881984710693,
      "learning_rate": 1.772725521669342e-05,
      "loss": 0.067,
      "step": 18200
    },
    {
      "epoch": 0.5856,
      "grad_norm": 0.04466241970658302,
      "learning_rate": 1.7714414125200644e-05,
      "loss": 0.0657,
      "step": 18300
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.014231475070118904,
      "learning_rate": 1.7701573033707865e-05,
      "loss": 0.0666,
      "step": 18400
    },
    {
      "epoch": 0.592,
      "grad_norm": 10.516510009765625,
      "learning_rate": 1.768873194221509e-05,
      "loss": 0.0692,
      "step": 18500
    },
    {
      "epoch": 0.5952,
      "grad_norm": 1.2347426414489746,
      "learning_rate": 1.767589085072231e-05,
      "loss": 0.057,
      "step": 18600
    },
    {
      "epoch": 0.5984,
      "grad_norm": 0.09256485849618912,
      "learning_rate": 1.7663049759229537e-05,
      "loss": 0.0726,
      "step": 18700
    },
    {
      "epoch": 0.6016,
      "grad_norm": 9.093379020690918,
      "learning_rate": 1.7650208667736758e-05,
      "loss": 0.0902,
      "step": 18800
    },
    {
      "epoch": 0.6048,
      "grad_norm": 2.5893750190734863,
      "learning_rate": 1.7637367576243983e-05,
      "loss": 0.0611,
      "step": 18900
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.708980143070221,
      "learning_rate": 1.7624526484751204e-05,
      "loss": 0.0726,
      "step": 19000
    },
    {
      "epoch": 0.6112,
      "grad_norm": 0.35581639409065247,
      "learning_rate": 1.761168539325843e-05,
      "loss": 0.0681,
      "step": 19100
    },
    {
      "epoch": 0.6144,
      "grad_norm": 1.3588510751724243,
      "learning_rate": 1.759884430176565e-05,
      "loss": 0.0662,
      "step": 19200
    },
    {
      "epoch": 0.6176,
      "grad_norm": 9.142585754394531,
      "learning_rate": 1.7586003210272875e-05,
      "loss": 0.0559,
      "step": 19300
    },
    {
      "epoch": 0.6208,
      "grad_norm": 16.729188919067383,
      "learning_rate": 1.7573162118780097e-05,
      "loss": 0.0754,
      "step": 19400
    },
    {
      "epoch": 0.624,
      "grad_norm": 11.582767486572266,
      "learning_rate": 1.756032102728732e-05,
      "loss": 0.0681,
      "step": 19500
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.046063363552093506,
      "learning_rate": 1.7547479935794543e-05,
      "loss": 0.0603,
      "step": 19600
    },
    {
      "epoch": 0.6304,
      "grad_norm": 0.294583261013031,
      "learning_rate": 1.7534638844301768e-05,
      "loss": 0.0518,
      "step": 19700
    },
    {
      "epoch": 0.6336,
      "grad_norm": 0.014278042130172253,
      "learning_rate": 1.7521797752808993e-05,
      "loss": 0.0576,
      "step": 19800
    },
    {
      "epoch": 0.6368,
      "grad_norm": 0.16866210103034973,
      "learning_rate": 1.7508956661316214e-05,
      "loss": 0.0701,
      "step": 19900
    },
    {
      "epoch": 0.64,
      "grad_norm": 6.832259654998779,
      "learning_rate": 1.749611556982344e-05,
      "loss": 0.0776,
      "step": 20000
    },
    {
      "epoch": 0.64,
      "eval_accuracy": 0.98464,
      "eval_f1": 0.9846426496660109,
      "eval_loss": 0.061699531972408295,
      "eval_precision": 0.9846784488090538,
      "eval_recall": 0.98464,
      "eval_runtime": 814.0166,
      "eval_samples_per_second": 122.848,
      "eval_steps_per_second": 7.678,
      "step": 20000
    },
    {
      "epoch": 0.6432,
      "grad_norm": 25.919387817382812,
      "learning_rate": 1.7483274478330657e-05,
      "loss": 0.0704,
      "step": 20100
    },
    {
      "epoch": 0.6464,
      "grad_norm": 0.27127301692962646,
      "learning_rate": 1.7470433386837882e-05,
      "loss": 0.0749,
      "step": 20200
    },
    {
      "epoch": 0.6496,
      "grad_norm": 0.1059252917766571,
      "learning_rate": 1.7457592295345103e-05,
      "loss": 0.0793,
      "step": 20300
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.6019250154495239,
      "learning_rate": 1.7444751203852328e-05,
      "loss": 0.059,
      "step": 20400
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.28291046619415283,
      "learning_rate": 1.7431910112359553e-05,
      "loss": 0.0569,
      "step": 20500
    },
    {
      "epoch": 0.6592,
      "grad_norm": 0.15100154280662537,
      "learning_rate": 1.7419069020866774e-05,
      "loss": 0.0398,
      "step": 20600
    },
    {
      "epoch": 0.6624,
      "grad_norm": 0.017900506034493446,
      "learning_rate": 1.7406227929374e-05,
      "loss": 0.0559,
      "step": 20700
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.007751260884106159,
      "learning_rate": 1.739338683788122e-05,
      "loss": 0.0621,
      "step": 20800
    },
    {
      "epoch": 0.6688,
      "grad_norm": 5.354798793792725,
      "learning_rate": 1.7380545746388445e-05,
      "loss": 0.085,
      "step": 20900
    },
    {
      "epoch": 0.672,
      "grad_norm": 2.312457799911499,
      "learning_rate": 1.7367704654895667e-05,
      "loss": 0.0654,
      "step": 21000
    },
    {
      "epoch": 0.6752,
      "grad_norm": 0.10008107125759125,
      "learning_rate": 1.7354863563402892e-05,
      "loss": 0.0697,
      "step": 21100
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.008539400063455105,
      "learning_rate": 1.7342022471910113e-05,
      "loss": 0.0687,
      "step": 21200
    },
    {
      "epoch": 0.6816,
      "grad_norm": 1.0686814785003662,
      "learning_rate": 1.7329181380417338e-05,
      "loss": 0.0491,
      "step": 21300
    },
    {
      "epoch": 0.6848,
      "grad_norm": 42.248897552490234,
      "learning_rate": 1.731634028892456e-05,
      "loss": 0.0464,
      "step": 21400
    },
    {
      "epoch": 0.688,
      "grad_norm": 17.70836067199707,
      "learning_rate": 1.7303499197431784e-05,
      "loss": 0.109,
      "step": 21500
    },
    {
      "epoch": 0.6912,
      "grad_norm": 11.702173233032227,
      "learning_rate": 1.7290658105939006e-05,
      "loss": 0.0626,
      "step": 21600
    },
    {
      "epoch": 0.6944,
      "grad_norm": 0.15207910537719727,
      "learning_rate": 1.727781701444623e-05,
      "loss": 0.0617,
      "step": 21700
    },
    {
      "epoch": 0.6976,
      "grad_norm": 0.7698332667350769,
      "learning_rate": 1.7264975922953452e-05,
      "loss": 0.0508,
      "step": 21800
    },
    {
      "epoch": 0.7008,
      "grad_norm": 0.012268565595149994,
      "learning_rate": 1.7252134831460677e-05,
      "loss": 0.0518,
      "step": 21900
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.07914119213819504,
      "learning_rate": 1.7239293739967898e-05,
      "loss": 0.0699,
      "step": 22000
    },
    {
      "epoch": 0.7072,
      "grad_norm": 0.5616400241851807,
      "learning_rate": 1.7226452648475123e-05,
      "loss": 0.0649,
      "step": 22100
    },
    {
      "epoch": 0.7104,
      "grad_norm": 6.950782299041748,
      "learning_rate": 1.7213611556982345e-05,
      "loss": 0.0719,
      "step": 22200
    },
    {
      "epoch": 0.7136,
      "grad_norm": 0.07157002389431,
      "learning_rate": 1.720077046548957e-05,
      "loss": 0.0403,
      "step": 22300
    },
    {
      "epoch": 0.7168,
      "grad_norm": 2.784773588180542,
      "learning_rate": 1.718792937399679e-05,
      "loss": 0.0468,
      "step": 22400
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.088102325797081,
      "learning_rate": 1.7175088282504012e-05,
      "loss": 0.0612,
      "step": 22500
    },
    {
      "epoch": 0.7232,
      "grad_norm": 0.373806357383728,
      "learning_rate": 1.7162247191011237e-05,
      "loss": 0.0607,
      "step": 22600
    },
    {
      "epoch": 0.7264,
      "grad_norm": 10.401127815246582,
      "learning_rate": 1.714940609951846e-05,
      "loss": 0.0572,
      "step": 22700
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.006438109558075666,
      "learning_rate": 1.7136565008025683e-05,
      "loss": 0.0472,
      "step": 22800
    },
    {
      "epoch": 0.7328,
      "grad_norm": 0.15433204174041748,
      "learning_rate": 1.7123723916532905e-05,
      "loss": 0.0578,
      "step": 22900
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.29676365852355957,
      "learning_rate": 1.711088282504013e-05,
      "loss": 0.0355,
      "step": 23000
    },
    {
      "epoch": 0.7392,
      "grad_norm": 0.007739920634776354,
      "learning_rate": 1.709804173354735e-05,
      "loss": 0.0545,
      "step": 23100
    },
    {
      "epoch": 0.7424,
      "grad_norm": 16.565767288208008,
      "learning_rate": 1.7085200642054576e-05,
      "loss": 0.0662,
      "step": 23200
    },
    {
      "epoch": 0.7456,
      "grad_norm": 0.013131607323884964,
      "learning_rate": 1.7072359550561797e-05,
      "loss": 0.0734,
      "step": 23300
    },
    {
      "epoch": 0.7488,
      "grad_norm": 1.746962308883667,
      "learning_rate": 1.7059518459069022e-05,
      "loss": 0.0558,
      "step": 23400
    },
    {
      "epoch": 0.752,
      "grad_norm": 6.599545955657959,
      "learning_rate": 1.7046677367576247e-05,
      "loss": 0.0485,
      "step": 23500
    },
    {
      "epoch": 0.7552,
      "grad_norm": 4.333959102630615,
      "learning_rate": 1.703383627608347e-05,
      "loss": 0.0554,
      "step": 23600
    },
    {
      "epoch": 0.7584,
      "grad_norm": 0.16271114349365234,
      "learning_rate": 1.7020995184590693e-05,
      "loss": 0.0367,
      "step": 23700
    },
    {
      "epoch": 0.7616,
      "grad_norm": 17.760648727416992,
      "learning_rate": 1.7008154093097915e-05,
      "loss": 0.0871,
      "step": 23800
    },
    {
      "epoch": 0.7648,
      "grad_norm": 0.15831367671489716,
      "learning_rate": 1.699531300160514e-05,
      "loss": 0.0525,
      "step": 23900
    },
    {
      "epoch": 0.768,
      "grad_norm": 10.259693145751953,
      "learning_rate": 1.698247191011236e-05,
      "loss": 0.0643,
      "step": 24000
    },
    {
      "epoch": 0.768,
      "eval_accuracy": 0.98307,
      "eval_f1": 0.9830752640408086,
      "eval_loss": 0.07612209022045135,
      "eval_precision": 0.9832125198389433,
      "eval_recall": 0.98307,
      "eval_runtime": 774.4597,
      "eval_samples_per_second": 129.122,
      "eval_steps_per_second": 8.07,
      "step": 24000
    },
    {
      "epoch": 0.7712,
      "grad_norm": 0.025170153006911278,
      "learning_rate": 1.6969630818619586e-05,
      "loss": 0.0476,
      "step": 24100
    },
    {
      "epoch": 0.7744,
      "grad_norm": 0.005416714586317539,
      "learning_rate": 1.6956789727126807e-05,
      "loss": 0.0625,
      "step": 24200
    },
    {
      "epoch": 0.7776,
      "grad_norm": 35.962677001953125,
      "learning_rate": 1.6943948635634032e-05,
      "loss": 0.0492,
      "step": 24300
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.019019972532987595,
      "learning_rate": 1.6931107544141254e-05,
      "loss": 0.0567,
      "step": 24400
    },
    {
      "epoch": 0.784,
      "grad_norm": 4.536252021789551,
      "learning_rate": 1.691826645264848e-05,
      "loss": 0.0564,
      "step": 24500
    },
    {
      "epoch": 0.7872,
      "grad_norm": 20.884357452392578,
      "learning_rate": 1.69054253611557e-05,
      "loss": 0.059,
      "step": 24600
    },
    {
      "epoch": 0.7904,
      "grad_norm": 4.154411792755127,
      "learning_rate": 1.689258426966292e-05,
      "loss": 0.0567,
      "step": 24700
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.23815973103046417,
      "learning_rate": 1.6879743178170146e-05,
      "loss": 0.0593,
      "step": 24800
    },
    {
      "epoch": 0.7968,
      "grad_norm": 0.027695050463080406,
      "learning_rate": 1.6866902086677368e-05,
      "loss": 0.0545,
      "step": 24900
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.052229318767786026,
      "learning_rate": 1.6854060995184592e-05,
      "loss": 0.0584,
      "step": 25000
    },
    {
      "epoch": 0.8032,
      "grad_norm": 0.007615574169903994,
      "learning_rate": 1.6841219903691814e-05,
      "loss": 0.0492,
      "step": 25100
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.34495148062705994,
      "learning_rate": 1.682837881219904e-05,
      "loss": 0.0512,
      "step": 25200
    },
    {
      "epoch": 0.8096,
      "grad_norm": 0.4945124685764313,
      "learning_rate": 1.681553772070626e-05,
      "loss": 0.0659,
      "step": 25300
    },
    {
      "epoch": 0.8128,
      "grad_norm": 3.508509397506714,
      "learning_rate": 1.6802696629213485e-05,
      "loss": 0.0431,
      "step": 25400
    },
    {
      "epoch": 0.816,
      "grad_norm": 9.751060485839844,
      "learning_rate": 1.6789855537720706e-05,
      "loss": 0.0609,
      "step": 25500
    },
    {
      "epoch": 0.8192,
      "grad_norm": 13.404821395874023,
      "learning_rate": 1.677701444622793e-05,
      "loss": 0.0451,
      "step": 25600
    },
    {
      "epoch": 0.8224,
      "grad_norm": 0.09565193206071854,
      "learning_rate": 1.6764173354735153e-05,
      "loss": 0.0545,
      "step": 25700
    },
    {
      "epoch": 0.8256,
      "grad_norm": 0.010966203175485134,
      "learning_rate": 1.6751332263242377e-05,
      "loss": 0.0703,
      "step": 25800
    },
    {
      "epoch": 0.8288,
      "grad_norm": 0.18196341395378113,
      "learning_rate": 1.67384911717496e-05,
      "loss": 0.0392,
      "step": 25900
    },
    {
      "epoch": 0.832,
      "grad_norm": 15.195699691772461,
      "learning_rate": 1.6725650080256824e-05,
      "loss": 0.0429,
      "step": 26000
    },
    {
      "epoch": 0.8352,
      "grad_norm": 0.2465728521347046,
      "learning_rate": 1.6712808988764045e-05,
      "loss": 0.0546,
      "step": 26100
    },
    {
      "epoch": 0.8384,
      "grad_norm": 15.004085540771484,
      "learning_rate": 1.669996789727127e-05,
      "loss": 0.0716,
      "step": 26200
    },
    {
      "epoch": 0.8416,
      "grad_norm": 0.17839568853378296,
      "learning_rate": 1.668712680577849e-05,
      "loss": 0.0413,
      "step": 26300
    },
    {
      "epoch": 0.8448,
      "grad_norm": 30.638254165649414,
      "learning_rate": 1.6674285714285716e-05,
      "loss": 0.0391,
      "step": 26400
    },
    {
      "epoch": 0.848,
      "grad_norm": 8.340238571166992,
      "learning_rate": 1.6661444622792938e-05,
      "loss": 0.0579,
      "step": 26500
    },
    {
      "epoch": 0.8512,
      "grad_norm": 0.026733344420790672,
      "learning_rate": 1.6648603531300163e-05,
      "loss": 0.0647,
      "step": 26600
    },
    {
      "epoch": 0.8544,
      "grad_norm": 0.013905318453907967,
      "learning_rate": 1.6635762439807387e-05,
      "loss": 0.0258,
      "step": 26700
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.011157176457345486,
      "learning_rate": 1.662292134831461e-05,
      "loss": 0.0497,
      "step": 26800
    },
    {
      "epoch": 0.8608,
      "grad_norm": 0.029731517657637596,
      "learning_rate": 1.6610080256821834e-05,
      "loss": 0.0567,
      "step": 26900
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.3443889319896698,
      "learning_rate": 1.6597239165329055e-05,
      "loss": 0.0533,
      "step": 27000
    },
    {
      "epoch": 0.8672,
      "grad_norm": 0.5098379254341125,
      "learning_rate": 1.6584398073836277e-05,
      "loss": 0.0532,
      "step": 27100
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.045412395149469376,
      "learning_rate": 1.6571556982343498e-05,
      "loss": 0.0533,
      "step": 27200
    },
    {
      "epoch": 0.8736,
      "grad_norm": 3.6077659130096436,
      "learning_rate": 1.6558715890850723e-05,
      "loss": 0.0432,
      "step": 27300
    },
    {
      "epoch": 0.8768,
      "grad_norm": 27.717470169067383,
      "learning_rate": 1.6545874799357948e-05,
      "loss": 0.0599,
      "step": 27400
    },
    {
      "epoch": 0.88,
      "grad_norm": 8.342029571533203,
      "learning_rate": 1.653303370786517e-05,
      "loss": 0.066,
      "step": 27500
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.09634260088205338,
      "learning_rate": 1.6520192616372394e-05,
      "loss": 0.0516,
      "step": 27600
    },
    {
      "epoch": 0.8864,
      "grad_norm": 0.13491930067539215,
      "learning_rate": 1.6507351524879615e-05,
      "loss": 0.0539,
      "step": 27700
    },
    {
      "epoch": 0.8896,
      "grad_norm": 0.23464186489582062,
      "learning_rate": 1.649451043338684e-05,
      "loss": 0.0415,
      "step": 27800
    },
    {
      "epoch": 0.8928,
      "grad_norm": 0.46864306926727295,
      "learning_rate": 1.648166934189406e-05,
      "loss": 0.0535,
      "step": 27900
    },
    {
      "epoch": 0.896,
      "grad_norm": 6.844827175140381,
      "learning_rate": 1.6468828250401286e-05,
      "loss": 0.064,
      "step": 28000
    },
    {
      "epoch": 0.896,
      "eval_accuracy": 0.98781,
      "eval_f1": 0.9878109998616666,
      "eval_loss": 0.04953546077013016,
      "eval_precision": 0.9878187731391986,
      "eval_recall": 0.98781,
      "eval_runtime": 778.6432,
      "eval_samples_per_second": 128.429,
      "eval_steps_per_second": 8.027,
      "step": 28000
    },
    {
      "epoch": 0.8992,
      "grad_norm": 0.008244618773460388,
      "learning_rate": 1.6455987158908508e-05,
      "loss": 0.041,
      "step": 28100
    },
    {
      "epoch": 0.9024,
      "grad_norm": 0.01580977439880371,
      "learning_rate": 1.6443146067415733e-05,
      "loss": 0.057,
      "step": 28200
    },
    {
      "epoch": 0.9056,
      "grad_norm": 10.525986671447754,
      "learning_rate": 1.6430304975922954e-05,
      "loss": 0.0322,
      "step": 28300
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.016806138679385185,
      "learning_rate": 1.641746388443018e-05,
      "loss": 0.0523,
      "step": 28400
    },
    {
      "epoch": 0.912,
      "grad_norm": 6.311640739440918,
      "learning_rate": 1.64046227929374e-05,
      "loss": 0.0497,
      "step": 28500
    },
    {
      "epoch": 0.9152,
      "grad_norm": 0.09537007659673691,
      "learning_rate": 1.6391781701444625e-05,
      "loss": 0.0523,
      "step": 28600
    },
    {
      "epoch": 0.9184,
      "grad_norm": 0.010998793877661228,
      "learning_rate": 1.6378940609951847e-05,
      "loss": 0.0481,
      "step": 28700
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.24172453582286835,
      "learning_rate": 1.636609951845907e-05,
      "loss": 0.0537,
      "step": 28800
    },
    {
      "epoch": 0.9248,
      "grad_norm": 0.00843421183526516,
      "learning_rate": 1.6353258426966293e-05,
      "loss": 0.0345,
      "step": 28900
    },
    {
      "epoch": 0.928,
      "grad_norm": 26.664979934692383,
      "learning_rate": 1.6340417335473518e-05,
      "loss": 0.0667,
      "step": 29000
    },
    {
      "epoch": 0.9312,
      "grad_norm": 0.3694003224372864,
      "learning_rate": 1.632757624398074e-05,
      "loss": 0.0555,
      "step": 29100
    },
    {
      "epoch": 0.9344,
      "grad_norm": 24.855958938598633,
      "learning_rate": 1.6314735152487964e-05,
      "loss": 0.058,
      "step": 29200
    },
    {
      "epoch": 0.9376,
      "grad_norm": 2.051378011703491,
      "learning_rate": 1.6301894060995186e-05,
      "loss": 0.0427,
      "step": 29300
    },
    {
      "epoch": 0.9408,
      "grad_norm": 0.8996158838272095,
      "learning_rate": 1.6289052969502407e-05,
      "loss": 0.0462,
      "step": 29400
    },
    {
      "epoch": 0.944,
      "grad_norm": 14.316937446594238,
      "learning_rate": 1.6276211878009632e-05,
      "loss": 0.0658,
      "step": 29500
    },
    {
      "epoch": 0.9472,
      "grad_norm": 11.959718704223633,
      "learning_rate": 1.6263370786516853e-05,
      "loss": 0.0396,
      "step": 29600
    },
    {
      "epoch": 0.9504,
      "grad_norm": 0.015293744392693043,
      "learning_rate": 1.6250529695024078e-05,
      "loss": 0.0489,
      "step": 29700
    },
    {
      "epoch": 0.9536,
      "grad_norm": 14.037763595581055,
      "learning_rate": 1.62376886035313e-05,
      "loss": 0.0746,
      "step": 29800
    },
    {
      "epoch": 0.9568,
      "grad_norm": 0.04080112278461456,
      "learning_rate": 1.6224847512038524e-05,
      "loss": 0.0612,
      "step": 29900
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06590835005044937,
      "learning_rate": 1.6212006420545746e-05,
      "loss": 0.0597,
      "step": 30000
    },
    {
      "epoch": 0.9632,
      "grad_norm": 8.91706657409668,
      "learning_rate": 1.619916532905297e-05,
      "loss": 0.0489,
      "step": 30100
    },
    {
      "epoch": 0.9664,
      "grad_norm": 0.019029080867767334,
      "learning_rate": 1.6186324237560192e-05,
      "loss": 0.0572,
      "step": 30200
    },
    {
      "epoch": 0.9696,
      "grad_norm": 4.674193382263184,
      "learning_rate": 1.6173483146067417e-05,
      "loss": 0.0587,
      "step": 30300
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.14981134235858917,
      "learning_rate": 1.6160642054574642e-05,
      "loss": 0.0323,
      "step": 30400
    },
    {
      "epoch": 0.976,
      "grad_norm": 4.462047100067139,
      "learning_rate": 1.6147800963081863e-05,
      "loss": 0.053,
      "step": 30500
    },
    {
      "epoch": 0.9792,
      "grad_norm": 0.10449015349149704,
      "learning_rate": 1.6134959871589088e-05,
      "loss": 0.0465,
      "step": 30600
    },
    {
      "epoch": 0.9824,
      "grad_norm": 1.134883999824524,
      "learning_rate": 1.612211878009631e-05,
      "loss": 0.0534,
      "step": 30700
    },
    {
      "epoch": 0.9856,
      "grad_norm": 21.06899070739746,
      "learning_rate": 1.6109277688603534e-05,
      "loss": 0.0515,
      "step": 30800
    },
    {
      "epoch": 0.9888,
      "grad_norm": 20.929187774658203,
      "learning_rate": 1.6096436597110756e-05,
      "loss": 0.046,
      "step": 30900
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.008979029022157192,
      "learning_rate": 1.608359550561798e-05,
      "loss": 0.0288,
      "step": 31000
    },
    {
      "epoch": 0.9952,
      "grad_norm": 10.832496643066406,
      "learning_rate": 1.6070754414125202e-05,
      "loss": 0.0533,
      "step": 31100
    },
    {
      "epoch": 0.9984,
      "grad_norm": 10.279513359069824,
      "learning_rate": 1.6057913322632427e-05,
      "loss": 0.0535,
      "step": 31200
    },
    {
      "epoch": 1.0016,
      "grad_norm": 0.050070084631443024,
      "learning_rate": 1.6045072231139648e-05,
      "loss": 0.0488,
      "step": 31300
    },
    {
      "epoch": 1.0048,
      "grad_norm": 7.610085964202881,
      "learning_rate": 1.6032231139646873e-05,
      "loss": 0.0499,
      "step": 31400
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.03847907483577728,
      "learning_rate": 1.6019390048154095e-05,
      "loss": 0.0668,
      "step": 31500
    },
    {
      "epoch": 1.0112,
      "grad_norm": 0.009822272695600986,
      "learning_rate": 1.600654895666132e-05,
      "loss": 0.0403,
      "step": 31600
    },
    {
      "epoch": 1.0144,
      "grad_norm": 0.1967863291501999,
      "learning_rate": 1.599370786516854e-05,
      "loss": 0.0565,
      "step": 31700
    },
    {
      "epoch": 1.0176,
      "grad_norm": 8.522165298461914,
      "learning_rate": 1.5980866773675762e-05,
      "loss": 0.0298,
      "step": 31800
    },
    {
      "epoch": 1.0208,
      "grad_norm": 0.7742573618888855,
      "learning_rate": 1.5968025682182987e-05,
      "loss": 0.0411,
      "step": 31900
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.07143627107143402,
      "learning_rate": 1.595518459069021e-05,
      "loss": 0.0477,
      "step": 32000
    },
    {
      "epoch": 1.024,
      "eval_accuracy": 0.98794,
      "eval_f1": 0.9879419419991998,
      "eval_loss": 0.04801899939775467,
      "eval_precision": 0.9879724568651884,
      "eval_recall": 0.98794,
      "eval_runtime": 775.4534,
      "eval_samples_per_second": 128.957,
      "eval_steps_per_second": 8.06,
      "step": 32000
    },
    {
      "epoch": 1.0272,
      "grad_norm": 1.0557373762130737,
      "learning_rate": 1.5942343499197433e-05,
      "loss": 0.0594,
      "step": 32100
    },
    {
      "epoch": 1.0304,
      "grad_norm": 0.03562343493103981,
      "learning_rate": 1.5929502407704655e-05,
      "loss": 0.0537,
      "step": 32200
    },
    {
      "epoch": 1.0336,
      "grad_norm": 0.06482692807912827,
      "learning_rate": 1.591666131621188e-05,
      "loss": 0.0463,
      "step": 32300
    },
    {
      "epoch": 1.0368,
      "grad_norm": 0.49017927050590515,
      "learning_rate": 1.59038202247191e-05,
      "loss": 0.0661,
      "step": 32400
    },
    {
      "epoch": 1.04,
      "grad_norm": 15.849417686462402,
      "learning_rate": 1.5890979133226326e-05,
      "loss": 0.0237,
      "step": 32500
    },
    {
      "epoch": 1.0432,
      "grad_norm": 0.6910932064056396,
      "learning_rate": 1.5878138041733547e-05,
      "loss": 0.0383,
      "step": 32600
    },
    {
      "epoch": 1.0464,
      "grad_norm": 0.06304027885198593,
      "learning_rate": 1.5865296950240772e-05,
      "loss": 0.0541,
      "step": 32700
    },
    {
      "epoch": 1.0496,
      "grad_norm": 11.758397102355957,
      "learning_rate": 1.5852455858747994e-05,
      "loss": 0.0573,
      "step": 32800
    },
    {
      "epoch": 1.0528,
      "grad_norm": 0.007580827921628952,
      "learning_rate": 1.583961476725522e-05,
      "loss": 0.0551,
      "step": 32900
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.7389895915985107,
      "learning_rate": 1.582677367576244e-05,
      "loss": 0.0408,
      "step": 33000
    },
    {
      "epoch": 1.0592,
      "grad_norm": 0.011490071192383766,
      "learning_rate": 1.5813932584269665e-05,
      "loss": 0.0474,
      "step": 33100
    },
    {
      "epoch": 1.0624,
      "grad_norm": 0.00892989058047533,
      "learning_rate": 1.5801091492776886e-05,
      "loss": 0.0338,
      "step": 33200
    },
    {
      "epoch": 1.0656,
      "grad_norm": 0.21890480816364288,
      "learning_rate": 1.578825040128411e-05,
      "loss": 0.0465,
      "step": 33300
    },
    {
      "epoch": 1.0688,
      "grad_norm": 20.05085563659668,
      "learning_rate": 1.5775409309791332e-05,
      "loss": 0.0633,
      "step": 33400
    },
    {
      "epoch": 1.072,
      "grad_norm": 3.5141100883483887,
      "learning_rate": 1.5762568218298557e-05,
      "loss": 0.0743,
      "step": 33500
    },
    {
      "epoch": 1.0752,
      "grad_norm": 0.03382471203804016,
      "learning_rate": 1.5749727126805782e-05,
      "loss": 0.0409,
      "step": 33600
    },
    {
      "epoch": 1.0784,
      "grad_norm": 9.916868209838867,
      "learning_rate": 1.5736886035313004e-05,
      "loss": 0.0498,
      "step": 33700
    },
    {
      "epoch": 1.0816,
      "grad_norm": 0.007973396219313145,
      "learning_rate": 1.572404494382023e-05,
      "loss": 0.0399,
      "step": 33800
    },
    {
      "epoch": 1.0848,
      "grad_norm": 0.15778931975364685,
      "learning_rate": 1.571120385232745e-05,
      "loss": 0.0406,
      "step": 33900
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.027699623256921768,
      "learning_rate": 1.569836276083467e-05,
      "loss": 0.0481,
      "step": 34000
    },
    {
      "epoch": 1.0912,
      "grad_norm": 2.7082841396331787,
      "learning_rate": 1.5685521669341893e-05,
      "loss": 0.0427,
      "step": 34100
    },
    {
      "epoch": 1.0944,
      "grad_norm": 2.933098316192627,
      "learning_rate": 1.5672680577849118e-05,
      "loss": 0.0605,
      "step": 34200
    },
    {
      "epoch": 1.0976,
      "grad_norm": 5.093338489532471,
      "learning_rate": 1.5659839486356342e-05,
      "loss": 0.0625,
      "step": 34300
    },
    {
      "epoch": 1.1008,
      "grad_norm": 0.14764878153800964,
      "learning_rate": 1.5646998394863564e-05,
      "loss": 0.0467,
      "step": 34400
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.45360442996025085,
      "learning_rate": 1.563415730337079e-05,
      "loss": 0.0517,
      "step": 34500
    },
    {
      "epoch": 1.1072,
      "grad_norm": 0.007702784612774849,
      "learning_rate": 1.562131621187801e-05,
      "loss": 0.0367,
      "step": 34600
    },
    {
      "epoch": 1.1104,
      "grad_norm": 0.01513522956520319,
      "learning_rate": 1.5608475120385235e-05,
      "loss": 0.0514,
      "step": 34700
    },
    {
      "epoch": 1.1136,
      "grad_norm": 0.29241982102394104,
      "learning_rate": 1.5595634028892456e-05,
      "loss": 0.0428,
      "step": 34800
    },
    {
      "epoch": 1.1168,
      "grad_norm": 0.02503369376063347,
      "learning_rate": 1.558279293739968e-05,
      "loss": 0.0583,
      "step": 34900
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.094393789768219,
      "learning_rate": 1.5569951845906903e-05,
      "loss": 0.0636,
      "step": 35000
    },
    {
      "epoch": 1.1232,
      "grad_norm": 0.011400578543543816,
      "learning_rate": 1.5557110754414127e-05,
      "loss": 0.0392,
      "step": 35100
    },
    {
      "epoch": 1.1264,
      "grad_norm": 0.015260876156389713,
      "learning_rate": 1.554426966292135e-05,
      "loss": 0.0452,
      "step": 35200
    },
    {
      "epoch": 1.1296,
      "grad_norm": 0.07425595074892044,
      "learning_rate": 1.5531428571428574e-05,
      "loss": 0.0506,
      "step": 35300
    },
    {
      "epoch": 1.1328,
      "grad_norm": 2.20249605178833,
      "learning_rate": 1.5518587479935795e-05,
      "loss": 0.0742,
      "step": 35400
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.027821656316518784,
      "learning_rate": 1.550574638844302e-05,
      "loss": 0.062,
      "step": 35500
    },
    {
      "epoch": 1.1392,
      "grad_norm": 0.02665848284959793,
      "learning_rate": 1.549290529695024e-05,
      "loss": 0.0739,
      "step": 35600
    },
    {
      "epoch": 1.1424,
      "grad_norm": 5.973049163818359,
      "learning_rate": 1.5480064205457466e-05,
      "loss": 0.0504,
      "step": 35700
    },
    {
      "epoch": 1.1456,
      "grad_norm": 10.988951683044434,
      "learning_rate": 1.5467223113964688e-05,
      "loss": 0.0493,
      "step": 35800
    },
    {
      "epoch": 1.1488,
      "grad_norm": 15.630033493041992,
      "learning_rate": 1.5454382022471913e-05,
      "loss": 0.0492,
      "step": 35900
    },
    {
      "epoch": 1.152,
      "grad_norm": 4.891533851623535,
      "learning_rate": 1.5441540930979134e-05,
      "loss": 0.0427,
      "step": 36000
    },
    {
      "epoch": 1.152,
      "eval_accuracy": 0.98938,
      "eval_f1": 0.9893807849919393,
      "eval_loss": 0.0424417182803154,
      "eval_precision": 0.9893870324245919,
      "eval_recall": 0.98938,
      "eval_runtime": 778.7856,
      "eval_samples_per_second": 128.405,
      "eval_steps_per_second": 8.025,
      "step": 36000
    },
    {
      "epoch": 1.1552,
      "grad_norm": 7.563354969024658,
      "learning_rate": 1.542869983948636e-05,
      "loss": 0.0446,
      "step": 36100
    },
    {
      "epoch": 1.1584,
      "grad_norm": 0.017443129792809486,
      "learning_rate": 1.541585874799358e-05,
      "loss": 0.0472,
      "step": 36200
    },
    {
      "epoch": 1.1616,
      "grad_norm": 0.007690173573791981,
      "learning_rate": 1.5403017656500805e-05,
      "loss": 0.0368,
      "step": 36300
    },
    {
      "epoch": 1.1648,
      "grad_norm": 0.024819310754537582,
      "learning_rate": 1.5390176565008027e-05,
      "loss": 0.0466,
      "step": 36400
    },
    {
      "epoch": 1.168,
      "grad_norm": 1.0305715799331665,
      "learning_rate": 1.5377335473515248e-05,
      "loss": 0.0396,
      "step": 36500
    },
    {
      "epoch": 1.1712,
      "grad_norm": 13.792978286743164,
      "learning_rate": 1.5364494382022473e-05,
      "loss": 0.0382,
      "step": 36600
    },
    {
      "epoch": 1.1743999999999999,
      "grad_norm": 4.012645721435547,
      "learning_rate": 1.5351653290529694e-05,
      "loss": 0.0519,
      "step": 36700
    },
    {
      "epoch": 1.1776,
      "grad_norm": 0.015255521982908249,
      "learning_rate": 1.533881219903692e-05,
      "loss": 0.0331,
      "step": 36800
    },
    {
      "epoch": 1.1808,
      "grad_norm": 0.03518729284405708,
      "learning_rate": 1.532597110754414e-05,
      "loss": 0.0442,
      "step": 36900
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.12012261152267456,
      "learning_rate": 1.5313130016051365e-05,
      "loss": 0.0392,
      "step": 37000
    },
    {
      "epoch": 1.1872,
      "grad_norm": 0.03485884144902229,
      "learning_rate": 1.5300288924558587e-05,
      "loss": 0.0214,
      "step": 37100
    },
    {
      "epoch": 1.1904,
      "grad_norm": 10.218805313110352,
      "learning_rate": 1.528744783306581e-05,
      "loss": 0.0528,
      "step": 37200
    },
    {
      "epoch": 1.1936,
      "grad_norm": 0.0384359173476696,
      "learning_rate": 1.5274606741573036e-05,
      "loss": 0.0625,
      "step": 37300
    },
    {
      "epoch": 1.1968,
      "grad_norm": 0.3779418170452118,
      "learning_rate": 1.5261765650080258e-05,
      "loss": 0.0328,
      "step": 37400
    },
    {
      "epoch": 1.2,
      "grad_norm": 5.618625640869141,
      "learning_rate": 1.5248924558587481e-05,
      "loss": 0.065,
      "step": 37500
    },
    {
      "epoch": 1.2032,
      "grad_norm": 2.0705819129943848,
      "learning_rate": 1.5236083467094704e-05,
      "loss": 0.0594,
      "step": 37600
    },
    {
      "epoch": 1.2064,
      "grad_norm": 0.14193743467330933,
      "learning_rate": 1.5223242375601927e-05,
      "loss": 0.0417,
      "step": 37700
    },
    {
      "epoch": 1.2096,
      "grad_norm": 0.034703925251960754,
      "learning_rate": 1.521040128410915e-05,
      "loss": 0.0389,
      "step": 37800
    },
    {
      "epoch": 1.2128,
      "grad_norm": 0.011800256557762623,
      "learning_rate": 1.5197560192616374e-05,
      "loss": 0.0393,
      "step": 37900
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.28774189949035645,
      "learning_rate": 1.5184719101123597e-05,
      "loss": 0.0504,
      "step": 38000
    },
    {
      "epoch": 1.2192,
      "grad_norm": 0.035763729363679886,
      "learning_rate": 1.517187800963082e-05,
      "loss": 0.0534,
      "step": 38100
    },
    {
      "epoch": 1.2224,
      "grad_norm": 0.158742755651474,
      "learning_rate": 1.5159036918138043e-05,
      "loss": 0.0436,
      "step": 38200
    },
    {
      "epoch": 1.2256,
      "grad_norm": 9.794978141784668,
      "learning_rate": 1.5146195826645266e-05,
      "loss": 0.0502,
      "step": 38300
    },
    {
      "epoch": 1.2288000000000001,
      "grad_norm": 0.021368766203522682,
      "learning_rate": 1.513335473515249e-05,
      "loss": 0.0286,
      "step": 38400
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.5888408422470093,
      "learning_rate": 1.5120513643659714e-05,
      "loss": 0.0674,
      "step": 38500
    },
    {
      "epoch": 1.2352,
      "grad_norm": 0.005416017957031727,
      "learning_rate": 1.5107672552166937e-05,
      "loss": 0.0381,
      "step": 38600
    },
    {
      "epoch": 1.2384,
      "grad_norm": 0.03922798112034798,
      "learning_rate": 1.5094831460674157e-05,
      "loss": 0.0747,
      "step": 38700
    },
    {
      "epoch": 1.2416,
      "grad_norm": 0.030901480466127396,
      "learning_rate": 1.508199036918138e-05,
      "loss": 0.0491,
      "step": 38800
    },
    {
      "epoch": 1.2448,
      "grad_norm": 0.02417912147939205,
      "learning_rate": 1.5069149277688603e-05,
      "loss": 0.0465,
      "step": 38900
    },
    {
      "epoch": 1.248,
      "grad_norm": 15.668951988220215,
      "learning_rate": 1.5056308186195826e-05,
      "loss": 0.0535,
      "step": 39000
    },
    {
      "epoch": 1.2511999999999999,
      "grad_norm": 0.21102702617645264,
      "learning_rate": 1.504346709470305e-05,
      "loss": 0.0517,
      "step": 39100
    },
    {
      "epoch": 1.2544,
      "grad_norm": 0.06641241163015366,
      "learning_rate": 1.5030626003210274e-05,
      "loss": 0.0416,
      "step": 39200
    },
    {
      "epoch": 1.2576,
      "grad_norm": 0.5495890974998474,
      "learning_rate": 1.5017784911717497e-05,
      "loss": 0.0357,
      "step": 39300
    },
    {
      "epoch": 1.2608,
      "grad_norm": 0.035381533205509186,
      "learning_rate": 1.500494382022472e-05,
      "loss": 0.0577,
      "step": 39400
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.03879441320896149,
      "learning_rate": 1.4992102728731944e-05,
      "loss": 0.0191,
      "step": 39500
    },
    {
      "epoch": 1.2671999999999999,
      "grad_norm": 0.014720222912728786,
      "learning_rate": 1.4979261637239167e-05,
      "loss": 0.0423,
      "step": 39600
    },
    {
      "epoch": 1.2704,
      "grad_norm": 3.2292592525482178,
      "learning_rate": 1.496642054574639e-05,
      "loss": 0.0602,
      "step": 39700
    },
    {
      "epoch": 1.2736,
      "grad_norm": 1.6030577421188354,
      "learning_rate": 1.4953579454253613e-05,
      "loss": 0.0543,
      "step": 39800
    },
    {
      "epoch": 1.2768,
      "grad_norm": 0.031688716262578964,
      "learning_rate": 1.4940738362760836e-05,
      "loss": 0.0341,
      "step": 39900
    },
    {
      "epoch": 1.28,
      "grad_norm": 9.190576553344727,
      "learning_rate": 1.492789727126806e-05,
      "loss": 0.0381,
      "step": 40000
    },
    {
      "epoch": 1.28,
      "eval_accuracy": 0.98796,
      "eval_f1": 0.9879625821520611,
      "eval_loss": 0.04839452728629112,
      "eval_precision": 0.9880194851769686,
      "eval_recall": 0.98796,
      "eval_runtime": 777.527,
      "eval_samples_per_second": 128.613,
      "eval_steps_per_second": 8.038,
      "step": 40000
    },
    {
      "epoch": 1.2832,
      "grad_norm": 0.879464328289032,
      "learning_rate": 1.4915056179775283e-05,
      "loss": 0.0371,
      "step": 40100
    },
    {
      "epoch": 1.2864,
      "grad_norm": 0.5318993926048279,
      "learning_rate": 1.4902215088282506e-05,
      "loss": 0.0638,
      "step": 40200
    },
    {
      "epoch": 1.2896,
      "grad_norm": 0.024928994476795197,
      "learning_rate": 1.4889373996789729e-05,
      "loss": 0.039,
      "step": 40300
    },
    {
      "epoch": 1.2928,
      "grad_norm": 15.540450096130371,
      "learning_rate": 1.4876532905296952e-05,
      "loss": 0.0392,
      "step": 40400
    },
    {
      "epoch": 1.296,
      "grad_norm": 3.986953020095825,
      "learning_rate": 1.4863691813804175e-05,
      "loss": 0.0518,
      "step": 40500
    },
    {
      "epoch": 1.2992,
      "grad_norm": 0.03195634484291077,
      "learning_rate": 1.4850850722311398e-05,
      "loss": 0.0614,
      "step": 40600
    },
    {
      "epoch": 1.3024,
      "grad_norm": 0.004710075911134481,
      "learning_rate": 1.4838009630818621e-05,
      "loss": 0.0384,
      "step": 40700
    },
    {
      "epoch": 1.3056,
      "grad_norm": 0.08971494436264038,
      "learning_rate": 1.4825168539325845e-05,
      "loss": 0.051,
      "step": 40800
    },
    {
      "epoch": 1.3088,
      "grad_norm": 0.00958671048283577,
      "learning_rate": 1.4812327447833068e-05,
      "loss": 0.042,
      "step": 40900
    },
    {
      "epoch": 1.312,
      "grad_norm": 26.961130142211914,
      "learning_rate": 1.4799486356340289e-05,
      "loss": 0.0512,
      "step": 41000
    },
    {
      "epoch": 1.3152,
      "grad_norm": 0.12558290362358093,
      "learning_rate": 1.4786645264847512e-05,
      "loss": 0.0262,
      "step": 41100
    },
    {
      "epoch": 1.3184,
      "grad_norm": 0.020398223772644997,
      "learning_rate": 1.4773804173354735e-05,
      "loss": 0.0504,
      "step": 41200
    },
    {
      "epoch": 1.3216,
      "grad_norm": 0.04079282656311989,
      "learning_rate": 1.4760963081861959e-05,
      "loss": 0.0467,
      "step": 41300
    },
    {
      "epoch": 1.3248,
      "grad_norm": 0.01801035739481449,
      "learning_rate": 1.4748121990369182e-05,
      "loss": 0.031,
      "step": 41400
    },
    {
      "epoch": 1.328,
      "grad_norm": 19.165552139282227,
      "learning_rate": 1.4735280898876405e-05,
      "loss": 0.0425,
      "step": 41500
    },
    {
      "epoch": 1.3312,
      "grad_norm": 0.06247144564986229,
      "learning_rate": 1.4722439807383628e-05,
      "loss": 0.0377,
      "step": 41600
    },
    {
      "epoch": 1.3344,
      "grad_norm": 0.07584625482559204,
      "learning_rate": 1.4709598715890851e-05,
      "loss": 0.0318,
      "step": 41700
    },
    {
      "epoch": 1.3376000000000001,
      "grad_norm": 0.659372866153717,
      "learning_rate": 1.4696757624398074e-05,
      "loss": 0.0392,
      "step": 41800
    },
    {
      "epoch": 1.3408,
      "grad_norm": 0.027756713330745697,
      "learning_rate": 1.4683916532905297e-05,
      "loss": 0.0518,
      "step": 41900
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.006904853507876396,
      "learning_rate": 1.467107544141252e-05,
      "loss": 0.0456,
      "step": 42000
    },
    {
      "epoch": 1.3472,
      "grad_norm": 0.005585466045886278,
      "learning_rate": 1.4658234349919744e-05,
      "loss": 0.046,
      "step": 42100
    },
    {
      "epoch": 1.3504,
      "grad_norm": 5.473335266113281,
      "learning_rate": 1.4645393258426967e-05,
      "loss": 0.0428,
      "step": 42200
    },
    {
      "epoch": 1.3536000000000001,
      "grad_norm": 10.384184837341309,
      "learning_rate": 1.4632552166934192e-05,
      "loss": 0.0512,
      "step": 42300
    },
    {
      "epoch": 1.3568,
      "grad_norm": 4.152897357940674,
      "learning_rate": 1.4619711075441415e-05,
      "loss": 0.0378,
      "step": 42400
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.06695935130119324,
      "learning_rate": 1.4606869983948638e-05,
      "loss": 0.0411,
      "step": 42500
    },
    {
      "epoch": 1.3632,
      "grad_norm": 21.025299072265625,
      "learning_rate": 1.4594028892455861e-05,
      "loss": 0.0373,
      "step": 42600
    },
    {
      "epoch": 1.3664,
      "grad_norm": 13.606021881103516,
      "learning_rate": 1.4581187800963084e-05,
      "loss": 0.0454,
      "step": 42700
    },
    {
      "epoch": 1.3696,
      "grad_norm": 0.17352361977100372,
      "learning_rate": 1.4568346709470307e-05,
      "loss": 0.0513,
      "step": 42800
    },
    {
      "epoch": 1.3728,
      "grad_norm": 1.2343215942382812,
      "learning_rate": 1.455550561797753e-05,
      "loss": 0.0699,
      "step": 42900
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.01240515150129795,
      "learning_rate": 1.4542664526484754e-05,
      "loss": 0.0402,
      "step": 43000
    },
    {
      "epoch": 1.3792,
      "grad_norm": 5.457210063934326,
      "learning_rate": 1.4529823434991977e-05,
      "loss": 0.0519,
      "step": 43100
    },
    {
      "epoch": 1.3824,
      "grad_norm": 0.8150522708892822,
      "learning_rate": 1.45169823434992e-05,
      "loss": 0.0605,
      "step": 43200
    },
    {
      "epoch": 1.3856,
      "grad_norm": 0.046282608062028885,
      "learning_rate": 1.4504141252006421e-05,
      "loss": 0.0523,
      "step": 43300
    },
    {
      "epoch": 1.3888,
      "grad_norm": 0.009331628680229187,
      "learning_rate": 1.4491300160513644e-05,
      "loss": 0.0453,
      "step": 43400
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.15661238133907318,
      "learning_rate": 1.4478459069020868e-05,
      "loss": 0.0303,
      "step": 43500
    },
    {
      "epoch": 1.3952,
      "grad_norm": 5.842204570770264,
      "learning_rate": 1.446561797752809e-05,
      "loss": 0.0369,
      "step": 43600
    },
    {
      "epoch": 1.3984,
      "grad_norm": 32.753719329833984,
      "learning_rate": 1.4452776886035314e-05,
      "loss": 0.0423,
      "step": 43700
    },
    {
      "epoch": 1.4016,
      "grad_norm": 0.0857323631644249,
      "learning_rate": 1.4439935794542537e-05,
      "loss": 0.0452,
      "step": 43800
    },
    {
      "epoch": 1.4048,
      "grad_norm": 0.03770207613706589,
      "learning_rate": 1.442709470304976e-05,
      "loss": 0.0455,
      "step": 43900
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.10206503421068192,
      "learning_rate": 1.4414253611556983e-05,
      "loss": 0.0423,
      "step": 44000
    },
    {
      "epoch": 1.408,
      "eval_accuracy": 0.99009,
      "eval_f1": 0.9900904784547742,
      "eval_loss": 0.03986356034874916,
      "eval_precision": 0.9900932283159651,
      "eval_recall": 0.99009,
      "eval_runtime": 775.1079,
      "eval_samples_per_second": 129.014,
      "eval_steps_per_second": 8.063,
      "step": 44000
    },
    {
      "epoch": 1.4112,
      "grad_norm": 0.6451414823532104,
      "learning_rate": 1.4401412520064206e-05,
      "loss": 0.044,
      "step": 44100
    },
    {
      "epoch": 1.4144,
      "grad_norm": 0.03619956597685814,
      "learning_rate": 1.438857142857143e-05,
      "loss": 0.0386,
      "step": 44200
    },
    {
      "epoch": 1.4176,
      "grad_norm": 0.005635638255625963,
      "learning_rate": 1.4375730337078653e-05,
      "loss": 0.0371,
      "step": 44300
    },
    {
      "epoch": 1.4208,
      "grad_norm": 20.394947052001953,
      "learning_rate": 1.4362889245585876e-05,
      "loss": 0.0468,
      "step": 44400
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.008449492044746876,
      "learning_rate": 1.4350048154093099e-05,
      "loss": 0.0536,
      "step": 44500
    },
    {
      "epoch": 1.4272,
      "grad_norm": 0.06385083496570587,
      "learning_rate": 1.4337207062600322e-05,
      "loss": 0.0383,
      "step": 44600
    },
    {
      "epoch": 1.4304000000000001,
      "grad_norm": 0.016077406704425812,
      "learning_rate": 1.4324365971107545e-05,
      "loss": 0.0341,
      "step": 44700
    },
    {
      "epoch": 1.4336,
      "grad_norm": 0.012415707111358643,
      "learning_rate": 1.4311524879614768e-05,
      "loss": 0.0356,
      "step": 44800
    },
    {
      "epoch": 1.4368,
      "grad_norm": 0.03126490116119385,
      "learning_rate": 1.4298683788121991e-05,
      "loss": 0.0456,
      "step": 44900
    },
    {
      "epoch": 1.44,
      "grad_norm": 5.324023723602295,
      "learning_rate": 1.4285842696629215e-05,
      "loss": 0.0653,
      "step": 45000
    },
    {
      "epoch": 1.4432,
      "grad_norm": 0.02962222322821617,
      "learning_rate": 1.4273001605136438e-05,
      "loss": 0.0664,
      "step": 45100
    },
    {
      "epoch": 1.4464000000000001,
      "grad_norm": 0.03100472316145897,
      "learning_rate": 1.426016051364366e-05,
      "loss": 0.0494,
      "step": 45200
    },
    {
      "epoch": 1.4496,
      "grad_norm": 8.572321891784668,
      "learning_rate": 1.4247319422150884e-05,
      "loss": 0.0276,
      "step": 45300
    },
    {
      "epoch": 1.4527999999999999,
      "grad_norm": 0.004455466754734516,
      "learning_rate": 1.4234478330658109e-05,
      "loss": 0.0292,
      "step": 45400
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.03781688213348389,
      "learning_rate": 1.4221637239165332e-05,
      "loss": 0.0407,
      "step": 45500
    },
    {
      "epoch": 1.4592,
      "grad_norm": 10.108696937561035,
      "learning_rate": 1.4208796147672552e-05,
      "loss": 0.0531,
      "step": 45600
    },
    {
      "epoch": 1.4624,
      "grad_norm": 0.059839170426130295,
      "learning_rate": 1.4195955056179775e-05,
      "loss": 0.0373,
      "step": 45700
    },
    {
      "epoch": 1.4656,
      "grad_norm": 0.00919304322451353,
      "learning_rate": 1.4183113964686998e-05,
      "loss": 0.0402,
      "step": 45800
    },
    {
      "epoch": 1.4687999999999999,
      "grad_norm": 12.830222129821777,
      "learning_rate": 1.4170272873194221e-05,
      "loss": 0.0321,
      "step": 45900
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.006019544322043657,
      "learning_rate": 1.4157431781701444e-05,
      "loss": 0.0327,
      "step": 46000
    },
    {
      "epoch": 1.4752,
      "grad_norm": 0.024647433310747147,
      "learning_rate": 1.4144590690208669e-05,
      "loss": 0.0386,
      "step": 46100
    },
    {
      "epoch": 1.4784,
      "grad_norm": 0.01691538281738758,
      "learning_rate": 1.4131749598715892e-05,
      "loss": 0.0523,
      "step": 46200
    },
    {
      "epoch": 1.4816,
      "grad_norm": 0.007636231370270252,
      "learning_rate": 1.4118908507223115e-05,
      "loss": 0.043,
      "step": 46300
    },
    {
      "epoch": 1.4848,
      "grad_norm": 0.04239976033568382,
      "learning_rate": 1.4106067415730338e-05,
      "loss": 0.0422,
      "step": 46400
    },
    {
      "epoch": 1.488,
      "grad_norm": 6.693536758422852,
      "learning_rate": 1.4093226324237562e-05,
      "loss": 0.0412,
      "step": 46500
    },
    {
      "epoch": 1.4912,
      "grad_norm": 0.014838839881122112,
      "learning_rate": 1.4080385232744785e-05,
      "loss": 0.038,
      "step": 46600
    },
    {
      "epoch": 1.4944,
      "grad_norm": 9.719799995422363,
      "learning_rate": 1.4067544141252008e-05,
      "loss": 0.056,
      "step": 46700
    },
    {
      "epoch": 1.4976,
      "grad_norm": 4.120741367340088,
      "learning_rate": 1.4054703049759231e-05,
      "loss": 0.0453,
      "step": 46800
    },
    {
      "epoch": 1.5008,
      "grad_norm": 0.019338663667440414,
      "learning_rate": 1.4041861958266454e-05,
      "loss": 0.0355,
      "step": 46900
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.015643298625946045,
      "learning_rate": 1.4029020866773677e-05,
      "loss": 0.0276,
      "step": 47000
    },
    {
      "epoch": 1.5072,
      "grad_norm": 11.701508522033691,
      "learning_rate": 1.40161797752809e-05,
      "loss": 0.0513,
      "step": 47100
    },
    {
      "epoch": 1.5104,
      "grad_norm": 0.00980925839394331,
      "learning_rate": 1.4003338683788124e-05,
      "loss": 0.0304,
      "step": 47200
    },
    {
      "epoch": 1.5135999999999998,
      "grad_norm": 0.018979301676154137,
      "learning_rate": 1.3990497592295347e-05,
      "loss": 0.0443,
      "step": 47300
    },
    {
      "epoch": 1.5168,
      "grad_norm": 9.20014762878418,
      "learning_rate": 1.397765650080257e-05,
      "loss": 0.0411,
      "step": 47400
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.06917817145586014,
      "learning_rate": 1.3964815409309793e-05,
      "loss": 0.0414,
      "step": 47500
    },
    {
      "epoch": 1.5232,
      "grad_norm": 22.683095932006836,
      "learning_rate": 1.3951974317817016e-05,
      "loss": 0.0338,
      "step": 47600
    },
    {
      "epoch": 1.5264,
      "grad_norm": 0.03558173030614853,
      "learning_rate": 1.393913322632424e-05,
      "loss": 0.0396,
      "step": 47700
    },
    {
      "epoch": 1.5295999999999998,
      "grad_norm": 0.12180989980697632,
      "learning_rate": 1.3926292134831462e-05,
      "loss": 0.0359,
      "step": 47800
    },
    {
      "epoch": 1.5328,
      "grad_norm": 2.8462178707122803,
      "learning_rate": 1.3913451043338686e-05,
      "loss": 0.0234,
      "step": 47900
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.032463911920785904,
      "learning_rate": 1.3900609951845907e-05,
      "loss": 0.0389,
      "step": 48000
    },
    {
      "epoch": 1.536,
      "eval_accuracy": 0.98882,
      "eval_f1": 0.9888222770915966,
      "eval_loss": 0.051280781626701355,
      "eval_precision": 0.9888728773724597,
      "eval_recall": 0.98882,
      "eval_runtime": 775.3173,
      "eval_samples_per_second": 128.979,
      "eval_steps_per_second": 8.061,
      "step": 48000
    },
    {
      "epoch": 1.5392000000000001,
      "grad_norm": 6.397082805633545,
      "learning_rate": 1.388776886035313e-05,
      "loss": 0.035,
      "step": 48100
    },
    {
      "epoch": 1.5424,
      "grad_norm": 0.11342862993478775,
      "learning_rate": 1.3874927768860353e-05,
      "loss": 0.0541,
      "step": 48200
    },
    {
      "epoch": 1.5455999999999999,
      "grad_norm": 0.02208523452281952,
      "learning_rate": 1.3862086677367576e-05,
      "loss": 0.0506,
      "step": 48300
    },
    {
      "epoch": 1.5488,
      "grad_norm": 0.15493257343769073,
      "learning_rate": 1.38492455858748e-05,
      "loss": 0.0283,
      "step": 48400
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.004556428641080856,
      "learning_rate": 1.3836404494382023e-05,
      "loss": 0.0583,
      "step": 48500
    },
    {
      "epoch": 1.5552000000000001,
      "grad_norm": 0.10255400836467743,
      "learning_rate": 1.3823563402889246e-05,
      "loss": 0.0379,
      "step": 48600
    },
    {
      "epoch": 1.5584,
      "grad_norm": 0.04857850447297096,
      "learning_rate": 1.3810722311396469e-05,
      "loss": 0.0362,
      "step": 48700
    },
    {
      "epoch": 1.5615999999999999,
      "grad_norm": 0.07100783288478851,
      "learning_rate": 1.3797881219903692e-05,
      "loss": 0.0691,
      "step": 48800
    },
    {
      "epoch": 1.5648,
      "grad_norm": 10.417929649353027,
      "learning_rate": 1.3785040128410915e-05,
      "loss": 0.0555,
      "step": 48900
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.06572629511356354,
      "learning_rate": 1.3772199036918138e-05,
      "loss": 0.0373,
      "step": 49000
    },
    {
      "epoch": 1.5712000000000002,
      "grad_norm": 0.47768735885620117,
      "learning_rate": 1.3759357945425361e-05,
      "loss": 0.0483,
      "step": 49100
    },
    {
      "epoch": 1.5744,
      "grad_norm": 0.07465988397598267,
      "learning_rate": 1.3746516853932586e-05,
      "loss": 0.0327,
      "step": 49200
    },
    {
      "epoch": 1.5776,
      "grad_norm": 0.018970176577568054,
      "learning_rate": 1.373367576243981e-05,
      "loss": 0.0493,
      "step": 49300
    },
    {
      "epoch": 1.5808,
      "grad_norm": 0.0272968802601099,
      "learning_rate": 1.3720834670947033e-05,
      "loss": 0.0418,
      "step": 49400
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.010071586817502975,
      "learning_rate": 1.3707993579454256e-05,
      "loss": 0.0416,
      "step": 49500
    },
    {
      "epoch": 1.5872000000000002,
      "grad_norm": 0.13110236823558807,
      "learning_rate": 1.3695152487961479e-05,
      "loss": 0.0353,
      "step": 49600
    },
    {
      "epoch": 1.5904,
      "grad_norm": 0.9969918727874756,
      "learning_rate": 1.3682311396468702e-05,
      "loss": 0.046,
      "step": 49700
    },
    {
      "epoch": 1.5936,
      "grad_norm": 0.010477591305971146,
      "learning_rate": 1.3669470304975925e-05,
      "loss": 0.0351,
      "step": 49800
    },
    {
      "epoch": 1.5968,
      "grad_norm": 14.14805793762207,
      "learning_rate": 1.3656629213483148e-05,
      "loss": 0.0376,
      "step": 49900
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.004804316442459822,
      "learning_rate": 1.3643788121990371e-05,
      "loss": 0.0381,
      "step": 50000
    },
    {
      "epoch": 1.6032,
      "grad_norm": 0.9756079912185669,
      "learning_rate": 1.3630947030497595e-05,
      "loss": 0.0495,
      "step": 50100
    },
    {
      "epoch": 1.6064,
      "grad_norm": 0.005941998213529587,
      "learning_rate": 1.3618105939004818e-05,
      "loss": 0.0404,
      "step": 50200
    },
    {
      "epoch": 1.6096,
      "grad_norm": 0.017781252041459084,
      "learning_rate": 1.3605264847512039e-05,
      "loss": 0.0467,
      "step": 50300
    },
    {
      "epoch": 1.6128,
      "grad_norm": 0.11217786371707916,
      "learning_rate": 1.3592423756019262e-05,
      "loss": 0.0348,
      "step": 50400
    },
    {
      "epoch": 1.616,
      "grad_norm": 1.8749943971633911,
      "learning_rate": 1.3579582664526485e-05,
      "loss": 0.0323,
      "step": 50500
    },
    {
      "epoch": 1.6192,
      "grad_norm": 0.07430779188871384,
      "learning_rate": 1.3566741573033709e-05,
      "loss": 0.0481,
      "step": 50600
    },
    {
      "epoch": 1.6223999999999998,
      "grad_norm": 0.22179456055164337,
      "learning_rate": 1.3553900481540932e-05,
      "loss": 0.0424,
      "step": 50700
    },
    {
      "epoch": 1.6256,
      "grad_norm": 0.020223159343004227,
      "learning_rate": 1.3541059390048155e-05,
      "loss": 0.0398,
      "step": 50800
    },
    {
      "epoch": 1.6288,
      "grad_norm": 0.021107584238052368,
      "learning_rate": 1.3528218298555378e-05,
      "loss": 0.0326,
      "step": 50900
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.047376956790685654,
      "learning_rate": 1.3515377207062601e-05,
      "loss": 0.0544,
      "step": 51000
    },
    {
      "epoch": 1.6352,
      "grad_norm": 17.578815460205078,
      "learning_rate": 1.3502536115569824e-05,
      "loss": 0.0629,
      "step": 51100
    },
    {
      "epoch": 1.6383999999999999,
      "grad_norm": 18.477867126464844,
      "learning_rate": 1.3489695024077047e-05,
      "loss": 0.039,
      "step": 51200
    },
    {
      "epoch": 1.6416,
      "grad_norm": 1.2129385471343994,
      "learning_rate": 1.347685393258427e-05,
      "loss": 0.0442,
      "step": 51300
    },
    {
      "epoch": 1.6448,
      "grad_norm": 0.21100889146327972,
      "learning_rate": 1.3464012841091494e-05,
      "loss": 0.0588,
      "step": 51400
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.01275007613003254,
      "learning_rate": 1.3451171749598717e-05,
      "loss": 0.0467,
      "step": 51500
    },
    {
      "epoch": 1.6512,
      "grad_norm": 8.823915481567383,
      "learning_rate": 1.343833065810594e-05,
      "loss": 0.0379,
      "step": 51600
    },
    {
      "epoch": 1.6543999999999999,
      "grad_norm": 4.7289252281188965,
      "learning_rate": 1.3425489566613163e-05,
      "loss": 0.041,
      "step": 51700
    },
    {
      "epoch": 1.6576,
      "grad_norm": 0.026279212906956673,
      "learning_rate": 1.3412648475120386e-05,
      "loss": 0.0551,
      "step": 51800
    },
    {
      "epoch": 1.6608,
      "grad_norm": 9.168363571166992,
      "learning_rate": 1.339980738362761e-05,
      "loss": 0.0357,
      "step": 51900
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.06355811655521393,
      "learning_rate": 1.3386966292134832e-05,
      "loss": 0.0416,
      "step": 52000
    },
    {
      "epoch": 1.6640000000000001,
      "eval_accuracy": 0.99082,
      "eval_f1": 0.9908199660129274,
      "eval_loss": 0.035849522799253464,
      "eval_precision": 0.9908199447350458,
      "eval_recall": 0.99082,
      "eval_runtime": 774.0001,
      "eval_samples_per_second": 129.199,
      "eval_steps_per_second": 8.075,
      "step": 52000
    },
    {
      "epoch": 1.6672,
      "grad_norm": 4.400208473205566,
      "learning_rate": 1.3374125200642056e-05,
      "loss": 0.0351,
      "step": 52100
    },
    {
      "epoch": 1.6703999999999999,
      "grad_norm": 5.015504837036133,
      "learning_rate": 1.3361284109149279e-05,
      "loss": 0.0528,
      "step": 52200
    },
    {
      "epoch": 1.6736,
      "grad_norm": 0.026230236515402794,
      "learning_rate": 1.3348443017656504e-05,
      "loss": 0.0435,
      "step": 52300
    },
    {
      "epoch": 1.6768,
      "grad_norm": 8.737045288085938,
      "learning_rate": 1.3335601926163727e-05,
      "loss": 0.0466,
      "step": 52400
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.2274281084537506,
      "learning_rate": 1.332276083467095e-05,
      "loss": 0.0561,
      "step": 52500
    },
    {
      "epoch": 1.6832,
      "grad_norm": 0.006623820401728153,
      "learning_rate": 1.330991974317817e-05,
      "loss": 0.0284,
      "step": 52600
    },
    {
      "epoch": 1.6864,
      "grad_norm": 0.0021350777242332697,
      "learning_rate": 1.3297078651685393e-05,
      "loss": 0.0511,
      "step": 52700
    },
    {
      "epoch": 1.6896,
      "grad_norm": 0.018413754180073738,
      "learning_rate": 1.3284237560192616e-05,
      "loss": 0.0543,
      "step": 52800
    },
    {
      "epoch": 1.6928,
      "grad_norm": 0.1010914072394371,
      "learning_rate": 1.3271396468699839e-05,
      "loss": 0.0453,
      "step": 52900
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.004039776977151632,
      "learning_rate": 1.3258555377207064e-05,
      "loss": 0.0338,
      "step": 53000
    },
    {
      "epoch": 1.6992,
      "grad_norm": 14.739033699035645,
      "learning_rate": 1.3245714285714287e-05,
      "loss": 0.0382,
      "step": 53100
    },
    {
      "epoch": 1.7024,
      "grad_norm": 0.016198845580220222,
      "learning_rate": 1.323287319422151e-05,
      "loss": 0.016,
      "step": 53200
    },
    {
      "epoch": 1.7056,
      "grad_norm": 2.079624891281128,
      "learning_rate": 1.3220032102728733e-05,
      "loss": 0.0627,
      "step": 53300
    },
    {
      "epoch": 1.7088,
      "grad_norm": 0.11790735274553299,
      "learning_rate": 1.3207191011235956e-05,
      "loss": 0.0592,
      "step": 53400
    },
    {
      "epoch": 1.712,
      "grad_norm": 1.2402265071868896,
      "learning_rate": 1.319434991974318e-05,
      "loss": 0.0355,
      "step": 53500
    },
    {
      "epoch": 1.7151999999999998,
      "grad_norm": 0.004012857098132372,
      "learning_rate": 1.3181508828250403e-05,
      "loss": 0.0233,
      "step": 53600
    },
    {
      "epoch": 1.7184,
      "grad_norm": 9.97103500366211,
      "learning_rate": 1.3168667736757626e-05,
      "loss": 0.0416,
      "step": 53700
    },
    {
      "epoch": 1.7216,
      "grad_norm": 0.00929461419582367,
      "learning_rate": 1.3155826645264849e-05,
      "loss": 0.0245,
      "step": 53800
    },
    {
      "epoch": 1.7248,
      "grad_norm": 0.014831352047622204,
      "learning_rate": 1.3142985553772072e-05,
      "loss": 0.0568,
      "step": 53900
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.017993494868278503,
      "learning_rate": 1.3130144462279295e-05,
      "loss": 0.0316,
      "step": 54000
    },
    {
      "epoch": 1.7311999999999999,
      "grad_norm": 7.752192974090576,
      "learning_rate": 1.3117303370786518e-05,
      "loss": 0.0435,
      "step": 54100
    },
    {
      "epoch": 1.7344,
      "grad_norm": 0.022409453988075256,
      "learning_rate": 1.3104462279293741e-05,
      "loss": 0.0272,
      "step": 54200
    },
    {
      "epoch": 1.7376,
      "grad_norm": 0.022196965292096138,
      "learning_rate": 1.3091621187800965e-05,
      "loss": 0.0389,
      "step": 54300
    },
    {
      "epoch": 1.7408000000000001,
      "grad_norm": 0.010344170965254307,
      "learning_rate": 1.3078780096308188e-05,
      "loss": 0.0292,
      "step": 54400
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.026820389553904533,
      "learning_rate": 1.306593900481541e-05,
      "loss": 0.0318,
      "step": 54500
    },
    {
      "epoch": 1.7471999999999999,
      "grad_norm": 3.427290916442871,
      "learning_rate": 1.3053097913322634e-05,
      "loss": 0.04,
      "step": 54600
    },
    {
      "epoch": 1.7504,
      "grad_norm": 0.0476866252720356,
      "learning_rate": 1.3040256821829857e-05,
      "loss": 0.0356,
      "step": 54700
    },
    {
      "epoch": 1.7536,
      "grad_norm": 0.16033174097537994,
      "learning_rate": 1.302741573033708e-05,
      "loss": 0.0465,
      "step": 54800
    },
    {
      "epoch": 1.7568000000000001,
      "grad_norm": 0.00891600176692009,
      "learning_rate": 1.3014574638844302e-05,
      "loss": 0.0354,
      "step": 54900
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.09468699991703033,
      "learning_rate": 1.3001733547351525e-05,
      "loss": 0.049,
      "step": 55000
    },
    {
      "epoch": 1.7631999999999999,
      "grad_norm": 0.11951547861099243,
      "learning_rate": 1.2988892455858748e-05,
      "loss": 0.0488,
      "step": 55100
    },
    {
      "epoch": 1.7664,
      "grad_norm": 0.008669690228998661,
      "learning_rate": 1.2976051364365971e-05,
      "loss": 0.0418,
      "step": 55200
    },
    {
      "epoch": 1.7696,
      "grad_norm": 5.866086006164551,
      "learning_rate": 1.2963210272873194e-05,
      "loss": 0.0452,
      "step": 55300
    },
    {
      "epoch": 1.7728000000000002,
      "grad_norm": 0.007491165306419134,
      "learning_rate": 1.2950369181380417e-05,
      "loss": 0.0331,
      "step": 55400
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.10585305094718933,
      "learning_rate": 1.293752808988764e-05,
      "loss": 0.0406,
      "step": 55500
    },
    {
      "epoch": 1.7792,
      "grad_norm": 0.3077317178249359,
      "learning_rate": 1.2924686998394864e-05,
      "loss": 0.0455,
      "step": 55600
    },
    {
      "epoch": 1.7824,
      "grad_norm": 0.008049139752984047,
      "learning_rate": 1.2911845906902087e-05,
      "loss": 0.0271,
      "step": 55700
    },
    {
      "epoch": 1.7856,
      "grad_norm": 0.005238874349743128,
      "learning_rate": 1.289900481540931e-05,
      "loss": 0.0312,
      "step": 55800
    },
    {
      "epoch": 1.7888,
      "grad_norm": 0.011361650191247463,
      "learning_rate": 1.2886163723916533e-05,
      "loss": 0.0387,
      "step": 55900
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.0051416209898889065,
      "learning_rate": 1.2873322632423756e-05,
      "loss": 0.0374,
      "step": 56000
    },
    {
      "epoch": 1.792,
      "eval_accuracy": 0.99052,
      "eval_f1": 0.9905207896506175,
      "eval_loss": 0.03697649762034416,
      "eval_precision": 0.9905285934060213,
      "eval_recall": 0.99052,
      "eval_runtime": 764.6577,
      "eval_samples_per_second": 130.777,
      "eval_steps_per_second": 8.174,
      "step": 56000
    },
    {
      "epoch": 1.7952,
      "grad_norm": 0.0088375024497509,
      "learning_rate": 1.2860481540930981e-05,
      "loss": 0.0303,
      "step": 56100
    },
    {
      "epoch": 1.7984,
      "grad_norm": 0.0020017733331769705,
      "learning_rate": 1.2847640449438204e-05,
      "loss": 0.0222,
      "step": 56200
    },
    {
      "epoch": 1.8016,
      "grad_norm": 0.0033814297057688236,
      "learning_rate": 1.2834799357945427e-05,
      "loss": 0.0399,
      "step": 56300
    },
    {
      "epoch": 1.8048,
      "grad_norm": 0.09427639096975327,
      "learning_rate": 1.282195826645265e-05,
      "loss": 0.0325,
      "step": 56400
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.02629452385008335,
      "learning_rate": 1.2809117174959874e-05,
      "loss": 0.0265,
      "step": 56500
    },
    {
      "epoch": 1.8112,
      "grad_norm": 0.24074454605579376,
      "learning_rate": 1.2796276083467097e-05,
      "loss": 0.0473,
      "step": 56600
    },
    {
      "epoch": 1.8144,
      "grad_norm": 0.05172184109687805,
      "learning_rate": 1.278343499197432e-05,
      "loss": 0.0392,
      "step": 56700
    },
    {
      "epoch": 1.8176,
      "grad_norm": 0.042050667107105255,
      "learning_rate": 1.2770593900481543e-05,
      "loss": 0.0365,
      "step": 56800
    },
    {
      "epoch": 1.8208,
      "grad_norm": 0.011465741321444511,
      "learning_rate": 1.2757752808988766e-05,
      "loss": 0.0301,
      "step": 56900
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 1.5907392501831055,
      "learning_rate": 1.274491171749599e-05,
      "loss": 0.0489,
      "step": 57000
    },
    {
      "epoch": 1.8272,
      "grad_norm": 0.01520006824284792,
      "learning_rate": 1.2732070626003212e-05,
      "loss": 0.0425,
      "step": 57100
    },
    {
      "epoch": 1.8304,
      "grad_norm": 0.03128599748015404,
      "learning_rate": 1.2719229534510436e-05,
      "loss": 0.016,
      "step": 57200
    },
    {
      "epoch": 1.8336000000000001,
      "grad_norm": 0.07054321467876434,
      "learning_rate": 1.2706388443017657e-05,
      "loss": 0.0455,
      "step": 57300
    },
    {
      "epoch": 1.8368,
      "grad_norm": 1.4368666410446167,
      "learning_rate": 1.269354735152488e-05,
      "loss": 0.0507,
      "step": 57400
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.012565890327095985,
      "learning_rate": 1.2680706260032103e-05,
      "loss": 0.041,
      "step": 57500
    },
    {
      "epoch": 1.8432,
      "grad_norm": 1.327050805091858,
      "learning_rate": 1.2667865168539326e-05,
      "loss": 0.0167,
      "step": 57600
    },
    {
      "epoch": 1.8464,
      "grad_norm": 5.873330593109131,
      "learning_rate": 1.265502407704655e-05,
      "loss": 0.0417,
      "step": 57700
    },
    {
      "epoch": 1.8496000000000001,
      "grad_norm": 1.0156079530715942,
      "learning_rate": 1.2642182985553773e-05,
      "loss": 0.051,
      "step": 57800
    },
    {
      "epoch": 1.8528,
      "grad_norm": 0.2399500459432602,
      "learning_rate": 1.2629341894060996e-05,
      "loss": 0.0235,
      "step": 57900
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.5918147563934326,
      "learning_rate": 1.2616500802568219e-05,
      "loss": 0.0383,
      "step": 58000
    },
    {
      "epoch": 1.8592,
      "grad_norm": 0.8496889472007751,
      "learning_rate": 1.2603659711075442e-05,
      "loss": 0.0329,
      "step": 58100
    },
    {
      "epoch": 1.8624,
      "grad_norm": 3.212545871734619,
      "learning_rate": 1.2590818619582665e-05,
      "loss": 0.0363,
      "step": 58200
    },
    {
      "epoch": 1.8656000000000001,
      "grad_norm": 0.2524072527885437,
      "learning_rate": 1.2577977528089888e-05,
      "loss": 0.0443,
      "step": 58300
    },
    {
      "epoch": 1.8688,
      "grad_norm": 0.09237070381641388,
      "learning_rate": 1.2565136436597111e-05,
      "loss": 0.0394,
      "step": 58400
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.08935701102018356,
      "learning_rate": 1.2552295345104335e-05,
      "loss": 0.0251,
      "step": 58500
    },
    {
      "epoch": 1.8752,
      "grad_norm": 0.03011847473680973,
      "learning_rate": 1.2539454253611558e-05,
      "loss": 0.0364,
      "step": 58600
    },
    {
      "epoch": 1.8784,
      "grad_norm": 0.00672591058537364,
      "learning_rate": 1.2526613162118781e-05,
      "loss": 0.0453,
      "step": 58700
    },
    {
      "epoch": 1.8816000000000002,
      "grad_norm": 0.01110851764678955,
      "learning_rate": 1.2513772070626004e-05,
      "loss": 0.0316,
      "step": 58800
    },
    {
      "epoch": 1.8848,
      "grad_norm": 13.021896362304688,
      "learning_rate": 1.2500930979133227e-05,
      "loss": 0.0438,
      "step": 58900
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.01617710292339325,
      "learning_rate": 1.248808988764045e-05,
      "loss": 0.0281,
      "step": 59000
    },
    {
      "epoch": 1.8912,
      "grad_norm": 0.126037135720253,
      "learning_rate": 1.2475248796147675e-05,
      "loss": 0.0361,
      "step": 59100
    },
    {
      "epoch": 1.8944,
      "grad_norm": 0.1865486055612564,
      "learning_rate": 1.2462407704654898e-05,
      "loss": 0.0294,
      "step": 59200
    },
    {
      "epoch": 1.8976,
      "grad_norm": 24.230648040771484,
      "learning_rate": 1.2449566613162121e-05,
      "loss": 0.0418,
      "step": 59300
    },
    {
      "epoch": 1.9008,
      "grad_norm": 0.008240806870162487,
      "learning_rate": 1.2436725521669345e-05,
      "loss": 0.0369,
      "step": 59400
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.13642114400863647,
      "learning_rate": 1.2423884430176568e-05,
      "loss": 0.0264,
      "step": 59500
    },
    {
      "epoch": 1.9072,
      "grad_norm": 7.658884525299072,
      "learning_rate": 1.2411043338683787e-05,
      "loss": 0.0358,
      "step": 59600
    },
    {
      "epoch": 1.9104,
      "grad_norm": 0.019852541387081146,
      "learning_rate": 1.239820224719101e-05,
      "loss": 0.0431,
      "step": 59700
    },
    {
      "epoch": 1.9136,
      "grad_norm": 0.2717871367931366,
      "learning_rate": 1.2385361155698234e-05,
      "loss": 0.0429,
      "step": 59800
    },
    {
      "epoch": 1.9167999999999998,
      "grad_norm": 0.020897701382637024,
      "learning_rate": 1.2372520064205458e-05,
      "loss": 0.0372,
      "step": 59900
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.02349219284951687,
      "learning_rate": 1.2359678972712682e-05,
      "loss": 0.0441,
      "step": 60000
    },
    {
      "epoch": 1.92,
      "eval_accuracy": 0.99049,
      "eval_f1": 0.9904909638313073,
      "eval_loss": 0.03547532483935356,
      "eval_precision": 0.9905025162088448,
      "eval_recall": 0.99049,
      "eval_runtime": 764.9462,
      "eval_samples_per_second": 130.728,
      "eval_steps_per_second": 8.171,
      "step": 60000
    },
    {
      "epoch": 1.9232,
      "grad_norm": 0.016066577285528183,
      "learning_rate": 1.2346837881219905e-05,
      "loss": 0.0324,
      "step": 60100
    },
    {
      "epoch": 1.9264000000000001,
      "grad_norm": 1.0818510055541992,
      "learning_rate": 1.2333996789727128e-05,
      "loss": 0.0333,
      "step": 60200
    },
    {
      "epoch": 1.9296,
      "grad_norm": 1.9333336353302002,
      "learning_rate": 1.2321155698234351e-05,
      "loss": 0.0465,
      "step": 60300
    },
    {
      "epoch": 1.9327999999999999,
      "grad_norm": 0.015184523537755013,
      "learning_rate": 1.2308314606741574e-05,
      "loss": 0.031,
      "step": 60400
    },
    {
      "epoch": 1.936,
      "grad_norm": 3.1265370845794678,
      "learning_rate": 1.2295473515248797e-05,
      "loss": 0.0265,
      "step": 60500
    },
    {
      "epoch": 1.9392,
      "grad_norm": 0.06526759266853333,
      "learning_rate": 1.228263242375602e-05,
      "loss": 0.0396,
      "step": 60600
    },
    {
      "epoch": 1.9424000000000001,
      "grad_norm": 0.051179856061935425,
      "learning_rate": 1.2269791332263244e-05,
      "loss": 0.0457,
      "step": 60700
    },
    {
      "epoch": 1.9456,
      "grad_norm": 0.012131915427744389,
      "learning_rate": 1.2256950240770467e-05,
      "loss": 0.0377,
      "step": 60800
    },
    {
      "epoch": 1.9487999999999999,
      "grad_norm": 6.335480690002441,
      "learning_rate": 1.224410914927769e-05,
      "loss": 0.0378,
      "step": 60900
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.6301658749580383,
      "learning_rate": 1.2231268057784913e-05,
      "loss": 0.0442,
      "step": 61000
    },
    {
      "epoch": 1.9552,
      "grad_norm": 0.3388197124004364,
      "learning_rate": 1.2218426966292136e-05,
      "loss": 0.0489,
      "step": 61100
    },
    {
      "epoch": 1.9584000000000001,
      "grad_norm": 0.007041617762297392,
      "learning_rate": 1.220558587479936e-05,
      "loss": 0.0384,
      "step": 61200
    },
    {
      "epoch": 1.9616,
      "grad_norm": 0.10959050804376602,
      "learning_rate": 1.2192744783306582e-05,
      "loss": 0.0463,
      "step": 61300
    },
    {
      "epoch": 1.9647999999999999,
      "grad_norm": 3.765045642852783,
      "learning_rate": 1.2179903691813806e-05,
      "loss": 0.043,
      "step": 61400
    },
    {
      "epoch": 1.968,
      "grad_norm": 2.442903757095337,
      "learning_rate": 1.2167062600321029e-05,
      "loss": 0.0431,
      "step": 61500
    },
    {
      "epoch": 1.9712,
      "grad_norm": 3.0291242599487305,
      "learning_rate": 1.2154221508828252e-05,
      "loss": 0.0439,
      "step": 61600
    },
    {
      "epoch": 1.9744000000000002,
      "grad_norm": 0.1264086663722992,
      "learning_rate": 1.2141380417335475e-05,
      "loss": 0.029,
      "step": 61700
    },
    {
      "epoch": 1.9776,
      "grad_norm": 0.09380912035703659,
      "learning_rate": 1.2128539325842698e-05,
      "loss": 0.05,
      "step": 61800
    },
    {
      "epoch": 1.9808,
      "grad_norm": 0.012730620801448822,
      "learning_rate": 1.211569823434992e-05,
      "loss": 0.0235,
      "step": 61900
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.04120282083749771,
      "learning_rate": 1.2102857142857143e-05,
      "loss": 0.0342,
      "step": 62000
    },
    {
      "epoch": 1.9872,
      "grad_norm": 0.22701594233512878,
      "learning_rate": 1.2090016051364366e-05,
      "loss": 0.0499,
      "step": 62100
    },
    {
      "epoch": 1.9904,
      "grad_norm": 0.005121626891195774,
      "learning_rate": 1.2077174959871589e-05,
      "loss": 0.0223,
      "step": 62200
    },
    {
      "epoch": 1.9936,
      "grad_norm": 4.5423583984375,
      "learning_rate": 1.2064333868378812e-05,
      "loss": 0.0351,
      "step": 62300
    },
    {
      "epoch": 1.9968,
      "grad_norm": 0.6799706816673279,
      "learning_rate": 1.2051492776886035e-05,
      "loss": 0.0374,
      "step": 62400
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4670400023460388,
      "learning_rate": 1.2038651685393258e-05,
      "loss": 0.0389,
      "step": 62500
    },
    {
      "epoch": 2.0032,
      "grad_norm": 0.0014514782233163714,
      "learning_rate": 1.2025810593900481e-05,
      "loss": 0.0407,
      "step": 62600
    },
    {
      "epoch": 2.0064,
      "grad_norm": 10.322093963623047,
      "learning_rate": 1.2012969502407705e-05,
      "loss": 0.0364,
      "step": 62700
    },
    {
      "epoch": 2.0096,
      "grad_norm": 0.7346168160438538,
      "learning_rate": 1.2000128410914928e-05,
      "loss": 0.063,
      "step": 62800
    },
    {
      "epoch": 2.0128,
      "grad_norm": 15.471858978271484,
      "learning_rate": 1.1987287319422153e-05,
      "loss": 0.0365,
      "step": 62900
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.22428256273269653,
      "learning_rate": 1.1974446227929376e-05,
      "loss": 0.0437,
      "step": 63000
    },
    {
      "epoch": 2.0192,
      "grad_norm": 5.6665849685668945,
      "learning_rate": 1.1961605136436599e-05,
      "loss": 0.0448,
      "step": 63100
    },
    {
      "epoch": 2.0224,
      "grad_norm": 0.011902675963938236,
      "learning_rate": 1.1948764044943822e-05,
      "loss": 0.0309,
      "step": 63200
    },
    {
      "epoch": 2.0256,
      "grad_norm": 0.01199142262339592,
      "learning_rate": 1.1935922953451045e-05,
      "loss": 0.0181,
      "step": 63300
    },
    {
      "epoch": 2.0288,
      "grad_norm": 0.2028602510690689,
      "learning_rate": 1.1923081861958268e-05,
      "loss": 0.0433,
      "step": 63400
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.05186166614294052,
      "learning_rate": 1.1910240770465491e-05,
      "loss": 0.0349,
      "step": 63500
    },
    {
      "epoch": 2.0352,
      "grad_norm": 8.039327621459961,
      "learning_rate": 1.1897399678972715e-05,
      "loss": 0.0447,
      "step": 63600
    },
    {
      "epoch": 2.0384,
      "grad_norm": 0.013709252700209618,
      "learning_rate": 1.1884558587479938e-05,
      "loss": 0.0264,
      "step": 63700
    },
    {
      "epoch": 2.0416,
      "grad_norm": 0.12741540372371674,
      "learning_rate": 1.187171749598716e-05,
      "loss": 0.0285,
      "step": 63800
    },
    {
      "epoch": 2.0448,
      "grad_norm": 38.967525482177734,
      "learning_rate": 1.1858876404494384e-05,
      "loss": 0.0406,
      "step": 63900
    },
    {
      "epoch": 2.048,
      "grad_norm": 10.748799324035645,
      "learning_rate": 1.1846035313001607e-05,
      "loss": 0.0358,
      "step": 64000
    },
    {
      "epoch": 2.048,
      "eval_accuracy": 0.99072,
      "eval_f1": 0.9907211797405157,
      "eval_loss": 0.038402359932661057,
      "eval_precision": 0.990739513426471,
      "eval_recall": 0.99072,
      "eval_runtime": 764.7435,
      "eval_samples_per_second": 130.763,
      "eval_steps_per_second": 8.173,
      "step": 64000
    }
  ],
  "logging_steps": 100,
  "max_steps": 156250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 4000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7177787451207846e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}