{
  "best_global_step": 32000,
  "best_metric": 0.9879419419991998,
  "best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-32000",
  "epoch": 1.024,
  "eval_steps": 4000,
  "global_step": 32000,
  "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
    }
  ],
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3588330900845235e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}