{
  "best_metric": 0.014622284099459648,
  "best_model_checkpoint": "sentiment-distillation-smollm/checkpoint-1875",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 9.476157188415527,
      "learning_rate": 1.597444089456869e-06,
      "loss": 1.074,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 10.569486618041992,
      "learning_rate": 3.194888178913738e-06,
      "loss": 1.0372,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 8.480586051940918,
      "learning_rate": 4.792332268370607e-06,
      "loss": 0.9365,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 6.626020908355713,
      "learning_rate": 6.389776357827476e-06,
      "loss": 0.8842,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 12.755849838256836,
      "learning_rate": 7.987220447284345e-06,
      "loss": 0.9098,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 7.676151275634766,
      "learning_rate": 9.584664536741214e-06,
      "loss": 0.7348,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 5.426048278808594,
      "learning_rate": 1.1182108626198083e-05,
      "loss": 0.4936,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.9603002071380615,
      "learning_rate": 1.2779552715654951e-05,
      "loss": 0.3438,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 3.396127700805664,
      "learning_rate": 1.4376996805111822e-05,
      "loss": 0.1482,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 4.765463829040527,
      "learning_rate": 1.597444089456869e-05,
      "loss": 0.1855,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.04306459426879883,
      "learning_rate": 1.757188498402556e-05,
      "loss": 0.1788,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.04322272166609764,
      "learning_rate": 1.9169329073482428e-05,
      "loss": 0.1233,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.053582437336444855,
      "learning_rate": 2.07667731629393e-05,
      "loss": 0.0908,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 8.254273414611816,
      "learning_rate": 2.2364217252396165e-05,
      "loss": 0.1362,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.054730091243982315,
      "learning_rate": 2.3961661341853036e-05,
      "loss": 0.072,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.0763891264796257,
      "learning_rate": 2.5559105431309903e-05,
      "loss": 0.1823,
      "step": 160
    },
    {
      "epoch": 0.272,
      "grad_norm": 6.117145538330078,
      "learning_rate": 2.7156549520766773e-05,
      "loss": 0.0963,
      "step": 170
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.8248779773712158,
      "learning_rate": 2.8753993610223644e-05,
      "loss": 0.2741,
      "step": 180
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.014617039822041988,
      "learning_rate": 3.0351437699680514e-05,
      "loss": 0.0691,
      "step": 190
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.316850423812866,
      "learning_rate": 3.194888178913738e-05,
      "loss": 0.0186,
      "step": 200
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.010957750491797924,
      "learning_rate": 3.354632587859425e-05,
      "loss": 0.1676,
      "step": 210
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.02525000460445881,
      "learning_rate": 3.514376996805112e-05,
      "loss": 0.1689,
      "step": 220
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.010558371432125568,
      "learning_rate": 3.6741214057507985e-05,
      "loss": 0.1759,
      "step": 230
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.009851646609604359,
      "learning_rate": 3.8338658146964856e-05,
      "loss": 0.1253,
      "step": 240
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.009924142621457577,
      "learning_rate": 3.9936102236421726e-05,
      "loss": 0.1141,
      "step": 250
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.00981380045413971,
      "learning_rate": 4.15335463258786e-05,
      "loss": 0.1227,
      "step": 260
    },
    {
      "epoch": 0.432,
      "grad_norm": 4.685519218444824,
      "learning_rate": 4.313099041533547e-05,
      "loss": 0.2,
      "step": 270
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.1163793802261353,
      "learning_rate": 4.472843450479233e-05,
      "loss": 0.073,
      "step": 280
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.01022783387452364,
      "learning_rate": 4.632587859424921e-05,
      "loss": 0.1287,
      "step": 290
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.018457185477018356,
      "learning_rate": 4.792332268370607e-05,
      "loss": 0.0794,
      "step": 300
    },
    {
      "epoch": 0.496,
      "grad_norm": 10.666505813598633,
      "learning_rate": 4.952076677316294e-05,
      "loss": 0.17,
      "step": 310
    },
    {
      "epoch": 0.512,
      "grad_norm": 2.132030725479126,
      "learning_rate": 4.987553342816501e-05,
      "loss": 0.0952,
      "step": 320
    },
    {
      "epoch": 0.528,
      "grad_norm": 11.730767250061035,
      "learning_rate": 4.969772403982931e-05,
      "loss": 0.1995,
      "step": 330
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.01148867979645729,
      "learning_rate": 4.95199146514936e-05,
      "loss": 0.1019,
      "step": 340
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.047348447144031525,
      "learning_rate": 4.9342105263157894e-05,
      "loss": 0.0706,
      "step": 350
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.010151210241019726,
      "learning_rate": 4.916429587482219e-05,
      "loss": 0.0878,
      "step": 360
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.4587936997413635,
      "learning_rate": 4.8986486486486486e-05,
      "loss": 0.0864,
      "step": 370
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.1231539249420166,
      "learning_rate": 4.8808677098150786e-05,
      "loss": 0.0096,
      "step": 380
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.005615161266177893,
      "learning_rate": 4.863086770981508e-05,
      "loss": 0.1351,
      "step": 390
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.02301601506769657,
      "learning_rate": 4.845305832147938e-05,
      "loss": 0.0363,
      "step": 400
    },
    {
      "epoch": 0.656,
      "grad_norm": 3.3105900287628174,
      "learning_rate": 4.827524893314367e-05,
      "loss": 0.0764,
      "step": 410
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.0835251584649086,
      "learning_rate": 4.809743954480797e-05,
      "loss": 0.0238,
      "step": 420
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.0839819684624672,
      "learning_rate": 4.7919630156472264e-05,
      "loss": 0.1182,
      "step": 430
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.0160073135048151,
      "learning_rate": 4.774182076813656e-05,
      "loss": 0.1647,
      "step": 440
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.09903815388679504,
      "learning_rate": 4.756401137980086e-05,
      "loss": 0.138,
      "step": 450
    },
    {
      "epoch": 0.736,
      "grad_norm": 8.14660930633545,
      "learning_rate": 4.738620199146515e-05,
      "loss": 0.0731,
      "step": 460
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.07308264076709747,
      "learning_rate": 4.720839260312945e-05,
      "loss": 0.017,
      "step": 470
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.8220946788787842,
      "learning_rate": 4.703058321479374e-05,
      "loss": 0.0299,
      "step": 480
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.007219772785902023,
      "learning_rate": 4.685277382645804e-05,
      "loss": 0.0162,
      "step": 490
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.009510455653071404,
      "learning_rate": 4.6674964438122335e-05,
      "loss": 0.0011,
      "step": 500
    },
    {
      "epoch": 0.816,
      "grad_norm": 9.018925666809082,
      "learning_rate": 4.6497155049786634e-05,
      "loss": 0.1081,
      "step": 510
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.008953461423516273,
      "learning_rate": 4.631934566145093e-05,
      "loss": 0.0494,
      "step": 520
    },
    {
      "epoch": 0.848,
      "grad_norm": 10.596187591552734,
      "learning_rate": 4.614153627311522e-05,
      "loss": 0.0158,
      "step": 530
    },
    {
      "epoch": 0.864,
      "grad_norm": 2.3671252727508545,
      "learning_rate": 4.596372688477952e-05,
      "loss": 0.0816,
      "step": 540
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.002445698482915759,
      "learning_rate": 4.578591749644381e-05,
      "loss": 0.0042,
      "step": 550
    },
    {
      "epoch": 0.896,
      "grad_norm": 11.779576301574707,
      "learning_rate": 4.560810810810811e-05,
      "loss": 0.1067,
      "step": 560
    },
    {
      "epoch": 0.912,
      "grad_norm": 7.589051246643066,
      "learning_rate": 4.5430298719772405e-05,
      "loss": 0.0853,
      "step": 570
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.11888572573661804,
      "learning_rate": 4.5252489331436705e-05,
      "loss": 0.0317,
      "step": 580
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.07746365666389465,
      "learning_rate": 4.5074679943101e-05,
      "loss": 0.2303,
      "step": 590
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.004527238663285971,
      "learning_rate": 4.489687055476529e-05,
      "loss": 0.0665,
      "step": 600
    },
    {
      "epoch": 0.976,
      "grad_norm": 4.120000839233398,
      "learning_rate": 4.471906116642959e-05,
      "loss": 0.0546,
      "step": 610
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.0016751989023759961,
      "learning_rate": 4.4541251778093884e-05,
      "loss": 0.0051,
      "step": 620
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9939879759519038,
      "eval_f1_macro": 0.9861065168559803,
      "eval_f1_micro": 0.9939879759519038,
      "eval_f1_weighted": 0.9939373007372426,
      "eval_loss": 0.015998151153326035,
      "eval_precision_macro": 0.9959514170040485,
      "eval_precision_micro": 0.9939879759519038,
      "eval_precision_weighted": 0.994060996486901,
      "eval_recall_macro": 0.9770065284178188,
      "eval_recall_micro": 0.9939879759519038,
      "eval_recall_weighted": 0.9939879759519038,
      "eval_runtime": 10.7994,
      "eval_samples_per_second": 46.206,
      "eval_steps_per_second": 2.963,
      "step": 625
    },
    {
      "epoch": 1.008,
      "grad_norm": 4.363436222076416,
      "learning_rate": 4.436344238975818e-05,
      "loss": 0.0119,
      "step": 630
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.002567918971180916,
      "learning_rate": 4.4185633001422476e-05,
      "loss": 0.0736,
      "step": 640
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.00732471002265811,
      "learning_rate": 4.4007823613086776e-05,
      "loss": 0.0001,
      "step": 650
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.002863505156710744,
      "learning_rate": 4.383001422475107e-05,
      "loss": 0.0608,
      "step": 660
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.008520668372511864,
      "learning_rate": 4.365220483641537e-05,
      "loss": 0.0125,
      "step": 670
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.001538406009785831,
      "learning_rate": 4.347439544807966e-05,
      "loss": 0.0653,
      "step": 680
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.001671103062108159,
      "learning_rate": 4.3296586059743954e-05,
      "loss": 0.081,
      "step": 690
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.20056261122226715,
      "learning_rate": 4.3118776671408254e-05,
      "loss": 0.0057,
      "step": 700
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.008405996486544609,
      "learning_rate": 4.294096728307255e-05,
      "loss": 0.0091,
      "step": 710
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.19218170642852783,
      "learning_rate": 4.2763157894736847e-05,
      "loss": 0.0019,
      "step": 720
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.07524432241916656,
      "learning_rate": 4.258534850640114e-05,
      "loss": 0.0952,
      "step": 730
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.0015570322284474969,
      "learning_rate": 4.240753911806544e-05,
      "loss": 0.0435,
      "step": 740
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0036333040334284306,
      "learning_rate": 4.222972972972973e-05,
      "loss": 0.0207,
      "step": 750
    },
    {
      "epoch": 1.216,
      "grad_norm": 9.78964900970459,
      "learning_rate": 4.205192034139403e-05,
      "loss": 0.1004,
      "step": 760
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.0014888375299051404,
      "learning_rate": 4.187411095305832e-05,
      "loss": 0.0671,
      "step": 770
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.023692140355706215,
      "learning_rate": 4.169630156472262e-05,
      "loss": 0.0026,
      "step": 780
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.004593148361891508,
      "learning_rate": 4.151849217638692e-05,
      "loss": 0.0423,
      "step": 790
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.003923716489225626,
      "learning_rate": 4.134068278805121e-05,
      "loss": 0.0236,
      "step": 800
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.002044517546892166,
      "learning_rate": 4.116287339971551e-05,
      "loss": 0.005,
      "step": 810
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.022982032969594002,
      "learning_rate": 4.09850640113798e-05,
      "loss": 0.0697,
      "step": 820
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.23058412969112396,
      "learning_rate": 4.08072546230441e-05,
      "loss": 0.1222,
      "step": 830
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.0017761716153472662,
      "learning_rate": 4.0629445234708395e-05,
      "loss": 0.0022,
      "step": 840
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.12850730121135712,
      "learning_rate": 4.0451635846372695e-05,
      "loss": 0.0189,
      "step": 850
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.0014099746476858854,
      "learning_rate": 4.027382645803698e-05,
      "loss": 0.0001,
      "step": 860
    },
    {
      "epoch": 1.392,
      "grad_norm": 10.44194507598877,
      "learning_rate": 4.009601706970128e-05,
      "loss": 0.1423,
      "step": 870
    },
    {
      "epoch": 1.408,
      "grad_norm": 5.446048736572266,
      "learning_rate": 3.9918207681365574e-05,
      "loss": 0.1013,
      "step": 880
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.017437923699617386,
      "learning_rate": 3.9740398293029873e-05,
      "loss": 0.0002,
      "step": 890
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.007926377467811108,
      "learning_rate": 3.956258890469417e-05,
      "loss": 0.0661,
      "step": 900
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.0029465279076248407,
      "learning_rate": 3.9384779516358466e-05,
      "loss": 0.0338,
      "step": 910
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.0010107713751494884,
      "learning_rate": 3.9206970128022766e-05,
      "loss": 0.0171,
      "step": 920
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.036259789019823074,
      "learning_rate": 3.902916073968706e-05,
      "loss": 0.0004,
      "step": 930
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.7286566495895386,
      "learning_rate": 3.885135135135135e-05,
      "loss": 0.014,
      "step": 940
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.008453834801912308,
      "learning_rate": 3.8673541963015645e-05,
      "loss": 0.0002,
      "step": 950
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.1271582841873169,
      "learning_rate": 3.8495732574679944e-05,
      "loss": 0.0043,
      "step": 960
    },
    {
      "epoch": 1.552,
      "grad_norm": 6.197739124298096,
      "learning_rate": 3.831792318634424e-05,
      "loss": 0.0075,
      "step": 970
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.008371386677026749,
      "learning_rate": 3.814011379800854e-05,
      "loss": 0.0299,
      "step": 980
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.0011657042196020484,
      "learning_rate": 3.796230440967283e-05,
      "loss": 0.1188,
      "step": 990
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.010952652432024479,
      "learning_rate": 3.778449502133713e-05,
      "loss": 0.0116,
      "step": 1000
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.0010061347857117653,
      "learning_rate": 3.760668563300143e-05,
      "loss": 0.0043,
      "step": 1010
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.06395132839679718,
      "learning_rate": 3.742887624466572e-05,
      "loss": 0.0445,
      "step": 1020
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.001108819618821144,
      "learning_rate": 3.7251066856330015e-05,
      "loss": 0.0323,
      "step": 1030
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.0014280881732702255,
      "learning_rate": 3.707325746799431e-05,
      "loss": 0.0008,
      "step": 1040
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.0012123563792556524,
      "learning_rate": 3.689544807965861e-05,
      "loss": 0.0014,
      "step": 1050
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.0011878483928740025,
      "learning_rate": 3.67176386913229e-05,
      "loss": 0.0524,
      "step": 1060
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.0037567925173789263,
      "learning_rate": 3.65398293029872e-05,
      "loss": 0.0237,
      "step": 1070
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.002096337964758277,
      "learning_rate": 3.636201991465149e-05,
      "loss": 0.0334,
      "step": 1080
    },
    {
      "epoch": 1.744,
      "grad_norm": 8.111098289489746,
      "learning_rate": 3.618421052631579e-05,
      "loss": 0.1467,
      "step": 1090
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.0023632964584976435,
      "learning_rate": 3.600640113798009e-05,
      "loss": 0.0003,
      "step": 1100
    },
    {
      "epoch": 1.776,
      "grad_norm": 9.071378707885742,
      "learning_rate": 3.5828591749644385e-05,
      "loss": 0.0176,
      "step": 1110
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.08811729401350021,
      "learning_rate": 3.565078236130868e-05,
      "loss": 0.1454,
      "step": 1120
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.0101834237575531,
      "learning_rate": 3.547297297297297e-05,
      "loss": 0.0172,
      "step": 1130
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.1676841378211975,
      "learning_rate": 3.529516358463727e-05,
      "loss": 0.049,
      "step": 1140
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.043762240558862686,
      "learning_rate": 3.5117354196301564e-05,
      "loss": 0.0432,
      "step": 1150
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.011058449745178223,
      "learning_rate": 3.4939544807965863e-05,
      "loss": 0.001,
      "step": 1160
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.0018902173032984138,
      "learning_rate": 3.4761735419630156e-05,
      "loss": 0.0399,
      "step": 1170
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.001800389145500958,
      "learning_rate": 3.4583926031294456e-05,
      "loss": 0.0184,
      "step": 1180
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.06505569815635681,
      "learning_rate": 3.440611664295875e-05,
      "loss": 0.0073,
      "step": 1190
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.5011488199234009,
      "learning_rate": 3.422830725462304e-05,
      "loss": 0.0007,
      "step": 1200
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.013254979625344276,
      "learning_rate": 3.405049786628734e-05,
      "loss": 0.0059,
      "step": 1210
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.7582728266716003,
      "learning_rate": 3.3872688477951634e-05,
      "loss": 0.0013,
      "step": 1220
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.009909105487167835,
      "learning_rate": 3.3694879089615934e-05,
      "loss": 0.0002,
      "step": 1230
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.000718823226634413,
      "learning_rate": 3.351706970128023e-05,
      "loss": 0.0047,
      "step": 1240
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6642739772796631,
      "learning_rate": 3.333926031294453e-05,
      "loss": 0.0015,
      "step": 1250
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9919839679358717,
      "eval_f1_macro": 0.9810672282141238,
      "eval_f1_micro": 0.9919839679358717,
      "eval_f1_weighted": 0.992107547860045,
      "eval_loss": 0.019453825429081917,
      "eval_precision_macro": 0.9692164931816348,
      "eval_precision_micro": 0.9919839679358717,
      "eval_precision_weighted": 0.9925061936994298,
      "eval_recall_macro": 0.9942915690866512,
      "eval_recall_micro": 0.9919839679358717,
      "eval_recall_weighted": 0.9919839679358717,
      "eval_runtime": 10.636,
      "eval_samples_per_second": 46.916,
      "eval_steps_per_second": 3.009,
      "step": 1250
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.005395730957388878,
      "learning_rate": 3.316145092460882e-05,
      "loss": 0.0001,
      "step": 1260
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.0008304046932607889,
      "learning_rate": 3.298364153627312e-05,
      "loss": 0.0001,
      "step": 1270
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.0007791437674313784,
      "learning_rate": 3.280583214793741e-05,
      "loss": 0.0001,
      "step": 1280
    },
    {
      "epoch": 2.064,
      "grad_norm": 0.0008820474613457918,
      "learning_rate": 3.2628022759601705e-05,
      "loss": 0.0001,
      "step": 1290
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.000594152370467782,
      "learning_rate": 3.2450213371266005e-05,
      "loss": 0.0002,
      "step": 1300
    },
    {
      "epoch": 2.096,
      "grad_norm": 0.0006243674433790147,
      "learning_rate": 3.22724039829303e-05,
      "loss": 0.0022,
      "step": 1310
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.0007709413184784353,
      "learning_rate": 3.20945945945946e-05,
      "loss": 0.0154,
      "step": 1320
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.004626740701496601,
      "learning_rate": 3.191678520625889e-05,
      "loss": 0.0012,
      "step": 1330
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.002739989897236228,
      "learning_rate": 3.173897581792319e-05,
      "loss": 0.0004,
      "step": 1340
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.007507917005568743,
      "learning_rate": 3.156116642958748e-05,
      "loss": 0.0001,
      "step": 1350
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.004014975391328335,
      "learning_rate": 3.138335704125178e-05,
      "loss": 0.001,
      "step": 1360
    },
    {
      "epoch": 2.192,
      "grad_norm": 0.000455196452094242,
      "learning_rate": 3.1205547652916076e-05,
      "loss": 0.0005,
      "step": 1370
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.00030664558289572597,
      "learning_rate": 3.102773826458037e-05,
      "loss": 0.0265,
      "step": 1380
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.00043227567221038043,
      "learning_rate": 3.084992887624467e-05,
      "loss": 0.0001,
      "step": 1390
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.0481143593788147,
      "learning_rate": 3.067211948790896e-05,
      "loss": 0.0023,
      "step": 1400
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.005968974903225899,
      "learning_rate": 3.0494310099573257e-05,
      "loss": 0.0025,
      "step": 1410
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.21466164290905,
      "learning_rate": 3.0316500711237557e-05,
      "loss": 0.0003,
      "step": 1420
    },
    {
      "epoch": 2.288,
      "grad_norm": 0.0018357799854129553,
      "learning_rate": 3.0138691322901853e-05,
      "loss": 0.0001,
      "step": 1430
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.0004517412162385881,
      "learning_rate": 2.996088193456615e-05,
      "loss": 0.0001,
      "step": 1440
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.005384071730077267,
      "learning_rate": 2.9783072546230446e-05,
      "loss": 0.002,
      "step": 1450
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.00046941509936004877,
      "learning_rate": 2.9605263157894735e-05,
      "loss": 0.0001,
      "step": 1460
    },
    {
      "epoch": 2.352,
      "grad_norm": 0.011709867045283318,
      "learning_rate": 2.9427453769559032e-05,
      "loss": 0.0001,
      "step": 1470
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.03616934269666672,
      "learning_rate": 2.9249644381223328e-05,
      "loss": 0.0008,
      "step": 1480
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.0006385542219504714,
      "learning_rate": 2.9071834992887624e-05,
      "loss": 0.0001,
      "step": 1490
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.0423965454101562,
      "learning_rate": 2.889402560455192e-05,
      "loss": 0.0021,
      "step": 1500
    },
    {
      "epoch": 2.416,
      "grad_norm": 0.21064622700214386,
      "learning_rate": 2.8716216216216217e-05,
      "loss": 0.0003,
      "step": 1510
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.0016910170670598745,
      "learning_rate": 2.8538406827880517e-05,
      "loss": 0.0001,
      "step": 1520
    },
    {
      "epoch": 2.448,
      "grad_norm": 0.0004065225657541305,
      "learning_rate": 2.8360597439544813e-05,
      "loss": 0.0004,
      "step": 1530
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.0006998078897595406,
      "learning_rate": 2.8182788051209103e-05,
      "loss": 0.0001,
      "step": 1540
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.0057923863641917706,
      "learning_rate": 2.80049786628734e-05,
      "loss": 0.0012,
      "step": 1550
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.00030601295293308794,
      "learning_rate": 2.7827169274537695e-05,
      "loss": 0.0236,
      "step": 1560
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.00045617681462317705,
      "learning_rate": 2.764935988620199e-05,
      "loss": 0.0001,
      "step": 1570
    },
    {
      "epoch": 2.528,
      "grad_norm": 0.00044945545960217714,
      "learning_rate": 2.7471550497866288e-05,
      "loss": 0.0001,
      "step": 1580
    },
    {
      "epoch": 2.544,
      "grad_norm": 0.0003521046892274171,
      "learning_rate": 2.7293741109530584e-05,
      "loss": 0.0263,
      "step": 1590
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.008946732617914677,
      "learning_rate": 2.711593172119488e-05,
      "loss": 0.0006,
      "step": 1600
    },
    {
      "epoch": 2.576,
      "grad_norm": 0.09531024098396301,
      "learning_rate": 2.6938122332859177e-05,
      "loss": 0.0003,
      "step": 1610
    },
    {
      "epoch": 2.592,
      "grad_norm": 0.0010131685994565487,
      "learning_rate": 2.6760312944523473e-05,
      "loss": 0.0001,
      "step": 1620
    },
    {
      "epoch": 2.608,
      "grad_norm": 0.0016723967855796218,
      "learning_rate": 2.6582503556187766e-05,
      "loss": 0.0018,
      "step": 1630
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.008407480083405972,
      "learning_rate": 2.6404694167852062e-05,
      "loss": 0.0344,
      "step": 1640
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.001671052654273808,
      "learning_rate": 2.622688477951636e-05,
      "loss": 0.0005,
      "step": 1650
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.0003514339041430503,
      "learning_rate": 2.6049075391180655e-05,
      "loss": 0.0001,
      "step": 1660
    },
    {
      "epoch": 2.672,
      "grad_norm": 0.00044292688835412264,
      "learning_rate": 2.587126600284495e-05,
      "loss": 0.0017,
      "step": 1670
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.00033179231104440987,
      "learning_rate": 2.5693456614509247e-05,
      "loss": 0.0243,
      "step": 1680
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 0.0023233199026435614,
      "learning_rate": 2.5515647226173544e-05,
      "loss": 0.0001,
      "step": 1690
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.0012358427047729492,
      "learning_rate": 2.533783783783784e-05,
      "loss": 0.0002,
      "step": 1700
    },
    {
      "epoch": 2.7359999999999998,
      "grad_norm": 0.00035215960815548897,
      "learning_rate": 2.5160028449502136e-05,
      "loss": 0.0235,
      "step": 1710
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.24424146115779877,
      "learning_rate": 2.4982219061166433e-05,
      "loss": 0.0005,
      "step": 1720
    },
    {
      "epoch": 2.768,
      "grad_norm": 2.014695167541504,
      "learning_rate": 2.480440967283073e-05,
      "loss": 0.0111,
      "step": 1730
    },
    {
      "epoch": 2.784,
      "grad_norm": 0.00039951372309587896,
      "learning_rate": 2.4626600284495022e-05,
      "loss": 0.0004,
      "step": 1740
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.0016597098438069224,
      "learning_rate": 2.4448790896159318e-05,
      "loss": 0.0002,
      "step": 1750
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.010242385789752007,
      "learning_rate": 2.4270981507823614e-05,
      "loss": 0.0001,
      "step": 1760
    },
    {
      "epoch": 2.832,
      "grad_norm": 0.0023806928656995296,
      "learning_rate": 2.409317211948791e-05,
      "loss": 0.0001,
      "step": 1770
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.01970355026423931,
      "learning_rate": 2.3915362731152204e-05,
      "loss": 0.0183,
      "step": 1780
    },
    {
      "epoch": 2.864,
      "grad_norm": 0.0002463227428961545,
      "learning_rate": 2.37375533428165e-05,
      "loss": 0.0,
      "step": 1790
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.000822290952783078,
      "learning_rate": 2.35597439544808e-05,
      "loss": 0.0001,
      "step": 1800
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.0026505696587264538,
      "learning_rate": 2.3381934566145096e-05,
      "loss": 0.0004,
      "step": 1810
    },
    {
      "epoch": 2.912,
      "grad_norm": 0.0005039023817516863,
      "learning_rate": 2.320412517780939e-05,
      "loss": 0.0001,
      "step": 1820
    },
    {
      "epoch": 2.928,
      "grad_norm": 0.009028232656419277,
      "learning_rate": 2.3026315789473685e-05,
      "loss": 0.0001,
      "step": 1830
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.002705842722207308,
      "learning_rate": 2.284850640113798e-05,
      "loss": 0.0003,
      "step": 1840
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.00383372837677598,
      "learning_rate": 2.2670697012802278e-05,
      "loss": 0.0017,
      "step": 1850
    },
    {
      "epoch": 2.976,
      "grad_norm": 0.00024894202942959964,
      "learning_rate": 2.2492887624466574e-05,
      "loss": 0.0002,
      "step": 1860
    },
    {
      "epoch": 2.992,
      "grad_norm": 0.0009176091407425702,
      "learning_rate": 2.2315078236130867e-05,
      "loss": 0.0,
      "step": 1870
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9939879759519038,
      "eval_f1_macro": 0.9910040909369707,
      "eval_f1_micro": 0.9939879759519038,
      "eval_f1_weighted": 0.9939809297459037,
      "eval_loss": 0.014622284099459648,
      "eval_precision_macro": 0.9959514170040485,
      "eval_precision_micro": 0.9939879759519038,
      "eval_precision_weighted": 0.994060996486901,
      "eval_recall_macro": 0.9862711213517666,
      "eval_recall_micro": 0.9939879759519038,
      "eval_recall_weighted": 0.9939879759519038,
      "eval_runtime": 10.5217,
      "eval_samples_per_second": 47.426,
      "eval_steps_per_second": 3.041,
      "step": 1875
    }
  ],
  "logging_steps": 10,
  "max_steps": 3125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2446967439360000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}