{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6657789613848203,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003328894806924101,
      "grad_norm": 37.75,
      "learning_rate": 1.9933422103861518e-05,
      "loss": 1.4084,
      "step": 10
    },
    {
      "epoch": 0.006657789613848202,
      "grad_norm": 12.125,
      "learning_rate": 1.9866844207723038e-05,
      "loss": 1.0474,
      "step": 20
    },
    {
      "epoch": 0.009986684420772303,
      "grad_norm": 45.25,
      "learning_rate": 1.9800266311584554e-05,
      "loss": 1.2455,
      "step": 30
    },
    {
      "epoch": 0.013315579227696404,
      "grad_norm": 13.9375,
      "learning_rate": 1.9733688415446073e-05,
      "loss": 1.1969,
      "step": 40
    },
    {
      "epoch": 0.016644474034620507,
      "grad_norm": 32.0,
      "learning_rate": 1.966711051930759e-05,
      "loss": 1.1659,
      "step": 50
    },
    {
      "epoch": 0.019973368841544607,
      "grad_norm": 19.0,
      "learning_rate": 1.960053262316911e-05,
      "loss": 1.1159,
      "step": 60
    },
    {
      "epoch": 0.02330226364846871,
      "grad_norm": 27.5,
      "learning_rate": 1.953395472703063e-05,
      "loss": 1.1861,
      "step": 70
    },
    {
      "epoch": 0.02663115845539281,
      "grad_norm": 17.5,
      "learning_rate": 1.9467376830892145e-05,
      "loss": 1.1073,
      "step": 80
    },
    {
      "epoch": 0.02996005326231691,
      "grad_norm": 33.75,
      "learning_rate": 1.9400798934753665e-05,
      "loss": 1.1506,
      "step": 90
    },
    {
      "epoch": 0.033288948069241014,
      "grad_norm": 9.5,
      "learning_rate": 1.933422103861518e-05,
      "loss": 1.246,
      "step": 100
    },
    {
      "epoch": 0.03661784287616511,
      "grad_norm": 11.3125,
      "learning_rate": 1.92676431424767e-05,
      "loss": 1.1708,
      "step": 110
    },
    {
      "epoch": 0.03994673768308921,
      "grad_norm": 14.375,
      "learning_rate": 1.9201065246338217e-05,
      "loss": 1.1302,
      "step": 120
    },
    {
      "epoch": 0.043275632490013316,
      "grad_norm": 20.625,
      "learning_rate": 1.9134487350199737e-05,
      "loss": 1.0537,
      "step": 130
    },
    {
      "epoch": 0.04660452729693742,
      "grad_norm": 21.75,
      "learning_rate": 1.9067909454061253e-05,
      "loss": 1.0669,
      "step": 140
    },
    {
      "epoch": 0.049933422103861515,
      "grad_norm": 14.125,
      "learning_rate": 1.900133155792277e-05,
      "loss": 1.0482,
      "step": 150
    },
    {
      "epoch": 0.05326231691078562,
      "grad_norm": 27.625,
      "learning_rate": 1.893475366178429e-05,
      "loss": 1.1468,
      "step": 160
    },
    {
      "epoch": 0.05659121171770972,
      "grad_norm": 4.53125,
      "learning_rate": 1.8868175765645805e-05,
      "loss": 1.092,
      "step": 170
    },
    {
      "epoch": 0.05992010652463382,
      "grad_norm": 32.5,
      "learning_rate": 1.8801597869507325e-05,
      "loss": 1.2208,
      "step": 180
    },
    {
      "epoch": 0.06324900133155792,
      "grad_norm": 56.0,
      "learning_rate": 1.873501997336884e-05,
      "loss": 1.2359,
      "step": 190
    },
    {
      "epoch": 0.06657789613848203,
      "grad_norm": 8.375,
      "learning_rate": 1.866844207723036e-05,
      "loss": 1.0712,
      "step": 200
    },
    {
      "epoch": 0.06990679094540612,
      "grad_norm": 26.375,
      "learning_rate": 1.860186418109188e-05,
      "loss": 1.0156,
      "step": 210
    },
    {
      "epoch": 0.07323568575233022,
      "grad_norm": 12.0,
      "learning_rate": 1.8535286284953397e-05,
      "loss": 1.0407,
      "step": 220
    },
    {
      "epoch": 0.07656458055925433,
      "grad_norm": 13.75,
      "learning_rate": 1.8468708388814916e-05,
      "loss": 1.0161,
      "step": 230
    },
    {
      "epoch": 0.07989347536617843,
      "grad_norm": 27.125,
      "learning_rate": 1.8402130492676432e-05,
      "loss": 1.1466,
      "step": 240
    },
    {
      "epoch": 0.08322237017310254,
      "grad_norm": 26.125,
      "learning_rate": 1.8335552596537952e-05,
      "loss": 1.3192,
      "step": 250
    },
    {
      "epoch": 0.08655126498002663,
      "grad_norm": 25.75,
      "learning_rate": 1.826897470039947e-05,
      "loss": 1.0628,
      "step": 260
    },
    {
      "epoch": 0.08988015978695073,
      "grad_norm": 29.25,
      "learning_rate": 1.8202396804260988e-05,
      "loss": 0.967,
      "step": 270
    },
    {
      "epoch": 0.09320905459387484,
      "grad_norm": 29.75,
      "learning_rate": 1.8135818908122504e-05,
      "loss": 1.0356,
      "step": 280
    },
    {
      "epoch": 0.09653794940079893,
      "grad_norm": 11.6875,
      "learning_rate": 1.806924101198402e-05,
      "loss": 0.9853,
      "step": 290
    },
    {
      "epoch": 0.09986684420772303,
      "grad_norm": 27.5,
      "learning_rate": 1.800266311584554e-05,
      "loss": 1.0279,
      "step": 300
    },
    {
      "epoch": 0.10319573901464714,
      "grad_norm": 5.65625,
      "learning_rate": 1.7936085219707056e-05,
      "loss": 1.0115,
      "step": 310
    },
    {
      "epoch": 0.10652463382157124,
      "grad_norm": 8.1875,
      "learning_rate": 1.7869507323568576e-05,
      "loss": 0.942,
      "step": 320
    },
    {
      "epoch": 0.10985352862849534,
      "grad_norm": 65.0,
      "learning_rate": 1.7802929427430096e-05,
      "loss": 1.0208,
      "step": 330
    },
    {
      "epoch": 0.11318242343541944,
      "grad_norm": 9.625,
      "learning_rate": 1.7736351531291612e-05,
      "loss": 1.1729,
      "step": 340
    },
    {
      "epoch": 0.11651131824234354,
      "grad_norm": 17.5,
      "learning_rate": 1.766977363515313e-05,
      "loss": 0.9322,
      "step": 350
    },
    {
      "epoch": 0.11984021304926765,
      "grad_norm": 28.125,
      "learning_rate": 1.7603195739014648e-05,
      "loss": 1.0417,
      "step": 360
    },
    {
      "epoch": 0.12316910785619174,
      "grad_norm": 18.25,
      "learning_rate": 1.7536617842876168e-05,
      "loss": 1.2491,
      "step": 370
    },
    {
      "epoch": 0.12649800266311584,
      "grad_norm": 27.375,
      "learning_rate": 1.7470039946737684e-05,
      "loss": 0.9388,
      "step": 380
    },
    {
      "epoch": 0.12982689747003995,
      "grad_norm": 22.125,
      "learning_rate": 1.7403462050599203e-05,
      "loss": 1.0488,
      "step": 390
    },
    {
      "epoch": 0.13315579227696406,
      "grad_norm": 21.25,
      "learning_rate": 1.733688415446072e-05,
      "loss": 0.9951,
      "step": 400
    },
    {
      "epoch": 0.13648468708388814,
      "grad_norm": 11.75,
      "learning_rate": 1.727030625832224e-05,
      "loss": 0.9212,
      "step": 410
    },
    {
      "epoch": 0.13981358189081225,
      "grad_norm": 16.25,
      "learning_rate": 1.7203728362183756e-05,
      "loss": 1.0548,
      "step": 420
    },
    {
      "epoch": 0.14314247669773636,
      "grad_norm": 19.875,
      "learning_rate": 1.7137150466045275e-05,
      "loss": 1.0238,
      "step": 430
    },
    {
      "epoch": 0.14647137150466044,
      "grad_norm": 18.875,
      "learning_rate": 1.707057256990679e-05,
      "loss": 1.0327,
      "step": 440
    },
    {
      "epoch": 0.14980026631158455,
      "grad_norm": 7.84375,
      "learning_rate": 1.7003994673768308e-05,
      "loss": 1.1155,
      "step": 450
    },
    {
      "epoch": 0.15312916111850866,
      "grad_norm": 14.125,
      "learning_rate": 1.693741677762983e-05,
      "loss": 0.9627,
      "step": 460
    },
    {
      "epoch": 0.15645805592543274,
      "grad_norm": 7.4375,
      "learning_rate": 1.6870838881491347e-05,
      "loss": 1.0216,
      "step": 470
    },
    {
      "epoch": 0.15978695073235685,
      "grad_norm": 9.375,
      "learning_rate": 1.6804260985352863e-05,
      "loss": 1.0489,
      "step": 480
    },
    {
      "epoch": 0.16311584553928096,
      "grad_norm": 19.5,
      "learning_rate": 1.6737683089214383e-05,
      "loss": 1.1254,
      "step": 490
    },
    {
      "epoch": 0.16644474034620507,
      "grad_norm": 26.125,
      "learning_rate": 1.66711051930759e-05,
      "loss": 1.0134,
      "step": 500
    },
    {
      "epoch": 0.16644474034620507,
      "eval_accuracy": 0.5015762402521985,
      "eval_loss": 0.9942083358764648,
      "eval_runtime": 211.8123,
      "eval_samples_per_second": 113.818,
      "eval_steps_per_second": 28.454,
      "step": 500
    },
    {
      "epoch": 0.16977363515312915,
      "grad_norm": 12.3125,
      "learning_rate": 1.660452729693742e-05,
      "loss": 1.0164,
      "step": 510
    },
    {
      "epoch": 0.17310252996005326,
      "grad_norm": 38.75,
      "learning_rate": 1.6537949400798935e-05,
      "loss": 1.0042,
      "step": 520
    },
    {
      "epoch": 0.17643142476697737,
      "grad_norm": 20.125,
      "learning_rate": 1.6471371504660455e-05,
      "loss": 0.9786,
      "step": 530
    },
    {
      "epoch": 0.17976031957390146,
      "grad_norm": 11.4375,
      "learning_rate": 1.640479360852197e-05,
      "loss": 0.9678,
      "step": 540
    },
    {
      "epoch": 0.18308921438082557,
      "grad_norm": 19.375,
      "learning_rate": 1.633821571238349e-05,
      "loss": 1.0477,
      "step": 550
    },
    {
      "epoch": 0.18641810918774968,
      "grad_norm": 16.75,
      "learning_rate": 1.6271637816245007e-05,
      "loss": 1.02,
      "step": 560
    },
    {
      "epoch": 0.18974700399467376,
      "grad_norm": 15.5,
      "learning_rate": 1.6205059920106527e-05,
      "loss": 0.9864,
      "step": 570
    },
    {
      "epoch": 0.19307589880159787,
      "grad_norm": 9.75,
      "learning_rate": 1.6138482023968043e-05,
      "loss": 1.0019,
      "step": 580
    },
    {
      "epoch": 0.19640479360852198,
      "grad_norm": 12.125,
      "learning_rate": 1.6071904127829563e-05,
      "loss": 0.9483,
      "step": 590
    },
    {
      "epoch": 0.19973368841544606,
      "grad_norm": 30.875,
      "learning_rate": 1.6005326231691082e-05,
      "loss": 1.0692,
      "step": 600
    },
    {
      "epoch": 0.20306258322237017,
      "grad_norm": 10.125,
      "learning_rate": 1.59387483355526e-05,
      "loss": 0.9279,
      "step": 610
    },
    {
      "epoch": 0.20639147802929428,
      "grad_norm": 11.6875,
      "learning_rate": 1.5872170439414115e-05,
      "loss": 0.941,
      "step": 620
    },
    {
      "epoch": 0.2097203728362184,
      "grad_norm": 3.03125,
      "learning_rate": 1.5805592543275634e-05,
      "loss": 1.0259,
      "step": 630
    },
    {
      "epoch": 0.21304926764314247,
      "grad_norm": 10.4375,
      "learning_rate": 1.573901464713715e-05,
      "loss": 0.9687,
      "step": 640
    },
    {
      "epoch": 0.21637816245006658,
      "grad_norm": 12.8125,
      "learning_rate": 1.567243675099867e-05,
      "loss": 0.9512,
      "step": 650
    },
    {
      "epoch": 0.2197070572569907,
      "grad_norm": 9.75,
      "learning_rate": 1.5605858854860187e-05,
      "loss": 0.9569,
      "step": 660
    },
    {
      "epoch": 0.22303595206391477,
      "grad_norm": 17.375,
      "learning_rate": 1.5539280958721706e-05,
      "loss": 0.9694,
      "step": 670
    },
    {
      "epoch": 0.22636484687083888,
      "grad_norm": 9.625,
      "learning_rate": 1.5472703062583222e-05,
      "loss": 0.97,
      "step": 680
    },
    {
      "epoch": 0.229693741677763,
      "grad_norm": 21.0,
      "learning_rate": 1.5406125166444742e-05,
      "loss": 1.0506,
      "step": 690
    },
    {
      "epoch": 0.23302263648468707,
      "grad_norm": 10.3125,
      "learning_rate": 1.533954727030626e-05,
      "loss": 0.9184,
      "step": 700
    },
    {
      "epoch": 0.23635153129161118,
      "grad_norm": 21.5,
      "learning_rate": 1.5272969374167778e-05,
      "loss": 1.005,
      "step": 710
    },
    {
      "epoch": 0.2396804260985353,
      "grad_norm": 4.40625,
      "learning_rate": 1.5206391478029296e-05,
      "loss": 0.8624,
      "step": 720
    },
    {
      "epoch": 0.24300932090545938,
      "grad_norm": 13.9375,
      "learning_rate": 1.5139813581890814e-05,
      "loss": 1.0051,
      "step": 730
    },
    {
      "epoch": 0.24633821571238348,
      "grad_norm": 16.625,
      "learning_rate": 1.5073235685752332e-05,
      "loss": 1.0378,
      "step": 740
    },
    {
      "epoch": 0.2496671105193076,
      "grad_norm": 6.4375,
      "learning_rate": 1.500665778961385e-05,
      "loss": 0.9191,
      "step": 750
    },
    {
      "epoch": 0.2529960053262317,
      "grad_norm": 5.5625,
      "learning_rate": 1.4940079893475368e-05,
      "loss": 0.9722,
      "step": 760
    },
    {
      "epoch": 0.2563249001331558,
      "grad_norm": 22.625,
      "learning_rate": 1.4873501997336886e-05,
      "loss": 1.014,
      "step": 770
    },
    {
      "epoch": 0.2596537949400799,
      "grad_norm": 21.0,
      "learning_rate": 1.4806924101198404e-05,
      "loss": 1.0986,
      "step": 780
    },
    {
      "epoch": 0.262982689747004,
      "grad_norm": 10.4375,
      "learning_rate": 1.4740346205059922e-05,
      "loss": 0.9672,
      "step": 790
    },
    {
      "epoch": 0.2663115845539281,
      "grad_norm": 17.0,
      "learning_rate": 1.467376830892144e-05,
      "loss": 0.9605,
      "step": 800
    },
    {
      "epoch": 0.26964047936085217,
      "grad_norm": 31.75,
      "learning_rate": 1.4607190412782957e-05,
      "loss": 1.0308,
      "step": 810
    },
    {
      "epoch": 0.2729693741677763,
      "grad_norm": 12.4375,
      "learning_rate": 1.4540612516644474e-05,
      "loss": 0.9268,
      "step": 820
    },
    {
      "epoch": 0.2762982689747004,
      "grad_norm": 17.125,
      "learning_rate": 1.4474034620505992e-05,
      "loss": 0.9656,
      "step": 830
    },
    {
      "epoch": 0.2796271637816245,
      "grad_norm": 4.53125,
      "learning_rate": 1.440745672436751e-05,
      "loss": 0.9865,
      "step": 840
    },
    {
      "epoch": 0.2829560585885486,
      "grad_norm": 22.625,
      "learning_rate": 1.434087882822903e-05,
      "loss": 1.1118,
      "step": 850
    },
    {
      "epoch": 0.2862849533954727,
      "grad_norm": 13.0,
      "learning_rate": 1.4274300932090547e-05,
      "loss": 1.0043,
      "step": 860
    },
    {
      "epoch": 0.28961384820239683,
      "grad_norm": 9.0625,
      "learning_rate": 1.4207723035952065e-05,
      "loss": 0.9768,
      "step": 870
    },
    {
      "epoch": 0.2929427430093209,
      "grad_norm": 6.75,
      "learning_rate": 1.4141145139813583e-05,
      "loss": 1.0237,
      "step": 880
    },
    {
      "epoch": 0.296271637816245,
      "grad_norm": 10.875,
      "learning_rate": 1.4074567243675101e-05,
      "loss": 1.1597,
      "step": 890
    },
    {
      "epoch": 0.2996005326231691,
      "grad_norm": 5.75,
      "learning_rate": 1.4007989347536619e-05,
      "loss": 0.7993,
      "step": 900
    },
    {
      "epoch": 0.3029294274300932,
      "grad_norm": 31.5,
      "learning_rate": 1.3941411451398137e-05,
      "loss": 0.9802,
      "step": 910
    },
    {
      "epoch": 0.3062583222370173,
      "grad_norm": 12.25,
      "learning_rate": 1.3874833555259655e-05,
      "loss": 0.9565,
      "step": 920
    },
    {
      "epoch": 0.30958721704394143,
      "grad_norm": 11.8125,
      "learning_rate": 1.3808255659121173e-05,
      "loss": 1.0024,
      "step": 930
    },
    {
      "epoch": 0.3129161118508655,
      "grad_norm": 16.625,
      "learning_rate": 1.3741677762982691e-05,
      "loss": 1.0209,
      "step": 940
    },
    {
      "epoch": 0.3162450066577896,
      "grad_norm": 13.375,
      "learning_rate": 1.3675099866844209e-05,
      "loss": 0.8767,
      "step": 950
    },
    {
      "epoch": 0.3195739014647137,
      "grad_norm": 20.875,
      "learning_rate": 1.3608521970705725e-05,
      "loss": 0.9642,
      "step": 960
    },
    {
      "epoch": 0.3229027962716378,
      "grad_norm": 17.25,
      "learning_rate": 1.3541944074567243e-05,
      "loss": 0.9508,
      "step": 970
    },
    {
      "epoch": 0.3262316910785619,
      "grad_norm": 22.25,
      "learning_rate": 1.3475366178428764e-05,
      "loss": 1.1324,
      "step": 980
    },
    {
      "epoch": 0.32956058588548603,
      "grad_norm": 11.5,
      "learning_rate": 1.3408788282290282e-05,
      "loss": 1.0655,
      "step": 990
    },
    {
      "epoch": 0.33288948069241014,
      "grad_norm": 15.625,
      "learning_rate": 1.3342210386151799e-05,
      "loss": 0.9608,
      "step": 1000
    },
    {
      "epoch": 0.33288948069241014,
      "eval_accuracy": 0.507300481168077,
      "eval_loss": 0.9467151165008545,
      "eval_runtime": 211.5004,
      "eval_samples_per_second": 113.986,
      "eval_steps_per_second": 28.496,
      "step": 1000
    },
    {
      "epoch": 0.3362183754993342,
      "grad_norm": 20.0,
      "learning_rate": 1.3275632490013317e-05,
      "loss": 1.0432,
      "step": 1010
    },
    {
      "epoch": 0.3395472703062583,
      "grad_norm": 22.375,
      "learning_rate": 1.3209054593874834e-05,
      "loss": 1.0393,
      "step": 1020
    },
    {
      "epoch": 0.3428761651131824,
      "grad_norm": 18.375,
      "learning_rate": 1.3142476697736352e-05,
      "loss": 1.0398,
      "step": 1030
    },
    {
      "epoch": 0.34620505992010653,
      "grad_norm": 17.25,
      "learning_rate": 1.307589880159787e-05,
      "loss": 0.9225,
      "step": 1040
    },
    {
      "epoch": 0.34953395472703064,
      "grad_norm": 11.75,
      "learning_rate": 1.3009320905459388e-05,
      "loss": 0.9262,
      "step": 1050
    },
    {
      "epoch": 0.35286284953395475,
      "grad_norm": 10.25,
      "learning_rate": 1.2942743009320906e-05,
      "loss": 0.7248,
      "step": 1060
    },
    {
      "epoch": 0.3561917443408788,
      "grad_norm": 12.875,
      "learning_rate": 1.2876165113182424e-05,
      "loss": 0.8358,
      "step": 1070
    },
    {
      "epoch": 0.3595206391478029,
      "grad_norm": 4.65625,
      "learning_rate": 1.2809587217043942e-05,
      "loss": 0.8156,
      "step": 1080
    },
    {
      "epoch": 0.362849533954727,
      "grad_norm": 23.5,
      "learning_rate": 1.274300932090546e-05,
      "loss": 1.0211,
      "step": 1090
    },
    {
      "epoch": 0.36617842876165113,
      "grad_norm": 17.5,
      "learning_rate": 1.2676431424766978e-05,
      "loss": 0.9804,
      "step": 1100
    },
    {
      "epoch": 0.36950732356857524,
      "grad_norm": 6.375,
      "learning_rate": 1.2609853528628498e-05,
      "loss": 0.9636,
      "step": 1110
    },
    {
      "epoch": 0.37283621837549935,
      "grad_norm": 20.25,
      "learning_rate": 1.2543275632490016e-05,
      "loss": 0.9873,
      "step": 1120
    },
    {
      "epoch": 0.37616511318242346,
      "grad_norm": 17.0,
      "learning_rate": 1.2476697736351534e-05,
      "loss": 0.9674,
      "step": 1130
    },
    {
      "epoch": 0.3794940079893475,
      "grad_norm": 20.5,
      "learning_rate": 1.241011984021305e-05,
      "loss": 1.0073,
      "step": 1140
    },
    {
      "epoch": 0.3828229027962716,
      "grad_norm": 4.125,
      "learning_rate": 1.2343541944074568e-05,
      "loss": 1.0919,
      "step": 1150
    },
    {
      "epoch": 0.38615179760319573,
      "grad_norm": 15.3125,
      "learning_rate": 1.2276964047936086e-05,
      "loss": 1.0103,
      "step": 1160
    },
    {
      "epoch": 0.38948069241011984,
      "grad_norm": 22.125,
      "learning_rate": 1.2210386151797604e-05,
      "loss": 0.9629,
      "step": 1170
    },
    {
      "epoch": 0.39280958721704395,
      "grad_norm": 2.953125,
      "learning_rate": 1.2143808255659122e-05,
      "loss": 0.9545,
      "step": 1180
    },
    {
      "epoch": 0.39613848202396806,
      "grad_norm": 7.59375,
      "learning_rate": 1.207723035952064e-05,
      "loss": 0.8836,
      "step": 1190
    },
    {
      "epoch": 0.3994673768308921,
      "grad_norm": 28.125,
      "learning_rate": 1.2010652463382158e-05,
      "loss": 0.9632,
      "step": 1200
    },
    {
      "epoch": 0.40279627163781623,
      "grad_norm": 15.125,
      "learning_rate": 1.1944074567243676e-05,
      "loss": 1.0765,
      "step": 1210
    },
    {
      "epoch": 0.40612516644474034,
      "grad_norm": 11.625,
      "learning_rate": 1.1877496671105194e-05,
      "loss": 0.7911,
      "step": 1220
    },
    {
      "epoch": 0.40945406125166445,
      "grad_norm": 15.5625,
      "learning_rate": 1.1810918774966711e-05,
      "loss": 1.0908,
      "step": 1230
    },
    {
      "epoch": 0.41278295605858856,
      "grad_norm": 6.3125,
      "learning_rate": 1.1744340878828231e-05,
      "loss": 1.0418,
      "step": 1240
    },
    {
      "epoch": 0.41611185086551267,
      "grad_norm": 2.671875,
      "learning_rate": 1.1677762982689749e-05,
      "loss": 0.9041,
      "step": 1250
    },
    {
      "epoch": 0.4194407456724368,
      "grad_norm": 19.125,
      "learning_rate": 1.1611185086551267e-05,
      "loss": 1.0392,
      "step": 1260
    },
    {
      "epoch": 0.42276964047936083,
      "grad_norm": 6.8125,
      "learning_rate": 1.1544607190412785e-05,
      "loss": 0.8439,
      "step": 1270
    },
    {
      "epoch": 0.42609853528628494,
      "grad_norm": 7.75,
      "learning_rate": 1.1478029294274303e-05,
      "loss": 1.0188,
      "step": 1280
    },
    {
      "epoch": 0.42942743009320905,
      "grad_norm": 17.25,
      "learning_rate": 1.141145139813582e-05,
      "loss": 1.1353,
      "step": 1290
    },
    {
      "epoch": 0.43275632490013316,
      "grad_norm": 22.125,
      "learning_rate": 1.1344873501997337e-05,
      "loss": 0.987,
      "step": 1300
    },
    {
      "epoch": 0.43608521970705727,
      "grad_norm": 16.0,
      "learning_rate": 1.1278295605858855e-05,
      "loss": 0.8446,
      "step": 1310
    },
    {
      "epoch": 0.4394141145139814,
      "grad_norm": 48.25,
      "learning_rate": 1.1211717709720373e-05,
      "loss": 1.0588,
      "step": 1320
    },
    {
      "epoch": 0.44274300932090543,
      "grad_norm": 17.625,
      "learning_rate": 1.1145139813581891e-05,
      "loss": 0.8579,
      "step": 1330
    },
    {
      "epoch": 0.44607190412782954,
      "grad_norm": 20.25,
      "learning_rate": 1.1078561917443409e-05,
      "loss": 1.0973,
      "step": 1340
    },
    {
      "epoch": 0.44940079893475365,
      "grad_norm": 14.25,
      "learning_rate": 1.1011984021304927e-05,
      "loss": 0.975,
      "step": 1350
    },
    {
      "epoch": 0.45272969374167776,
      "grad_norm": 22.875,
      "learning_rate": 1.0945406125166447e-05,
      "loss": 0.9035,
      "step": 1360
    },
    {
      "epoch": 0.4560585885486019,
      "grad_norm": 13.0,
      "learning_rate": 1.0878828229027965e-05,
      "loss": 1.0748,
      "step": 1370
    },
    {
      "epoch": 0.459387483355526,
      "grad_norm": 13.125,
      "learning_rate": 1.0812250332889482e-05,
      "loss": 1.0373,
      "step": 1380
    },
    {
      "epoch": 0.4627163781624501,
      "grad_norm": 15.0,
      "learning_rate": 1.0745672436751e-05,
      "loss": 0.9623,
      "step": 1390
    },
    {
      "epoch": 0.46604527296937415,
      "grad_norm": 26.25,
      "learning_rate": 1.0679094540612518e-05,
      "loss": 0.9579,
      "step": 1400
    },
    {
      "epoch": 0.46937416777629826,
      "grad_norm": 12.125,
      "learning_rate": 1.0612516644474036e-05,
      "loss": 0.918,
      "step": 1410
    },
    {
      "epoch": 0.47270306258322237,
      "grad_norm": 30.75,
      "learning_rate": 1.0545938748335554e-05,
      "loss": 0.9823,
      "step": 1420
    },
    {
      "epoch": 0.4760319573901465,
      "grad_norm": 7.0,
      "learning_rate": 1.047936085219707e-05,
      "loss": 0.9885,
      "step": 1430
    },
    {
      "epoch": 0.4793608521970706,
      "grad_norm": 19.5,
      "learning_rate": 1.0412782956058588e-05,
      "loss": 0.9654,
      "step": 1440
    },
    {
      "epoch": 0.4826897470039947,
      "grad_norm": 13.5,
      "learning_rate": 1.0346205059920106e-05,
      "loss": 0.8212,
      "step": 1450
    },
    {
      "epoch": 0.48601864181091875,
      "grad_norm": 17.0,
      "learning_rate": 1.0279627163781624e-05,
      "loss": 0.9406,
      "step": 1460
    },
    {
      "epoch": 0.48934753661784286,
      "grad_norm": 28.0,
      "learning_rate": 1.0213049267643142e-05,
      "loss": 0.9908,
      "step": 1470
    },
    {
      "epoch": 0.49267643142476697,
      "grad_norm": 14.25,
      "learning_rate": 1.014647137150466e-05,
      "loss": 0.9418,
      "step": 1480
    },
    {
      "epoch": 0.4960053262316911,
      "grad_norm": 12.25,
      "learning_rate": 1.007989347536618e-05,
      "loss": 1.075,
      "step": 1490
    },
    {
      "epoch": 0.4993342210386152,
      "grad_norm": 10.625,
      "learning_rate": 1.0013315579227698e-05,
      "loss": 1.0111,
      "step": 1500
    },
    {
      "epoch": 0.4993342210386152,
      "eval_accuracy": 0.508752281400365,
      "eval_loss": 0.9421009421348572,
      "eval_runtime": 209.8514,
      "eval_samples_per_second": 114.881,
      "eval_steps_per_second": 28.72,
      "step": 1500
    },
    {
      "epoch": 0.5026631158455392,
      "grad_norm": 31.5,
      "learning_rate": 9.946737683089214e-06,
      "loss": 0.9077,
      "step": 1510
    },
    {
      "epoch": 0.5059920106524634,
      "grad_norm": 19.375,
      "learning_rate": 9.880159786950732e-06,
      "loss": 1.1292,
      "step": 1520
    },
    {
      "epoch": 0.5093209054593875,
      "grad_norm": 8.4375,
      "learning_rate": 9.813581890812252e-06,
      "loss": 1.0658,
      "step": 1530
    },
    {
      "epoch": 0.5126498002663116,
      "grad_norm": 17.375,
      "learning_rate": 9.74700399467377e-06,
      "loss": 0.9691,
      "step": 1540
    },
    {
      "epoch": 0.5159786950732357,
      "grad_norm": 8.125,
      "learning_rate": 9.680426098535288e-06,
      "loss": 1.0146,
      "step": 1550
    },
    {
      "epoch": 0.5193075898801598,
      "grad_norm": 17.5,
      "learning_rate": 9.613848202396806e-06,
      "loss": 1.0196,
      "step": 1560
    },
    {
      "epoch": 0.5226364846870839,
      "grad_norm": 15.1875,
      "learning_rate": 9.547270306258324e-06,
      "loss": 0.8996,
      "step": 1570
    },
    {
      "epoch": 0.525965379494008,
      "grad_norm": 55.5,
      "learning_rate": 9.48069241011984e-06,
      "loss": 1.0211,
      "step": 1580
    },
    {
      "epoch": 0.5292942743009321,
      "grad_norm": 4.21875,
      "learning_rate": 9.41411451398136e-06,
      "loss": 0.9728,
      "step": 1590
    },
    {
      "epoch": 0.5326231691078562,
      "grad_norm": 6.71875,
      "learning_rate": 9.347536617842877e-06,
      "loss": 1.0168,
      "step": 1600
    },
    {
      "epoch": 0.5359520639147803,
      "grad_norm": 24.75,
      "learning_rate": 9.280958721704395e-06,
      "loss": 0.9252,
      "step": 1610
    },
    {
      "epoch": 0.5392809587217043,
      "grad_norm": 9.0625,
      "learning_rate": 9.214380825565913e-06,
      "loss": 1.0479,
      "step": 1620
    },
    {
      "epoch": 0.5426098535286284,
      "grad_norm": 15.375,
      "learning_rate": 9.147802929427431e-06,
      "loss": 1.0699,
      "step": 1630
    },
    {
      "epoch": 0.5459387483355526,
      "grad_norm": 17.5,
      "learning_rate": 9.08122503328895e-06,
      "loss": 0.9407,
      "step": 1640
    },
    {
      "epoch": 0.5492676431424767,
      "grad_norm": 9.625,
      "learning_rate": 9.014647137150465e-06,
      "loss": 1.0124,
      "step": 1650
    },
    {
      "epoch": 0.5525965379494008,
      "grad_norm": 10.375,
      "learning_rate": 8.948069241011985e-06,
      "loss": 0.8612,
      "step": 1660
    },
    {
      "epoch": 0.5559254327563249,
      "grad_norm": 21.375,
      "learning_rate": 8.881491344873503e-06,
      "loss": 0.9613,
      "step": 1670
    },
    {
      "epoch": 0.559254327563249,
      "grad_norm": 9.3125,
      "learning_rate": 8.814913448735021e-06,
      "loss": 0.9752,
      "step": 1680
    },
    {
      "epoch": 0.5625832223701731,
      "grad_norm": 8.375,
      "learning_rate": 8.748335552596539e-06,
      "loss": 0.8926,
      "step": 1690
    },
    {
      "epoch": 0.5659121171770972,
      "grad_norm": 17.625,
      "learning_rate": 8.681757656458057e-06,
      "loss": 1.0054,
      "step": 1700
    },
    {
      "epoch": 0.5692410119840213,
      "grad_norm": 20.125,
      "learning_rate": 8.615179760319575e-06,
      "loss": 0.9203,
      "step": 1710
    },
    {
      "epoch": 0.5725699067909454,
      "grad_norm": 28.75,
      "learning_rate": 8.548601864181093e-06,
      "loss": 0.9583,
      "step": 1720
    },
    {
      "epoch": 0.5758988015978695,
      "grad_norm": 17.0,
      "learning_rate": 8.48202396804261e-06,
      "loss": 0.9582,
      "step": 1730
    },
    {
      "epoch": 0.5792276964047937,
      "grad_norm": 13.4375,
      "learning_rate": 8.415446071904129e-06,
      "loss": 1.0034,
      "step": 1740
    },
    {
      "epoch": 0.5825565912117177,
      "grad_norm": 27.75,
      "learning_rate": 8.348868175765647e-06,
      "loss": 1.0647,
      "step": 1750
    },
    {
      "epoch": 0.5858854860186418,
      "grad_norm": 33.75,
      "learning_rate": 8.282290279627165e-06,
      "loss": 1.0575,
      "step": 1760
    },
    {
      "epoch": 0.5892143808255659,
      "grad_norm": 14.375,
      "learning_rate": 8.215712383488683e-06,
      "loss": 1.0699,
      "step": 1770
    },
    {
      "epoch": 0.59254327563249,
      "grad_norm": 6.09375,
      "learning_rate": 8.1491344873502e-06,
      "loss": 0.7706,
      "step": 1780
    },
    {
      "epoch": 0.5958721704394141,
      "grad_norm": 8.5625,
      "learning_rate": 8.082556591211719e-06,
      "loss": 0.8626,
      "step": 1790
    },
    {
      "epoch": 0.5992010652463382,
      "grad_norm": 7.46875,
      "learning_rate": 8.015978695073236e-06,
      "loss": 0.9427,
      "step": 1800
    },
    {
      "epoch": 0.6025299600532623,
      "grad_norm": 23.375,
      "learning_rate": 7.949400798934754e-06,
      "loss": 0.962,
      "step": 1810
    },
    {
      "epoch": 0.6058588548601864,
      "grad_norm": 7.65625,
      "learning_rate": 7.882822902796272e-06,
      "loss": 1.1216,
      "step": 1820
    },
    {
      "epoch": 0.6091877496671105,
      "grad_norm": 10.0625,
      "learning_rate": 7.81624500665779e-06,
      "loss": 0.9076,
      "step": 1830
    },
    {
      "epoch": 0.6125166444740346,
      "grad_norm": 6.78125,
      "learning_rate": 7.749667110519308e-06,
      "loss": 0.8158,
      "step": 1840
    },
    {
      "epoch": 0.6158455392809588,
      "grad_norm": 29.5,
      "learning_rate": 7.683089214380826e-06,
      "loss": 0.9828,
      "step": 1850
    },
    {
      "epoch": 0.6191744340878829,
      "grad_norm": 9.6875,
      "learning_rate": 7.616511318242344e-06,
      "loss": 0.9181,
      "step": 1860
    },
    {
      "epoch": 0.622503328894807,
      "grad_norm": 7.6875,
      "learning_rate": 7.549933422103862e-06,
      "loss": 0.9864,
      "step": 1870
    },
    {
      "epoch": 0.625832223701731,
      "grad_norm": 33.0,
      "learning_rate": 7.48335552596538e-06,
      "loss": 0.9898,
      "step": 1880
    },
    {
      "epoch": 0.6291611185086551,
      "grad_norm": 13.1875,
      "learning_rate": 7.416777629826898e-06,
      "loss": 0.948,
      "step": 1890
    },
    {
      "epoch": 0.6324900133155792,
      "grad_norm": 6.59375,
      "learning_rate": 7.350199733688416e-06,
      "loss": 0.9811,
      "step": 1900
    },
    {
      "epoch": 0.6358189081225033,
      "grad_norm": 8.5625,
      "learning_rate": 7.283621837549935e-06,
      "loss": 1.0461,
      "step": 1910
    },
    {
      "epoch": 0.6391478029294274,
      "grad_norm": 30.25,
      "learning_rate": 7.217043941411453e-06,
      "loss": 1.0408,
      "step": 1920
    },
    {
      "epoch": 0.6424766977363515,
      "grad_norm": 25.625,
      "learning_rate": 7.15046604527297e-06,
      "loss": 1.0327,
      "step": 1930
    },
    {
      "epoch": 0.6458055925432756,
      "grad_norm": 27.125,
      "learning_rate": 7.083888149134488e-06,
      "loss": 0.9213,
      "step": 1940
    },
    {
      "epoch": 0.6491344873501997,
      "grad_norm": 22.125,
      "learning_rate": 7.017310252996006e-06,
      "loss": 1.1191,
      "step": 1950
    },
    {
      "epoch": 0.6524633821571239,
      "grad_norm": 10.6875,
      "learning_rate": 6.950732356857524e-06,
      "loss": 0.9514,
      "step": 1960
    },
    {
      "epoch": 0.655792276964048,
      "grad_norm": 16.375,
      "learning_rate": 6.884154460719042e-06,
      "loss": 0.9437,
      "step": 1970
    },
    {
      "epoch": 0.6591211717709721,
      "grad_norm": 7.5625,
      "learning_rate": 6.8175765645805605e-06,
      "loss": 1.0645,
      "step": 1980
    },
    {
      "epoch": 0.6624500665778962,
      "grad_norm": 9.125,
      "learning_rate": 6.7509986684420784e-06,
      "loss": 0.9085,
      "step": 1990
    },
    {
      "epoch": 0.6657789613848203,
      "grad_norm": 9.6875,
      "learning_rate": 6.6844207723035955e-06,
      "loss": 0.9784,
      "step": 2000
    },
    {
      "epoch": 0.6657789613848203,
      "eval_accuracy": 0.5068027210884354,
      "eval_loss": 0.9414482712745667,
      "eval_runtime": 213.4336,
      "eval_samples_per_second": 112.953,
      "eval_steps_per_second": 28.238,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3004,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}