{
  "best_metric": 0.2912794053554535,
  "best_model_checkpoint": "vit-base-patch16-224-in21k-bridgedefectVIT\\checkpoint-3060",
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 3825,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 6.535947712418301e-07,
      "loss": 1.6179,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.3071895424836602e-06,
      "loss": 1.6223,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.96078431372549e-06,
      "loss": 1.6263,
      "step": 30
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.6143790849673204e-06,
      "loss": 1.601,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.2679738562091506e-06,
      "loss": 1.6074,
      "step": 50
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.92156862745098e-06,
      "loss": 1.5955,
      "step": 60
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.5751633986928105e-06,
      "loss": 1.5698,
      "step": 70
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.228758169934641e-06,
      "loss": 1.5797,
      "step": 80
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.5531,
      "step": 90
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.535947712418301e-06,
      "loss": 1.5434,
      "step": 100
    },
    {
      "epoch": 0.43,
      "learning_rate": 7.1895424836601305e-06,
      "loss": 1.5433,
      "step": 110
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.84313725490196e-06,
      "loss": 1.5329,
      "step": 120
    },
    {
      "epoch": 0.51,
      "learning_rate": 8.496732026143791e-06,
      "loss": 1.4995,
      "step": 130
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.150326797385621e-06,
      "loss": 1.4875,
      "step": 140
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.803921568627451e-06,
      "loss": 1.4863,
      "step": 150
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.0457516339869281e-05,
      "loss": 1.4209,
      "step": 160
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.4354,
      "step": 170
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.3572,
      "step": 180
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2418300653594772e-05,
      "loss": 1.3714,
      "step": 190
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.3071895424836602e-05,
      "loss": 1.3406,
      "step": 200
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.3725490196078432e-05,
      "loss": 1.2574,
      "step": 210
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.4379084967320261e-05,
      "loss": 1.2965,
      "step": 220
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.5032679738562091e-05,
      "loss": 1.2021,
      "step": 230
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.568627450980392e-05,
      "loss": 1.2072,
      "step": 240
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6339869281045753e-05,
      "loss": 1.1457,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": {
        "accuracy": 0.6941176470588235
      },
      "eval_f1": {
        "f1": 0.683792091280419
      },
      "eval_loss": 1.158827304840088,
      "eval_precision": {
        "precision": 0.7377494408375539
      },
      "eval_recall": {
        "recall": 0.6941484490686618
      },
      "eval_runtime": 25.3262,
      "eval_samples_per_second": 20.137,
      "eval_steps_per_second": 10.069,
      "step": 255
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.6993464052287582e-05,
      "loss": 1.0924,
      "step": 260
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.0007,
      "step": 270
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.8300653594771242e-05,
      "loss": 1.0054,
      "step": 280
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.895424836601307e-05,
      "loss": 0.9365,
      "step": 290
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 0.8932,
      "step": 300
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.0261437908496734e-05,
      "loss": 0.916,
      "step": 310
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.0915032679738563e-05,
      "loss": 0.8099,
      "step": 320
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.1568627450980395e-05,
      "loss": 0.8211,
      "step": 330
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6861,
      "step": 340
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.2875816993464052e-05,
      "loss": 0.7379,
      "step": 350
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.7349,
      "step": 360
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.4183006535947712e-05,
      "loss": 0.6907,
      "step": 370
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.4836601307189544e-05,
      "loss": 0.7376,
      "step": 380
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.5490196078431373e-05,
      "loss": 0.6827,
      "step": 390
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.6143790849673204e-05,
      "loss": 0.6969,
      "step": 400
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.6797385620915033e-05,
      "loss": 0.6247,
      "step": 410
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.7450980392156865e-05,
      "loss": 0.5244,
      "step": 420
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.8104575163398693e-05,
      "loss": 0.7068,
      "step": 430
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.8758169934640522e-05,
      "loss": 0.5623,
      "step": 440
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.5931,
      "step": 450
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.0065359477124182e-05,
      "loss": 0.6641,
      "step": 460
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.0718954248366014e-05,
      "loss": 0.5438,
      "step": 470
    },
    {
      "epoch": 1.88,
      "learning_rate": 3.137254901960784e-05,
      "loss": 0.5134,
      "step": 480
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.202614379084967e-05,
      "loss": 0.4682,
      "step": 490
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.2679738562091506e-05,
      "loss": 0.4762,
      "step": 500
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4558,
      "step": 510
    },
    {
      "epoch": 2.0,
      "eval_accuracy": {
        "accuracy": 0.8470588235294118
      },
      "eval_f1": {
        "f1": 0.8510200857474889
      },
      "eval_loss": 0.498457670211792,
      "eval_precision": {
        "precision": 0.8766865984788879
      },
      "eval_recall": {
        "recall": 0.8454231938274491
      },
      "eval_runtime": 10.0517,
      "eval_samples_per_second": 50.738,
      "eval_steps_per_second": 25.369,
      "step": 510
    },
    {
      "epoch": 2.04,
      "learning_rate": 3.3986928104575163e-05,
      "loss": 0.4716,
      "step": 520
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.464052287581699e-05,
      "loss": 0.5375,
      "step": 530
    },
    {
      "epoch": 2.12,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.4725,
      "step": 540
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.5947712418300656e-05,
      "loss": 0.4804,
      "step": 550
    },
    {
      "epoch": 2.2,
      "learning_rate": 3.6601307189542484e-05,
      "loss": 0.3504,
      "step": 560
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.725490196078432e-05,
      "loss": 0.4049,
      "step": 570
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.790849673202614e-05,
      "loss": 0.4309,
      "step": 580
    },
    {
      "epoch": 2.31,
      "learning_rate": 3.8562091503267977e-05,
      "loss": 0.4938,
      "step": 590
    },
    {
      "epoch": 2.35,
      "learning_rate": 3.9215686274509805e-05,
      "loss": 0.5427,
      "step": 600
    },
    {
      "epoch": 2.39,
      "learning_rate": 3.986928104575164e-05,
      "loss": 0.4719,
      "step": 610
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.052287581699347e-05,
      "loss": 0.4627,
      "step": 620
    },
    {
      "epoch": 2.47,
      "learning_rate": 4.11764705882353e-05,
      "loss": 0.5277,
      "step": 630
    },
    {
      "epoch": 2.51,
      "learning_rate": 4.1830065359477126e-05,
      "loss": 0.3109,
      "step": 640
    },
    {
      "epoch": 2.55,
      "learning_rate": 4.2483660130718954e-05,
      "loss": 0.3799,
      "step": 650
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.313725490196079e-05,
      "loss": 0.3515,
      "step": 660
    },
    {
      "epoch": 2.63,
      "learning_rate": 4.379084967320262e-05,
      "loss": 0.3722,
      "step": 670
    },
    {
      "epoch": 2.67,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5337,
      "step": 680
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.3263,
      "step": 690
    },
    {
      "epoch": 2.75,
      "learning_rate": 4.5751633986928104e-05,
      "loss": 0.3703,
      "step": 700
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.640522875816994e-05,
      "loss": 0.4498,
      "step": 710
    },
    {
      "epoch": 2.82,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.4109,
      "step": 720
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.77124183006536e-05,
      "loss": 0.2953,
      "step": 730
    },
    {
      "epoch": 2.9,
      "learning_rate": 4.8366013071895424e-05,
      "loss": 0.4033,
      "step": 740
    },
    {
      "epoch": 2.94,
      "learning_rate": 4.901960784313725e-05,
      "loss": 0.4186,
      "step": 750
    },
    {
      "epoch": 2.98,
      "learning_rate": 4.967320261437909e-05,
      "loss": 0.3368,
      "step": 760
    },
    {
      "epoch": 3.0,
      "eval_accuracy": {
        "accuracy": 0.8705882352941177
      },
      "eval_f1": {
        "f1": 0.8713991689505157
      },
      "eval_loss": 0.44290485978126526,
      "eval_precision": {
        "precision": 0.8884985994397759
      },
      "eval_recall": {
        "recall": 0.8711626139817629
      },
      "eval_runtime": 9.9506,
      "eval_samples_per_second": 51.253,
      "eval_steps_per_second": 25.626,
      "step": 765
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.9963689179375456e-05,
      "loss": 0.3347,
      "step": 770
    },
    {
      "epoch": 3.06,
      "learning_rate": 4.9891067538126364e-05,
      "loss": 0.3339,
      "step": 780
    },
    {
      "epoch": 3.1,
      "learning_rate": 4.981844589687727e-05,
      "loss": 0.5573,
      "step": 790
    },
    {
      "epoch": 3.14,
      "learning_rate": 4.974582425562818e-05,
      "loss": 0.5463,
      "step": 800
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.967320261437909e-05,
      "loss": 0.3453,
      "step": 810
    },
    {
      "epoch": 3.22,
      "learning_rate": 4.9600580973129996e-05,
      "loss": 0.3814,
      "step": 820
    },
    {
      "epoch": 3.25,
      "learning_rate": 4.9527959331880904e-05,
      "loss": 0.4434,
      "step": 830
    },
    {
      "epoch": 3.29,
      "learning_rate": 4.945533769063181e-05,
      "loss": 0.3675,
      "step": 840
    },
    {
      "epoch": 3.33,
      "learning_rate": 4.938271604938271e-05,
      "loss": 0.5386,
      "step": 850
    },
    {
      "epoch": 3.37,
      "learning_rate": 4.931009440813363e-05,
      "loss": 0.2692,
      "step": 860
    },
    {
      "epoch": 3.41,
      "learning_rate": 4.9237472766884536e-05,
      "loss": 0.4815,
      "step": 870
    },
    {
      "epoch": 3.45,
      "learning_rate": 4.9164851125635444e-05,
      "loss": 0.4178,
      "step": 880
    },
    {
      "epoch": 3.49,
      "learning_rate": 4.909222948438635e-05,
      "loss": 0.3618,
      "step": 890
    },
    {
      "epoch": 3.53,
      "learning_rate": 4.901960784313725e-05,
      "loss": 0.6841,
      "step": 900
    },
    {
      "epoch": 3.57,
      "learning_rate": 4.894698620188817e-05,
      "loss": 0.471,
      "step": 910
    },
    {
      "epoch": 3.61,
      "learning_rate": 4.8874364560639076e-05,
      "loss": 0.313,
      "step": 920
    },
    {
      "epoch": 3.65,
      "learning_rate": 4.8801742919389983e-05,
      "loss": 0.2437,
      "step": 930
    },
    {
      "epoch": 3.69,
      "learning_rate": 4.8729121278140885e-05,
      "loss": 0.4748,
      "step": 940
    },
    {
      "epoch": 3.73,
      "learning_rate": 4.865649963689179e-05,
      "loss": 0.5519,
      "step": 950
    },
    {
      "epoch": 3.76,
      "learning_rate": 4.85838779956427e-05,
      "loss": 0.3051,
      "step": 960
    },
    {
      "epoch": 3.8,
      "learning_rate": 4.8511256354393615e-05,
      "loss": 0.3847,
      "step": 970
    },
    {
      "epoch": 3.84,
      "learning_rate": 4.843863471314452e-05,
      "loss": 0.2454,
      "step": 980
    },
    {
      "epoch": 3.88,
      "learning_rate": 4.8366013071895424e-05,
      "loss": 0.379,
      "step": 990
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.829339143064633e-05,
      "loss": 0.4485,
      "step": 1000
    },
    {
      "epoch": 3.96,
      "learning_rate": 4.822076978939724e-05,
      "loss": 0.2484,
      "step": 1010
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.4402,
      "step": 1020
    },
    {
      "epoch": 4.0,
      "eval_accuracy": {
        "accuracy": 0.8784313725490196
      },
      "eval_f1": {
        "f1": 0.880471094803992
      },
      "eval_loss": 0.3946979343891144,
      "eval_precision": {
        "precision": 0.8952890487430221
      },
      "eval_recall": {
        "recall": 0.8776488582339645
      },
      "eval_runtime": 10.1771,
      "eval_samples_per_second": 50.113,
      "eval_steps_per_second": 25.056,
      "step": 1020
    },
    {
      "epoch": 4.04,
      "learning_rate": 4.807552650689906e-05,
      "loss": 0.3494,
      "step": 1030
    },
    {
      "epoch": 4.08,
      "learning_rate": 4.8002904865649964e-05,
      "loss": 0.3327,
      "step": 1040
    },
    {
      "epoch": 4.12,
      "learning_rate": 4.793028322440087e-05,
      "loss": 0.2898,
      "step": 1050
    },
    {
      "epoch": 4.16,
      "learning_rate": 4.785766158315178e-05,
      "loss": 0.3965,
      "step": 1060
    },
    {
      "epoch": 4.2,
      "learning_rate": 4.778503994190269e-05,
      "loss": 0.3607,
      "step": 1070
    },
    {
      "epoch": 4.24,
      "learning_rate": 4.77124183006536e-05,
      "loss": 0.3714,
      "step": 1080
    },
    {
      "epoch": 4.27,
      "learning_rate": 4.7639796659404504e-05,
      "loss": 0.1796,
      "step": 1090
    },
    {
      "epoch": 4.31,
      "learning_rate": 4.756717501815541e-05,
      "loss": 0.1874,
      "step": 1100
    },
    {
      "epoch": 4.35,
      "learning_rate": 4.749455337690632e-05,
      "loss": 0.3462,
      "step": 1110
    },
    {
      "epoch": 4.39,
      "learning_rate": 4.742193173565723e-05,
      "loss": 0.2082,
      "step": 1120
    },
    {
      "epoch": 4.43,
      "learning_rate": 4.7349310094408136e-05,
      "loss": 0.4531,
      "step": 1130
    },
    {
      "epoch": 4.47,
      "learning_rate": 4.7276688453159044e-05,
      "loss": 0.3951,
      "step": 1140
    },
    {
      "epoch": 4.51,
      "learning_rate": 4.720406681190995e-05,
      "loss": 0.2337,
      "step": 1150
    },
    {
      "epoch": 4.55,
      "learning_rate": 4.713144517066086e-05,
      "loss": 0.2118,
      "step": 1160
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.373,
      "step": 1170
    },
    {
      "epoch": 4.63,
      "learning_rate": 4.6986201888162675e-05,
      "loss": 0.1484,
      "step": 1180
    },
    {
      "epoch": 4.67,
      "learning_rate": 4.691358024691358e-05,
      "loss": 0.2568,
      "step": 1190
    },
    {
      "epoch": 4.71,
      "learning_rate": 4.684095860566449e-05,
      "loss": 0.3067,
      "step": 1200
    },
    {
      "epoch": 4.75,
      "learning_rate": 4.67683369644154e-05,
      "loss": 0.2007,
      "step": 1210
    },
    {
      "epoch": 4.78,
      "learning_rate": 4.669571532316631e-05,
      "loss": 0.2493,
      "step": 1220
    },
    {
      "epoch": 4.82,
      "learning_rate": 4.6623093681917215e-05,
      "loss": 0.2717,
      "step": 1230
    },
    {
      "epoch": 4.86,
      "learning_rate": 4.6550472040668116e-05,
      "loss": 0.4134,
      "step": 1240
    },
    {
      "epoch": 4.9,
      "learning_rate": 4.647785039941903e-05,
      "loss": 0.2417,
      "step": 1250
    },
    {
      "epoch": 4.94,
      "learning_rate": 4.640522875816994e-05,
      "loss": 0.2573,
      "step": 1260
    },
    {
      "epoch": 4.98,
      "learning_rate": 4.633260711692085e-05,
      "loss": 0.3937,
      "step": 1270
    },
    {
      "epoch": 5.0,
      "eval_accuracy": {
        "accuracy": 0.8725490196078431
      },
      "eval_f1": {
        "f1": 0.8703780158419334
      },
      "eval_loss": 0.4377364218235016,
      "eval_precision": {
        "precision": 0.8900760323128502
      },
      "eval_recall": {
        "recall": 0.8691138648585458
      },
      "eval_runtime": 10.1762,
      "eval_samples_per_second": 50.117,
      "eval_steps_per_second": 25.058,
      "step": 1275
    },
    {
      "epoch": 5.02,
      "learning_rate": 4.6259985475671755e-05,
      "loss": 0.165,
      "step": 1280
    },
    {
      "epoch": 5.06,
      "learning_rate": 4.6187363834422656e-05,
      "loss": 0.1452,
      "step": 1290
    },
    {
      "epoch": 5.1,
      "learning_rate": 4.6114742193173564e-05,
      "loss": 0.1548,
      "step": 1300
    },
    {
      "epoch": 5.14,
      "learning_rate": 4.604212055192448e-05,
      "loss": 0.4443,
      "step": 1310
    },
    {
      "epoch": 5.18,
      "learning_rate": 4.5969498910675387e-05,
      "loss": 0.4322,
      "step": 1320
    },
    {
      "epoch": 5.22,
      "learning_rate": 4.5896877269426294e-05,
      "loss": 0.2355,
      "step": 1330
    },
    {
      "epoch": 5.25,
      "learning_rate": 4.5824255628177196e-05,
      "loss": 0.1949,
      "step": 1340
    },
    {
      "epoch": 5.29,
      "learning_rate": 4.5751633986928104e-05,
      "loss": 0.1959,
      "step": 1350
    },
    {
      "epoch": 5.33,
      "learning_rate": 4.567901234567901e-05,
      "loss": 0.3841,
      "step": 1360
    },
    {
      "epoch": 5.37,
      "learning_rate": 4.5606390704429926e-05,
      "loss": 0.1401,
      "step": 1370
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.5533769063180834e-05,
      "loss": 0.1148,
      "step": 1380
    },
    {
      "epoch": 5.45,
      "learning_rate": 4.5461147421931735e-05,
      "loss": 0.234,
      "step": 1390
    },
    {
      "epoch": 5.49,
      "learning_rate": 4.538852578068264e-05,
      "loss": 0.3899,
      "step": 1400
    },
    {
      "epoch": 5.53,
      "learning_rate": 4.531590413943355e-05,
      "loss": 0.4873,
      "step": 1410
    },
    {
      "epoch": 5.57,
      "learning_rate": 4.5243282498184466e-05,
      "loss": 0.2483,
      "step": 1420
    },
    {
      "epoch": 5.61,
      "learning_rate": 4.5170660856935374e-05,
      "loss": 0.2654,
      "step": 1430
    },
    {
      "epoch": 5.65,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.2035,
      "step": 1440
    },
    {
      "epoch": 5.69,
      "learning_rate": 4.502541757443718e-05,
      "loss": 0.3744,
      "step": 1450
    },
    {
      "epoch": 5.73,
      "learning_rate": 4.495279593318809e-05,
      "loss": 0.2139,
      "step": 1460
    },
    {
      "epoch": 5.76,
      "learning_rate": 4.4880174291939e-05,
      "loss": 0.2212,
      "step": 1470
    },
    {
      "epoch": 5.8,
      "learning_rate": 4.480755265068991e-05,
      "loss": 0.376,
      "step": 1480
    },
    {
      "epoch": 5.84,
      "learning_rate": 4.4734931009440815e-05,
      "loss": 0.2399,
      "step": 1490
    },
    {
      "epoch": 5.88,
      "learning_rate": 4.466230936819172e-05,
      "loss": 0.3534,
      "step": 1500
    },
    {
      "epoch": 5.92,
      "learning_rate": 4.458968772694263e-05,
      "loss": 0.3667,
      "step": 1510
    },
    {
      "epoch": 5.96,
      "learning_rate": 4.451706608569354e-05,
      "loss": 0.496,
      "step": 1520
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.4042,
      "step": 1530
    },
    {
      "epoch": 6.0,
      "eval_accuracy": {
        "accuracy": 0.8862745098039215
      },
      "eval_f1": {
        "f1": 0.8859196308355288
      },
      "eval_loss": 0.39891302585601807,
      "eval_precision": {
        "precision": 0.8972093144987638
      },
      "eval_recall": {
        "recall": 0.8834955381497934
      },
      "eval_runtime": 10.1174,
      "eval_samples_per_second": 50.408,
      "eval_steps_per_second": 25.204,
      "step": 1530
    },
    {
      "epoch": 6.04,
      "learning_rate": 4.4371822803195355e-05,
      "loss": 0.2637,
      "step": 1540
    },
    {
      "epoch": 6.08,
      "learning_rate": 4.429920116194626e-05,
      "loss": 0.2821,
      "step": 1550
    },
    {
      "epoch": 6.12,
      "learning_rate": 4.422657952069717e-05,
      "loss": 0.1201,
      "step": 1560
    },
    {
      "epoch": 6.16,
      "learning_rate": 4.415395787944808e-05,
      "loss": 0.262,
      "step": 1570
    },
    {
      "epoch": 6.2,
      "learning_rate": 4.4081336238198986e-05,
      "loss": 0.2064,
      "step": 1580
    },
    {
      "epoch": 6.24,
      "learning_rate": 4.400871459694989e-05,
      "loss": 0.1815,
      "step": 1590
    },
    {
      "epoch": 6.27,
      "learning_rate": 4.39360929557008e-05,
      "loss": 0.1959,
      "step": 1600
    },
    {
      "epoch": 6.31,
      "learning_rate": 4.386347131445171e-05,
      "loss": 0.1959,
      "step": 1610
    },
    {
      "epoch": 6.35,
      "learning_rate": 4.379084967320262e-05,
      "loss": 0.2398,
      "step": 1620
    },
    {
      "epoch": 6.39,
      "learning_rate": 4.3718228031953526e-05,
      "loss": 0.2038,
      "step": 1630
    },
    {
      "epoch": 6.43,
      "learning_rate": 4.364560639070443e-05,
      "loss": 0.2004,
      "step": 1640
    },
    {
      "epoch": 6.47,
      "learning_rate": 4.357298474945534e-05,
      "loss": 0.0377,
      "step": 1650
    },
    {
      "epoch": 6.51,
      "learning_rate": 4.350036310820625e-05,
      "loss": 0.2022,
      "step": 1660
    },
    {
      "epoch": 6.55,
      "learning_rate": 4.342774146695716e-05,
      "loss": 0.4403,
      "step": 1670
    },
    {
      "epoch": 6.59,
      "learning_rate": 4.3355119825708066e-05,
      "loss": 0.2577,
      "step": 1680
    },
    {
      "epoch": 6.63,
      "learning_rate": 4.328249818445897e-05,
      "loss": 0.3312,
      "step": 1690
    },
    {
      "epoch": 6.67,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 0.307,
      "step": 1700
    },
    {
      "epoch": 6.71,
      "learning_rate": 4.313725490196079e-05,
      "loss": 0.0961,
      "step": 1710
    },
    {
      "epoch": 6.75,
      "learning_rate": 4.30646332607117e-05,
      "loss": 0.3266,
      "step": 1720
    },
    {
      "epoch": 6.78,
      "learning_rate": 4.2992011619462605e-05,
      "loss": 0.2601,
      "step": 1730
    },
    {
      "epoch": 6.82,
      "learning_rate": 4.291938997821351e-05,
      "loss": 0.2382,
      "step": 1740
    },
    {
      "epoch": 6.86,
      "learning_rate": 4.2846768336964415e-05,
      "loss": 0.1469,
      "step": 1750
    },
    {
      "epoch": 6.9,
      "learning_rate": 4.277414669571532e-05,
      "loss": 0.2158,
      "step": 1760
    },
    {
      "epoch": 6.94,
      "learning_rate": 4.270152505446624e-05,
      "loss": 0.4392,
      "step": 1770
    },
    {
      "epoch": 6.98,
      "learning_rate": 4.262890341321714e-05,
      "loss": 0.4321,
      "step": 1780
    },
    {
      "epoch": 7.0,
      "eval_accuracy": {
        "accuracy": 0.8901960784313725
      },
      "eval_f1": {
        "f1": 0.8896787277785286
      },
      "eval_loss": 0.36420056223869324,
      "eval_precision": {
        "precision": 0.9002265766283616
      },
      "eval_recall": {
        "recall": 0.8878911425453978
      },
      "eval_runtime": 10.2347,
      "eval_samples_per_second": 49.83,
      "eval_steps_per_second": 24.915,
      "step": 1785
    },
    {
      "epoch": 7.02,
      "learning_rate": 4.2556281771968046e-05,
      "loss": 0.5162,
      "step": 1790
    },
    {
      "epoch": 7.06,
      "learning_rate": 4.2483660130718954e-05,
      "loss": 0.2491,
      "step": 1800
    },
    {
      "epoch": 7.1,
      "learning_rate": 4.241103848946986e-05,
      "loss": 0.2267,
      "step": 1810
    },
    {
      "epoch": 7.14,
      "learning_rate": 4.233841684822078e-05,
      "loss": 0.2395,
      "step": 1820
    },
    {
      "epoch": 7.18,
      "learning_rate": 4.226579520697168e-05,
      "loss": 0.3007,
      "step": 1830
    },
    {
      "epoch": 7.22,
      "learning_rate": 4.2193173565722586e-05,
      "loss": 0.1316,
      "step": 1840
    },
    {
      "epoch": 7.25,
      "learning_rate": 4.2120551924473494e-05,
      "loss": 0.1592,
      "step": 1850
    },
    {
      "epoch": 7.29,
      "learning_rate": 4.20479302832244e-05,
      "loss": 0.3467,
      "step": 1860
    },
    {
      "epoch": 7.33,
      "learning_rate": 4.197530864197531e-05,
      "loss": 0.4195,
      "step": 1870
    },
    {
      "epoch": 7.37,
      "learning_rate": 4.190268700072622e-05,
      "loss": 0.3561,
      "step": 1880
    },
    {
      "epoch": 7.41,
      "learning_rate": 4.1830065359477126e-05,
      "loss": 0.1572,
      "step": 1890
    },
    {
      "epoch": 7.45,
      "learning_rate": 4.1757443718228034e-05,
      "loss": 0.2104,
      "step": 1900
    },
    {
      "epoch": 7.49,
      "learning_rate": 4.168482207697894e-05,
      "loss": 0.3536,
      "step": 1910
    },
    {
      "epoch": 7.53,
      "learning_rate": 4.161220043572985e-05,
      "loss": 0.345,
      "step": 1920
    },
    {
      "epoch": 7.57,
      "learning_rate": 4.153957879448076e-05,
      "loss": 0.1083,
      "step": 1930
    },
    {
      "epoch": 7.61,
      "learning_rate": 4.1466957153231666e-05,
      "loss": 0.1895,
      "step": 1940
    },
    {
      "epoch": 7.65,
      "learning_rate": 4.1394335511982573e-05,
      "loss": 0.3232,
      "step": 1950
    },
    {
      "epoch": 7.69,
      "learning_rate": 4.132171387073348e-05,
      "loss": 0.2939,
      "step": 1960
    },
    {
      "epoch": 7.73,
      "learning_rate": 4.124909222948439e-05,
      "loss": 0.0918,
      "step": 1970
    },
    {
      "epoch": 7.76,
      "learning_rate": 4.11764705882353e-05,
      "loss": 0.1722,
      "step": 1980
    },
    {
      "epoch": 7.8,
      "learning_rate": 4.1103848946986205e-05,
      "loss": 0.3229,
      "step": 1990
    },
    {
      "epoch": 7.84,
      "learning_rate": 4.103122730573711e-05,
      "loss": 0.1501,
      "step": 2000
    },
    {
      "epoch": 7.88,
      "learning_rate": 4.095860566448802e-05,
      "loss": 0.1468,
      "step": 2010
    },
    {
      "epoch": 7.92,
      "learning_rate": 4.088598402323893e-05,
      "loss": 0.1665,
      "step": 2020
    },
    {
      "epoch": 7.96,
      "learning_rate": 4.081336238198984e-05,
      "loss": 0.1324,
      "step": 2030
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.2618,
      "step": 2040
    },
    {
      "epoch": 8.0,
      "eval_accuracy": {
        "accuracy": 0.8960784313725491
      },
      "eval_f1": {
        "f1": 0.8950352545633242
      },
      "eval_loss": 0.40923169255256653,
      "eval_precision": {
        "precision": 0.9033601037449228
      },
      "eval_recall": {
        "recall": 0.8953584093211753
      },
      "eval_runtime": 10.3235,
      "eval_samples_per_second": 49.402,
      "eval_steps_per_second": 24.701,
      "step": 2040
    },
    {
      "epoch": 8.04,
      "learning_rate": 4.066811909949165e-05,
      "loss": 0.1887,
      "step": 2050
    },
    {
      "epoch": 8.08,
      "learning_rate": 4.059549745824256e-05,
      "loss": 0.4153,
      "step": 2060
    },
    {
      "epoch": 8.12,
      "learning_rate": 4.052287581699347e-05,
      "loss": 0.2771,
      "step": 2070
    },
    {
      "epoch": 8.16,
      "learning_rate": 4.045025417574437e-05,
      "loss": 0.3316,
      "step": 2080
    },
    {
      "epoch": 8.2,
      "learning_rate": 4.037763253449528e-05,
      "loss": 0.1125,
      "step": 2090
    },
    {
      "epoch": 8.24,
      "learning_rate": 4.0305010893246186e-05,
      "loss": 0.3016,
      "step": 2100
    },
    {
      "epoch": 8.27,
      "learning_rate": 4.02323892519971e-05,
      "loss": 0.2458,
      "step": 2110
    },
    {
      "epoch": 8.31,
      "learning_rate": 4.015976761074801e-05,
      "loss": 0.179,
      "step": 2120
    },
    {
      "epoch": 8.35,
      "learning_rate": 4.008714596949891e-05,
      "loss": 0.224,
      "step": 2130
    },
    {
      "epoch": 8.39,
      "learning_rate": 4.001452432824982e-05,
      "loss": 0.0803,
      "step": 2140
    },
    {
      "epoch": 8.43,
      "learning_rate": 3.9941902687000726e-05,
      "loss": 0.1121,
      "step": 2150
    },
    {
      "epoch": 8.47,
      "learning_rate": 3.986928104575164e-05,
      "loss": 0.3751,
      "step": 2160
    },
    {
      "epoch": 8.51,
      "learning_rate": 3.979665940450255e-05,
      "loss": 0.1354,
      "step": 2170
    },
    {
      "epoch": 8.55,
      "learning_rate": 3.972403776325345e-05,
      "loss": 0.3105,
      "step": 2180
    },
    {
      "epoch": 8.59,
      "learning_rate": 3.965141612200436e-05,
      "loss": 0.1937,
      "step": 2190
    },
    {
      "epoch": 8.63,
      "learning_rate": 3.9578794480755265e-05,
      "loss": 0.3028,
      "step": 2200
    },
    {
      "epoch": 8.67,
      "learning_rate": 3.950617283950617e-05,
      "loss": 0.1851,
      "step": 2210
    },
    {
      "epoch": 8.71,
      "learning_rate": 3.943355119825709e-05,
      "loss": 0.074,
      "step": 2220
    },
    {
      "epoch": 8.75,
      "learning_rate": 3.936092955700799e-05,
      "loss": 0.2098,
      "step": 2230
    },
    {
      "epoch": 8.78,
      "learning_rate": 3.92883079157589e-05,
      "loss": 0.3167,
      "step": 2240
    },
    {
      "epoch": 8.82,
      "learning_rate": 3.9215686274509805e-05,
      "loss": 0.2527,
      "step": 2250
    },
    {
      "epoch": 8.86,
      "learning_rate": 3.914306463326071e-05,
      "loss": 0.1521,
      "step": 2260
    },
    {
      "epoch": 8.9,
      "learning_rate": 3.907044299201162e-05,
      "loss": 0.1393,
      "step": 2270
    },
    {
      "epoch": 8.94,
      "learning_rate": 3.899782135076253e-05,
      "loss": 0.1155,
      "step": 2280
    },
    {
      "epoch": 8.98,
      "learning_rate": 3.892519970951344e-05,
      "loss": 0.3376,
      "step": 2290
    },
    {
      "epoch": 9.0,
      "eval_accuracy": {
        "accuracy": 0.8941176470588236
      },
      "eval_f1": {
        "f1": 0.8933906521569781
      },
      "eval_loss": 0.4055422246456146,
      "eval_precision": {
        "precision": 0.9014239716079142
      },
      "eval_recall": {
        "recall": 0.8936214051905541
      },
      "eval_runtime": 10.1735,
      "eval_samples_per_second": 50.13,
      "eval_steps_per_second": 25.065,
      "step": 2295
    },
    {
      "epoch": 9.02,
      "learning_rate": 3.8852578068264345e-05,
      "loss": 0.1807,
      "step": 2300
    },
    {
      "epoch": 9.06,
      "learning_rate": 3.877995642701525e-05,
      "loss": 0.1127,
      "step": 2310
    },
    {
      "epoch": 9.1,
      "learning_rate": 3.870733478576616e-05,
      "loss": 0.0503,
      "step": 2320
    },
    {
      "epoch": 9.14,
      "learning_rate": 3.863471314451707e-05,
      "loss": 0.0748,
      "step": 2330
    },
    {
      "epoch": 9.18,
      "learning_rate": 3.8562091503267977e-05,
      "loss": 0.2657,
      "step": 2340
    },
    {
      "epoch": 9.22,
      "learning_rate": 3.8489469862018884e-05,
      "loss": 0.1785,
      "step": 2350
    },
    {
      "epoch": 9.25,
      "learning_rate": 3.841684822076979e-05,
      "loss": 0.0808,
      "step": 2360
    },
    {
      "epoch": 9.29,
      "learning_rate": 3.83442265795207e-05,
      "loss": 0.3348,
      "step": 2370
    },
    {
      "epoch": 9.33,
      "learning_rate": 3.82716049382716e-05,
      "loss": 0.259,
      "step": 2380
    },
    {
      "epoch": 9.37,
      "learning_rate": 3.8198983297022516e-05,
      "loss": 0.1707,
      "step": 2390
    },
    {
      "epoch": 9.41,
      "learning_rate": 3.8126361655773424e-05,
      "loss": 0.0915,
      "step": 2400
    },
    {
      "epoch": 9.45,
      "learning_rate": 3.805374001452433e-05,
      "loss": 0.0987,
      "step": 2410
    },
    {
      "epoch": 9.49,
      "learning_rate": 3.798111837327524e-05,
      "loss": 0.0906,
      "step": 2420
    },
    {
      "epoch": 9.53,
      "learning_rate": 3.790849673202614e-05,
      "loss": 0.1955,
      "step": 2430
    },
    {
      "epoch": 9.57,
      "learning_rate": 3.783587509077705e-05,
      "loss": 0.1936,
      "step": 2440
    },
    {
      "epoch": 9.61,
      "learning_rate": 3.7763253449527964e-05,
      "loss": 0.1479,
      "step": 2450
    },
    {
      "epoch": 9.65,
      "learning_rate": 3.769063180827887e-05,
      "loss": 0.1662,
      "step": 2460
    },
    {
      "epoch": 9.69,
      "learning_rate": 3.761801016702978e-05,
      "loss": 0.0815,
      "step": 2470
    },
    {
      "epoch": 9.73,
      "learning_rate": 3.754538852578068e-05,
      "loss": 0.1128,
      "step": 2480
    },
    {
      "epoch": 9.76,
      "learning_rate": 3.747276688453159e-05,
      "loss": 0.0891,
      "step": 2490
    },
    {
      "epoch": 9.8,
      "learning_rate": 3.74001452432825e-05,
      "loss": 0.0853,
      "step": 2500
    },
    {
      "epoch": 9.84,
      "learning_rate": 3.732752360203341e-05,
      "loss": 0.2403,
      "step": 2510
    },
    {
      "epoch": 9.88,
      "learning_rate": 3.725490196078432e-05,
      "loss": 0.2393,
      "step": 2520
    },
    {
      "epoch": 9.92,
      "learning_rate": 3.718228031953522e-05,
      "loss": 0.113,
      "step": 2530
    },
    {
      "epoch": 9.96,
      "learning_rate": 3.710965867828613e-05,
      "loss": 0.1374,
      "step": 2540
    },
    {
      "epoch": 10.0,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.2592,
      "step": 2550
    },
    {
      "epoch": 10.0,
      "eval_accuracy": {
        "accuracy": 0.8627450980392157
      },
      "eval_f1": {
        "f1": 0.8639402375974159
      },
      "eval_loss": 0.49467796087265015,
      "eval_precision": {
        "precision": 0.8837020302136581
      },
      "eval_recall": {
        "recall": 0.8620484568622867
      },
      "eval_runtime": 10.09,
      "eval_samples_per_second": 50.545,
      "eval_steps_per_second": 25.273,
      "step": 2550
    },
    {
      "epoch": 10.04,
      "learning_rate": 3.696441539578795e-05,
      "loss": 0.1971,
      "step": 2560
    },
    {
      "epoch": 10.08,
      "learning_rate": 3.689179375453886e-05,
      "loss": 0.1467,
      "step": 2570
    },
    {
      "epoch": 10.12,
      "learning_rate": 3.681917211328976e-05,
      "loss": 0.2304,
      "step": 2580
    },
    {
      "epoch": 10.16,
      "learning_rate": 3.674655047204067e-05,
      "loss": 0.1111,
      "step": 2590
    },
    {
      "epoch": 10.2,
      "learning_rate": 3.6673928830791576e-05,
      "loss": 0.2193,
      "step": 2600
    },
    {
      "epoch": 10.24,
      "learning_rate": 3.6601307189542484e-05,
      "loss": 0.1701,
      "step": 2610
    },
    {
      "epoch": 10.27,
      "learning_rate": 3.652868554829339e-05,
      "loss": 0.0251,
      "step": 2620
    },
    {
      "epoch": 10.31,
      "learning_rate": 3.64560639070443e-05,
      "loss": 0.0138,
      "step": 2630
    },
    {
      "epoch": 10.35,
      "learning_rate": 3.638344226579521e-05,
      "loss": 0.191,
      "step": 2640
    },
    {
      "epoch": 10.39,
      "learning_rate": 3.6310820624546116e-05,
      "loss": 0.1112,
      "step": 2650
    },
    {
      "epoch": 10.43,
      "learning_rate": 3.6238198983297024e-05,
      "loss": 0.1115,
      "step": 2660
    },
    {
      "epoch": 10.47,
      "learning_rate": 3.616557734204793e-05,
      "loss": 0.1842,
      "step": 2670
    },
    {
      "epoch": 10.51,
      "learning_rate": 3.609295570079884e-05,
      "loss": 0.1397,
      "step": 2680
    },
    {
      "epoch": 10.55,
      "learning_rate": 3.602033405954975e-05,
      "loss": 0.1044,
      "step": 2690
    },
    {
      "epoch": 10.59,
      "learning_rate": 3.5947712418300656e-05,
      "loss": 0.1015,
      "step": 2700
    },
    {
      "epoch": 10.63,
      "learning_rate": 3.5875090777051564e-05,
      "loss": 0.2076,
      "step": 2710
    },
    {
      "epoch": 10.67,
      "learning_rate": 3.580246913580247e-05,
      "loss": 0.1405,
      "step": 2720
    },
    {
      "epoch": 10.71,
      "learning_rate": 3.572984749455338e-05,
      "loss": 0.154,
      "step": 2730
    },
    {
      "epoch": 10.75,
      "learning_rate": 3.565722585330429e-05,
      "loss": 0.2566,
      "step": 2740
    },
    {
      "epoch": 10.78,
      "learning_rate": 3.5584604212055195e-05,
      "loss": 0.1589,
      "step": 2750
    },
    {
      "epoch": 10.82,
      "learning_rate": 3.55119825708061e-05,
      "loss": 0.2138,
      "step": 2760
    },
    {
      "epoch": 10.86,
      "learning_rate": 3.543936092955701e-05,
      "loss": 0.1734,
      "step": 2770
    },
    {
      "epoch": 10.9,
      "learning_rate": 3.536673928830791e-05,
      "loss": 0.0846,
      "step": 2780
    },
    {
      "epoch": 10.94,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.2093,
      "step": 2790
    },
    {
      "epoch": 10.98,
      "learning_rate": 3.5221496005809735e-05,
      "loss": 0.363,
      "step": 2800
    },
    {
      "epoch": 11.0,
      "eval_accuracy": {
        "accuracy": 0.8862745098039215
      },
      "eval_f1": {
        "f1": 0.8871534026726227
      },
      "eval_loss": 0.45857715606689453,
      "eval_precision": {
        "precision": 0.89776885319054
      },
      "eval_recall": {
        "recall": 0.8850722858701582
      },
      "eval_runtime": 9.9484,
      "eval_samples_per_second": 51.265,
      "eval_steps_per_second": 25.632,
      "step": 2805
    },
    {
      "epoch": 11.02,
      "learning_rate": 3.514887436456064e-05,
      "loss": 0.161,
      "step": 2810
    },
    {
      "epoch": 11.06,
      "learning_rate": 3.507625272331155e-05,
      "loss": 0.0835,
      "step": 2820
    },
    {
      "epoch": 11.1,
      "learning_rate": 3.500363108206245e-05,
      "loss": 0.1329,
      "step": 2830
    },
    {
      "epoch": 11.14,
      "learning_rate": 3.493100944081336e-05,
      "loss": 0.0135,
      "step": 2840
    },
    {
      "epoch": 11.18,
      "learning_rate": 3.4858387799564275e-05,
      "loss": 0.0124,
      "step": 2850
    },
    {
      "epoch": 11.22,
      "learning_rate": 3.478576615831518e-05,
      "loss": 0.2865,
      "step": 2860
    },
    {
      "epoch": 11.25,
      "learning_rate": 3.471314451706609e-05,
      "loss": 0.2016,
      "step": 2870
    },
    {
      "epoch": 11.29,
      "learning_rate": 3.464052287581699e-05,
      "loss": 0.1214,
      "step": 2880
    },
    {
      "epoch": 11.33,
      "learning_rate": 3.45679012345679e-05,
      "loss": 0.1795,
      "step": 2890
    },
    {
      "epoch": 11.37,
      "learning_rate": 3.4495279593318815e-05,
      "loss": 0.028,
      "step": 2900
    },
    {
      "epoch": 11.41,
      "learning_rate": 3.442265795206972e-05,
      "loss": 0.3366,
      "step": 2910
    },
    {
      "epoch": 11.45,
      "learning_rate": 3.4350036310820624e-05,
      "loss": 0.161,
      "step": 2920
    },
    {
      "epoch": 11.49,
      "learning_rate": 3.427741466957153e-05,
      "loss": 0.1429,
      "step": 2930
    },
    {
      "epoch": 11.53,
      "learning_rate": 3.420479302832244e-05,
      "loss": 0.1995,
      "step": 2940
    },
    {
      "epoch": 11.57,
      "learning_rate": 3.413217138707335e-05,
      "loss": 0.0369,
      "step": 2950
    },
    {
      "epoch": 11.61,
      "learning_rate": 3.405954974582426e-05,
      "loss": 0.1814,
      "step": 2960
    },
    {
      "epoch": 11.65,
      "learning_rate": 3.3986928104575163e-05,
      "loss": 0.1466,
      "step": 2970
    },
    {
      "epoch": 11.69,
      "learning_rate": 3.391430646332607e-05,
      "loss": 0.0435,
      "step": 2980
    },
    {
      "epoch": 11.73,
      "learning_rate": 3.384168482207698e-05,
      "loss": 0.0945,
      "step": 2990
    },
    {
      "epoch": 11.76,
      "learning_rate": 3.376906318082789e-05,
      "loss": 0.3593,
      "step": 3000
    },
    {
      "epoch": 11.8,
      "learning_rate": 3.3696441539578795e-05,
      "loss": 0.1862,
      "step": 3010
    },
    {
      "epoch": 11.84,
      "learning_rate": 3.36238198983297e-05,
      "loss": 0.1031,
      "step": 3020
    },
    {
      "epoch": 11.88,
      "learning_rate": 3.355119825708061e-05,
      "loss": 0.1794,
      "step": 3030
    },
    {
      "epoch": 11.92,
      "learning_rate": 3.347857661583152e-05,
      "loss": 0.2495,
      "step": 3040
    },
    {
      "epoch": 11.96,
      "learning_rate": 3.340595497458243e-05,
      "loss": 0.168,
      "step": 3050
    },
    {
      "epoch": 12.0,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.278,
      "step": 3060
    },
    {
      "epoch": 12.0,
      "eval_accuracy": {
        "accuracy": 0.9196078431372549
      },
      "eval_f1": {
        "f1": 0.9203616179126926
      },
      "eval_loss": 0.2912794053554535,
      "eval_precision": {
        "precision": 0.9237222880261108
      },
      "eval_recall": {
        "recall": 0.920318466993999
      },
      "eval_runtime": 10.2193,
      "eval_samples_per_second": 49.905,
      "eval_steps_per_second": 24.953,
      "step": 3060
    },
    {
      "epoch": 12.04,
      "learning_rate": 3.326071169208424e-05,
      "loss": 0.0654,
      "step": 3070
    },
    {
      "epoch": 12.08,
      "learning_rate": 3.318809005083515e-05,
      "loss": 0.1827,
      "step": 3080
    },
    {
      "epoch": 12.12,
      "learning_rate": 3.311546840958606e-05,
      "loss": 0.1608,
      "step": 3090
    },
    {
      "epoch": 12.16,
      "learning_rate": 3.304284676833697e-05,
      "loss": 0.1133,
      "step": 3100
    },
    {
      "epoch": 12.2,
      "learning_rate": 3.2970225127087875e-05,
      "loss": 0.1324,
      "step": 3110
    },
    {
      "epoch": 12.24,
      "learning_rate": 3.289760348583878e-05,
      "loss": 0.233,
      "step": 3120
    },
    {
      "epoch": 12.27,
      "learning_rate": 3.282498184458969e-05,
      "loss": 0.1262,
      "step": 3130
    },
    {
      "epoch": 12.31,
      "learning_rate": 3.27523602033406e-05,
      "loss": 0.1989,
      "step": 3140
    },
    {
      "epoch": 12.35,
      "learning_rate": 3.2679738562091506e-05,
      "loss": 0.0913,
      "step": 3150
    },
    {
      "epoch": 12.39,
      "learning_rate": 3.2607116920842414e-05,
      "loss": 0.14,
      "step": 3160
    },
    {
      "epoch": 12.43,
      "learning_rate": 3.2534495279593316e-05,
      "loss": 0.1296,
      "step": 3170
    },
    {
      "epoch": 12.47,
      "learning_rate": 3.2461873638344223e-05,
      "loss": 0.137,
      "step": 3180
    },
    {
      "epoch": 12.51,
      "learning_rate": 3.238925199709514e-05,
      "loss": 0.2531,
      "step": 3190
    },
    {
      "epoch": 12.55,
      "learning_rate": 3.2316630355846046e-05,
      "loss": 0.1718,
      "step": 3200
    },
    {
      "epoch": 12.59,
      "learning_rate": 3.2244008714596954e-05,
      "loss": 0.0158,
      "step": 3210
    },
    {
      "epoch": 12.63,
      "learning_rate": 3.2171387073347855e-05,
      "loss": 0.2503,
      "step": 3220
    },
    {
      "epoch": 12.67,
      "learning_rate": 3.209876543209876e-05,
      "loss": 0.0101,
      "step": 3230
    },
    {
      "epoch": 12.71,
      "learning_rate": 3.202614379084967e-05,
      "loss": 0.1985,
      "step": 3240
    },
    {
      "epoch": 12.75,
      "learning_rate": 3.1953522149600586e-05,
      "loss": 0.2394,
      "step": 3250
    },
    {
      "epoch": 12.78,
      "learning_rate": 3.1880900508351494e-05,
      "loss": 0.183,
      "step": 3260
    },
    {
      "epoch": 12.82,
      "learning_rate": 3.1808278867102395e-05,
      "loss": 0.1489,
      "step": 3270
    },
    {
      "epoch": 12.86,
      "learning_rate": 3.17356572258533e-05,
      "loss": 0.0722,
      "step": 3280
    },
    {
      "epoch": 12.9,
      "learning_rate": 3.166303558460421e-05,
      "loss": 0.0889,
      "step": 3290
    },
    {
      "epoch": 12.94,
      "learning_rate": 3.1590413943355126e-05,
      "loss": 0.1194,
      "step": 3300
    },
    {
      "epoch": 12.98,
      "learning_rate": 3.1517792302106034e-05,
      "loss": 0.1436,
      "step": 3310
    },
    {
      "epoch": 13.0,
      "eval_accuracy": {
        "accuracy": 0.9
      },
      "eval_f1": {
        "f1": 0.8997771222806092
      },
      "eval_loss": 0.4294499456882477,
      "eval_precision": {
        "precision": 0.9095799880746632
      },
      "eval_recall": {
        "recall": 0.901510989010989
      },
      "eval_runtime": 10.2735,
      "eval_samples_per_second": 49.642,
      "eval_steps_per_second": 24.821,
      "step": 3315
    },
    {
      "epoch": 13.02,
      "learning_rate": 3.1445170660856935e-05,
      "loss": 0.1158,
      "step": 3320
    },
    {
      "epoch": 13.06,
      "learning_rate": 3.137254901960784e-05,
      "loss": 0.1086,
      "step": 3330
    },
    {
      "epoch": 13.1,
      "learning_rate": 3.129992737835875e-05,
      "loss": 0.1612,
      "step": 3340
    },
    {
      "epoch": 13.14,
      "learning_rate": 3.122730573710966e-05,
      "loss": 0.1272,
      "step": 3350
    },
    {
      "epoch": 13.18,
      "learning_rate": 3.115468409586057e-05,
      "loss": 0.2715,
      "step": 3360
    },
    {
      "epoch": 13.22,
      "learning_rate": 3.1082062454611474e-05,
      "loss": 0.1432,
      "step": 3370
    },
    {
      "epoch": 13.25,
      "learning_rate": 3.100944081336238e-05,
      "loss": 0.0573,
      "step": 3380
    },
    {
      "epoch": 13.29,
      "learning_rate": 3.093681917211329e-05,
      "loss": 0.141,
      "step": 3390
    },
    {
      "epoch": 13.33,
      "learning_rate": 3.08641975308642e-05,
      "loss": 0.156,
      "step": 3400
    },
    {
      "epoch": 13.37,
      "learning_rate": 3.0791575889615106e-05,
      "loss": 0.1558,
      "step": 3410
    },
    {
      "epoch": 13.41,
      "learning_rate": 3.0718954248366014e-05,
      "loss": 0.1606,
      "step": 3420
    },
    {
      "epoch": 13.45,
      "learning_rate": 3.064633260711692e-05,
      "loss": 0.1677,
      "step": 3430
    },
    {
      "epoch": 13.49,
      "learning_rate": 3.057371096586783e-05,
      "loss": 0.0562,
      "step": 3440
    },
    {
      "epoch": 13.53,
      "learning_rate": 3.0501089324618738e-05,
      "loss": 0.1684,
      "step": 3450
    },
    {
      "epoch": 13.57,
      "learning_rate": 3.0428467683369643e-05,
      "loss": 0.3589,
      "step": 3460
    },
    {
      "epoch": 13.61,
      "learning_rate": 3.0355846042120557e-05,
      "loss": 0.2076,
      "step": 3470
    },
    {
      "epoch": 13.65,
      "learning_rate": 3.0283224400871462e-05,
      "loss": 0.0773,
      "step": 3480
    },
    {
      "epoch": 13.69,
      "learning_rate": 3.021060275962237e-05,
      "loss": 0.0424,
      "step": 3490
    },
    {
      "epoch": 13.73,
      "learning_rate": 3.0137981118373278e-05,
      "loss": 0.1573,
      "step": 3500
    },
    {
      "epoch": 13.76,
      "learning_rate": 3.0065359477124182e-05,
      "loss": 0.0465,
      "step": 3510
    },
    {
      "epoch": 13.8,
      "learning_rate": 2.999273783587509e-05,
      "loss": 0.0091,
      "step": 3520
    },
    {
      "epoch": 13.84,
      "learning_rate": 2.9920116194626e-05,
      "loss": 0.2262,
      "step": 3530
    },
    {
      "epoch": 13.88,
      "learning_rate": 2.984749455337691e-05,
      "loss": 0.0253,
      "step": 3540
    },
    {
      "epoch": 13.92,
      "learning_rate": 2.9774872912127817e-05,
      "loss": 0.184,
      "step": 3550
    },
    {
      "epoch": 13.96,
      "learning_rate": 2.9702251270878722e-05,
      "loss": 0.1289,
      "step": 3560
    },
    {
      "epoch": 14.0,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.2017,
      "step": 3570
    },
    {
      "epoch": 14.0,
      "eval_accuracy": {
        "accuracy": 0.9274509803921569
      },
      "eval_f1": {
        "f1": 0.9275152403725876
      },
      "eval_loss": 0.3324253261089325,
      "eval_precision": {
        "precision": 0.9309834626869261
      },
      "eval_recall": {
        "recall": 0.9275085729872963
      },
      "eval_runtime": 10.2109,
      "eval_samples_per_second": 49.947,
      "eval_steps_per_second": 24.973,
      "step": 3570
    },
    {
      "epoch": 14.04,
      "learning_rate": 2.9557007988380538e-05,
      "loss": 0.2156,
      "step": 3580
    },
    {
      "epoch": 14.08,
      "learning_rate": 2.948438634713145e-05,
      "loss": 0.1672,
      "step": 3590
    },
    {
      "epoch": 14.12,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.0842,
      "step": 3600
    },
    {
      "epoch": 14.16,
      "learning_rate": 2.9339143064633262e-05,
      "loss": 0.1529,
      "step": 3610
    },
    {
      "epoch": 14.2,
      "learning_rate": 2.926652142338417e-05,
      "loss": 0.0904,
      "step": 3620
    },
    {
      "epoch": 14.24,
      "learning_rate": 2.9193899782135074e-05,
      "loss": 0.1129,
      "step": 3630
    },
    {
      "epoch": 14.27,
      "learning_rate": 2.912127814088599e-05,
      "loss": 0.0721,
      "step": 3640
    },
    {
      "epoch": 14.31,
      "learning_rate": 2.9048656499636893e-05,
      "loss": 0.137,
      "step": 3650
    },
    {
      "epoch": 14.35,
      "learning_rate": 2.89760348583878e-05,
      "loss": 0.1637,
      "step": 3660
    },
    {
      "epoch": 14.39,
      "learning_rate": 2.890341321713871e-05,
      "loss": 0.1298,
      "step": 3670
    },
    {
      "epoch": 14.43,
      "learning_rate": 2.8830791575889614e-05,
      "loss": 0.037,
      "step": 3680
    },
    {
      "epoch": 14.47,
      "learning_rate": 2.8758169934640522e-05,
      "loss": 0.1013,
      "step": 3690
    },
    {
      "epoch": 14.51,
      "learning_rate": 2.8685548293391433e-05,
      "loss": 0.1149,
      "step": 3700
    },
    {
      "epoch": 14.55,
      "learning_rate": 2.861292665214234e-05,
      "loss": 0.1502,
      "step": 3710
    },
    {
      "epoch": 14.59,
      "learning_rate": 2.854030501089325e-05,
      "loss": 0.1915,
      "step": 3720
    },
    {
      "epoch": 14.63,
      "learning_rate": 2.8467683369644154e-05,
      "loss": 0.0854,
      "step": 3730
    },
    {
      "epoch": 14.67,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.0395,
      "step": 3740
    },
    {
      "epoch": 14.71,
      "learning_rate": 2.832244008714597e-05,
      "loss": 0.1681,
      "step": 3750
    },
    {
      "epoch": 14.75,
      "learning_rate": 2.824981844589688e-05,
      "loss": 0.1236,
      "step": 3760
    },
    {
      "epoch": 14.78,
      "learning_rate": 2.817719680464779e-05,
      "loss": 0.1138,
      "step": 3770
    },
    {
      "epoch": 14.82,
      "learning_rate": 2.8104575163398693e-05,
      "loss": 0.1743,
      "step": 3780
    },
    {
      "epoch": 14.86,
      "learning_rate": 2.80319535221496e-05,
      "loss": 0.0698,
      "step": 3790
    },
    {
      "epoch": 14.9,
      "learning_rate": 2.795933188090051e-05,
      "loss": 0.1649,
      "step": 3800
    },
    {
      "epoch": 14.94,
      "learning_rate": 2.788671023965142e-05,
      "loss": 0.0095,
      "step": 3810
    },
    {
      "epoch": 14.98,
      "learning_rate": 2.781408859840233e-05,
      "loss": 0.017,
      "step": 3820
    },
    {
      "epoch": 15.0,
      "eval_accuracy": {
        "accuracy": 0.9235294117647059
      },
      "eval_f1": {
        "f1": 0.9236114478832926
      },
      "eval_loss": 0.319390207529068,
      "eval_precision": {
        "precision": 0.9261443200762086
      },
      "eval_recall": {
        "recall": 0.9255596796820201
      },
      "eval_runtime": 10.1385,
      "eval_samples_per_second": 50.303,
      "eval_steps_per_second": 25.152,
      "step": 3825
    }
  ],
  "logging_steps": 10,
  "max_steps": 7650,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 2.371318640628941e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}