{
  "best_metric": 0.11477231234312057,
  "best_model_checkpoint": "Result/OffsetTwo_batch4_step2000_dropout01_data5\\checkpoint-600",
  "epoch": 15.189873417721518,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.00019910000000000001,
      "loss": 0.7699,
      "step": 10
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019810000000000002,
      "loss": 0.6794,
      "step": 20
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019710000000000002,
      "loss": 0.6679,
      "step": 30
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019610000000000002,
      "loss": 0.6,
      "step": 40
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019510000000000003,
      "loss": 0.7582,
      "step": 50
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001941,
      "loss": 0.5271,
      "step": 60
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001931,
      "loss": 0.3892,
      "step": 70
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001921,
      "loss": 0.5038,
      "step": 80
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001911,
      "loss": 0.9304,
      "step": 90
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001901,
      "loss": 0.5224,
      "step": 100
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00018910000000000002,
      "loss": 0.2114,
      "step": 110
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00018810000000000002,
      "loss": 0.4839,
      "step": 120
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00018710000000000002,
      "loss": 0.4868,
      "step": 130
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001861,
      "loss": 0.4647,
      "step": 140
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001851,
      "loss": 0.6468,
      "step": 150
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001841,
      "loss": 0.534,
      "step": 160
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001831,
      "loss": 0.4389,
      "step": 170
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001821,
      "loss": 0.7613,
      "step": 180
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001811,
      "loss": 0.5378,
      "step": 190
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00018010000000000001,
      "loss": 0.4595,
      "step": 200
    },
    {
      "epoch": 2.53,
      "eval_accuracy": 0.9318181818181818,
      "eval_f1": 0.8646153846153846,
      "eval_loss": 0.23132099211215973,
      "eval_precision": 0.8903508771929824,
      "eval_recall": 0.8436293436293436,
      "eval_runtime": 0.574,
      "eval_samples_per_second": 76.655,
      "eval_steps_per_second": 10.453,
      "step": 200
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001791,
      "loss": 0.6753,
      "step": 210
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001781,
      "loss": 0.6403,
      "step": 220
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001771,
      "loss": 0.3846,
      "step": 230
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001761,
      "loss": 0.436,
      "step": 240
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0001751,
      "loss": 0.5878,
      "step": 250
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00017410000000000003,
      "loss": 0.6039,
      "step": 260
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001731,
      "loss": 0.3482,
      "step": 270
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0001721,
      "loss": 0.5476,
      "step": 280
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0001711,
      "loss": 0.8293,
      "step": 290
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00017010000000000001,
      "loss": 0.4146,
      "step": 300
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.00016910000000000002,
      "loss": 0.2258,
      "step": 310
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00016810000000000002,
      "loss": 0.205,
      "step": 320
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00016710000000000002,
      "loss": 0.5747,
      "step": 330
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0001661,
      "loss": 0.4064,
      "step": 340
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0001651,
      "loss": 0.5639,
      "step": 350
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001642,
      "loss": 0.3854,
      "step": 360
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001632,
      "loss": 0.5548,
      "step": 370
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001622,
      "loss": 0.5231,
      "step": 380
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.00016120000000000002,
      "loss": 0.3772,
      "step": 390
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00016020000000000002,
      "loss": 0.5486,
      "step": 400
    },
    {
      "epoch": 5.06,
      "eval_accuracy": 0.9545454545454546,
      "eval_f1": 0.9035087719298245,
      "eval_loss": 0.18894661962985992,
      "eval_precision": 0.9743589743589743,
      "eval_recall": 0.8571428571428572,
      "eval_runtime": 0.521,
      "eval_samples_per_second": 84.453,
      "eval_steps_per_second": 11.516,
      "step": 400
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00015920000000000002,
      "loss": 0.5041,
      "step": 410
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00015820000000000002,
      "loss": 0.3767,
      "step": 420
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.00015720000000000003,
      "loss": 0.1914,
      "step": 430
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001562,
      "loss": 0.4182,
      "step": 440
    },
    {
      "epoch": 5.7,
      "learning_rate": 0.0001552,
      "loss": 0.1872,
      "step": 450
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.0001542,
      "loss": 0.3854,
      "step": 460
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.0001532,
      "loss": 0.0307,
      "step": 470
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.0001522,
      "loss": 0.0157,
      "step": 480
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00015120000000000002,
      "loss": 0.2349,
      "step": 490
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00015020000000000002,
      "loss": 0.2716,
      "step": 500
    },
    {
      "epoch": 6.46,
      "learning_rate": 0.0001492,
      "loss": 0.2278,
      "step": 510
    },
    {
      "epoch": 6.58,
      "learning_rate": 0.0001482,
      "loss": 0.0078,
      "step": 520
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0001472,
      "loss": 0.0069,
      "step": 530
    },
    {
      "epoch": 6.84,
      "learning_rate": 0.0001462,
      "loss": 0.3477,
      "step": 540
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.0001452,
      "loss": 0.0098,
      "step": 550
    },
    {
      "epoch": 7.09,
      "learning_rate": 0.0001442,
      "loss": 0.0061,
      "step": 560
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.0001432,
      "loss": 0.005,
      "step": 570
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.0001422,
      "loss": 0.0047,
      "step": 580
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.0001412,
      "loss": 0.0043,
      "step": 590
    },
    {
      "epoch": 7.59,
      "learning_rate": 0.0001402,
      "loss": 0.0045,
      "step": 600
    },
    {
      "epoch": 7.59,
      "eval_accuracy": 0.9772727272727273,
      "eval_f1": 0.9548717948717949,
      "eval_loss": 0.11477231234312057,
      "eval_precision": 0.986842105263158,
      "eval_recall": 0.9285714285714286,
      "eval_runtime": 0.622,
      "eval_samples_per_second": 70.74,
      "eval_steps_per_second": 9.646,
      "step": 600
    },
    {
      "epoch": 7.72,
      "learning_rate": 0.0001392,
      "loss": 0.0037,
      "step": 610
    },
    {
      "epoch": 7.85,
      "learning_rate": 0.0001382,
      "loss": 0.0042,
      "step": 620
    },
    {
      "epoch": 7.97,
      "learning_rate": 0.00013720000000000003,
      "loss": 0.3004,
      "step": 630
    },
    {
      "epoch": 8.1,
      "learning_rate": 0.0001362,
      "loss": 0.0332,
      "step": 640
    },
    {
      "epoch": 8.23,
      "learning_rate": 0.0001352,
      "loss": 0.0033,
      "step": 650
    },
    {
      "epoch": 8.35,
      "learning_rate": 0.0001342,
      "loss": 0.0033,
      "step": 660
    },
    {
      "epoch": 8.48,
      "learning_rate": 0.0001332,
      "loss": 0.0406,
      "step": 670
    },
    {
      "epoch": 8.61,
      "learning_rate": 0.00013220000000000001,
      "loss": 0.003,
      "step": 680
    },
    {
      "epoch": 8.73,
      "learning_rate": 0.00013120000000000002,
      "loss": 0.0043,
      "step": 690
    },
    {
      "epoch": 8.86,
      "learning_rate": 0.00013020000000000002,
      "loss": 0.0055,
      "step": 700
    },
    {
      "epoch": 8.99,
      "learning_rate": 0.00012920000000000002,
      "loss": 0.0029,
      "step": 710
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0001282,
      "loss": 0.0027,
      "step": 720
    },
    {
      "epoch": 9.24,
      "learning_rate": 0.0001272,
      "loss": 0.0027,
      "step": 730
    },
    {
      "epoch": 9.37,
      "learning_rate": 0.0001262,
      "loss": 0.0024,
      "step": 740
    },
    {
      "epoch": 9.49,
      "learning_rate": 0.0001252,
      "loss": 0.0922,
      "step": 750
    },
    {
      "epoch": 9.62,
      "learning_rate": 0.0001242,
      "loss": 0.0691,
      "step": 760
    },
    {
      "epoch": 9.75,
      "learning_rate": 0.0001232,
      "loss": 0.0023,
      "step": 770
    },
    {
      "epoch": 9.87,
      "learning_rate": 0.00012220000000000002,
      "loss": 0.0022,
      "step": 780
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001212,
      "loss": 0.2026,
      "step": 790
    },
    {
      "epoch": 10.13,
      "learning_rate": 0.00012020000000000001,
      "loss": 0.0024,
      "step": 800
    },
    {
      "epoch": 10.13,
      "eval_accuracy": 0.9545454545454546,
      "eval_f1": 0.915057915057915,
      "eval_loss": 0.31218913197517395,
      "eval_precision": 0.915057915057915,
      "eval_recall": 0.915057915057915,
      "eval_runtime": 0.585,
      "eval_samples_per_second": 75.214,
      "eval_steps_per_second": 10.256,
      "step": 800
    },
    {
      "epoch": 10.25,
      "learning_rate": 0.0001192,
      "loss": 0.0021,
      "step": 810
    },
    {
      "epoch": 10.38,
      "learning_rate": 0.0001182,
      "loss": 0.0021,
      "step": 820
    },
    {
      "epoch": 10.51,
      "learning_rate": 0.0001172,
      "loss": 0.002,
      "step": 830
    },
    {
      "epoch": 10.63,
      "learning_rate": 0.00011619999999999999,
      "loss": 0.002,
      "step": 840
    },
    {
      "epoch": 10.76,
      "learning_rate": 0.0001152,
      "loss": 0.0019,
      "step": 850
    },
    {
      "epoch": 10.89,
      "learning_rate": 0.0001142,
      "loss": 0.0018,
      "step": 860
    },
    {
      "epoch": 11.01,
      "learning_rate": 0.0001132,
      "loss": 0.0018,
      "step": 870
    },
    {
      "epoch": 11.14,
      "learning_rate": 0.00011220000000000002,
      "loss": 0.0017,
      "step": 880
    },
    {
      "epoch": 11.27,
      "learning_rate": 0.00011120000000000002,
      "loss": 0.0017,
      "step": 890
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.00011020000000000001,
      "loss": 0.0017,
      "step": 900
    },
    {
      "epoch": 11.52,
      "learning_rate": 0.00010920000000000001,
      "loss": 0.0016,
      "step": 910
    },
    {
      "epoch": 11.65,
      "learning_rate": 0.00010820000000000001,
      "loss": 0.0016,
      "step": 920
    },
    {
      "epoch": 11.77,
      "learning_rate": 0.00010720000000000002,
      "loss": 0.0016,
      "step": 930
    },
    {
      "epoch": 11.9,
      "learning_rate": 0.0001062,
      "loss": 0.0016,
      "step": 940
    },
    {
      "epoch": 12.03,
      "learning_rate": 0.00010520000000000001,
      "loss": 0.0015,
      "step": 950
    },
    {
      "epoch": 12.15,
      "learning_rate": 0.00010420000000000001,
      "loss": 0.0015,
      "step": 960
    },
    {
      "epoch": 12.28,
      "learning_rate": 0.0001032,
      "loss": 0.0014,
      "step": 970
    },
    {
      "epoch": 12.41,
      "learning_rate": 0.0001022,
      "loss": 0.0014,
      "step": 980
    },
    {
      "epoch": 12.53,
      "learning_rate": 0.00010120000000000001,
      "loss": 0.0014,
      "step": 990
    },
    {
      "epoch": 12.66,
      "learning_rate": 0.00010020000000000001,
      "loss": 0.0014,
      "step": 1000
    },
    {
      "epoch": 12.66,
      "eval_accuracy": 0.9545454545454546,
      "eval_f1": 0.915057915057915,
      "eval_loss": 0.32846134901046753,
      "eval_precision": 0.915057915057915,
      "eval_recall": 0.915057915057915,
      "eval_runtime": 0.572,
      "eval_samples_per_second": 76.923,
      "eval_steps_per_second": 10.49,
      "step": 1000
    },
    {
      "epoch": 12.78,
      "learning_rate": 9.92e-05,
      "loss": 0.0014,
      "step": 1010
    },
    {
      "epoch": 12.91,
      "learning_rate": 9.82e-05,
      "loss": 0.0013,
      "step": 1020
    },
    {
      "epoch": 13.04,
      "learning_rate": 9.72e-05,
      "loss": 0.0013,
      "step": 1030
    },
    {
      "epoch": 13.16,
      "learning_rate": 9.620000000000001e-05,
      "loss": 0.0013,
      "step": 1040
    },
    {
      "epoch": 13.29,
      "learning_rate": 9.52e-05,
      "loss": 0.0013,
      "step": 1050
    },
    {
      "epoch": 13.42,
      "learning_rate": 9.42e-05,
      "loss": 0.0012,
      "step": 1060
    },
    {
      "epoch": 13.54,
      "learning_rate": 9.320000000000002e-05,
      "loss": 0.0012,
      "step": 1070
    },
    {
      "epoch": 13.67,
      "learning_rate": 9.22e-05,
      "loss": 0.0012,
      "step": 1080
    },
    {
      "epoch": 13.8,
      "learning_rate": 9.120000000000001e-05,
      "loss": 0.0012,
      "step": 1090
    },
    {
      "epoch": 13.92,
      "learning_rate": 9.020000000000001e-05,
      "loss": 0.0012,
      "step": 1100
    },
    {
      "epoch": 14.05,
      "learning_rate": 8.92e-05,
      "loss": 0.0012,
      "step": 1110
    },
    {
      "epoch": 14.18,
      "learning_rate": 8.82e-05,
      "loss": 0.0011,
      "step": 1120
    },
    {
      "epoch": 14.3,
      "learning_rate": 8.72e-05,
      "loss": 0.0011,
      "step": 1130
    },
    {
      "epoch": 14.43,
      "learning_rate": 8.620000000000001e-05,
      "loss": 0.0011,
      "step": 1140
    },
    {
      "epoch": 14.56,
      "learning_rate": 8.52e-05,
      "loss": 0.0011,
      "step": 1150
    },
    {
      "epoch": 14.68,
      "learning_rate": 8.42e-05,
      "loss": 0.0011,
      "step": 1160
    },
    {
      "epoch": 14.81,
      "learning_rate": 8.32e-05,
      "loss": 0.0011,
      "step": 1170
    },
    {
      "epoch": 14.94,
      "learning_rate": 8.22e-05,
      "loss": 0.0011,
      "step": 1180
    },
    {
      "epoch": 15.06,
      "learning_rate": 8.120000000000001e-05,
      "loss": 0.001,
      "step": 1190
    },
    {
      "epoch": 15.19,
      "learning_rate": 8.020000000000001e-05,
      "loss": 0.001,
      "step": 1200
    },
    {
      "epoch": 15.19,
      "eval_accuracy": 0.9545454545454546,
      "eval_f1": 0.915057915057915,
      "eval_loss": 0.3429644703865051,
      "eval_precision": 0.915057915057915,
      "eval_recall": 0.915057915057915,
      "eval_runtime": 0.592,
      "eval_samples_per_second": 74.325,
      "eval_steps_per_second": 10.135,
      "step": 1200
    }
  ],
  "max_steps": 2000,
  "num_train_epochs": 26,
  "total_flos": 3.6847441061738496e+17,
  "trial_name": null,
  "trial_params": null
}