{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.276863700995328,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4925,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5536,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5285,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3814,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5555,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5348,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4383,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3489,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5326,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5263,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.4014,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3948,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.4192,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3897,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3975,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.3531,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4205,
      "step": 170
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4895,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.4019,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.4694,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.4013,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.4683,
      "step": 220
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.3596,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.446,
      "step": 240
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4396,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.4667,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.3853,
      "step": 270
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.329,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.3598,
      "step": 290
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.4108,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.351,
      "step": 310
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4217,
      "step": 320
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.2958,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4875,
      "step": 340
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.3135,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.4256,
      "step": 360
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.333,
      "step": 370
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.404,
      "step": 380
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.423,
      "step": 390
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.299,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.3195,
      "step": 410
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.444,
      "step": 420
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.3588,
      "step": 430
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.2012,
      "step": 440
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.3377,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.3287,
      "step": 460
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.4087,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.2598,
      "step": 480
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.2902,
      "step": 490
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.2608,
      "step": 500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.3329,
      "step": 510
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.3429,
      "step": 520
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.5191,
      "step": 530
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.3305,
      "step": 540
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.297,
      "step": 550
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.2586,
      "step": 560
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.394,
      "step": 570
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.2972,
      "step": 580
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.3989,
      "step": 590
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.404,
      "step": 600
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4292,
      "step": 610
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.2685,
      "step": 620
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.275,
      "step": 630
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.3224,
      "step": 640
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.3715,
      "step": 650
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.3544,
      "step": 660
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.3164,
      "step": 670
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.3901,
      "step": 680
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.3552,
      "step": 690
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.1242,
      "step": 700
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.1625,
      "step": 710
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.365,
      "step": 720
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.239,
      "step": 730
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.3183,
      "step": 740
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.3209,
      "step": 750
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.2468,
      "step": 760
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.1396,
      "step": 770
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.2955,
      "step": 780
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.3382,
      "step": 790
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.29,
      "step": 800
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.2515,
      "step": 810
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.3559,
      "step": 820
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.3572,
      "step": 830
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.2415,
      "step": 840
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.3382,
      "step": 850
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.3466,
      "step": 860
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.2496,
      "step": 870
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.3328,
      "step": 880
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.2793,
      "step": 890
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.3802,
      "step": 900
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.3284,
      "step": 910
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.2867,
      "step": 920
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.402,
      "step": 930
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.299,
      "step": 940
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.3946,
      "step": 950
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.2259,
      "step": 960
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.3248,
      "step": 970
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.4078,
      "step": 980
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.3553,
      "step": 990
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.2495,
      "step": 1000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.3544,
      "step": 1010
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.3392,
      "step": 1020
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.2176,
      "step": 1030
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.3656,
      "step": 1040
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.3731,
      "step": 1050
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.2354,
      "step": 1060
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.3184,
      "step": 1070
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.2772,
      "step": 1080
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.2803,
      "step": 1090
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.2614,
      "step": 1100
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.3461,
      "step": 1110
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.2487,
      "step": 1120
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.4393,
      "step": 1130
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3058,
      "step": 1140
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.2309,
      "step": 1150
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.329,
      "step": 1160
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.2415,
      "step": 1170
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.2988,
      "step": 1180
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.2211,
      "step": 1190
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.3688,
      "step": 1200
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.4223,
      "step": 1210
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.3736,
      "step": 1220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.434,
      "step": 1230
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.5222,
      "step": 1240
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.3718,
      "step": 1250
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.3461,
      "step": 1260
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.4405,
      "step": 1270
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.356,
      "step": 1280
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.4298,
      "step": 1290
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.4098,
      "step": 1300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.47,
      "step": 1310
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.3258,
      "step": 1320
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.4649,
      "step": 1330
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.3641,
      "step": 1340
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.3667,
      "step": 1350
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.4318,
      "step": 1360
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.3711,
      "step": 1370
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.2749,
      "step": 1380
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.3315,
      "step": 1390
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.3908,
      "step": 1400
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.3234,
      "step": 1410
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.3838,
      "step": 1420
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.437,
      "step": 1430
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.4413,
      "step": 1440
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.3568,
      "step": 1450
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.3885,
      "step": 1460
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.5233,
      "step": 1470
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.3296,
      "step": 1480
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.3491,
      "step": 1490
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.424,
      "step": 1500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.4289,
      "step": 1510
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.3127,
      "step": 1520
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.2241,
      "step": 1530
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.2274,
      "step": 1540
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.2479,
      "step": 1550
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.2007,
      "step": 1560
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.1126,
      "step": 1570
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.2896,
      "step": 1580
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3011,
      "step": 1590
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3503,
      "step": 1600
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3813,
      "step": 1610
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.2528,
      "step": 1620
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.2553,
      "step": 1630
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.1805,
      "step": 1640
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.3116,
      "step": 1650
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.1715,
      "step": 1660
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.2623,
      "step": 1670
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.2662,
      "step": 1680
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.2418,
      "step": 1690
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.2849,
      "step": 1700
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.2327,
      "step": 1710
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.3089,
      "step": 1720
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.3146,
      "step": 1730
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.2685,
      "step": 1740
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.2235,
      "step": 1750
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.3032,
      "step": 1760
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.3883,
      "step": 1770
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.2174,
      "step": 1780
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.1867,
      "step": 1790
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.4143,
      "step": 1800
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.2782,
      "step": 1810
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.3217,
      "step": 1820
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.2473,
      "step": 1830
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.3987,
      "step": 1840
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.234,
      "step": 1850
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.2514,
      "step": 1860
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.3796,
      "step": 1870
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.2765,
      "step": 1880
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.3145,
      "step": 1890
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.4093,
      "step": 1900
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.2911,
      "step": 1910
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.3648,
      "step": 1920
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.3821,
      "step": 1930
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.285,
      "step": 1940
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.2649,
      "step": 1950
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.3154,
      "step": 1960
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.3199,
      "step": 1970
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.5186,
      "step": 1980
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.4233,
      "step": 1990
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.09,
      "step": 2000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.5042,
      "step": 2010
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.3121,
      "step": 2020
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 2030
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.3869,
      "step": 2040
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.2218,
      "step": 2050
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.2642,
      "step": 2060
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.3121,
      "step": 2070
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.4389,
      "step": 2080
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.2192,
      "step": 2090
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.2253,
      "step": 2100
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.3525,
      "step": 2110
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.3316,
      "step": 2120
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.3159,
      "step": 2130
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.2644,
      "step": 2140
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.3955,
      "step": 2150
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.4202,
      "step": 2160
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.4747,
      "step": 2170
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.3474,
      "step": 2180
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.2907,
      "step": 2190
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.3435,
      "step": 2200
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.3529,
      "step": 2210
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.4306,
      "step": 2220
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.3955,
      "step": 2230
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.2154,
      "step": 2240
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.3629,
      "step": 2250
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.3808,
      "step": 2260
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.3418,
      "step": 2270
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.356,
      "step": 2280
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.313,
      "step": 2290
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.2293,
      "step": 2300
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.3212,
      "step": 2310
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.311,
      "step": 2320
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.3077,
      "step": 2330
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.3911,
      "step": 2340
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.4614,
      "step": 2350
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.4474,
      "step": 2360
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.3504,
      "step": 2370
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.3172,
      "step": 2380
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3395,
      "step": 2390
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.2341,
      "step": 2400
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.2946,
      "step": 2410
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.3462,
      "step": 2420
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2562,
      "step": 2430
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.4423,
      "step": 2440
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.3309,
      "step": 2450
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.3252,
      "step": 2460
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.4931,
      "step": 2470
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.394,
      "step": 2480
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.3699,
      "step": 2490
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.2406,
      "step": 2500
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.3237,
      "step": 2510
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.3276,
      "step": 2520
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.3059,
      "step": 2530
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.4309,
      "step": 2540
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.4383,
      "step": 2550
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.2884,
      "step": 2560
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.3261,
      "step": 2570
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.3703,
      "step": 2580
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.2999,
      "step": 2590
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.3064,
      "step": 2600
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.2047,
      "step": 2610
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.2324,
      "step": 2620
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.2054,
      "step": 2630
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.3494,
      "step": 2640
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.2357,
      "step": 2650
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.4672,
      "step": 2660
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.2774,
      "step": 2670
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.2379,
      "step": 2680
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.3238,
      "step": 2690
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.4009,
      "step": 2700
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.2842,
      "step": 2710
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.3255,
      "step": 2720
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.3245,
      "step": 2730
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.3019,
      "step": 2740
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.4429,
      "step": 2750
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.2882,
      "step": 2760
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.3345,
      "step": 2770
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.341,
      "step": 2780
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.3499,
      "step": 2790
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.3036,
      "step": 2800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.2273,
      "step": 2810
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.2335,
      "step": 2820
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.3036,
      "step": 2830
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.2379,
      "step": 2840
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.2315,
      "step": 2850
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.4824,
      "step": 2860
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.3188,
      "step": 2870
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.2669,
      "step": 2880
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.2523,
      "step": 2890
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.4137,
      "step": 2900
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.3962,
      "step": 2910
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.2809,
      "step": 2920
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.2891,
      "step": 2930
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.2922,
      "step": 2940
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.3226,
      "step": 2950
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.2633,
      "step": 2960
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 2970
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.1686,
      "step": 2980
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.2729,
      "step": 2990
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.3322,
      "step": 3000
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 5,
  "total_flos": 2.44965925453824e+17,
  "trial_name": null,
  "trial_params": null
}