{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.25017499650007,
  "global_step": 8930,
  "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": 0.8401,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7948,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7995,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7895,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7783,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7651,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7701,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7683,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7668,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7739,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7609,
      "step": 220
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7591,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7525,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7587,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7479,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7545,
      "step": 340
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7556,
      "step": 360
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7509,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7595,
      "step": 400
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7474,
      "step": 420
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7442,
      "step": 440
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7491,
      "step": 460
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7604,
      "step": 480
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7527,
      "step": 500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7577,
      "step": 520
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.745,
      "step": 540
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7426,
      "step": 560
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7316,
      "step": 580
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7477,
      "step": 600
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7293,
      "step": 620
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7337,
      "step": 640
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7326,
      "step": 660
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7364,
      "step": 680
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7416,
      "step": 700
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7413,
      "step": 720
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7385,
      "step": 740
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7375,
      "step": 760
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7296,
      "step": 780
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7464,
      "step": 800
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7199,
      "step": 820
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.72,
      "step": 840
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7301,
      "step": 860
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7168,
      "step": 880
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7421,
      "step": 900
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7354,
      "step": 920
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7202,
      "step": 940
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.736,
      "step": 960
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7264,
      "step": 980
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7214,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7209,
      "step": 1020
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7141,
      "step": 1040
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7299,
      "step": 1060
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7319,
      "step": 1080
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7268,
      "step": 1100
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.7305,
      "step": 1120
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.7262,
      "step": 1140
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.7304,
      "step": 1160
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7237,
      "step": 1180
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7229,
      "step": 1200
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7295,
      "step": 1220
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7181,
      "step": 1240
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7285,
      "step": 1260
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7273,
      "step": 1280
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7242,
      "step": 1300
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7171,
      "step": 1320
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7405,
      "step": 1340
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7118,
      "step": 1360
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.725,
      "step": 1380
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7155,
      "step": 1400
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7195,
      "step": 1420
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7217,
      "step": 1440
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7162,
      "step": 1460
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.704,
      "step": 1480
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.712,
      "step": 1500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.7277,
      "step": 1520
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7228,
      "step": 1540
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7114,
      "step": 1560
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7229,
      "step": 1580
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7153,
      "step": 1600
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7189,
      "step": 1620
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7126,
      "step": 1640
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7047,
      "step": 1660
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.7083,
      "step": 1680
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.718,
      "step": 1700
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.721,
      "step": 1720
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.7116,
      "step": 1740
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7043,
      "step": 1760
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7019,
      "step": 1780
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7162,
      "step": 1800
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7175,
      "step": 1820
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7222,
      "step": 1840
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7238,
      "step": 1860
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7212,
      "step": 1880
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.701,
      "step": 1900
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.7171,
      "step": 1920
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.719,
      "step": 1940
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.7139,
      "step": 1960
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.7085,
      "step": 1980
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.7281,
      "step": 2000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.7132,
      "step": 2020
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.6934,
      "step": 2040
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7176,
      "step": 2060
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7113,
      "step": 2080
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7158,
      "step": 2100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.7142,
      "step": 2120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.7007,
      "step": 2140
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.712,
      "step": 2160
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.7054,
      "step": 2180
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6999,
      "step": 2200
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.7122,
      "step": 2220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6966,
      "step": 2240
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.7123,
      "step": 2260
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.6991,
      "step": 2280
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.7104,
      "step": 2300
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.7026,
      "step": 2320
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.7147,
      "step": 2340
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6981,
      "step": 2360
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.7053,
      "step": 2380
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.7153,
      "step": 2400
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.6991,
      "step": 2420
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.712,
      "step": 2440
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.6918,
      "step": 2460
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.6991,
      "step": 2480
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.6973,
      "step": 2500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.7032,
      "step": 2520
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.7077,
      "step": 2540
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.7085,
      "step": 2560
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.7092,
      "step": 2580
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6968,
      "step": 2600
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.7101,
      "step": 2620
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.7131,
      "step": 2640
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.6951,
      "step": 2660
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.6991,
      "step": 2680
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.7116,
      "step": 2700
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.6928,
      "step": 2720
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.7094,
      "step": 2740
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.7084,
      "step": 2760
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6982,
      "step": 2780
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.7067,
      "step": 2800
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.7047,
      "step": 2820
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.7184,
      "step": 2840
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.7087,
      "step": 2860
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.6987,
      "step": 2880
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.6938,
      "step": 2900
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7005,
      "step": 2920
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7054,
      "step": 2940
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7009,
      "step": 2960
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6951,
      "step": 2980
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.7039,
      "step": 3000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6951,
      "step": 3020
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6997,
      "step": 3040
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7068,
      "step": 3060
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7104,
      "step": 3080
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6924,
      "step": 3100
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.7088,
      "step": 3120
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.7114,
      "step": 3140
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6913,
      "step": 3160
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.7,
      "step": 3180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6963,
      "step": 3200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.7086,
      "step": 3220
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.7044,
      "step": 3240
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.7031,
      "step": 3260
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6927,
      "step": 3280
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6985,
      "step": 3300
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.7014,
      "step": 3320
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6958,
      "step": 3340
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.698,
      "step": 3360
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6992,
      "step": 3380
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.7,
      "step": 3400
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.7039,
      "step": 3420
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.6907,
      "step": 3440
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.7026,
      "step": 3460
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.6968,
      "step": 3480
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.695,
      "step": 3500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.7059,
      "step": 3520
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.6892,
      "step": 3540
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.694,
      "step": 3560
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.6917,
      "step": 3580
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.6912,
      "step": 3600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.6797,
      "step": 3620
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.7071,
      "step": 3640
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.6925,
      "step": 3660
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.6986,
      "step": 3680
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.705,
      "step": 3700
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.6925,
      "step": 3720
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.6915,
      "step": 3740
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.7167,
      "step": 3760
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.6808,
      "step": 3780
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.6859,
      "step": 3800
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.7077,
      "step": 3820
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6987,
      "step": 3840
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.7023,
      "step": 3860
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.7013,
      "step": 3880
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.7041,
      "step": 3900
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.6866,
      "step": 3920
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.6918,
      "step": 3940
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.7061,
      "step": 3960
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.6915,
      "step": 3980
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.6844,
      "step": 4000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.6746,
      "step": 4020
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6714,
      "step": 4040
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6979,
      "step": 4060
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.688,
      "step": 4080
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6858,
      "step": 4100
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.6921,
      "step": 4120
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.6815,
      "step": 4140
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.6971,
      "step": 4160
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.7009,
      "step": 4180
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.6903,
      "step": 4200
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.6928,
      "step": 4220
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.696,
      "step": 4240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.7005,
      "step": 4260
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.6923,
      "step": 4280
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.6963,
      "step": 4300
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.6925,
      "step": 4320
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6873,
      "step": 4340
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6962,
      "step": 4360
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6861,
      "step": 4380
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6843,
      "step": 4400
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6823,
      "step": 4420
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6861,
      "step": 4440
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6864,
      "step": 4460
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6839,
      "step": 4480
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6855,
      "step": 4500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.7058,
      "step": 4520
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.7038,
      "step": 4540
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.689,
      "step": 4560
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6793,
      "step": 4580
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6983,
      "step": 4600
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.6943,
      "step": 4620
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.6905,
      "step": 4640
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.6849,
      "step": 4660
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6895,
      "step": 4680
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6955,
      "step": 4700
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6848,
      "step": 4720
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6997,
      "step": 4740
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.6828,
      "step": 4760
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.6873,
      "step": 4780
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.689,
      "step": 4800
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.679,
      "step": 4820
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.6844,
      "step": 4840
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.6938,
      "step": 4860
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.6938,
      "step": 4880
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.687,
      "step": 4900
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.6808,
      "step": 4920
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.6798,
      "step": 4940
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.6979,
      "step": 4960
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.6843,
      "step": 4980
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.6991,
      "step": 5000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.6799,
      "step": 5020
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6819,
      "step": 5040
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6763,
      "step": 5060
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6814,
      "step": 5080
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6902,
      "step": 5100
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.6954,
      "step": 5120
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.6936,
      "step": 5140
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.6854,
      "step": 5160
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.687,
      "step": 5180
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.6835,
      "step": 5200
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.6881,
      "step": 5220
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.6917,
      "step": 5240
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6984,
      "step": 5260
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6856,
      "step": 5280
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6838,
      "step": 5300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6877,
      "step": 5320
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.6721,
      "step": 5340
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.682,
      "step": 5360
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.6905,
      "step": 5380
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.6806,
      "step": 5400
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.6869,
      "step": 5420
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.6928,
      "step": 5440
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.6818,
      "step": 5460
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.6771,
      "step": 5480
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.693,
      "step": 5500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.6762,
      "step": 5520
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.6837,
      "step": 5540
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.684,
      "step": 5560
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.6707,
      "step": 5580
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.6959,
      "step": 5600
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.6944,
      "step": 5620
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.6851,
      "step": 5640
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.6758,
      "step": 5660
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.6971,
      "step": 5680
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.6858,
      "step": 5700
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.6941,
      "step": 5720
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.698,
      "step": 5740
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.6932,
      "step": 5760
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.678,
      "step": 5780
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 5800
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 5820
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.6846,
      "step": 5840
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.684,
      "step": 5860
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.6791,
      "step": 5880
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.6819,
      "step": 5900
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.6805,
      "step": 5920
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.675,
      "step": 5940
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.6945,
      "step": 5960
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.6761,
      "step": 5980
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.6828,
      "step": 6000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.6836,
      "step": 6020
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.6776,
      "step": 6040
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.6959,
      "step": 6060
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.6864,
      "step": 6080
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.6851,
      "step": 6100
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.6736,
      "step": 6120
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.6855,
      "step": 6140
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.6882,
      "step": 6160
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.6965,
      "step": 6180
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.6824,
      "step": 6200
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.6772,
      "step": 6220
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.6877,
      "step": 6240
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6712,
      "step": 6260
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6809,
      "step": 6280
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6782,
      "step": 6300
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.676,
      "step": 6320
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.6749,
      "step": 6340
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.679,
      "step": 6360
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.6858,
      "step": 6380
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.6772,
      "step": 6400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.686,
      "step": 6420
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.6782,
      "step": 6440
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.691,
      "step": 6460
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.6898,
      "step": 6480
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.68,
      "step": 6500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.6808,
      "step": 6520
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.6885,
      "step": 6540
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.6798,
      "step": 6560
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.685,
      "step": 6580
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.677,
      "step": 6600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.6798,
      "step": 6620
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.6792,
      "step": 6640
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.6767,
      "step": 6660
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.6848,
      "step": 6680
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.6775,
      "step": 6700
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.6772,
      "step": 6720
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.678,
      "step": 6740
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.6875,
      "step": 6760
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.6712,
      "step": 6780
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.6879,
      "step": 6800
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.6743,
      "step": 6820
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.6883,
      "step": 6840
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.6822,
      "step": 6860
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.6833,
      "step": 6880
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.6714,
      "step": 6900
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.6663,
      "step": 6920
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.6814,
      "step": 6940
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.6774,
      "step": 6960
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.6812,
      "step": 6980
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.6812,
      "step": 7000
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.68,
      "step": 7020
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.6761,
      "step": 7040
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.6772,
      "step": 7060
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.703,
      "step": 7080
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.679,
      "step": 7100
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.6841,
      "step": 7120
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.6752,
      "step": 7140
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.6493,
      "step": 7160
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6358,
      "step": 7180
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6454,
      "step": 7200
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6483,
      "step": 7220
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6485,
      "step": 7240
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.625,
      "step": 7260
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.6431,
      "step": 7280
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.648,
      "step": 7300
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.6372,
      "step": 7320
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.6442,
      "step": 7340
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.6426,
      "step": 7360
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.6449,
      "step": 7380
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6358,
      "step": 7400
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6564,
      "step": 7420
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6409,
      "step": 7440
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6371,
      "step": 7460
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.6343,
      "step": 7480
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.6487,
      "step": 7500
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.6393,
      "step": 7520
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.6349,
      "step": 7540
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.6445,
      "step": 7560
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.642,
      "step": 7580
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.6528,
      "step": 7600
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.6408,
      "step": 7620
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.6516,
      "step": 7640
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.6573,
      "step": 7660
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6399,
      "step": 7680
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.64,
      "step": 7700
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6555,
      "step": 7720
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6534,
      "step": 7740
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.6492,
      "step": 7760
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.6563,
      "step": 7780
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.6566,
      "step": 7800
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.6564,
      "step": 7820
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.6482,
      "step": 7840
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.6579,
      "step": 7860
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.642,
      "step": 7880
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.6529,
      "step": 7900
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.6498,
      "step": 7920
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.658,
      "step": 7940
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.6465,
      "step": 7960
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.6378,
      "step": 7980
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.6511,
      "step": 8000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.6472,
      "step": 8020
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.6463,
      "step": 8040
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.6494,
      "step": 8060
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.6405,
      "step": 8080
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.648,
      "step": 8100
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.6352,
      "step": 8120
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.655,
      "step": 8140
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.6497,
      "step": 8160
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.6463,
      "step": 8180
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.6522,
      "step": 8200
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.6356,
      "step": 8220
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.6531,
      "step": 8240
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.6612,
      "step": 8260
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.6542,
      "step": 8280
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.6399,
      "step": 8300
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.6458,
      "step": 8320
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.6459,
      "step": 8340
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.6458,
      "step": 8360
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.6471,
      "step": 8380
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6515,
      "step": 8400
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6484,
      "step": 8420
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6398,
      "step": 8440
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6461,
      "step": 8460
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.6395,
      "step": 8480
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.6394,
      "step": 8500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.6611,
      "step": 8520
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.6399,
      "step": 8540
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.6424,
      "step": 8560
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.6507,
      "step": 8580
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.6424,
      "step": 8600
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.6525,
      "step": 8620
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.6559,
      "step": 8640
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.6365,
      "step": 8660
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.6458,
      "step": 8680
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.6551,
      "step": 8700
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.6333,
      "step": 8720
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.6621,
      "step": 8740
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6413,
      "step": 8760
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6499,
      "step": 8780
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6433,
      "step": 8800
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6456,
      "step": 8820
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.6609,
      "step": 8840
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.6482,
      "step": 8860
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.6554,
      "step": 8880
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.6614,
      "step": 8900
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.6511,
      "step": 8920
    }
  ],
  "max_steps": 14286,
  "num_train_epochs": 2,
  "total_flos": 1.422334853310002e+19,
  "trial_name": null,
  "trial_params": null
}