{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5466666666666666,
  "global_step": 174000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.001,
      "loss": 3.4556,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.001,
      "loss": 2.4843,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.001,
      "loss": 2.3101,
      "step": 1500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001,
      "loss": 2.2064,
      "step": 2000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001,
      "loss": 2.1047,
      "step": 2500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001,
      "loss": 2.0111,
      "step": 3000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001,
      "loss": 1.9859,
      "step": 3500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001,
      "loss": 1.9798,
      "step": 4000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001,
      "loss": 1.9326,
      "step": 4500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001,
      "loss": 1.9219,
      "step": 5000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001,
      "loss": 1.8928,
      "step": 5500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001,
      "loss": 1.821,
      "step": 6000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001,
      "loss": 1.8349,
      "step": 6500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001,
      "loss": 1.802,
      "step": 7000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001,
      "loss": 1.7597,
      "step": 7500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001,
      "loss": 1.7561,
      "step": 8000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001,
      "loss": 1.7207,
      "step": 8500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001,
      "loss": 1.7251,
      "step": 9000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001,
      "loss": 1.7242,
      "step": 9500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001,
      "loss": 1.7137,
      "step": 10000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001,
      "loss": 1.6853,
      "step": 10500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 1.6986,
      "step": 11000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 1.6425,
      "step": 11500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 1.6921,
      "step": 12000
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 1.6364,
      "step": 12500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 1.6264,
      "step": 13000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 1.6333,
      "step": 13500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 1.6122,
      "step": 14000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 1.5976,
      "step": 14500
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 1.6001,
      "step": 15000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 1.5895,
      "step": 15500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 1.5867,
      "step": 16000
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 1.6001,
      "step": 16500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 1.5723,
      "step": 17000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 1.5526,
      "step": 17500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 1.5429,
      "step": 18000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 1.5487,
      "step": 18500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 1.5323,
      "step": 19000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 1.545,
      "step": 19500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 1.5183,
      "step": 20000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 1.5281,
      "step": 20500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 1.5144,
      "step": 21000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 1.5134,
      "step": 21500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 1.4865,
      "step": 22000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 1.4814,
      "step": 22500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 1.5141,
      "step": 23000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 1.5223,
      "step": 23500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 1.4913,
      "step": 24000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 1.4862,
      "step": 24500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 1.4814,
      "step": 25000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 1.4684,
      "step": 25500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 1.4753,
      "step": 26000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 1.4666,
      "step": 26500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 1.4431,
      "step": 27000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 1.4427,
      "step": 27500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 1.4621,
      "step": 28000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 1.43,
      "step": 28500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 1.4348,
      "step": 29000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 1.4254,
      "step": 29500
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 1.4607,
      "step": 30000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 1.4302,
      "step": 30500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 1.4194,
      "step": 31000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 1.4368,
      "step": 31500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 1.4111,
      "step": 32000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 1.4014,
      "step": 32500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 1.3937,
      "step": 33000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 1.4116,
      "step": 33500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 1.425,
      "step": 34000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 1.405,
      "step": 34500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 1.4144,
      "step": 35000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 1.3871,
      "step": 35500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 1.4143,
      "step": 36000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 1.4053,
      "step": 36500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 1.3857,
      "step": 37000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 1.4009,
      "step": 37500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 1.3764,
      "step": 38000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 1.3638,
      "step": 38500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 1.3687,
      "step": 39000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 1.3825,
      "step": 39500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 1.3804,
      "step": 40000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 1.3601,
      "step": 40500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 1.386,
      "step": 41000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 1.3633,
      "step": 41500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 1.3844,
      "step": 42000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 1.3465,
      "step": 42500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 1.3405,
      "step": 43000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 1.3266,
      "step": 43500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 1.3687,
      "step": 44000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 1.3169,
      "step": 44500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 1.3478,
      "step": 45000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 1.3242,
      "step": 45500
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 1.333,
      "step": 46000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 1.323,
      "step": 46500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 1.3311,
      "step": 47000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 1.3164,
      "step": 47500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 1.327,
      "step": 48000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 1.3076,
      "step": 48500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 1.3133,
      "step": 49000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 1.3133,
      "step": 49500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 1.3376,
      "step": 50000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 1.3203,
      "step": 50500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 1.3356,
      "step": 51000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 1.3197,
      "step": 51500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 1.3176,
      "step": 52000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 1.3042,
      "step": 52500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 1.3031,
      "step": 53000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 1.2999,
      "step": 53500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 1.3158,
      "step": 54000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 1.2983,
      "step": 54500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 1.306,
      "step": 55000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 1.3072,
      "step": 55500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 1.298,
      "step": 56000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 1.2886,
      "step": 56500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001,
      "loss": 1.296,
      "step": 57000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001,
      "loss": 1.296,
      "step": 57500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001,
      "loss": 1.286,
      "step": 58000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001,
      "loss": 1.2855,
      "step": 58500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001,
      "loss": 1.2754,
      "step": 59000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.001,
      "loss": 1.2904,
      "step": 59500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.001,
      "loss": 1.2922,
      "step": 60000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.001,
      "loss": 1.2966,
      "step": 60500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.001,
      "loss": 1.29,
      "step": 61000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.001,
      "loss": 1.2766,
      "step": 61500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.001,
      "loss": 1.2709,
      "step": 62000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001,
      "loss": 1.2684,
      "step": 62500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001,
      "loss": 1.2461,
      "step": 63000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001,
      "loss": 1.2539,
      "step": 63500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.001,
      "loss": 1.2634,
      "step": 64000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.001,
      "loss": 1.2681,
      "step": 64500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.001,
      "loss": 1.2544,
      "step": 65000
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.001,
      "loss": 1.26,
      "step": 65500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.001,
      "loss": 1.2601,
      "step": 66000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.001,
      "loss": 1.2748,
      "step": 66500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.001,
      "loss": 1.265,
      "step": 67000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.001,
      "loss": 1.2495,
      "step": 67500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.001,
      "loss": 1.2569,
      "step": 68000
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.001,
      "loss": 1.2484,
      "step": 68500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.001,
      "loss": 1.2728,
      "step": 69000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.001,
      "loss": 1.231,
      "step": 69500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.001,
      "loss": 1.2527,
      "step": 70000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.001,
      "loss": 1.2294,
      "step": 70500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.001,
      "loss": 1.2435,
      "step": 71000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.001,
      "loss": 1.2319,
      "step": 71500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.001,
      "loss": 1.2236,
      "step": 72000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.001,
      "loss": 1.245,
      "step": 72500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.001,
      "loss": 1.2397,
      "step": 73000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.001,
      "loss": 1.2377,
      "step": 73500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.001,
      "loss": 1.2247,
      "step": 74000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.001,
      "loss": 1.2354,
      "step": 74500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.001,
      "loss": 1.215,
      "step": 75000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.001,
      "loss": 1.2277,
      "step": 75500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.001,
      "loss": 1.2464,
      "step": 76000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.001,
      "loss": 1.2375,
      "step": 76500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.001,
      "loss": 1.2307,
      "step": 77000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.001,
      "loss": 1.2056,
      "step": 77500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.001,
      "loss": 1.2232,
      "step": 78000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.001,
      "loss": 1.2274,
      "step": 78500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.001,
      "loss": 1.2175,
      "step": 79000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.001,
      "loss": 1.2059,
      "step": 79500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.001,
      "loss": 1.2274,
      "step": 80000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001,
      "loss": 1.2042,
      "step": 80500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001,
      "loss": 1.221,
      "step": 81000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001,
      "loss": 1.2163,
      "step": 81500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001,
      "loss": 1.2295,
      "step": 82000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001,
      "loss": 1.2114,
      "step": 82500
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001,
      "loss": 1.2228,
      "step": 83000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001,
      "loss": 1.2094,
      "step": 83500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001,
      "loss": 1.1924,
      "step": 84000
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001,
      "loss": 1.2422,
      "step": 84500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001,
      "loss": 1.2321,
      "step": 85000
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001,
      "loss": 1.2157,
      "step": 85500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001,
      "loss": 1.2033,
      "step": 86000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001,
      "loss": 1.2134,
      "step": 86500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001,
      "loss": 1.1787,
      "step": 87000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001,
      "loss": 1.2102,
      "step": 87500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001,
      "loss": 1.2061,
      "step": 88000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001,
      "loss": 1.2195,
      "step": 88500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001,
      "loss": 1.2125,
      "step": 89000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001,
      "loss": 1.2188,
      "step": 89500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001,
      "loss": 1.1938,
      "step": 90000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001,
      "loss": 1.1988,
      "step": 90500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.001,
      "loss": 1.1952,
      "step": 91000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.001,
      "loss": 1.2115,
      "step": 91500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.001,
      "loss": 1.2101,
      "step": 92000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.001,
      "loss": 1.1925,
      "step": 92500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.001,
      "loss": 1.1897,
      "step": 93000
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.001,
      "loss": 1.1962,
      "step": 93500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.001,
      "loss": 1.1838,
      "step": 94000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.001,
      "loss": 1.1766,
      "step": 94500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.001,
      "loss": 1.1399,
      "step": 95000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.001,
      "loss": 1.1644,
      "step": 95500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.001,
      "loss": 1.1878,
      "step": 96000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.001,
      "loss": 1.1957,
      "step": 96500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.001,
      "loss": 1.1802,
      "step": 97000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.001,
      "loss": 1.1685,
      "step": 97500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.001,
      "loss": 1.1803,
      "step": 98000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.001,
      "loss": 1.1914,
      "step": 98500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.001,
      "loss": 1.1811,
      "step": 99000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.001,
      "loss": 1.1798,
      "step": 99500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.001,
      "loss": 1.1686,
      "step": 100000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.001,
      "loss": 1.1655,
      "step": 100500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.001,
      "loss": 1.1653,
      "step": 101000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.001,
      "loss": 1.1826,
      "step": 101500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.001,
      "loss": 1.1657,
      "step": 102000
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.001,
      "loss": 1.1515,
      "step": 102500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.001,
      "loss": 1.1611,
      "step": 103000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.001,
      "loss": 1.1718,
      "step": 103500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.001,
      "loss": 1.1719,
      "step": 104000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.001,
      "loss": 1.1583,
      "step": 104500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.001,
      "loss": 1.1698,
      "step": 105000
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.001,
      "loss": 1.1643,
      "step": 105500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.001,
      "loss": 1.1648,
      "step": 106000
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.001,
      "loss": 1.1458,
      "step": 106500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.001,
      "loss": 1.1485,
      "step": 107000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.001,
      "loss": 1.1641,
      "step": 107500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.001,
      "loss": 1.1567,
      "step": 108000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.001,
      "loss": 1.172,
      "step": 108500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.001,
      "loss": 1.1746,
      "step": 109000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.001,
      "loss": 1.1646,
      "step": 109500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.001,
      "loss": 1.14,
      "step": 110000
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.001,
      "loss": 1.1533,
      "step": 110500
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.001,
      "loss": 1.1541,
      "step": 111000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.001,
      "loss": 1.1381,
      "step": 111500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 1.1591,
      "step": 112000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 1.1502,
      "step": 112500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 21.0872,
      "eval_gen_len": 12.0896,
      "eval_loss": 1.478177785873413,
      "eval_runtime": 1045.1107,
      "eval_samples_per_second": 13.396,
      "step": 112500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 1.0899,
      "step": 113000
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.001,
      "loss": 1.0716,
      "step": 113500
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.001,
      "loss": 1.1085,
      "step": 114000
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.001,
      "loss": 1.0761,
      "step": 114500
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.001,
      "loss": 1.0929,
      "step": 115000
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.001,
      "loss": 1.0829,
      "step": 115500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.001,
      "loss": 1.0996,
      "step": 116000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.001,
      "loss": 1.092,
      "step": 116500
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.001,
      "loss": 1.0791,
      "step": 117000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.001,
      "loss": 1.0793,
      "step": 117500
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.001,
      "loss": 1.0768,
      "step": 118000
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.001,
      "loss": 1.1088,
      "step": 118500
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001,
      "loss": 1.1054,
      "step": 119000
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001,
      "loss": 1.0745,
      "step": 119500
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.001,
      "loss": 1.0851,
      "step": 120000
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.001,
      "loss": 1.0762,
      "step": 120500
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.001,
      "loss": 1.0778,
      "step": 121000
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.001,
      "loss": 1.1035,
      "step": 121500
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.001,
      "loss": 1.0813,
      "step": 122000
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.001,
      "loss": 1.0853,
      "step": 122500
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.001,
      "loss": 1.0712,
      "step": 123000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.001,
      "loss": 1.0729,
      "step": 123500
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.001,
      "loss": 1.0839,
      "step": 124000
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.001,
      "loss": 1.0812,
      "step": 124500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.001,
      "loss": 1.0811,
      "step": 125000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.001,
      "loss": 1.0886,
      "step": 125500
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.001,
      "loss": 1.074,
      "step": 126000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.001,
      "loss": 1.0828,
      "step": 126500
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.001,
      "loss": 1.0771,
      "step": 127000
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.001,
      "loss": 1.0851,
      "step": 127500
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.001,
      "loss": 1.075,
      "step": 128000
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.001,
      "loss": 1.0858,
      "step": 128500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.001,
      "loss": 1.0899,
      "step": 129000
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.001,
      "loss": 1.0967,
      "step": 129500
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.001,
      "loss": 1.0951,
      "step": 130000
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.001,
      "loss": 1.078,
      "step": 130500
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.001,
      "loss": 1.0671,
      "step": 131000
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.001,
      "loss": 1.0718,
      "step": 131500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.001,
      "loss": 1.0791,
      "step": 132000
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.001,
      "loss": 1.1058,
      "step": 132500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.001,
      "loss": 1.0814,
      "step": 133000
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.001,
      "loss": 1.0855,
      "step": 133500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.001,
      "loss": 1.0707,
      "step": 134000
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.001,
      "loss": 1.0674,
      "step": 134500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.001,
      "loss": 1.0774,
      "step": 135000
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.001,
      "loss": 1.0722,
      "step": 135500
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.001,
      "loss": 1.0868,
      "step": 136000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.001,
      "loss": 1.0684,
      "step": 136500
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.001,
      "loss": 1.0647,
      "step": 137000
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.001,
      "loss": 1.0845,
      "step": 137500
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.001,
      "loss": 1.0857,
      "step": 138000
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.001,
      "loss": 1.0744,
      "step": 138500
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.001,
      "loss": 1.0747,
      "step": 139000
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.001,
      "loss": 1.0628,
      "step": 139500
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.001,
      "loss": 1.0822,
      "step": 140000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.001,
      "loss": 1.0917,
      "step": 140500
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.001,
      "loss": 1.0739,
      "step": 141000
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.001,
      "loss": 1.0694,
      "step": 141500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.001,
      "loss": 1.0741,
      "step": 142000
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.001,
      "loss": 1.0517,
      "step": 142500
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.001,
      "loss": 1.0878,
      "step": 143000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.001,
      "loss": 1.0591,
      "step": 143500
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.001,
      "loss": 1.0717,
      "step": 144000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.001,
      "loss": 1.0816,
      "step": 144500
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.001,
      "loss": 1.0582,
      "step": 145000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.001,
      "loss": 1.085,
      "step": 145500
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.001,
      "loss": 1.0552,
      "step": 146000
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.001,
      "loss": 1.0776,
      "step": 146500
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.001,
      "loss": 1.0493,
      "step": 147000
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.001,
      "loss": 1.0676,
      "step": 147500
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.001,
      "loss": 1.0601,
      "step": 148000
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.001,
      "loss": 1.0706,
      "step": 148500
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.001,
      "loss": 1.0853,
      "step": 149000
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.001,
      "loss": 1.0588,
      "step": 149500
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.001,
      "loss": 1.0589,
      "step": 150000
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.001,
      "loss": 1.0705,
      "step": 150500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.001,
      "loss": 1.0749,
      "step": 151000
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.001,
      "loss": 1.0705,
      "step": 151500
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.001,
      "loss": 1.0652,
      "step": 152000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.001,
      "loss": 1.063,
      "step": 152500
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.001,
      "loss": 1.0551,
      "step": 153000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.001,
      "loss": 1.0437,
      "step": 153500
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.001,
      "loss": 1.0278,
      "step": 154000
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.001,
      "loss": 1.0439,
      "step": 154500
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.001,
      "loss": 1.0619,
      "step": 155000
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.001,
      "loss": 1.0382,
      "step": 155500
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.001,
      "loss": 1.0643,
      "step": 156000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.001,
      "loss": 1.0583,
      "step": 156500
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.001,
      "loss": 1.0651,
      "step": 157000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.001,
      "loss": 1.06,
      "step": 157500
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.001,
      "loss": 1.0591,
      "step": 158000
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.001,
      "loss": 1.0718,
      "step": 158500
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.001,
      "loss": 1.0671,
      "step": 159000
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.001,
      "loss": 1.0517,
      "step": 159500
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.001,
      "loss": 1.0578,
      "step": 160000
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.001,
      "loss": 1.0761,
      "step": 160500
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.001,
      "loss": 1.0234,
      "step": 161000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.001,
      "loss": 1.047,
      "step": 161500
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.001,
      "loss": 1.0539,
      "step": 162000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.001,
      "loss": 1.0642,
      "step": 162500
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.001,
      "loss": 1.0563,
      "step": 163000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.001,
      "loss": 1.0507,
      "step": 163500
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.001,
      "loss": 1.0556,
      "step": 164000
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.001,
      "loss": 1.0525,
      "step": 164500
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.001,
      "loss": 1.0422,
      "step": 165000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.001,
      "loss": 1.0455,
      "step": 165500
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001,
      "loss": 1.04,
      "step": 166000
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001,
      "loss": 1.0365,
      "step": 166500
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001,
      "loss": 1.0379,
      "step": 167000
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.001,
      "loss": 1.0655,
      "step": 167500
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.001,
      "loss": 1.0412,
      "step": 168000
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.001,
      "loss": 1.0677,
      "step": 168500
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.001,
      "loss": 1.0596,
      "step": 169000
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.001,
      "loss": 1.0531,
      "step": 169500
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.001,
      "loss": 1.0193,
      "step": 170000
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.001,
      "loss": 1.0533,
      "step": 170500
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.001,
      "loss": 1.033,
      "step": 171000
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.001,
      "loss": 1.0497,
      "step": 171500
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.001,
      "loss": 1.0361,
      "step": 172000
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.001,
      "loss": 1.033,
      "step": 172500
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.001,
      "loss": 1.0578,
      "step": 173000
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.001,
      "loss": 1.0392,
      "step": 173500
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.001,
      "loss": 1.0427,
      "step": 174000
    }
  ],
  "max_steps": 337500,
  "num_train_epochs": 3,
  "total_flos": 819679556720640.0,
  "trial_name": null,
  "trial_params": null
}