{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 210.0839983200336,
  "global_step": 250000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42,
      "learning_rate": 1e-05,
      "learning_rate_embeddings": 1e-05,
      "loss": 8.3386,
      "step": 500
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "learning_rate_embeddings": 2e-05,
      "loss": 6.258,
      "step": 1000
    },
    {
      "epoch": 1.26,
      "learning_rate": 3e-05,
      "learning_rate_embeddings": 3e-05,
      "loss": 5.5397,
      "step": 1500
    },
    {
      "epoch": 1.68,
      "learning_rate": 4e-05,
      "learning_rate_embeddings": 4e-05,
      "loss": 4.9715,
      "step": 2000
    },
    {
      "epoch": 2.1,
      "learning_rate": 5e-05,
      "learning_rate_embeddings": 5e-05,
      "loss": 4.5681,
      "step": 2500
    },
    {
      "epoch": 2.52,
      "learning_rate": 6e-05,
      "learning_rate_embeddings": 6e-05,
      "loss": 4.2633,
      "step": 3000
    },
    {
      "epoch": 2.94,
      "learning_rate": 7.000000000000001e-05,
      "learning_rate_embeddings": 7.000000000000001e-05,
      "loss": 4.0337,
      "step": 3500
    },
    {
      "epoch": 3.36,
      "learning_rate": 8e-05,
      "learning_rate_embeddings": 8e-05,
      "loss": 3.8598,
      "step": 4000
    },
    {
      "epoch": 3.78,
      "learning_rate": 8.999999999999999e-05,
      "learning_rate_embeddings": 8.999999999999999e-05,
      "loss": 3.7204,
      "step": 4500
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0001,
      "learning_rate_embeddings": 0.0001,
      "loss": 3.5946,
      "step": 5000
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00011,
      "learning_rate_embeddings": 0.00011,
      "loss": 3.4963,
      "step": 5500
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00012,
      "learning_rate_embeddings": 0.00012,
      "loss": 3.4189,
      "step": 6000
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.00013000000000000002,
      "learning_rate_embeddings": 0.00013000000000000002,
      "loss": 3.3369,
      "step": 6500
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.00014000000000000001,
      "learning_rate_embeddings": 0.00014000000000000001,
      "loss": 3.2837,
      "step": 7000
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.00015,
      "learning_rate_embeddings": 0.00015,
      "loss": 3.2359,
      "step": 7500
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.00016,
      "learning_rate_embeddings": 0.00016,
      "loss": 3.1786,
      "step": 8000
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00017,
      "learning_rate_embeddings": 0.00017,
      "loss": 3.1396,
      "step": 8500
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.00017999999999999998,
      "learning_rate_embeddings": 0.00017999999999999998,
      "loss": 3.0931,
      "step": 9000
    },
    {
      "epoch": 7.98,
      "learning_rate": 0.00019,
      "learning_rate_embeddings": 0.00019,
      "loss": 3.0626,
      "step": 9500
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.0002,
      "learning_rate_embeddings": 0.0002,
      "loss": 3.0226,
      "step": 10000
    },
    {
      "epoch": 8.82,
      "learning_rate": 0.00021,
      "learning_rate_embeddings": 0.00021,
      "loss": 3.0012,
      "step": 10500
    },
    {
      "epoch": 9.24,
      "learning_rate": 0.00022,
      "learning_rate_embeddings": 0.00022,
      "loss": 2.9775,
      "step": 11000
    },
    {
      "epoch": 9.66,
      "learning_rate": 0.00023,
      "learning_rate_embeddings": 0.00023,
      "loss": 2.9286,
      "step": 11500
    },
    {
      "epoch": 10.08,
      "learning_rate": 0.00024,
      "learning_rate_embeddings": 0.00024,
      "loss": 2.918,
      "step": 12000
    },
    {
      "epoch": 10.5,
      "learning_rate": 0.00025,
      "learning_rate_embeddings": 0.00025,
      "loss": 2.8907,
      "step": 12500
    },
    {
      "epoch": 10.5,
      "eval_loss": 2.839508533477783,
      "eval_runtime": 131.8919,
      "eval_samples_per_second": 513.36,
      "eval_steps_per_second": 4.011,
      "step": 12500
    },
    {
      "epoch": 10.92,
      "learning_rate": 0.00026000000000000003,
      "learning_rate_embeddings": 0.00026000000000000003,
      "loss": 2.8764,
      "step": 13000
    },
    {
      "epoch": 11.34,
      "learning_rate": 0.00027,
      "learning_rate_embeddings": 0.00027,
      "loss": 2.8521,
      "step": 13500
    },
    {
      "epoch": 11.76,
      "learning_rate": 0.00028000000000000003,
      "learning_rate_embeddings": 0.00028000000000000003,
      "loss": 2.8284,
      "step": 14000
    },
    {
      "epoch": 12.18,
      "learning_rate": 0.00029,
      "learning_rate_embeddings": 0.00029,
      "loss": 2.8186,
      "step": 14500
    },
    {
      "epoch": 12.6,
      "learning_rate": 0.0003,
      "learning_rate_embeddings": 0.0003,
      "loss": 2.7952,
      "step": 15000
    },
    {
      "epoch": 13.03,
      "learning_rate": 0.00031,
      "learning_rate_embeddings": 0.00031,
      "loss": 2.7799,
      "step": 15500
    },
    {
      "epoch": 13.45,
      "learning_rate": 0.00032,
      "learning_rate_embeddings": 0.00032,
      "loss": 2.7439,
      "step": 16000
    },
    {
      "epoch": 13.87,
      "learning_rate": 0.00033,
      "learning_rate_embeddings": 0.00033,
      "loss": 2.7479,
      "step": 16500
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.00034,
      "learning_rate_embeddings": 0.00034,
      "loss": 2.7336,
      "step": 17000
    },
    {
      "epoch": 14.71,
      "learning_rate": 0.00035,
      "learning_rate_embeddings": 0.00035,
      "loss": 2.7165,
      "step": 17500
    },
    {
      "epoch": 15.13,
      "learning_rate": 0.00035999999999999997,
      "learning_rate_embeddings": 0.00035999999999999997,
      "loss": 2.709,
      "step": 18000
    },
    {
      "epoch": 15.55,
      "learning_rate": 0.00037,
      "learning_rate_embeddings": 0.00037,
      "loss": 2.6872,
      "step": 18500
    },
    {
      "epoch": 15.97,
      "learning_rate": 0.00038,
      "learning_rate_embeddings": 0.00038,
      "loss": 2.6845,
      "step": 19000
    },
    {
      "epoch": 16.39,
      "learning_rate": 0.00039000000000000005,
      "learning_rate_embeddings": 0.00039000000000000005,
      "loss": 2.6605,
      "step": 19500
    },
    {
      "epoch": 16.81,
      "learning_rate": 0.0004,
      "learning_rate_embeddings": 0.0004,
      "loss": 2.6651,
      "step": 20000
    },
    {
      "epoch": 17.23,
      "learning_rate": 0.00041,
      "learning_rate_embeddings": 0.00041,
      "loss": 2.6473,
      "step": 20500
    },
    {
      "epoch": 17.65,
      "learning_rate": 0.00042,
      "learning_rate_embeddings": 0.00042,
      "loss": 2.6304,
      "step": 21000
    },
    {
      "epoch": 18.07,
      "learning_rate": 0.00043,
      "learning_rate_embeddings": 0.00043,
      "loss": 2.6374,
      "step": 21500
    },
    {
      "epoch": 18.49,
      "learning_rate": 0.00044,
      "learning_rate_embeddings": 0.00044,
      "loss": 2.6037,
      "step": 22000
    },
    {
      "epoch": 18.91,
      "learning_rate": 0.00045000000000000004,
      "learning_rate_embeddings": 0.00045000000000000004,
      "loss": 2.6156,
      "step": 22500
    },
    {
      "epoch": 19.33,
      "learning_rate": 0.00046,
      "learning_rate_embeddings": 0.00046,
      "loss": 2.5906,
      "step": 23000
    },
    {
      "epoch": 19.75,
      "learning_rate": 0.00047,
      "learning_rate_embeddings": 0.00047,
      "loss": 2.5834,
      "step": 23500
    },
    {
      "epoch": 20.17,
      "learning_rate": 0.00048,
      "learning_rate_embeddings": 0.00048,
      "loss": 2.5827,
      "step": 24000
    },
    {
      "epoch": 20.59,
      "learning_rate": 0.00049,
      "learning_rate_embeddings": 0.00049,
      "loss": 2.571,
      "step": 24500
    },
    {
      "epoch": 21.01,
      "learning_rate": 0.0005,
      "learning_rate_embeddings": 0.0005,
      "loss": 2.5741,
      "step": 25000
    },
    {
      "epoch": 21.01,
      "eval_loss": 2.566823959350586,
      "eval_runtime": 117.9068,
      "eval_samples_per_second": 574.25,
      "eval_steps_per_second": 4.487,
      "step": 25000
    },
    {
      "epoch": 21.43,
      "learning_rate": 0.0004988888888888889,
      "learning_rate_embeddings": 0.0004988888888888889,
      "loss": 2.5472,
      "step": 25500
    },
    {
      "epoch": 21.85,
      "learning_rate": 0.0004977777777777778,
      "learning_rate_embeddings": 0.0004977777777777778,
      "loss": 2.561,
      "step": 26000
    },
    {
      "epoch": 22.27,
      "learning_rate": 0.0004966666666666666,
      "learning_rate_embeddings": 0.0004966666666666666,
      "loss": 2.5334,
      "step": 26500
    },
    {
      "epoch": 22.69,
      "learning_rate": 0.0004955555555555556,
      "learning_rate_embeddings": 0.0004955555555555556,
      "loss": 2.532,
      "step": 27000
    },
    {
      "epoch": 23.11,
      "learning_rate": 0.0004944444444444445,
      "learning_rate_embeddings": 0.0004944444444444445,
      "loss": 2.5293,
      "step": 27500
    },
    {
      "epoch": 23.53,
      "learning_rate": 0.0004933333333333334,
      "learning_rate_embeddings": 0.0004933333333333334,
      "loss": 2.5181,
      "step": 28000
    },
    {
      "epoch": 23.95,
      "learning_rate": 0.0004922222222222222,
      "learning_rate_embeddings": 0.0004922222222222222,
      "loss": 2.5275,
      "step": 28500
    },
    {
      "epoch": 24.37,
      "learning_rate": 0.0004911111111111111,
      "learning_rate_embeddings": 0.0004911111111111111,
      "loss": 2.5083,
      "step": 29000
    },
    {
      "epoch": 24.79,
      "learning_rate": 0.00049,
      "learning_rate_embeddings": 0.00049,
      "loss": 2.5055,
      "step": 29500
    },
    {
      "epoch": 25.21,
      "learning_rate": 0.0004888888888888889,
      "learning_rate_embeddings": 0.0004888888888888889,
      "loss": 2.4865,
      "step": 30000
    },
    {
      "epoch": 25.63,
      "learning_rate": 0.0004877777777777778,
      "learning_rate_embeddings": 0.0004877777777777778,
      "loss": 2.4861,
      "step": 30500
    },
    {
      "epoch": 26.05,
      "learning_rate": 0.0004866666666666667,
      "learning_rate_embeddings": 0.0004866666666666667,
      "loss": 2.499,
      "step": 31000
    },
    {
      "epoch": 26.47,
      "learning_rate": 0.0004855555555555556,
      "learning_rate_embeddings": 0.0004855555555555556,
      "loss": 2.4629,
      "step": 31500
    },
    {
      "epoch": 26.89,
      "learning_rate": 0.00048444444444444446,
      "learning_rate_embeddings": 0.00048444444444444446,
      "loss": 2.4815,
      "step": 32000
    },
    {
      "epoch": 27.31,
      "learning_rate": 0.00048333333333333334,
      "learning_rate_embeddings": 0.00048333333333333334,
      "loss": 2.4599,
      "step": 32500
    },
    {
      "epoch": 27.73,
      "learning_rate": 0.0004822222222222222,
      "learning_rate_embeddings": 0.0004822222222222222,
      "loss": 2.4602,
      "step": 33000
    },
    {
      "epoch": 28.15,
      "learning_rate": 0.0004811111111111111,
      "learning_rate_embeddings": 0.0004811111111111111,
      "loss": 2.469,
      "step": 33500
    },
    {
      "epoch": 28.57,
      "learning_rate": 0.00048,
      "learning_rate_embeddings": 0.00048,
      "loss": 2.458,
      "step": 34000
    },
    {
      "epoch": 28.99,
      "learning_rate": 0.0004788888888888889,
      "learning_rate_embeddings": 0.0004788888888888889,
      "loss": 2.4497,
      "step": 34500
    },
    {
      "epoch": 29.41,
      "learning_rate": 0.0004777777777777778,
      "learning_rate_embeddings": 0.0004777777777777778,
      "loss": 2.4361,
      "step": 35000
    },
    {
      "epoch": 29.83,
      "learning_rate": 0.0004766666666666667,
      "learning_rate_embeddings": 0.0004766666666666667,
      "loss": 2.4574,
      "step": 35500
    },
    {
      "epoch": 30.25,
      "learning_rate": 0.00047555555555555556,
      "learning_rate_embeddings": 0.00047555555555555556,
      "loss": 2.4342,
      "step": 36000
    },
    {
      "epoch": 30.67,
      "learning_rate": 0.00047444444444444444,
      "learning_rate_embeddings": 0.00047444444444444444,
      "loss": 2.4379,
      "step": 36500
    },
    {
      "epoch": 31.09,
      "learning_rate": 0.00047333333333333336,
      "learning_rate_embeddings": 0.00047333333333333336,
      "loss": 2.4303,
      "step": 37000
    },
    {
      "epoch": 31.51,
      "learning_rate": 0.00047222222222222224,
      "learning_rate_embeddings": 0.00047222222222222224,
      "loss": 2.4203,
      "step": 37500
    },
    {
      "epoch": 31.51,
      "eval_loss": 2.4701642990112305,
      "eval_runtime": 117.9305,
      "eval_samples_per_second": 574.135,
      "eval_steps_per_second": 4.486,
      "step": 37500
    },
    {
      "epoch": 31.93,
      "learning_rate": 0.0004711111111111111,
      "learning_rate_embeddings": 0.0004711111111111111,
      "loss": 2.4321,
      "step": 38000
    },
    {
      "epoch": 32.35,
      "learning_rate": 0.00047,
      "learning_rate_embeddings": 0.00047,
      "loss": 2.4119,
      "step": 38500
    },
    {
      "epoch": 32.77,
      "learning_rate": 0.0004688888888888889,
      "learning_rate_embeddings": 0.0004688888888888889,
      "loss": 2.4266,
      "step": 39000
    },
    {
      "epoch": 33.19,
      "learning_rate": 0.0004677777777777778,
      "learning_rate_embeddings": 0.0004677777777777778,
      "loss": 2.419,
      "step": 39500
    },
    {
      "epoch": 33.61,
      "learning_rate": 0.00046666666666666666,
      "learning_rate_embeddings": 0.00046666666666666666,
      "loss": 2.4148,
      "step": 40000
    },
    {
      "epoch": 34.03,
      "learning_rate": 0.0004655555555555556,
      "learning_rate_embeddings": 0.0004655555555555556,
      "loss": 2.4137,
      "step": 40500
    },
    {
      "epoch": 34.45,
      "learning_rate": 0.00046444444444444446,
      "learning_rate_embeddings": 0.00046444444444444446,
      "loss": 2.4042,
      "step": 41000
    },
    {
      "epoch": 34.87,
      "learning_rate": 0.00046333333333333334,
      "learning_rate_embeddings": 0.00046333333333333334,
      "loss": 2.4017,
      "step": 41500
    },
    {
      "epoch": 35.29,
      "learning_rate": 0.0004622222222222222,
      "learning_rate_embeddings": 0.0004622222222222222,
      "loss": 2.3965,
      "step": 42000
    },
    {
      "epoch": 35.71,
      "learning_rate": 0.00046111111111111114,
      "learning_rate_embeddings": 0.00046111111111111114,
      "loss": 2.3876,
      "step": 42500
    },
    {
      "epoch": 36.13,
      "learning_rate": 0.00046,
      "learning_rate_embeddings": 0.00046,
      "loss": 2.3936,
      "step": 43000
    },
    {
      "epoch": 36.55,
      "learning_rate": 0.0004588888888888889,
      "learning_rate_embeddings": 0.0004588888888888889,
      "loss": 2.3879,
      "step": 43500
    },
    {
      "epoch": 36.97,
      "learning_rate": 0.0004577777777777778,
      "learning_rate_embeddings": 0.0004577777777777778,
      "loss": 2.3967,
      "step": 44000
    },
    {
      "epoch": 37.39,
      "learning_rate": 0.0004566666666666667,
      "learning_rate_embeddings": 0.0004566666666666667,
      "loss": 2.374,
      "step": 44500
    },
    {
      "epoch": 37.81,
      "learning_rate": 0.00045555555555555556,
      "learning_rate_embeddings": 0.00045555555555555556,
      "loss": 2.3918,
      "step": 45000
    },
    {
      "epoch": 38.24,
      "learning_rate": 0.00045444444444444444,
      "learning_rate_embeddings": 0.00045444444444444444,
      "loss": 2.3791,
      "step": 45500
    },
    {
      "epoch": 38.66,
      "learning_rate": 0.0004533333333333333,
      "learning_rate_embeddings": 0.0004533333333333333,
      "loss": 2.3799,
      "step": 46000
    },
    {
      "epoch": 39.08,
      "learning_rate": 0.00045222222222222224,
      "learning_rate_embeddings": 0.00045222222222222224,
      "loss": 2.3938,
      "step": 46500
    },
    {
      "epoch": 39.5,
      "learning_rate": 0.0004511111111111111,
      "learning_rate_embeddings": 0.0004511111111111111,
      "loss": 2.3739,
      "step": 47000
    },
    {
      "epoch": 39.92,
      "learning_rate": 0.00045000000000000004,
      "learning_rate_embeddings": 0.00045000000000000004,
      "loss": 2.3757,
      "step": 47500
    },
    {
      "epoch": 40.34,
      "learning_rate": 0.0004488888888888889,
      "learning_rate_embeddings": 0.0004488888888888889,
      "loss": 2.3656,
      "step": 48000
    },
    {
      "epoch": 40.76,
      "learning_rate": 0.0004477777777777778,
      "learning_rate_embeddings": 0.0004477777777777778,
      "loss": 2.3712,
      "step": 48500
    },
    {
      "epoch": 41.18,
      "learning_rate": 0.00044666666666666666,
      "learning_rate_embeddings": 0.00044666666666666666,
      "loss": 2.368,
      "step": 49000
    },
    {
      "epoch": 41.6,
      "learning_rate": 0.00044555555555555554,
      "learning_rate_embeddings": 0.00044555555555555554,
      "loss": 2.3585,
      "step": 49500
    },
    {
      "epoch": 42.02,
      "learning_rate": 0.0004444444444444444,
      "learning_rate_embeddings": 0.0004444444444444444,
      "loss": 2.3721,
      "step": 50000
    },
    {
      "epoch": 42.02,
      "eval_loss": 2.4272959232330322,
      "eval_runtime": 118.2532,
      "eval_samples_per_second": 572.568,
      "eval_steps_per_second": 4.473,
      "step": 50000
    },
    {
      "epoch": 42.44,
      "learning_rate": 0.00044333333333333334,
      "learning_rate_embeddings": 0.00044333333333333334,
      "loss": 2.3561,
      "step": 50500
    },
    {
      "epoch": 42.86,
      "learning_rate": 0.00044222222222222227,
      "learning_rate_embeddings": 0.00044222222222222227,
      "loss": 2.3623,
      "step": 51000
    },
    {
      "epoch": 43.28,
      "learning_rate": 0.00044111111111111114,
      "learning_rate_embeddings": 0.00044111111111111114,
      "loss": 2.3465,
      "step": 51500
    },
    {
      "epoch": 43.7,
      "learning_rate": 0.00044,
      "learning_rate_embeddings": 0.00044,
      "loss": 2.365,
      "step": 52000
    },
    {
      "epoch": 44.12,
      "learning_rate": 0.0004388888888888889,
      "learning_rate_embeddings": 0.0004388888888888889,
      "loss": 2.3568,
      "step": 52500
    },
    {
      "epoch": 44.54,
      "learning_rate": 0.00043777777777777776,
      "learning_rate_embeddings": 0.00043777777777777776,
      "loss": 2.3502,
      "step": 53000
    },
    {
      "epoch": 44.96,
      "learning_rate": 0.00043666666666666664,
      "learning_rate_embeddings": 0.00043666666666666664,
      "loss": 2.3521,
      "step": 53500
    },
    {
      "epoch": 45.38,
      "learning_rate": 0.0004355555555555555,
      "learning_rate_embeddings": 0.0004355555555555555,
      "loss": 2.3435,
      "step": 54000
    },
    {
      "epoch": 45.8,
      "learning_rate": 0.0004344444444444445,
      "learning_rate_embeddings": 0.0004344444444444445,
      "loss": 2.345,
      "step": 54500
    },
    {
      "epoch": 46.22,
      "learning_rate": 0.00043333333333333337,
      "learning_rate_embeddings": 0.00043333333333333337,
      "loss": 2.3477,
      "step": 55000
    },
    {
      "epoch": 46.64,
      "learning_rate": 0.00043222222222222224,
      "learning_rate_embeddings": 0.00043222222222222224,
      "loss": 2.336,
      "step": 55500
    },
    {
      "epoch": 47.06,
      "learning_rate": 0.0004311111111111111,
      "learning_rate_embeddings": 0.0004311111111111111,
      "loss": 2.3475,
      "step": 56000
    },
    {
      "epoch": 47.48,
      "learning_rate": 0.00043,
      "learning_rate_embeddings": 0.00043,
      "loss": 2.3292,
      "step": 56500
    },
    {
      "epoch": 47.9,
      "learning_rate": 0.00042888888888888886,
      "learning_rate_embeddings": 0.00042888888888888886,
      "loss": 2.3491,
      "step": 57000
    },
    {
      "epoch": 48.32,
      "learning_rate": 0.0004277777777777778,
      "learning_rate_embeddings": 0.0004277777777777778,
      "loss": 2.341,
      "step": 57500
    },
    {
      "epoch": 48.74,
      "learning_rate": 0.0004266666666666667,
      "learning_rate_embeddings": 0.0004266666666666667,
      "loss": 2.3308,
      "step": 58000
    },
    {
      "epoch": 49.16,
      "learning_rate": 0.0004255555555555556,
      "learning_rate_embeddings": 0.0004255555555555556,
      "loss": 2.3379,
      "step": 58500
    },
    {
      "epoch": 49.58,
      "learning_rate": 0.00042444444444444447,
      "learning_rate_embeddings": 0.00042444444444444447,
      "loss": 2.3315,
      "step": 59000
    },
    {
      "epoch": 50.0,
      "learning_rate": 0.00042333333333333334,
      "learning_rate_embeddings": 0.00042333333333333334,
      "loss": 2.3408,
      "step": 59500
    },
    {
      "epoch": 50.42,
      "learning_rate": 0.0004222222222222222,
      "learning_rate_embeddings": 0.0004222222222222222,
      "loss": 2.3248,
      "step": 60000
    },
    {
      "epoch": 50.84,
      "learning_rate": 0.0004211111111111111,
      "learning_rate_embeddings": 0.0004211111111111111,
      "loss": 2.3307,
      "step": 60500
    },
    {
      "epoch": 51.26,
      "learning_rate": 0.00042,
      "learning_rate_embeddings": 0.00042,
      "loss": 2.3275,
      "step": 61000
    },
    {
      "epoch": 51.68,
      "learning_rate": 0.0004188888888888889,
      "learning_rate_embeddings": 0.0004188888888888889,
      "loss": 2.3251,
      "step": 61500
    },
    {
      "epoch": 52.1,
      "learning_rate": 0.0004177777777777778,
      "learning_rate_embeddings": 0.0004177777777777778,
      "loss": 2.3249,
      "step": 62000
    },
    {
      "epoch": 52.52,
      "learning_rate": 0.0004166666666666667,
      "learning_rate_embeddings": 0.0004166666666666667,
      "loss": 2.3142,
      "step": 62500
    },
    {
      "epoch": 52.52,
      "eval_loss": 2.400498867034912,
      "eval_runtime": 117.9974,
      "eval_samples_per_second": 573.809,
      "eval_steps_per_second": 4.483,
      "step": 62500
    },
    {
      "epoch": 52.94,
      "learning_rate": 0.00041555555555555557,
      "learning_rate_embeddings": 0.00041555555555555557,
      "loss": 2.3245,
      "step": 63000
    },
    {
      "epoch": 53.36,
      "learning_rate": 0.00041444444444444444,
      "learning_rate_embeddings": 0.00041444444444444444,
      "loss": 2.3147,
      "step": 63500
    },
    {
      "epoch": 53.78,
      "learning_rate": 0.0004133333333333333,
      "learning_rate_embeddings": 0.0004133333333333333,
      "loss": 2.3264,
      "step": 64000
    },
    {
      "epoch": 54.2,
      "learning_rate": 0.00041222222222222224,
      "learning_rate_embeddings": 0.00041222222222222224,
      "loss": 2.3162,
      "step": 64500
    },
    {
      "epoch": 54.62,
      "learning_rate": 0.0004111111111111111,
      "learning_rate_embeddings": 0.0004111111111111111,
      "loss": 2.3142,
      "step": 65000
    },
    {
      "epoch": 55.04,
      "learning_rate": 0.00041,
      "learning_rate_embeddings": 0.00041,
      "loss": 2.3228,
      "step": 65500
    },
    {
      "epoch": 55.46,
      "learning_rate": 0.0004088888888888889,
      "learning_rate_embeddings": 0.0004088888888888889,
      "loss": 2.2975,
      "step": 66000
    },
    {
      "epoch": 55.88,
      "learning_rate": 0.0004077777777777778,
      "learning_rate_embeddings": 0.0004077777777777778,
      "loss": 2.3202,
      "step": 66500
    },
    {
      "epoch": 56.3,
      "learning_rate": 0.00040666666666666667,
      "learning_rate_embeddings": 0.00040666666666666667,
      "loss": 2.3113,
      "step": 67000
    },
    {
      "epoch": 56.72,
      "learning_rate": 0.00040555555555555554,
      "learning_rate_embeddings": 0.00040555555555555554,
      "loss": 2.3096,
      "step": 67500
    },
    {
      "epoch": 57.14,
      "learning_rate": 0.00040444444444444447,
      "learning_rate_embeddings": 0.00040444444444444447,
      "loss": 2.3102,
      "step": 68000
    },
    {
      "epoch": 57.56,
      "learning_rate": 0.00040333333333333334,
      "learning_rate_embeddings": 0.00040333333333333334,
      "loss": 2.2945,
      "step": 68500
    },
    {
      "epoch": 57.98,
      "learning_rate": 0.0004022222222222222,
      "learning_rate_embeddings": 0.0004022222222222222,
      "loss": 2.3174,
      "step": 69000
    },
    {
      "epoch": 58.4,
      "learning_rate": 0.0004011111111111111,
      "learning_rate_embeddings": 0.0004011111111111111,
      "loss": 2.2979,
      "step": 69500
    },
    {
      "epoch": 58.82,
      "learning_rate": 0.0004,
      "learning_rate_embeddings": 0.0004,
      "loss": 2.3039,
      "step": 70000
    },
    {
      "epoch": 59.24,
      "learning_rate": 0.0003988888888888889,
      "learning_rate_embeddings": 0.0003988888888888889,
      "loss": 2.3082,
      "step": 70500
    },
    {
      "epoch": 59.66,
      "learning_rate": 0.00039777777777777777,
      "learning_rate_embeddings": 0.00039777777777777777,
      "loss": 2.3063,
      "step": 71000
    },
    {
      "epoch": 60.08,
      "learning_rate": 0.0003966666666666667,
      "learning_rate_embeddings": 0.0003966666666666667,
      "loss": 2.3047,
      "step": 71500
    },
    {
      "epoch": 60.5,
      "learning_rate": 0.00039555555555555557,
      "learning_rate_embeddings": 0.00039555555555555557,
      "loss": 2.2869,
      "step": 72000
    },
    {
      "epoch": 60.92,
      "learning_rate": 0.00039444444444444444,
      "learning_rate_embeddings": 0.00039444444444444444,
      "loss": 2.3031,
      "step": 72500
    },
    {
      "epoch": 61.34,
      "learning_rate": 0.0003933333333333333,
      "learning_rate_embeddings": 0.0003933333333333333,
      "loss": 2.2872,
      "step": 73000
    },
    {
      "epoch": 61.76,
      "learning_rate": 0.00039222222222222225,
      "learning_rate_embeddings": 0.00039222222222222225,
      "loss": 2.2996,
      "step": 73500
    },
    {
      "epoch": 62.18,
      "learning_rate": 0.0003911111111111111,
      "learning_rate_embeddings": 0.0003911111111111111,
      "loss": 2.2943,
      "step": 74000
    },
    {
      "epoch": 62.6,
      "learning_rate": 0.00039000000000000005,
      "learning_rate_embeddings": 0.00039000000000000005,
      "loss": 2.2937,
      "step": 74500
    },
    {
      "epoch": 63.03,
      "learning_rate": 0.0003888888888888889,
      "learning_rate_embeddings": 0.0003888888888888889,
      "loss": 2.3,
      "step": 75000
    },
    {
      "epoch": 63.03,
      "eval_loss": 2.39066219329834,
      "eval_runtime": 117.9428,
      "eval_samples_per_second": 574.075,
      "eval_steps_per_second": 4.485,
      "step": 75000
    },
    {
      "epoch": 63.45,
      "learning_rate": 0.0003877777777777778,
      "learning_rate_embeddings": 0.0003877777777777778,
      "loss": 2.2961,
      "step": 75500
    },
    {
      "epoch": 63.87,
      "learning_rate": 0.00038666666666666667,
      "learning_rate_embeddings": 0.00038666666666666667,
      "loss": 2.2994,
      "step": 76000
    },
    {
      "epoch": 64.29,
      "learning_rate": 0.00038555555555555554,
      "learning_rate_embeddings": 0.00038555555555555554,
      "loss": 2.2929,
      "step": 76500
    },
    {
      "epoch": 64.71,
      "learning_rate": 0.0003844444444444444,
      "learning_rate_embeddings": 0.0003844444444444444,
      "loss": 2.2994,
      "step": 77000
    },
    {
      "epoch": 65.13,
      "learning_rate": 0.00038333333333333334,
      "learning_rate_embeddings": 0.00038333333333333334,
      "loss": 2.3068,
      "step": 77500
    },
    {
      "epoch": 65.55,
      "learning_rate": 0.0003822222222222223,
      "learning_rate_embeddings": 0.0003822222222222223,
      "loss": 2.2818,
      "step": 78000
    },
    {
      "epoch": 65.97,
      "learning_rate": 0.00038111111111111115,
      "learning_rate_embeddings": 0.00038111111111111115,
      "loss": 2.2925,
      "step": 78500
    },
    {
      "epoch": 66.39,
      "learning_rate": 0.00038,
      "learning_rate_embeddings": 0.00038,
      "loss": 2.2828,
      "step": 79000
    },
    {
      "epoch": 66.81,
      "learning_rate": 0.0003788888888888889,
      "learning_rate_embeddings": 0.0003788888888888889,
      "loss": 2.298,
      "step": 79500
    },
    {
      "epoch": 67.23,
      "learning_rate": 0.00037777777777777777,
      "learning_rate_embeddings": 0.00037777777777777777,
      "loss": 2.2866,
      "step": 80000
    },
    {
      "epoch": 67.65,
      "learning_rate": 0.00037666666666666664,
      "learning_rate_embeddings": 0.00037666666666666664,
      "loss": 2.2917,
      "step": 80500
    },
    {
      "epoch": 68.07,
      "learning_rate": 0.0003755555555555555,
      "learning_rate_embeddings": 0.0003755555555555555,
      "loss": 2.2881,
      "step": 81000
    },
    {
      "epoch": 68.49,
      "learning_rate": 0.0003744444444444445,
      "learning_rate_embeddings": 0.0003744444444444445,
      "loss": 2.2837,
      "step": 81500
    },
    {
      "epoch": 68.91,
      "learning_rate": 0.0003733333333333334,
      "learning_rate_embeddings": 0.0003733333333333334,
      "loss": 2.2836,
      "step": 82000
    },
    {
      "epoch": 69.33,
      "learning_rate": 0.00037222222222222225,
      "learning_rate_embeddings": 0.00037222222222222225,
      "loss": 2.2715,
      "step": 82500
    },
    {
      "epoch": 69.75,
      "learning_rate": 0.0003711111111111111,
      "learning_rate_embeddings": 0.0003711111111111111,
      "loss": 2.29,
      "step": 83000
    },
    {
      "epoch": 70.17,
      "learning_rate": 0.00037,
      "learning_rate_embeddings": 0.00037,
      "loss": 2.276,
      "step": 83500
    },
    {
      "epoch": 70.59,
      "learning_rate": 0.00036888888888888887,
      "learning_rate_embeddings": 0.00036888888888888887,
      "loss": 2.2796,
      "step": 84000
    },
    {
      "epoch": 71.01,
      "learning_rate": 0.00036777777777777774,
      "learning_rate_embeddings": 0.00036777777777777774,
      "loss": 2.2864,
      "step": 84500
    },
    {
      "epoch": 71.43,
      "learning_rate": 0.00036666666666666667,
      "learning_rate_embeddings": 0.00036666666666666667,
      "loss": 2.2673,
      "step": 85000
    },
    {
      "epoch": 71.85,
      "learning_rate": 0.0003655555555555556,
      "learning_rate_embeddings": 0.0003655555555555556,
      "loss": 2.2769,
      "step": 85500
    },
    {
      "epoch": 72.27,
      "learning_rate": 0.00036444444444444447,
      "learning_rate_embeddings": 0.00036444444444444447,
      "loss": 2.2738,
      "step": 86000
    },
    {
      "epoch": 72.69,
      "learning_rate": 0.00036333333333333335,
      "learning_rate_embeddings": 0.00036333333333333335,
      "loss": 2.273,
      "step": 86500
    },
    {
      "epoch": 73.11,
      "learning_rate": 0.0003622222222222222,
      "learning_rate_embeddings": 0.0003622222222222222,
      "loss": 2.2796,
      "step": 87000
    },
    {
      "epoch": 73.53,
      "learning_rate": 0.0003611111111111111,
      "learning_rate_embeddings": 0.0003611111111111111,
      "loss": 2.2718,
      "step": 87500
    },
    {
      "epoch": 73.53,
      "eval_loss": 2.375969409942627,
      "eval_runtime": 117.8648,
      "eval_samples_per_second": 574.455,
      "eval_steps_per_second": 4.488,
      "step": 87500
    },
    {
      "epoch": 73.95,
      "learning_rate": 0.00035999999999999997,
      "learning_rate_embeddings": 0.00035999999999999997,
      "loss": 2.2792,
      "step": 88000
    },
    {
      "epoch": 74.37,
      "learning_rate": 0.0003588888888888889,
      "learning_rate_embeddings": 0.0003588888888888889,
      "loss": 2.2674,
      "step": 88500
    },
    {
      "epoch": 74.79,
      "learning_rate": 0.00035777777777777777,
      "learning_rate_embeddings": 0.00035777777777777777,
      "loss": 2.2713,
      "step": 89000
    },
    {
      "epoch": 75.21,
      "learning_rate": 0.0003566666666666667,
      "learning_rate_embeddings": 0.0003566666666666667,
      "loss": 2.2771,
      "step": 89500
    },
    {
      "epoch": 75.63,
      "learning_rate": 0.00035555555555555557,
      "learning_rate_embeddings": 0.00035555555555555557,
      "loss": 2.2696,
      "step": 90000
    },
    {
      "epoch": 76.05,
      "learning_rate": 0.00035444444444444445,
      "learning_rate_embeddings": 0.00035444444444444445,
      "loss": 2.2767,
      "step": 90500
    },
    {
      "epoch": 76.47,
      "learning_rate": 0.0003533333333333333,
      "learning_rate_embeddings": 0.0003533333333333333,
      "loss": 2.2606,
      "step": 91000
    },
    {
      "epoch": 76.89,
      "learning_rate": 0.00035222222222222225,
      "learning_rate_embeddings": 0.00035222222222222225,
      "loss": 2.2622,
      "step": 91500
    },
    {
      "epoch": 77.31,
      "learning_rate": 0.0003511111111111111,
      "learning_rate_embeddings": 0.0003511111111111111,
      "loss": 2.2661,
      "step": 92000
    },
    {
      "epoch": 77.73,
      "learning_rate": 0.00035,
      "learning_rate_embeddings": 0.00035,
      "loss": 2.2712,
      "step": 92500
    },
    {
      "epoch": 78.15,
      "learning_rate": 0.0003488888888888889,
      "learning_rate_embeddings": 0.0003488888888888889,
      "loss": 2.2667,
      "step": 93000
    },
    {
      "epoch": 78.57,
      "learning_rate": 0.0003477777777777778,
      "learning_rate_embeddings": 0.0003477777777777778,
      "loss": 2.2621,
      "step": 93500
    },
    {
      "epoch": 78.99,
      "learning_rate": 0.00034666666666666667,
      "learning_rate_embeddings": 0.00034666666666666667,
      "loss": 2.2717,
      "step": 94000
    },
    {
      "epoch": 79.41,
      "learning_rate": 0.00034555555555555555,
      "learning_rate_embeddings": 0.00034555555555555555,
      "loss": 2.2536,
      "step": 94500
    },
    {
      "epoch": 79.83,
      "learning_rate": 0.0003444444444444445,
      "learning_rate_embeddings": 0.0003444444444444445,
      "loss": 2.2705,
      "step": 95000
    },
    {
      "epoch": 80.25,
      "learning_rate": 0.00034333333333333335,
      "learning_rate_embeddings": 0.00034333333333333335,
      "loss": 2.2659,
      "step": 95500
    },
    {
      "epoch": 80.67,
      "learning_rate": 0.0003422222222222222,
      "learning_rate_embeddings": 0.0003422222222222222,
      "loss": 2.2648,
      "step": 96000
    },
    {
      "epoch": 81.09,
      "learning_rate": 0.0003411111111111111,
      "learning_rate_embeddings": 0.0003411111111111111,
      "loss": 2.2671,
      "step": 96500
    },
    {
      "epoch": 81.51,
      "learning_rate": 0.00034,
      "learning_rate_embeddings": 0.00034,
      "loss": 2.2566,
      "step": 97000
    },
    {
      "epoch": 81.93,
      "learning_rate": 0.0003388888888888889,
      "learning_rate_embeddings": 0.0003388888888888889,
      "loss": 2.2726,
      "step": 97500
    },
    {
      "epoch": 82.35,
      "learning_rate": 0.00033777777777777777,
      "learning_rate_embeddings": 0.00033777777777777777,
      "loss": 2.2503,
      "step": 98000
    },
    {
      "epoch": 82.77,
      "learning_rate": 0.0003366666666666667,
      "learning_rate_embeddings": 0.0003366666666666667,
      "loss": 2.2573,
      "step": 98500
    },
    {
      "epoch": 83.19,
      "learning_rate": 0.0003355555555555556,
      "learning_rate_embeddings": 0.0003355555555555556,
      "loss": 2.2644,
      "step": 99000
    },
    {
      "epoch": 83.61,
      "learning_rate": 0.00033444444444444445,
      "learning_rate_embeddings": 0.00033444444444444445,
      "loss": 2.2525,
      "step": 99500
    },
    {
      "epoch": 84.03,
      "learning_rate": 0.0003333333333333333,
      "learning_rate_embeddings": 0.0003333333333333333,
      "loss": 2.2627,
      "step": 100000
    },
    {
      "epoch": 84.03,
      "eval_loss": 2.3599398136138916,
      "eval_runtime": 117.9754,
      "eval_samples_per_second": 573.916,
      "eval_steps_per_second": 4.484,
      "step": 100000
    },
    {
      "epoch": 84.45,
      "learning_rate": 0.0003322222222222222,
      "learning_rate_embeddings": 0.0003322222222222222,
      "loss": 2.2558,
      "step": 100500
    },
    {
      "epoch": 84.87,
      "learning_rate": 0.0003311111111111111,
      "learning_rate_embeddings": 0.0003311111111111111,
      "loss": 2.2678,
      "step": 101000
    },
    {
      "epoch": 85.29,
      "learning_rate": 0.00033,
      "learning_rate_embeddings": 0.00033,
      "loss": 2.2504,
      "step": 101500
    },
    {
      "epoch": 85.71,
      "learning_rate": 0.0003288888888888889,
      "learning_rate_embeddings": 0.0003288888888888889,
      "loss": 2.2486,
      "step": 102000
    },
    {
      "epoch": 86.13,
      "learning_rate": 0.0003277777777777778,
      "learning_rate_embeddings": 0.0003277777777777778,
      "loss": 2.2584,
      "step": 102500
    },
    {
      "epoch": 86.55,
      "learning_rate": 0.0003266666666666667,
      "learning_rate_embeddings": 0.0003266666666666667,
      "loss": 2.2436,
      "step": 103000
    },
    {
      "epoch": 86.97,
      "learning_rate": 0.00032555555555555555,
      "learning_rate_embeddings": 0.00032555555555555555,
      "loss": 2.2623,
      "step": 103500
    },
    {
      "epoch": 87.39,
      "learning_rate": 0.0003244444444444444,
      "learning_rate_embeddings": 0.0003244444444444444,
      "loss": 2.2446,
      "step": 104000
    },
    {
      "epoch": 87.81,
      "learning_rate": 0.0003233333333333333,
      "learning_rate_embeddings": 0.0003233333333333333,
      "loss": 2.2468,
      "step": 104500
    },
    {
      "epoch": 88.24,
      "learning_rate": 0.0003222222222222222,
      "learning_rate_embeddings": 0.0003222222222222222,
      "loss": 2.2445,
      "step": 105000
    },
    {
      "epoch": 88.66,
      "learning_rate": 0.00032111111111111115,
      "learning_rate_embeddings": 0.00032111111111111115,
      "loss": 2.254,
      "step": 105500
    },
    {
      "epoch": 89.08,
      "learning_rate": 0.00032,
      "learning_rate_embeddings": 0.00032,
      "loss": 2.264,
      "step": 106000
    },
    {
      "epoch": 89.5,
      "learning_rate": 0.0003188888888888889,
      "learning_rate_embeddings": 0.0003188888888888889,
      "loss": 2.2492,
      "step": 106500
    },
    {
      "epoch": 89.92,
      "learning_rate": 0.0003177777777777778,
      "learning_rate_embeddings": 0.0003177777777777778,
      "loss": 2.2563,
      "step": 107000
    },
    {
      "epoch": 90.34,
      "learning_rate": 0.00031666666666666665,
      "learning_rate_embeddings": 0.00031666666666666665,
      "loss": 2.2282,
      "step": 107500
    },
    {
      "epoch": 90.76,
      "learning_rate": 0.0003155555555555555,
      "learning_rate_embeddings": 0.0003155555555555555,
      "loss": 2.2429,
      "step": 108000
    },
    {
      "epoch": 91.18,
      "learning_rate": 0.0003144444444444445,
      "learning_rate_embeddings": 0.0003144444444444445,
      "loss": 2.2458,
      "step": 108500
    },
    {
      "epoch": 91.6,
      "learning_rate": 0.0003133333333333334,
      "learning_rate_embeddings": 0.0003133333333333334,
      "loss": 2.2512,
      "step": 109000
    },
    {
      "epoch": 92.02,
      "learning_rate": 0.00031222222222222225,
      "learning_rate_embeddings": 0.00031222222222222225,
      "loss": 2.2461,
      "step": 109500
    },
    {
      "epoch": 92.44,
      "learning_rate": 0.0003111111111111111,
      "learning_rate_embeddings": 0.0003111111111111111,
      "loss": 2.2313,
      "step": 110000
    },
    {
      "epoch": 92.86,
      "learning_rate": 0.00031,
      "learning_rate_embeddings": 0.00031,
      "loss": 2.2521,
      "step": 110500
    },
    {
      "epoch": 93.28,
      "learning_rate": 0.0003088888888888889,
      "learning_rate_embeddings": 0.0003088888888888889,
      "loss": 2.2322,
      "step": 111000
    },
    {
      "epoch": 93.7,
      "learning_rate": 0.00030777777777777775,
      "learning_rate_embeddings": 0.00030777777777777775,
      "loss": 2.2432,
      "step": 111500
    },
    {
      "epoch": 94.12,
      "learning_rate": 0.0003066666666666667,
      "learning_rate_embeddings": 0.0003066666666666667,
      "loss": 2.239,
      "step": 112000
    },
    {
      "epoch": 94.54,
      "learning_rate": 0.0003055555555555556,
      "learning_rate_embeddings": 0.0003055555555555556,
      "loss": 2.2238,
      "step": 112500
    },
    {
      "epoch": 94.54,
      "eval_loss": 2.356623411178589,
      "eval_runtime": 118.007,
      "eval_samples_per_second": 573.763,
      "eval_steps_per_second": 4.483,
      "step": 112500
    },
    {
      "epoch": 94.96,
      "learning_rate": 0.0003044444444444445,
      "learning_rate_embeddings": 0.0003044444444444445,
      "loss": 2.237,
      "step": 113000
    },
    {
      "epoch": 95.38,
      "learning_rate": 0.00030333333333333335,
      "learning_rate_embeddings": 0.00030333333333333335,
      "loss": 2.23,
      "step": 113500
    },
    {
      "epoch": 95.8,
      "learning_rate": 0.0003022222222222222,
      "learning_rate_embeddings": 0.0003022222222222222,
      "loss": 2.2383,
      "step": 114000
    },
    {
      "epoch": 96.22,
      "learning_rate": 0.0003011111111111111,
      "learning_rate_embeddings": 0.0003011111111111111,
      "loss": 2.234,
      "step": 114500
    },
    {
      "epoch": 96.64,
      "learning_rate": 0.0003,
      "learning_rate_embeddings": 0.0003,
      "loss": 2.2285,
      "step": 115000
    },
    {
      "epoch": 97.06,
      "learning_rate": 0.0002988888888888889,
      "learning_rate_embeddings": 0.0002988888888888889,
      "loss": 2.2527,
      "step": 115500
    },
    {
      "epoch": 97.48,
      "learning_rate": 0.0002977777777777778,
      "learning_rate_embeddings": 0.0002977777777777778,
      "loss": 2.2366,
      "step": 116000
    },
    {
      "epoch": 97.9,
      "learning_rate": 0.0002966666666666667,
      "learning_rate_embeddings": 0.0002966666666666667,
      "loss": 2.2437,
      "step": 116500
    },
    {
      "epoch": 98.32,
      "learning_rate": 0.0002955555555555556,
      "learning_rate_embeddings": 0.0002955555555555556,
      "loss": 2.2262,
      "step": 117000
    },
    {
      "epoch": 98.74,
      "learning_rate": 0.00029444444444444445,
      "learning_rate_embeddings": 0.00029444444444444445,
      "loss": 2.235,
      "step": 117500
    },
    {
      "epoch": 99.16,
      "learning_rate": 0.0002933333333333333,
      "learning_rate_embeddings": 0.0002933333333333333,
      "loss": 2.2463,
      "step": 118000
    },
    {
      "epoch": 99.58,
      "learning_rate": 0.0002922222222222222,
      "learning_rate_embeddings": 0.0002922222222222222,
      "loss": 2.2273,
      "step": 118500
    },
    {
      "epoch": 100.0,
      "learning_rate": 0.00029111111111111113,
      "learning_rate_embeddings": 0.00029111111111111113,
      "loss": 2.2438,
      "step": 119000
    },
    {
      "epoch": 100.42,
      "learning_rate": 0.00029,
      "learning_rate_embeddings": 0.00029,
      "loss": 2.2216,
      "step": 119500
    },
    {
      "epoch": 100.84,
      "learning_rate": 0.0002888888888888889,
      "learning_rate_embeddings": 0.0002888888888888889,
      "loss": 2.2296,
      "step": 120000
    },
    {
      "epoch": 101.26,
      "learning_rate": 0.0002877777777777778,
      "learning_rate_embeddings": 0.0002877777777777778,
      "loss": 2.2246,
      "step": 120500
    },
    {
      "epoch": 101.68,
      "learning_rate": 0.0002866666666666667,
      "learning_rate_embeddings": 0.0002866666666666667,
      "loss": 2.2296,
      "step": 121000
    },
    {
      "epoch": 102.1,
      "learning_rate": 0.00028555555555555555,
      "learning_rate_embeddings": 0.00028555555555555555,
      "loss": 2.2296,
      "step": 121500
    },
    {
      "epoch": 102.52,
      "learning_rate": 0.0002844444444444444,
      "learning_rate_embeddings": 0.0002844444444444444,
      "loss": 2.238,
      "step": 122000
    },
    {
      "epoch": 102.94,
      "learning_rate": 0.00028333333333333335,
      "learning_rate_embeddings": 0.00028333333333333335,
      "loss": 2.2346,
      "step": 122500
    },
    {
      "epoch": 103.36,
      "learning_rate": 0.00028222222222222223,
      "learning_rate_embeddings": 0.00028222222222222223,
      "loss": 2.2188,
      "step": 123000
    },
    {
      "epoch": 103.78,
      "learning_rate": 0.0002811111111111111,
      "learning_rate_embeddings": 0.0002811111111111111,
      "loss": 2.2319,
      "step": 123500
    },
    {
      "epoch": 104.2,
      "learning_rate": 0.00028000000000000003,
      "learning_rate_embeddings": 0.00028000000000000003,
      "loss": 2.2312,
      "step": 124000
    },
    {
      "epoch": 104.62,
      "learning_rate": 0.0002788888888888889,
      "learning_rate_embeddings": 0.0002788888888888889,
      "loss": 2.2273,
      "step": 124500
    },
    {
      "epoch": 105.04,
      "learning_rate": 0.0002777777777777778,
      "learning_rate_embeddings": 0.0002777777777777778,
      "loss": 2.2271,
      "step": 125000
    },
    {
      "epoch": 105.04,
      "eval_loss": 2.353121042251587,
      "eval_runtime": 118.053,
      "eval_samples_per_second": 573.539,
      "eval_steps_per_second": 4.481,
      "step": 125000
    },
    {
      "epoch": 105.46,
      "learning_rate": 0.00027666666666666665,
      "learning_rate_embeddings": 0.00027666666666666665,
      "loss": 2.2206,
      "step": 125500
    },
    {
      "epoch": 105.88,
      "learning_rate": 0.0002755555555555556,
      "learning_rate_embeddings": 0.0002755555555555556,
      "loss": 2.2287,
      "step": 126000
    },
    {
      "epoch": 106.3,
      "learning_rate": 0.00027444444444444445,
      "learning_rate_embeddings": 0.00027444444444444445,
      "loss": 2.2179,
      "step": 126500
    },
    {
      "epoch": 106.72,
      "learning_rate": 0.00027333333333333333,
      "learning_rate_embeddings": 0.00027333333333333333,
      "loss": 2.2206,
      "step": 127000
    },
    {
      "epoch": 107.14,
      "learning_rate": 0.0002722222222222222,
      "learning_rate_embeddings": 0.0002722222222222222,
      "loss": 2.2271,
      "step": 127500
    },
    {
      "epoch": 107.56,
      "learning_rate": 0.00027111111111111113,
      "learning_rate_embeddings": 0.00027111111111111113,
      "loss": 2.2219,
      "step": 128000
    },
    {
      "epoch": 107.98,
      "learning_rate": 0.00027,
      "learning_rate_embeddings": 0.00027,
      "loss": 2.2333,
      "step": 128500
    },
    {
      "epoch": 108.4,
      "learning_rate": 0.00026888888888888893,
      "learning_rate_embeddings": 0.00026888888888888893,
      "loss": 2.218,
      "step": 129000
    },
    {
      "epoch": 108.82,
      "learning_rate": 0.0002677777777777778,
      "learning_rate_embeddings": 0.0002677777777777778,
      "loss": 2.2332,
      "step": 129500
    },
    {
      "epoch": 109.24,
      "learning_rate": 0.0002666666666666667,
      "learning_rate_embeddings": 0.0002666666666666667,
      "loss": 2.2199,
      "step": 130000
    },
    {
      "epoch": 109.66,
      "learning_rate": 0.00026555555555555555,
      "learning_rate_embeddings": 0.00026555555555555555,
      "loss": 2.2111,
      "step": 130500
    },
    {
      "epoch": 110.08,
      "learning_rate": 0.00026444444444444443,
      "learning_rate_embeddings": 0.00026444444444444443,
      "loss": 2.2294,
      "step": 131000
    },
    {
      "epoch": 110.5,
      "learning_rate": 0.0002633333333333333,
      "learning_rate_embeddings": 0.0002633333333333333,
      "loss": 2.2118,
      "step": 131500
    },
    {
      "epoch": 110.92,
      "learning_rate": 0.00026222222222222223,
      "learning_rate_embeddings": 0.00026222222222222223,
      "loss": 2.2269,
      "step": 132000
    },
    {
      "epoch": 111.34,
      "learning_rate": 0.00026111111111111116,
      "learning_rate_embeddings": 0.00026111111111111116,
      "loss": 2.2142,
      "step": 132500
    },
    {
      "epoch": 111.76,
      "learning_rate": 0.00026000000000000003,
      "learning_rate_embeddings": 0.00026000000000000003,
      "loss": 2.2195,
      "step": 133000
    },
    {
      "epoch": 112.18,
      "learning_rate": 0.0002588888888888889,
      "learning_rate_embeddings": 0.0002588888888888889,
      "loss": 2.2152,
      "step": 133500
    },
    {
      "epoch": 112.6,
      "learning_rate": 0.0002577777777777778,
      "learning_rate_embeddings": 0.0002577777777777778,
      "loss": 2.2244,
      "step": 134000
    },
    {
      "epoch": 113.03,
      "learning_rate": 0.00025666666666666665,
      "learning_rate_embeddings": 0.00025666666666666665,
      "loss": 2.2308,
      "step": 134500
    },
    {
      "epoch": 113.45,
      "learning_rate": 0.00025555555555555553,
      "learning_rate_embeddings": 0.00025555555555555553,
      "loss": 2.2138,
      "step": 135000
    },
    {
      "epoch": 113.87,
      "learning_rate": 0.0002544444444444444,
      "learning_rate_embeddings": 0.0002544444444444444,
      "loss": 2.2158,
      "step": 135500
    },
    {
      "epoch": 114.29,
      "learning_rate": 0.0002533333333333334,
      "learning_rate_embeddings": 0.0002533333333333334,
      "loss": 2.2147,
      "step": 136000
    },
    {
      "epoch": 114.71,
      "learning_rate": 0.00025222222222222226,
      "learning_rate_embeddings": 0.00025222222222222226,
      "loss": 2.2134,
      "step": 136500
    },
    {
      "epoch": 115.13,
      "learning_rate": 0.00025111111111111113,
      "learning_rate_embeddings": 0.00025111111111111113,
      "loss": 2.2084,
      "step": 137000
    },
    {
      "epoch": 115.55,
      "learning_rate": 0.00025,
      "learning_rate_embeddings": 0.00025,
      "loss": 2.2041,
      "step": 137500
    },
    {
      "epoch": 115.55,
      "eval_loss": 2.3373777866363525,
      "eval_runtime": 117.8501,
      "eval_samples_per_second": 574.527,
      "eval_steps_per_second": 4.489,
      "step": 137500
    },
    {
      "epoch": 115.97,
      "learning_rate": 0.0002488888888888889,
      "learning_rate_embeddings": 0.0002488888888888889,
      "loss": 2.226,
      "step": 138000
    },
    {
      "epoch": 116.39,
      "learning_rate": 0.0002477777777777778,
      "learning_rate_embeddings": 0.0002477777777777778,
      "loss": 2.1967,
      "step": 138500
    },
    {
      "epoch": 116.81,
      "learning_rate": 0.0002466666666666667,
      "learning_rate_embeddings": 0.0002466666666666667,
      "loss": 2.2217,
      "step": 139000
    },
    {
      "epoch": 117.23,
      "learning_rate": 0.00024555555555555556,
      "learning_rate_embeddings": 0.00024555555555555556,
      "loss": 2.2117,
      "step": 139500
    },
    {
      "epoch": 117.65,
      "learning_rate": 0.00024444444444444443,
      "learning_rate_embeddings": 0.00024444444444444443,
      "loss": 2.2164,
      "step": 140000
    },
    {
      "epoch": 118.07,
      "learning_rate": 0.00024333333333333336,
      "learning_rate_embeddings": 0.00024333333333333336,
      "loss": 2.2186,
      "step": 140500
    },
    {
      "epoch": 118.49,
      "learning_rate": 0.00024222222222222223,
      "learning_rate_embeddings": 0.00024222222222222223,
      "loss": 2.1994,
      "step": 141000
    },
    {
      "epoch": 118.91,
      "learning_rate": 0.0002411111111111111,
      "learning_rate_embeddings": 0.0002411111111111111,
      "loss": 2.2184,
      "step": 141500
    },
    {
      "epoch": 119.33,
      "learning_rate": 0.00024,
      "learning_rate_embeddings": 0.00024,
      "loss": 2.2062,
      "step": 142000
    },
    {
      "epoch": 119.75,
      "learning_rate": 0.0002388888888888889,
      "learning_rate_embeddings": 0.0002388888888888889,
      "loss": 2.216,
      "step": 142500
    },
    {
      "epoch": 120.17,
      "learning_rate": 0.00023777777777777778,
      "learning_rate_embeddings": 0.00023777777777777778,
      "loss": 2.21,
      "step": 143000
    },
    {
      "epoch": 120.59,
      "learning_rate": 0.00023666666666666668,
      "learning_rate_embeddings": 0.00023666666666666668,
      "loss": 2.2112,
      "step": 143500
    },
    {
      "epoch": 121.01,
      "learning_rate": 0.00023555555555555556,
      "learning_rate_embeddings": 0.00023555555555555556,
      "loss": 2.2096,
      "step": 144000
    },
    {
      "epoch": 121.43,
      "learning_rate": 0.00023444444444444446,
      "learning_rate_embeddings": 0.00023444444444444446,
      "loss": 2.2044,
      "step": 144500
    },
    {
      "epoch": 121.85,
      "learning_rate": 0.00023333333333333333,
      "learning_rate_embeddings": 0.00023333333333333333,
      "loss": 2.2158,
      "step": 145000
    },
    {
      "epoch": 122.27,
      "learning_rate": 0.00023222222222222223,
      "learning_rate_embeddings": 0.00023222222222222223,
      "loss": 2.2093,
      "step": 145500
    },
    {
      "epoch": 122.69,
      "learning_rate": 0.0002311111111111111,
      "learning_rate_embeddings": 0.0002311111111111111,
      "loss": 2.2058,
      "step": 146000
    },
    {
      "epoch": 123.11,
      "learning_rate": 0.00023,
      "learning_rate_embeddings": 0.00023,
      "loss": 2.2102,
      "step": 146500
    },
    {
      "epoch": 123.53,
      "learning_rate": 0.0002288888888888889,
      "learning_rate_embeddings": 0.0002288888888888889,
      "loss": 2.1978,
      "step": 147000
    },
    {
      "epoch": 123.95,
      "learning_rate": 0.00022777777777777778,
      "learning_rate_embeddings": 0.00022777777777777778,
      "loss": 2.2105,
      "step": 147500
    },
    {
      "epoch": 124.37,
      "learning_rate": 0.00022666666666666666,
      "learning_rate_embeddings": 0.00022666666666666666,
      "loss": 2.1972,
      "step": 148000
    },
    {
      "epoch": 124.79,
      "learning_rate": 0.00022555555555555556,
      "learning_rate_embeddings": 0.00022555555555555556,
      "loss": 2.2071,
      "step": 148500
    },
    {
      "epoch": 125.21,
      "learning_rate": 0.00022444444444444446,
      "learning_rate_embeddings": 0.00022444444444444446,
      "loss": 2.2144,
      "step": 149000
    },
    {
      "epoch": 125.63,
      "learning_rate": 0.00022333333333333333,
      "learning_rate_embeddings": 0.00022333333333333333,
      "loss": 2.2037,
      "step": 149500
    },
    {
      "epoch": 126.05,
      "learning_rate": 0.0002222222222222222,
      "learning_rate_embeddings": 0.0002222222222222222,
      "loss": 2.206,
      "step": 150000
    },
    {
      "epoch": 126.05,
      "eval_loss": 2.3389413356781006,
      "eval_runtime": 117.7332,
      "eval_samples_per_second": 575.097,
      "eval_steps_per_second": 4.493,
      "step": 150000
    },
    {
      "epoch": 126.47,
      "learning_rate": 0.00022111111111111113,
      "learning_rate_embeddings": 0.00022111111111111113,
      "loss": 2.1956,
      "step": 150500
    },
    {
      "epoch": 126.89,
      "learning_rate": 0.00022,
      "learning_rate_embeddings": 0.00022,
      "loss": 2.2087,
      "step": 151000
    },
    {
      "epoch": 127.31,
      "learning_rate": 0.00021888888888888888,
      "learning_rate_embeddings": 0.00021888888888888888,
      "loss": 2.1942,
      "step": 151500
    },
    {
      "epoch": 127.73,
      "learning_rate": 0.00021777777777777776,
      "learning_rate_embeddings": 0.00021777777777777776,
      "loss": 2.206,
      "step": 152000
    },
    {
      "epoch": 128.15,
      "learning_rate": 0.00021666666666666668,
      "learning_rate_embeddings": 0.00021666666666666668,
      "loss": 2.2029,
      "step": 152500
    },
    {
      "epoch": 128.57,
      "learning_rate": 0.00021555555555555556,
      "learning_rate_embeddings": 0.00021555555555555556,
      "loss": 2.1988,
      "step": 153000
    },
    {
      "epoch": 128.99,
      "learning_rate": 0.00021444444444444443,
      "learning_rate_embeddings": 0.00021444444444444443,
      "loss": 2.2121,
      "step": 153500
    },
    {
      "epoch": 129.41,
      "learning_rate": 0.00021333333333333336,
      "learning_rate_embeddings": 0.00021333333333333336,
      "loss": 2.1833,
      "step": 154000
    },
    {
      "epoch": 129.83,
      "learning_rate": 0.00021222222222222223,
      "learning_rate_embeddings": 0.00021222222222222223,
      "loss": 2.2016,
      "step": 154500
    },
    {
      "epoch": 130.25,
      "learning_rate": 0.0002111111111111111,
      "learning_rate_embeddings": 0.0002111111111111111,
      "loss": 2.1974,
      "step": 155000
    },
    {
      "epoch": 130.67,
      "learning_rate": 0.00021,
      "learning_rate_embeddings": 0.00021,
      "loss": 2.1969,
      "step": 155500
    },
    {
      "epoch": 131.09,
      "learning_rate": 0.0002088888888888889,
      "learning_rate_embeddings": 0.0002088888888888889,
      "loss": 2.2003,
      "step": 156000
    },
    {
      "epoch": 131.51,
      "learning_rate": 0.00020777777777777778,
      "learning_rate_embeddings": 0.00020777777777777778,
      "loss": 2.1987,
      "step": 156500
    },
    {
      "epoch": 131.93,
      "learning_rate": 0.00020666666666666666,
      "learning_rate_embeddings": 0.00020666666666666666,
      "loss": 2.2038,
      "step": 157000
    },
    {
      "epoch": 132.35,
      "learning_rate": 0.00020555555555555556,
      "learning_rate_embeddings": 0.00020555555555555556,
      "loss": 2.189,
      "step": 157500
    },
    {
      "epoch": 132.77,
      "learning_rate": 0.00020444444444444446,
      "learning_rate_embeddings": 0.00020444444444444446,
      "loss": 2.2054,
      "step": 158000
    },
    {
      "epoch": 133.19,
      "learning_rate": 0.00020333333333333333,
      "learning_rate_embeddings": 0.00020333333333333333,
      "loss": 2.197,
      "step": 158500
    },
    {
      "epoch": 133.61,
      "learning_rate": 0.00020222222222222223,
      "learning_rate_embeddings": 0.00020222222222222223,
      "loss": 2.1855,
      "step": 159000
    },
    {
      "epoch": 134.03,
      "learning_rate": 0.0002011111111111111,
      "learning_rate_embeddings": 0.0002011111111111111,
      "loss": 2.2069,
      "step": 159500
    },
    {
      "epoch": 134.45,
      "learning_rate": 0.0002,
      "learning_rate_embeddings": 0.0002,
      "loss": 2.1969,
      "step": 160000
    },
    {
      "epoch": 134.87,
      "learning_rate": 0.00019888888888888888,
      "learning_rate_embeddings": 0.00019888888888888888,
      "loss": 2.1952,
      "step": 160500
    },
    {
      "epoch": 135.29,
      "learning_rate": 0.00019777777777777778,
      "learning_rate_embeddings": 0.00019777777777777778,
      "loss": 2.2002,
      "step": 161000
    },
    {
      "epoch": 135.71,
      "learning_rate": 0.00019666666666666666,
      "learning_rate_embeddings": 0.00019666666666666666,
      "loss": 2.1968,
      "step": 161500
    },
    {
      "epoch": 136.13,
      "learning_rate": 0.00019555555555555556,
      "learning_rate_embeddings": 0.00019555555555555556,
      "loss": 2.2008,
      "step": 162000
    },
    {
      "epoch": 136.55,
      "learning_rate": 0.00019444444444444446,
      "learning_rate_embeddings": 0.00019444444444444446,
      "loss": 2.1835,
      "step": 162500
    },
    {
      "epoch": 136.55,
      "eval_loss": 2.3406405448913574,
      "eval_runtime": 118.0375,
      "eval_samples_per_second": 573.614,
      "eval_steps_per_second": 4.482,
      "step": 162500
    },
    {
      "epoch": 136.97,
      "learning_rate": 0.00019333333333333333,
      "learning_rate_embeddings": 0.00019333333333333333,
      "loss": 2.2014,
      "step": 163000
    },
    {
      "epoch": 137.39,
      "learning_rate": 0.0001922222222222222,
      "learning_rate_embeddings": 0.0001922222222222222,
      "loss": 2.1768,
      "step": 163500
    },
    {
      "epoch": 137.81,
      "learning_rate": 0.00019111111111111114,
      "learning_rate_embeddings": 0.00019111111111111114,
      "loss": 2.19,
      "step": 164000
    },
    {
      "epoch": 138.24,
      "learning_rate": 0.00019,
      "learning_rate_embeddings": 0.00019,
      "loss": 2.185,
      "step": 164500
    },
    {
      "epoch": 138.66,
      "learning_rate": 0.00018888888888888888,
      "learning_rate_embeddings": 0.00018888888888888888,
      "loss": 2.1859,
      "step": 165000
    },
    {
      "epoch": 139.08,
      "learning_rate": 0.00018777777777777776,
      "learning_rate_embeddings": 0.00018777777777777776,
      "loss": 2.1926,
      "step": 165500
    },
    {
      "epoch": 139.5,
      "learning_rate": 0.0001866666666666667,
      "learning_rate_embeddings": 0.0001866666666666667,
      "loss": 2.1814,
      "step": 166000
    },
    {
      "epoch": 139.92,
      "learning_rate": 0.00018555555555555556,
      "learning_rate_embeddings": 0.00018555555555555556,
      "loss": 2.199,
      "step": 166500
    },
    {
      "epoch": 140.34,
      "learning_rate": 0.00018444444444444443,
      "learning_rate_embeddings": 0.00018444444444444443,
      "loss": 2.1957,
      "step": 167000
    },
    {
      "epoch": 140.76,
      "learning_rate": 0.00018333333333333334,
      "learning_rate_embeddings": 0.00018333333333333334,
      "loss": 2.1959,
      "step": 167500
    },
    {
      "epoch": 141.18,
      "learning_rate": 0.00018222222222222224,
      "learning_rate_embeddings": 0.00018222222222222224,
      "loss": 2.1904,
      "step": 168000
    },
    {
      "epoch": 141.6,
      "learning_rate": 0.0001811111111111111,
      "learning_rate_embeddings": 0.0001811111111111111,
      "loss": 2.1863,
      "step": 168500
    },
    {
      "epoch": 142.02,
      "learning_rate": 0.00017999999999999998,
      "learning_rate_embeddings": 0.00017999999999999998,
      "loss": 2.1972,
      "step": 169000
    },
    {
      "epoch": 142.44,
      "learning_rate": 0.00017888888888888889,
      "learning_rate_embeddings": 0.00017888888888888889,
      "loss": 2.1745,
      "step": 169500
    },
    {
      "epoch": 142.86,
      "learning_rate": 0.00017777777777777779,
      "learning_rate_embeddings": 0.00017777777777777779,
      "loss": 2.1828,
      "step": 170000
    },
    {
      "epoch": 143.28,
      "learning_rate": 0.00017666666666666666,
      "learning_rate_embeddings": 0.00017666666666666666,
      "loss": 2.1897,
      "step": 170500
    },
    {
      "epoch": 143.7,
      "learning_rate": 0.00017555555555555556,
      "learning_rate_embeddings": 0.00017555555555555556,
      "loss": 2.1803,
      "step": 171000
    },
    {
      "epoch": 144.12,
      "learning_rate": 0.00017444444444444446,
      "learning_rate_embeddings": 0.00017444444444444446,
      "loss": 2.1868,
      "step": 171500
    },
    {
      "epoch": 144.54,
      "learning_rate": 0.00017333333333333334,
      "learning_rate_embeddings": 0.00017333333333333334,
      "loss": 2.1727,
      "step": 172000
    },
    {
      "epoch": 144.96,
      "learning_rate": 0.00017222222222222224,
      "learning_rate_embeddings": 0.00017222222222222224,
      "loss": 2.1928,
      "step": 172500
    },
    {
      "epoch": 145.38,
      "learning_rate": 0.0001711111111111111,
      "learning_rate_embeddings": 0.0001711111111111111,
      "loss": 2.1804,
      "step": 173000
    },
    {
      "epoch": 145.8,
      "learning_rate": 0.00017,
      "learning_rate_embeddings": 0.00017,
      "loss": 2.1848,
      "step": 173500
    },
    {
      "epoch": 146.22,
      "learning_rate": 0.00016888888888888889,
      "learning_rate_embeddings": 0.00016888888888888889,
      "loss": 2.1702,
      "step": 174000
    },
    {
      "epoch": 146.64,
      "learning_rate": 0.0001677777777777778,
      "learning_rate_embeddings": 0.0001677777777777778,
      "loss": 2.178,
      "step": 174500
    },
    {
      "epoch": 147.06,
      "learning_rate": 0.00016666666666666666,
      "learning_rate_embeddings": 0.00016666666666666666,
      "loss": 2.1891,
      "step": 175000
    },
    {
      "epoch": 147.06,
      "eval_loss": 2.336824655532837,
      "eval_runtime": 117.8332,
      "eval_samples_per_second": 574.609,
      "eval_steps_per_second": 4.489,
      "step": 175000
    },
    {
      "epoch": 147.48,
      "learning_rate": 0.00016555555555555556,
      "learning_rate_embeddings": 0.00016555555555555556,
      "loss": 2.1814,
      "step": 175500
    },
    {
      "epoch": 147.9,
      "learning_rate": 0.00016444444444444446,
      "learning_rate_embeddings": 0.00016444444444444446,
      "loss": 2.1889,
      "step": 176000
    },
    {
      "epoch": 148.32,
      "learning_rate": 0.00016333333333333334,
      "learning_rate_embeddings": 0.00016333333333333334,
      "loss": 2.1768,
      "step": 176500
    },
    {
      "epoch": 148.74,
      "learning_rate": 0.0001622222222222222,
      "learning_rate_embeddings": 0.0001622222222222222,
      "loss": 2.1798,
      "step": 177000
    },
    {
      "epoch": 149.16,
      "learning_rate": 0.0001611111111111111,
      "learning_rate_embeddings": 0.0001611111111111111,
      "loss": 2.1849,
      "step": 177500
    },
    {
      "epoch": 149.58,
      "learning_rate": 0.00016,
      "learning_rate_embeddings": 0.00016,
      "loss": 2.1773,
      "step": 178000
    },
    {
      "epoch": 150.0,
      "learning_rate": 0.0001588888888888889,
      "learning_rate_embeddings": 0.0001588888888888889,
      "loss": 2.1832,
      "step": 178500
    },
    {
      "epoch": 150.42,
      "learning_rate": 0.00015777777777777776,
      "learning_rate_embeddings": 0.00015777777777777776,
      "loss": 2.1789,
      "step": 179000
    },
    {
      "epoch": 150.84,
      "learning_rate": 0.0001566666666666667,
      "learning_rate_embeddings": 0.0001566666666666667,
      "loss": 2.167,
      "step": 179500
    },
    {
      "epoch": 151.26,
      "learning_rate": 0.00015555555555555556,
      "learning_rate_embeddings": 0.00015555555555555556,
      "loss": 2.1787,
      "step": 180000
    },
    {
      "epoch": 151.68,
      "learning_rate": 0.00015444444444444444,
      "learning_rate_embeddings": 0.00015444444444444444,
      "loss": 2.1812,
      "step": 180500
    },
    {
      "epoch": 152.1,
      "learning_rate": 0.00015333333333333334,
      "learning_rate_embeddings": 0.00015333333333333334,
      "loss": 2.1847,
      "step": 181000
    },
    {
      "epoch": 152.52,
      "learning_rate": 0.00015222222222222224,
      "learning_rate_embeddings": 0.00015222222222222224,
      "loss": 2.168,
      "step": 181500
    },
    {
      "epoch": 152.94,
      "learning_rate": 0.0001511111111111111,
      "learning_rate_embeddings": 0.0001511111111111111,
      "loss": 2.1833,
      "step": 182000
    },
    {
      "epoch": 153.36,
      "learning_rate": 0.00015,
      "learning_rate_embeddings": 0.00015,
      "loss": 2.1714,
      "step": 182500
    },
    {
      "epoch": 153.78,
      "learning_rate": 0.0001488888888888889,
      "learning_rate_embeddings": 0.0001488888888888889,
      "loss": 2.1763,
      "step": 183000
    },
    {
      "epoch": 154.2,
      "learning_rate": 0.0001477777777777778,
      "learning_rate_embeddings": 0.0001477777777777778,
      "loss": 2.1729,
      "step": 183500
    },
    {
      "epoch": 154.62,
      "learning_rate": 0.00014666666666666666,
      "learning_rate_embeddings": 0.00014666666666666666,
      "loss": 2.1761,
      "step": 184000
    },
    {
      "epoch": 155.04,
      "learning_rate": 0.00014555555555555556,
      "learning_rate_embeddings": 0.00014555555555555556,
      "loss": 2.1786,
      "step": 184500
    },
    {
      "epoch": 155.46,
      "learning_rate": 0.00014444444444444444,
      "learning_rate_embeddings": 0.00014444444444444444,
      "loss": 2.1629,
      "step": 185000
    },
    {
      "epoch": 155.88,
      "learning_rate": 0.00014333333333333334,
      "learning_rate_embeddings": 0.00014333333333333334,
      "loss": 2.1791,
      "step": 185500
    },
    {
      "epoch": 156.3,
      "learning_rate": 0.0001422222222222222,
      "learning_rate_embeddings": 0.0001422222222222222,
      "loss": 2.1769,
      "step": 186000
    },
    {
      "epoch": 156.72,
      "learning_rate": 0.00014111111111111111,
      "learning_rate_embeddings": 0.00014111111111111111,
      "loss": 2.1755,
      "step": 186500
    },
    {
      "epoch": 157.14,
      "learning_rate": 0.00014000000000000001,
      "learning_rate_embeddings": 0.00014000000000000001,
      "loss": 2.1771,
      "step": 187000
    },
    {
      "epoch": 157.56,
      "learning_rate": 0.0001388888888888889,
      "learning_rate_embeddings": 0.0001388888888888889,
      "loss": 2.1667,
      "step": 187500
    },
    {
      "epoch": 157.56,
      "eval_loss": 2.3346025943756104,
      "eval_runtime": 118.1677,
      "eval_samples_per_second": 572.982,
      "eval_steps_per_second": 4.477,
      "step": 187500
    },
    {
      "epoch": 157.98,
      "learning_rate": 0.0001377777777777778,
      "learning_rate_embeddings": 0.0001377777777777778,
      "loss": 2.1747,
      "step": 188000
    },
    {
      "epoch": 158.4,
      "learning_rate": 0.00013666666666666666,
      "learning_rate_embeddings": 0.00013666666666666666,
      "loss": 2.1649,
      "step": 188500
    },
    {
      "epoch": 158.82,
      "learning_rate": 0.00013555555555555556,
      "learning_rate_embeddings": 0.00013555555555555556,
      "loss": 2.1755,
      "step": 189000
    },
    {
      "epoch": 159.24,
      "learning_rate": 0.00013444444444444447,
      "learning_rate_embeddings": 0.00013444444444444447,
      "loss": 2.1728,
      "step": 189500
    },
    {
      "epoch": 159.66,
      "learning_rate": 0.00013333333333333334,
      "learning_rate_embeddings": 0.00013333333333333334,
      "loss": 2.1705,
      "step": 190000
    },
    {
      "epoch": 160.08,
      "learning_rate": 0.00013222222222222221,
      "learning_rate_embeddings": 0.00013222222222222221,
      "loss": 2.1725,
      "step": 190500
    },
    {
      "epoch": 160.5,
      "learning_rate": 0.00013111111111111111,
      "learning_rate_embeddings": 0.00013111111111111111,
      "loss": 2.1645,
      "step": 191000
    },
    {
      "epoch": 160.92,
      "learning_rate": 0.00013000000000000002,
      "learning_rate_embeddings": 0.00013000000000000002,
      "loss": 2.1827,
      "step": 191500
    },
    {
      "epoch": 161.34,
      "learning_rate": 0.0001288888888888889,
      "learning_rate_embeddings": 0.0001288888888888889,
      "loss": 2.1649,
      "step": 192000
    },
    {
      "epoch": 161.76,
      "learning_rate": 0.00012777777777777776,
      "learning_rate_embeddings": 0.00012777777777777776,
      "loss": 2.1729,
      "step": 192500
    },
    {
      "epoch": 162.18,
      "learning_rate": 0.0001266666666666667,
      "learning_rate_embeddings": 0.0001266666666666667,
      "loss": 2.1746,
      "step": 193000
    },
    {
      "epoch": 162.6,
      "learning_rate": 0.00012555555555555557,
      "learning_rate_embeddings": 0.00012555555555555557,
      "loss": 2.1673,
      "step": 193500
    },
    {
      "epoch": 163.03,
      "learning_rate": 0.00012444444444444444,
      "learning_rate_embeddings": 0.00012444444444444444,
      "loss": 2.1736,
      "step": 194000
    },
    {
      "epoch": 163.45,
      "learning_rate": 0.00012333333333333334,
      "learning_rate_embeddings": 0.00012333333333333334,
      "loss": 2.1577,
      "step": 194500
    },
    {
      "epoch": 163.87,
      "learning_rate": 0.00012222222222222221,
      "learning_rate_embeddings": 0.00012222222222222221,
      "loss": 2.1663,
      "step": 195000
    },
    {
      "epoch": 164.29,
      "learning_rate": 0.00012111111111111112,
      "learning_rate_embeddings": 0.00012111111111111112,
      "loss": 2.1659,
      "step": 195500
    },
    {
      "epoch": 164.71,
      "learning_rate": 0.00012,
      "learning_rate_embeddings": 0.00012,
      "loss": 2.172,
      "step": 196000
    },
    {
      "epoch": 165.13,
      "learning_rate": 0.00011888888888888889,
      "learning_rate_embeddings": 0.00011888888888888889,
      "loss": 2.1727,
      "step": 196500
    },
    {
      "epoch": 165.55,
      "learning_rate": 0.00011777777777777778,
      "learning_rate_embeddings": 0.00011777777777777778,
      "loss": 2.1555,
      "step": 197000
    },
    {
      "epoch": 165.97,
      "learning_rate": 0.00011666666666666667,
      "learning_rate_embeddings": 0.00011666666666666667,
      "loss": 2.1692,
      "step": 197500
    },
    {
      "epoch": 166.39,
      "learning_rate": 0.00011555555555555555,
      "learning_rate_embeddings": 0.00011555555555555555,
      "loss": 2.1691,
      "step": 198000
    },
    {
      "epoch": 166.81,
      "learning_rate": 0.00011444444444444445,
      "learning_rate_embeddings": 0.00011444444444444445,
      "loss": 2.1659,
      "step": 198500
    },
    {
      "epoch": 167.23,
      "learning_rate": 0.00011333333333333333,
      "learning_rate_embeddings": 0.00011333333333333333,
      "loss": 2.1584,
      "step": 199000
    },
    {
      "epoch": 167.65,
      "learning_rate": 0.00011222222222222223,
      "learning_rate_embeddings": 0.00011222222222222223,
      "loss": 2.1605,
      "step": 199500
    },
    {
      "epoch": 168.07,
      "learning_rate": 0.0001111111111111111,
      "learning_rate_embeddings": 0.0001111111111111111,
      "loss": 2.1679,
      "step": 200000
    },
    {
      "epoch": 168.07,
      "eval_loss": 2.330087661743164,
      "eval_runtime": 117.8736,
      "eval_samples_per_second": 574.412,
      "eval_steps_per_second": 4.488,
      "step": 200000
    },
    {
      "epoch": 168.49,
      "learning_rate": 0.00011,
      "learning_rate_embeddings": 0.00011,
      "loss": 2.1569,
      "step": 200500
    },
    {
      "epoch": 168.91,
      "learning_rate": 0.00010888888888888888,
      "learning_rate_embeddings": 0.00010888888888888888,
      "loss": 2.1558,
      "step": 201000
    },
    {
      "epoch": 169.33,
      "learning_rate": 0.00010777777777777778,
      "learning_rate_embeddings": 0.00010777777777777778,
      "loss": 2.1498,
      "step": 201500
    },
    {
      "epoch": 169.75,
      "learning_rate": 0.00010666666666666668,
      "learning_rate_embeddings": 0.00010666666666666668,
      "loss": 2.1562,
      "step": 202000
    },
    {
      "epoch": 170.17,
      "learning_rate": 0.00010555555555555555,
      "learning_rate_embeddings": 0.00010555555555555555,
      "loss": 2.1641,
      "step": 202500
    },
    {
      "epoch": 170.59,
      "learning_rate": 0.00010444444444444445,
      "learning_rate_embeddings": 0.00010444444444444445,
      "loss": 2.1579,
      "step": 203000
    },
    {
      "epoch": 171.01,
      "learning_rate": 0.00010333333333333333,
      "learning_rate_embeddings": 0.00010333333333333333,
      "loss": 2.1755,
      "step": 203500
    },
    {
      "epoch": 171.43,
      "learning_rate": 0.00010222222222222223,
      "learning_rate_embeddings": 0.00010222222222222223,
      "loss": 2.1546,
      "step": 204000
    },
    {
      "epoch": 171.85,
      "learning_rate": 0.00010111111111111112,
      "learning_rate_embeddings": 0.00010111111111111112,
      "loss": 2.1662,
      "step": 204500
    },
    {
      "epoch": 172.27,
      "learning_rate": 0.0001,
      "learning_rate_embeddings": 0.0001,
      "loss": 2.1624,
      "step": 205000
    },
    {
      "epoch": 172.69,
      "learning_rate": 9.888888888888889e-05,
      "learning_rate_embeddings": 9.888888888888889e-05,
      "loss": 2.1639,
      "step": 205500
    },
    {
      "epoch": 173.11,
      "learning_rate": 9.777777777777778e-05,
      "learning_rate_embeddings": 9.777777777777778e-05,
      "loss": 2.1687,
      "step": 206000
    },
    {
      "epoch": 173.53,
      "learning_rate": 9.666666666666667e-05,
      "learning_rate_embeddings": 9.666666666666667e-05,
      "loss": 2.165,
      "step": 206500
    },
    {
      "epoch": 173.95,
      "learning_rate": 9.555555555555557e-05,
      "learning_rate_embeddings": 9.555555555555557e-05,
      "loss": 2.1599,
      "step": 207000
    },
    {
      "epoch": 174.37,
      "learning_rate": 9.444444444444444e-05,
      "learning_rate_embeddings": 9.444444444444444e-05,
      "loss": 2.1465,
      "step": 207500
    },
    {
      "epoch": 174.79,
      "learning_rate": 9.333333333333334e-05,
      "learning_rate_embeddings": 9.333333333333334e-05,
      "loss": 2.1523,
      "step": 208000
    },
    {
      "epoch": 175.21,
      "learning_rate": 9.222222222222222e-05,
      "learning_rate_embeddings": 9.222222222222222e-05,
      "loss": 2.1502,
      "step": 208500
    },
    {
      "epoch": 175.63,
      "learning_rate": 9.111111111111112e-05,
      "learning_rate_embeddings": 9.111111111111112e-05,
      "loss": 2.153,
      "step": 209000
    },
    {
      "epoch": 176.05,
      "learning_rate": 8.999999999999999e-05,
      "learning_rate_embeddings": 8.999999999999999e-05,
      "loss": 2.1602,
      "step": 209500
    },
    {
      "epoch": 176.47,
      "learning_rate": 8.888888888888889e-05,
      "learning_rate_embeddings": 8.888888888888889e-05,
      "loss": 2.1502,
      "step": 210000
    },
    {
      "epoch": 176.89,
      "learning_rate": 8.777777777777778e-05,
      "learning_rate_embeddings": 8.777777777777778e-05,
      "loss": 2.1581,
      "step": 210500
    },
    {
      "epoch": 177.31,
      "learning_rate": 8.666666666666667e-05,
      "learning_rate_embeddings": 8.666666666666667e-05,
      "loss": 2.1499,
      "step": 211000
    },
    {
      "epoch": 177.73,
      "learning_rate": 8.555555555555556e-05,
      "learning_rate_embeddings": 8.555555555555556e-05,
      "loss": 2.145,
      "step": 211500
    },
    {
      "epoch": 178.15,
      "learning_rate": 8.444444444444444e-05,
      "learning_rate_embeddings": 8.444444444444444e-05,
      "loss": 2.1601,
      "step": 212000
    },
    {
      "epoch": 178.57,
      "learning_rate": 8.333333333333333e-05,
      "learning_rate_embeddings": 8.333333333333333e-05,
      "loss": 2.1498,
      "step": 212500
    },
    {
      "epoch": 178.57,
      "eval_loss": 2.323934555053711,
      "eval_runtime": 118.086,
      "eval_samples_per_second": 573.379,
      "eval_steps_per_second": 4.48,
      "step": 212500
    },
    {
      "epoch": 178.99,
      "learning_rate": 8.222222222222223e-05,
      "learning_rate_embeddings": 8.222222222222223e-05,
      "loss": 2.1592,
      "step": 213000
    },
    {
      "epoch": 179.41,
      "learning_rate": 8.11111111111111e-05,
      "learning_rate_embeddings": 8.11111111111111e-05,
      "loss": 2.1557,
      "step": 213500
    },
    {
      "epoch": 179.83,
      "learning_rate": 8e-05,
      "learning_rate_embeddings": 8e-05,
      "loss": 2.154,
      "step": 214000
    },
    {
      "epoch": 180.25,
      "learning_rate": 7.888888888888888e-05,
      "learning_rate_embeddings": 7.888888888888888e-05,
      "loss": 2.1584,
      "step": 214500
    },
    {
      "epoch": 180.67,
      "learning_rate": 7.777777777777778e-05,
      "learning_rate_embeddings": 7.777777777777778e-05,
      "loss": 2.1604,
      "step": 215000
    },
    {
      "epoch": 181.09,
      "learning_rate": 7.666666666666667e-05,
      "learning_rate_embeddings": 7.666666666666667e-05,
      "loss": 2.1608,
      "step": 215500
    },
    {
      "epoch": 181.51,
      "learning_rate": 7.555555555555556e-05,
      "learning_rate_embeddings": 7.555555555555556e-05,
      "loss": 2.1534,
      "step": 216000
    },
    {
      "epoch": 181.93,
      "learning_rate": 7.444444444444444e-05,
      "learning_rate_embeddings": 7.444444444444444e-05,
      "loss": 2.1523,
      "step": 216500
    },
    {
      "epoch": 182.35,
      "learning_rate": 7.333333333333333e-05,
      "learning_rate_embeddings": 7.333333333333333e-05,
      "loss": 2.1446,
      "step": 217000
    },
    {
      "epoch": 182.77,
      "learning_rate": 7.222222222222222e-05,
      "learning_rate_embeddings": 7.222222222222222e-05,
      "loss": 2.1628,
      "step": 217500
    },
    {
      "epoch": 183.19,
      "learning_rate": 7.11111111111111e-05,
      "learning_rate_embeddings": 7.11111111111111e-05,
      "loss": 2.1528,
      "step": 218000
    },
    {
      "epoch": 183.61,
      "learning_rate": 7.000000000000001e-05,
      "learning_rate_embeddings": 7.000000000000001e-05,
      "loss": 2.15,
      "step": 218500
    },
    {
      "epoch": 184.03,
      "learning_rate": 6.88888888888889e-05,
      "learning_rate_embeddings": 6.88888888888889e-05,
      "loss": 2.1555,
      "step": 219000
    },
    {
      "epoch": 184.45,
      "learning_rate": 6.777777777777778e-05,
      "learning_rate_embeddings": 6.777777777777778e-05,
      "loss": 2.1445,
      "step": 219500
    },
    {
      "epoch": 184.87,
      "learning_rate": 6.666666666666667e-05,
      "learning_rate_embeddings": 6.666666666666667e-05,
      "loss": 2.1531,
      "step": 220000
    },
    {
      "epoch": 185.29,
      "learning_rate": 6.555555555555556e-05,
      "learning_rate_embeddings": 6.555555555555556e-05,
      "loss": 2.1524,
      "step": 220500
    },
    {
      "epoch": 185.71,
      "learning_rate": 6.444444444444444e-05,
      "learning_rate_embeddings": 6.444444444444444e-05,
      "loss": 2.1533,
      "step": 221000
    },
    {
      "epoch": 186.13,
      "learning_rate": 6.333333333333335e-05,
      "learning_rate_embeddings": 6.333333333333335e-05,
      "loss": 2.1517,
      "step": 221500
    },
    {
      "epoch": 186.55,
      "learning_rate": 6.222222222222222e-05,
      "learning_rate_embeddings": 6.222222222222222e-05,
      "loss": 2.147,
      "step": 222000
    },
    {
      "epoch": 186.97,
      "learning_rate": 6.111111111111111e-05,
      "learning_rate_embeddings": 6.111111111111111e-05,
      "loss": 2.1503,
      "step": 222500
    },
    {
      "epoch": 187.39,
      "learning_rate": 6e-05,
      "learning_rate_embeddings": 6e-05,
      "loss": 2.1482,
      "step": 223000
    },
    {
      "epoch": 187.81,
      "learning_rate": 5.888888888888889e-05,
      "learning_rate_embeddings": 5.888888888888889e-05,
      "loss": 2.1409,
      "step": 223500
    },
    {
      "epoch": 188.24,
      "learning_rate": 5.7777777777777776e-05,
      "learning_rate_embeddings": 5.7777777777777776e-05,
      "loss": 2.1478,
      "step": 224000
    },
    {
      "epoch": 188.66,
      "learning_rate": 5.6666666666666664e-05,
      "learning_rate_embeddings": 5.6666666666666664e-05,
      "loss": 2.1479,
      "step": 224500
    },
    {
      "epoch": 189.08,
      "learning_rate": 5.555555555555555e-05,
      "learning_rate_embeddings": 5.555555555555555e-05,
      "loss": 2.1633,
      "step": 225000
    },
    {
      "epoch": 189.08,
      "eval_loss": 2.321134567260742,
      "eval_runtime": 117.9835,
      "eval_samples_per_second": 573.877,
      "eval_steps_per_second": 4.484,
      "step": 225000
    },
    {
      "epoch": 189.5,
      "learning_rate": 5.444444444444444e-05,
      "learning_rate_embeddings": 5.444444444444444e-05,
      "loss": 2.1425,
      "step": 225500
    },
    {
      "epoch": 189.92,
      "learning_rate": 5.333333333333334e-05,
      "learning_rate_embeddings": 5.333333333333334e-05,
      "loss": 2.1498,
      "step": 226000
    },
    {
      "epoch": 190.34,
      "learning_rate": 5.222222222222223e-05,
      "learning_rate_embeddings": 5.222222222222223e-05,
      "loss": 2.1415,
      "step": 226500
    },
    {
      "epoch": 190.76,
      "learning_rate": 5.1111111111111115e-05,
      "learning_rate_embeddings": 5.1111111111111115e-05,
      "loss": 2.145,
      "step": 227000
    },
    {
      "epoch": 191.18,
      "learning_rate": 5e-05,
      "learning_rate_embeddings": 5e-05,
      "loss": 2.1516,
      "step": 227500
    },
    {
      "epoch": 191.6,
      "learning_rate": 4.888888888888889e-05,
      "learning_rate_embeddings": 4.888888888888889e-05,
      "loss": 2.1514,
      "step": 228000
    },
    {
      "epoch": 192.02,
      "learning_rate": 4.7777777777777784e-05,
      "learning_rate_embeddings": 4.7777777777777784e-05,
      "loss": 2.14,
      "step": 228500
    },
    {
      "epoch": 192.44,
      "learning_rate": 4.666666666666667e-05,
      "learning_rate_embeddings": 4.666666666666667e-05,
      "loss": 2.1454,
      "step": 229000
    },
    {
      "epoch": 192.86,
      "learning_rate": 4.555555555555556e-05,
      "learning_rate_embeddings": 4.555555555555556e-05,
      "loss": 2.1453,
      "step": 229500
    },
    {
      "epoch": 193.28,
      "learning_rate": 4.4444444444444447e-05,
      "learning_rate_embeddings": 4.4444444444444447e-05,
      "loss": 2.151,
      "step": 230000
    },
    {
      "epoch": 193.7,
      "learning_rate": 4.3333333333333334e-05,
      "learning_rate_embeddings": 4.3333333333333334e-05,
      "loss": 2.144,
      "step": 230500
    },
    {
      "epoch": 194.12,
      "learning_rate": 4.222222222222222e-05,
      "learning_rate_embeddings": 4.222222222222222e-05,
      "loss": 2.1479,
      "step": 231000
    },
    {
      "epoch": 194.54,
      "learning_rate": 4.1111111111111116e-05,
      "learning_rate_embeddings": 4.1111111111111116e-05,
      "loss": 2.1408,
      "step": 231500
    },
    {
      "epoch": 194.96,
      "learning_rate": 4e-05,
      "learning_rate_embeddings": 4e-05,
      "loss": 2.1473,
      "step": 232000
    },
    {
      "epoch": 195.38,
      "learning_rate": 3.888888888888889e-05,
      "learning_rate_embeddings": 3.888888888888889e-05,
      "loss": 2.1388,
      "step": 232500
    },
    {
      "epoch": 195.8,
      "learning_rate": 3.777777777777778e-05,
      "learning_rate_embeddings": 3.777777777777778e-05,
      "loss": 2.1355,
      "step": 233000
    },
    {
      "epoch": 196.22,
      "learning_rate": 3.6666666666666666e-05,
      "learning_rate_embeddings": 3.6666666666666666e-05,
      "loss": 2.1448,
      "step": 233500
    },
    {
      "epoch": 196.64,
      "learning_rate": 3.555555555555555e-05,
      "learning_rate_embeddings": 3.555555555555555e-05,
      "loss": 2.136,
      "step": 234000
    },
    {
      "epoch": 197.06,
      "learning_rate": 3.444444444444445e-05,
      "learning_rate_embeddings": 3.444444444444445e-05,
      "loss": 2.1362,
      "step": 234500
    },
    {
      "epoch": 197.48,
      "learning_rate": 3.3333333333333335e-05,
      "learning_rate_embeddings": 3.3333333333333335e-05,
      "loss": 2.1379,
      "step": 235000
    },
    {
      "epoch": 197.9,
      "learning_rate": 3.222222222222222e-05,
      "learning_rate_embeddings": 3.222222222222222e-05,
      "loss": 2.1405,
      "step": 235500
    },
    {
      "epoch": 198.32,
      "learning_rate": 3.111111111111111e-05,
      "learning_rate_embeddings": 3.111111111111111e-05,
      "loss": 2.1439,
      "step": 236000
    },
    {
      "epoch": 198.74,
      "learning_rate": 3e-05,
      "learning_rate_embeddings": 3e-05,
      "loss": 2.1311,
      "step": 236500
    },
    {
      "epoch": 199.16,
      "learning_rate": 2.8888888888888888e-05,
      "learning_rate_embeddings": 2.8888888888888888e-05,
      "loss": 2.1411,
      "step": 237000
    },
    {
      "epoch": 199.58,
      "learning_rate": 2.7777777777777776e-05,
      "learning_rate_embeddings": 2.7777777777777776e-05,
      "loss": 2.1369,
      "step": 237500
    },
    {
      "epoch": 199.58,
      "eval_loss": 2.3181934356689453,
      "eval_runtime": 117.8788,
      "eval_samples_per_second": 574.387,
      "eval_steps_per_second": 4.488,
      "step": 237500
    },
    {
      "epoch": 200.0,
      "learning_rate": 2.666666666666667e-05,
      "learning_rate_embeddings": 2.666666666666667e-05,
      "loss": 2.143,
      "step": 238000
    },
    {
      "epoch": 200.42,
      "learning_rate": 2.5555555555555557e-05,
      "learning_rate_embeddings": 2.5555555555555557e-05,
      "loss": 2.134,
      "step": 238500
    },
    {
      "epoch": 200.84,
      "learning_rate": 2.4444444444444445e-05,
      "learning_rate_embeddings": 2.4444444444444445e-05,
      "loss": 2.1366,
      "step": 239000
    },
    {
      "epoch": 201.26,
      "learning_rate": 2.3333333333333336e-05,
      "learning_rate_embeddings": 2.3333333333333336e-05,
      "loss": 2.1355,
      "step": 239500
    },
    {
      "epoch": 201.68,
      "learning_rate": 2.2222222222222223e-05,
      "learning_rate_embeddings": 2.2222222222222223e-05,
      "loss": 2.1378,
      "step": 240000
    },
    {
      "epoch": 202.1,
      "learning_rate": 2.111111111111111e-05,
      "learning_rate_embeddings": 2.111111111111111e-05,
      "loss": 2.1364,
      "step": 240500
    },
    {
      "epoch": 202.52,
      "learning_rate": 2e-05,
      "learning_rate_embeddings": 2e-05,
      "loss": 2.1378,
      "step": 241000
    },
    {
      "epoch": 202.94,
      "learning_rate": 1.888888888888889e-05,
      "learning_rate_embeddings": 1.888888888888889e-05,
      "loss": 2.1364,
      "step": 241500
    },
    {
      "epoch": 203.36,
      "learning_rate": 1.7777777777777777e-05,
      "learning_rate_embeddings": 1.7777777777777777e-05,
      "loss": 2.1386,
      "step": 242000
    },
    {
      "epoch": 203.78,
      "learning_rate": 1.6666666666666667e-05,
      "learning_rate_embeddings": 1.6666666666666667e-05,
      "loss": 2.1351,
      "step": 242500
    },
    {
      "epoch": 204.2,
      "learning_rate": 1.5555555555555555e-05,
      "learning_rate_embeddings": 1.5555555555555555e-05,
      "loss": 2.1299,
      "step": 243000
    },
    {
      "epoch": 204.62,
      "learning_rate": 1.4444444444444444e-05,
      "learning_rate_embeddings": 1.4444444444444444e-05,
      "loss": 2.1334,
      "step": 243500
    },
    {
      "epoch": 205.04,
      "learning_rate": 1.3333333333333335e-05,
      "learning_rate_embeddings": 1.3333333333333335e-05,
      "loss": 2.1388,
      "step": 244000
    },
    {
      "epoch": 205.46,
      "learning_rate": 1.2222222222222222e-05,
      "learning_rate_embeddings": 1.2222222222222222e-05,
      "loss": 2.126,
      "step": 244500
    },
    {
      "epoch": 205.88,
      "learning_rate": 1.1111111111111112e-05,
      "learning_rate_embeddings": 1.1111111111111112e-05,
      "loss": 2.1353,
      "step": 245000
    },
    {
      "epoch": 206.3,
      "learning_rate": 1e-05,
      "learning_rate_embeddings": 1e-05,
      "loss": 2.1333,
      "step": 245500
    },
    {
      "epoch": 206.72,
      "learning_rate": 8.888888888888888e-06,
      "learning_rate_embeddings": 8.888888888888888e-06,
      "loss": 2.1291,
      "step": 246000
    },
    {
      "epoch": 207.14,
      "learning_rate": 7.777777777777777e-06,
      "learning_rate_embeddings": 7.777777777777777e-06,
      "loss": 2.1352,
      "step": 246500
    },
    {
      "epoch": 207.56,
      "learning_rate": 6.6666666666666675e-06,
      "learning_rate_embeddings": 6.6666666666666675e-06,
      "loss": 2.1403,
      "step": 247000
    },
    {
      "epoch": 207.98,
      "learning_rate": 5.555555555555556e-06,
      "learning_rate_embeddings": 5.555555555555556e-06,
      "loss": 2.1278,
      "step": 247500
    },
    {
      "epoch": 208.4,
      "learning_rate": 4.444444444444444e-06,
      "learning_rate_embeddings": 4.444444444444444e-06,
      "loss": 2.1254,
      "step": 248000
    },
    {
      "epoch": 208.82,
      "learning_rate": 3.3333333333333337e-06,
      "learning_rate_embeddings": 3.3333333333333337e-06,
      "loss": 2.1348,
      "step": 248500
    },
    {
      "epoch": 209.24,
      "learning_rate": 2.222222222222222e-06,
      "learning_rate_embeddings": 2.222222222222222e-06,
      "loss": 2.1306,
      "step": 249000
    },
    {
      "epoch": 209.66,
      "learning_rate": 1.111111111111111e-06,
      "learning_rate_embeddings": 1.111111111111111e-06,
      "loss": 2.1266,
      "step": 249500
    },
    {
      "epoch": 210.08,
      "learning_rate": 0.0,
      "learning_rate_embeddings": 0.0,
      "loss": 2.1316,
      "step": 250000
    },
    {
      "epoch": 210.08,
      "eval_loss": 2.3166539669036865,
      "eval_runtime": 117.9198,
      "eval_samples_per_second": 574.187,
      "eval_steps_per_second": 4.486,
      "step": 250000
    }
  ],
  "max_steps": 250000,
  "num_train_epochs": 211,
  "total_flos": 4.18242839445504e+18,
  "trial_name": null,
  "trial_params": null
}