{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.648419565601271,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 3.8996,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 2.8239,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-05,
      "loss": 2.5627,
      "step": 150
    },
    {
      "epoch": 0.09,
      "learning_rate": 8e-05,
      "loss": 2.4302,
      "step": 200
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 2.3182,
      "step": 250
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00012,
      "loss": 2.2618,
      "step": 300
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014,
      "loss": 2.2389,
      "step": 350
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016,
      "loss": 2.1958,
      "step": 400
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018,
      "loss": 2.1725,
      "step": 450
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.1412,
      "step": 500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00022000000000000003,
      "loss": 2.1315,
      "step": 550
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00024,
      "loss": 2.1238,
      "step": 600
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.1238,
      "step": 650
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00028,
      "loss": 2.1039,
      "step": 700
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00030000000000000003,
      "loss": 2.1185,
      "step": 750
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00032,
      "loss": 2.1009,
      "step": 800
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00034,
      "loss": 2.1063,
      "step": 850
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00036,
      "loss": 2.1236,
      "step": 900
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00038,
      "loss": 2.1137,
      "step": 950
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0004,
      "loss": 2.1108,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "eval_loss": 2.0146186351776123,
      "eval_runtime": 108.3636,
      "eval_samples_per_second": 1673.071,
      "eval_steps_per_second": 6.543,
      "step": 1000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003977777777777778,
      "loss": 2.1429,
      "step": 1050
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00039555555555555557,
      "loss": 2.1205,
      "step": 1100
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003933333333333333,
      "loss": 2.1013,
      "step": 1150
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003911111111111111,
      "loss": 2.0935,
      "step": 1200
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003888888888888889,
      "loss": 2.0949,
      "step": 1250
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00038666666666666667,
      "loss": 2.0991,
      "step": 1300
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00038444444444444447,
      "loss": 2.0847,
      "step": 1350
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003822222222222223,
      "loss": 2.0796,
      "step": 1400
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00038,
      "loss": 2.0739,
      "step": 1450
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00037777777777777777,
      "loss": 2.0609,
      "step": 1500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00037555555555555557,
      "loss": 2.0617,
      "step": 1550
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003733333333333334,
      "loss": 2.0511,
      "step": 1600
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003711111111111111,
      "loss": 2.0392,
      "step": 1650
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003688888888888889,
      "loss": 2.0501,
      "step": 1700
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00036666666666666667,
      "loss": 2.0416,
      "step": 1750
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00036444444444444447,
      "loss": 2.0364,
      "step": 1800
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003622222222222222,
      "loss": 2.0281,
      "step": 1850
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00036,
      "loss": 1.9976,
      "step": 1900
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003577777777777778,
      "loss": 2.0201,
      "step": 1950
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00035555555555555557,
      "loss": 2.031,
      "step": 2000
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.9337339401245117,
      "eval_runtime": 108.2702,
      "eval_samples_per_second": 1674.514,
      "eval_steps_per_second": 6.548,
      "step": 2000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003533333333333333,
      "loss": 2.0055,
      "step": 2050
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003511111111111111,
      "loss": 1.9967,
      "step": 2100
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0003488888888888889,
      "loss": 2.0085,
      "step": 2150
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00034666666666666667,
      "loss": 1.9884,
      "step": 2200
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003444444444444445,
      "loss": 1.9852,
      "step": 2250
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0003422222222222222,
      "loss": 1.9645,
      "step": 2300
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00034,
      "loss": 1.9663,
      "step": 2350
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00033777777777777777,
      "loss": 1.966,
      "step": 2400
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003355555555555556,
      "loss": 1.9506,
      "step": 2450
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003333333333333334,
      "loss": 1.9577,
      "step": 2500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003311111111111111,
      "loss": 1.9453,
      "step": 2550
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00032888888888888887,
      "loss": 1.9506,
      "step": 2600
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003266666666666667,
      "loss": 1.9488,
      "step": 2650
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003244444444444445,
      "loss": 1.9336,
      "step": 2700
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003222222222222222,
      "loss": 1.9355,
      "step": 2750
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00032,
      "loss": 1.959,
      "step": 2800
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003177777777777778,
      "loss": 1.9257,
      "step": 2850
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003155555555555556,
      "loss": 1.9246,
      "step": 2900
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003133333333333333,
      "loss": 1.9358,
      "step": 2950
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003111111111111111,
      "loss": 1.9215,
      "step": 3000
    },
    {
      "epoch": 1.41,
      "eval_loss": 1.8456602096557617,
      "eval_runtime": 108.7408,
      "eval_samples_per_second": 1667.268,
      "eval_steps_per_second": 6.52,
      "step": 3000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00030888888888888893,
      "loss": 1.9159,
      "step": 3050
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003066666666666667,
      "loss": 1.9129,
      "step": 3100
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003044444444444444,
      "loss": 1.9167,
      "step": 3150
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0003022222222222222,
      "loss": 1.9087,
      "step": 3200
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00030000000000000003,
      "loss": 1.9018,
      "step": 3250
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002977777777777778,
      "loss": 1.9006,
      "step": 3300
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002955555555555556,
      "loss": 1.8893,
      "step": 3350
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002933333333333333,
      "loss": 1.8906,
      "step": 3400
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00029111111111111113,
      "loss": 1.8814,
      "step": 3450
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002888888888888889,
      "loss": 1.8869,
      "step": 3500
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002866666666666667,
      "loss": 1.8983,
      "step": 3550
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002844444444444445,
      "loss": 1.8818,
      "step": 3600
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00028222222222222223,
      "loss": 1.8772,
      "step": 3650
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00028,
      "loss": 1.8764,
      "step": 3700
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002777777777777778,
      "loss": 1.8642,
      "step": 3750
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002755555555555556,
      "loss": 1.8847,
      "step": 3800
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00027333333333333333,
      "loss": 1.877,
      "step": 3850
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00027111111111111113,
      "loss": 1.8636,
      "step": 3900
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00026888888888888893,
      "loss": 1.8675,
      "step": 3950
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002666666666666667,
      "loss": 1.8556,
      "step": 4000
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.7807087898254395,
      "eval_runtime": 107.6293,
      "eval_samples_per_second": 1684.486,
      "eval_steps_per_second": 6.587,
      "step": 4000
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00026444444444444443,
      "loss": 1.8651,
      "step": 4050
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00026222222222222223,
      "loss": 1.8685,
      "step": 4100
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00026000000000000003,
      "loss": 1.8498,
      "step": 4150
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00025777777777777783,
      "loss": 1.8606,
      "step": 4200
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00025555555555555553,
      "loss": 1.8769,
      "step": 4250
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00025333333333333333,
      "loss": 1.8323,
      "step": 4300
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00025111111111111113,
      "loss": 1.8338,
      "step": 4350
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0002488888888888889,
      "loss": 1.8175,
      "step": 4400
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002466666666666667,
      "loss": 1.8092,
      "step": 4450
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002444444444444445,
      "loss": 1.8175,
      "step": 4500
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002422222222222222,
      "loss": 1.8128,
      "step": 4550
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00024,
      "loss": 1.8082,
      "step": 4600
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00023777777777777778,
      "loss": 1.8095,
      "step": 4650
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00023555555555555558,
      "loss": 1.8138,
      "step": 4700
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00023333333333333336,
      "loss": 1.8046,
      "step": 4750
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002311111111111111,
      "loss": 1.8067,
      "step": 4800
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00022888888888888888,
      "loss": 1.8014,
      "step": 4850
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00022666666666666668,
      "loss": 1.7784,
      "step": 4900
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00022444444444444446,
      "loss": 1.8049,
      "step": 4950
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00022222222222222223,
      "loss": 1.8056,
      "step": 5000
    },
    {
      "epoch": 2.36,
      "eval_loss": 1.7309892177581787,
      "eval_runtime": 108.3732,
      "eval_samples_per_second": 1672.923,
      "eval_steps_per_second": 6.542,
      "step": 5000
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00022000000000000003,
      "loss": 1.8004,
      "step": 5050
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00021777777777777778,
      "loss": 1.7945,
      "step": 5100
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00021555555555555556,
      "loss": 1.7917,
      "step": 5150
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00021333333333333333,
      "loss": 1.7872,
      "step": 5200
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00021111111111111113,
      "loss": 1.7822,
      "step": 5250
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002088888888888889,
      "loss": 1.7669,
      "step": 5300
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00020666666666666668,
      "loss": 1.7717,
      "step": 5350
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00020444444444444443,
      "loss": 1.7857,
      "step": 5400
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00020222222222222223,
      "loss": 1.7753,
      "step": 5450
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 1.7689,
      "step": 5500
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00019777777777777778,
      "loss": 1.7609,
      "step": 5550
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00019555555555555556,
      "loss": 1.7641,
      "step": 5600
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.7632,
      "step": 5650
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00019111111111111114,
      "loss": 1.755,
      "step": 5700
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00018888888888888888,
      "loss": 1.757,
      "step": 5750
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.7654,
      "step": 5800
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00018444444444444446,
      "loss": 1.7456,
      "step": 5850
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00018222222222222224,
      "loss": 1.7466,
      "step": 5900
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00018,
      "loss": 1.7476,
      "step": 5950
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.73,
      "step": 6000
    },
    {
      "epoch": 2.83,
      "eval_loss": 1.69302499294281,
      "eval_runtime": 109.9,
      "eval_samples_per_second": 1649.682,
      "eval_steps_per_second": 6.451,
      "step": 6000
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00017555555555555556,
      "loss": 1.7368,
      "step": 6050
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.736,
      "step": 6100
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001711111111111111,
      "loss": 1.7348,
      "step": 6150
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00016888888888888889,
      "loss": 1.7386,
      "step": 6200
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.7324,
      "step": 6250
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00016444444444444444,
      "loss": 1.7257,
      "step": 6300
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00016222222222222224,
      "loss": 1.7286,
      "step": 6350
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00016,
      "loss": 1.7445,
      "step": 6400
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001577777777777778,
      "loss": 1.7168,
      "step": 6450
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.7103,
      "step": 6500
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00015333333333333334,
      "loss": 1.6631,
      "step": 6550
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001511111111111111,
      "loss": 1.6732,
      "step": 6600
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001488888888888889,
      "loss": 1.6888,
      "step": 6650
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.00014666666666666666,
      "loss": 1.702,
      "step": 6700
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00014444444444444444,
      "loss": 1.7005,
      "step": 6750
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00014222222222222224,
      "loss": 1.702,
      "step": 6800
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00014,
      "loss": 1.6924,
      "step": 6850
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001377777777777778,
      "loss": 1.6867,
      "step": 6900
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00013555555555555556,
      "loss": 1.689,
      "step": 6950
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6674,
      "step": 7000
    },
    {
      "epoch": 3.24,
      "eval_loss": 1.6436110734939575,
      "eval_runtime": 118.934,
      "eval_samples_per_second": 1524.375,
      "eval_steps_per_second": 5.961,
      "step": 7000
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00013111111111111111,
      "loss": 1.6856,
      "step": 7050
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00012888888888888892,
      "loss": 1.666,
      "step": 7100
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00012666666666666666,
      "loss": 1.6984,
      "step": 7150
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00012444444444444444,
      "loss": 1.6749,
      "step": 7200
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00012222222222222224,
      "loss": 1.6731,
      "step": 7250
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00012,
      "loss": 1.675,
      "step": 7300
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00011777777777777779,
      "loss": 1.6768,
      "step": 7350
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00011555555555555555,
      "loss": 1.6672,
      "step": 7400
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00011333333333333334,
      "loss": 1.6701,
      "step": 7450
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.6693,
      "step": 7500
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.00010888888888888889,
      "loss": 1.6778,
      "step": 7550
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.6578,
      "step": 7600
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00010444444444444445,
      "loss": 1.6579,
      "step": 7650
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00010222222222222222,
      "loss": 1.6449,
      "step": 7700
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001,
      "loss": 1.6522,
      "step": 7750
    },
    {
      "epoch": 3.61,
      "learning_rate": 9.777777777777778e-05,
      "loss": 1.6565,
      "step": 7800
    },
    {
      "epoch": 3.64,
      "learning_rate": 9.555555555555557e-05,
      "loss": 1.6475,
      "step": 7850
    },
    {
      "epoch": 3.66,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.6535,
      "step": 7900
    },
    {
      "epoch": 3.68,
      "learning_rate": 9.111111111111112e-05,
      "loss": 1.6518,
      "step": 7950
    },
    {
      "epoch": 3.71,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.6495,
      "step": 8000
    },
    {
      "epoch": 3.71,
      "eval_loss": 1.611691951751709,
      "eval_runtime": 105.0645,
      "eval_samples_per_second": 1725.607,
      "eval_steps_per_second": 6.748,
      "step": 8000
    },
    {
      "epoch": 3.73,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.6411,
      "step": 8050
    },
    {
      "epoch": 3.75,
      "learning_rate": 8.444444444444444e-05,
      "loss": 1.6538,
      "step": 8100
    },
    {
      "epoch": 3.78,
      "learning_rate": 8.222222222222222e-05,
      "loss": 1.6442,
      "step": 8150
    },
    {
      "epoch": 3.8,
      "learning_rate": 8e-05,
      "loss": 1.637,
      "step": 8200
    },
    {
      "epoch": 3.82,
      "learning_rate": 7.777777777777778e-05,
      "loss": 1.6532,
      "step": 8250
    },
    {
      "epoch": 3.85,
      "learning_rate": 7.555555555555556e-05,
      "loss": 1.6407,
      "step": 8300
    },
    {
      "epoch": 3.87,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.634,
      "step": 8350
    },
    {
      "epoch": 3.89,
      "learning_rate": 7.111111111111112e-05,
      "loss": 1.6491,
      "step": 8400
    },
    {
      "epoch": 3.92,
      "learning_rate": 6.88888888888889e-05,
      "loss": 1.6295,
      "step": 8450
    },
    {
      "epoch": 3.94,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6292,
      "step": 8500
    },
    {
      "epoch": 3.97,
      "learning_rate": 6.444444444444446e-05,
      "loss": 1.6223,
      "step": 8550
    },
    {
      "epoch": 3.99,
      "learning_rate": 6.222222222222222e-05,
      "loss": 1.6191,
      "step": 8600
    },
    {
      "epoch": 4.01,
      "learning_rate": 6e-05,
      "loss": 1.632,
      "step": 8650
    },
    {
      "epoch": 4.04,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 1.6052,
      "step": 8700
    },
    {
      "epoch": 4.06,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.6194,
      "step": 8750
    },
    {
      "epoch": 4.08,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.6077,
      "step": 8800
    },
    {
      "epoch": 4.11,
      "learning_rate": 5.111111111111111e-05,
      "loss": 1.5978,
      "step": 8850
    },
    {
      "epoch": 4.13,
      "learning_rate": 4.888888888888889e-05,
      "loss": 1.5971,
      "step": 8900
    },
    {
      "epoch": 4.15,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.5922,
      "step": 8950
    },
    {
      "epoch": 4.18,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.5955,
      "step": 9000
    },
    {
      "epoch": 4.18,
      "eval_loss": 1.5719584226608276,
      "eval_runtime": 104.5389,
      "eval_samples_per_second": 1734.282,
      "eval_steps_per_second": 6.782,
      "step": 9000
    },
    {
      "epoch": 4.2,
      "learning_rate": 4.222222222222222e-05,
      "loss": 1.5953,
      "step": 9050
    },
    {
      "epoch": 4.22,
      "learning_rate": 4e-05,
      "loss": 1.5986,
      "step": 9100
    },
    {
      "epoch": 4.25,
      "learning_rate": 3.777777777777778e-05,
      "loss": 1.5897,
      "step": 9150
    },
    {
      "epoch": 4.27,
      "learning_rate": 3.555555555555556e-05,
      "loss": 1.5975,
      "step": 9200
    },
    {
      "epoch": 4.3,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6016,
      "step": 9250
    },
    {
      "epoch": 4.32,
      "learning_rate": 3.111111111111111e-05,
      "loss": 1.5895,
      "step": 9300
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 1.5792,
      "step": 9350
    },
    {
      "epoch": 4.37,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.5898,
      "step": 9400
    },
    {
      "epoch": 4.39,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 1.59,
      "step": 9450
    },
    {
      "epoch": 4.41,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.5768,
      "step": 9500
    },
    {
      "epoch": 4.44,
      "learning_rate": 2e-05,
      "loss": 1.5919,
      "step": 9550
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.777777777777778e-05,
      "loss": 1.5791,
      "step": 9600
    },
    {
      "epoch": 4.48,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 1.5779,
      "step": 9650
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.5686,
      "step": 9700
    },
    {
      "epoch": 4.53,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.5856,
      "step": 9750
    },
    {
      "epoch": 4.55,
      "learning_rate": 8.88888888888889e-06,
      "loss": 1.5756,
      "step": 9800
    },
    {
      "epoch": 4.58,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.5866,
      "step": 9850
    },
    {
      "epoch": 4.6,
      "learning_rate": 4.444444444444445e-06,
      "loss": 1.5703,
      "step": 9900
    },
    {
      "epoch": 4.62,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 1.5773,
      "step": 9950
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0,
      "loss": 1.5882,
      "step": 10000
    },
    {
      "epoch": 4.65,
      "eval_loss": 1.5537059307098389,
      "eval_runtime": 104.9822,
      "eval_samples_per_second": 1726.959,
      "eval_steps_per_second": 6.754,
      "step": 10000
    },
    {
      "epoch": 4.65,
      "step": 10000,
      "total_flos": 1.685551202992128e+17,
      "train_loss": 0.5719003509521484,
      "train_runtime": 13336.4941,
      "train_samples_per_second": 1535.636,
      "train_steps_per_second": 0.75
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 5,
  "total_flos": 1.685551202992128e+17,
  "trial_name": null,
  "trial_params": null
}