{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.235449930100802,
  "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": 1.9334,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 1.5585,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-05,
      "loss": 1.395,
      "step": 150
    },
    {
      "epoch": 0.09,
      "learning_rate": 8e-05,
      "loss": 1.3066,
      "step": 200
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.2233,
      "step": 250
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.1738,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00014,
      "loss": 1.1226,
      "step": 350
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016,
      "loss": 1.0725,
      "step": 400
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018,
      "loss": 1.0292,
      "step": 450
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.9738,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00022000000000000003,
      "loss": 0.945,
      "step": 550
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00024,
      "loss": 0.909,
      "step": 600
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.8708,
      "step": 650
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00028,
      "loss": 0.8421,
      "step": 700
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.7962,
      "step": 750
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00032,
      "loss": 0.9506,
      "step": 800
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00034,
      "loss": 0.9377,
      "step": 850
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00036,
      "loss": 0.9104,
      "step": 900
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00038,
      "loss": 0.8926,
      "step": 950
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0004,
      "loss": 0.8887,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.1447917222976685,
      "eval_runtime": 449.5318,
      "eval_samples_per_second": 403.309,
      "eval_steps_per_second": 3.152,
      "step": 1000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003977777777777778,
      "loss": 0.8758,
      "step": 1050
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039555555555555557,
      "loss": 0.8647,
      "step": 1100
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003933333333333333,
      "loss": 0.8493,
      "step": 1150
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003911111111111111,
      "loss": 0.8352,
      "step": 1200
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003888888888888889,
      "loss": 0.8327,
      "step": 1250
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00038666666666666667,
      "loss": 0.8237,
      "step": 1300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00038444444444444447,
      "loss": 0.8107,
      "step": 1350
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003822222222222223,
      "loss": 0.8036,
      "step": 1400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00038,
      "loss": 0.7962,
      "step": 1450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00037777777777777777,
      "loss": 0.7826,
      "step": 1500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00037555555555555557,
      "loss": 0.767,
      "step": 1550
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003733333333333334,
      "loss": 0.7636,
      "step": 1600
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003711111111111111,
      "loss": 0.7588,
      "step": 1650
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003688888888888889,
      "loss": 0.7497,
      "step": 1700
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00036666666666666667,
      "loss": 0.7306,
      "step": 1750
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00036444444444444447,
      "loss": 0.7448,
      "step": 1800
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003622222222222222,
      "loss": 0.7401,
      "step": 1850
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00036,
      "loss": 0.7257,
      "step": 1900
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003577777777777778,
      "loss": 0.7148,
      "step": 1950
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00035555555555555557,
      "loss": 0.7197,
      "step": 2000
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.1351628303527832,
      "eval_runtime": 478.0275,
      "eval_samples_per_second": 379.267,
      "eval_steps_per_second": 5.926,
      "step": 2000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003533333333333333,
      "loss": 0.7227,
      "step": 2050
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003511111111111111,
      "loss": 0.7212,
      "step": 2100
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003488888888888889,
      "loss": 0.7105,
      "step": 2150
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00034666666666666667,
      "loss": 0.704,
      "step": 2200
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003444444444444445,
      "loss": 0.71,
      "step": 2250
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003422222222222222,
      "loss": 0.706,
      "step": 2300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00034,
      "loss": 0.6928,
      "step": 2350
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00033777777777777777,
      "loss": 0.6959,
      "step": 2400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003355555555555556,
      "loss": 0.6872,
      "step": 2450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003333333333333334,
      "loss": 0.6824,
      "step": 2500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003311111111111111,
      "loss": 0.6793,
      "step": 2550
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00032888888888888887,
      "loss": 0.6736,
      "step": 2600
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003266666666666667,
      "loss": 0.6768,
      "step": 2650
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003244444444444445,
      "loss": 0.6656,
      "step": 2700
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003222222222222222,
      "loss": 0.666,
      "step": 2750
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00032,
      "loss": 0.6657,
      "step": 2800
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003177777777777778,
      "loss": 0.671,
      "step": 2850
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003155555555555556,
      "loss": 0.6611,
      "step": 2900
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003133333333333333,
      "loss": 0.6607,
      "step": 2950
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003111111111111111,
      "loss": 0.6601,
      "step": 3000
    },
    {
      "epoch": 0.71,
      "eval_loss": 1.107571005821228,
      "eval_runtime": 467.6904,
      "eval_samples_per_second": 387.65,
      "eval_steps_per_second": 6.057,
      "step": 3000
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00030888888888888893,
      "loss": 0.6436,
      "step": 3050
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003066666666666667,
      "loss": 0.6536,
      "step": 3100
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003044444444444444,
      "loss": 0.646,
      "step": 3150
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003022222222222222,
      "loss": 0.6457,
      "step": 3200
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.6328,
      "step": 3250
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002977777777777778,
      "loss": 0.6441,
      "step": 3300
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002955555555555556,
      "loss": 0.6421,
      "step": 3350
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002933333333333333,
      "loss": 0.6297,
      "step": 3400
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00029111111111111113,
      "loss": 0.6284,
      "step": 3450
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002888888888888889,
      "loss": 0.6298,
      "step": 3500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002866666666666667,
      "loss": 0.6232,
      "step": 3550
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002844444444444445,
      "loss": 0.622,
      "step": 3600
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00028222222222222223,
      "loss": 0.6159,
      "step": 3650
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00028,
      "loss": 0.6129,
      "step": 3700
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.6216,
      "step": 3750
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002755555555555556,
      "loss": 0.615,
      "step": 3800
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00027333333333333333,
      "loss": 0.6143,
      "step": 3850
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00027111111111111113,
      "loss": 0.6116,
      "step": 3900
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00026888888888888893,
      "loss": 0.6144,
      "step": 3950
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.6122,
      "step": 4000
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.106411337852478,
      "eval_runtime": 475.9492,
      "eval_samples_per_second": 380.923,
      "eval_steps_per_second": 5.952,
      "step": 4000
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00026444444444444443,
      "loss": 0.6104,
      "step": 4050
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00026222222222222223,
      "loss": 0.6107,
      "step": 4100
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.6047,
      "step": 4150
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00025777777777777783,
      "loss": 0.6034,
      "step": 4200
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00025555555555555553,
      "loss": 0.5928,
      "step": 4250
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00025333333333333333,
      "loss": 0.596,
      "step": 4300
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00025111111111111113,
      "loss": 0.5994,
      "step": 4350
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002488888888888889,
      "loss": 0.5891,
      "step": 4400
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002466666666666667,
      "loss": 0.5974,
      "step": 4450
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002444444444444445,
      "loss": 0.5908,
      "step": 4500
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002422222222222222,
      "loss": 0.591,
      "step": 4550
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00024,
      "loss": 0.5872,
      "step": 4600
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00023777777777777778,
      "loss": 0.5827,
      "step": 4650
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00023555555555555558,
      "loss": 0.5748,
      "step": 4700
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00023333333333333336,
      "loss": 0.5822,
      "step": 4750
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002311111111111111,
      "loss": 0.5831,
      "step": 4800
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00022888888888888888,
      "loss": 0.5772,
      "step": 4850
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00022666666666666668,
      "loss": 0.5823,
      "step": 4900
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00022444444444444446,
      "loss": 0.5803,
      "step": 4950
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00022222222222222223,
      "loss": 0.5805,
      "step": 5000
    },
    {
      "epoch": 1.94,
      "eval_loss": 1.084761381149292,
      "eval_runtime": 462.6876,
      "eval_samples_per_second": 391.841,
      "eval_steps_per_second": 6.123,
      "step": 5000
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00022000000000000003,
      "loss": 0.5696,
      "step": 5050
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00021777777777777778,
      "loss": 0.5714,
      "step": 5100
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00021555555555555556,
      "loss": 0.5607,
      "step": 5150
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00021333333333333333,
      "loss": 0.5736,
      "step": 5200
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00021111111111111113,
      "loss": 0.5684,
      "step": 5250
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002088888888888889,
      "loss": 0.5604,
      "step": 5300
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00020666666666666668,
      "loss": 0.5551,
      "step": 5350
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00020444444444444443,
      "loss": 0.5666,
      "step": 5400
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00020222222222222223,
      "loss": 0.5561,
      "step": 5450
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 0.5655,
      "step": 5500
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00019777777777777778,
      "loss": 0.5601,
      "step": 5550
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00019555555555555556,
      "loss": 0.5562,
      "step": 5600
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.555,
      "step": 5650
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00019111111111111114,
      "loss": 0.5541,
      "step": 5700
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.5508,
      "step": 5750
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.5574,
      "step": 5800
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.5507,
      "step": 5850
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018222222222222224,
      "loss": 0.5539,
      "step": 5900
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018,
      "loss": 0.5472,
      "step": 5950
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.5472,
      "step": 6000
    },
    {
      "epoch": 2.47,
      "eval_loss": 1.0653705596923828,
      "eval_runtime": 480.2201,
      "eval_samples_per_second": 377.535,
      "eval_steps_per_second": 5.899,
      "step": 6000
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00017555555555555556,
      "loss": 0.5346,
      "step": 6050
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.547,
      "step": 6100
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001711111111111111,
      "loss": 0.5392,
      "step": 6150
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00016888888888888889,
      "loss": 0.5384,
      "step": 6200
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.5377,
      "step": 6250
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00016444444444444444,
      "loss": 0.5386,
      "step": 6300
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.5332,
      "step": 6350
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00016,
      "loss": 0.5372,
      "step": 6400
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0001577777777777778,
      "loss": 0.5346,
      "step": 6450
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.5364,
      "step": 6500
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.5317,
      "step": 6550
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.5302,
      "step": 6600
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001488888888888889,
      "loss": 0.5294,
      "step": 6650
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.531,
      "step": 6700
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.5285,
      "step": 6750
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00014222222222222224,
      "loss": 0.5271,
      "step": 6800
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00014,
      "loss": 0.4382,
      "step": 6850
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001377777777777778,
      "loss": 0.4379,
      "step": 6900
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00013555555555555556,
      "loss": 0.4339,
      "step": 6950
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.4342,
      "step": 7000
    },
    {
      "epoch": 3.09,
      "eval_loss": 1.108401894569397,
      "eval_runtime": 470.4667,
      "eval_samples_per_second": 385.362,
      "eval_steps_per_second": 6.022,
      "step": 7000
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00013111111111111111,
      "loss": 0.5279,
      "step": 7050
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00012888888888888892,
      "loss": 0.5269,
      "step": 7100
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.525,
      "step": 7150
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00012444444444444444,
      "loss": 0.5239,
      "step": 7200
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.5251,
      "step": 7250
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00012,
      "loss": 0.5199,
      "step": 7300
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00011777777777777779,
      "loss": 0.5193,
      "step": 7350
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.5193,
      "step": 7400
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.5154,
      "step": 7450
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.5173,
      "step": 7500
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00010888888888888889,
      "loss": 0.5152,
      "step": 7550
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.5119,
      "step": 7600
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00010444444444444445,
      "loss": 0.512,
      "step": 7650
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00010222222222222222,
      "loss": 0.512,
      "step": 7700
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0001,
      "loss": 0.5103,
      "step": 7750
    },
    {
      "epoch": 3.47,
      "learning_rate": 9.777777777777778e-05,
      "loss": 0.5118,
      "step": 7800
    },
    {
      "epoch": 3.49,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.5081,
      "step": 7850
    },
    {
      "epoch": 3.52,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.5088,
      "step": 7900
    },
    {
      "epoch": 3.54,
      "learning_rate": 9.111111111111112e-05,
      "loss": 0.5043,
      "step": 7950
    },
    {
      "epoch": 3.57,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.5045,
      "step": 8000
    },
    {
      "epoch": 3.57,
      "eval_loss": 1.057867169380188,
      "eval_runtime": 457.9261,
      "eval_samples_per_second": 395.915,
      "eval_steps_per_second": 6.187,
      "step": 8000
    },
    {
      "epoch": 3.59,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.504,
      "step": 8050
    },
    {
      "epoch": 3.61,
      "learning_rate": 8.444444444444444e-05,
      "loss": 0.503,
      "step": 8100
    },
    {
      "epoch": 3.64,
      "learning_rate": 8.222222222222222e-05,
      "loss": 0.5042,
      "step": 8150
    },
    {
      "epoch": 3.66,
      "learning_rate": 8e-05,
      "loss": 0.5023,
      "step": 8200
    },
    {
      "epoch": 3.68,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.5,
      "step": 8250
    },
    {
      "epoch": 3.71,
      "learning_rate": 7.555555555555556e-05,
      "loss": 0.5002,
      "step": 8300
    },
    {
      "epoch": 3.73,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.4991,
      "step": 8350
    },
    {
      "epoch": 3.75,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.5,
      "step": 8400
    },
    {
      "epoch": 3.78,
      "learning_rate": 6.88888888888889e-05,
      "loss": 0.4978,
      "step": 8450
    },
    {
      "epoch": 3.8,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.4971,
      "step": 8500
    },
    {
      "epoch": 3.82,
      "learning_rate": 6.444444444444446e-05,
      "loss": 0.4931,
      "step": 8550
    },
    {
      "epoch": 3.85,
      "learning_rate": 6.222222222222222e-05,
      "loss": 0.4989,
      "step": 8600
    },
    {
      "epoch": 3.87,
      "learning_rate": 6e-05,
      "loss": 0.4955,
      "step": 8650
    },
    {
      "epoch": 3.89,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 0.4933,
      "step": 8700
    },
    {
      "epoch": 3.92,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.4931,
      "step": 8750
    },
    {
      "epoch": 3.94,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.4899,
      "step": 8800
    },
    {
      "epoch": 3.97,
      "learning_rate": 5.111111111111111e-05,
      "loss": 0.4903,
      "step": 8850
    },
    {
      "epoch": 3.99,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.493,
      "step": 8900
    },
    {
      "epoch": 4.01,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.4969,
      "step": 8950
    },
    {
      "epoch": 4.04,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.4863,
      "step": 9000
    },
    {
      "epoch": 4.04,
      "eval_loss": 1.0444583892822266,
      "eval_runtime": 458.1475,
      "eval_samples_per_second": 395.724,
      "eval_steps_per_second": 6.184,
      "step": 9000
    },
    {
      "epoch": 4.06,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.4854,
      "step": 9050
    },
    {
      "epoch": 4.08,
      "learning_rate": 4e-05,
      "loss": 0.4869,
      "step": 9100
    },
    {
      "epoch": 4.11,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.4883,
      "step": 9150
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.4849,
      "step": 9200
    },
    {
      "epoch": 4.15,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4839,
      "step": 9250
    },
    {
      "epoch": 4.18,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.4833,
      "step": 9300
    },
    {
      "epoch": 4.2,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.4856,
      "step": 9350
    },
    {
      "epoch": 4.22,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.4835,
      "step": 9400
    },
    {
      "epoch": 4.25,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.4809,
      "step": 9450
    },
    {
      "epoch": 4.27,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.479,
      "step": 9500
    },
    {
      "epoch": 4.02,
      "learning_rate": 2e-05,
      "loss": 0.4785,
      "step": 9550
    },
    {
      "epoch": 4.05,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.4773,
      "step": 9600
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.4782,
      "step": 9650
    },
    {
      "epoch": 4.09,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4785,
      "step": 9700
    },
    {
      "epoch": 4.12,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.4799,
      "step": 9750
    },
    {
      "epoch": 4.14,
      "learning_rate": 8.88888888888889e-06,
      "loss": 0.4781,
      "step": 9800
    },
    {
      "epoch": 4.16,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4787,
      "step": 9850
    },
    {
      "epoch": 4.19,
      "learning_rate": 4.444444444444445e-06,
      "loss": 0.4795,
      "step": 9900
    },
    {
      "epoch": 4.21,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.4788,
      "step": 9950
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0,
      "loss": 0.4788,
      "step": 10000
    },
    {
      "epoch": 4.24,
      "eval_loss": 1.0352369546890259,
      "eval_runtime": 476.9291,
      "eval_samples_per_second": 380.14,
      "eval_steps_per_second": 5.94,
      "step": 10000
    },
    {
      "epoch": 4.24,
      "step": 10000,
      "total_flos": 6.740919900404122e+17,
      "train_loss": 0.023931974029541017,
      "train_runtime": 6473.1334,
      "train_samples_per_second": 3163.846,
      "train_steps_per_second": 1.545
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 5,
  "total_flos": 6.740919900404122e+17,
  "trial_name": null,
  "trial_params": null
}