{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "global_step": 32000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.5625e-05,
      "loss": 5.407,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.125e-05,
      "loss": 5.1931,
      "step": 200
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.6875e-05,
      "loss": 4.7863,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-05,
      "loss": 4.2329,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.8125e-05,
      "loss": 3.5639,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.375e-05,
      "loss": 3.092,
      "step": 600
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000109375,
      "loss": 2.9092,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000125,
      "loss": 2.7752,
      "step": 800
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014062500000000002,
      "loss": 2.7062,
      "step": 900
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015625,
      "loss": 2.6179,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000171875,
      "loss": 2.6036,
      "step": 1100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001875,
      "loss": 2.5718,
      "step": 1200
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00020312500000000002,
      "loss": 2.5639,
      "step": 1300
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00021875,
      "loss": 2.5482,
      "step": 1400
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000234375,
      "loss": 2.5276,
      "step": 1500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00025,
      "loss": 2.4814,
      "step": 1600
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000265625,
      "loss": 2.4904,
      "step": 1700
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00028125000000000003,
      "loss": 2.5022,
      "step": 1800
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000296875,
      "loss": 2.4521,
      "step": 1900
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003125,
      "loss": 2.45,
      "step": 2000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000328125,
      "loss": 2.4725,
      "step": 2100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00034375,
      "loss": 2.4415,
      "step": 2200
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000359375,
      "loss": 2.443,
      "step": 2300
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000375,
      "loss": 2.4593,
      "step": 2400
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000390625,
      "loss": 2.4487,
      "step": 2500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00040625000000000004,
      "loss": 2.4259,
      "step": 2600
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000421875,
      "loss": 2.4278,
      "step": 2700
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004375,
      "loss": 2.4052,
      "step": 2800
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000453125,
      "loss": 2.4142,
      "step": 2900
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00046875,
      "loss": 2.4338,
      "step": 3000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000484375,
      "loss": 2.443,
      "step": 3100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0005,
      "loss": 2.4501,
      "step": 3200
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000515625,
      "loss": 2.4415,
      "step": 3300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00053125,
      "loss": 2.4484,
      "step": 3400
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000546875,
      "loss": 2.4132,
      "step": 3500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0005625000000000001,
      "loss": 2.4372,
      "step": 3600
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000578125,
      "loss": 2.3958,
      "step": 3700
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00059375,
      "loss": 2.407,
      "step": 3800
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000609375,
      "loss": 2.4142,
      "step": 3900
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000625,
      "loss": 2.4185,
      "step": 4000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000640625,
      "loss": 2.4373,
      "step": 4100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00065625,
      "loss": 2.4092,
      "step": 4200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0006718750000000001,
      "loss": 2.4009,
      "step": 4300
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0006875,
      "loss": 2.4403,
      "step": 4400
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000703125,
      "loss": 2.4071,
      "step": 4500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00071875,
      "loss": 2.4034,
      "step": 4600
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000734375,
      "loss": 2.4111,
      "step": 4700
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00075,
      "loss": 2.4132,
      "step": 4800
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000765625,
      "loss": 2.4142,
      "step": 4900
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00078125,
      "loss": 2.4,
      "step": 5000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007968750000000001,
      "loss": 2.4329,
      "step": 5100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0008125000000000001,
      "loss": 2.4136,
      "step": 5200
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000828125,
      "loss": 2.4137,
      "step": 5300
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00084375,
      "loss": 2.4154,
      "step": 5400
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000859375,
      "loss": 2.4205,
      "step": 5500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000875,
      "loss": 2.4154,
      "step": 5600
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000890625,
      "loss": 2.4248,
      "step": 5700
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00090625,
      "loss": 2.4149,
      "step": 5800
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009218750000000001,
      "loss": 2.4124,
      "step": 5900
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009375,
      "loss": 2.4105,
      "step": 6000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000953125,
      "loss": 2.4132,
      "step": 6100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00096875,
      "loss": 2.4079,
      "step": 6200
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000984375,
      "loss": 2.4307,
      "step": 6300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 2.4311,
      "step": 6400
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.5866917775886576,
      "eval_loss": 2.239835500717163,
      "eval_runtime": 7535.276,
      "eval_samples_per_second": 43.51,
      "eval_steps_per_second": 2.719,
      "step": 6400
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 8.359,
      "step": 6500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 8.1564,
      "step": 6600
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 8.1469,
      "step": 6700
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.1211,
      "step": 6800
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.0988,
      "step": 6900
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.0913,
      "step": 7000
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.0833,
      "step": 7100
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.0939,
      "step": 7200
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001,
      "loss": 8.4426,
      "step": 7300
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.3,
      "step": 7400
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.1645,
      "step": 7500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.108,
      "step": 7600
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.0965,
      "step": 7700
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.0708,
      "step": 7800
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.0746,
      "step": 7900
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 8.0687,
      "step": 8000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.0715,
      "step": 8100
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.0598,
      "step": 8200
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.053,
      "step": 8300
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.0404,
      "step": 8400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.0718,
      "step": 8500
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 8.0426,
      "step": 8600
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.032,
      "step": 8700
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.0338,
      "step": 8800
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.0468,
      "step": 8900
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.0502,
      "step": 9000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.0691,
      "step": 9100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001,
      "loss": 8.0611,
      "step": 9200
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0346,
      "step": 9300
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0438,
      "step": 9400
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0291,
      "step": 9500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0502,
      "step": 9600
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.05,
      "step": 9700
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0522,
      "step": 9800
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 8.0441,
      "step": 9900
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.0455,
      "step": 10000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.0476,
      "step": 10100
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.03,
      "step": 10200
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.0411,
      "step": 10300
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.0654,
      "step": 10400
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 8.0569,
      "step": 10500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0407,
      "step": 10600
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0456,
      "step": 10700
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0497,
      "step": 10800
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0309,
      "step": 10900
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0575,
      "step": 11000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0367,
      "step": 11100
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001,
      "loss": 8.0366,
      "step": 11200
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0422,
      "step": 11300
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0385,
      "step": 11400
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0415,
      "step": 11500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0335,
      "step": 11600
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0523,
      "step": 11700
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 8.0565,
      "step": 11800
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0442,
      "step": 11900
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0478,
      "step": 12000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0319,
      "step": 12100
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0463,
      "step": 12200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0549,
      "step": 12300
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 8.0676,
      "step": 12400
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.0362,
      "step": 12500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.0437,
      "step": 12600
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.0502,
      "step": 12700
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.046,
      "step": 12800
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.032781328733133316,
      "eval_loss": 8.042789459228516,
      "eval_runtime": 7220.6269,
      "eval_samples_per_second": 45.406,
      "eval_steps_per_second": 2.838,
      "step": 12800
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.0474,
      "step": 12900
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.054,
      "step": 13000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001,
      "loss": 8.0506,
      "step": 13100
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0485,
      "step": 13200
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0485,
      "step": 13300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0515,
      "step": 13400
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0295,
      "step": 13500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0456,
      "step": 13600
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 8.0278,
      "step": 13700
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.0358,
      "step": 13800
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.0513,
      "step": 13900
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.0443,
      "step": 14000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.0657,
      "step": 14100
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.0381,
      "step": 14200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 8.047,
      "step": 14300
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0441,
      "step": 14400
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0293,
      "step": 14500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0308,
      "step": 14600
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0353,
      "step": 14700
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0098,
      "step": 14800
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0422,
      "step": 14900
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 8.0427,
      "step": 15000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.0323,
      "step": 15100
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.035,
      "step": 15200
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.0574,
      "step": 15300
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.0365,
      "step": 15400
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.0341,
      "step": 15500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001,
      "loss": 8.0484,
      "step": 15600
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0409,
      "step": 15700
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0363,
      "step": 15800
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0415,
      "step": 15900
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.043,
      "step": 16000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0307,
      "step": 16100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0179,
      "step": 16200
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 8.0279,
      "step": 16300
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.0552,
      "step": 16400
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.0437,
      "step": 16500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.0356,
      "step": 16600
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.0427,
      "step": 16700
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.0472,
      "step": 16800
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 8.043,
      "step": 16900
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0567,
      "step": 17000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0474,
      "step": 17100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0295,
      "step": 17200
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0364,
      "step": 17300
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0474,
      "step": 17400
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001,
      "loss": 8.0282,
      "step": 17500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0525,
      "step": 17600
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0464,
      "step": 17700
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0516,
      "step": 17800
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0322,
      "step": 17900
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0376,
      "step": 18000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0235,
      "step": 18100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 8.0316,
      "step": 18200
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.0319,
      "step": 18300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.0393,
      "step": 18400
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.0248,
      "step": 18500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.0463,
      "step": 18600
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.024,
      "step": 18700
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 8.0062,
      "step": 18800
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.0302,
      "step": 18900
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.054,
      "step": 19000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.0448,
      "step": 19100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.0465,
      "step": 19200
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.03331597495163198,
      "eval_loss": 8.039088249206543,
      "eval_runtime": 7133.5004,
      "eval_samples_per_second": 45.96,
      "eval_steps_per_second": 2.873,
      "step": 19200
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.043,
      "step": 19300
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.0459,
      "step": 19400
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001,
      "loss": 8.0138,
      "step": 19500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.0321,
      "step": 19600
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.0512,
      "step": 19700
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.0284,
      "step": 19800
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.0347,
      "step": 19900
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.046,
      "step": 20000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 8.0466,
      "step": 20100
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0612,
      "step": 20200
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0392,
      "step": 20300
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0422,
      "step": 20400
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0386,
      "step": 20500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0504,
      "step": 20600
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 8.0483,
      "step": 20700
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0463,
      "step": 20800
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0545,
      "step": 20900
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0491,
      "step": 21000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0336,
      "step": 21100
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0372,
      "step": 21200
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.0405,
      "step": 21300
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001,
      "loss": 8.028,
      "step": 21400
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.0234,
      "step": 21500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.0256,
      "step": 21600
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.028,
      "step": 21700
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.0338,
      "step": 21800
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.0345,
      "step": 21900
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 8.0353,
      "step": 22000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0426,
      "step": 22100
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0318,
      "step": 22200
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0341,
      "step": 22300
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.026,
      "step": 22400
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0333,
      "step": 22500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0265,
      "step": 22600
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 8.0764,
      "step": 22700
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0355,
      "step": 22800
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0472,
      "step": 22900
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0376,
      "step": 23000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0335,
      "step": 23100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0429,
      "step": 23200
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.0431,
      "step": 23300
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0259,
      "step": 23400
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0339,
      "step": 23500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0192,
      "step": 23600
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0515,
      "step": 23700
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0258,
      "step": 23800
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 8.0422,
      "step": 23900
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0326,
      "step": 24000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0392,
      "step": 24100
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0414,
      "step": 24200
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0505,
      "step": 24300
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0267,
      "step": 24400
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0391,
      "step": 24500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 8.0381,
      "step": 24600
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0339,
      "step": 24700
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0448,
      "step": 24800
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0633,
      "step": 24900
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0064,
      "step": 25000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0323,
      "step": 25100
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001,
      "loss": 8.0286,
      "step": 25200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0349,
      "step": 25300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0373,
      "step": 25400
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0447,
      "step": 25500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0302,
      "step": 25600
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.03333073104167396,
      "eval_loss": 8.036836624145508,
      "eval_runtime": 6892.0068,
      "eval_samples_per_second": 47.571,
      "eval_steps_per_second": 2.973,
      "step": 25600
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0132,
      "step": 25700
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0267,
      "step": 25800
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 8.0349,
      "step": 25900
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0377,
      "step": 26000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0409,
      "step": 26100
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0425,
      "step": 26200
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0298,
      "step": 26300
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0544,
      "step": 26400
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 8.0618,
      "step": 26500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0472,
      "step": 26600
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0336,
      "step": 26700
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0259,
      "step": 26800
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0586,
      "step": 26900
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0368,
      "step": 27000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0449,
      "step": 27100
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 8.0363,
      "step": 27200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.0408,
      "step": 27300
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.0384,
      "step": 27400
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.0441,
      "step": 27500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.0367,
      "step": 27600
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.007,
      "step": 27700
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 8.0189,
      "step": 27800
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0445,
      "step": 27900
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0319,
      "step": 28000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0251,
      "step": 28100
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0329,
      "step": 28200
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0335,
      "step": 28300
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 8.0351,
      "step": 28400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0346,
      "step": 28500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0238,
      "step": 28600
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0372,
      "step": 28700
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0329,
      "step": 28800
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0469,
      "step": 28900
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0512,
      "step": 29000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 8.0712,
      "step": 29100
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0281,
      "step": 29200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0215,
      "step": 29300
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0279,
      "step": 29400
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0259,
      "step": 29500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0386,
      "step": 29600
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001,
      "loss": 8.0274,
      "step": 29700
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0392,
      "step": 29800
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0247,
      "step": 29900
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0488,
      "step": 30000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0593,
      "step": 30100
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0317,
      "step": 30200
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0359,
      "step": 30300
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 8.0255,
      "step": 30400
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.0325,
      "step": 30500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.0467,
      "step": 30600
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.0361,
      "step": 30700
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.033,
      "step": 30800
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.033,
      "step": 30900
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 8.0386,
      "step": 31000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0326,
      "step": 31100
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0219,
      "step": 31200
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0468,
      "step": 31300
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0328,
      "step": 31400
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0347,
      "step": 31500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001,
      "loss": 8.0341,
      "step": 31600
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 8.06,
      "step": 31700
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 8.0331,
      "step": 31800
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 8.052,
      "step": 31900
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 8.0273,
      "step": 32000
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.033282358556154815,
      "eval_loss": 8.0352144241333,
      "eval_runtime": 8285.0113,
      "eval_samples_per_second": 39.572,
      "eval_steps_per_second": 2.473,
      "step": 32000
    }
  ],
  "max_steps": 64000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.69245882187776e+17,
  "trial_name": null,
  "trial_params": null
}