{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0000058823875435,
  "eval_steps": 10000,
  "global_step": 170000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.848,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.7223,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6764,
      "step": 1500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.7175,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.7574,
      "step": 2500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.7264,
      "step": 3000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.663,
      "step": 3500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.6491,
      "step": 4000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.6539,
      "step": 4500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.6336,
      "step": 5000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.714,
      "step": 5500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6978,
      "step": 6000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6446,
      "step": 6500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6985,
      "step": 7000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.717,
      "step": 7500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.665,
      "step": 8000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.6201,
      "step": 8500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.6889,
      "step": 9000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.6772,
      "step": 9500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.677,
      "step": 10000
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.0160539150238037,
      "eval_runtime": 10760.1771,
      "eval_samples_per_second": 1.975,
      "eval_steps_per_second": 1.975,
      "step": 10000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.6959,
      "step": 10500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.6537,
      "step": 11000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.646,
      "step": 11500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.6385,
      "step": 12000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7758,
      "step": 12500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.6346,
      "step": 13000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.6672,
      "step": 13500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.6466,
      "step": 14000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.6491,
      "step": 14500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.6354,
      "step": 15000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.6093,
      "step": 15500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.6614,
      "step": 16000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.6479,
      "step": 16500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.6402,
      "step": 17000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.6736,
      "step": 17500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.7083,
      "step": 18000
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.5751,
      "step": 18500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.7049,
      "step": 19000
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.6079,
      "step": 19500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.6031,
      "step": 20000
    },
    {
      "epoch": 0.12,
      "eval_loss": 0.9962247014045715,
      "eval_runtime": 10758.8023,
      "eval_samples_per_second": 1.975,
      "eval_steps_per_second": 1.975,
      "step": 20000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.6583,
      "step": 20500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.6182,
      "step": 21000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.6299,
      "step": 21500
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.6448,
      "step": 22000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.6013,
      "step": 22500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.6863,
      "step": 23000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.6656,
      "step": 23500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.6429,
      "step": 24000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.6574,
      "step": 24500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6068,
      "step": 25000
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.608,
      "step": 25500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.5827,
      "step": 26000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.5467,
      "step": 26500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.5671,
      "step": 27000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.5771,
      "step": 27500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.5697,
      "step": 28000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.5959,
      "step": 28500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.6184,
      "step": 29000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.5886,
      "step": 29500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.6198,
      "step": 30000
    },
    {
      "epoch": 0.18,
      "eval_loss": 0.9876086115837097,
      "eval_runtime": 4361.4057,
      "eval_samples_per_second": 4.872,
      "eval_steps_per_second": 4.872,
      "step": 30000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.6259,
      "step": 30500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.531,
      "step": 31000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.6404,
      "step": 31500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.5938,
      "step": 32000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.6468,
      "step": 32500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.5516,
      "step": 33000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.5667,
      "step": 33500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.5937,
      "step": 34000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.554,
      "step": 34500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.6059,
      "step": 35000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.6047,
      "step": 35500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.6003,
      "step": 36000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.5939,
      "step": 36500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.6079,
      "step": 37000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5879,
      "step": 37500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5627,
      "step": 38000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.5913,
      "step": 38500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.5924,
      "step": 39000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.541,
      "step": 39500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.5684,
      "step": 40000
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.9882351160049438,
      "eval_runtime": 4362.1091,
      "eval_samples_per_second": 4.871,
      "eval_steps_per_second": 4.871,
      "step": 40000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.6912,
      "step": 40500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.5589,
      "step": 41000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.5529,
      "step": 41500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 2.6136,
      "step": 42000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 2.5734,
      "step": 42500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 2.5784,
      "step": 43000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.571,
      "step": 43500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.5876,
      "step": 44000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.5619,
      "step": 44500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.5827,
      "step": 45000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.5261,
      "step": 45500
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.5892,
      "step": 46000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.5985,
      "step": 46500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.5743,
      "step": 47000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.5872,
      "step": 47500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.631,
      "step": 48000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5579,
      "step": 48500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5076,
      "step": 49000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5812,
      "step": 49500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5464,
      "step": 50000
    },
    {
      "epoch": 0.29,
      "eval_loss": 0.9824422597885132,
      "eval_runtime": 4360.8255,
      "eval_samples_per_second": 4.873,
      "eval_steps_per_second": 4.873,
      "step": 50000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 2.5652,
      "step": 50500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 2.6049,
      "step": 51000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 2.5393,
      "step": 51500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.567,
      "step": 52000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.6241,
      "step": 52500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.5549,
      "step": 53000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.5779,
      "step": 53500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.5542,
      "step": 54000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.5893,
      "step": 54500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.5856,
      "step": 55000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 2.6168,
      "step": 55500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 2.537,
      "step": 56000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 2.4988,
      "step": 56500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.5916,
      "step": 57000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.5199,
      "step": 57500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.5634,
      "step": 58000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.5705,
      "step": 58500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.5698,
      "step": 59000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.5691,
      "step": 59500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.5616,
      "step": 60000
    },
    {
      "epoch": 0.35,
      "eval_loss": 0.982897162437439,
      "eval_runtime": 4362.1163,
      "eval_samples_per_second": 4.871,
      "eval_steps_per_second": 4.871,
      "step": 60000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5571,
      "step": 60500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5538,
      "step": 61000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5666,
      "step": 61500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5532,
      "step": 62000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 2.5578,
      "step": 62500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 2.5467,
      "step": 63000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 2.5936,
      "step": 63500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 2.5476,
      "step": 64000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 2.584,
      "step": 64500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 2.4837,
      "step": 65000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.5666,
      "step": 65500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.5333,
      "step": 66000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.4762,
      "step": 66500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.5221,
      "step": 67000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.5362,
      "step": 67500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.5554,
      "step": 68000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.5525,
      "step": 68500
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 2.6418,
      "step": 69000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 2.5773,
      "step": 69500
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 2.4553,
      "step": 70000
    },
    {
      "epoch": 0.41,
      "eval_loss": 0.9774429202079773,
      "eval_runtime": 4360.3352,
      "eval_samples_per_second": 4.873,
      "eval_steps_per_second": 4.873,
      "step": 70000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 2.5563,
      "step": 70500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.5383,
      "step": 71000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.569,
      "step": 71500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.5254,
      "step": 72000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.5403,
      "step": 72500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.5346,
      "step": 73000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.5149,
      "step": 73500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.5542,
      "step": 74000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4683,
      "step": 74500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.5426,
      "step": 75000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.5678,
      "step": 75500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 2.5233,
      "step": 76000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 2.5101,
      "step": 76500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 2.5563,
      "step": 77000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.4892,
      "step": 77500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.5376,
      "step": 78000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.5388,
      "step": 78500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.6034,
      "step": 79000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 2.5005,
      "step": 79500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 2.5341,
      "step": 80000
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.9903130531311035,
      "eval_runtime": 4360.6192,
      "eval_samples_per_second": 4.873,
      "eval_steps_per_second": 4.873,
      "step": 80000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 2.524,
      "step": 80500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.5629,
      "step": 81000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.5062,
      "step": 81500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.5454,
      "step": 82000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.5476,
      "step": 82500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.5474,
      "step": 83000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.5022,
      "step": 83500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.5171,
      "step": 84000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.5552,
      "step": 84500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.5438,
      "step": 85000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.5372,
      "step": 85500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.5573,
      "step": 86000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.529,
      "step": 86500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.5663,
      "step": 87000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.6346,
      "step": 87500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 2.5278,
      "step": 88000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 2.3625,
      "step": 88500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 2.3439,
      "step": 89000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 2.3465,
      "step": 89500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 2.3382,
      "step": 90000
    },
    {
      "epoch": 0.53,
      "eval_loss": 2.6655304431915283,
      "eval_runtime": 4818.1263,
      "eval_samples_per_second": 4.41,
      "eval_steps_per_second": 4.41,
      "step": 90000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 2.3589,
      "step": 90500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.3548,
      "step": 91000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.3523,
      "step": 91500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.3466,
      "step": 92000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.3472,
      "step": 92500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 2.3599,
      "step": 93000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 2.3891,
      "step": 93500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 2.3451,
      "step": 94000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.3753,
      "step": 94500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.3492,
      "step": 95000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.315,
      "step": 95500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.361,
      "step": 96000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 2.3837,
      "step": 96500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 2.3445,
      "step": 97000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 2.349,
      "step": 97500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.3372,
      "step": 98000
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.3443,
      "step": 98500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.3264,
      "step": 99000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 2.3284,
      "step": 99500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 2.364,
      "step": 100000
    },
    {
      "epoch": 0.59,
      "eval_loss": 2.6744492053985596,
      "eval_runtime": 4817.3407,
      "eval_samples_per_second": 4.411,
      "eval_steps_per_second": 4.411,
      "step": 100000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 2.3644,
      "step": 100500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 2.3559,
      "step": 101000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.3435,
      "step": 101500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.3936,
      "step": 102000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.3371,
      "step": 102500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 2.3501,
      "step": 103000
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 2.3649,
      "step": 103500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 2.3642,
      "step": 104000
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 2.3534,
      "step": 104500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.3466,
      "step": 105000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.2974,
      "step": 105500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.3481,
      "step": 106000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 2.3419,
      "step": 106500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 2.3576,
      "step": 107000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 2.3623,
      "step": 107500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.3495,
      "step": 108000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.3712,
      "step": 108500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.3906,
      "step": 109000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.4141,
      "step": 109500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 2.3699,
      "step": 110000
    },
    {
      "epoch": 0.65,
      "eval_loss": 2.673431634902954,
      "eval_runtime": 4815.7605,
      "eval_samples_per_second": 4.413,
      "eval_steps_per_second": 4.413,
      "step": 110000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 2.3651,
      "step": 110500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 2.3447,
      "step": 111000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3671,
      "step": 111500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.356,
      "step": 112000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3909,
      "step": 112500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3871,
      "step": 113000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 2.3786,
      "step": 113500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 2.3473,
      "step": 114000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 2.3424,
      "step": 114500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 2.3396,
      "step": 115000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 2.3395,
      "step": 115500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 2.3115,
      "step": 116000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 2.3832,
      "step": 116500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 2.3606,
      "step": 117000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 2.3634,
      "step": 117500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 2.365,
      "step": 118000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.3456,
      "step": 118500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.3678,
      "step": 119000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.3941,
      "step": 119500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 2.3415,
      "step": 120000
    },
    {
      "epoch": 0.71,
      "eval_loss": 2.6743311882019043,
      "eval_runtime": 4816.0272,
      "eval_samples_per_second": 4.412,
      "eval_steps_per_second": 4.412,
      "step": 120000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 2.3634,
      "step": 120500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 2.3707,
      "step": 121000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 2.3635,
      "step": 121500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 2.351,
      "step": 122000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 2.3491,
      "step": 122500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 2.3578,
      "step": 123000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3551,
      "step": 123500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3329,
      "step": 124000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3587,
      "step": 124500
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.3825,
      "step": 125000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.3499,
      "step": 125500
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.3618,
      "step": 126000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.3611,
      "step": 126500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 2.3519,
      "step": 127000
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 2.3942,
      "step": 127500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 2.3654,
      "step": 128000
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.34,
      "step": 128500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.3108,
      "step": 129000
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.378,
      "step": 129500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.356,
      "step": 130000
    },
    {
      "epoch": 0.76,
      "eval_loss": 2.6768763065338135,
      "eval_runtime": 4816.6925,
      "eval_samples_per_second": 4.412,
      "eval_steps_per_second": 4.412,
      "step": 130000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 2.3822,
      "step": 130500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 2.3459,
      "step": 131000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 2.3586,
      "step": 131500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 2.3454,
      "step": 132000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 2.3247,
      "step": 132500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 2.4073,
      "step": 133000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 2.3414,
      "step": 133500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 2.3574,
      "step": 134000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 2.3388,
      "step": 134500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 2.3689,
      "step": 135000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3185,
      "step": 135500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.337,
      "step": 136000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3462,
      "step": 136500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 2.3661,
      "step": 137000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 2.3596,
      "step": 137500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 2.3333,
      "step": 138000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 2.3709,
      "step": 138500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 2.3717,
      "step": 139000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 2.3709,
      "step": 139500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 2.3056,
      "step": 140000
    },
    {
      "epoch": 0.82,
      "eval_loss": 2.681723117828369,
      "eval_runtime": 4815.0048,
      "eval_samples_per_second": 4.413,
      "eval_steps_per_second": 4.413,
      "step": 140000
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 2.3498,
      "step": 140500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 2.372,
      "step": 141000
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 2.3824,
      "step": 141500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.3486,
      "step": 142000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.3141,
      "step": 142500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.3696,
      "step": 143000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.3762,
      "step": 143500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 2.3766,
      "step": 144000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 2.3511,
      "step": 144500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 2.3493,
      "step": 145000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.3244,
      "step": 145500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.3146,
      "step": 146000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.3676,
      "step": 146500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.3497,
      "step": 147000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 2.375,
      "step": 147500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 2.2942,
      "step": 148000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 2.384,
      "step": 148500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.3533,
      "step": 149000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.3455,
      "step": 149500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.3398,
      "step": 150000
    },
    {
      "epoch": 0.88,
      "eval_loss": 2.672765016555786,
      "eval_runtime": 4814.8179,
      "eval_samples_per_second": 4.413,
      "eval_steps_per_second": 4.413,
      "step": 150000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.318,
      "step": 150500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.3638,
      "step": 151000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.3714,
      "step": 151500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.334,
      "step": 152000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 2.3208,
      "step": 152500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 2.3684,
      "step": 153000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 2.3963,
      "step": 153500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.3087,
      "step": 154000
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.3193,
      "step": 154500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.3295,
      "step": 155000
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.3711,
      "step": 155500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 2.3697,
      "step": 156000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 2.3053,
      "step": 156500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 2.3356,
      "step": 157000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 2.3786,
      "step": 157500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 2.3693,
      "step": 158000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 2.3334,
      "step": 158500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 2.3657,
      "step": 159000
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 2.3242,
      "step": 159500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 2.3508,
      "step": 160000
    },
    {
      "epoch": 0.94,
      "eval_loss": 2.671438694000244,
      "eval_runtime": 4816.9535,
      "eval_samples_per_second": 4.412,
      "eval_steps_per_second": 4.412,
      "step": 160000
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 2.345,
      "step": 160500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.3409,
      "step": 161000
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.3205,
      "step": 161500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.3881,
      "step": 162000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 2.3543,
      "step": 162500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 2.3467,
      "step": 163000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 2.3788,
      "step": 163500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 2.359,
      "step": 164000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 2.339,
      "step": 164500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 2.3557,
      "step": 165000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 2.3321,
      "step": 165500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 2.4048,
      "step": 166000
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 2.3428,
      "step": 166500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 2.3249,
      "step": 167000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.3743,
      "step": 167500
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.3225,
      "step": 168000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.3038,
      "step": 168500
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.3347,
      "step": 169000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 2.3798,
      "step": 169500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 2.3568,
      "step": 170000
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.66947865486145,
      "eval_runtime": 4817.1455,
      "eval_samples_per_second": 4.411,
      "eval_steps_per_second": 4.411,
      "step": 170000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1699990,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "total_flos": 1.772080615538583e+18,
  "trial_name": null,
  "trial_params": null
}