{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3099381673356165,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 9.7906,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 7.9188,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 6.8487,
      "step": 150
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 6.0994,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 5.7442,
      "step": 250
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 5.5492,
      "step": 300
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014000000000000001,
      "loss": 5.4021,
      "step": 350
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 5.2486,
      "step": 400
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017999999999999998,
      "loss": 5.128,
      "step": 450
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 5.0186,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00022,
      "loss": 4.9228,
      "step": 550
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00024,
      "loss": 4.8538,
      "step": 600
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00026000000000000003,
      "loss": 4.7268,
      "step": 650
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00028000000000000003,
      "loss": 4.6724,
      "step": 700
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 4.5713,
      "step": 750
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00032,
      "loss": 4.488,
      "step": 800
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00034,
      "loss": 4.4322,
      "step": 850
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00035999999999999997,
      "loss": 4.3735,
      "step": 900
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00038,
      "loss": 4.3239,
      "step": 950
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 4.254,
      "step": 1000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00042,
      "loss": 4.2093,
      "step": 1050
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00044,
      "loss": 4.1751,
      "step": 1100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00046,
      "loss": 4.11,
      "step": 1150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00048,
      "loss": 4.0559,
      "step": 1200
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0005,
      "loss": 4.0179,
      "step": 1250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0005200000000000001,
      "loss": 3.9553,
      "step": 1300
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00054,
      "loss": 3.8982,
      "step": 1350
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0005600000000000001,
      "loss": 3.8803,
      "step": 1400
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00058,
      "loss": 3.865,
      "step": 1450
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0006,
      "loss": 3.8174,
      "step": 1500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00062,
      "loss": 3.8031,
      "step": 1550
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00064,
      "loss": 3.7598,
      "step": 1600
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00066,
      "loss": 3.7252,
      "step": 1650
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00068,
      "loss": 3.715,
      "step": 1700
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0007,
      "loss": 3.6863,
      "step": 1750
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0007199999999999999,
      "loss": 3.6786,
      "step": 1800
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00074,
      "loss": 3.6639,
      "step": 1850
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00076,
      "loss": 3.647,
      "step": 1900
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0007800000000000001,
      "loss": 3.6227,
      "step": 1950
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0008,
      "loss": 3.6005,
      "step": 2000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00082,
      "loss": 3.5824,
      "step": 2050
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00084,
      "loss": 3.5806,
      "step": 2100
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00086,
      "loss": 3.5605,
      "step": 2150
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00088,
      "loss": 3.5325,
      "step": 2200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009000000000000001,
      "loss": 3.5417,
      "step": 2250
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00092,
      "loss": 3.4979,
      "step": 2300
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00094,
      "loss": 3.5149,
      "step": 2350
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00096,
      "loss": 3.4793,
      "step": 2400
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00098,
      "loss": 3.5049,
      "step": 2450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 3.4843,
      "step": 2500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00098,
      "loss": 3.464,
      "step": 2550
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00096,
      "loss": 3.4651,
      "step": 2600
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00094,
      "loss": 3.4353,
      "step": 2650
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00092,
      "loss": 3.4139,
      "step": 2700
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009000000000000001,
      "loss": 3.4013,
      "step": 2750
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00088,
      "loss": 3.3647,
      "step": 2800
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00086,
      "loss": 3.3461,
      "step": 2850
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00084,
      "loss": 3.3339,
      "step": 2900
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00082,
      "loss": 3.3228,
      "step": 2950
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0008,
      "loss": 3.3239,
      "step": 3000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0007800000000000001,
      "loss": 3.2763,
      "step": 3050
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00076,
      "loss": 3.2408,
      "step": 3100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00074,
      "loss": 3.231,
      "step": 3150
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0007199999999999999,
      "loss": 3.2317,
      "step": 3200
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0007,
      "loss": 3.2208,
      "step": 3250
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00068,
      "loss": 3.1952,
      "step": 3300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00066,
      "loss": 3.1825,
      "step": 3350
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00064,
      "loss": 3.184,
      "step": 3400
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00062,
      "loss": 3.1452,
      "step": 3450
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0006,
      "loss": 3.1298,
      "step": 3500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00058,
      "loss": 3.1244,
      "step": 3550
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005600000000000001,
      "loss": 3.114,
      "step": 3600
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00054,
      "loss": 3.1101,
      "step": 3650
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005200000000000001,
      "loss": 3.0911,
      "step": 3700
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005,
      "loss": 3.0805,
      "step": 3750
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00048,
      "loss": 3.0669,
      "step": 3800
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00046,
      "loss": 3.0597,
      "step": 3850
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00044,
      "loss": 3.0388,
      "step": 3900
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00042,
      "loss": 3.0504,
      "step": 3950
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0004,
      "loss": 3.0222,
      "step": 4000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00038,
      "loss": 3.0142,
      "step": 4050
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00035999999999999997,
      "loss": 3.0106,
      "step": 4100
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00034,
      "loss": 3.0054,
      "step": 4150
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00032,
      "loss": 2.9846,
      "step": 4200
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 2.967,
      "step": 4250
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00028000000000000003,
      "loss": 2.9749,
      "step": 4300
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.9415,
      "step": 4350
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00024,
      "loss": 2.9486,
      "step": 4400
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00022,
      "loss": 2.9509,
      "step": 4450
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.9261,
      "step": 4500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.9138,
      "step": 4550
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016,
      "loss": 2.9356,
      "step": 4600
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014000000000000001,
      "loss": 2.9036,
      "step": 4650
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00012,
      "loss": 2.8768,
      "step": 4700
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 2.8875,
      "step": 4750
    },
    {
      "epoch": 0.3,
      "learning_rate": 8e-05,
      "loss": 2.8752,
      "step": 4800
    },
    {
      "epoch": 0.3,
      "learning_rate": 6e-05,
      "loss": 2.8816,
      "step": 4850
    },
    {
      "epoch": 0.3,
      "learning_rate": 4e-05,
      "loss": 2.8772,
      "step": 4900
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 2.8658,
      "step": 4950
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 2.8755,
      "step": 5000
    },
    {
      "epoch": 0.31,
      "step": 5000,
      "total_flos": 7.55408830464e+16,
      "train_loss": 3.758148254394531,
      "train_runtime": 13724.031,
      "train_samples_per_second": 93.267,
      "train_steps_per_second": 0.364
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "total_flos": 7.55408830464e+16,
  "trial_name": null,
  "trial_params": null
}