{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.77710843373494,
  "eval_steps": 500,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.2303,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.21,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.5e-06,
      "loss": 0.2118,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2131,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.5e-06,
      "loss": 0.2076,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 3e-06,
      "loss": 0.2116,
      "step": 600
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.5e-06,
      "loss": 0.2154,
      "step": 700
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2129,
      "step": 800
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.5e-06,
      "loss": 0.211,
      "step": 900
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-06,
      "loss": 0.2178,
      "step": 1000
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.2104,
      "step": 1100
    },
    {
      "epoch": 0.9,
      "learning_rate": 6e-06,
      "loss": 0.215,
      "step": 1200
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.2107,
      "step": 1300
    },
    {
      "epoch": 1.05,
      "learning_rate": 7e-06,
      "loss": 0.2091,
      "step": 1400
    },
    {
      "epoch": 1.13,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.207,
      "step": 1500
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1942,
      "step": 1600
    },
    {
      "epoch": 1.28,
      "learning_rate": 8.5e-06,
      "loss": 0.2037,
      "step": 1700
    },
    {
      "epoch": 1.36,
      "learning_rate": 9e-06,
      "loss": 0.2071,
      "step": 1800
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.5e-06,
      "loss": 0.2072,
      "step": 1900
    },
    {
      "epoch": 1.51,
      "learning_rate": 1e-05,
      "loss": 0.2035,
      "step": 2000
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.666666666666667e-06,
      "loss": 0.21,
      "step": 2100
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.2062,
      "step": 2200
    },
    {
      "epoch": 1.73,
      "learning_rate": 9e-06,
      "loss": 0.2067,
      "step": 2300
    },
    {
      "epoch": 1.81,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.2043,
      "step": 2400
    },
    {
      "epoch": 1.88,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.1953,
      "step": 2500
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2021,
      "step": 2600
    },
    {
      "epoch": 2.03,
      "learning_rate": 7.666666666666667e-06,
      "loss": 0.1764,
      "step": 2700
    },
    {
      "epoch": 2.11,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.1506,
      "step": 2800
    },
    {
      "epoch": 2.18,
      "learning_rate": 7e-06,
      "loss": 0.152,
      "step": 2900
    },
    {
      "epoch": 2.26,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1539,
      "step": 3000
    },
    {
      "epoch": 2.33,
      "learning_rate": 6.333333333333333e-06,
      "loss": 0.1509,
      "step": 3100
    },
    {
      "epoch": 2.41,
      "learning_rate": 6e-06,
      "loss": 0.1504,
      "step": 3200
    },
    {
      "epoch": 2.48,
      "learning_rate": 5.666666666666667e-06,
      "loss": 0.1484,
      "step": 3300
    },
    {
      "epoch": 2.56,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1501,
      "step": 3400
    },
    {
      "epoch": 2.64,
      "learning_rate": 5e-06,
      "loss": 0.1479,
      "step": 3500
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.1489,
      "step": 3600
    },
    {
      "epoch": 2.79,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.1494,
      "step": 3700
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1481,
      "step": 3800
    },
    {
      "epoch": 2.94,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.1478,
      "step": 3900
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.1355,
      "step": 4000
    },
    {
      "epoch": 3.09,
      "learning_rate": 3e-06,
      "loss": 0.0891,
      "step": 4100
    },
    {
      "epoch": 3.16,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.089,
      "step": 4200
    },
    {
      "epoch": 3.24,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0848,
      "step": 4300
    },
    {
      "epoch": 3.31,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0842,
      "step": 4400
    },
    {
      "epoch": 3.39,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0885,
      "step": 4500
    },
    {
      "epoch": 3.46,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.1122,
      "step": 4600
    },
    {
      "epoch": 3.54,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1053,
      "step": 4700
    },
    {
      "epoch": 3.61,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.1032,
      "step": 4800
    },
    {
      "epoch": 3.69,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.1016,
      "step": 4900
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0,
      "loss": 0.1031,
      "step": 5000
    },
    {
      "epoch": 3.84,
      "learning_rate": 6.125000000000001e-06,
      "loss": 0.1106,
      "step": 5100
    },
    {
      "epoch": 3.92,
      "learning_rate": 6e-06,
      "loss": 0.1184,
      "step": 5200
    },
    {
      "epoch": 3.99,
      "learning_rate": 5.8750000000000005e-06,
      "loss": 0.1195,
      "step": 5300
    },
    {
      "epoch": 4.07,
      "learning_rate": 5.75e-06,
      "loss": 0.0922,
      "step": 5400
    },
    {
      "epoch": 4.14,
      "learning_rate": 5.625e-06,
      "loss": 0.0909,
      "step": 5500
    },
    {
      "epoch": 4.22,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.0893,
      "step": 5600
    },
    {
      "epoch": 4.29,
      "learning_rate": 5.375e-06,
      "loss": 0.0918,
      "step": 5700
    },
    {
      "epoch": 4.37,
      "learning_rate": 5.2500000000000006e-06,
      "loss": 0.0917,
      "step": 5800
    },
    {
      "epoch": 4.44,
      "learning_rate": 5.125e-06,
      "loss": 0.0912,
      "step": 5900
    },
    {
      "epoch": 4.52,
      "learning_rate": 5e-06,
      "loss": 0.0913,
      "step": 6000
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.875e-06,
      "loss": 0.0907,
      "step": 6100
    },
    {
      "epoch": 4.67,
      "learning_rate": 4.75e-06,
      "loss": 0.0925,
      "step": 6200
    },
    {
      "epoch": 4.74,
      "learning_rate": 4.625000000000001e-06,
      "loss": 0.0913,
      "step": 6300
    },
    {
      "epoch": 4.82,
      "learning_rate": 4.5e-06,
      "loss": 0.0906,
      "step": 6400
    },
    {
      "epoch": 4.89,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 0.0916,
      "step": 6500
    },
    {
      "epoch": 4.97,
      "learning_rate": 4.25e-06,
      "loss": 0.0903,
      "step": 6600
    },
    {
      "epoch": 5.05,
      "learning_rate": 4.125e-06,
      "loss": 0.0719,
      "step": 6700
    },
    {
      "epoch": 5.12,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.058,
      "step": 6800
    },
    {
      "epoch": 5.2,
      "learning_rate": 3.875e-06,
      "loss": 0.0563,
      "step": 6900
    },
    {
      "epoch": 5.27,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0581,
      "step": 7000
    },
    {
      "epoch": 5.35,
      "learning_rate": 3.625e-06,
      "loss": 0.0568,
      "step": 7100
    },
    {
      "epoch": 5.42,
      "learning_rate": 3.5e-06,
      "loss": 0.0577,
      "step": 7200
    },
    {
      "epoch": 5.5,
      "learning_rate": 3.3750000000000003e-06,
      "loss": 0.0553,
      "step": 7300
    },
    {
      "epoch": 5.57,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0571,
      "step": 7400
    },
    {
      "epoch": 5.65,
      "learning_rate": 3.125e-06,
      "loss": 0.056,
      "step": 7500
    },
    {
      "epoch": 5.72,
      "learning_rate": 3e-06,
      "loss": 0.0567,
      "step": 7600
    },
    {
      "epoch": 5.8,
      "learning_rate": 2.875e-06,
      "loss": 0.0581,
      "step": 7700
    },
    {
      "epoch": 5.87,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.058,
      "step": 7800
    },
    {
      "epoch": 5.95,
      "learning_rate": 2.6250000000000003e-06,
      "loss": 0.0568,
      "step": 7900
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.5e-06,
      "loss": 0.0477,
      "step": 8000
    },
    {
      "epoch": 6.1,
      "learning_rate": 2.375e-06,
      "loss": 0.0336,
      "step": 8100
    },
    {
      "epoch": 6.17,
      "learning_rate": 2.25e-06,
      "loss": 0.0343,
      "step": 8200
    },
    {
      "epoch": 6.25,
      "learning_rate": 2.125e-06,
      "loss": 0.0337,
      "step": 8300
    },
    {
      "epoch": 6.33,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0324,
      "step": 8400
    },
    {
      "epoch": 6.4,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.0333,
      "step": 8500
    },
    {
      "epoch": 6.48,
      "learning_rate": 1.75e-06,
      "loss": 0.0335,
      "step": 8600
    },
    {
      "epoch": 6.55,
      "learning_rate": 1.6250000000000001e-06,
      "loss": 0.0341,
      "step": 8700
    },
    {
      "epoch": 6.63,
      "learning_rate": 1.5e-06,
      "loss": 0.0333,
      "step": 8800
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.3750000000000002e-06,
      "loss": 0.0326,
      "step": 8900
    },
    {
      "epoch": 6.78,
      "learning_rate": 1.25e-06,
      "loss": 0.0318,
      "step": 9000
    }
  ],
  "logging_steps": 100,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 1000,
  "total_flos": 2.077641731063808e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}