{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9929078014184397,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.666666666666667e-06,
      "loss": 3.1504,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.1699,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 3.0879,
      "step": 3
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9989008914857115e-05,
      "loss": 2.6113,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9956059820218982e-05,
      "loss": 2.373,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.990122514534651e-05,
      "loss": 2.4902,
      "step": 6
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.982462542875576e-05,
      "loss": 2.5117,
      "step": 7
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.972642905324813e-05,
      "loss": 2.3848,
      "step": 8
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9606851875768404e-05,
      "loss": 2.5195,
      "step": 9
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9466156752904344e-05,
      "loss": 2.5762,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9304652963070868e-05,
      "loss": 2.2676,
      "step": 11
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9122695526648968e-05,
      "loss": 2.4043,
      "step": 12
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8920684425573865e-05,
      "loss": 2.4199,
      "step": 13
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8699063724087905e-05,
      "loss": 2.4121,
      "step": 14
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8458320592590976e-05,
      "loss": 2.4805,
      "step": 15
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8198984236734246e-05,
      "loss": 2.2734,
      "step": 16
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7921624734111292e-05,
      "loss": 2.3574,
      "step": 17
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.762685178110382e-05,
      "loss": 2.3848,
      "step": 18
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.731531335263669e-05,
      "loss": 2.2383,
      "step": 19
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.698769427778842e-05,
      "loss": 2.5195,
      "step": 20
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.664471473438822e-05,
      "loss": 2.3809,
      "step": 21
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.628712866590885e-05,
      "loss": 2.3125,
      "step": 22
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5915722124135227e-05,
      "loss": 2.252,
      "step": 23
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.5531311541251995e-05,
      "loss": 2.2363,
      "step": 24
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.513474193514842e-05,
      "loss": 2.3203,
      "step": 25
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.4726885051885654e-05,
      "loss": 2.3477,
      "step": 26
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.4308637449409705e-05,
      "loss": 2.2314,
      "step": 27
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3880918526722497e-05,
      "loss": 2.3613,
      "step": 28
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.344466850284333e-05,
      "loss": 2.3096,
      "step": 29
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.300084635000341e-05,
      "loss": 2.2373,
      "step": 30
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.2550427685616767e-05,
      "loss": 2.1748,
      "step": 31
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2094402627661447e-05,
      "loss": 2.3242,
      "step": 32
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.1633773618185302e-05,
      "loss": 2.2578,
      "step": 33
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.1169553219720828e-05,
      "loss": 2.4395,
      "step": 34
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.070276188945293e-05,
      "loss": 2.252,
      "step": 35
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.0234425736032607e-05,
      "loss": 2.2334,
      "step": 36
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.765574263967397e-06,
      "loss": 2.2354,
      "step": 37
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.297238110547075e-06,
      "loss": 2.293,
      "step": 38
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.830446780279175e-06,
      "loss": 2.1807,
      "step": 39
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.366226381814698e-06,
      "loss": 2.2178,
      "step": 40
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.905597372338558e-06,
      "loss": 2.2744,
      "step": 41
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.449572314383237e-06,
      "loss": 2.3652,
      "step": 42
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.999153649996595e-06,
      "loss": 2.2529,
      "step": 43
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.555331497156671e-06,
      "loss": 2.2402,
      "step": 44
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.119081473277502e-06,
      "loss": 2.1729,
      "step": 45
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6913625505902966e-06,
      "loss": 2.0986,
      "step": 46
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.273114948114346e-06,
      "loss": 2.2559,
      "step": 47
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.865258064851579e-06,
      "loss": 2.2832,
      "step": 48
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.468688458748006e-06,
      "loss": 2.3027,
      "step": 49
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.084277875864776e-06,
      "loss": 2.2676,
      "step": 50
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.712871334091154e-06,
      "loss": 2.1201,
      "step": 51
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.355285265611784e-06,
      "loss": 2.1416,
      "step": 52
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0123057222115835e-06,
      "loss": 2.2139,
      "step": 53
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6846866473633126e-06,
      "loss": 2.168,
      "step": 54
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.373148218896182e-06,
      "loss": 2.3066,
      "step": 55
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.078375265888707e-06,
      "loss": 2.3066,
      "step": 56
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8010157632657544e-06,
      "loss": 2.1279,
      "step": 57
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5416794074090258e-06,
      "loss": 2.2891,
      "step": 58
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.300936275912098e-06,
      "loss": 2.2139,
      "step": 59
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0793155744261352e-06,
      "loss": 2.123,
      "step": 60
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.773044733510338e-07,
      "loss": 2.1484,
      "step": 61
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.953470369291349e-07,
      "loss": 2.2588,
      "step": 62
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.33843247095659e-07,
      "loss": 2.2129,
      "step": 63
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.931481242315993e-07,
      "loss": 2.2383,
      "step": 64
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.735709467518699e-07,
      "loss": 2.2207,
      "step": 65
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7537457124423896e-07,
      "loss": 2.1211,
      "step": 66
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.877485465349057e-08,
      "loss": 2.2598,
      "step": 67
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.394017978101905e-08,
      "loss": 2.1055,
      "step": 68
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.099108514288627e-08,
      "loss": 2.0752,
      "step": 69
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0,
      "loss": 2.0234,
      "step": 70
    },
    {
      "epoch": 0.99,
      "step": 70,
      "total_flos": 6.980494046527488e+16,
      "train_loss": 2.3202706473214287,
      "train_runtime": 1763.9053,
      "train_samples_per_second": 5.102,
      "train_steps_per_second": 0.04
    }
  ],
  "max_steps": 70,
  "num_train_epochs": 1,
  "total_flos": 6.980494046527488e+16,
  "trial_name": null,
  "trial_params": null
}