{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.4503,
      "step": 1
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.8456,
      "step": 2
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 2.8668,
      "step": 3
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.9059,
      "step": 4
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001666666666666667,
      "loss": 2.5708,
      "step": 5
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 2.7615,
      "step": 6
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001962962962962963,
      "loss": 2.6243,
      "step": 7
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001925925925925926,
      "loss": 2.5775,
      "step": 8
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018888888888888888,
      "loss": 2.6956,
      "step": 9
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001851851851851852,
      "loss": 2.787,
      "step": 10
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001814814814814815,
      "loss": 2.6009,
      "step": 11
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00017777777777777779,
      "loss": 2.6854,
      "step": 12
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00017407407407407408,
      "loss": 2.4677,
      "step": 13
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00017037037037037037,
      "loss": 2.5312,
      "step": 14
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001666666666666667,
      "loss": 2.6109,
      "step": 15
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00016296296296296295,
      "loss": 2.4935,
      "step": 16
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00015925925925925927,
      "loss": 2.2393,
      "step": 17
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00015555555555555556,
      "loss": 2.5754,
      "step": 18
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00015185185185185185,
      "loss": 2.6152,
      "step": 19
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00014814814814814815,
      "loss": 2.4088,
      "step": 20
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00014444444444444444,
      "loss": 2.3049,
      "step": 21
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00014074074074074076,
      "loss": 2.5026,
      "step": 22
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.00013703703703703705,
      "loss": 2.3374,
      "step": 23
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.4622,
      "step": 24
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00012962962962962963,
      "loss": 2.3252,
      "step": 25
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00012592592592592592,
      "loss": 2.3418,
      "step": 26
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00012222222222222224,
      "loss": 2.1923,
      "step": 27
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.00011851851851851852,
      "loss": 2.2973,
      "step": 28
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.00011481481481481482,
      "loss": 2.4804,
      "step": 29
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00011111111111111112,
      "loss": 2.2357,
      "step": 30
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00010740740740740742,
      "loss": 2.3561,
      "step": 31
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0001037037037037037,
      "loss": 2.2779,
      "step": 32
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.0001,
      "loss": 2.3664,
      "step": 33
    },
    {
      "epoch": 6.8,
      "learning_rate": 9.62962962962963e-05,
      "loss": 2.1453,
      "step": 34
    },
    {
      "epoch": 7.0,
      "learning_rate": 9.25925925925926e-05,
      "loss": 2.0024,
      "step": 35
    },
    {
      "epoch": 7.2,
      "learning_rate": 8.888888888888889e-05,
      "loss": 2.304,
      "step": 36
    },
    {
      "epoch": 7.4,
      "learning_rate": 8.518518518518518e-05,
      "loss": 2.2658,
      "step": 37
    },
    {
      "epoch": 7.6,
      "learning_rate": 8.148148148148148e-05,
      "loss": 2.1194,
      "step": 38
    },
    {
      "epoch": 7.8,
      "learning_rate": 7.777777777777778e-05,
      "loss": 2.1706,
      "step": 39
    },
    {
      "epoch": 8.0,
      "learning_rate": 7.407407407407407e-05,
      "loss": 1.9328,
      "step": 40
    },
    {
      "epoch": 8.2,
      "learning_rate": 7.037037037037038e-05,
      "loss": 2.1522,
      "step": 41
    },
    {
      "epoch": 8.4,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.2023,
      "step": 42
    },
    {
      "epoch": 8.6,
      "learning_rate": 6.296296296296296e-05,
      "loss": 1.9102,
      "step": 43
    },
    {
      "epoch": 8.8,
      "learning_rate": 5.925925925925926e-05,
      "loss": 2.2065,
      "step": 44
    },
    {
      "epoch": 9.0,
      "learning_rate": 5.555555555555556e-05,
      "loss": 2.0384,
      "step": 45
    },
    {
      "epoch": 9.2,
      "learning_rate": 5.185185185185185e-05,
      "loss": 2.1244,
      "step": 46
    },
    {
      "epoch": 9.4,
      "learning_rate": 4.814814814814815e-05,
      "loss": 1.9094,
      "step": 47
    },
    {
      "epoch": 9.6,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.1645,
      "step": 48
    },
    {
      "epoch": 9.8,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.9839,
      "step": 49
    },
    {
      "epoch": 10.0,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 2.0715,
      "step": 50
    },
    {
      "epoch": 10.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.068,
      "step": 51
    },
    {
      "epoch": 10.4,
      "learning_rate": 2.962962962962963e-05,
      "loss": 2.073,
      "step": 52
    },
    {
      "epoch": 10.6,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 1.8552,
      "step": 53
    },
    {
      "epoch": 10.8,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.0742,
      "step": 54
    },
    {
      "epoch": 11.0,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.9392,
      "step": 55
    },
    {
      "epoch": 11.2,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 2.0671,
      "step": 56
    },
    {
      "epoch": 11.4,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.0202,
      "step": 57
    },
    {
      "epoch": 11.6,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 2.0001,
      "step": 58
    },
    {
      "epoch": 11.8,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 1.7318,
      "step": 59
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.0,
      "loss": 2.1089,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_train_epochs": 12,
  "save_steps": 500,
  "total_flos": 4731631621373952.0,
  "trial_name": null,
  "trial_params": null
}