{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.38888888888889,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.7271,
      "step": 3
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.9643,
      "step": 6
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.5e-05,
      "loss": 1.872,
      "step": 9
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6191,
      "step": 12
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.8705,
      "step": 15
    },
    {
      "epoch": 2.22,
      "learning_rate": 5e-05,
      "loss": 1.5021,
      "step": 18
    },
    {
      "epoch": 2.39,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.6868,
      "step": 21
    },
    {
      "epoch": 3.17,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.5721,
      "step": 24
    },
    {
      "epoch": 3.33,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3664,
      "step": 27
    },
    {
      "epoch": 4.11,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.5311,
      "step": 30
    },
    {
      "epoch": 4.28,
      "learning_rate": 9.166666666666667e-05,
      "loss": 1.3607,
      "step": 33
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001,
      "loss": 1.0423,
      "step": 36
    },
    {
      "epoch": 5.22,
      "learning_rate": 9.907407407407407e-05,
      "loss": 1.2364,
      "step": 39
    },
    {
      "epoch": 5.39,
      "learning_rate": 9.814814814814815e-05,
      "loss": 1.1658,
      "step": 42
    },
    {
      "epoch": 6.17,
      "learning_rate": 9.722222222222223e-05,
      "loss": 1.056,
      "step": 45
    },
    {
      "epoch": 6.33,
      "learning_rate": 9.62962962962963e-05,
      "loss": 1.0494,
      "step": 48
    },
    {
      "epoch": 7.11,
      "learning_rate": 9.537037037037038e-05,
      "loss": 0.8505,
      "step": 51
    },
    {
      "epoch": 7.28,
      "learning_rate": 9.444444444444444e-05,
      "loss": 0.8941,
      "step": 54
    },
    {
      "epoch": 8.06,
      "learning_rate": 9.351851851851852e-05,
      "loss": 0.7708,
      "step": 57
    },
    {
      "epoch": 8.22,
      "learning_rate": 9.25925925925926e-05,
      "loss": 0.5983,
      "step": 60
    },
    {
      "epoch": 8.39,
      "learning_rate": 9.166666666666667e-05,
      "loss": 0.5789,
      "step": 63
    },
    {
      "epoch": 9.17,
      "learning_rate": 9.074074074074075e-05,
      "loss": 0.4382,
      "step": 66
    },
    {
      "epoch": 9.33,
      "learning_rate": 8.981481481481481e-05,
      "loss": 0.6309,
      "step": 69
    },
    {
      "epoch": 10.11,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.4637,
      "step": 72
    },
    {
      "epoch": 10.28,
      "learning_rate": 8.796296296296297e-05,
      "loss": 0.4983,
      "step": 75
    },
    {
      "epoch": 11.06,
      "learning_rate": 8.703703703703704e-05,
      "loss": 0.3079,
      "step": 78
    },
    {
      "epoch": 11.22,
      "learning_rate": 8.611111111111112e-05,
      "loss": 0.3754,
      "step": 81
    },
    {
      "epoch": 11.39,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.3138,
      "step": 84
    },
    {
      "epoch": 12.17,
      "learning_rate": 8.425925925925926e-05,
      "loss": 0.3076,
      "step": 87
    },
    {
      "epoch": 12.33,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.3103,
      "step": 90
    },
    {
      "epoch": 13.11,
      "learning_rate": 8.240740740740741e-05,
      "loss": 0.2391,
      "step": 93
    },
    {
      "epoch": 13.28,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.2365,
      "step": 96
    },
    {
      "epoch": 14.06,
      "learning_rate": 8.055555555555556e-05,
      "loss": 0.195,
      "step": 99
    },
    {
      "epoch": 14.22,
      "learning_rate": 7.962962962962964e-05,
      "loss": 0.186,
      "step": 102
    },
    {
      "epoch": 14.39,
      "learning_rate": 7.870370370370372e-05,
      "loss": 0.2039,
      "step": 105
    },
    {
      "epoch": 15.17,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.1912,
      "step": 108
    },
    {
      "epoch": 15.33,
      "learning_rate": 7.685185185185185e-05,
      "loss": 0.1421,
      "step": 111
    },
    {
      "epoch": 16.11,
      "learning_rate": 7.592592592592593e-05,
      "loss": 0.1349,
      "step": 114
    },
    {
      "epoch": 16.28,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1201,
      "step": 117
    },
    {
      "epoch": 17.06,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.1364,
      "step": 120
    },
    {
      "epoch": 17.22,
      "learning_rate": 7.314814814814815e-05,
      "loss": 0.1249,
      "step": 123
    },
    {
      "epoch": 17.39,
      "learning_rate": 7.222222222222222e-05,
      "loss": 0.101,
      "step": 126
    },
    {
      "epoch": 18.17,
      "learning_rate": 7.12962962962963e-05,
      "loss": 0.0961,
      "step": 129
    },
    {
      "epoch": 18.33,
      "learning_rate": 7.037037037037038e-05,
      "loss": 0.1026,
      "step": 132
    },
    {
      "epoch": 19.11,
      "learning_rate": 6.944444444444444e-05,
      "loss": 0.0982,
      "step": 135
    },
    {
      "epoch": 19.28,
      "learning_rate": 6.851851851851852e-05,
      "loss": 0.0791,
      "step": 138
    }
  ],
  "logging_steps": 3,
  "max_steps": 360,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.13811835060224e+16,
  "trial_name": null,
  "trial_params": null
}