{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9956483899042646,
  "global_step": 143,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 9.63768115942029e-06,
      "loss": 0.7658,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.91304347826087e-06,
      "loss": 0.7411,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.188405797101449e-06,
      "loss": 0.7329,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.4637681159420295e-06,
      "loss": 0.7241,
      "step": 40
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.739130434782609e-06,
      "loss": 0.737,
      "step": 50
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.014492753623189e-06,
      "loss": 0.7344,
      "step": 60
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.289855072463769e-06,
      "loss": 0.7305,
      "step": 70
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.565217391304348e-06,
      "loss": 0.7426,
      "step": 80
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.840579710144928e-06,
      "loss": 0.7263,
      "step": 90
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.1159420289855073e-06,
      "loss": 0.7343,
      "step": 100
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.391304347826087e-06,
      "loss": 0.7348,
      "step": 110
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.7413,
      "step": 120
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.420289855072465e-07,
      "loss": 0.7311,
      "step": 130
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.173913043478261e-07,
      "loss": 0.7225,
      "step": 140
    },
    {
      "epoch": 1.0,
      "step": 143,
      "total_flos": 0.0,
      "train_loss": 0.7351172920707223,
      "train_runtime": 1535.7461,
      "train_samples_per_second": 5.985,
      "train_steps_per_second": 0.093
    }
  ],
  "max_steps": 143,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}