{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.92,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 3.0266,
      "step": 1
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 3.0107,
      "step": 2
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 2.6686,
      "step": 3
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.6548607339452853e-05,
      "loss": 2.741,
      "step": 4
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 2.3865,
      "step": 5
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 2.4957,
      "step": 6
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.576851617267151e-06,
      "loss": 2.425,
      "step": 7
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.845849869981137e-06,
      "loss": 2.4254,
      "step": 8
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.4513926605471504e-06,
      "loss": 2.2729,
      "step": 9
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.587464671688187e-06,
      "loss": 2.2357,
      "step": 10
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 2.2729,
      "step": 11
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0,
      "loss": 2.2377,
      "step": 12
    },
    {
      "epoch": 1.92,
      "step": 12,
      "total_flos": 2601669460230144.0,
      "train_loss": 2.5165560046831765,
      "train_runtime": 131.5492,
      "train_samples_per_second": 12.163,
      "train_steps_per_second": 0.091
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 12,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 2601669460230144.0,
  "trial_name": null,
  "trial_params": null
}