{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.1376,
      "step": 1
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.2032106230692394e-05,
      "loss": 1.0191,
      "step": 500
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.537114663038579e-07,
      "loss": 0.9331,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9246799349784851,
      "eval_runtime": 88.9299,
      "eval_samples_per_second": 173.519,
      "eval_steps_per_second": 0.349,
      "step": 1090
    },
    {
      "epoch": 1.0,
      "step": 1090,
      "total_flos": 445559907287040.0,
      "train_loss": 0.9711837689810937,
      "train_runtime": 6724.2493,
      "train_samples_per_second": 20.735,
      "train_steps_per_second": 0.162
    }
  ],
  "logging_steps": 500,
  "max_steps": 1090,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 445559907287040.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}