{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6666666666666665,
  "eval_steps": 100,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 27.295928955078125,
      "learning_rate": 9.549150281252633e-07,
      "log_odds_chosen": -0.7398602366447449,
      "log_odds_ratio": -1.4472485780715942,
      "logits/chosen": 4.57342529296875,
      "logits/rejected": 4.563874244689941,
      "logps/chosen": -4.301087379455566,
      "logps/rejected": -3.5536251068115234,
      "loss": 3.998,
      "nll_loss": 3.853286027908325,
      "rewards/accuracies": 0.534375011920929,
      "rewards/chosen": -0.4301087260246277,
      "rewards/margins": -0.07474623620510101,
      "rewards/rejected": -0.3553624749183655,
      "step": 10
    },
    {
      "epoch": 2.6666666666666665,
      "step": 12,
      "total_flos": 0.0,
      "train_loss": 3.9789788722991943,
      "train_runtime": 28.7351,
      "train_samples_per_second": 14.825,
      "train_steps_per_second": 0.418
    }
  ],
  "logging_steps": 10,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}