{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.044444444444444446,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 49.98692321777344,
      "learning_rate": 5e-07,
      "logits/chosen": -1.6455594301223755,
      "logits/rejected": -1.8609813451766968,
      "logps/chosen": -69.99601745605469,
      "logps/rejected": -28.68402099609375,
      "loss": 0.4811,
      "rewards/accuracies": 0.9200000166893005,
      "rewards/chosen": 0.43002215027809143,
      "rewards/margins": 0.5248908400535583,
      "rewards/rejected": -0.09486865252256393,
      "step": 50
    },
    {
      "epoch": 0.044444444444444446,
      "eval_logits/chosen": -1.683065414428711,
      "eval_logits/rejected": -1.8381606340408325,
      "eval_logps/chosen": -65.2982406616211,
      "eval_logps/rejected": -31.1202335357666,
      "eval_loss": 0.26570644974708557,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 0.9695585370063782,
      "eval_rewards/margins": 1.199601650238037,
      "eval_rewards/rejected": -0.23004300892353058,
      "eval_runtime": 547.5928,
      "eval_samples_per_second": 0.51,
      "eval_steps_per_second": 0.51,
      "step": 50
    }
  ],
  "logging_steps": 50,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}