{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14222222222222222,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 108.5,
      "learning_rate": 2.0930232558139536e-06,
      "logits/chosen": 4.719546318054199,
      "logits/rejected": 4.862860202789307,
      "logps/chosen": -389.59698486328125,
      "logps/rejected": -377.825439453125,
      "loss": 0.6845,
      "rewards/accuracies": 0.4312500059604645,
      "rewards/chosen": 0.6139063835144043,
      "rewards/margins": 0.04724857956171036,
      "rewards/rejected": 0.5666579008102417,
      "step": 10
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 109.0,
      "learning_rate": 4.418604651162791e-06,
      "logits/chosen": 4.730769634246826,
      "logits/rejected": 4.875722408294678,
      "logps/chosen": -366.2303161621094,
      "logps/rejected": -381.54351806640625,
      "loss": 0.603,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": 2.2159204483032227,
      "rewards/margins": 0.5498644113540649,
      "rewards/rejected": 1.6660559177398682,
      "step": 20
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 64.5,
      "learning_rate": 6.744186046511628e-06,
      "logits/chosen": 4.784668922424316,
      "logits/rejected": 4.905774116516113,
      "logps/chosen": -407.79986572265625,
      "logps/rejected": -423.7102966308594,
      "loss": 0.5481,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -0.20952901244163513,
      "rewards/margins": 0.7444091439247131,
      "rewards/rejected": -0.9539381265640259,
      "step": 30
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 75.5,
      "learning_rate": 9.069767441860465e-06,
      "logits/chosen": 4.709995746612549,
      "logits/rejected": 4.814078330993652,
      "logps/chosen": -397.01055908203125,
      "logps/rejected": -400.6348571777344,
      "loss": 0.4682,
      "rewards/accuracies": 0.796875,
      "rewards/chosen": 2.5699944496154785,
      "rewards/margins": 1.2299325466156006,
      "rewards/rejected": 1.340061902999878,
      "step": 40
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 102.0,
      "learning_rate": 9.993784606094612e-06,
      "logits/chosen": 4.691997528076172,
      "logits/rejected": 4.816564083099365,
      "logps/chosen": -410.54034423828125,
      "logps/rejected": -446.1881408691406,
      "loss": 0.4441,
      "rewards/accuracies": 0.778124988079071,
      "rewards/chosen": -0.03334064409136772,
      "rewards/margins": 1.9787142276763916,
      "rewards/rejected": -2.012054443359375,
      "step": 50
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 96.0,
      "learning_rate": 9.955857588395065e-06,
      "logits/chosen": 4.5857696533203125,
      "logits/rejected": 4.653135299682617,
      "logps/chosen": -393.78936767578125,
      "logps/rejected": -445.19342041015625,
      "loss": 0.4635,
      "rewards/accuracies": 0.768750011920929,
      "rewards/chosen": 2.299717426300049,
      "rewards/margins": 2.069148302078247,
      "rewards/rejected": 0.23056945204734802,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 421,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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
}