{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "grad_norm": 38.601383184946684,
      "learning_rate": 2.5e-07,
      "logits/chosen": -1.6994600296020508,
      "logits/rejected": -2.8606085777282715,
      "logps/chosen": -233.19979858398438,
      "logps/rejected": -774.4999389648438,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.56,
      "grad_norm": 36.041657544647855,
      "learning_rate": 2.5e-07,
      "logits/chosen": -1.7672981023788452,
      "logits/rejected": -2.8025903701782227,
      "logps/chosen": -332.4769592285156,
      "logps/rejected": -844.6215209960938,
      "loss": 0.5902,
      "rewards/accuracies": 0.8541666865348816,
      "rewards/chosen": -0.010878211818635464,
      "rewards/margins": 0.23639048635959625,
      "rewards/rejected": -0.2472686767578125,
      "step": 10
    },
    {
      "epoch": 1.0,
      "step": 18,
      "total_flos": 0.0,
      "train_loss": 0.5004948377609253,
      "train_runtime": 257.4676,
      "train_samples_per_second": 4.381,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}