{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9379743522638053,
  "eval_steps": 100,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 2.5e-06,
      "logits/chosen": -2.9041404724121094,
      "logits/rejected": -2.8873558044433594,
      "logps/chosen": -256.58734130859375,
      "logps/rejected": -238.80397033691406,
      "loss": 0.6932,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.2500000000000007e-06,
      "logits/chosen": -2.9109790325164795,
      "logits/rejected": -2.8924036026000977,
      "logps/chosen": -258.4911193847656,
      "logps/rejected": -244.30831909179688,
      "loss": 0.6793,
      "rewards/accuracies": 0.5908203125,
      "rewards/chosen": 0.04758377745747566,
      "rewards/margins": 0.029919220134615898,
      "rewards/rejected": 0.017664561048150063,
      "step": 10
    },
    {
      "epoch": 0.94,
      "step": 14,
      "total_flos": 0.0,
      "train_loss": 0.6761519227709089,
      "train_runtime": 40312.7822,
      "train_samples_per_second": 1.517,
      "train_steps_per_second": 0.0
    }
  ],
  "logging_steps": 10,
  "max_steps": 14,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}