{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032112393376818866,
  "eval_steps": 400,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001338016390700786,
      "grad_norm": 102.5,
      "learning_rate": 4.6945927106677224e-08,
      "logits/chosen": -0.8076202273368835,
      "logits/rejected": -0.6951009035110474,
      "logps/chosen": -1.798179030418396,
      "logps/rejected": -1.9123386144638062,
      "loss": 5.1741,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -17.98179054260254,
      "rewards/margins": 1.141597032546997,
      "rewards/rejected": -19.12338638305664,
      "step": 5
    },
    {
      "epoch": 0.002676032781401572,
      "grad_norm": 91.0,
      "learning_rate": 0.0,
      "logits/chosen": -0.6589593291282654,
      "logits/rejected": -0.5773996710777283,
      "logps/chosen": -1.6277735233306885,
      "logps/rejected": -1.8583186864852905,
      "loss": 5.1644,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -16.277734756469727,
      "rewards/margins": 2.305452823638916,
      "rewards/rejected": -18.583187103271484,
      "step": 10
    },
    {
      "epoch": 0.0032112393376818866,
      "step": 12,
      "total_flos": 0.0,
      "train_loss": 0.40756722291310626,
      "train_runtime": 13.7037,
      "train_samples_per_second": 11.676,
      "train_steps_per_second": 0.73
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}