{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9681528662420382,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.050955414012738856,
      "grad_norm": 3.913437703076424,
      "learning_rate": 2.5e-07,
      "logits/chosen": 0.8591324090957642,
      "logits/rejected": 1.6159521341323853,
      "logps/chosen": -357.07135009765625,
      "logps/pi_response": -209.15574645996094,
      "logps/ref_response": -209.15574645996094,
      "logps/rejected": -329.1061096191406,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 3.793842175270246,
      "learning_rate": 2.730670898658255e-07,
      "logits/chosen": 1.115877628326416,
      "logits/rejected": 1.177431583404541,
      "logps/chosen": -341.7428894042969,
      "logps/pi_response": -215.8357391357422,
      "logps/ref_response": -216.03538513183594,
      "logps/rejected": -361.9898681640625,
      "loss": 0.6924,
      "rewards/accuracies": 0.4583333432674408,
      "rewards/chosen": -0.003969590645283461,
      "rewards/margins": 0.0014600297436118126,
      "rewards/rejected": -0.005429620388895273,
      "step": 10
    },
    {
      "epoch": 0.9681528662420382,
      "step": 19,
      "total_flos": 0.0,
      "train_loss": 0.690451371042352,
      "train_runtime": 978.7878,
      "train_samples_per_second": 2.554,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}