{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 38,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 2.592954402820238,
      "learning_rate": 1.25e-07,
      "logits/chosen": 0.4306640625,
      "logits/rejected": 0.537109375,
      "logps/chosen": -237.5,
      "logps/rejected": -228.0,
      "loss": 0.6914,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.5257972591559534,
      "learning_rate": 4.6255428393240354e-07,
      "logits/chosen": 0.4337022602558136,
      "logits/rejected": 0.4523654580116272,
      "logps/chosen": -243.11111450195312,
      "logps/rejected": -236.94444274902344,
      "loss": 0.6919,
      "rewards/accuracies": 0.28125,
      "rewards/chosen": 0.004753430839627981,
      "rewards/margins": 0.0010722478618845344,
      "rewards/rejected": 0.0036805470008403063,
      "step": 10
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.555743613102717,
      "learning_rate": 2.730670898658255e-07,
      "logits/chosen": 0.36152344942092896,
      "logits/rejected": 0.45283204317092896,
      "logps/chosen": -243.5,
      "logps/rejected": -237.3000030517578,
      "loss": 0.6873,
      "rewards/accuracies": 0.54296875,
      "rewards/chosen": 0.03550415113568306,
      "rewards/margins": 0.011375045403838158,
      "rewards/rejected": 0.02410888671875,
      "step": 20
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 2.6433738154085615,
      "learning_rate": 6.524777069483525e-08,
      "logits/chosen": 0.35273438692092896,
      "logits/rejected": 0.47441405057907104,
      "logps/chosen": -243.14999389648438,
      "logps/rejected": -235.14999389648438,
      "loss": 0.6832,
      "rewards/accuracies": 0.594531238079071,
      "rewards/chosen": 0.06180419772863388,
      "rewards/margins": 0.02066650427877903,
      "rewards/rejected": 0.04110107570886612,
      "step": 30
    },
    {
      "epoch": 1.0,
      "step": 38,
      "total_flos": 0.0,
      "train_loss": 0.685900236430921,
      "train_runtime": 550.0055,
      "train_samples_per_second": 8.8,
      "train_steps_per_second": 0.069
    }
  ],
  "logging_steps": 10,
  "max_steps": 38,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}