{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 100,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.25e-06,
      "logits/chosen": -2.3930084705352783,
      "logits/rejected": -2.4061639308929443,
      "logps/chosen": -245.26866149902344,
      "logps/rejected": -261.33184814453125,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.646121984004666e-06,
      "logits/chosen": -2.525505542755127,
      "logits/rejected": -2.416348695755005,
      "logps/chosen": -264.3957214355469,
      "logps/rejected": -243.22918701171875,
      "loss": 0.6859,
      "rewards/accuracies": 0.5711805820465088,
      "rewards/chosen": 0.037347737699747086,
      "rewards/margins": 0.01542865764349699,
      "rewards/rejected": 0.02191907912492752,
      "step": 10
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.835583164544139e-06,
      "logits/chosen": -2.4794507026672363,
      "logits/rejected": -2.397329568862915,
      "logps/chosen": -257.61175537109375,
      "logps/rejected": -238.9801025390625,
      "loss": 0.6674,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": 0.03777569904923439,
      "rewards/margins": 0.06583560258150101,
      "rewards/rejected": -0.028059903532266617,
      "step": 20
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.723433775328385e-07,
      "logits/chosen": -2.5016331672668457,
      "logits/rejected": -2.392857074737549,
      "logps/chosen": -282.13555908203125,
      "logps/rejected": -262.0860595703125,
      "loss": 0.6557,
      "rewards/accuracies": 0.671875,
      "rewards/chosen": -0.02580374851822853,
      "rewards/margins": 0.10012584924697876,
      "rewards/rejected": -0.125929594039917,
      "step": 30
    },
    {
      "epoch": 1.0,
      "step": 39,
      "total_flos": 0.0,
      "train_loss": 0.6650766546909626,
      "train_runtime": 4758.2952,
      "train_samples_per_second": 2.102,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 10,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}