{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9915966386554622,
  "eval_steps": 100,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 6.892402047143212,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -1.1214768886566162,
      "logits/rejected": -1.0666239261627197,
      "logps/chosen": -773.5914306640625,
      "logps/rejected": -765.6082763671875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.17,
      "grad_norm": 6.623544286492592,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -1.280522346496582,
      "logits/rejected": -0.9248583912849426,
      "logps/chosen": -503.0466613769531,
      "logps/rejected": -899.9366455078125,
      "loss": 0.6904,
      "rewards/accuracies": 0.5347222089767456,
      "rewards/chosen": -0.0006784469587728381,
      "rewards/margins": 0.004367371555417776,
      "rewards/rejected": -0.005045818164944649,
      "step": 10
    },
    {
      "epoch": 0.34,
      "grad_norm": 7.366007707770025,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -1.253061294555664,
      "logits/rejected": -0.9847872853279114,
      "logps/chosen": -543.08447265625,
      "logps/rejected": -933.7767333984375,
      "loss": 0.6527,
      "rewards/accuracies": 0.856249988079071,
      "rewards/chosen": -0.020030761137604713,
      "rewards/margins": 0.08102954924106598,
      "rewards/rejected": -0.10106030851602554,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 8.97929873252708,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -1.188706398010254,
      "logits/rejected": -0.9695678949356079,
      "logps/chosen": -547.2942504882812,
      "logps/rejected": -972.0201416015625,
      "loss": 0.5278,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -0.08773749321699142,
      "rewards/margins": 0.4440121054649353,
      "rewards/rejected": -0.5317496061325073,
      "step": 30
    },
    {
      "epoch": 0.67,
      "grad_norm": 7.373164759260948,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -1.121267557144165,
      "logits/rejected": -0.9862432479858398,
      "logps/chosen": -544.4817504882812,
      "logps/rejected": -1049.937744140625,
      "loss": 0.4145,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -0.19056306779384613,
      "rewards/margins": 0.9457426071166992,
      "rewards/rejected": -1.136305570602417,
      "step": 40
    },
    {
      "epoch": 0.84,
      "grad_norm": 6.631179730087488,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -1.0745445489883423,
      "logits/rejected": -1.0211777687072754,
      "logps/chosen": -568.6431884765625,
      "logps/rejected": -1094.7789306640625,
      "loss": 0.3982,
      "rewards/accuracies": 0.8687499761581421,
      "rewards/chosen": -0.33096131682395935,
      "rewards/margins": 1.3629460334777832,
      "rewards/rejected": -1.6939074993133545,
      "step": 50
    },
    {
      "epoch": 0.99,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.5081947011462713,
      "train_runtime": 896.7003,
      "train_samples_per_second": 4.227,
      "train_steps_per_second": 0.066
    }
  ],
  "logging_steps": 10,
  "max_steps": 59,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}