{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-07,
      "logits/chosen": -2.521343946456909,
      "logits/rejected": -2.3620429039001465,
      "logps/chosen": -521.3419189453125,
      "logps/rejected": -476.025146484375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.989335440737587e-06,
      "logits/chosen": -2.358004093170166,
      "logits/rejected": -2.4325995445251465,
      "logps/chosen": -345.5417175292969,
      "logps/rejected": -309.4444580078125,
      "loss": 0.6911,
      "rewards/accuracies": 0.5694444179534912,
      "rewards/chosen": 0.01685788854956627,
      "rewards/margins": 0.004424349870532751,
      "rewards/rejected": 0.012433539144694805,
      "step": 10
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.625542839324036e-06,
      "logits/chosen": -2.4209659099578857,
      "logits/rejected": -2.4008195400238037,
      "logps/chosen": -297.3746643066406,
      "logps/rejected": -285.84234619140625,
      "loss": 0.679,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": 0.07351277023553848,
      "rewards/margins": 0.030746515840291977,
      "rewards/rejected": 0.04276625066995621,
      "step": 20
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.81608040719339e-06,
      "logits/chosen": -2.4519193172454834,
      "logits/rejected": -2.5038084983825684,
      "logps/chosen": -297.0643005371094,
      "logps/rejected": -273.5292053222656,
      "loss": 0.6686,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": 0.1535051167011261,
      "rewards/margins": 0.07135292887687683,
      "rewards/rejected": 0.08215219527482986,
      "step": 30
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.730670898658255e-06,
      "logits/chosen": -2.4741883277893066,
      "logits/rejected": -2.297362804412842,
      "logps/chosen": -321.7876281738281,
      "logps/rejected": -261.57379150390625,
      "loss": 0.673,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": 0.1949460208415985,
      "rewards/margins": 0.07163376361131668,
      "rewards/rejected": 0.12331227213144302,
      "step": 40
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.5968958345321178e-06,
      "logits/chosen": -2.4305148124694824,
      "logits/rejected": -2.4470670223236084,
      "logps/chosen": -298.35980224609375,
      "logps/rejected": -267.8696594238281,
      "loss": 0.6744,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": 0.09592735767364502,
      "rewards/margins": 0.0405537411570549,
      "rewards/rejected": 0.05537362024188042,
      "step": 50
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.524777069483526e-07,
      "logits/chosen": -2.4608042240142822,
      "logits/rejected": -2.472360849380493,
      "logps/chosen": -333.09967041015625,
      "logps/rejected": -280.1986389160156,
      "loss": 0.6734,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": 0.23129253089427948,
      "rewards/margins": 0.10529744625091553,
      "rewards/rejected": 0.12599506974220276,
      "step": 60
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.54358920679524e-08,
      "logits/chosen": -2.3924319744110107,
      "logits/rejected": -2.393690586090088,
      "logps/chosen": -306.0284729003906,
      "logps/rejected": -271.36529541015625,
      "loss": 0.6684,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": 0.06389348953962326,
      "rewards/margins": 0.027882063761353493,
      "rewards/rejected": 0.03601142764091492,
      "step": 70
    },
    {
      "epoch": 1.0,
      "step": 76,
      "total_flos": 0.0,
      "train_loss": 0.6752520862378573,
      "train_runtime": 2732.0836,
      "train_samples_per_second": 1.779,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 10,
  "max_steps": 76,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}