{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.869565217391304,
  "eval_steps": 500,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 34.87980270385742,
      "learning_rate": 4.985344892885899e-06,
      "logits/chosen": -2.584322214126587,
      "logits/rejected": -2.617506265640259,
      "logps/chosen": -174.532958984375,
      "logps/rejected": -184.2425994873047,
      "loss": 0.6893,
      "rewards/accuracies": 0.3500000238418579,
      "rewards/chosen": 0.011605634354054928,
      "rewards/margins": 0.008320190012454987,
      "rewards/rejected": 0.003285445272922516,
      "step": 5
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 38.83084487915039,
      "learning_rate": 4.49023266426411e-06,
      "logits/chosen": -2.530242919921875,
      "logits/rejected": -2.510067939758301,
      "logps/chosen": -242.34451293945312,
      "logps/rejected": -242.54403686523438,
      "loss": 0.692,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.0007201525731943548,
      "rewards/margins": 0.003676743945106864,
      "rewards/rejected": -0.004396896343678236,
      "step": 10
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 30.36626434326172,
      "learning_rate": 3.425345388349787e-06,
      "logits/chosen": -2.5426576137542725,
      "logits/rejected": -2.5685505867004395,
      "logps/chosen": -190.65333557128906,
      "logps/rejected": -173.3209991455078,
      "loss": 0.6321,
      "rewards/accuracies": 0.9500000476837158,
      "rewards/chosen": 0.0738275945186615,
      "rewards/margins": 0.1280260980129242,
      "rewards/rejected": -0.05419851467013359,
      "step": 15
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 35.945823669433594,
      "learning_rate": 2.0955450086180883e-06,
      "logits/chosen": -2.534226894378662,
      "logits/rejected": -2.5561437606811523,
      "logps/chosen": -194.49790954589844,
      "logps/rejected": -207.09521484375,
      "loss": 0.6019,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.0849701538681984,
      "rewards/margins": 0.19348573684692383,
      "rewards/rejected": -0.10851557552814484,
      "step": 20
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 31.386171340942383,
      "learning_rate": 8.815342880454312e-07,
      "logits/chosen": -2.5661137104034424,
      "logits/rejected": -2.5473780632019043,
      "logps/chosen": -220.97113037109375,
      "logps/rejected": -215.14369201660156,
      "loss": 0.5646,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.12264734506607056,
      "rewards/margins": 0.2811417579650879,
      "rewards/rejected": -0.15849439799785614,
      "step": 25
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 30.438610076904297,
      "learning_rate": 1.3086707204299415e-07,
      "logits/chosen": -2.565887928009033,
      "logits/rejected": -2.572723388671875,
      "logps/chosen": -226.0846710205078,
      "logps/rejected": -220.2860565185547,
      "loss": 0.5412,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.1668781042098999,
      "rewards/margins": 0.3352271318435669,
      "rewards/rejected": -0.16834904253482819,
      "step": 30
    }
  ],
  "logging_steps": 5,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6055611024277504.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}