{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 200,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 346.3062021602437,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -3.196486711502075,
      "logits/real": -2.3527207374572754,
      "logps/generated": -231.1735382080078,
      "logps/real": -99.6369400024414,
      "loss": 0.7803,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.4299127951132924,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -3.081599235534668,
      "logits/real": -2.270655870437622,
      "logps/generated": -280.790771484375,
      "logps/real": -82.0130844116211,
      "loss": 0.2552,
      "rewards/accuracies": 0.8888888955116272,
      "rewards/generated": -4.4418439865112305,
      "rewards/margins": 5.652818202972412,
      "rewards/real": 1.2109735012054443,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9060775786875579,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -3.208840847015381,
      "logits/real": -2.1548514366149902,
      "logps/generated": -326.5088195800781,
      "logps/real": -72.36115264892578,
      "loss": 0.0712,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.6439790725708,
      "rewards/margins": 12.68847370147705,
      "rewards/real": 3.044494867324829,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9746129145559742,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -3.225053071975708,
      "logits/real": -2.0585813522338867,
      "logps/generated": -353.51434326171875,
      "logps/real": -57.8585090637207,
      "loss": 0.0641,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.199175834655762,
      "rewards/margins": 14.336624145507812,
      "rewards/real": 3.137446165084839,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.114683085793999,
      "learning_rate": 2e-07,
      "logits/generated": -3.1570346355438232,
      "logits/real": -2.1495680809020996,
      "logps/generated": -325.97515869140625,
      "logps/real": -78.28927612304688,
      "loss": 0.075,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.375910758972168,
      "rewards/margins": 13.806567192077637,
      "rewards/real": 3.4306564331054688,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7978164295236632,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -3.2370517253875732,
      "logits/real": -2.0745859146118164,
      "logps/generated": -342.4796447753906,
      "logps/real": -65.09725189208984,
      "loss": 0.0641,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.8725004196167,
      "rewards/margins": 14.377031326293945,
      "rewards/real": 3.5045323371887207,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7374328187221965,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -3.1993775367736816,
      "logits/real": -2.025631904602051,
      "logps/generated": -341.24053955078125,
      "logps/real": -61.965667724609375,
      "loss": 0.0622,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.041067123413086,
      "rewards/margins": 14.699417114257812,
      "rewards/real": 3.6583499908447266,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.10689828472752724,
      "train_runtime": 796.2858,
      "train_samples_per_second": 2.51,
      "train_steps_per_second": 0.078
    }
  ],
  "logging_steps": 10,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}