{
  "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": 96.2128665571533,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -0.9641311168670654,
      "logits/real": -0.837032675743103,
      "logps/generated": -316.6651611328125,
      "logps/real": -193.79689025878906,
      "loss": 0.8794,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 9.929461004560975,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -0.800748348236084,
      "logits/real": -0.686944842338562,
      "logps/generated": -300.80072021484375,
      "logps/real": -183.3310089111328,
      "loss": 0.6279,
      "rewards/accuracies": 0.7916666865348816,
      "rewards/generated": -0.5565835237503052,
      "rewards/margins": 0.8458547592163086,
      "rewards/real": 0.28927114605903625,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9333047201791761,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -0.5756534337997437,
      "logits/real": -0.5391597151756287,
      "logps/generated": -323.87567138671875,
      "logps/real": -149.74313354492188,
      "loss": 0.1575,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.065367698669434,
      "rewards/margins": 7.087759971618652,
      "rewards/real": 3.0223922729492188,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6096167237951732,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -0.7163437604904175,
      "logits/real": -0.8505982160568237,
      "logps/generated": -335.216064453125,
      "logps/real": -128.8068084716797,
      "loss": 0.1235,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.5739593505859375,
      "rewards/margins": 10.22940444946289,
      "rewards/real": 5.655444145202637,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3499258307052779,
      "learning_rate": 2e-07,
      "logits/generated": -0.7304865717887878,
      "logits/real": -1.0877403020858765,
      "logps/generated": -331.02947998046875,
      "logps/real": -102.53155517578125,
      "loss": 0.1132,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.106600284576416,
      "rewards/margins": 9.94569206237793,
      "rewards/real": 6.8390913009643555,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6642335718783683,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -0.6633592844009399,
      "logits/real": -1.1091253757476807,
      "logps/generated": -323.6708984375,
      "logps/real": -105.15264892578125,
      "loss": 0.1109,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.9631121158599854,
      "rewards/margins": 10.039856910705566,
      "rewards/real": 7.07674503326416,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5839224821994671,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -0.6755737662315369,
      "logits/real": -1.0861049890518188,
      "logps/generated": -323.3614501953125,
      "logps/real": -114.15528869628906,
      "loss": 0.1076,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.938748836517334,
      "rewards/margins": 9.908994674682617,
      "rewards/real": 6.970245361328125,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.20858578624263888,
      "train_runtime": 705.6832,
      "train_samples_per_second": 2.83,
      "train_steps_per_second": 0.088
    }
  ],
  "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
}