{
  "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": 109.01377934229137,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -0.8064159750938416,
      "logits/real": -0.6185171008110046,
      "logps/generated": -299.50262451171875,
      "logps/real": -200.14151000976562,
      "loss": 0.8305,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.93805669339485,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -0.8030985593795776,
      "logits/real": -0.9910727739334106,
      "logps/generated": -297.23883056640625,
      "logps/real": -149.21435546875,
      "loss": 0.5796,
      "rewards/accuracies": 0.8472222089767456,
      "rewards/generated": -0.6651551127433777,
      "rewards/margins": 0.8789473176002502,
      "rewards/real": 0.21379214525222778,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.9438497765014935,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -0.6849241256713867,
      "logits/real": -1.017528772354126,
      "logps/generated": -333.42095947265625,
      "logps/real": -111.25775146484375,
      "loss": 0.1117,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.297724723815918,
      "rewards/margins": 7.266044616699219,
      "rewards/real": 2.9683196544647217,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.32023611073019653,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -0.7841335535049438,
      "logits/real": -1.2851266860961914,
      "logps/generated": -332.90576171875,
      "logps/real": -84.8996810913086,
      "loss": 0.0784,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.298463344573975,
      "rewards/margins": 9.964227676391602,
      "rewards/real": 5.6657633781433105,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.30864894937218457,
      "learning_rate": 2e-07,
      "logits/generated": -0.8037096858024597,
      "logits/real": -1.3239915370941162,
      "logps/generated": -326.4043273925781,
      "logps/real": -85.57597351074219,
      "loss": 0.0809,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.9041149616241455,
      "rewards/margins": 9.894041061401367,
      "rewards/real": 5.989926338195801,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2846132147152826,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -0.7309826612472534,
      "logits/real": -1.3372870683670044,
      "logps/generated": -338.34381103515625,
      "logps/real": -83.98223876953125,
      "loss": 0.078,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.595585823059082,
      "rewards/margins": 10.817425727844238,
      "rewards/real": 6.221841335296631,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.3292451035644288,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -0.773565948009491,
      "logits/real": -1.342200756072998,
      "logps/generated": -328.13323974609375,
      "logps/real": -75.390625,
      "loss": 0.071,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.468616485595703,
      "rewards/margins": 10.645805358886719,
      "rewards/real": 6.177188396453857,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.1698731828120447,
      "train_runtime": 767.8502,
      "train_samples_per_second": 2.603,
      "train_steps_per_second": 0.081
    }
  ],
  "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
}