{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 85.24139006970277,
      "learning_rate": 6.25e-08,
      "logits/generated": -1.035823106765747,
      "logits/real": -0.7845579385757446,
      "logps/generated": -221.43978881835938,
      "logps/real": -290.43585205078125,
      "loss": 0.9091,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 57.78188477455482,
      "learning_rate": 4.857142857142857e-07,
      "logits/generated": -1.00705885887146,
      "logits/real": -0.9160953164100647,
      "logps/generated": -217.96315002441406,
      "logps/real": -228.15171813964844,
      "loss": 0.9081,
      "rewards/accuracies": 0.5,
      "rewards/generated": 0.11379219591617584,
      "rewards/margins": 0.00582469254732132,
      "rewards/real": 0.11961688101291656,
      "step": 10
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 55.19183682235091,
      "learning_rate": 4.142857142857143e-07,
      "logits/generated": -1.052150011062622,
      "logits/real": -1.0221259593963623,
      "logps/generated": -200.09579467773438,
      "logps/real": -193.20050048828125,
      "loss": 0.88,
      "rewards/accuracies": 0.5625,
      "rewards/generated": 0.9856117367744446,
      "rewards/margins": 0.019290633499622345,
      "rewards/real": 1.0049023628234863,
      "step": 20
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 70.19010436249343,
      "learning_rate": 3.4285714285714286e-07,
      "logits/generated": -1.1168638467788696,
      "logits/real": -1.0286533832550049,
      "logps/generated": -196.82545471191406,
      "logps/real": -194.75421142578125,
      "loss": 0.8597,
      "rewards/accuracies": 0.637499988079071,
      "rewards/generated": 1.657329797744751,
      "rewards/margins": 0.09445972740650177,
      "rewards/real": 1.7517893314361572,
      "step": 30
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 59.8434152735345,
      "learning_rate": 2.714285714285714e-07,
      "logits/generated": -1.0656118392944336,
      "logits/real": -0.9198936223983765,
      "logps/generated": -174.37677001953125,
      "logps/real": -206.28683471679688,
      "loss": 0.8633,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/generated": 2.180746555328369,
      "rewards/margins": 0.10865961015224457,
      "rewards/real": 2.2894062995910645,
      "step": 40
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 62.50654161583806,
      "learning_rate": 2e-07,
      "logits/generated": -1.1591944694519043,
      "logits/real": -0.9199365377426147,
      "logps/generated": -167.31390380859375,
      "logps/real": -196.71131896972656,
      "loss": 0.8212,
      "rewards/accuracies": 0.762499988079071,
      "rewards/generated": 2.3674254417419434,
      "rewards/margins": 0.24083653092384338,
      "rewards/real": 2.608261823654175,
      "step": 50
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 56.97503359063291,
      "learning_rate": 1.2857142857142855e-07,
      "logits/generated": -1.0447438955307007,
      "logits/real": -0.9084192514419556,
      "logps/generated": -174.6784210205078,
      "logps/real": -183.24168395996094,
      "loss": 0.8568,
      "rewards/accuracies": 0.637499988079071,
      "rewards/generated": 2.725738525390625,
      "rewards/margins": 0.11709457635879517,
      "rewards/real": 2.8428330421447754,
      "step": 60
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 70.79977219793189,
      "learning_rate": 5.714285714285714e-08,
      "logits/generated": -1.0091984272003174,
      "logits/real": -0.8863734006881714,
      "logps/generated": -181.19216918945312,
      "logps/real": -198.0881805419922,
      "loss": 0.85,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/generated": 2.8773930072784424,
      "rewards/margins": 0.09863928705453873,
      "rewards/real": 2.976032257080078,
      "step": 70
    },
    {
      "epoch": 1.0,
      "step": 78,
      "total_flos": 0.0,
      "train_loss": 0.8588812213677627,
      "train_runtime": 1105.0645,
      "train_samples_per_second": 2.248,
      "train_steps_per_second": 0.071
    }
  ],
  "logging_steps": 10,
  "max_steps": 78,
  "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
}