{
  "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": 171.73661439403955,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -0.7590318322181702,
      "logits/real": -1.0396332740783691,
      "logps/generated": -289.2199401855469,
      "logps/real": -197.24859619140625,
      "loss": 0.9187,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 34.20735933667791,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -0.952869176864624,
      "logits/real": -0.9400660991668701,
      "logps/generated": -267.64935302734375,
      "logps/real": -216.30641174316406,
      "loss": 0.6785,
      "rewards/accuracies": 0.8611111044883728,
      "rewards/generated": -0.6007769107818604,
      "rewards/margins": 0.7688150405883789,
      "rewards/real": 0.16803814470767975,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.89230891359901,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -0.8387147188186646,
      "logits/real": -0.6731612086296082,
      "logps/generated": -285.69097900390625,
      "logps/real": -183.71739196777344,
      "loss": 0.1842,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.0443050861358643,
      "rewards/margins": 6.490469455718994,
      "rewards/real": 4.446164608001709,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.462947343445185,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -0.7116909027099609,
      "logits/real": -0.5934397578239441,
      "logps/generated": -282.5917053222656,
      "logps/real": -128.06210327148438,
      "loss": 0.1377,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.1207313537597656,
      "rewards/margins": 9.267239570617676,
      "rewards/real": 7.146508693695068,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.017306581553629,
      "learning_rate": 2e-07,
      "logits/generated": -0.5800212621688843,
      "logits/real": -0.6825695633888245,
      "logps/generated": -289.5108337402344,
      "logps/real": -159.77926635742188,
      "loss": 0.1543,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.36224627494812,
      "rewards/margins": 9.751206398010254,
      "rewards/real": 7.3889594078063965,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9620294445274639,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -0.6641489267349243,
      "logits/real": -0.6202989220619202,
      "logps/generated": -291.93603515625,
      "logps/real": -158.97694396972656,
      "loss": 0.1462,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.7126903533935547,
      "rewards/margins": 10.294529914855957,
      "rewards/real": 7.581839561462402,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0600372275387984,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -0.4919801354408264,
      "logits/real": -0.810921311378479,
      "logps/generated": -301.64776611328125,
      "logps/real": -126.55671691894531,
      "loss": 0.1347,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.056795835494995,
      "rewards/margins": 10.84618854522705,
      "rewards/real": 7.78939151763916,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.24013032932435313,
      "train_runtime": 796.2749,
      "train_samples_per_second": 2.502,
      "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
}