{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 477.2496337890625,
      "learning_rate": 7.692307692307694e-07,
      "logits/chosen": 2.15625,
      "logits/rejected": 1.4375,
      "logps/chosen": -146.0,
      "logps/rejected": -131.0,
      "loss": 2.7656,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.534887996967882e-05,
      "learning_rate": 7.692307692307694e-06,
      "logits/chosen": 1.8359375,
      "logits/rejected": 1.1328125,
      "logps/chosen": -125.0,
      "logps/rejected": -187.0,
      "loss": 0.9163,
      "rewards/accuracies": 0.8055555820465088,
      "rewards/chosen": 1.46875,
      "rewards/margins": 8.3125,
      "rewards/rejected": -6.84375,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.47921126473161e-12,
      "learning_rate": 9.903926402016153e-06,
      "logits/chosen": 0.3828125,
      "logits/rejected": 0.357421875,
      "logps/chosen": -160.0,
      "logps/rejected": -540.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.921875,
      "rewards/margins": 39.25,
      "rewards/rejected": -42.25,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 5.994430991895002e-15,
      "learning_rate": 9.442228179894362e-06,
      "logits/chosen": -0.060791015625,
      "logits/rejected": -0.28515625,
      "logps/chosen": -264.0,
      "logps/rejected": -728.0,
      "loss": 0.0075,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -13.9375,
      "rewards/margins": 47.25,
      "rewards/rejected": -61.25,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 5.643975006320093e-14,
      "learning_rate": 8.633301610170136e-06,
      "logits/chosen": 1.0703125,
      "logits/rejected": 0.59375,
      "logps/chosen": -164.0,
      "logps/rejected": -740.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.609375,
      "rewards/margins": 59.25,
      "rewards/rejected": -62.0,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.0163520159099946e-11,
      "learning_rate": 7.540376726232648e-06,
      "logits/chosen": 1.234375,
      "logits/rejected": 0.6640625,
      "logps/chosen": -130.0,
      "logps/rejected": -636.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.015625,
      "rewards/margins": 52.0,
      "rewards/rejected": -53.0,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.786671276360566e-15,
      "learning_rate": 6.248882390836135e-06,
      "logits/chosen": 1.359375,
      "logits/rejected": 0.78515625,
      "logps/chosen": -146.0,
      "logps/rejected": -660.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.71875,
      "rewards/margins": 52.5,
      "rewards/rejected": -54.0,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.9845672956549099e-13,
      "learning_rate": 4.859768718620656e-06,
      "logits/chosen": 1.359375,
      "logits/rejected": 0.83984375,
      "logps/chosen": -150.0,
      "logps/rejected": -640.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.58203125,
      "rewards/margins": 52.0,
      "rewards/rejected": -52.5,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.1451468355701492e-15,
      "learning_rate": 3.4816162744519266e-06,
      "logits/chosen": 1.3125,
      "logits/rejected": 0.73828125,
      "logps/chosen": -149.0,
      "logps/rejected": -688.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.97265625,
      "rewards/margins": 55.75,
      "rewards/rejected": -56.75,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.8802392639811344e-13,
      "learning_rate": 2.2221488349019903e-06,
      "logits/chosen": 1.3359375,
      "logits/rejected": 0.79296875,
      "logps/chosen": -144.0,
      "logps/rejected": -680.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.796875,
      "rewards/margins": 54.5,
      "rewards/rejected": -56.25,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.8757966674675117e-07,
      "learning_rate": 1.1798131208919628e-06,
      "logits/chosen": 1.359375,
      "logits/rejected": 0.76171875,
      "logps/chosen": -150.0,
      "logps/rejected": -632.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.4453125,
      "rewards/margins": 49.75,
      "rewards/rejected": -51.25,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.703149137021777e-14,
      "learning_rate": 4.3608367469340553e-07,
      "logits/chosen": 1.34375,
      "logits/rejected": 0.7734375,
      "logps/chosen": -153.0,
      "logps/rejected": -628.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.078125,
      "rewards/margins": 50.0,
      "rewards/rejected": -52.0,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.835807033238558e-16,
      "learning_rate": 4.909437331777178e-08,
      "logits/chosen": 1.3515625,
      "logits/rejected": 0.7734375,
      "logps/chosen": -144.0,
      "logps/rejected": -676.0,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.203125,
      "rewards/margins": 54.0,
      "rewards/rejected": -55.25,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 0.0,
      "train_loss": 0.08870122274137147,
      "train_runtime": 1811.5821,
      "train_samples_per_second": 1.104,
      "train_steps_per_second": 0.069
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}