{
  "task": "dpo",
  "strategy": "full",
  "base_model": "gpt2-medium",
  "beta": 0.1,
  "epochs": 2,
  "effective_batch": 16,
  "n_train_pairs": 4000,
  "learning_rate": 5e-06,
  "param_stats": {
    "total_params": 354823168,
    "trainable_params": 354823168,
    "trainable_pct": 100.0,
    "total_M": 354.82,
    "trainable_M": 354.823
  },
  "build_notes": [
    "patched PeftModelForSequenceClassification.add_adapter() to tolerate low_cpu_mem_usage (PEFT prompt-learning signature mismatch)",
    "patched PeftModelForTokenClassification.add_adapter() to tolerate low_cpu_mem_usage (PEFT prompt-learning signature mismatch)",
    "patched PeftModelForQuestionAnswering.add_adapter() to tolerate low_cpu_mem_usage (PEFT prompt-learning signature mismatch)",
    "replaced PeftModelForCausalLM.prepare_inputs_for_generation() with a corrected copy (transcribed from and verified against the installed PEFT source) that defaults past_key_values to None when the wrapped base model's own method omits the key - fixes KeyError: 'past_key_values' on prefix/prompt tuning's first generate() call, for both legacy-tuple and Cache-native backbones"
  ],
  "final_val": {
    "val_loss": 0.007946740909068871,
    "val_reward_accuracy": 1.0,
    "val_reward_chosen": 2.0053974252844613,
    "val_reward_rejected": -8.401155846459526,
    "val_reward_margin": 10.406553185175335,
    "val_logp_chosen": -307.98636929951016,
    "val_logp_rejected": -402.400384812128
  },
  "reward_start": null,
  "reward_final": null,
  "reward_delta": null,
  "train_seconds": 2745.66,
  "peak_gpu_mb": 10173.0,
  "data_source": "hf:nrizwan/safe_ai_assignment_1"
}