run.json

{
  "format_version": "1.0",
  "created": "2026-06-19 11:20:51",
  "model_name": "Qwen/Qwen3.5-4B",
  "dtype": "bfloat16",
  "quantization": "nf4",
  "device": "cuda",
  "target_layers": [
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29,
    30,
    31
  ],
  "cross_attn_layers": [
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29,
    30,
    31
  ],
  "encoder_type": "selective",
  "prompt_format": "auto",
  "attn_implementation": null,
  "quantize_lm_head": false,
  "answer_suffix": "\n\nAnswer with ONLY the letter of the correct option (A, B, C, or D). Do not explain.",
  "chat_template_kwargs": {
    "enable_thinking": false
  },
  "dataset": "mmlu",
  "train_size": 250,
  "val_size": 50,
  "test_size": 50,
  "hidden_dim": 2560,
  "num_layers": 32
}