deepparse_finetune_config.json

{
  "train_file": "artifacts/training/train_paper.jsonl",
  "output_dir": "artifacts/checkpoints/deepparse-r1-8b",
  "model_name": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
  "epochs": 25,
  "learning_rate": 0.0002,
  "batch_size": 8,
  "grad_accum": 4,
  "lora_rank": 8,
  "lora_alpha": 32,
  "lora_dropout": 0.01,
  "max_length": 512,
  "bf16": false,
  "attn_implementation": "eager",
  "seed": 1337,
  "eval_split": 0.0,
  "save_steps": 200,
  "log_steps": 25,
  "target_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ]
}