{
  "run_name": "lora_quickfinal_acct2",
  "approach": "option_b_quickfinal",
  "base_model": "Qwen/Qwen2.5-7B-Instruct",
  "base_model_revision": "a09a35458c702b33eeacc393d103063234e8bc28",
  "learning_rate": 0.0002,
  "lora_rank": 16,
  "lora_alpha": 32,
  "best_eval_loss": 0.011455,
  "num_epochs": 1,
  "max_seq_length": 600,
  "per_device_train_batch_size": 2,
  "gradient_accumulation_steps": 8,
  "effective_batch_size": 16,
  "optimizer": "adamw_torch",
  "fp16": true,
  "bf16": false,
  "target_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ],
  "lora_dropout": 0.05
}