Fine-tuned Model: legalRefExtractor-Adaptor-v1

📚 Training Configuration

• data_path: QomSSLab/legalRefExtractor_dataset
• output_dir: gemma312b_lora_chckpnts
• new_model_name: legalRefExtractor-Adaptor-v1
• data_ratio: 1.0
• model_name: QomSSLab/Legal-gemma3-12b-it-lora-thinking
• use_4bit: False
• use_lora: True
• max_seq_length: 8000
• batch_size: 1
• gradient_accu: 16
• epochs: 1
• learning_rate: 5e-05
• lora_alpha: 64
• lora_drop: 0.05
• lora_r: 64
• tune_embedding_layer: False
• hf_token: ********
• resume_from_checkpoint: False
• use_8bit_optimizer: True
• push_to_hub: True
• push_lora_only: True
• train_only_on_assistant: False
• last_response: False