Fine-tuned Model: Judge-Adaptor-v3
📚 Training Configuration
- data_path:
QomSSLab/Legal_SyntheticDraftRuling_Selected_v2 - output_dir:
gemma312b_lora_chckpnts - new_model_name:
Judge-Adaptor-v3 - data_ratio:
1.0 - model_name:
QomSSLab/Legal-gemma3-12b-it-lora-thinking - use_4bit:
False - use_lora:
True - max_seq_length:
40000 - batch_size:
1 - gradient_accu:
8 - epochs:
2 - learning_rate:
1e-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:
True - last_response:
False
Auto-generated after training.