loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/logical-reasoning/.env
Adding /common/home/users/d/dh.huang.2023/common2/code/logical-reasoning to sys.path
loading /common/home/users/d/dh.huang.2023/common2/code/logical-reasoning/llm_toolkit/logical_reasoning_utils.py
Qwen/Qwen2-72B-Instruct None True datasets/mgtv results/Qwen2-72B-Instruct_p2.csv
(1) GPU = NVIDIA H100 PCIe. Max memory = 79.097 GB.
0.0 GB of memory reserved.
loading model: Qwen/Qwen2-72B-Instruct with adapter: None
09/09/2024 14:38:58 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
09/09/2024 14:38:58 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.
09/09/2024 14:38:58 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.
09/09/2024 14:38:58 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.