export MKL_THREADING_LAYER=GNU
export MKL_SERVICE_FORCE_INTEL=0
export OMP_NUM_THREADS=1

# CUDA_VISIBLE_DEVICES=0 python tools/eval_aime2024_vllm.py \
#     --model /mnt/disk1/yihao/Lightning-OPD/model_weights/qwen3-8b \
#     --num-gpus 1 \
#     --n-samples 1 \
#     --temperature 0.0 \
#     --top-p 1.0 \
#     --max-tokens 32768 \
#     --prompt-template paper \
#     --hf-cache /mnt/disk1/yihao/hf_cache \
#     --output outputs/aime2024_qwen3_8b_paper_n1_32k.jsonl

# CUDA_VISIBLE_DEVICES=0 python tools/eval_aime2024_vllm.py \
#     --model /mnt/disk1/yihao/Lightning-OPD/checkpoints/qwen3-4b-poe-distill-lora-opd-ppo-clip-locking-b-5-self-distill-100 \
#     --num-gpus 1 \
#     --n-samples 1 \
#     --temperature 0.0 \
#     --top-p 1.0 \
#     --max-tokens 32768 \
#     --prompt-template paper \
#     --hf-cache /mnt/disk1/yihao/hf_cache \
#     --output outputs/aime2024_qwen3_8b_paper_n1_32k.jsonl


CUDA_VISIBLE_DEVICES=4,5,6,7 python tools/eval_aime2024_vllm.py \
    --model /mnt/disk1/yihao/Lightning-OPD/checkpoints/qwen3-4b-poe-distill-lora-opd-ppo-clip-locking-b-5-self-distill-100 \
    --num-gpus 4 \
    --n-samples 32 \
    --temperature 0.6 \
    --top-p 0.95 \
    --max-tokens 32768 \
    --prompt-template paper \
    --hf-cache /mnt/disk1/yihao/hf_cache \
    --output outputs/aime2024_qwen3_4b_poe_distill_lora_paper_n1_32k.jsonl \
    --enable-thinking



# CUDA_VISIBLE_DEVICES=4,5,6,7 python tools/eval_aime2024_vllm.py \
#     --model /mnt/disk1/yihao/Lightning-OPD/checkpoints/qwen3-4b-poe-distill-lora-opd-ppo-clip-60 \
#     --num-gpus 4 \
#     --n-samples 32 \
#     --temperature 0.6 \
#     --top-p 0.95 \
#     --max-tokens 32768 \
#     --enable-thinking \
#     --prompt-template paper \
#     --hf-cache /mnt/disk1/yihao/hf_cache \
#     --output outputs/aime2024_qwen3_4b_lightning_opd_paper_n32_32k.jsonl \