math test

openr/prm/infer_fns.py

@@ -4,6 +4,7 @@ from vllm import LLM, SamplingParams
 import re
 import json
 from envs.MATH import extract_answer, extract_groundtruth, judge_correct
+import random
 
 question_item_map = {}
 with open("./envs/MATH/dataset/test500.jsonl", encoding="utf-8") as f:
@@ -85,7 +86,9 @@ def _qwen_math_gold_infer_fn(input_str: str, model, tokenizer, device, acc):
                 step_score = 1
                 break
 
-        # math verify
+        # invers
+        if random.random() > acc:
+            step_score = 1 - step_score
         step_scores.append(step_score)
 
     return step_scores

openr/reason/llm_service/create_service_qwen2.5_math_vllm_gold_prm.sh

@@ -3,6 +3,7 @@ set -e
 HOST_ADDR=0.0.0.0
 CONTROLER_PORT=28777
 WORKER_BASE_PORT=30010
+ACC=1.0
 
 echo PYTHON_EXECUTABLE=$(which python3)
 PYTHON_EXECUTABLE=$(which python3)
@@ -45,5 +46,5 @@ do
   WORKER_PORT=$((i+WORKER_BASE_PORT+NUM_LM_WORKER))
   tmux new-window -n value_worker
   tmux send-keys "export LOGDIR=${LOGDIR}" Enter
-  tmux send-keys "CUDA_VISIBLE_DEVICES=$((i+NUM_LM_WORKER+CUDA_DEVICE_BASE)) $PYTHON_EXECUTABLE -m reason.llm_service.workers.gold_reward_model_worker --model-path $VALUE_MODEL_PATH --controller-address http://$HOST_ADDR:$CONTROLER_PORT --host $HOST_ADDR --port $WORKER_PORT --worker-address http://$HOST_ADDR:$WORKER_PORT" Enter
+  tmux send-keys "CUDA_VISIBLE_DEVICES=$((i+NUM_LM_WORKER+CUDA_DEVICE_BASE)) $PYTHON_EXECUTABLE -m reason.llm_service.workers.gold_reward_model_worker --model-path $VALUE_MODEL_PATH --controller-address http://$HOST_ADDR:$CONTROLER_PORT --host $HOST_ADDR --port $WORKER_PORT --worker-address http://$HOST_ADDR:$WORKER_PORT --acc $ACC" Enter
 done