Setup improvement and utf-8 logging

setup.sh

@@ -1,15 +1,17 @@
 # Install the packages in r1-v .
 cd src/r1-v 
-pip install -e ".[dev]"
+pip install uv pip --upgrade
+
+uv pip install -e ".[dev]"
 
 # Addtional modules
-pip install wandb==0.18.3
-pip install tensorboardx
-pip install qwen_vl_utils torchvision
-pip install flash-attn --no-build-isolation
+uv pip install wandb==0.18.3
+uv pip install tensorboardx
+uv pip install qwen_vl_utils torchvision
+uv pip install flash-attn --no-build-isolation
 
 # vLLM support 
-pip install vllm==0.7.2
+uv pip install vllm==0.7.2
 
 # fix transformers version
-pip install git+https://github.com/huggingface/transformers.git@336dc69d63d56f232a183a3e7f52790429b871ef
+uv pip install git+https://github.com/huggingface/transformers.git@336dc69d63d56f232a183a3e7f52790429b871ef

src/r1-v/src/open_r1/grpo.py

@@ -86,7 +86,7 @@ def accuracy_reward(completions, solution, **kwargs):
         if os.getenv("DEBUG_MODE") == "true":
             log_path = os.getenv("LOG_PATH")
             # local_rank = int(os.getenv("LOCAL_RANK", 0))
-            with open(log_path, "a") as f:
+            with open(log_path, "a", encoding="utf-8") as f:
                 f.write(f"------------- {current_time} Accuracy reward: {reward} -------------\n")
                 f.write(f"Content: {content}\n")
                 f.write(f"Solution: {sol}\n")