fix: trl 0.8.6 has GRPOConfig, compatible with torch 2.1.2

Dockerfile

@@ -15,11 +15,11 @@ RUN pip install --no-cache-dir numpy==1.26.4
 RUN pip install --no-cache-dir torch==2.1.2 --index-url https://download.pytorch.org/whl/cu118
 
 RUN pip install --no-cache-dir \
-    transformers==4.36.2 \
-    accelerate==0.25.0 \
-    peft==0.7.1 \
-    trl==0.7.11 \
-    bitsandbytes==0.41.3 \
+    transformers==4.40.0 \
+    accelerate==0.30.0 \
+    peft==0.10.0 \
+    trl==0.8.6 \
+    bitsandbytes==0.43.0 \
     wandb datasets huggingface_hub matplotlib Pillow
 
 RUN pip install --no-cache-dir git+https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment-.git && \