feat(vla): align transformer training stack and rollout validation

environment.yml

@@ -229,6 +229,11 @@ dependencies:
   - python-xxhash=3.6.0
   - python_abi=3.10
   - pytorch=2.4.0
+  - hydra-core=1.3.2
+  - omegaconf=2.3.0
+  - einops=0.8.2
+  - diffusers=0.36.0
+  - torchvision=0.19.0
   - pytz=2024.1
   - pyyaml=6.0.3
   - qhull=2020.2
@@ -321,12 +326,10 @@ dependencies:
     - datasets==4.5.0
     - decorator==5.2.1
     - deepdiff==8.6.1
-    - diffusers==0.30.0
     - dill==0.4.0
     - docstring_parser==0.17.0
     - draccus==0.10.0
     - eigenpy==3.10.3
-    - einops==0.8.1
     - etils==1.7.0
     - evdev==1.9.2
     - exceptiongroup==1.3.1
@@ -350,7 +353,6 @@ dependencies:
     - httpcore==1.0.9
     - httpx==0.28.1
     - huggingface_hub==1.3.2
-    - hydra-core==1.3.2
     - imageio==2.35.1
     - imageio-ffmpeg==0.6.0
     - importlib_metadata==8.7.1
@@ -380,22 +382,6 @@ dependencies:
     - networkx==3.4.2
     - numcodecs==0.13.1
     - numpy==2.2.6
-    - nvidia-cublas-cu12==12.4.5.8
-    - nvidia-cuda-cupti-cu12==12.4.127
-    - nvidia-cuda-nvrtc-cu12==12.4.127
-    - nvidia-cuda-runtime-cu12==12.4.127
-    - nvidia-cudnn-cu12==9.1.0.70
-    - nvidia-cufft-cu12==11.2.1.3
-    - nvidia-cufile-cu12==1.11.1.6
-    - nvidia-curand-cu12==10.3.5.147
-    - nvidia-cusolver-cu12==11.6.1.9
-    - nvidia-cusparse-cu12==12.3.1.170
-    - nvidia-cusparselt-cu12==0.6.3
-    - nvidia-nccl-cu12==2.21.5
-    - nvidia-nvjitlink-cu12==12.4.127
-    - nvidia-nvshmem-cu12==3.3.20
-    - nvidia-nvtx-cu12==12.4.127
-    - omegaconf==2.3.0
     - opencv-contrib-python==4.10.0.84
     - opencv-python==4.13.0.90
     - orderly-set==5.5.0
@@ -431,7 +417,7 @@ dependencies:
     - regex==2026.1.15
     - requests==2.32.5
     - rerun-sdk==0.26.2
-    - rich==14.2.0
+    - rich==13.9.4
     - ruckig==0.9.2
     - safehttpx==0.1.7
     - safetensors==0.7.0
@@ -443,18 +429,16 @@ dependencies:
     - stack-data==0.6.3
     - starlette==0.50.0
     - sympy==1.13.1
+    - swanlab==0.7.13
     - termcolor==3.3.0
     - timm==1.0.24
     - toml==0.10.2
     - tomli==2.4.0
     - tomlkit==0.13.3
-    - torch==2.5.0
     - torchcodec==0.5
     - torchmetrics==1.8.2
-    - torchvision==0.20.0
     - tqdm==4.67.1
     - traitlets==5.14.3
-    - triton==3.1.0
     - typer==0.21.1
     - typer-slim==0.21.1
     - typeshed_client==2.8.2