act Model - phospho Training Pipeline
Error Traceback
We faced an issue while training your model.
Training process failed with exit code 1:
frames_batch = decoder.get_frames_at(indices=frame_indices)
File "/opt/conda/envs/lerobot/lib/python3.10/site-packages/torchcodec/decoders/_video_decoder.py", line 212, in get_frames_at
data, pts_seconds, duration_seconds = core.get_frames_at_indices(
File "/opt/conda/envs/lerobot/lib/python3.10/site-packages/torch/_ops.py", line 723, in __call__
return self._op(*args, **kwargs)
RuntimeError: Invalid frame index=260 for streamIndex=0 numFrames=254
[1;34mwandb[0m:
[1;34mwandb[0m: ๐ View run [33mact[0m at: [34mhttps://wandb.ai/fspacheco-hamk/phospho-ACT/runs/ic7xvfuc[0m
[1;34mwandb[0m: Find logs at: [1;35m../data/phospho-app/Gozia-ACT-lov_cube_standkoko-qje19/1753947708.865646/wandb/run-20250731_094239-ic7xvfuc/logs[0m
Training parameters:
- Dataset: Gozia/lov_cube_standkoko
- Wandb run URL: None
- Epochs: None
- Batch size: 60
- Training steps: 8000
๐ Get Started: docs.phospho.ai
๐ค Get your robot: robots.phospho.ai
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support