Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Hello,
I have been trying to replicate the results of the paper: pi-Tuning: Transferring Multimodal Foundation Models
with Optimal Multi-task Interpolation, but have been going through the error: train.py: error: unrecognized arguments: --local-rank=0
train.py: error: unrecognized arguments: --local-rank=1
[2023-12-07 20:59:50,625] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 2) local_rank: 0 (pid: 4867) of binary: /Users/nikhilbhavani/Desktop/pit/venv/bin/python3
Hello, I have been trying to replicate the results of the paper: pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation, but have been going through the error: train.py: error: unrecognized arguments: --local-rank=0 train.py: error: unrecognized arguments: --local-rank=1 [2023-12-07 20:59:50,625] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 2) local_rank: 0 (pid: 4867) of binary: /Users/nikhilbhavani/Desktop/pit/venv/bin/python3
Can I get some advice on how to proceed?