Divyam Goel comments

Results 8 comments of


                                            Divyam Goel

Train adapters without Hugging Face Trainer scripts

Hey @calpt, I'd love to work on this. While the modifications are pretty straightforward, I think that it would save inexperienced users some time if the code were to be...

Train adapters without Hugging Face Trainer scripts

Hey @calpt, I will take this up then! Will send in a PR soon 😄

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Hi @aishwaryap, The metrics file can be found [here](https://drive.google.com/file/d/1lVxHFNHM3Mx0UlKAoXNNlgdEotJOFMUh/view?usp=sharing). Please let me know if you need any other information from my side! Thanks, Divyam

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Cool! I'll try it out and let you know how it goes.

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Hi @aishwaryap I ran inference on a pertained ET baseline model using `--num_processes 1` on a small subset of EDH instances. I also removed the `try-catch` blocks around the `_run_edh_instance`...

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Hi @aishwaryap I tried running the inference on 4GPUs using `--num_processes 2` on the full data. While I did get some successful instances this time around, the process still failed...

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Hi @hangjieshi A total of 68 instances were successfully processed. I checked the GPU memory usage multiple times during the process, none of the GPUs ran out of memory at...

Evaluating Episodic Transformer baselines for EDH instances gives zero successes

Hi @aishwaryap Thank you for your insights. I tried using `replay_timeout = 1000` and ran into the same issue with multiple threads ending the process on account of a `TimeoutError`....