Junxiong Wang

I got the following error. building database indexes (this may take a while) 2019-08-25 15:50:33,256 WARNING [imdbpy.parser.sql.alchemy] /home/jw2544/.local/lib/python3.5/site-packages/imdb/parser/sql/alchemyadapter.py:343: Skipping creation of the movie_info.info index: (psycopg2.errors.ProgramLimitExceeded) index row requires 16536 bytes,...

TIME completeCast() : 0min, 9sec (wall) 0min, 2sec (user) 0min, 1sec (system) TIME fushing caches... : 0min, 1sec (wall) 0min, 1sec (user) 0min, 0sec (system) TIME TOTAL TIME TO INSERT/WRITE...

I also have this problem follow using the same command in the repo. @liranringel Did you find the solution for this? ``` export dataset=quality export model=led-1024 export split=validation CUDA_VISIBLE_DEVICES=0 python...

@eladsegal thank the authors for this great work! Is it possible for you to release those model numbers in validation dataset? That be very helpful for me! thank.

any updates on this, i can get the same issue. i don't think it is caused by vllm. it hangout in ray::WorkerDict not rollout. ``` Thread 3500638 (idle): "MainThread" main_loop...

Hi, thank you for this amazing work. it is possible to share the deepspeed backend engine. i have come customized model which uses its own cuda graph in generation. And...