Commit graph

4 commits

Author SHA1 Message Date
Oliver
661cbc4c71 rename 2025-03-26 21:06:06 +00:00
Oliver
678eaa5b81 allow longer outputs 2025-03-26 21:05:37 +00:00
Oliver
165d1de86e add puzzles config for qwen 3b 2025-03-26 21:04:09 +00:00
Oliver Stanley
eb69916c1b
initial verl training codebase (#389)
* fixes for latest verl
* composite dataset training experiment
* use stateful dataloaders to match verl changes
* training readme
* add formatting reward
* length reward impl
* standalone reasoning_gym config section
* curriculum learning, new length reward, more config
2025-03-20 15:04:57 +00:00