Wing Lian a0670abc94 add output for train loss in assertian err

2025-04-18 08:11:11 -07:00

..

__init__.py

Updates for trl 0.16.0 - mostly for GRPO (#2437) [skip ci]

2025-03-31 15:47:11 -04:00

test_flex.py

add output for train loss in assertian err

2025-04-18 08:11:11 -07:00

test_grpo.py

Fix: add delinearization and make qlora work with fsdp2 (#2515)

2025-04-15 23:31:39 -07:00