hoshi-hiyouga 302e4e22bf Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation ...

support effective tokens calculation on sft/dpo

Former-commit-id: bd639a137e6f46e1a0005cc91572f5f1ec894f74

2024-11-20 13:43:15 +08:00

..

dpo

Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation

2024-11-20 13:43:15 +08:00

kto

fix dpo metrics

2024-11-02 20:59:01 +08:00

ppo

support rank0 logger

2024-11-02 18:31:04 +08:00

pt

fix dpo metrics

2024-11-02 20:59:01 +08:00

rm

support rank0 logger

2024-11-02 18:31:04 +08:00

sft

code refactor

2024-11-19 20:33:18 +08:00

__init__.py

rename package

2024-05-16 18:39:08 +08:00

callbacks.py

fix dpo metrics

2024-11-02 20:59:01 +08:00

test_utils.py

update tests

2024-11-02 12:41:44 +08:00

trainer_utils.py

support rank0 logger

2024-11-02 18:31:04 +08:00

tuner.py

support rank0 logger

2024-11-02 18:31:04 +08:00