Actions: huggingface/trl
Actions
723 workflow runs
723 workflow runs
0.13.0.dev0
(#2305)
Build documentation
#942:
Commit 2f34a16
pushed
by
qgallouedec
optimizer_cls_and_kwargs
attribute to PPOTrainer
and `RLOOT…
Build documentation
#938:
Commit d57a181
pushed
by
qgallouedec
_save_checkpoint
for online methods (#2288)
Build documentation
#934:
Commit bb56c6e
pushed
by
qgallouedec
LogCompletionsCallback
(#2285)
Build documentation
#931:
Commit 0ce3b65
pushed
by
qgallouedec
eval_dataset
in scripts when no eval strategy (#2270)
Build documentation
#930:
Commit e155cb8
pushed
by
qgallouedec
bos_token_id
only if it exists (#2279)
Build documentation
#928:
Commit 110d088
pushed
by
qgallouedec
F.log(F.sigmoid(log_odds)
with F.logsigmoid(log_odds)
(…
Build documentation
#927:
Commit 57ba9b9
pushed
by
qgallouedec
log_reports.py
for Improved Logging, File Processing, an…
Build documentation
#926:
Commit 0de75b2
pushed
by
qgallouedec
max_new_tokens
(#2272)
Build documentation
#925:
Commit e615974
pushed
by
qgallouedec
torch_dtype
to model kwargs in reward modeling example (#2266)
Build documentation
#924:
Commit c2bb1ee
pushed
by
qgallouedec
KTOTrainer
(#2248)
Build documentation
#922:
Commit 1699473
pushed
by
qgallouedec