Actions: huggingface/trl
Actions
424 workflow run results
424 workflow run results
SmolVLM
models via standalone script `sft_…
Slow tests (on push)
#424:
Commit e1d7813
pushed
by
qgallouedec
KTOTrainer
(#2394)
Slow tests (on push)
#420:
Commit baee06f
pushed
by
qgallouedec
policy
in favor of model
in PPOTrainer
(#2386)
Slow tests (on push)
#417:
Commit 16fa13c
pushed
by
qgallouedec
config
in favor of args
in PPOTrainer
(#2384)
Slow tests (on push)
#416:
Commit ee3cbe1
pushed
by
qgallouedec
MergeModelCallBack
(#2282)
Slow tests (on push)
#411:
Commit 6578fdc
pushed
by
qgallouedec
start_time
to _maybe_log_save_evaluate
(#2373)
Slow tests (on push)
#410:
Commit a0066f4
pushed
by
qgallouedec
PPOTrainer
(#2344)
Slow tests (on push)
#404:
Commit 1293f37
pushed
by
qgallouedec
data_collator
in RLOOTrainer
and PPOTrainer
(#…
Slow tests (on push)
#403:
Commit e7870dd
pushed
by
kashif
GeometricMixtureWrapper.forward
(#2345)
Slow tests (on push)
#402:
Commit 21d5baf
pushed
by
kashif
use_soft_judge
option to WinRateCallback
(#2347)
Slow tests (on push)
#400:
Commit b8c9d9c
pushed
by
kashif