Skip to content

Actions: gaetanlop/trl

Secret Leaks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
167 workflow runs
167 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix typo in reward logits lacking sigmoid
Secret Leaks #42: Commit 37e5caa pushed by gaetanlop
October 2, 2024 12:20 22s cgpo_calibrated_reward
October 2, 2024 12:20 22s
fix small typo in doc
Secret Leaks #41: Commit f1a70e7 pushed by gaetanlop
October 2, 2024 02:14 14s cgpo_calibrated_reward
October 2, 2024 02:14 14s
calibrated reward fn
Secret Leaks #40: Commit 20c2892 pushed by gaetanlop
October 2, 2024 02:07 21s cgpo_calibrated_reward
October 2, 2024 02:07 21s
skeleton
Secret Leaks #39: Commit eeb973f pushed by gaetanlop
October 2, 2024 01:25 15s cgpo_calibrated_reward
October 2, 2024 01:25 15s
[CI] Don't use eval_strategy="steps" when no eval dataset (#2152)
Secret Leaks #38: Commit 5c21de3 pushed by gaetanlop
October 2, 2024 01:15 22s main
October 2, 2024 01:15 22s
Merge branch 'main' into wpo
Secret Leaks #37: Commit e3f9a75 pushed by kashif
October 1, 2024 13:18 17s wpo
wpo
October 1, 2024 13:18 17s
Merge branch 'main' into wpo
Secret Leaks #36: Commit 84269e0 pushed by kashif
October 1, 2024 08:05 15s wpo
wpo
October 1, 2024 08:05 15s
Merge branch 'main' into prmtrainer
Secret Leaks #35: Commit c582464 pushed by qgallouedec
October 1, 2024 08:01 20s prmtrainer
October 1, 2024 08:01 20s
formatting
Secret Leaks #34: Commit 614fb4e pushed by gaetanlop
October 1, 2024 01:49 15s prmtrainer
October 1, 2024 01:49 15s
October 1, 2024 01:46 14s
fixing booleans
Secret Leaks #32: Commit 8e4e159 pushed by gaetanlop
October 1, 2024 01:36 20s prmtrainer
October 1, 2024 01:36 20s
add create_model_card and renaming
Secret Leaks #31: Commit 8b3fa52 pushed by gaetanlop
October 1, 2024 00:33 18s prmtrainer
October 1, 2024 00:33 18s
fixed detach
Secret Leaks #30: Commit 4d0162b pushed by gaetanlop
September 30, 2024 19:42 21s wpo
wpo
September 30, 2024 19:42 21s
rename example (#2139)
Secret Leaks #29: Commit 1201aa6 pushed by gaetanlop
September 29, 2024 20:03 12s gkd_adaptive_teaching
September 29, 2024 20:03 12s
do not compute gradients in weighting term
Secret Leaks #28: Commit 18c258f pushed by gaetanlop
September 29, 2024 19:43 15s wpo
wpo
September 29, 2024 19:43 15s
fix doc
Secret Leaks #27: Commit 3828296 pushed by gaetanlop
September 29, 2024 19:40 23s wpo
wpo
September 29, 2024 19:40 23s
formatting
Secret Leaks #26: Commit 5bcd60c pushed by gaetanlop
September 29, 2024 19:28 23s wpo
wpo
September 29, 2024 19:28 23s
add weighting arg in config
Secret Leaks #25: Commit a793436 pushed by gaetanlop
September 29, 2024 19:03 18s wpo
wpo
September 29, 2024 19:03 18s
skeleton
Secret Leaks #24: Commit aa42338 pushed by gaetanlop
September 29, 2024 14:42 16s wpo
wpo
September 29, 2024 14:42 16s
fix small typo
Secret Leaks #23: Commit 8c4ac31 pushed by gaetanlop
September 28, 2024 18:31 15s prmtrainer
September 28, 2024 18:31 15s
adding example script
Secret Leaks #22: Commit 1461a61 pushed by gaetanlop
September 28, 2024 18:30 18s prmtrainer
September 28, 2024 18:30 18s
renaming prm to stepwisereward
Secret Leaks #21: Commit b96ef4d pushed by gaetanlop
September 28, 2024 18:08 14s prmtrainer
September 28, 2024 18:08 14s
do not add post step_tokens to last step of the reasoning process
Secret Leaks #20: Commit 613d838 pushed by gaetanlop
September 28, 2024 18:01 15s prmtrainer
September 28, 2024 18:01 15s
doc post_step_separator
Secret Leaks #19: Commit 2dd752d pushed by gaetanlop
September 28, 2024 17:55 15s prmtrainer
September 28, 2024 17:55 15s
let user decide post step separator in config
Secret Leaks #18: Commit afa9e0a pushed by gaetanlop
September 28, 2024 17:53 21s prmtrainer
September 28, 2024 17:53 21s