Skip to content

Actions: huggingface/trl

Secret Leaks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
2,415 workflow runs
2,415 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Merge branch 'main' into log-completion
Secret Leaks #2365: Commit 818f864 pushed by lewtun
February 7, 2025 10:24 15s log-completion
February 7, 2025 10:24 15s
Fix completions
Secret Leaks #2364: Commit 0c271b2 pushed by lewtun
February 7, 2025 10:21 17s log-completion
February 7, 2025 10:21 17s
🎯 [SFT] add token accuracy metric (#2597)
Secret Leaks #2363: Commit 84d73fd pushed by qgallouedec
February 7, 2025 10:09 18s main
February 7, 2025 10:09 18s
🆚 Distinguish padding and eos when they differ (#2793)
Secret Leaks #2362: Commit 2241f17 pushed by qgallouedec
February 7, 2025 10:08 18s main
February 7, 2025 10:08 18s
Merge branch 'main' into mean_token_accuracy
Secret Leaks #2361: Commit dfe218c pushed by qgallouedec
February 7, 2025 09:10 20s mean_token_accuracy
February 7, 2025 09:10 20s
Merge branch 'main' into log-completion
Secret Leaks #2360: Commit 4b8d9aa pushed by lewtun
February 7, 2025 08:13 16s log-completion
February 7, 2025 08:13 16s
💡 Add 'Post training an LLM for reasoning with GRPO in TRL' tutorial …
Secret Leaks #2359: Commit 724acb9 pushed by qgallouedec
February 6, 2025 17:28 15s main
February 6, 2025 17:28 15s
Revert "Before the first training step, the model has no optimizer: f…
Secret Leaks #2357: Commit 7134a1e pushed by qgallouedec
February 6, 2025 17:20 16s main
February 6, 2025 17:20 16s
Before the first training step, the model has no optimizer: fix ds3
Secret Leaks #2356: Commit bf6e7ed pushed by qgallouedec
February 6, 2025 17:19 19s main
February 6, 2025 17:19 19s
Revert "log completions"
Secret Leaks #2355: Commit c3d42ac pushed by qgallouedec
February 6, 2025 15:17 15s distribute_batch_grpo
February 6, 2025 15:17 15s
log completions
Secret Leaks #2354: Commit 1e4af8f pushed by qgallouedec
February 6, 2025 15:16 18s distribute_batch_grpo
February 6, 2025 15:16 18s
fix slice
Secret Leaks #2353: Commit cb42eb0 pushed by qgallouedec
February 6, 2025 10:53 16s distribute_batch_grpo
February 6, 2025 10:53 16s
Merge branch 'main' into distribute_batch_grpo
Secret Leaks #2351: Commit 1ad2bfd pushed by qgallouedec
February 6, 2025 10:40 16s distribute_batch_grpo
February 6, 2025 10:40 16s
roll back to distribute generation
Secret Leaks #2350: Commit 0695722 pushed by qgallouedec
February 6, 2025 10:37 17s distribute_batch_grpo
February 6, 2025 10:37 17s
🙃 Fix reward function in GRPO example (#2777)
Secret Leaks #2349: Commit e95f9fb pushed by qgallouedec
February 6, 2025 08:51 22s main
February 6, 2025 08:51 22s
💡 GRPO vram-efficiency improvement; only compute relevant logprobs (…
Secret Leaks #2348: Commit a85768f pushed by qgallouedec
February 6, 2025 07:52 17s main
February 6, 2025 07:52 17s
↔️ GRPO: Set max_model_len when initializing vLLM instance (#2728)
Secret Leaks #2347: Commit 78c5ce2 pushed by qgallouedec
February 5, 2025 23:12 15s main
February 5, 2025 23:12 15s
fix tests
Secret Leaks #2346: Commit 9025cbc pushed by qgallouedec
February 5, 2025 20:14 20s distribute_batch_grpo
February 5, 2025 20:14 20s
fix type hint
Secret Leaks #2345: Commit f999a30 pushed by qgallouedec
February 5, 2025 19:58 20s distribute_batch_grpo
February 5, 2025 19:58 20s
doc clarification
Secret Leaks #2344: Commit 05778b8 pushed by qgallouedec
February 5, 2025 19:56 17s distribute_batch_grpo
February 5, 2025 19:56 17s
comment
Secret Leaks #2343: Commit 3a738f9 pushed by qgallouedec
February 5, 2025 19:50 17s distribute_batch_grpo
February 5, 2025 19:50 17s
fix and document RepeatRandomSampler
Secret Leaks #2342: Commit a38231f pushed by qgallouedec
February 5, 2025 19:49 17s distribute_batch_grpo
February 5, 2025 19:49 17s
fix some logic errors
Secret Leaks #2341: Commit 0b131b1 pushed by qgallouedec
February 5, 2025 19:29 17s distribute_batch_grpo
February 5, 2025 19:29 17s