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

Distribute
Secret Leaks #2340: Commit 5f37e3d pushed by qgallouedec
February 5, 2025 18:49 24s distribute_batch_grpo
February 5, 2025 18:49 24s
wandb
Secret Leaks #2339: Commit d1cd035 pushed by qgallouedec
February 5, 2025 15:14 15s log-completion
February 5, 2025 15:14 15s
adds SDLang remote model
Secret Leaks #2338: Commit b2304ed pushed by edbeeching
February 5, 2025 15:01 27s remote-gpro-ref-model
February 5, 2025 15:01 27s
typo
Secret Leaks #2337: Commit 818ab09 pushed by qgallouedec
February 5, 2025 14:43 16s log-completion
February 5, 2025 14:43 16s
log completions
Secret Leaks #2336: Commit 82750d3 pushed by qgallouedec
February 5, 2025 14:42 22s log-completion
February 5, 2025 14:42 22s
🚧 Add Optional ZeRO-3 Weight Gathering for GRPO in Sequence Generatio…
Secret Leaks #2335: Commit af4ad47 pushed by qgallouedec
February 4, 2025 22:24 14s main
February 4, 2025 22:24 14s
🔁 🦈 Support iterative GRPO (#2700)
Secret Leaks #2334: Commit b2ae999 pushed by qgallouedec
February 4, 2025 22:10 17s main
February 4, 2025 22:10 17s
🤖 Properly unwrap torch.compile-ed models in GRPO (#2750)
Secret Leaks #2333: Commit bd946f9 pushed by qgallouedec
February 4, 2025 21:22 16s main
February 4, 2025 21:22 16s
🔎 Add missing script argument in PPO documentation (#2720)
Secret Leaks #2332: Commit f42e34e pushed by qgallouedec
February 4, 2025 20:53 15s main
February 4, 2025 20:53 15s
📖 Clarification max len in Reward documentation (#2740)
Secret Leaks #2331: Commit 338fbd5 pushed by qgallouedec
February 4, 2025 20:16 20s main
February 4, 2025 20:16 20s
📐 Add vLLM dtype configuration for GRPO trainer (#2738)
Secret Leaks #2330: Commit 32f8fa8 pushed by qgallouedec
February 4, 2025 20:11 16s main
February 4, 2025 20:11 16s
📌 vLLM >= 0.7.1 for device fix (#2766)
Secret Leaks #2329: Commit 1a22764 pushed by qgallouedec
February 4, 2025 19:12 18s main
February 4, 2025 19:12 18s
log from main process
Secret Leaks #2328: Commit 8a9f916 pushed by kashif
February 4, 2025 17:28 14s mean_token_accuracy
February 4, 2025 17:28 14s
add to logs
Secret Leaks #2327: Commit 9a22b94 pushed by kashif
February 4, 2025 16:46 16s mean_token_accuracy
February 4, 2025 16:46 16s
Merge branch 'main' into mean_token_accuracy
Secret Leaks #2326: Commit d8cdc39 pushed by kashif
February 4, 2025 16:17 20s mean_token_accuracy
February 4, 2025 16:17 20s
cleanup
Secret Leaks #2325: Commit 5bcc0f6 pushed by edbeeching
February 4, 2025 15:38 18s remote-gpro-ref-model
February 4, 2025 15:38 18s
precommit
Secret Leaks #2324: Commit f6eb99b pushed by edbeeching
February 4, 2025 15:37 21s remote-gpro-ref-model
February 4, 2025 15:37 21s
fix usage command
Secret Leaks #2323: Commit cc9434e pushed by edbeeching
February 4, 2025 15:26 15s remote-gpro-ref-model
February 4, 2025 15:26 15s
adds remote ref models to GRPO
Secret Leaks #2322: Commit 9b4c4c1 pushed by edbeeching
February 4, 2025 14:44 18s remote-gpro-ref-model
February 4, 2025 14:44 18s
💔 Decouple loss computing and generation in GRPO (#2762)
Secret Leaks #2321: Commit 1f344c9 pushed by qgallouedec
February 4, 2025 12:21 19s main
February 4, 2025 12:21 19s
decouple loss and generation
Secret Leaks #2320: Commit 0b3d108 pushed by qgallouedec
February 4, 2025 11:49 18s decouple-generation-and-loss
February 4, 2025 11:49 18s
🔂 Use vLLM prefix caching for speedup (#2757)
Secret Leaks #2319: Commit 85121fc pushed by qgallouedec
February 4, 2025 10:20 18s main
February 4, 2025 10:20 18s
resolving merge conflict
Secret Leaks #2318: Commit a64c79a pushed by ariG23498
February 3, 2025 08:59 22s mpo
mpo
February 3, 2025 08:59 22s
chore: review suggestions
Secret Leaks #2317: Commit 04fddb5 pushed by ariG23498
February 3, 2025 08:41 16s mpo
mpo
February 3, 2025 08:41 16s
⚠️ Fix attention masking in GRPO (#2708)
Secret Leaks #2316: Commit bbdd6db pushed by qgallouedec
February 2, 2025 19:44 22s main
February 2, 2025 19:44 22s