Skip to content

Actions: kashif/trl

Slow tests (on push)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
117 workflow runs
117 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

💔 Decouple loss computing and generation in GRPO (#2762)
Slow tests (on push) #117: Commit 1f344c9 pushed by kashif
February 4, 2025 14:26 7s main
February 4, 2025 14:26 7s
🥞 Fix KTO gradient accumulation loss scaling (#2648)
Slow tests (on push) #116: Commit 6f99f42 pushed by kashif
January 24, 2025 16:55 6s main
January 24, 2025 16:55 6s
💾 Reduce memory peak in GRPO by adding max_prompt_length and loop u…
Slow tests (on push) #115: Commit b6a084c pushed by kashif
January 21, 2025 15:38 27s main
January 21, 2025 15:38 27s
🧰 Tool fine-tuning support DPO (#2479)
Slow tests (on push) #114: Commit d9f0568 pushed by kashif
January 21, 2025 08:25 6s main
January 21, 2025 08:25 6s
[RLOO] fix token_level_kl (#2575)
Slow tests (on push) #113: Commit 1b1140a pushed by kashif
January 17, 2025 15:24 6s main
January 17, 2025 15:24 6s
✨ Refine model card method docstring (#2566)
Slow tests (on push) #112: Commit 57d9a97 pushed by kashif
January 16, 2025 14:01 7s main
January 16, 2025 14:01 7s
[RLOO] Reinforce++ (#2552)
Slow tests (on push) #111: Commit edabe0a pushed by kashif
January 9, 2025 11:37 6s main
January 9, 2025 11:37 6s
💔 Fix dataset type unpair conversion docs (#2550)
Slow tests (on push) #110: Commit abfffc5 pushed by kashif
January 8, 2025 19:26 6s main
January 8, 2025 19:26 6s
☄️ Update Comet integration to include LogCompletionsCallback and Tr…
Slow tests (on push) #109: Commit 763738f pushed by kashif
January 1, 2025 10:48 5s main
January 1, 2025 10:48 5s
🏞️ Proper dataset for documentation images (#2499)
Slow tests (on push) #108: Commit 5e204e1 pushed by kashif
December 18, 2024 15:04 6s main
December 18, 2024 15:04 6s
☄️ Add support for Comet experiment management SDK integration (#2462)
Slow tests (on push) #107: Commit 6d4ed07 pushed by kashif
December 15, 2024 09:34 5s main
December 15, 2024 09:34 5s
Update modeling_base.py (#2419)
Slow tests (on push) #106: Commit 148b592 pushed by kashif
December 12, 2024 10:21 7s main
December 12, 2024 10:21 7s
🗝️ Update type hints (#2399)
Slow tests (on push) #105: Commit c10cc89 pushed by kashif
November 27, 2024 10:08 7s main
November 27, 2024 10:08 7s
🧳 Move zen generation script and fix tests (#2393)
Slow tests (on push) #104: Commit 43df3a4 pushed by kashif
November 26, 2024 13:13 7s main
November 26, 2024 13:13 7s
Update log method to include start_time parameter (#2381)
Slow tests (on push) #103: Commit 672c965 pushed by kashif
November 22, 2024 09:17 4s main
November 22, 2024 09:17 4s
Fix dev install (#2369)
Slow tests (on push) #102: Commit 066fc37 pushed by kashif
November 19, 2024 17:37 6s main
November 19, 2024 17:37 6s
📉 Add PEFT support for PPOTrainer (#2344)
Slow tests (on push) #101: Commit 1293f37 pushed by kashif
November 18, 2024 11:05 6s main
November 18, 2024 11:05 6s
🔮 Inference mode in GeometricMixtureWrapper.forward (#2345)
Slow tests (on push) #100: Commit 21d5baf pushed by kashif
November 18, 2024 09:21 7s main
November 18, 2024 09:21 7s
⚖️ Add use_soft_judge option to WinRateCallback (#2347)
Slow tests (on push) #99: Commit b8c9d9c pushed by kashif
November 18, 2024 08:41 6s main
November 18, 2024 08:41 6s
DPO trainer supports num_logits_to_keep to save memory (#2129)
Slow tests (on push) #98: Commit 0238d96 pushed by kashif
November 11, 2024 12:09 7s main
November 11, 2024 12:09 7s
🧮 Fix the computation of KL divergence loss (#2277)
Slow tests (on push) #97: Commit ea7a1be pushed by kashif
October 26, 2024 19:02 4s main
October 26, 2024 19:02 4s
🧘 Replace F.log(F.sigmoid(log_odds) with F.logsigmoid(log_odds) (…
Slow tests (on push) #96: Commit 57ba9b9 pushed by kashif
October 25, 2024 10:49 5s main
October 25, 2024 10:49 5s
🏗️ Refactor DPO data processing (#2209)
Slow tests (on push) #95: Commit 92f6d24 pushed by kashif
October 21, 2024 11:49 5s main
October 21, 2024 11:49 5s
🔀 Rename get_batch_sample and add num_items_in_batch to `compute_…
Slow tests (on push) #94: Commit 31b7820 pushed by kashif
October 19, 2024 09:10 4s main
October 19, 2024 09:10 4s
Merge branch 'huggingface:main' into main
Slow tests (on push) #93: Commit 0002893 pushed by kashif
October 19, 2024 09:04 4s main
October 19, 2024 09:04 4s