Skip to content

Actions: huggingface/trl

Slow tests (on push)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
481 workflow runs
481 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix: Fix typo in filename in ultrafeedback-prompt.py (#2716)
Slow tests (on push) #481: Commit a325a0e pushed by qgallouedec
February 1, 2025 13:53 17m 41s main
February 1, 2025 13:53 17m 41s
🏰 num_logits_to_keep to logits_to_keep (#2721)
Slow tests (on push) #480: Commit 1c35a48 pushed by qgallouedec
January 31, 2025 19:19 18m 49s main
January 31, 2025 19:19 18m 49s
fix: Fix typo in filename Update ultrafeedback.py (#2699)
Slow tests (on push) #479: Commit 5ab15d3 pushed by qgallouedec
January 31, 2025 09:01 21m 8s main
January 31, 2025 09:01 21m 8s
📋 Add eval loss logging during prediction in GRPO (#2694)
Slow tests (on push) #478: Commit fecaa99 pushed by qgallouedec
January 30, 2025 17:37 17m 48s main
January 30, 2025 17:37 17m 48s
☠️ Remove deprecated (#2692)
Slow tests (on push) #477: Commit 6dc278a pushed by qgallouedec
January 30, 2025 15:30 17m 6s main
January 30, 2025 15:30 17m 6s
⬆️ Bump dev version (#2689)
Slow tests (on push) #476: Commit 56880ba pushed by qgallouedec
January 30, 2025 08:23 17m 59s main
January 30, 2025 08:23 17m 59s
📉 Use num_logits_to_keep to reduce memory usage in GRPO (#2683)
Slow tests (on push) #475: Commit 801582e pushed by qgallouedec
January 29, 2025 16:12 13m 54s main
January 29, 2025 16:12 13m 54s
🖊 Fix typos (#2673)
Slow tests (on push) #474: Commit 4659ad9 pushed by qgallouedec
January 28, 2025 10:26 16m 48s main
January 28, 2025 10:26 16m 48s
🏷️ Add model tags to model trained with GRPO (#2663)
Slow tests (on push) #473: Commit 1123bd0 pushed by qgallouedec
January 26, 2025 12:37 16m 47s main
January 26, 2025 12:37 16m 47s
🌀 Fix GRPO default completion length doc (#2662)
Slow tests (on push) #472: Commit 55a329e pushed by qgallouedec
January 26, 2025 09:05 17m 23s main
January 26, 2025 09:05 17m 23s
📏 Log completion length in GRPO (#2659)
Slow tests (on push) #471: Commit 4720656 pushed by qgallouedec
January 25, 2025 19:56 16m 46s main
January 25, 2025 19:56 16m 46s
📍 Disable caching when grad checkpointing enable in GRPO (#2653)
Slow tests (on push) #470: Commit 807046b pushed by qgallouedec
January 25, 2025 12:14 17m 29s main
January 25, 2025 12:14 17m 29s
🔎 Finegrained reward logging for GRPO (#2651)
Slow tests (on push) #469: Commit 317d2d4 pushed by qgallouedec
January 25, 2025 10:43 17m 0s main
January 25, 2025 10:43 17m 0s
👐 DeepSpeed integration for GRPO (#2652)
Slow tests (on push) #468: Commit aeb03cf pushed by qgallouedec
January 25, 2025 09:10 17m 33s main
January 25, 2025 09:10 17m 33s
🥞 Fix KTO gradient accumulation loss scaling (#2648)
Slow tests (on push) #467: Commit 6f99f42 pushed by qgallouedec
January 24, 2025 15:23 17m 55s main
January 24, 2025 15:23 17m 55s
🥞 Fix GRPO gradient accumulation loss scaling (#2647)
Slow tests (on push) #466: Commit d14f7f3 pushed by qgallouedec
January 24, 2025 15:22 17m 5s main
January 24, 2025 15:22 17m 5s
🥞 Fix CPO gradient accumulation loss scaling (#2645)
Slow tests (on push) #465: Commit 8e65825 pushed by qgallouedec
January 24, 2025 11:22 18m 30s main
January 24, 2025 11:22 18m 30s
🌯 Fix context manager runtime error when gather is disabled (#2639)
Slow tests (on push) #464: Commit f34b70a pushed by qgallouedec
January 23, 2025 20:23 19m 33s main
January 23, 2025 20:23 19m 33s
🍭 Custom reward function for RLOO (#2612)
Slow tests (on push) #463: Commit 0e216f7 pushed by August-murr
January 23, 2025 19:16 17m 30s main
January 23, 2025 19:16 17m 30s
🥞 Fix BCO gradient accumulation loss scaling (#2638)
Slow tests (on push) #462: Commit 59c2014 pushed by qgallouedec
January 23, 2025 17:57 16m 41s main
January 23, 2025 17:57 16m 41s
🥞 Fix DPO gradient accumulation loss scaling (#2615)
Slow tests (on push) #461: Commit 40c2383 pushed by qgallouedec
January 23, 2025 17:12 14m 40s main
January 23, 2025 17:12 14m 40s
Slow tests (on push)
Slow tests (on push) #460: by qgallouedec
January 23, 2025 16:30 18m 6s main
January 23, 2025 16:30 18m 6s
💾 Reduce memory peak in GRPO by adding max_prompt_length and loop u…
Slow tests (on push) #459: Commit b6a084c pushed by qgallouedec
January 21, 2025 14:12 16m 38s main
January 21, 2025 14:12 16m 38s
🧰 Tool fine-tuning support DPO (#2479)
Slow tests (on push) #458: Commit d9f0568 pushed by August-murr
January 21, 2025 06:02 17m 35s main
January 21, 2025 06:02 17m 35s
[RLOO] fix token_level_kl (#2575)
Slow tests (on push) #457: Commit 1b1140a pushed by kashif
January 17, 2025 13:59 17m 43s main
January 17, 2025 13:59 17m 43s