Skip to content

Actions: huggingface/open-r1

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
552 workflow runs
552 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

hardcodes num_processes to 7 when using vllm
Quality #394: Pull request #264 opened by edbeeching
February 10, 2025 10:23 2m 20s fix-slurm-n-proc
February 10, 2025 10:23 2m 20s
Adds repetition penalty reward
Quality #393: Pull request #263 synchronize by edbeeching
February 10, 2025 10:13 2m 24s repitition-penaly-reward
February 10, 2025 10:13 2m 24s
Adds repetition penalty reward
Quality #392: Pull request #263 opened by edbeeching
February 10, 2025 10:10 2m 21s repitition-penaly-reward
February 10, 2025 10:10 2m 21s
Initial GRPO exps on the Numina dataset
Quality #391: Pull request #262 opened by edbeeching
February 10, 2025 09:22 2m 26s grpo-numina
February 10, 2025 09:22 2m 26s
chore(README): fix link, consistent formatting for CUDA warning (#248)
Quality #390: Commit db19392 pushed by lewtun
February 9, 2025 08:45 2m 18s main
February 9, 2025 08:45 2m 18s
Add retry mechanism for pushing eval results (#252)
Quality #389: Commit 9be2e9a pushed by lewtun
February 9, 2025 08:44 2m 14s main
February 9, 2025 08:44 2m 14s
Fix README: Correct recipes path and missing --config option (#247)
Quality #388: Commit 90c1bfe pushed by lewtun
February 9, 2025 07:21 2m 29s main
February 9, 2025 07:21 2m 29s
Add retry mechanism for pushing eval results
Quality #387: Pull request #252 opened by lewtun
February 9, 2025 07:07 2m 27s lewtun-patch-1
February 9, 2025 07:07 2m 27s
chore(README): fix link, consistent formatting for CUDA warning
Quality #386: Pull request #248 opened by ctjlewis
February 8, 2025 23:30 2m 19s ctjlewis:patch-4
February 8, 2025 23:30 2m 19s
fix format reward (#238)
Quality #382: Commit d12886d pushed by lewtun
February 8, 2025 14:46 2m 18s main
February 8, 2025 14:46 2m 18s
fix format reward
Quality #381: Pull request #238 synchronize by kashif
February 8, 2025 13:46 2m 22s JamesHujy:fix_format_reward
February 8, 2025 13:46 2m 22s
fix format reward
Quality #380: Pull request #238 synchronize by kashif
February 8, 2025 13:37 2m 22s JamesHujy:fix_format_reward
February 8, 2025 13:37 2m 22s
Fix typo (#241)
Quality #378: Commit f5f0b55 pushed by kashif
February 8, 2025 09:28 2m 39s main
February 8, 2025 09:28 2m 39s
Fix typo
Quality #377: Pull request #241 opened by xu-song
February 8, 2025 09:27 2m 17s xu-song:patch-1
February 8, 2025 09:27 2m 17s
fix format reward
Quality #376: Pull request #238 reopened by JamesHujy
February 8, 2025 03:39 2m 25s JamesHujy:fix_format_reward
February 8, 2025 03:39 2m 25s
Remove duplicate math-verify (#234)
Quality #374: Commit 3519a7f pushed by lewtun
February 7, 2025 19:01 2m 31s main
February 7, 2025 19:01 2m 31s
Remove duplicate math-verify
Quality #373: Pull request #234 opened by lewtun
February 7, 2025 18:58 3m 7s fix-setup
February 7, 2025 18:58 3m 7s
Remove puzzles (#233)
Quality #372: Commit 9c768d5 pushed by Rocketknight1
February 7, 2025 16:52 2m 22s main
February 7, 2025 16:52 2m 22s
Remove puzzles
Quality #371: Pull request #233 opened by Rocketknight1
February 7, 2025 16:49 2m 30s deprecate-puzzles
February 7, 2025 16:49 2m 30s
Refactor training configs and unify Slurm for training SFT & GRPO (#231)
Quality #370: Commit 0da0f7c pushed by lewtun
February 7, 2025 14:56 2m 16s main
February 7, 2025 14:56 2m 16s
Refactor training configs and unify Slurm for training SFT & GRPO
Quality #369: Pull request #231 synchronize by lewtun
February 7, 2025 14:37 2m 26s refactor-slurm
February 7, 2025 14:37 2m 26s
Use new GRPO logic
Quality #368: Pull request #232 synchronize by qgallouedec
February 7, 2025 14:30 2m 19s update-grpo-params
February 7, 2025 14:30 2m 19s
Refactor training configs and unify Slurm for training SFT & GRPO
Quality #367: Pull request #231 synchronize by lewtun
February 7, 2025 14:26 2m 18s refactor-slurm
February 7, 2025 14:26 2m 18s
Use new GRPO logic
Quality #366: Pull request #232 synchronize by qgallouedec
February 7, 2025 14:22 2m 28s update-grpo-params
February 7, 2025 14:22 2m 28s