Commit Graph

  • ceb7065d6d Merge pull request #6312 from hpcaitech/grpo-latest-dev YeAnbang 2025-06-05 15:51:38 +08:00
  • 96faf54542 fix typ and parameter description grpo-latest-dev YeAnbang 2025-06-05 15:41:14 +08:00
  • 97f4bee9d8 Merge pull request #6340 from hpcaitech/release/v0.5.0 Hanks 2025-06-04 13:57:10 +08:00
  • 84f523a080 [Hotfix] fix requirsments (#6338) duanjunwen 2025-06-04 09:51:31 +08:00
  • e00c9bbf38 upgrade python release/v0.5.0 BurkeHulk 2025-06-03 18:51:39 +08:00
  • 91f08c64a7 upgrade python BurkeHulk 2025-06-03 18:41:37 +08:00
  • 043c46941c upgrade python BurkeHulk 2025-06-03 18:38:07 +08:00
  • 916a8fef0e Update release_test_pypi_before_merge.yml Hanks 2025-06-03 18:25:01 +08:00
  • 0ba96e88d2 Update release_test_pypi_before_merge.yml Hanks 2025-06-03 18:12:19 +08:00
  • b9535f3c44 Update version.txt Hanks 2025-06-03 17:56:08 +08:00
  • c4fe9e812e Update release_pypi_after_merge.yml Hanks 2025-06-03 17:55:49 +08:00
  • 6dfedea98b Update release_test_pypi_before_merge.yml Hanks 2025-06-03 17:55:21 +08:00
  • b4ec405778 Merge pull request #6336 from BurkeHulk/fix/update-test-config Hanks 2025-06-03 09:46:06 +08:00
  • 067dd43246 fix pre-commit err BurkeHulk 2025-06-02 18:13:34 +08:00
  • c9cba49ab5 fix CI machine tag BurkeHulk 2025-06-02 17:45:40 +08:00
  • fd56b22278 Merge pull request #6334 from flybird11111/main v0.5.1 Hanks 2025-06-02 17:08:24 +08:00
  • 6f19618bb4 [fix] fix_lazy_init for deepseek model in transformers Hanks 2025-06-02 11:31:45 +08:00
  • 5890c8ecdd Merge pull request #6335 from wangbluo/lazy_deepseek upgrade_transformers Hanks 2025-06-02 11:30:11 +08:00
  • 71f9cedcdb [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-06-02 03:27:11 +00:00
  • 58e33776fd fix_lazy_init_deepseek wangbluo 2025-06-02 11:21:40 +08:00
  • 060102372e Update release_pypi_after_merge.yml Hanks 2025-05-30 16:54:27 +08:00
  • 374dcd4da9 Update release_test_pypi_before_merge.yml Hanks 2025-05-30 16:09:14 +08:00
  • 3f9159715f Update release_test_pypi_before_merge.yml Hanks 2025-05-30 15:27:32 +08:00
  • 948533f7de fix flybird11111 2025-05-30 14:59:56 +08:00
  • c8aaa92e36 Update release_test_pypi_before_merge.yml Hanks 2025-05-30 14:43:31 +08:00
  • 562767c884 fix flybird11111 2025-05-30 14:38:07 +08:00
  • 0d008110e7 [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-05-29 10:16:55 +00:00
  • 7b921acc8a merge grpo-latest YeAnbang 2025-05-29 18:14:43 +08:00
  • 594384328c fix flybird11111 2025-05-29 11:25:39 +08:00
  • cac878d7b7 fix flybird11111 2025-05-29 11:10:37 +08:00
  • 45dd5a7cf4 release flybird11111 2025-05-29 10:46:57 +08:00
  • ee939d9aa5 address conversation YeAnbang 2025-05-29 10:25:59 +08:00
  • c8b368c294 add overlength sample count (#6332) Tong Li 2025-05-28 19:18:09 +08:00
  • 58f8c9bb43 Merge branch 'grpo-latest' of https://github.com/hpcaitech/ColossalAI into grpo-latest-dev YeAnbang 2025-05-28 17:34:52 +08:00
  • 4c3656870a address conversation YeAnbang 2025-05-28 17:34:11 +08:00
  • d322ff8cd9 Merge pull request #6330 from flybird11111/main v0.5.0 Hanks 2025-05-28 17:27:44 +08:00
  • 180cea709b update to conform to json format Tong Li 2025-05-28 13:13:21 +08:00
  • f4e3063dc3 [Ascend] Update README (#6331) Tong Li 2025-05-28 11:35:35 +08:00
  • 4afff92138 fix flybird11111 2025-05-28 11:13:44 +08:00
  • e1ca2d22ae [ColossalRL] Support ColossalRL on Ascend (#6324) duanjunwen 2025-05-28 10:43:13 +08:00
  • d3c40b9de4 [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-05-27 08:48:11 +00:00
  • d7a03bfea2 release flybird11111 2025-05-27 16:47:12 +08:00
  • a9656e2915 fix flybird11111 2025-05-27 15:19:04 +08:00
  • 45779680bf release flybird11111 2025-05-27 15:10:19 +08:00
  • 4271e3daf6 release flybird11111 2025-05-27 14:38:59 +08:00
  • ddbbbaab3e [upgrade]Upgrade transformers (#6320) flybird11111 2025-05-27 14:29:01 +08:00
  • ba93bba8bf fix (#6329) flybird11111 2025-05-27 12:18:32 +08:00
  • 611c1247ba Update bert.py flybird11111 2025-05-27 10:57:06 +08:00
  • 17654cb6cb [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-05-26 10:12:40 +00:00
  • 559f15a4c9 fix (#6328) flybird11111 2025-05-26 18:10:57 +08:00
  • 63dc73d478 fix (#6327) flybird11111 2025-05-26 16:05:28 +08:00
  • 552778fb20 Update requirements.txt flybird11111 2025-05-23 16:56:44 +08:00
  • f009d3c5c6 Update build_on_pr.yml flybird11111 2025-05-23 15:31:28 +08:00
  • 7b398485a7 Merge pull request #6323 from wangbluo/fix_deepseek Hanks 2025-05-23 11:16:56 +08:00
  • b7df86848c Update test_shard_deepseek.py Hanks 2025-05-23 11:16:36 +08:00
  • 252efa63fc fix wangbluo 2025-05-23 11:13:41 +08:00
  • ef8084a75b Merge pull request #6322 from wangbluo/fix_falcon Hanks 2025-05-22 16:54:00 +08:00
  • 4a077e5dc3 fix falcon wangbluo 2025-05-22 16:50:40 +08:00
  • e1c72fd41c fix flybird11111 2025-05-22 16:49:06 +08:00
  • bafc80c3b0 [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-05-22 06:27:18 +00:00
  • bad9c8ab24 fix flybird11111 2025-05-22 14:26:18 +08:00
  • 6a29abdefd Merge pull request #6298 from wangbluo/upgrade_command Hanks 2025-05-22 14:21:58 +08:00
  • 6196faad3c Merge pull request #6318 from wangbluo/upgrade_t5 Hanks 2025-05-22 14:21:04 +08:00
  • 33614b84ce Merge pull request #6306 from wangbluo/upgrade_sam Hanks 2025-05-22 14:19:20 +08:00
  • e7ce5821de Merge pull request #6313 from wangbluo/upgrade_gptj Hanks 2025-05-22 14:18:49 +08:00
  • de2ad3b206 fix default eval setting (#6321) Tong Li 2025-05-22 11:52:41 +08:00
  • 6875a8a1cf [upgrade]upgrade mistral (#6296) flybird11111 2025-05-21 16:14:45 +08:00
  • 04516bb756 [upgrade]Upgrade vit (#6308) flybird11111 2025-05-21 16:14:20 +08:00
  • d0e13b85fd [upgrade]Upgrade mixtral (#6317) flybird11111 2025-05-21 16:14:05 +08:00
  • 2aa295e959 [upgrade]upgrade opt (#6307) flybird11111 2025-05-21 16:13:32 +08:00
  • 78a06f5ce3 fix missing tags parameter YeAnbang 2025-05-21 10:51:32 +08:00
  • 88e3b09c79 merge grpo-latest YeAnbang 2025-05-20 18:16:43 +08:00
  • 37663386bc fix metric calculation YeAnbang 2025-05-20 18:14:05 +08:00
  • 32afa7bf29 fix empty tensor (#6319) Tong Li 2025-05-20 17:41:44 +08:00
  • efb2d98da0 [pre-commit.ci] auto fixes from pre-commit.com hooks pre-commit-ci[bot] 2025-05-20 08:17:45 +00:00
  • 07fa048895 fix wangbluo 2025-05-20 16:13:34 +08:00
  • bcf2459db5 Merge pull request #6314 from hpcaitech/grpo-reward-dev YeAnbang 2025-05-20 10:06:00 +08:00
  • f8bd2db33f add uuid to rollout log grpo-reward-dev YeAnbang 2025-05-20 09:45:56 +08:00
  • 116621d004 merge reward and eval YeAnbang 2025-05-19 11:53:47 +08:00
  • 107470a360 fix logging rollouts YeAnbang 2025-05-17 21:12:58 +08:00
  • 03b41d6fb5 upgrade reward functions YeAnbang 2025-05-16 18:04:38 +08:00
  • 3c42c0ce82 Merge pull request #6309 from hpcaitech/grpo-eval-dev YeAnbang 2025-05-16 16:11:23 +08:00
  • 021914c565 support logging rollouts to wandb YeAnbang 2025-05-16 15:56:03 +08:00
  • 4e49f056d0 fix wangbluo 2025-05-16 15:32:16 +08:00
  • e1925b36c4 upgrade_gptj wangbluo 2025-05-16 15:28:04 +08:00
  • 203dfb1536 address conversation YeAnbang 2025-05-16 14:15:35 +08:00
  • 11a5854b50 remove redundant code and fix bugs YeAnbang 2025-05-16 14:08:23 +08:00
  • ced6b5e1c3 fix wangbluo 2025-05-16 11:39:50 +08:00
  • ab95624915 handle empty index (#6311) Tong Li 2025-05-16 10:00:10 +08:00
  • 6abffb9100 fix evaluation YeAnbang 2025-05-16 09:42:35 +08:00
  • 1644adf684 handle empty index Tong Li 2025-05-15 18:30:27 +08:00
  • a528921944 move prompt-level-filtering to buffer side YeAnbang 2025-05-15 18:30:32 +08:00
  • 55eee129d2 move prompt-level-filtering to buffer side YeAnbang 2025-05-15 18:16:50 +08:00
  • 10bc6af2b1 fix wangbluo 2025-05-15 17:55:24 +08:00
  • ba9fb549d5 fix wangbluo 2025-05-15 17:47:21 +08:00
  • 957e3a521a disable wandb tb syncing YeAnbang 2025-05-15 16:52:31 +08:00
  • 2223b64931 upgrade_t wangbluo 2025-05-15 14:31:24 +08:00
  • 4ec73298b2 use consumer global step YeAnbang 2025-05-15 14:15:40 +08:00
  • 18f2247a10 update consumer feat/agpo Chen Li 2025-05-14 18:19:47 +08:00
  • 094f119b3a merge YeAnbang 2025-05-14 18:13:47 +08:00