Commit Graph

8 Commits (2718fe1960f2cb465acac18108fe4d17eab80ea8)

Author SHA1 Message Date
Litar 2718fe1960
Update train_grpo.py 2025-10-26 22:22:23 +08:00
Litar 3052baff06
Update train_grpo.py 2025-10-26 22:20:58 +08:00
jingyaogong e8484874f5 [feat] pause-training 2025-10-26 18:49:52 +08:00
jingyaogong a82526da11 [feat] shuffle data 2025-10-23 20:13:28 +08:00
jingyaogong 805744e60a [fix] loss-issues-430 2025-10-23 19:08:42 +08:00
jingyaogong 463044e92a [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
jingyaogong fa7dff8291 [fix] graph-oom & ddp-pos_cis 2025-10-23 14:22:13 +08:00
jingyaogong 7d877db79b [feat] minimind-2510 2025-10-21 21:19:47 +08:00