PeterGriffinJin
7d6a15bfc5
remove unuseful file
2025-04-29 16:02:26 +00:00
PeterGriffinJin
a2870cb320
add multinode support
2025-04-10 12:26:43 +00:00
PeterGriffinJin
0b26e614f7
fix proto bug
2025-04-04 02:54:21 +00:00
PeterGriffinJin
7530318919
fix test dataloader shuffle bug
2025-04-02 22:23:11 +00:00
PeterGriffinJin
d874947732
fix turns_stats logging bug
2025-03-21 14:58:42 +00:00
PeterGriffinJin
83d10313be
add action status
2025-03-19 22:19:27 +00:00
PeterGriffinJin
9ec2fa9892
fix grpo id bug
2025-03-19 18:59:19 +00:00
PeterGriffinJin
8c7f04ca45
response length include retrieval info
2025-03-19 00:36:21 +00:00
Bowen Jin
50cedb2c00
Merge pull request #21 from xiaobo-yang/yxb/fix-info-mask-bugs
...
Fix bugs related to loss mask, meta info, and response length
2025-03-18 19:33:50 -05:00
PeterGriffinJin
4b3c09451a
fix kl loss issue
2025-03-18 20:07:47 +00:00
PeterGriffinJin
e85506f143
remove unnecessary codes
2025-03-17 16:08:33 +00:00
xiaobo-yang
32719b5119
Fix bugs related to loss mask, meta info, and response length
...
1. Construct the loss mask immediately after obtaining the observation to prevent encoding misalignment when converting back to tokens after text transformation.
2. Follow up on meta info to ensure that the test batch can apply do sample.
3. Remove the recording of info information for response length.
2025-03-14 14:25:40 +08:00
PeterGriffinJin
118c6e7361
fix reward bug
2025-03-13 19:18:56 +00:00
PeterGriffinJin
5fdfd52ac4
add logger
2025-03-01 04:28:07 +00:00
PeterGriffinJin
f0b4eef7d3
fix logging_utils bug
2025-03-01 04:08:28 +00:00
PeterGriffinJin
068516be64
Initial commit
2025-02-28 15:16:19 +00:00
