[GH-ISSUE #46] details about the paper #44

Open
opened 2026-10-26 21:07:32 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @Brucewuzhang on GitHub (Sep 4, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-Coder-V2/issues/46

Hi, thanks for your great work. I found that the number of total tokens reported in the paper (which is around 2T) is far less than the reported further training token (which is 6T), can you kindly share the reason? is it because the whole corpus has been trained for around 3 epochs?

Originally created by @Brucewuzhang on GitHub (Sep 4, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-Coder-V2/issues/46 Hi, thanks for your great work. I found that the number of total tokens reported in the paper (which is around 2T) is far less than the reported further training token (which is 6T), can you kindly share the reason? is it because the whole corpus has been trained for around 3 epochs?
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-Coder-V2#44
No description provided.