alibaba / alibaba/EasyTransfer

pai-bert-tiny-zh模型不收敛

Open
#32 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
861
Forks
162
PR merge metrics
No merged PRs in 30d

Description

这个模型根本训练不起来....比随机初始化还差

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing training for the pai-bert-tiny-zh model and compare its behavior with random initialization. The issue provides no file, entry point, configuration, or test to inspect, so identify the relevant training path before investigating why the model does not converge. Done should include a reproducible diagnosis and a verified correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.