babysor / babysor/MockingBird

Trainable Parameters: 0.000M正常吗

Open
#922 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
36.9k
Forks
5.2k
PR merge metrics
No merged PRs in 30d

Description

**Summary[问题简述(一句话)]**
我在训练自己的synthesizer时遇到如下提示:

\Saving the json with %s
data\ckpt\synthesizer\dan\dan.json
Trainable Parameters: 0.000M

是否正常?这是在训练吗?

**Env & To Reproduce[复现与环境]**
Python 3.9.8
模型用的是“75k steps 用3个开源数据集混合训练”

**Screenshots[截图(如有)]**
![屏幕截图 2023-06-26 011117](https://github.com/babysor/MockingBird/assets/123880399/8ebe023b-6fd8-4c74-b35a-2a41eecd901b)

Contributor guide

No contributing guide indexed for this repository

Research direction

No source file, test, or training entry point is named in the issue. Reproduce the run with the stated Python version and 75k-step mixed-data setup, then trace the parameter-count output and training logs to determine whether training is actually progressing; done means documenting whether 0.000M is expected and identifying the cause if it is not.

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.