Comments (3)
This is the test case matrix where the modified code behaves differently compared with the original code. The linear module maps to the whitelist and the rest belongs to the blacklist. This is generally the idea behind it.
Test Case | Module | Parameter | Original Code | Modified Code |
---|---|---|---|---|
1 | Linear | weight | decay | decay |
1 | Linear | bias | no_decay | no_decay |
2 | LayerNorm | weight | no_decay | no_decay |
2 | LayerNorm | bias | no_decay | no_decay |
3 | Embedding | weight | no_decay | no_decay |
4 | Custom | custom_param | N/A | decay |
from mingpt.
modifying the else should help fix it.
code:
decay = set()
no_decay = set()
blacklist_weight_modules = (torch.nn.LayerNorm, torch.nn.Embedding)
for mn, m in self.named_modules():
for pn, p in m.named_parameters():
fpn = f"{mn}.{pn}" if mn else pn # full param name
if pn.endswith("bias") or isinstance(m, blacklist_weight_modules):
no_decay.add(fpn)
elif pn.endswith("weight"):
decay.add(fpn)
from mingpt.
modifying the else should help fix it.
code:
decay = set() no_decay = set() blacklist_weight_modules = (torch.nn.LayerNorm, torch.nn.Embedding) for mn, m in self.named_modules(): for pn, p in m.named_parameters(): fpn = f"{mn}.{pn}" if mn else pn # full param name if pn.endswith("bias") or isinstance(m, blacklist_weight_modules): no_decay.add(fpn) elif pn.endswith("weight"): decay.add(fpn)
Thanks, missed the logic there.
from mingpt.
Related Issues (20)
- Stop words?
- how does this compare to aitextgen?
- Information leak in training procedure?
- Crashed Encoder possible data corruption
- About layer norm dimention parameter: HOT 1
- 生成圖片
- Question: does it support other utf-8 natual language? HOT 1
- Output of CausalSelfAttention HOT 1
- How can I run a trained model and can't run Test_ Hugging face_ Import. py HOT 1
- AssertionError when run generate.ipynb with default parameter HOT 4
- Should -1 marker (as special token) be counted in vocab_size? HOT 1
- What's the max output tokens this model supports? HOT 1
- what is the minimum hardware requirement to train
- which pytorch version should be used pls for windows OS only CPU use only for inference ?
- error line 200, in from_pretrained assert len(keys) == len(sd) HOT 7
- concatenate two BPE tokenizer
- Caching for generation HOT 1
- Facilitating setup with popular tools
- tests do not run in project as built HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mingpt.