Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Small typo fixes for model card: electra-base-german-uncased #6555

Merged
merged 2 commits into from
Aug 18, 2020
Merged

Small typo fixes for model card: electra-base-german-uncased #6555

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
40b5307
Update README.md
PhilipMay Aug 18, 2020
b2a7699
Update model_cards/german-nlp-group/electra-base-german-uncased/READM…
julien-c Aug 18, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions model_cards/german-nlp-group/electra-base-german-uncased/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ This Model is suitable for Training on many downstream tasks in German (Q&A, Sen

It can be used as a drop-in Replacement for **BERT** in most down-stream tasks (**ELECTRA** is even implemented as an extended **BERT** Class).

On the time of the realse (August 2020) this Model is the best performing publicly available German NLP Model on various German Evaluation Metrics (CONLL, GermEval19 Coarse, GermEval19 Fine).
On the time of the realse (August 2020) this Model is the best performing publicly available German NLP Model on various German Evaluation Metrics (CONLL03-DE, GermEval18 Coarse, GermEval18 Fine). For GermEval18 Coarse results see below. More will be published soon.
julien-c marked this conversation as resolved.
Show resolved Hide resolved

## Installation

Expand Down Expand Up @@ -159,4 +159,3 @@ We tried the following approaches which we found had no positive influence:

- **Increased Vocab Size**: Leads to more parameters and thus reduced examples/sec while no visible Performance gains were measured
- **Decreased Batch-Size**: The original Electra was trained with a Batch Size per TPU Core of 16 whereas this Model was trained with 32 BS / TPU Core. We found out that 32 BS leads to better results when you compare metrics over computation time