bert-base-german-cased-finetuned-subj

tbosse/bert-base-german-cased-finetuned-subj

bert-base-german-cased-finetuned-subj is a token classification model from tbosse. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

433

Public

Repo size

868 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin434 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Mar 28, 2022
Updated: Mar 28, 2022
SHA: dbe0faa3

Try a prompt

Model card

From the Hugging Face model README

bert-base-german-cased-finetuned-subj

This model is a fine-tuned version of bert-base-german-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1424
Precision: 0.6514
Recall: 0.0186
F1: 0.0363
Accuracy: 0.9511

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	140	0.1588	0.6	0.0016	0.0031	0.9507
No log	2.0	280	0.1466	0.75	0.0039	0.0078	0.9508
No log	3.0	420	0.1424	0.6514	0.0186	0.0363	0.9511

Framework versions

Transformers 4.17.0
Pytorch 1.10.0+cu111
Datasets 2.0.0
Tokenizers 0.11.6

Task: Token Classification
Library: transformers
Type: bert
License: mit
Created: Mar 28, 2022
Updated: Mar 28, 2022