Downloads · 30 days
12
29% of all-time downloads
german-party-sentiment-bert-1-1-1
Commandante/german-party-sentiment-bert-1-1-1
german-party-sentiment-bert-1-1-1 is a text classification model from Commandante. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
41
Public
Parameters
109M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 26, 2024
- Updated
- Jan 29, 2024
- SHA
- 621a9846
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
german-party-sentiment-bert-20240126
This model is a fine-tuned version of mdraw/german-news-sentiment-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0838
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: 8e-06
- train_batch_size: 20
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 120
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3186 | 1.0 | 25 | 1.1448 |
| 1.1259 | 2.0 | 50 | 1.0858 |
| 1.1259 | 3.0 | 75 | 1.0838 |
| 1.0331 | 4.0 | 100 | 1.1488 |
| 1.0331 | 5.0 | 125 | 1.1276 |
| 0.957 | 6.0 | 150 | 1.1704 |
| 0.957 | 7.0 | 175 | 1.1845 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu118
- Tokenizers 0.15.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Jan 26, 2024
- Updated
- Jan 29, 2024