Downloads · 30 days
13
1% of all-time downloads
news_topic_classification
kartashoffv/news_topic_classification
news_topic_classification is a text classification model from kartashoffv. 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
993
Public
Parameters
178M
5.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin712 MB · 50%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Sep 13, 2023
- Updated
- Sep 13, 2023
- SHA
- 14d1080c
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. -->
news_topic_classification
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7058
- F1: 0.8712
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.7979 | 1.0 | 700 | 0.5218 | 0.8569 |
| 0.3673 | 2.0 | 1400 | 0.5402 | 0.8697 |
| 0.2483 | 3.0 | 2100 | 0.6277 | 0.8668 |
| 0.1684 | 4.0 | 2800 | 0.6599 | 0.8712 |
| 0.1099 | 5.0 | 3500 | 0.7058 | 0.8712 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Sep 13, 2023
- Updated
- Sep 13, 2023