Downloads · 30 days
3
1% of all-time downloads
ruBertTiny_attr_name_addv2
Shakhovak/ruBertTiny_attr_name_addv2
ruBertTiny_attr_name_addv2 is a text classification model from Shakhovak. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
323
Public
Parameters
29.2M
117 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors117 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024
- SHA
- 3001c38c
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. -->
ruBertTiny_attr_name_addv2
This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3093
- Accuracy: 0.8889
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5285 | 0.2739 | 10000 | 0.4378 | 0.8120 |
| 0.463 | 0.5478 | 20000 | 0.4148 | 0.8077 |
| 0.4241 | 0.8217 | 30000 | 0.4169 | 0.8077 |
| 0.3883 | 1.0956 | 40000 | 0.3991 | 0.8248 |
| 0.3607 | 1.3695 | 50000 | 0.3772 | 0.8419 |
| 0.3496 | 1.6434 | 60000 | 0.3689 | 0.8333 |
| 0.3408 | 1.9173 | 70000 | 0.3249 | 0.8718 |
| 0.3127 | 2.1912 | 80000 | 0.3308 | 0.8803 |
| 0.2974 | 2.4651 | 90000 | 0.3100 | 0.8803 |
| 0.2961 | 2.7391 | 100000 | 0.3057 | 0.8974 |
| 0.2884 | 3.0130 | 110000 | 0.3024 | 0.8889 |
| 0.2594 | 3.2869 | 120000 | 0.3040 | 0.8846 |
| 0.2588 | 3.5608 | 130000 | 0.3169 | 0.8803 |
| 0.2581 | 3.8347 | 140000 | 0.2961 | 0.8974 |
| 0.2483 | 4.1086 | 150000 | 0.3061 | 0.8803 |
| 0.2375 | 4.3825 | 160000 | 0.3045 | 0.8846 |
| 0.2378 | 4.6564 | 170000 | 0.3091 | 0.8889 |
| 0.2367 | 4.9303 | 180000 | 0.3093 | 0.8889 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.0.1+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024