Downloads · 30 days
8
3% of all-time downloads
tiny-bert-sst2-distilled
Waldbrand100/tiny-bert-sst2-distilled
tiny-bert-sst2-distilled is a text classification model from Waldbrand100. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
253
Public
Parameters
4.4M
667 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt105 MB · 59%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 18, 2024
- Updated
- Dec 19, 2024
- SHA
- d79c4a87
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. -->
tiny-bert-sst2-distilled
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4375
- Accuracy: 0.8073
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: 0.00030231468122836585
- train_batch_size: 128
- eval_batch_size: 128
- seed: 33
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4362 | 1.0 | 527 | 0.4507 | 0.7970 |
| 0.3092 | 2.0 | 1054 | 0.4375 | 0.8073 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Dec 18, 2024
- Updated
- Dec 19, 2024