Downloads · 30 days
5
18% of all-time downloads
myTinyBertSST2Distilled
nlpAI/myTinyBertSST2Distilled
myTinyBertSST2Distilled is a text classification model from nlpAI. 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
28
Public
Parameters
4.4M
35.1 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.5 MB · 95%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 21, 2024
- Updated
- May 21, 2024
- SHA
- ee03194e
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. -->
myTinyBertSST2Distilled
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: 0.4454
- Accuracy: 0.8028
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: 1e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3503 | 1.0 | 264 | 0.4493 | 0.7982 |
| 0.3463 | 2.0 | 528 | 0.4454 | 0.8028 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 21, 2024
- Updated
- May 21, 2024