Downloads · 30 days
10
37% of all-time downloads
tinybert_base_train_kd_wnli
gokulsrinivasagan/tinybert_base_train_kd_wnli
tinybert_base_train_kd_wnli is a text classification model from gokulsrinivasagan. 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
27
Public
Parameters
67M
536 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- 8024b7ee
Try a prompt
Base models
Datasets
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. -->
tinybert_base_train_kd_wnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_kd on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6884
- Accuracy: 0.5634
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: 256
- eval_batch_size: 256
- seed: 10
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8341 | 1.0 | 3 | 0.7071 | 0.4366 |
| 0.6963 | 2.0 | 6 | 0.6884 | 0.5634 |
| 0.6962 | 3.0 | 9 | 0.6948 | 0.5070 |
| 0.6958 | 4.0 | 12 | 0.7017 | 0.4366 |
| 0.6979 | 5.0 | 15 | 0.7054 | 0.4648 |
| 0.6946 | 6.0 | 18 | 0.7002 | 0.4648 |
| 0.696 | 7.0 | 21 | 0.7013 | 0.4648 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025