Downloads · 30 days
8
14% of all-time downloads
tinybert_base_train_kd_mrpc
gokulsrinivasagan/tinybert_base_train_kd_mrpc
tinybert_base_train_kd_mrpc 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
58
Public
Parameters
67M
1.1 GB 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
- f3a271d9
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_mrpc
This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_kd on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5067
- Accuracy: 0.7917
- F1: 0.8562
- Combined Score: 0.8239
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6588 | 1.0 | 15 | 0.6283 | 0.6667 | 0.7655 | 0.7161 |
| 0.5998 | 2.0 | 30 | 0.5731 | 0.6961 | 0.8056 | 0.7509 |
| 0.5433 | 3.0 | 45 | 0.5614 | 0.7402 | 0.8333 | 0.7868 |
| 0.4574 | 4.0 | 60 | 0.5067 | 0.7917 | 0.8562 | 0.8239 |
| 0.3525 | 5.0 | 75 | 0.5204 | 0.7574 | 0.8203 | 0.7888 |
| 0.3015 | 6.0 | 90 | 0.8296 | 0.7426 | 0.8382 | 0.7904 |
| 0.2978 | 7.0 | 105 | 0.7863 | 0.75 | 0.8401 | 0.7951 |
| 0.2163 | 8.0 | 120 | 0.7096 | 0.7574 | 0.8308 | 0.7941 |
| 0.1329 | 9.0 | 135 | 0.7977 | 0.7549 | 0.8214 | 0.7882 |
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