Downloads · 30 days
4
19% of all-time downloads
t5-small-qnli
lightsout19/t5-small-qnli
t5-small-qnli is a text classification model from lightsout19. 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
21
Public
Parameters
60.8M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors243 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024
- SHA
- e47b7fa0
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. -->
t5-small-qnli
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3319
- Accuracy: 0.8977
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3933 | 1.0 | 13093 | 0.3401 | 0.8688 |
| 0.3351 | 2.0 | 26186 | 0.3176 | 0.8860 |
| 0.33 | 3.0 | 39279 | 0.3006 | 0.8942 |
| 0.3139 | 4.0 | 52372 | 0.3319 | 0.8977 |
| 0.3038 | 5.0 | 65465 | 0.3330 | 0.8973 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Text Classification
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024