Downloads · 30 days
11
2% of all-time downloads
squeezebert-uncased-finetuned-mrpc
VitaliiVrublevskyi/squeezebert-uncased-finetuned-mrpc
squeezebert-uncased-finetuned-mrpc is a text classification model from VitaliiVrublevskyi. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
459
Public
Repo size
18.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin204 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- squeezebert
- Access
- Public
- Created
- Sep 11, 2023
- Updated
- Sep 14, 2023
- SHA
- 6f495d1d
Try a prompt
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. -->
squeezebert-uncased-finetuned-mrpc
This model is a fine-tuned version of squeezebert/squeezebert-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4261
- Accuracy: 0.8137
- F1: 0.8733
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: 32
- eval_batch_size: 32
- seed: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 115 | 0.5015 | 0.7843 | 0.8603 |
| No log | 2.0 | 230 | 0.4571 | 0.7941 | 0.8627 |
| No log | 3.0 | 345 | 0.4261 | 0.8137 | 0.8733 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- squeezebert
- Created
- Sep 11, 2023
- Updated
- Sep 14, 2023