Downloads · 30 days
17
1% of all-time downloads
albert-base-v2-finetuned-rte
anirudh21/albert-base-v2-finetuned-rte
albert-base-v2-finetuned-rte is a text classification model from anirudh21. 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
1.4K
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin46.8 MB · 97%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- albert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jan 25, 2022
- SHA
- a05e21fb
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. -->
albert-base-v2-finetuned-rte
This model is a fine-tuned version of albert-base-v2 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.2496
- Accuracy: 0.7581
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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 249 | 0.5914 | 0.6751 |
| No log | 2.0 | 498 | 0.5843 | 0.7184 |
| 0.5873 | 3.0 | 747 | 0.6925 | 0.7220 |
| 0.5873 | 4.0 | 996 | 1.1613 | 0.7545 |
| 0.2149 | 5.0 | 1245 | 1.2496 | 0.7581 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.0
- Tokenizers 0.10.3
- Task
- Text Classification
- Library
- transformers
- Type
- albert
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Jan 25, 2022