Downloads · 30 days
10
5% of all-time downloads
t5-base_cola_dense_epochs-6_exp_size_4
thrunlab/t5-base_cola_dense_epochs-6_exp_size_4
t5-base_cola_dense_epochs-6_exp_size_4 is a text classification model from thrunlab. 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
204
Public
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin894 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Oct 24, 2023
- Updated
- Oct 24, 2023
- SHA
- be6f7d41
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. -->
t5-base_cola_dense_epochs-6_exp_size_4
This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4622
- Accuracy: 0.8236
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: 32
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5883 | 0.19 | 50 | 0.5895 | 0.6913 |
| 0.4961 | 0.37 | 100 | 0.5788 | 0.7574 |
| 0.5036 | 0.56 | 150 | 0.5192 | 0.7891 |
| 0.4038 | 0.75 | 200 | 0.4774 | 0.8025 |
| 0.4461 | 0.93 | 250 | 0.5380 | 0.7929 |
| 0.3573 | 1.12 | 300 | 0.5382 | 0.8169 |
| 0.3508 | 1.31 | 350 | 0.4526 | 0.8255 |
| 0.3379 | 1.49 | 400 | 0.4777 | 0.8245 |
| 0.3964 | 1.68 | 450 | 0.5148 | 0.8178 |
| 0.4137 | 1.87 | 500 | 0.4622 | 0.8236 |
| 0.3036 | 2.05 | 550 | 0.5171 | 0.8236 |
| 0.2913 | 2.24 | 600 | 0.5269 | 0.8322 |
| 0.277 | 2.43 | 650 | 0.5298 | 0.8293 |
| 0.2431 | 2.61 | 700 | 0.5129 | 0.8313 |
| 0.3551 | 2.8 | 750 | 0.5396 | 0.8255 |
| 0.2697 | 2.99 | 800 | 0.5307 | 0.8293 |
| 0.2494 | 3.17 | 850 | 0.5549 | 0.8332 |
| 0.2734 | 3.36 | 900 | 0.5431 | 0.8255 |
| 0.2886 | 3.54 | 950 | 0.5412 | 0.8245 |
| 0.3155 | 3.73 | 1000 | 0.5409 | 0.8284 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Oct 24, 2023
- Updated
- Oct 24, 2023