Downloads · 30 days
18
26% of all-time downloads
bertweet-base_3_4_2e-05_0.01
YanJiangJerry/bertweet-base_3_4_2e-05_0.01
bertweet-base_3_4_2e-05_0.01 is a text classification model from YanJiangJerry. 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
69
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin540 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Aug 5, 2023
- Updated
- Aug 5, 2023
- SHA
- ff379e0d
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. -->
bertweet-base_3_4_2e-05_0.01
This model is a fine-tuned version of vinai/bertweet-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9140
- F1: 0.7655
- Recall: 0.7655
- Precision: 0.7655
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: 4
- eval_batch_size: 4
- seed: 42
- 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 | F1 | Recall | Precision |
|---|---|---|---|---|---|---|
| 0.753 | 1.0 | 745 | 0.7215 | 0.7655 | 0.7655 | 0.7655 |
| 0.6313 | 2.0 | 1490 | 0.7928 | 0.7763 | 0.7763 | 0.7763 |
| 0.402 | 3.0 | 2235 | 0.9140 | 0.7655 | 0.7655 | 0.7655 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- Created
- Aug 5, 2023
- Updated
- Aug 5, 2023