Downloads · 30 days
4
17% of all-time downloads
roberta-base_ag_news2
clackshen/roberta-base_ag_news2
roberta-base_ag_news2 is a text classification model from clackshen. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Parameters
125M
499 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Oct 22, 2024
- Updated
- Oct 22, 2024
- SHA
- 8b593375
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. -->
roberta-base_ag_news2
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4152
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3815 | 1.0 | 375 | 0.4152 |
| 0.4249 | 2.0 | 750 | 0.4616 |
| 0.3977 | 3.0 | 1125 | 0.4938 |
| 0.1759 | 4.0 | 1500 | 0.5023 |
| 0.0791 | 5.0 | 1875 | 0.5065 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Oct 22, 2024
- Updated
- Oct 22, 2024