Downloads · 30 days
8
17% of all-time downloads
1008model
parkjigwang/1008model
1008model is a text classification model from parkjigwang. 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
47
Public
Parameters
109M
436 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024
- SHA
- a83afe9b
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. -->
1008model
This model is a fine-tuned version of beomi/kcbert-base on the LMH, the 10_class and the multi_labels datasets. It achieves the following results on the evaluation set:
- Loss: 0.1303
- Lrap: 0.8809
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: 64
- eval_batch_size: 64
- 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 | Lrap |
|---|---|---|---|---|
| No log | 1.0 | 235 | 0.1459 | 0.8585 |
| No log | 2.0 | 470 | 0.1265 | 0.8763 |
| 0.1694 | 3.0 | 705 | 0.1233 | 0.8798 |
| 0.1694 | 4.0 | 940 | 0.1285 | 0.8796 |
| 0.0767 | 5.0 | 1175 | 0.1303 | 0.8809 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024