Downloads · 30 days
8
21% of all-time downloads
DLthon_BERT_2
jhkim12/DLthon_BERT_2
DLthon_BERT_2 is a text classification model from jhkim12. 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
39
Public
Parameters
109M
2.2 GB 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 7, 2024
- Updated
- Oct 7, 2024
- SHA
- 7f107879
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. -->
DLthon_BERT_2
This model is a fine-tuned version of beomi/kcbert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0270
- F1: 0.9939
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- 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 | F1 |
|---|---|---|---|---|
| No log | 1.0 | 140 | 0.2067 | 0.9317 |
| No log | 2.0 | 280 | 0.1499 | 0.9595 |
| No log | 3.0 | 420 | 0.0540 | 0.9839 |
| 0.2578 | 4.0 | 560 | 0.0314 | 0.9939 |
| 0.2578 | 5.0 | 700 | 0.0270 | 0.9939 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 7, 2024
- Updated
- Oct 7, 2024