Downloads · 30 days
7
18% of all-time downloads
roberta_cws_granular_segment
tjspross/roberta_cws_granular_segment
roberta_cws_granular_segment is a token classification model from tjspross. Use it when you need labels on individual words, such as names. 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
38
Public
Parameters
324M
5.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 17, 2025
- Updated
- Mar 26, 2025
- SHA
- 992b2cfa
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_cws_granular_segment
This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2465
- Precision: 0.9228
- Recall: 0.9244
- F1: 0.9236
- Accuracy: 0.9276
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 85 | 0.2742 | 0.9173 | 0.9042 | 0.9107 | 0.9128 |
| No log | 2.0 | 170 | 0.2490 | 0.9287 | 0.9065 | 0.9175 | 0.9188 |
| No log | 3.0 | 255 | 0.2465 | 0.9228 | 0.9244 | 0.9236 | 0.9276 |
Framework versions
- Transformers 4.50.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 17, 2025
- Updated
- Mar 26, 2025