Downloads · 30 days
7
13% of all-time downloads
roberta-base-ner-demo
enhjino/roberta-base-ner-demo
roberta-base-ner-demo is a token classification model from enhjino. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
53
Public
Parameters
124M
993 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors496 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 14, 2024
- Updated
- May 15, 2024
- SHA
- 9565927b
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-ner-demo
This model is a fine-tuned version of bayartsogt/mongolian-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1320
- Precision: 0.9254
- Recall: 0.9350
- F1: 0.9302
- Accuracy: 0.9800
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1711 | 1.0 | 477 | 0.0834 | 0.8308 | 0.8820 | 0.8556 | 0.9697 |
| 0.0642 | 2.0 | 954 | 0.0817 | 0.8323 | 0.8888 | 0.8596 | 0.9720 |
| 0.0401 | 3.0 | 1431 | 0.0935 | 0.8404 | 0.8930 | 0.8659 | 0.9720 |
| 0.0272 | 4.0 | 1908 | 0.1043 | 0.8506 | 0.8959 | 0.8727 | 0.9721 |
| 0.0148 | 5.0 | 2385 | 0.1051 | 0.9195 | 0.9309 | 0.9252 | 0.9793 |
| 0.007 | 6.0 | 2862 | 0.1181 | 0.9190 | 0.9298 | 0.9243 | 0.9789 |
| 0.0054 | 7.0 | 3339 | 0.1185 | 0.9250 | 0.9337 | 0.9293 | 0.9796 |
| 0.0027 | 8.0 | 3816 | 0.1252 | 0.9239 | 0.9342 | 0.9290 | 0.9801 |
| 0.0018 | 9.0 | 4293 | 0.1298 | 0.9247 | 0.9335 | 0.9291 | 0.9799 |
| 0.0015 | 10.0 | 4770 | 0.1320 | 0.9254 | 0.9350 | 0.9302 | 0.9800 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Languages
- mn
- Created
- May 14, 2024
- Updated
- May 15, 2024