Downloads · 30 days
17
28% of all-time downloads
phobert-large_baseline_words
VampeeHuntee/phobert-large_baseline_words
phobert-large_baseline_words is a token classification model from VampeeHuntee. 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
60
Public
Parameters
368M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Jun 12, 2024
- Updated
- Jun 12, 2024
- SHA
- 724e1e81
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. -->
phobert-large_baseline_words
This model is a fine-tuned version of vinai/phobert-large on the covid19_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0943
- Patient Id: 0.9863
- Name: 0.9542
- Gender: 0.9664
- Age: 0.9633
- Job: 0.8300
- Location: 0.9521
- Organization: 0.9188
- Date: 0.9842
- Symptom And Disease: 0.8773
- Transportation: 1.0
- F1 Macro: 0.9433
- F1 Micro: 0.9521
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: 8
- eval_batch_size: 8
- 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 | Patient Id | Name | Gender | Age | Job | Location | Organization | Date | Symptom And Disease | Transportation | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2801 | 1.0 | 629 | 0.0981 | 0.9840 | 0.9455 | 0.9045 | 0.9010 | 0.5837 | 0.9265 | 0.8726 | 0.9812 | 0.8611 | 0.9831 | 0.8943 | 0.9266 |
| 0.0446 | 2.0 | 1258 | 0.0897 | 0.9863 | 0.9549 | 0.9501 | 0.9722 | 0.7833 | 0.9355 | 0.8907 | 0.9852 | 0.8814 | 0.9721 | 0.9312 | 0.9434 |
| 0.0283 | 3.0 | 1887 | 0.0809 | 0.9867 | 0.9516 | 0.9551 | 0.9695 | 0.7857 | 0.9487 | 0.9086 | 0.9860 | 0.8845 | 1.0 | 0.9376 | 0.9502 |
| 0.0198 | 4.0 | 2516 | 0.0905 | 0.9863 | 0.9542 | 0.9647 | 0.9633 | 0.8287 | 0.9483 | 0.9159 | 0.9842 | 0.8897 | 1.0 | 0.9435 | 0.9516 |
| 0.0134 | 5.0 | 3145 | 0.0943 | 0.9863 | 0.9542 | 0.9664 | 0.9633 | 0.8300 | 0.9521 | 0.9188 | 0.9842 | 0.8773 | 1.0 | 0.9433 | 0.9521 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Languages
- vi
- Created
- Jun 12, 2024
- Updated
- Jun 12, 2024