Downloads · 30 days
8
2% of all-time downloads
HeRo-finetuned-ner
msperka/HeRo-finetuned-ner
HeRo-finetuned-ner is a token classification model from msperka. 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
329
Public
Parameters
124M
1.5 GB 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
- Dec 25, 2023
- Updated
- Dec 25, 2023
- SHA
- 16d60ca1
Try a prompt
Base models
Datasets
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. -->
HeRo-finetuned-ner
This model is a fine-tuned version of HeNLP/HeRo on the nemo_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1244
- Precision: 0.8626
- Recall: 0.8485
- F1: 0.8555
- Accuracy: 0.9769
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2734 | 1.0 | 618 | 0.1445 | 0.8125 | 0.7576 | 0.7841 | 0.9667 |
| 0.0939 | 2.0 | 1236 | 0.1258 | 0.8449 | 0.8380 | 0.8414 | 0.9748 |
| 0.0545 | 3.0 | 1854 | 0.1244 | 0.8626 | 0.8485 | 0.8555 | 0.9769 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Created
- Dec 25, 2023
- Updated
- Dec 25, 2023