Downloads · 30 days
10
3% of all-time downloads
gpt2-token-class
vp224/gpt2-token-class
gpt2-token-class is a token classification model from vp224. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
362
Public
Repo size
5.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin510 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- May 12, 2023
- Updated
- May 14, 2023
- SHA
- 055d7cfd
Try a prompt
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. -->
gpt2-token-class
This model is a fine-tuned version of brad1141/gpt2-finetuned-comp2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3140
- Precision: 0.8139
- Recall: 0.6070
- F1: 0.6418
- Accuracy: 0.8854
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2737 | 1.0 | 1796 | 0.3191 | 0.8066 | 0.6061 | 0.6402 | 0.8845 |
| 0.2846 | 2.0 | 3592 | 0.3140 | 0.8139 | 0.6070 | 0.6418 | 0.8854 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- May 12, 2023
- Updated
- May 14, 2023