Downloads · 30 days
11
22% of all-time downloads
xlm-roberta-base-finetuned-panx-de-data
moghis/xlm-roberta-base-finetuned-panx-de-data
xlm-roberta-base-finetuned-panx-de-data is a token classification model from moghis. 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
51
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 98%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- May 21, 2022
- Updated
- May 21, 2022
- SHA
- a41b4090
Try a prompt
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. -->
xlm-roberta-base-finetuned-panx-de-data
This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset. It achieves the following results on the evaluation set:
- Loss: 0.1372
- F1 Score: 0.8621
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- 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 | F1 Score |
|---|---|---|---|---|
| 0.2575 | 1.0 | 525 | 0.1621 | 0.8292 |
| 0.1287 | 2.0 | 1050 | 0.1378 | 0.8526 |
| 0.0831 | 3.0 | 1575 | 0.1372 | 0.8621 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Task
- Token Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- May 21, 2022
- Updated
- May 21, 2022