Downloads · 30 days
16
3% of all-time downloads
xlmr-base-texas-squad-es
saattrupdan/xlmr-base-texas-squad-es
xlmr-base-texas-squad-es is a question answering model from saattrupdan. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
This model is a fine-tuned version of xlm-roberta-base on the TExAS-SQuAD-es dataset. It achieves the following results on the evaluation set: - Exact match: xx.xx% - F1-score: xx.xx%
All-time downloads
527
Public
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Dec 20, 2023
- SHA
- b9bed95f
Try a prompt
Base models
Model card
From the Hugging Face model README
TExAS-SQuAD-es
This model is a fine-tuned version of xlm-roberta-base on the TExAS-SQuAD-es dataset. It achieves the following results on the evaluation set:
- Exact match: xx.xx%
- F1-score: xx.xx%
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|
| 2.0645 | 0.24 | 1000 | 1.7915 |
| 1.8458 | 0.47 | 2000 | 1.7873 |
| 1.8208 | 0.71 | 3000 | 1.6628 |
| 1.7743 | 0.95 | 4000 | 1.5684 |
| 1.5636 | 1.18 | 5000 | 1.5686 |
| 1.6017 | 1.42 | 6000 | 1.5484 |
| 1.6271 | 1.66 | 7000 | 1.5173 |
| 1.5975 | 1.89 | 8000 | 1.5209 |
| 1.477 | 2.13 | 9000 | 1.5766 |
| 1.4389 | 2.37 | 10000 | 1.5392 |
| 1.3389 | 2.6 | 11000 | 1.5298 |
| 1.437 | 2.84 | 12000 | 1.5504 |
Framework versions
- Transformers 4.12.2
- Pytorch 1.8.1+cu101
- Datasets 1.12.1
- Tokenizers 0.10.3
- Task
- Question Answering
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Mar 2, 2022
- Updated
- Dec 20, 2023