TExAS-SQuAD-de
This model is a fine-tuned version of xlm-roberta-base on the TExAS-SQuAD-de dataset. It achieves the following results on the evaluation set:
- Exact match: 61.45%
- F1-score: 66.12%
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 |
|---|---|---|---|
| 1.8084 | 1.0 | 4233 | 1.5897 |
| 1.5696 | 2.0 | 8466 | 1.5478 |
| 1.4196 | 3.0 | 12699 | 1.5754 |
Framework versions
- Transformers 4.12.2
- Pytorch 1.8.1+cu101
- Datasets 1.12.1
- Tokenizers 0.10.3
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for saattrupdan/xlmr-base-texas-squad-de
Base model
FacebookAI/xlm-roberta-base