metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: QA_REDACTION_NOV1
results: []
QA_REDACTION_NOV1
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0170
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9087 | 1.0 | 928 | 0.0382 |
| 0.0727 | 2.0 | 1856 | 0.0195 |
| 0.0954 | 3.0 | 2784 | 3.1621 |
| 0.3541 | 4.0 | 3712 | 0.0192 |
| 0.0849 | 5.0 | 4640 | 0.0164 |
| 0.0317 | 6.0 | 5568 | 0.0131 |
| 0.0327 | 7.0 | 6496 | 0.0151 |
| 0.0407 | 8.0 | 7424 | 0.0142 |
| 0.0383 | 9.0 | 8352 | 0.0176 |
| 0.0182 | 10.0 | 9280 | 0.0170 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1