metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: QA_REDACTION_NOV1_17
results: []
QA_REDACTION_NOV1_17
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: 0.0463
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: 3
- eval_batch_size: 3
- 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 |
|---|---|---|---|
| 0.0217 | 1.0 | 1913 | 0.0561 |
| 0.076 | 2.0 | 3826 | 0.0338 |
| 0.0732 | 3.0 | 5739 | 0.0277 |
| 0.0483 | 4.0 | 7652 | 0.0250 |
| 0.0282 | 5.0 | 9565 | 0.1352 |
| 0.0255 | 6.0 | 11478 | 0.0270 |
| 0.0227 | 7.0 | 13391 | 0.0282 |
| 0.0038 | 8.0 | 15304 | 0.0499 |
| 0.0178 | 9.0 | 17217 | 0.0439 |
| 0.0052 | 10.0 | 19130 | 0.0463 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1