metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: xlmr_mask_punctuation
results: []
xlmr_mask_punctuation
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: 0.5160
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6352 | 0.05 | 500 | 1.4744 |
| 1.4623 | 0.11 | 1000 | 1.0987 |
| 1.1947 | 0.16 | 1500 | 1.1878 |
| 1.0693 | 0.21 | 2000 | 0.8077 |
| 0.9465 | 0.26 | 2500 | 0.8038 |
| 0.8394 | 0.32 | 3000 | 0.7772 |
| 0.8184 | 0.37 | 3500 | 0.8529 |
| 0.7773 | 0.42 | 4000 | 0.6255 |
| 0.7338 | 0.47 | 4500 | 0.6993 |
| 0.6935 | 0.53 | 5000 | 0.5952 |
| 0.6713 | 0.58 | 5500 | 0.5605 |
| 0.6636 | 0.63 | 6000 | 0.6588 |
| 0.6169 | 0.68 | 6500 | 0.5154 |
| 0.6045 | 0.74 | 7000 | 0.5374 |
| 0.5853 | 0.79 | 7500 | 0.5033 |
| 0.5752 | 0.84 | 8000 | 0.5002 |
| 0.5263 | 0.89 | 8500 | 0.5300 |
| 0.5512 | 0.95 | 9000 | 0.5138 |
| 0.541 | 1.0 | 9500 | 0.5160 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1