metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: mtl-xlmr-base-viwiki-v2
results: []
mtl-xlmr-base-viwiki-v2
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: 0.6919
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7756 | 1.0 | 960 | 0.7972 |
| 0.6104 | 2.0 | 1920 | 0.6775 |
| 0.5942 | 3.0 | 2880 | 0.6227 |
| 0.6037 | 4.0 | 3840 | 0.6349 |
| 0.5208 | 5.0 | 4800 | 0.5975 |
| 0.347 | 6.0 | 5760 | 0.6008 |
| 0.415 | 7.0 | 6720 | 0.6142 |
| 0.3473 | 8.0 | 7680 | 0.6252 |
| 0.3312 | 9.0 | 8640 | 0.6748 |
| 0.2134 | 10.0 | 9600 | 0.6919 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.2.1
- Datasets 2.20.0
- Tokenizers 0.19.1