metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: xlm_70k_co_vn
results: []
xlm_70k_co_vn
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1934
- Accuracy: 0.9679
- F1: 0.9680
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2054 | 1.0 | 1719 | 0.1449 | 0.9595 | 0.9599 |
| 0.1226 | 2.0 | 3438 | 0.1261 | 0.9638 | 0.9641 |
| 0.1038 | 3.0 | 5157 | 0.1055 | 0.9682 | 0.9684 |
| 0.0856 | 4.0 | 6876 | 0.1107 | 0.9676 | 0.9678 |
| 0.0732 | 5.0 | 8595 | 0.1240 | 0.9680 | 0.9680 |
| 0.0595 | 6.0 | 10314 | 0.1457 | 0.9679 | 0.9679 |
| 0.0494 | 7.0 | 12033 | 0.1931 | 0.9667 | 0.9668 |
| 0.0425 | 8.0 | 13752 | 0.1772 | 0.9672 | 0.9674 |
| 0.0375 | 9.0 | 15471 | 0.1867 | 0.9683 | 0.9684 |
| 0.034 | 10.0 | 17190 | 0.1934 | 0.9679 | 0.9680 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1