metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: xlm-roberta-base-VietNam-train
results: []
xlm-roberta-base-VietNam-train
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4360
- Accuracy: 0.84
- F1: 0.7909
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.9668 | 1.0 | 44 | 0.8894 | 0.58 | 0.4258 |
0.8302 | 2.0 | 88 | 0.6932 | 0.59 | 0.4479 |
0.6805 | 3.0 | 132 | 0.5111 | 0.84 | 0.7875 |
0.5672 | 4.0 | 176 | 0.4705 | 0.85 | 0.7981 |
0.5517 | 5.0 | 220 | 0.4360 | 0.84 | 0.7909 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3