|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: xlm-roberta-base-Mixed-replace-vi |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# xlm-roberta-base-Mixed-replace-vi |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6016 |
|
- Accuracy: 0.8018 |
|
- F1: 0.7987 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.1619 | 1.0 | 294 | 1.2621 | 0.7882 | 0.7966 | |
|
| 0.1296 | 2.0 | 588 | 1.3555 | 0.7973 | 0.8000 | |
|
| 0.1191 | 3.0 | 882 | 1.4282 | 0.7837 | 0.7902 | |
|
| 0.0991 | 4.0 | 1176 | 1.3073 | 0.7958 | 0.7980 | |
|
| 0.0478 | 5.0 | 1470 | 1.5468 | 0.7988 | 0.7996 | |
|
| 0.0527 | 6.0 | 1764 | 1.4876 | 0.7988 | 0.8033 | |
|
| 0.0528 | 7.0 | 2058 | 1.4934 | 0.8064 | 0.8012 | |
|
| 0.0474 | 8.0 | 2352 | 1.5715 | 0.8079 | 0.8047 | |
|
| 0.04 | 9.0 | 2646 | 1.5777 | 0.8033 | 0.7978 | |
|
| 0.0266 | 10.0 | 2940 | 1.6016 | 0.8018 | 0.7987 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
