|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: xlm-roberta-base-finetuned-detests24 |
|
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-finetuned-detests24 |
|
|
|
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: 1.0941 |
|
- Accuracy: 0.8151 |
|
- F1-score: 0.7439 |
|
- Precision: 0.7380 |
|
- Recall: 0.7509 |
|
- Auc: 0.7509 |
|
|
|
## 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-score | Precision | Recall | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|:------:| |
|
| 0.4432 | 1.0 | 153 | 0.4079 | 0.8298 | 0.7158 | 0.7778 | 0.6893 | 0.6893 | |
|
| 0.4326 | 2.0 | 306 | 0.5061 | 0.7447 | 0.7078 | 0.7052 | 0.7840 | 0.7840 | |
|
| 0.2533 | 3.0 | 459 | 0.5227 | 0.7676 | 0.7195 | 0.7070 | 0.7709 | 0.7709 | |
|
| 0.3354 | 4.0 | 612 | 0.5113 | 0.8347 | 0.7689 | 0.7645 | 0.7737 | 0.7737 | |
|
| 0.2157 | 5.0 | 765 | 0.8228 | 0.8020 | 0.7484 | 0.7321 | 0.7830 | 0.7830 | |
|
| 0.1815 | 6.0 | 918 | 0.9407 | 0.8036 | 0.7528 | 0.7359 | 0.7917 | 0.7917 | |
|
| 0.0829 | 7.0 | 1071 | 0.9539 | 0.8363 | 0.7648 | 0.7676 | 0.7621 | 0.7621 | |
|
| 0.1077 | 8.0 | 1224 | 0.9649 | 0.8200 | 0.7501 | 0.7445 | 0.7566 | 0.7566 | |
|
| 0.0473 | 9.0 | 1377 | 1.0557 | 0.8200 | 0.7439 | 0.7439 | 0.7439 | 0.7439 | |
|
| 0.0632 | 10.0 | 1530 | 1.0941 | 0.8151 | 0.7439 | 0.7380 | 0.7509 | 0.7509 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
