|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-ibo-finetuned |
|
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-ibo-finetuned |
|
|
|
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: 0.3021 |
|
- F1: 0.4617 |
|
- Roc Auc: 0.6940 |
|
- Accuracy: 0.5031 |
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.3848 | 1.0 | 123 | 0.3784 | 0.0 | 0.5 | 0.2150 | |
|
| 0.3508 | 2.0 | 246 | 0.3389 | 0.1062 | 0.5434 | 0.2839 | |
|
| 0.3227 | 3.0 | 369 | 0.3153 | 0.1134 | 0.5500 | 0.2881 | |
|
| 0.296 | 4.0 | 492 | 0.3016 | 0.2634 | 0.6048 | 0.4134 | |
|
| 0.2532 | 5.0 | 615 | 0.2942 | 0.3046 | 0.6338 | 0.4572 | |
|
| 0.2297 | 6.0 | 738 | 0.2838 | 0.3835 | 0.6544 | 0.4718 | |
|
| 0.2053 | 7.0 | 861 | 0.2839 | 0.4320 | 0.6687 | 0.4885 | |
|
| 0.1829 | 8.0 | 984 | 0.3069 | 0.4314 | 0.6773 | 0.4948 | |
|
| 0.1641 | 9.0 | 1107 | 0.3094 | 0.4295 | 0.6780 | 0.4802 | |
|
| 0.1532 | 10.0 | 1230 | 0.3021 | 0.4617 | 0.6940 | 0.5031 | |
|
| 0.1351 | 11.0 | 1353 | 0.3178 | 0.4432 | 0.6827 | 0.4843 | |
|
| 0.1288 | 12.0 | 1476 | 0.3184 | 0.4335 | 0.6737 | 0.4843 | |
|
| 0.1106 | 13.0 | 1599 | 0.3211 | 0.4530 | 0.6829 | 0.4760 | |
|
| 0.113 | 14.0 | 1722 | 0.3320 | 0.4437 | 0.6815 | 0.4781 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
