|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: fine-tuned-NLI-multilingual-with-xlm-roberta-large |
|
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. --> |
|
|
|
# fine-tuned-NLI-multilingual-with-xlm-roberta-large |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4158 |
|
- Accuracy: 0.8600 |
|
- F1: 0.8612 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- 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 | Accuracy | F1 | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:--------:|:------:|:---------------:| |
|
| 0.4647 | 0.5 | 1613 | 0.8396 | 0.8403 | 0.4262 | |
|
| 0.4437 | 1.0 | 3226 | 0.8511 | 0.8522 | 0.4042 | |
|
| 0.3956 | 1.5 | 4839 | 0.3783 | 0.8604 | 0.8602 | |
|
| 0.3639 | 2.0 | 6452 | 0.3913 | 0.8592 | 0.8600 | |
|
| 0.323 | 2.5 | 8065 | 0.3783 | 0.8657 | 0.8659 | |
|
| 0.3186 | 3.0 | 9678 | 0.3850 | 0.8626 | 0.8625 | |
|
| 0.2485 | 3.5 | 11291 | 0.4326 | 0.8597 | 0.8592 | |
|
| 0.2509 | 4.0 | 12904 | 0.4158 | 0.8600 | 0.8612 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.2.0 |
|
- Tokenizers 0.13.3 |
|
|
