|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: xlm-roberta-base_single_finetuned_on_cedr_augmented |
|
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_single_finetuned_on_cedr_augmented |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4650 |
|
- Accuracy: 0.8820 |
|
- F1: 0.8814 |
|
- Precision: 0.8871 |
|
- Recall: 0.8820 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.8868 | 1.0 | 69 | 0.4939 | 0.8403 | 0.8376 | 0.8431 | 0.8403 | |
|
| 0.4248 | 2.0 | 138 | 0.3969 | 0.8779 | 0.8768 | 0.8798 | 0.8779 | |
|
| 0.3197 | 3.0 | 207 | 0.4019 | 0.8758 | 0.8757 | 0.8758 | 0.8758 | |
|
| 0.2737 | 4.0 | 276 | 0.3915 | 0.8831 | 0.8827 | 0.8847 | 0.8831 | |
|
| 0.2053 | 5.0 | 345 | 0.4445 | 0.8643 | 0.8650 | 0.8714 | 0.8643 | |
|
| 0.1705 | 6.0 | 414 | 0.4650 | 0.8820 | 0.8814 | 0.8871 | 0.8820 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
