|
--- |
|
license: apache-2.0 |
|
base_model: distilroberta-base |
|
tags: |
|
- text-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
widget: |
|
- text: Hello my friends, nice to see you all., Hi, Its good to see you. |
|
example_title: Equivalent |
|
model-index: |
|
- name: destilroberta-base-mrpc-glue-ces |
|
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. --> |
|
|
|
# destilroberta-base-mrpc-glue-ces |
|
|
|
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the guel and the mrpc datasets. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4664 |
|
- Accuracy: 0.8162 |
|
- F1: 0.8718 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.5436 | 1.09 | 500 | 0.4664 | 0.8162 | 0.8718 | |
|
| 0.3757 | 2.18 | 1000 | 0.6894 | 0.8162 | 0.8629 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
