|
---
|
|
license: cc-by-4.0
|
|
base_model: EMBEDDIA/crosloengual-bert
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
- f1
|
|
model-index:
|
|
- name: fine_tuned_copa_croslo
|
|
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_copa_croslo
|
|
|
|
This model is a fine-tuned version of [EMBEDDIA/crosloengual-bert](https://huggingface.co/EMBEDDIA/crosloengual-bert) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.6931
|
|
- Accuracy: 0.55
|
|
- F1: 0.3903
|
|
|
|
## 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: 0.003
|
|
- 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
|
|
- training_steps: 400
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
|
| 0.7205 | 1.0 | 50 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.7204 | 2.0 | 100 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.7044 | 3.0 | 150 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.7288 | 4.0 | 200 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.7268 | 5.0 | 250 | 0.6931 | 0.54 | 0.3857 |
|
|
| 0.7047 | 6.0 | 300 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.7291 | 7.0 | 350 | 0.6931 | 0.55 | 0.3903 |
|
|
| 0.713 | 8.0 | 400 | 0.6931 | 0.55 | 0.3903 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.40.1
|
|
- Pytorch 2.1.1+cu121
|
|
- Datasets 2.19.0
|
|
- Tokenizers 0.19.1
|
|
|
