|
--- |
|
license: cc-by-4.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: EMBEDDIA/crosloengual-bert |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: loha_fine_tuned_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. --> |
|
|
|
# loha_fine_tuned_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: 0.6890 |
|
- Accuracy: 0.52 |
|
- F1: 0.5212 |
|
|
|
## 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.7072 | 1.0 | 50 | 0.6896 | 0.52 | 0.5212 | |
|
| 0.6973 | 2.0 | 100 | 0.6894 | 0.53 | 0.5312 | |
|
| 0.6988 | 3.0 | 150 | 0.6892 | 0.54 | 0.5411 | |
|
| 0.7016 | 4.0 | 200 | 0.6891 | 0.53 | 0.5312 | |
|
| 0.7034 | 5.0 | 250 | 0.6890 | 0.52 | 0.5212 | |
|
| 0.6978 | 6.0 | 300 | 0.6890 | 0.51 | 0.5112 | |
|
| 0.6965 | 7.0 | 350 | 0.6890 | 0.51 | 0.5112 | |
|
| 0.6907 | 8.0 | 400 | 0.6890 | 0.52 | 0.5212 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
