|
--- |
|
license: mit |
|
base_model: ukr-models/xlm-roberta-base-uk |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xddModel |
|
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. --> |
|
|
|
# xddModel |
|
|
|
This model is a fine-tuned version of [ukr-models/xlm-roberta-base-uk](https://huggingface.co/ukr-models/xlm-roberta-base-uk) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1495 |
|
- Precision: 0.8533 |
|
- Recall: 0.8819 |
|
- F1: 0.8674 |
|
- Accuracy: 0.9625 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- 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 | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 175 | 0.1730 | 0.7640 | 0.8340 | 0.7975 | 0.9463 | |
|
| No log | 2.0 | 350 | 0.1552 | 0.8131 | 0.8585 | 0.8352 | 0.9527 | |
|
| 0.2473 | 3.0 | 525 | 0.1334 | 0.8433 | 0.8718 | 0.8573 | 0.9611 | |
|
| 0.2473 | 4.0 | 700 | 0.1305 | 0.8429 | 0.8784 | 0.8603 | 0.9615 | |
|
| 0.2473 | 5.0 | 875 | 0.1293 | 0.8541 | 0.8788 | 0.8663 | 0.9626 | |
|
| 0.0833 | 6.0 | 1050 | 0.1346 | 0.8449 | 0.8828 | 0.8634 | 0.9621 | |
|
| 0.0833 | 7.0 | 1225 | 0.1386 | 0.8449 | 0.8827 | 0.8634 | 0.9624 | |
|
| 0.0833 | 8.0 | 1400 | 0.1474 | 0.8548 | 0.8851 | 0.8697 | 0.9632 | |
|
| 0.0558 | 9.0 | 1575 | 0.1496 | 0.8485 | 0.8830 | 0.8654 | 0.9622 | |
|
| 0.0558 | 10.0 | 1750 | 0.1495 | 0.8533 | 0.8819 | 0.8674 | 0.9625 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.15.2 |
|
|