|
--- |
|
license: mit |
|
base_model: xlm-roberta-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: fine_tuned_XLMROBERTA_cs_wikann |
|
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_XLMROBERTA_cs_wikann |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1238 |
|
- Overall Precision: 0.8962 |
|
- Overall Recall: 0.9193 |
|
- Overall F1: 0.9076 |
|
- Overall Accuracy: 0.9684 |
|
|
|
## 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: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.3625 | 0.4 | 500 | 0.1809 | 0.7915 | 0.8509 | 0.8201 | 0.9486 | |
|
| 0.1807 | 0.8 | 1000 | 0.1373 | 0.8363 | 0.8785 | 0.8568 | 0.9583 | |
|
| 0.1384 | 1.2 | 1500 | 0.1371 | 0.8758 | 0.9085 | 0.8918 | 0.9651 | |
|
| 0.1079 | 1.6 | 2000 | 0.1467 | 0.8924 | 0.9168 | 0.9044 | 0.9659 | |
|
| 0.0997 | 2.0 | 2500 | 0.1170 | 0.9018 | 0.9264 | 0.9139 | 0.9700 | |
|
| 0.0644 | 2.4 | 3000 | 0.1344 | 0.9123 | 0.9285 | 0.9203 | 0.9706 | |
|
| 0.0594 | 2.8 | 3500 | 0.1269 | 0.9138 | 0.9345 | 0.9240 | 0.9718 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
