|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: XLM-AgloBERTa-eu-hu-ner |
|
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. --> |
|
|
|
# XLM-AgloBERTa-eu-hu-ner |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2582 |
|
- Precision: 0.9039 |
|
- Recall: 0.9209 |
|
- F1: 0.9123 |
|
- Accuracy: 0.9661 |
|
|
|
## 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: 0.0001 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2501 | 1.0 | 1250 | 0.1919 | 0.8343 | 0.8634 | 0.8486 | 0.9456 | |
|
| 0.1718 | 2.0 | 2500 | 0.1631 | 0.8662 | 0.8793 | 0.8727 | 0.9540 | |
|
| 0.1269 | 3.0 | 3750 | 0.1743 | 0.8748 | 0.8913 | 0.8830 | 0.9571 | |
|
| 0.0899 | 4.0 | 5000 | 0.1642 | 0.8734 | 0.9083 | 0.8905 | 0.9587 | |
|
| 0.0578 | 5.0 | 6250 | 0.1958 | 0.8867 | 0.9000 | 0.8933 | 0.9599 | |
|
| 0.0474 | 6.0 | 7500 | 0.1823 | 0.9062 | 0.9069 | 0.9065 | 0.9647 | |
|
| 0.031 | 7.0 | 8750 | 0.1928 | 0.9007 | 0.9137 | 0.9071 | 0.9643 | |
|
| 0.0168 | 8.0 | 10000 | 0.2168 | 0.9042 | 0.9113 | 0.9077 | 0.9644 | |
|
| 0.0109 | 9.0 | 11250 | 0.2423 | 0.9028 | 0.9191 | 0.9108 | 0.9658 | |
|
| 0.0057 | 10.0 | 12500 | 0.2582 | 0.9039 | 0.9209 | 0.9123 | 0.9661 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
