metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: XLM-AgloBERTa-fi-ner
results: []
XLM-AgloBERTa-fi-ner
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2917
- Precision: 0.8818
- Recall: 0.8970
- F1: 0.8893
- Accuracy: 0.9578
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 |
|---|---|---|---|---|---|---|---|
| 0.2709 | 1.0 | 1250 | 0.2630 | 0.8052 | 0.8239 | 0.8145 | 0.9296 |
| 0.1861 | 2.0 | 2500 | 0.2313 | 0.8182 | 0.8543 | 0.8358 | 0.9357 |
| 0.1341 | 3.0 | 3750 | 0.1858 | 0.8599 | 0.8644 | 0.8621 | 0.9492 |
| 0.1035 | 4.0 | 5000 | 0.2108 | 0.8705 | 0.8738 | 0.8721 | 0.9520 |
| 0.0784 | 5.0 | 6250 | 0.2073 | 0.8736 | 0.8779 | 0.8757 | 0.9538 |
| 0.0572 | 6.0 | 7500 | 0.2226 | 0.8758 | 0.8828 | 0.8793 | 0.9549 |
| 0.0358 | 7.0 | 8750 | 0.2514 | 0.8763 | 0.8885 | 0.8824 | 0.9566 |
| 0.0226 | 8.0 | 10000 | 0.2522 | 0.8792 | 0.8922 | 0.8857 | 0.9563 |
| 0.0151 | 9.0 | 11250 | 0.2836 | 0.8795 | 0.8949 | 0.8871 | 0.9576 |
| 0.0079 | 10.0 | 12500 | 0.2917 | 0.8818 | 0.8970 | 0.8893 | 0.9578 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0