metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: XLM-AgloBERTa-hu-ner
results: []
XLM-AgloBERTa-hu-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: 0.2705
- Precision: 0.9070
- Recall: 0.9256
- F1: 0.9162
- Accuracy: 0.9671
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 |
|---|---|---|---|---|---|---|---|
| 0.0861 | 1.0 | 1250 | 0.2330 | 0.8811 | 0.9005 | 0.8907 | 0.9574 |
| 0.0666 | 2.0 | 2500 | 0.1955 | 0.8842 | 0.9113 | 0.8975 | 0.9597 |
| 0.0613 | 3.0 | 3750 | 0.2059 | 0.8941 | 0.9035 | 0.8988 | 0.9603 |
| 0.0408 | 4.0 | 5000 | 0.2386 | 0.9021 | 0.9023 | 0.9022 | 0.9616 |
| 0.0327 | 5.0 | 6250 | 0.2314 | 0.8892 | 0.9188 | 0.9038 | 0.9621 |
| 0.0222 | 6.0 | 7500 | 0.2574 | 0.9015 | 0.9108 | 0.9061 | 0.9631 |
| 0.0143 | 7.0 | 8750 | 0.2482 | 0.9070 | 0.9192 | 0.9131 | 0.9657 |
| 0.0093 | 8.0 | 10000 | 0.2570 | 0.9092 | 0.9206 | 0.9149 | 0.9664 |
| 0.0044 | 9.0 | 11250 | 0.2697 | 0.9055 | 0.9199 | 0.9126 | 0.9660 |
| 0.0026 | 10.0 | 12500 | 0.2705 | 0.9070 | 0.9256 | 0.9162 | 0.9671 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0