metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: uner-roberta-ner
results: []
uner-roberta-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: 0.0930
- Precision: 0.8622
- Recall: 0.9010
- F1: 0.8812
- Accuracy: 0.9728
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 144 | 0.1285 | 0.8005 | 0.8241 | 0.8121 | 0.9589 |
| No log | 2.0 | 288 | 0.1142 | 0.8142 | 0.8748 | 0.8434 | 0.9655 |
| No log | 3.0 | 432 | 0.0962 | 0.8485 | 0.8985 | 0.8728 | 0.9702 |
| 0.1923 | 4.0 | 576 | 0.0916 | 0.8543 | 0.9018 | 0.8774 | 0.9719 |
| 0.1923 | 5.0 | 720 | 0.0930 | 0.8622 | 0.9010 | 0.8812 | 0.9728 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3