metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_awesome_ner-token_classification_v1.0
results: []
my_awesome_ner-token_classification_v1.0
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8650
- Precision: 0.4582
- Recall: 0.5502
- F1: 0.5
- Accuracy: 0.8053
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: cosine
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.0426 | 1.9912 | 225 | 0.8857 | 0.3633 | 0.3365 | 0.3494 | 0.7753 |
| 0.7028 | 3.9823 | 450 | 0.7244 | 0.4994 | 0.4647 | 0.4815 | 0.8136 |
| 0.5281 | 5.9735 | 675 | 0.6965 | 0.4933 | 0.5513 | 0.5207 | 0.8124 |
| 0.3767 | 7.9646 | 900 | 0.7331 | 0.4760 | 0.5406 | 0.5063 | 0.8169 |
| 0.2995 | 9.9558 | 1125 | 0.7731 | 0.4646 | 0.5321 | 0.4960 | 0.8158 |
| 0.2731 | 11.9469 | 1350 | 0.8100 | 0.4650 | 0.5395 | 0.4995 | 0.8074 |
| 0.2259 | 13.9381 | 1575 | 0.8500 | 0.4769 | 0.5502 | 0.5109 | 0.8112 |
| 0.1916 | 15.9292 | 1800 | 0.8650 | 0.4582 | 0.5502 | 0.5 | 0.8053 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1