my_awesome_token_classification_v2
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: 0.0001
- Precision: 0.9730
- Recall: 0.9863
- F1: 0.9796
- Accuracy: 1.0000
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0009 | 1.0 | 490 | 0.0012 | 0.7490 | 0.8721 | 0.8059 | 0.9995 |
0.0004 | 2.0 | 980 | 0.0003 | 0.9211 | 0.9589 | 0.9396 | 0.9999 |
0.0003 | 3.0 | 1470 | 0.0003 | 0.9211 | 0.9589 | 0.9396 | 0.9999 |
0.0002 | 4.0 | 1960 | 0.0001 | 0.9730 | 0.9863 | 0.9796 | 1.0000 |
0.0001 | 5.0 | 2450 | 0.0001 | 0.9730 | 0.9863 | 0.9796 | 1.0000 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 11