RoBERTa-CNER
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0223
- Precision: 0.8722
- Recall: 0.9149
- F1: 0.8931
- Accuracy: 0.9930
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0344 | 1.0 | 2000 | 0.0300 | 0.8827 | 0.8094 | 0.8445 | 0.9902 |
0.0216 | 2.0 | 4000 | 0.0234 | 0.8632 | 0.9012 | 0.8818 | 0.9924 |
0.0139 | 3.0 | 6000 | 0.0223 | 0.8722 | 0.9149 | 0.8931 | 0.9930 |
0.0078 | 4.0 | 8000 | 0.0231 | 0.8869 | 0.9136 | 0.9000 | 0.9935 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 17
Model tree for Flamenco43/RoBERTa-CNER
Base model
FacebookAI/roberta-base