bge-small-en-v1.5-conll2003-ner
This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0823
- Precision: 0.9171
- Recall: 0.9349
- F1: 0.9259
- Accuracy: 0.9838
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3163 | 1.0 | 625 | 0.1085 | 0.8501 | 0.8962 | 0.8725 | 0.9753 |
| 0.1026 | 2.0 | 1250 | 0.0826 | 0.8879 | 0.9128 | 0.9002 | 0.9794 |
| 0.0662 | 3.0 | 1875 | 0.0776 | 0.8849 | 0.9196 | 0.9019 | 0.9801 |
| 0.0349 | 4.0 | 2500 | 0.0753 | 0.9056 | 0.9216 | 0.9135 | 0.9821 |
| 0.0253 | 5.0 | 3125 | 0.0810 | 0.8992 | 0.9293 | 0.9140 | 0.9816 |
| 0.0193 | 6.0 | 3750 | 0.0757 | 0.9086 | 0.9320 | 0.9202 | 0.9829 |
| 0.0164 | 7.0 | 4375 | 0.0786 | 0.9109 | 0.9340 | 0.9223 | 0.9834 |
| 0.0112 | 8.0 | 5000 | 0.0831 | 0.9175 | 0.9344 | 0.9259 | 0.9833 |
| 0.0094 | 9.0 | 5625 | 0.0824 | 0.9110 | 0.9320 | 0.9214 | 0.9831 |
| 0.008 | 10.0 | 6250 | 0.0823 | 0.9171 | 0.9349 | 0.9259 | 0.9838 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4