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: 0.2258
- Precision: 0.8564
- Recall: 0.8980
- F1: 0.8767
- Accuracy: 0.9768
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 313 | 0.5133 | 0.6808 | 0.7301 | 0.7046 | 0.9496 |
| 0.8931 | 2.0 | 626 | 0.3201 | 0.8034 | 0.8502 | 0.8262 | 0.9685 |
| 0.8931 | 3.0 | 939 | 0.2601 | 0.8312 | 0.8842 | 0.8569 | 0.9731 |
| 0.3135 | 4.0 | 1252 | 0.2338 | 0.8569 | 0.8948 | 0.8754 | 0.9765 |
| 0.2258 | 5.0 | 1565 | 0.2258 | 0.8564 | 0.8980 | 0.8767 | 0.9768 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1