# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("hadA42/ner-classification")
model = AutoModelForTokenClassification.from_pretrained("hadA42/ner-classification", device_map="auto")Quick Links
ner-classification
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: 0.1650
- Precision: 0.9019
- Recall: 0.9266
- F1: 0.9141
- Accuracy: 0.9818
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.9605 | 1.0 | 625 | 0.3528 | 0.7730 | 0.8223 | 0.7969 | 0.9629 |
| 0.3424 | 2.0 | 1250 | 0.2244 | 0.8615 | 0.8933 | 0.8771 | 0.9763 |
| 0.2283 | 3.0 | 1875 | 0.1831 | 0.8656 | 0.9093 | 0.8869 | 0.9785 |
| 0.1363 | 4.0 | 2500 | 0.1691 | 0.8847 | 0.9172 | 0.9007 | 0.9806 |
| 0.1088 | 5.0 | 3125 | 0.1673 | 0.8939 | 0.9212 | 0.9073 | 0.9810 |
| 0.0874 | 6.0 | 3750 | 0.1587 | 0.8909 | 0.9222 | 0.9063 | 0.9814 |
| 0.0816 | 7.0 | 4375 | 0.1624 | 0.8948 | 0.9246 | 0.9095 | 0.9814 |
| 0.0642 | 8.0 | 5000 | 0.1657 | 0.9002 | 0.9241 | 0.9120 | 0.9817 |
| 0.0586 | 9.0 | 5625 | 0.1653 | 0.9006 | 0.9254 | 0.9128 | 0.9818 |
| 0.0574 | 10.0 | 6250 | 0.1650 | 0.9019 | 0.9266 | 0.9141 | 0.9818 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1
- Downloads last month
- 18
Model tree for hadA42/ner-classification
Base model
BAAI/bge-small-en-v1.5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="hadA42/ner-classification")