ner_model_output
This model is a fine-tuned version of huggingface-course/bert-finetuned-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2567
- Precision: 0.6421
- Recall: 0.6747
- F1: 0.6580
- Accuracy: 0.9242
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: 8
- eval_batch_size: 8
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4135 | 1.0 | 1756 | 0.3290 | 0.5395 | 0.5106 | 0.5246 | 0.8946 |
| 0.2314 | 2.0 | 3512 | 0.2702 | 0.6515 | 0.6254 | 0.6382 | 0.9213 |
| 0.1599 | 3.0 | 5268 | 0.2567 | 0.6421 | 0.6747 | 0.6580 | 0.9242 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2