bert-base-conll03-ner
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1123
- Precision: 0.8931
- Recall: 0.9101
- F1: 0.9015
- Accuracy: 0.9805
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: 64
- 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0645 | 1.0 | 439 | 0.0503 | 0.9057 | 0.9278 | 0.9166 | 0.9851 |
| 0.0354 | 2.0 | 878 | 0.0434 | 0.9316 | 0.9488 | 0.9401 | 0.9883 |
| 0.0187 | 3.0 | 1317 | 0.0428 | 0.9359 | 0.9455 | 0.9406 | 0.9885 |
| 0.0100 | 4.0 | 1756 | 0.0447 | 0.9362 | 0.9482 | 0.9421 | 0.9890 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1