metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-finetuned-ner-prostata
results: []
bert-base-uncased-finetuned-ner-prostata
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1427
- Precision: 0.9238
- Recall: 0.9494
- F1: 0.9364
- Accuracy: 0.9755
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 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 |
|---|---|---|---|---|---|---|---|
| 0.1389 | 1.0 | 2395 | 0.1002 | 0.9331 | 0.9256 | 0.9293 | 0.9750 |
| 0.09 | 2.0 | 4790 | 0.0930 | 0.9334 | 0.9573 | 0.9452 | 0.9795 |
| 0.0608 | 3.0 | 7185 | 0.0983 | 0.9275 | 0.9525 | 0.9399 | 0.9770 |
| 0.0541 | 4.0 | 9580 | 0.1011 | 0.9390 | 0.9553 | 0.9471 | 0.9793 |
| 0.0447 | 5.0 | 11975 | 0.1060 | 0.9348 | 0.9489 | 0.9418 | 0.9789 |
| 0.0383 | 6.0 | 14370 | 0.1128 | 0.9324 | 0.9506 | 0.9414 | 0.9782 |
| 0.0306 | 7.0 | 16765 | 0.1130 | 0.9395 | 0.9493 | 0.9443 | 0.9795 |
| 0.0286 | 8.0 | 19160 | 0.1200 | 0.9331 | 0.9519 | 0.9424 | 0.9787 |
| 0.024 | 9.0 | 21555 | 0.1215 | 0.9352 | 0.9500 | 0.9425 | 0.9788 |
| 0.0213 | 10.0 | 23950 | 0.1242 | 0.9370 | 0.9488 | 0.9428 | 0.9788 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1