metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bertNer-biobert
results: []
bertNer-biobert
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1284
- Precision: 0.9471
- Recall: 0.9630
- F1: 0.9550
- Accuracy: 0.9758
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1851 | 1.0 | 1224 | 0.1186 | 0.9202 | 0.9550 | 0.9373 | 0.9670 |
| 0.1188 | 2.0 | 2448 | 0.1061 | 0.9349 | 0.9684 | 0.9514 | 0.9737 |
| 0.0789 | 3.0 | 3672 | 0.1051 | 0.9381 | 0.9710 | 0.9543 | 0.9755 |
| 0.0569 | 4.0 | 4896 | 0.1062 | 0.9403 | 0.9712 | 0.9555 | 0.9761 |
| 0.0492 | 5.0 | 6120 | 0.1174 | 0.9403 | 0.9646 | 0.9523 | 0.9734 |
| 0.0405 | 6.0 | 7344 | 0.1220 | 0.9426 | 0.9638 | 0.9531 | 0.9739 |
| 0.0355 | 7.0 | 8568 | 0.1175 | 0.9446 | 0.9651 | 0.9548 | 0.9756 |
| 0.0296 | 8.0 | 9792 | 0.1239 | 0.9446 | 0.9660 | 0.9552 | 0.9757 |
| 0.0224 | 9.0 | 11016 | 0.1247 | 0.9474 | 0.9640 | 0.9556 | 0.9760 |
| 0.0219 | 10.0 | 12240 | 0.1284 | 0.9471 | 0.9630 | 0.9550 | 0.9758 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0