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-biobert
results: []
bert-base-uncased-finetuned-ner-biobert
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: 0.1078
- Precision: 0.9466
- Recall: 0.9706
- F1: 0.9585
- Accuracy: 0.9788
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4602 | 1.0 | 612 | 0.1189 | 0.9232 | 0.9431 | 0.9330 | 0.9683 |
| 0.1394 | 2.0 | 1224 | 0.1071 | 0.9236 | 0.9702 | 0.9463 | 0.9728 |
| 0.0939 | 3.0 | 1836 | 0.0952 | 0.9445 | 0.9652 | 0.9547 | 0.9774 |
| 0.0759 | 4.0 | 2448 | 0.0968 | 0.9417 | 0.9680 | 0.9547 | 0.9770 |
| 0.0549 | 5.0 | 3060 | 0.0981 | 0.9448 | 0.9670 | 0.9558 | 0.9773 |
| 0.0481 | 6.0 | 3672 | 0.1025 | 0.9416 | 0.9706 | 0.9559 | 0.9774 |
| 0.0401 | 7.0 | 4284 | 0.1045 | 0.9407 | 0.9705 | 0.9554 | 0.9771 |
| 0.0387 | 8.0 | 4896 | 0.1042 | 0.9455 | 0.9705 | 0.9578 | 0.9784 |
| 0.0301 | 9.0 | 5508 | 0.1059 | 0.9475 | 0.9704 | 0.9588 | 0.9790 |
| 0.0286 | 10.0 | 6120 | 0.1078 | 0.9466 | 0.9706 | 0.9585 | 0.9788 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0