biobert-ner-finetuned
This model is a fine-tuned version of NazaGara/NER-fine-tuned-BETO on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0988
- Precision: 0.9505
- Recall: 0.9665
- F1: 0.9584
- Accuracy: 0.9778
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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 36
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3897 | 1.0 | 272 | 0.2170 | 0.8909 | 0.8755 | 0.8831 | 0.9430 |
0.146 | 2.0 | 544 | 0.1118 | 0.9242 | 0.9641 | 0.9438 | 0.9710 |
0.0929 | 3.0 | 816 | 0.1015 | 0.9403 | 0.9648 | 0.9524 | 0.9755 |
0.0794 | 4.0 | 1088 | 0.0988 | 0.9505 | 0.9665 | 0.9584 | 0.9778 |
0.0576 | 5.0 | 1360 | 0.1028 | 0.9502 | 0.9658 | 0.9580 | 0.9772 |
0.0439 | 6.0 | 1632 | 0.1088 | 0.9450 | 0.9640 | 0.9544 | 0.9759 |
0.0343 | 7.0 | 1904 | 0.1063 | 0.9479 | 0.9683 | 0.9580 | 0.9777 |
0.0314 | 8.0 | 2176 | 0.1117 | 0.9481 | 0.9678 | 0.9578 | 0.9777 |
0.0275 | 9.0 | 2448 | 0.1122 | 0.9512 | 0.9655 | 0.9583 | 0.9781 |
0.0218 | 10.0 | 2720 | 0.1155 | 0.9512 | 0.9656 | 0.9583 | 0.9781 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for anvorja/BETO-biobert-ner-finetuned
Base model
NazaGara/NER-fine-tuned-BETO