BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext-finetuned-ner-chemdis-30-v1
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1479
- Precision: 0.6670
- Recall: 0.8803
- F1: 0.7589
- Accuracy: 0.9386
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: 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 85 | 0.1637 | 0.6275 | 0.8375 | 0.7174 | 0.9314 |
| No log | 2.0 | 170 | 0.1552 | 0.6449 | 0.9021 | 0.7522 | 0.9344 |
| No log | 3.0 | 255 | 0.1479 | 0.6670 | 0.8803 | 0.7589 | 0.9386 |
| No log | 4.0 | 340 | 0.1582 | 0.6742 | 0.8474 | 0.7509 | 0.9380 |
| No log | 5.0 | 425 | 0.1581 | 0.6929 | 0.8037 | 0.7442 | 0.9382 |
| 0.1361 | 6.0 | 510 | 0.1805 | 0.7012 | 0.8147 | 0.7537 | 0.9395 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- 1