---
library_name: transformers
license: apache-2.0
base_model: d4data/biomedical-ner-all
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ner-biomedical-maccrobat2018
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# ner-biomedical-maccrobat2018

This model is a fine-tuned version of [d4data/biomedical-ner-all](https://huggingface.co/d4data/biomedical-ner-all) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5565
- Accuracy: 0.7909

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- 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: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.641         | 1.0   | 10   | 1.5081          | 0.3577   |
| 1.338         | 2.0   | 20   | 0.9042          | 0.6165   |
| 0.877         | 3.0   | 30   | 0.6942          | 0.7081   |
| 0.6363        | 4.0   | 40   | 0.5950          | 0.7520   |
| 0.4868        | 5.0   | 50   | 0.5515          | 0.7573   |
| 0.3798        | 6.0   | 60   | 0.5296          | 0.7688   |
| 0.3047        | 7.0   | 70   | 0.5217          | 0.7825   |
| 0.2521        | 8.0   | 80   | 0.5290          | 0.7788   |
| 0.2123        | 9.0   | 90   | 0.5283          | 0.7852   |
| 0.1819        | 10.0  | 100  | 0.5309          | 0.7880   |
| 0.1585        | 11.0  | 110  | 0.5345          | 0.7835   |
| 0.1388        | 12.0  | 120  | 0.5430          | 0.7823   |
| 0.1235        | 13.0  | 130  | 0.5350          | 0.7871   |
| 0.1128        | 14.0  | 140  | 0.5406          | 0.7882   |
| 0.1036        | 15.0  | 150  | 0.5561          | 0.7873   |
| 0.0985        | 16.0  | 160  | 0.5603          | 0.7887   |
| 0.0924        | 17.0  | 170  | 0.5559          | 0.7894   |
| 0.0883        | 18.0  | 180  | 0.5575          | 0.7909   |
| 0.0832        | 19.0  | 190  | 0.5545          | 0.7910   |
| 0.0843        | 20.0  | 200  | 0.5565          | 0.7909   |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0