---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Bioformer-LitCovid-v1.3h
  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. -->

# Bioformer-LitCovid-v1.3h

This model is a fine-tuned version of [bioformers/bioformer-litcovid](https://huggingface.co/bioformers/bioformer-litcovid) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8951
- Hamming loss: 0.0168
- F1 micro: 0.8565
- F1 macro: 0.3960
- F1 weighted: 0.8831
- F1 samples: 0.8789
- Precision micro: 0.7903
- Precision macro: 0.3221
- Precision weighted: 0.8426
- Precision samples: 0.8631
- Recall micro: 0.9348
- Recall macro: 0.6915
- Recall weighted: 0.9348
- Recall samples: 0.9435
- Roc Auc: 0.9604
- Accuracy: 0.6896

## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 3257
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Hamming loss | F1 micro | F1 macro | F1 weighted | F1 samples | Precision micro | Precision macro | Precision weighted | Precision samples | Recall micro | Recall macro | Recall weighted | Recall samples | Roc Auc | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:------------:|:--------:|:--------:|:-----------:|:----------:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:------------:|:---------------:|:--------------:|:-------:|:--------:|
| 1.2033        | 1.0   | 2272  | 0.5628          | 0.0616       | 0.6107   | 0.2167   | 0.7918      | 0.7257     | 0.4618          | 0.1789          | 0.7347             | 0.6771            | 0.9014       | 0.7310       | 0.9014          | 0.9194         | 0.9209  | 0.3870   |
| 1.2127        | 2.0   | 4544  | 0.5062          | 0.0325       | 0.7555   | 0.2834   | 0.8357      | 0.8037     | 0.6337          | 0.2273          | 0.7680             | 0.7535            | 0.9353       | 0.7100       | 0.9353          | 0.9434         | 0.9523  | 0.4954   |
| 0.96          | 3.0   | 6816  | 0.4943          | 0.0245       | 0.8043   | 0.3363   | 0.8608      | 0.8409     | 0.7043          | 0.2676          | 0.8069             | 0.8048            | 0.9372       | 0.7637       | 0.9372          | 0.9477         | 0.9575  | 0.5735   |
| 0.5852        | 4.0   | 9088  | 0.7306          | 0.0195       | 0.8371   | 0.3860   | 0.8687      | 0.8624     | 0.7568          | 0.3083          | 0.8212             | 0.8378            | 0.9365       | 0.7232       | 0.9365          | 0.9459         | 0.9597  | 0.6410   |
| 0.3454        | 5.0   | 11360 | 0.8951          | 0.0168       | 0.8565   | 0.3960   | 0.8831      | 0.8789     | 0.7903          | 0.3221          | 0.8426             | 0.8631            | 0.9348       | 0.6915       | 0.9348          | 0.9435         | 0.9604  | 0.6896   |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3