---
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SETH_2e-05_0404_ES6_strict_tok
  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. -->

# SETH_2e-05_0404_ES6_strict_tok

This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0910
- Precision: 0.8062
- Recall: 0.7659
- F1: 0.7855
- Accuracy: 0.9765

## 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
- training_steps: 2000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.7275        | 0.96  | 25   | 0.2746          | 0.0       | 0.0    | 0.0    | 0.9293   |
| 0.1794        | 1.92  | 50   | 0.1296          | 0.6835    | 0.3270 | 0.4424 | 0.9572   |
| 0.1018        | 2.88  | 75   | 0.0915          | 0.7093    | 0.7349 | 0.7219 | 0.9691   |
| 0.0769        | 3.85  | 100  | 0.0881          | 0.6844    | 0.8434 | 0.7556 | 0.9671   |
| 0.0674        | 4.81  | 125  | 0.0875          | 0.6478    | 0.8675 | 0.7417 | 0.9678   |
| 0.0497        | 5.77  | 150  | 0.0814          | 0.7543    | 0.7504 | 0.7524 | 0.9716   |
| 0.0441        | 6.73  | 175  | 0.0801          | 0.7756    | 0.8090 | 0.7919 | 0.9746   |
| 0.0369        | 7.69  | 200  | 0.0818          | 0.7989    | 0.7728 | 0.7857 | 0.9767   |
| 0.0266        | 8.65  | 225  | 0.0910          | 0.8062    | 0.7659 | 0.7855 | 0.9765   |


### Framework versions

- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3