---
license: mit
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: 2023MLMA_LAB9_task2
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: ncbi_disease
      type: ncbi_disease
      config: ncbi_disease
      split: validation
      args: ncbi_disease
    metrics:
    - name: Precision
      type: precision
      value: 0.4622186495176849
    - name: Recall
      type: recall
      value: 0.555019305019305
    - name: F1
      type: f1
      value: 0.5043859649122807
    - name: Accuracy
      type: accuracy
      value: 0.9518067602785016
---

<!-- 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. -->

# 2023MLMA_LAB9_task2

This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1673
- Precision: 0.4622
- Recall: 0.5550
- F1: 0.5044
- Accuracy: 0.9518

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.306         | 1.0   | 679  | 0.1701          | 0.3764    | 0.3938 | 0.3849 | 0.9442   |
| 0.1752        | 2.0   | 1358 | 0.1638          | 0.4538    | 0.5261 | 0.4873 | 0.9509   |
| 0.1072        | 3.0   | 2037 | 0.1673          | 0.4622    | 0.5550 | 0.5044 | 0.9518   |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3