---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: BertAbstractIntroduction
  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. -->

# BertAbstractIntroduction

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5373
- Accuracy: 0.8527
- Precision: 0.7768
- Recall: 0.7740
- F1: 0.7724
- Top3: 0.9608
- Top3macro: 0.9355

## 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
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     | Top3   | Top3macro |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|:---------:|
| 0.7833        | 1.0   | 4135  | 0.7301          | 0.7864   | 0.6818    | 0.6113 | 0.6160 | 0.9290 | 0.8766    |
| 0.5357        | 2.0   | 8270  | 0.5875          | 0.8291   | 0.7464    | 0.7173 | 0.7214 | 0.9503 | 0.9119    |
| 0.3875        | 3.0   | 12405 | 0.5240          | 0.8459   | 0.7629    | 0.7541 | 0.7541 | 0.9629 | 0.9359    |
| 0.2544        | 4.0   | 16540 | 0.5292          | 0.8577   | 0.7759    | 0.7680 | 0.7705 | 0.9643 | 0.9397    |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.2.1
- Tokenizers 0.19.1