---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-base-uncased-xsum-factuality
  results: []
datasets:
- xsum_factuality
language:
- en
---

<!-- 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. -->

# Distilbert-base-uncased-xsum-factuality

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [XSum-Factuality](https://huggingface.co/datasets/xsum_factuality) dataset.
You can view more implementation details as part of this [GitHub](https://github.com/ernlavr/llamarizer) repository. It achieves the following results on the evaluation set:
- Loss: 0.6850
- Accuracy: 0.6332
- F1: 0.6212
- Precision: 0.6526
- Recall: 0.6332

# Weights and Biases Documentation
View the full run on [Weights & Biases](https://wandb.ai/ernlavr/adv_nlp2023/runs/fqluc2vb)

## 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: 1e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.6904        | 6.93  | 1040 | 0.6850          | 0.6332   | 0.6212 | 0.6526    | 0.6332 |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1