---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: mpnet-base-News_About_Gold
  results: []
language:
- en
pipeline_tag: text-classification
---

# mpnet-base-News_About_Gold

This model is a fine-tuned version of [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base).
It achieves the following results on the evaluation set:
- Loss: 0.3098
- Accuracy: 0.9068
- Weighted f1: 0.9068
- Micro f1: 0.9068
- Macro f1: 0.8351
- Weighted recall: 0.9068
- Micro recall: 0.9068
- Macro recall: 0.8406
- Weighted precision: 0.9071
- Micro precision: 0.9068
- Macro precision: 0.8309

## Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)/News%20About%20Gold%20-%20Sentiment%20Analysis%20-%20MPNet-Base%20with%20W%26B.ipynb

This project is part of a comparison of seven (7) transformers. Here is the README page for the comparison: https://github.com/DunnBC22/NLP_Projects/tree/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)

## Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

## Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/ankurzing/sentiment-analysis-in-commodity-market-gold

_Input Word Length:_

![Length of Input Text (in Words)](https://github.com/DunnBC22/NLP_Projects/raw/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)/Images/Input%20Word%20Length.png)

_Class Distribution:_

![Length of Input Text (in Words)](https://github.com/DunnBC22/NLP_Projects/raw/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)/Images/Class%20Distribution.png)

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
| 0.8316        | 1.0   | 133  | 0.5146          | 0.8742   | 0.8604      | 0.8742   | 0.6541   | 0.8742          | 0.8742       | 0.6583       | 0.8487             | 0.8742          | 0.6515          |
| 0.4675        | 2.0   | 266  | 0.3833          | 0.8898   | 0.8857      | 0.8898   | 0.7813   | 0.8898          | 0.8898       | 0.7542       | 0.8862             | 0.8898          | 0.8298          |
| 0.3276        | 3.0   | 399  | 0.3464          | 0.8997   | 0.8985      | 0.8997   | 0.8302   | 0.8997          | 0.8997       | 0.8212       | 0.8984             | 0.8997          | 0.8408          |
| 0.2767        | 4.0   | 532  | 0.3098          | 0.9101   | 0.9103      | 0.9101   | 0.8412   | 0.9101          | 0.9101       | 0.8462       | 0.9106             | 0.9101          | 0.8367          |
| 0.2429        | 5.0   | 665  | 0.3098          | 0.9068   | 0.9068      | 0.9068   | 0.8351   | 0.9068          | 0.9068       | 0.8406       | 0.9071             | 0.9068          | 0.8309          |

### Framework versions

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