deberta-v3-small-Tweet_About_Disaster_Or_Not
This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2942
- Accuracy: 0.9050
- F1: 0.7453
- Recall: 0.7453
- Precision: 0.7453
Model description
This is a binary classification model to determine if tweet input samples are about a disaster or not.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Binary%20Classification/Transformer%20Comparison/Is%20This%20Tweet%20Referring%20to%20a%20Disaster%20or%20Not%3F%20-%20DeBERTa.ipynb
Associated Projects
This project is part of a comparison of multiple transformers. The others can be found at the following links:
- https://huggingface.co/DunnBC22/roberta-base-Tweet_About_Disaster_Or_Not
- https://huggingface.co/DunnBC22/albert-base-v2-Tweet_About_Disaster_Or_Not
- https://huggingface.co/DunnBC22/electra-base-emotion-Tweet_About_Disaster_Or_Not
- https://huggingface.co/DunnBC22/ernie-2.0-base-en-Tweet_About_Disaster_Or_Not
- https://huggingface.co/DunnBC22/distilbert-base-uncased-Tweet_About_Disaster_Or_Not
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
The main limitation is the quality of the data source.
Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/vstepanenko/disaster-tweets
Input Word Length By Class:
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 | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 0.4167 | 1.0 | 143 | 0.3148 | 0.8830 | 0.7164 | 0.7925 | 0.6537 |
| 0.255 | 2.0 | 286 | 0.2942 | 0.9050 | 0.7453 | 0.7453 | 0.7453 |
| 0.1935 | 3.0 | 429 | 0.3022 | 0.8874 | 0.7288 | 0.8113 | 0.6615 |
| 0.1512 | 4.0 | 572 | 0.3405 | 0.8786 | 0.7172 | 0.8255 | 0.6341 |
| 0.1192 | 5.0 | 715 | 0.3618 | 0.8909 | 0.7373 | 0.8208 | 0.6692 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.12.1
