---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base_corona_nlp_classif
  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. -->

# roberta-base_corona_nlp_classif

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5166

## Model description

This model is used to classify tweets regarding the COVID-19 as Extremely Positive, Positive, Neutral,Negative, Extremely Negative 

## Intended uses & limitations

Training is done on a raw uncleaned dataset. 

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-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
- lr_scheduler_warmup_steps: 500
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.6501        | 1.0   | 4496  | 0.6886          |
| 0.4461        | 2.0   | 8992  | 0.5166          |
| 0.3347        | 3.0   | 13488 | 0.6570          |
| 0.152         | 4.0   | 17984 | 0.6583          |


### Framework versions

- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3