---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: twitter-data-microsoft-deberta-base-mnli-sentiment-finetuned-memes
  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. -->

# twitter-data-microsoft-deberta-base-mnli-sentiment-finetuned-memes

This model is a fine-tuned version of [microsoft/deberta-base-mnli](https://huggingface.co/microsoft/deberta-base-mnli) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2438
- Accuracy: 0.9296
- Precision: 0.9301
- Recall: 0.9296
- F1: 0.9296

## 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-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: 6

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.3622        | 1.0   | 1762  | 0.2933          | 0.9060   | 0.9065    | 0.9060 | 0.9057 |
| 0.2601        | 2.0   | 3524  | 0.2593          | 0.9194   | 0.9196    | 0.9194 | 0.9192 |
| 0.2282        | 3.0   | 5286  | 0.2365          | 0.9279   | 0.9287    | 0.9279 | 0.9280 |
| 0.1977        | 4.0   | 7048  | 0.2325          | 0.9293   | 0.9298    | 0.9293 | 0.9293 |
| 0.181         | 5.0   | 8810  | 0.2421          | 0.9291   | 0.9301    | 0.9291 | 0.9292 |
| 0.1629        | 6.0   | 10572 | 0.2438          | 0.9296   | 0.9301    | 0.9296 | 0.9296 |


### Framework versions

- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1