---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: twitter_sentiment_small_3
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abson-/twitter_sentiment_small/runs/j4w9p70i)
# twitter_sentiment_small_3

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4820
- Accuracy: 0.811
- F1-score: 0.7869
- Precision: 0.8290
- Recall: 0.7489

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.8,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1-score | Precision | Recall |
|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
| 0.6739        | 0.0889 | 100  | 0.5831          | 0.742    | 0.6742   | 0.8190    | 0.5730 |
| 0.5084        | 0.1778 | 200  | 0.4898          | 0.787    | 0.7560   | 0.8108    | 0.7082 |
| 0.4133        | 0.2667 | 300  | 0.4619          | 0.801    | 0.7881   | 0.7822    | 0.7940 |
| 0.4277        | 0.3556 | 400  | 0.4401          | 0.797    | 0.768    | 0.8215    | 0.7210 |
| 0.4066        | 0.4444 | 500  | 0.4813          | 0.811    | 0.8062   | 0.7721    | 0.8433 |
| 0.4091        | 0.5333 | 600  | 0.4396          | 0.808    | 0.7876   | 0.8128    | 0.7639 |
| 0.3873        | 0.6222 | 700  | 0.4338          | 0.804    | 0.7971   | 0.77      | 0.8262 |
| 0.3851        | 0.7111 | 800  | 0.3983          | 0.803    | 0.7898   | 0.7856    | 0.7940 |
| 0.4003        | 0.8    | 900  | 0.4140          | 0.806    | 0.8012   | 0.7667    | 0.8391 |
| 0.3738        | 0.8889 | 1000 | 0.4047          | 0.81     | 0.8041   | 0.7738    | 0.8369 |
| 0.3718        | 0.9778 | 1100 | 0.4227          | 0.815    | 0.8083   | 0.7816    | 0.8369 |
| 0.3235        | 1.0667 | 1200 | 0.4731          | 0.815    | 0.8103   | 0.7760    | 0.8476 |
| 0.3132        | 1.1556 | 1300 | 0.4716          | 0.815    | 0.8099   | 0.7771    | 0.8455 |
| 0.3026        | 1.2444 | 1400 | 0.4650          | 0.811    | 0.8046   | 0.7764    | 0.8348 |
| 0.2918        | 1.3333 | 1500 | 0.4641          | 0.812    | 0.8070   | 0.7736    | 0.8433 |
| 0.296         | 1.4222 | 1600 | 0.4820          | 0.811    | 0.7869   | 0.8290    | 0.7489 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1