---
base_model: finiteautomata/bertweet-base-sentiment-analysis
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: experiment-model-bertweet
  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. -->

# experiment-model-bertweet

This model is a fine-tuned version of [finiteautomata/bertweet-base-sentiment-analysis](https://huggingface.co./finiteautomata/bertweet-base-sentiment-analysis) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6847
- Accuracy: 0.8306

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3532        | 1.0   | 760  | 0.3454          | 0.8453   |
| 0.2907        | 2.0   | 1521 | 0.3672          | 0.8465   |
| 0.2568        | 3.0   | 2281 | 0.4530          | 0.8393   |
| 0.2054        | 4.0   | 3042 | 0.5747          | 0.8369   |
| 0.1495        | 5.0   | 3800 | 0.6847          | 0.8306   |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2