---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BiBert-MultiTask-1
  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. -->

# BiBert-MultiTask-1

This model is a fine-tuned version of [nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2281          
- Accuracy: 0.7247

## 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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 345  | 1.2060          | 0.7063   |
| 0.7739        | 2.0   | 690  | 1.1887          | 0.7103   |
| 0.6183        | 3.0   | 1035 | 1.2281          | 0.7247   |
| 0.6183        | 4.0   | 1380 | 1.2635          | 0.7103   |
| 0.5103        | 5.0   | 1725 | 1.2971          | 0.7090   |


### Framework versions

- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.12.1