---
base_model: cardiffnlp/bert-base-multilingual-cased-sentiment-multilingual
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Improved-mBERT-attempt2
  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. -->

# Improved-mBERT-attempt2

This model is a fine-tuned version of [cardiffnlp/bert-base-multilingual-cased-sentiment-multilingual](https://huggingface.co/cardiffnlp/bert-base-multilingual-cased-sentiment-multilingual) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4767
- Accuracy: 0.83

## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.07  | 50   | 0.4113          | 0.83     |
| No log        | 0.14  | 100  | 0.4244          | 0.8      |
| No log        | 0.21  | 150  | 0.5003          | 0.79     |
| No log        | 0.27  | 200  | 0.6269          | 0.72     |
| No log        | 0.34  | 250  | 0.4152          | 0.79     |
| No log        | 0.41  | 300  | 0.5146          | 0.78     |
| No log        | 0.48  | 350  | 0.4050          | 0.83     |
| No log        | 0.55  | 400  | 0.3897          | 0.83     |
| No log        | 0.62  | 450  | 0.3976          | 0.82     |
| 0.4388        | 0.68  | 500  | 0.5089          | 0.78     |
| 0.4388        | 0.75  | 550  | 0.4276          | 0.82     |
| 0.4388        | 0.82  | 600  | 0.4009          | 0.83     |
| 0.4388        | 0.89  | 650  | 0.5864          | 0.73     |
| 0.4388        | 0.96  | 700  | 0.4581          | 0.79     |
| 0.4388        | 1.03  | 750  | 0.4783          | 0.8      |
| 0.4388        | 1.1   | 800  | 0.3497          | 0.88     |
| 0.4388        | 1.16  | 850  | 0.5715          | 0.75     |
| 0.4388        | 1.23  | 900  | 0.3953          | 0.84     |
| 0.4388        | 1.3   | 950  | 0.4425          | 0.85     |
| 0.3525        | 1.37  | 1000 | 0.4271          | 0.86     |
| 0.3525        | 1.44  | 1050 | 0.4252          | 0.84     |
| 0.3525        | 1.51  | 1100 | 0.4297          | 0.85     |
| 0.3525        | 1.58  | 1150 | 0.5833          | 0.8      |
| 0.3525        | 1.64  | 1200 | 0.5043          | 0.81     |
| 0.3525        | 1.71  | 1250 | 0.3593          | 0.87     |
| 0.3525        | 1.78  | 1300 | 0.3999          | 0.8      |
| 0.3525        | 1.85  | 1350 | 0.4493          | 0.8      |
| 0.3525        | 1.92  | 1400 | 0.4266          | 0.82     |
| 0.3525        | 1.99  | 1450 | 0.5052          | 0.81     |
| 0.304         | 2.05  | 1500 | 0.4767          | 0.83     |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.14.1