metadata
license: mit
base_model: nlptown/bert-base-multilingual-uncased-sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_bert
results: []
test_bert
This model is a fine-tuned version of nlptown/bert-base-multilingual-uncased-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8332
- Accuracy: 0.6817
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1121 | 0.13 | 500 | 0.9841 | 0.6302 |
| 1.0067 | 0.25 | 1000 | 0.9490 | 0.6499 |
| 0.9325 | 0.38 | 1500 | 0.9200 | 0.6577 |
| 0.9301 | 0.51 | 2000 | 0.9684 | 0.6418 |
| 0.927 | 0.63 | 2500 | 0.9837 | 0.6234 |
| 0.9067 | 0.76 | 3000 | 0.8973 | 0.6572 |
| 0.8986 | 0.88 | 3500 | 0.8663 | 0.6747 |
| 0.8964 | 1.01 | 4000 | 0.8408 | 0.6767 |
| 0.8115 | 1.14 | 4500 | 0.8478 | 0.6696 |
| 0.8081 | 1.26 | 5000 | 0.8600 | 0.6681 |
| 0.7896 | 1.39 | 5500 | 0.8569 | 0.6747 |
| 0.8075 | 1.52 | 6000 | 0.8353 | 0.6767 |
| 0.802 | 1.64 | 6500 | 0.8261 | 0.6767 |
| 0.768 | 1.77 | 7000 | 0.8289 | 0.6782 |
| 0.7505 | 1.9 | 7500 | 0.8332 | 0.6817 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2