metadata
base_model: finiteautomata/beto-sentiment-analysis
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: beto-sentiment-analysis-finetuned-detests24
results: []
beto-sentiment-analysis-finetuned-detests24
This model is a fine-tuned version of finiteautomata/beto-sentiment-analysis on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0647
- Accuracy: 0.8609
- F1-score: 0.7906
- Precision: 0.8107
- Recall: 0.7755
- Auc: 0.7755
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 | F1-score | Precision | Recall | Auc |
|---|---|---|---|---|---|---|---|---|
| 0.4035 | 1.0 | 153 | 0.3459 | 0.8527 | 0.7540 | 0.8257 | 0.7219 | 0.7219 |
| 0.2217 | 2.0 | 306 | 0.4773 | 0.8183 | 0.7700 | 0.7519 | 0.8088 | 0.8088 |
| 0.0787 | 3.0 | 459 | 0.6757 | 0.8576 | 0.7959 | 0.7982 | 0.7936 | 0.7936 |
| 0.016 | 4.0 | 612 | 0.7801 | 0.8478 | 0.7851 | 0.7830 | 0.7873 | 0.7873 |
| 0.0251 | 5.0 | 765 | 0.9783 | 0.8511 | 0.7994 | 0.7862 | 0.8173 | 0.8173 |
| 0.0159 | 6.0 | 918 | 0.9841 | 0.8576 | 0.7926 | 0.8001 | 0.7860 | 0.7860 |
| 0.0002 | 7.0 | 1071 | 0.9943 | 0.8609 | 0.7906 | 0.8107 | 0.7755 | 0.7755 |
| 0.0001 | 8.0 | 1224 | 1.0252 | 0.8625 | 0.7925 | 0.8139 | 0.7765 | 0.7765 |
| 0.0013 | 9.0 | 1377 | 1.0663 | 0.8511 | 0.7808 | 0.7916 | 0.7716 | 0.7716 |
| 0.0001 | 10.0 | 1530 | 1.0647 | 0.8609 | 0.7906 | 0.8107 | 0.7755 | 0.7755 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1