metadata
library_name: transformers
license: apache-2.0
base_model: google/rembert
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_bsample_413
results: []
populism_classifier_bsample_413
This model is a fine-tuned version of google/rembert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3564
- Accuracy: 0.6483
- 1-f1: 0.3030
- 1-recall: 1.0
- 1-precision: 0.1786
- Balanced Acc: 0.8096
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.004 | 1.0 | 6 | 1.2736 | 0.6850 | 0.3268 | 1.0 | 0.1953 | 0.8295 |
| 0.0439 | 2.0 | 12 | 0.5350 | 0.7492 | 0.3788 | 1.0 | 0.2336 | 0.8642 |
| 0.0218 | 3.0 | 18 | 0.6059 | 0.7798 | 0.4098 | 1.0 | 0.2577 | 0.8808 |
| 0.0023 | 4.0 | 24 | 1.3564 | 0.6483 | 0.3030 | 1.0 | 0.1786 | 0.8096 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3