metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_multilingual_bert_uncased_v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: antielite_classifier_all
results: []
antielite_classifier_all
This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert_uncased_v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7651
- Accuracy: 0.9293
- 1-f1: 0.6331
- 1-recall: 0.6543
- 1-precision: 0.6133
- Balanced Acc: 0.8060
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|---|---|---|---|---|---|---|---|---|
| 0.3031 | 1.0 | 871 | 0.3153 | 0.8819 | 0.5737 | 0.8522 | 0.4324 | 0.8686 |
| 0.2011 | 2.0 | 1742 | 0.3090 | 0.8848 | 0.5852 | 0.8714 | 0.4405 | 0.8788 |
| 0.1064 | 3.0 | 2613 | 0.5096 | 0.9195 | 0.6345 | 0.7498 | 0.5500 | 0.8434 |
| 0.0961 | 4.0 | 3484 | 0.7651 | 0.9293 | 0.6331 | 0.6543 | 0.6133 | 0.8060 |
Framework versions
- Transformers 5.8.0.dev0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2