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: populism_classifier_bsample_157
results: []
populism_classifier_bsample_157
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: 0.5646
- Accuracy: 0.8478
- 1-f1: 0.3659
- 1-recall: 0.9203
- 1-precision: 0.2284
- Balanced Acc: 0.8822
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 |
|---|---|---|---|---|---|---|---|---|
| 0.1677 | 1.0 | 167 | 0.8171 | 0.6118 | 0.1954 | 0.9880 | 0.1085 | 0.7905 |
| 0.0817 | 2.0 | 334 | 0.5852 | 0.7337 | 0.2574 | 0.9669 | 0.1485 | 0.8445 |
| 0.1066 | 3.0 | 501 | 0.6588 | 0.7424 | 0.2656 | 0.9759 | 0.1537 | 0.8533 |
| 0.104 | 4.0 | 668 | 0.5004 | 0.8377 | 0.3490 | 0.9113 | 0.2158 | 0.8727 |
| 0.0466 | 5.0 | 835 | 0.5637 | 0.8305 | 0.3453 | 0.9368 | 0.2117 | 0.8810 |
| 0.0349 | 6.0 | 1002 | 0.5646 | 0.8478 | 0.3659 | 0.9203 | 0.2284 | 0.8822 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3