metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_model111
results: []
populism_model111
This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6324
- Accuracy: 0.9331
- 1-f1: 0.3077
- 1-recall: 0.3810
- 1-precision: 0.2581
- Balanced Acc: 0.6682
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: 128
- eval_batch_size: 128
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 17 | 0.4979 | 0.9554 | 0.0769 | 0.0476 | 0.2 | 0.5199 |
| 0.4627 | 2.0 | 34 | 0.4936 | 0.9424 | 0.3404 | 0.3810 | 0.3077 | 0.6731 |
| 0.2898 | 3.0 | 51 | 0.5184 | 0.9015 | 0.2535 | 0.4286 | 0.18 | 0.6746 |
| 0.2898 | 4.0 | 68 | 0.5747 | 0.9145 | 0.2581 | 0.3810 | 0.1951 | 0.6586 |
| 0.2036 | 5.0 | 85 | 0.6324 | 0.9331 | 0.3077 | 0.3810 | 0.2581 | 0.6682 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0