metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: populism_model90
results: []
populism_model90
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: 0.7308
- Accuracy: 0.9179
- F1: 0.4335
- Recall: 0.5116
- Precision: 0.3761
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 | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 0.3922 | 1.0 | 88 | 0.3904 | 0.8769 | 0.4062 | 0.6860 | 0.2885 |
| 0.2731 | 2.0 | 176 | 0.7119 | 0.9347 | 0.3960 | 0.3488 | 0.4580 |
| 0.2129 | 3.0 | 264 | 0.4806 | 0.9040 | 0.4035 | 0.5291 | 0.3262 |
| 0.1491 | 4.0 | 352 | 0.6170 | 0.9162 | 0.4226 | 0.5 | 0.3660 |
| 0.1097 | 5.0 | 440 | 0.7308 | 0.9179 | 0.4335 | 0.5116 | 0.3761 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0