metadata
library_name: peft
license: apache-2.0
base_model: deepvk/RuModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: modernbert-spam-classifier
results: []
modernbert-spam-classifier
This model is a fine-tuned version of deepvk/RuModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2676
- Accuracy: 0.8820
- F1: 0.8440
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: 2e-05
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Use OptimizerNames.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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3165 | 1.0 | 888 | 0.2819 | 0.8775 | 0.8310 |
| 0.2763 | 2.0 | 1776 | 0.2676 | 0.8820 | 0.8440 |
Framework versions
- PEFT 0.15.2
- Transformers 4.53.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2