metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/modernbert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: modernbert_web3_classification
results: []
modernbert_web3_classification
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: 1.9429
- Accuracy: 0.6923
- F1: 0.6711
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: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 3.2458 | 1.0 | 643 | 1.4201 | 0.5509 | 0.5134 |
| 2.5825 | 2.0 | 1286 | 1.3174 | 0.5828 | 0.5521 |
| 2.0999 | 3.0 | 1929 | 1.3183 | 0.6240 | 0.6020 |
| 0.7625 | 4.0 | 2572 | 1.3098 | 0.6816 | 0.6592 |
| 0.333 | 5.0 | 3215 | 1.4979 | 0.6760 | 0.6509 |
| 0.1715 | 6.0 | 3858 | 1.5728 | 0.6915 | 0.6769 |
| 0.0617 | 7.0 | 4501 | 1.7623 | 0.6906 | 0.6713 |
| 0.041 | 8.0 | 5144 | 1.9429 | 0.6923 | 0.6711 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1