metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: modernbert_agree_classifier
results: []
modernbert_agree_classifier
This model is a fine-tuned version of answerdotai/ModernBERT-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0220
- Accuracy: 0.9976
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: 5.7142857142857145e-06
- train_batch_size: 8
- eval_batch_size: 2
- 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
- training_steps: 350
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2296 | 0.0597 | 50 | 0.3606 | 0.8215 |
| 0.1907 | 0.1193 | 100 | 0.1346 | 0.9560 |
| 0.0002 | 0.1790 | 150 | 0.1403 | 0.9756 |
| 0.0002 | 0.2387 | 200 | 0.0695 | 0.9804 |
| 0.0006 | 0.2983 | 250 | 0.0290 | 0.9853 |
| 0.0 | 0.3580 | 300 | 0.0209 | 0.9976 |
| 0.0 | 0.4177 | 350 | 0.0220 | 0.9976 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1