metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: modernbert-user-52991
results: []
modernbert-user-52991
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: 0.5458
- Accuracy: 0.9024
- F1: 0.8697
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
|---|---|---|---|---|---|
| 0.5116 | 1.0 | 123 | 0.9024 | 0.8562 | 0.4195 |
| 0.4601 | 2.0 | 246 | 0.8943 | 0.8521 | 0.3916 |
| 0.4513 | 3.0 | 369 | 0.8943 | 0.8521 | 0.4779 |
| 0.386 | 4.0 | 492 | 0.9024 | 0.8697 | 0.5458 |
| 0.241 | 5.0 | 615 | 0.8943 | 0.8647 | 0.6648 |
| 0.3768 | 6.0 | 738 | 0.8862 | 0.8597 | 1.3254 |
| 0.1477 | 7.0 | 861 | 0.8780 | 0.8548 | 1.1079 |
| 0.0525 | 8.0 | 984 | 0.8699 | 0.8500 | 1.1714 |
| 0.0406 | 9.0 | 1107 | 0.8780 | 0.8548 | 1.1469 |
| 0.0219 | 10.0 | 1230 | 0.8618 | 0.8451 | 1.1773 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.6.0
- Datasets 3.3.1
- Tokenizers 0.21.0