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-50149
results: []
modernbert-user-50149
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: 0.5840
- Accuracy: 0.7593
- F1: 0.7520
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 |
|---|---|---|---|---|---|
| 0.7322 | 1.0 | 108 | 0.6204 | 0.5067 | 0.6468 |
| 0.6447 | 2.0 | 216 | 0.7593 | 0.7520 | 0.5840 |
| 0.5615 | 3.0 | 324 | 0.6852 | 0.6852 | 0.7563 |
| 0.402 | 4.0 | 432 | 0.6481 | 0.6376 | 0.7424 |
| 0.4726 | 5.0 | 540 | 0.7130 | 0.7055 | 1.1261 |
| 0.3242 | 6.0 | 648 | 0.6852 | 0.6878 | 1.2393 |
| 0.3018 | 7.0 | 756 | 0.7130 | 0.7156 | 1.4921 |
| 0.2238 | 8.0 | 864 | 0.7407 | 0.7407 | 1.7148 |
| 0.2226 | 9.0 | 972 | 0.7315 | 0.7320 | 1.7904 |
| 0.1066 | 10.0 | 1080 | 0.7130 | 0.7144 | 1.8016 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.6.0
- Datasets 3.3.1
- Tokenizers 0.21.0