metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: answerdotai-ModernBERT-base-ai-detector
results: []
answerdotai-ModernBERT-base-ai-detector
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: 0.0036
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: 16
- eval_batch_size: 16
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0505 | 0.2228 | 500 | 0.0214 |
| 0.0114 | 0.4456 | 1000 | 0.0110 |
| 0.0088 | 0.6684 | 1500 | 0.0032 |
| 0.0 | 0.8913 | 2000 | 0.0048 |
| 0.0068 | 1.1141 | 2500 | 0.0035 |
| 0.0 | 1.3369 | 3000 | 0.0040 |
| 0.0 | 1.5597 | 3500 | 0.0097 |
| 0.0053 | 1.7825 | 4000 | 0.0101 |
| 0.0 | 2.0053 | 4500 | 0.0053 |
| 0.0 | 2.2282 | 5000 | 0.0039 |
| 0.0017 | 2.4510 | 5500 | 0.0046 |
| 0.0 | 2.6738 | 6000 | 0.0043 |
| 0.0 | 2.8966 | 6500 | 0.0036 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0