metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: edu-modernbert
results: []
edu-modernbert
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2863
- Precision: 0.5402
- Recall: 0.3945
- F1: 0.4305
- Accuracy: 0.6822
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: 0.0003
- train_batch_size: 1024
- eval_batch_size: 512
- seed: 0
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 1.7219 | 0.1827 | 0.1714 | 0.0934 | 0.2345 |
| 0.3195 | 2.4331 | 1000 | 0.3180 | 0.5267 | 0.3632 | 0.3841 | 0.6562 |
| 0.3096 | 4.8662 | 2000 | 0.3028 | 0.5275 | 0.3827 | 0.4108 | 0.6652 |
| 0.3027 | 7.2993 | 3000 | 0.2985 | 0.5332 | 0.3905 | 0.4223 | 0.6681 |
| 0.3004 | 9.7324 | 4000 | 0.2919 | 0.5392 | 0.3867 | 0.4204 | 0.6774 |
| 0.2965 | 12.1655 | 5000 | 0.2896 | 0.5345 | 0.3970 | 0.4311 | 0.6788 |
| 0.2942 | 14.5985 | 6000 | 0.2885 | 0.5355 | 0.3960 | 0.4312 | 0.6819 |
| 0.287 | 17.0316 | 7000 | 0.2912 | 0.5360 | 0.3813 | 0.4170 | 0.6828 |
| 0.2893 | 19.4647 | 8000 | 0.2863 | 0.5402 | 0.3945 | 0.4305 | 0.6822 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0