metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: marvelous-cat-327
results: []
marvelous-cat-327
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: 0.1549
- Hamming Loss: 0.0581
- Zero One Loss: 0.4087
- Jaccard Score: 0.3522
- Hamming Loss Optimised: 0.0566
- Hamming Loss Threshold: 0.6291
- Zero One Loss Optimised: 0.3875
- Zero One Loss Threshold: 0.4442
- Jaccard Score Optimised: 0.3185
- Jaccard Score Threshold: 0.2459
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: 2.981063961904907e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.913862773872536,0.981775961733248) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 100 | 0.1647 | 0.0635 | 0.485 | 0.4364 | 0.062 | 0.5617 | 0.4675 | 0.4177 | 0.3514 | 0.2886 |
| No log | 2.0 | 200 | 0.1537 | 0.0591 | 0.405 | 0.3445 | 0.0587 | 0.5717 | 0.4025 | 0.4646 | 0.3214 | 0.4353 |
| No log | 3.0 | 300 | 0.1549 | 0.0581 | 0.4087 | 0.3522 | 0.0566 | 0.6291 | 0.3875 | 0.4442 | 0.3185 | 0.2459 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0