metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: rare-mink-344
results: []
rare-mink-344
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: 0.1684
- Hamming Loss: 0.0622
- Zero One Loss: 0.4775
- Jaccard Score: 0.4349
- Hamming Loss Optimised: 0.0619
- Hamming Loss Threshold: 0.5161
- Zero One Loss Optimised: 0.4525
- Zero One Loss Threshold: 0.3657
- Jaccard Score Optimised: 0.3635
- Jaccard Score Threshold: 0.2643
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: 1.8001716530301675e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.8775527409811034,0.8351994879199208) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
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 | 0.1861 | 0.0686 | 0.5262 | 0.4890 | 0.0679 | 0.4904 | 0.4975 | 0.3930 | 0.4236 | 0.3044 |
| No log | 2.0 | 200 | 0.1684 | 0.0622 | 0.4775 | 0.4349 | 0.0619 | 0.5161 | 0.4525 | 0.3657 | 0.3635 | 0.2643 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0