metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: honorable-shrew-498
results: []
honorable-shrew-498
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: 0.1625
- Hamming Loss: 0.055
- Zero One Loss: 0.3725
- Jaccard Score: 0.3189
- Hamming Loss Optimised: 0.0541
- Hamming Loss Threshold: 0.7220
- Zero One Loss Optimised: 0.3712
- Zero One Loss Threshold: 0.4879
- Jaccard Score Optimised: 0.2997
- Jaccard Score Threshold: 0.2962
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: 8.935925952705373e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.8778562665922138,0.8720892866629456) 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 | 0.1595 | 0.0571 | 0.4600 | 0.4159 | 0.0559 | 0.4890 | 0.4225 | 0.3826 | 0.3403 | 0.2310 |
| No log | 2.0 | 200 | 0.1476 | 0.0564 | 0.3975 | 0.3373 | 0.0551 | 0.5746 | 0.3875 | 0.4361 | 0.2977 | 0.2865 |
| No log | 3.0 | 300 | 0.1625 | 0.055 | 0.3725 | 0.3189 | 0.0541 | 0.7220 | 0.3712 | 0.4879 | 0.2997 | 0.2962 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0