metadata
library_name: peft
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: debonair-bear-744
results: []
debonair-bear-744
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: 0.2373
- Hamming Loss: 0.0854
- Zero One Loss: 0.7175
- Jaccard Score: 0.7075
- Hamming Loss Optimised: 0.0846
- Hamming Loss Threshold: 0.4663
- Zero One Loss Optimised: 0.6487
- Zero One Loss Threshold: 0.3162
- Jaccard Score Optimised: 0.5542
- Jaccard Score Threshold: 0.1769
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: 8.857809698679913e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.8813380147543269,0.8027403115380221) 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 | 0.3191 | 0.1116 | 0.9938 | 0.9938 | 0.1024 | 0.3004 | 0.78 | 0.2247 | 0.7428 | 0.1619 |
| No log | 2.0 | 200 | 0.2554 | 0.0899 | 0.765 | 0.7562 | 0.088 | 0.4274 | 0.6825 | 0.2889 | 0.5940 | 0.1800 |
| No log | 3.0 | 300 | 0.2373 | 0.0854 | 0.7175 | 0.7075 | 0.0846 | 0.4663 | 0.6487 | 0.3162 | 0.5542 | 0.1769 |
Framework versions
- PEFT 0.13.2
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0