metadata
library_name: peft
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: whimsical-crane-88
results: []
whimsical-crane-88
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: 0.3017
- Hamming Loss: 0.1008
- Zero One Loss: 0.8638
- Jaccard Score: 0.8619
- Hamming Loss Optimised: 0.1005
- Hamming Loss Threshold: 0.4669
- Zero One Loss Optimised: 0.7662
- Zero One Loss Threshold: 0.2371
- Jaccard Score Optimised: 0.7019
- Jaccard Score Threshold: 0.1424
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: 5.6029632367762424e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.8378996868939299,0.8949526992950398) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
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 | 0.3418 | 0.1123 | 0.99 | 0.99 | 0.1121 | 0.5223 | 0.8287 | 0.2215 | 0.7749 | 0.1699 |
| No log | 2.0 | 200 | 0.3238 | 0.1098 | 0.965 | 0.9644 | 0.1069 | 0.4149 | 0.7863 | 0.2162 | 0.7400 | 0.1647 |
| No log | 3.0 | 300 | 0.3082 | 0.1021 | 0.8775 | 0.8762 | 0.1014 | 0.4735 | 0.7688 | 0.2369 | 0.7141 | 0.1721 |
| No log | 4.0 | 400 | 0.3017 | 0.1008 | 0.8638 | 0.8619 | 0.1005 | 0.4669 | 0.7662 | 0.2371 | 0.7019 | 0.1424 |
Framework versions
- PEFT 0.13.2
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0