metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
model-index:
- name: popular-newt-164
results: []
popular-newt-164
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: 0.1634
- Hamming Loss: 0.0581
- Zero One Loss: 0.4287
- Jaccard Score: 0.3757
- Hamming Loss Optimised: 0.0583
- Hamming Loss Threshold: 0.5931
- Zero One Loss Optimised: 0.4150
- Zero One Loss Threshold: 0.3577
- Jaccard Score Optimised: 0.3293
- Jaccard Score Threshold: 0.2227
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: 3.220762197755578e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9866282790391318,0.8034758511516535) 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 | 0.1844 | 0.0681 | 0.5375 | 0.5025 | 0.0676 | 0.5092 | 0.5025 | 0.4265 | 0.4224 | 0.2570 |
| No log | 2.0 | 200 | 0.1663 | 0.0633 | 0.4387 | 0.3643 | 0.0587 | 0.6431 | 0.4375 | 0.4758 | 0.3283 | 0.3124 |
| No log | 3.0 | 300 | 0.1634 | 0.0581 | 0.4287 | 0.3757 | 0.0583 | 0.5931 | 0.4150 | 0.3577 | 0.3293 | 0.2227 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0