metadata
library_name: peft
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: beautiful-worm-91
results: []
beautiful-worm-91
This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5762
- Hamming Loss: 0.2815
- Zero One Loss: 1.0
- Jaccard Score: 0.8606
- Hamming Loss Optimised: 0.1121
- Hamming Loss Threshold: 0.7112
- Zero One Loss Optimised: 0.8762
- Zero One Loss Threshold: 0.5937
- Jaccard Score Optimised: 0.8487
- Jaccard Score Threshold: 0.3892
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: 1.27612271859294e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7
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 | 0.7158 | 0.4196 | 1.0 | 0.8558 | 0.1123 | 0.7884 | 0.8688 | 0.7125 | 0.8208 | 0.5703 |
| No log | 2.0 | 200 | 0.6802 | 0.3589 | 1.0 | 0.8562 | 0.1123 | 0.8010 | 0.89 | 0.6870 | 0.8545 | 0.5943 |
| No log | 3.0 | 300 | 0.6461 | 0.3409 | 1.0 | 0.8701 | 0.1121 | 0.7495 | 0.885 | 0.6670 | 0.8457 | 0.6441 |
| No log | 4.0 | 400 | 0.6162 | 0.3392 | 1.0 | 0.8767 | 0.1123 | 0.7474 | 0.8812 | 0.6319 | 0.8506 | 0.4177 |
| 0.6723 | 5.0 | 500 | 0.5936 | 0.3326 | 1.0 | 0.8785 | 0.1121 | 0.7112 | 0.8775 | 0.6089 | 0.8457 | 0.6006 |
| 0.6723 | 6.0 | 600 | 0.5804 | 0.2973 | 1.0 | 0.8651 | 0.1121 | 0.7112 | 0.875 | 0.5979 | 0.8447 | 0.5836 |
| 0.6723 | 7.0 | 700 | 0.5762 | 0.2815 | 1.0 | 0.8606 | 0.1121 | 0.7112 | 0.8762 | 0.5937 | 0.8487 | 0.3892 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0