metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-cased
tags:
- generated_from_trainer
model-index:
- name: dashing-worm-457
results: []
dashing-worm-457
This model is a fine-tuned version of distilbert/distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1034
- Hamming Loss: 0.0304
- Zero One Loss: 0.595
- Jaccard Score: 0.5272
- Hamming Loss Optimised: 0.03
- Hamming Loss Threshold: 0.4790
- Zero One Loss Optimised: 0.5430
- Zero One Loss Threshold: 0.2889
- Jaccard Score Optimised: 0.4332
- Jaccard Score Threshold: 0.2108
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: 5.379556445396376e-05
- train_batch_size: 20
- eval_batch_size: 20
- 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: 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 | 160 | 0.1543 | 0.0428 | 0.8712 | 0.8502 | 0.0382 | 0.2350 | 0.7625 | 0.2178 | 0.6961 | 0.1808 |
| No log | 2.0 | 320 | 0.1173 | 0.0331 | 0.6713 | 0.6165 | 0.0323 | 0.2835 | 0.6238 | 0.2913 | 0.4819 | 0.1457 |
| No log | 3.0 | 480 | 0.1033 | 0.0294 | 0.5975 | 0.5256 | 0.0284 | 0.3878 | 0.5312 | 0.2564 | 0.4126 | 0.1647 |
| 0.1519 | 4.0 | 640 | 0.0985 | 0.0280 | 0.5813 | 0.5075 | 0.0274 | 0.4056 | 0.5137 | 0.2769 | 0.4014 | 0.2025 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3