metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: bemused-trout-607
results: []
bemused-trout-607
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1783
- Hamming Loss: 0.0643
- Zero One Loss: 0.4113
- Jaccard Score: 0.3643
- Hamming Loss Optimised: 0.0615
- Hamming Loss Threshold: 0.7239
- Zero One Loss Optimised: 0.4038
- Zero One Loss Threshold: 0.4731
- Jaccard Score Optimised: 0.3281
- Jaccard Score Threshold: 0.2446
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: 5.0943791435964314e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 2024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2941 | 1.0 | 400 | 0.2355 | 0.0934 | 0.7987 | 0.7963 | 0.0929 | 0.6046 | 0.6738 | 0.2934 | 0.5524 | 0.2658 |
| 0.2247 | 2.0 | 800 | 0.2132 | 0.0914 | 0.6188 | 0.5905 | 0.0906 | 0.6229 | 0.6262 | 0.3893 | 0.4890 | 0.2889 |
| 0.187 | 3.0 | 1200 | 0.1854 | 0.066 | 0.4712 | 0.4224 | 0.0653 | 0.7034 | 0.4325 | 0.4451 | 0.3701 | 0.4026 |
| 0.1495 | 4.0 | 1600 | 0.1783 | 0.0643 | 0.4113 | 0.3643 | 0.0615 | 0.7239 | 0.4038 | 0.4731 | 0.3281 | 0.2446 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3