metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-xsmall
tags:
- generated_from_trainer
model-index:
- name: likeable-donkey-705
results: []
likeable-donkey-705
This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2761
- Hamming Loss: 0.0936
- Zero One Loss: 0.7987
- Jaccard Score: 0.7963
- Hamming Loss Optimised: 0.093
- Hamming Loss Threshold: 0.6326
- Zero One Loss Optimised: 0.7137
- Zero One Loss Threshold: 0.2122
- Jaccard Score Optimised: 0.5948
- Jaccard Score Threshold: 0.1794
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: 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: 2
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 | 0.3190 | 0.1123 | 1.0 | 1.0 | 0.1123 | 0.9000 | 1.0 | 0.9000 | 1.0 | 0.9000 |
| No log | 2.0 | 320 | 0.2761 | 0.0936 | 0.7987 | 0.7963 | 0.093 | 0.6326 | 0.7137 | 0.2122 | 0.5948 | 0.1794 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3