metadata
library_name: peft
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: masked-slug-729
results: []
masked-slug-729
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: 0.5084
- Hamming Loss: 0.1123
- Zero One Loss: 0.995
- Jaccard Score: 0.995
- Hamming Loss Optimised: 0.1123
- Hamming Loss Threshold: 0.5944
- Zero One Loss Optimised: 1.0
- Zero One Loss Threshold: 0.9000
- Jaccard Score Optimised: 0.7627
- Jaccard Score Threshold: 0.4303
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: 5.408225206539412e-06
- train_batch_size: 4
- eval_batch_size: 4
- 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: 6
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6838 | 1.0 | 800 | 0.6757 | 0.4291 | 1.0 | 0.8717 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8878 | 0.2889 |
| 0.6577 | 2.0 | 1600 | 0.6238 | 0.2076 | 0.915 | 0.8579 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8224 | 0.4788 |
| 0.6103 | 3.0 | 2400 | 0.5443 | 0.113 | 0.9888 | 0.9888 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8487 | 0.4056 |
| 0.5495 | 4.0 | 3200 | 0.5206 | 0.1125 | 0.9938 | 0.9938 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.7640 | 0.4489 |
| 0.5332 | 5.0 | 4000 | 0.5112 | 0.1123 | 0.995 | 0.995 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.7633 | 0.4459 |
| 0.5304 | 6.0 | 4800 | 0.5084 | 0.1123 | 0.995 | 0.995 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.7627 | 0.4303 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0