metadata
library_name: peft
license: apache-2.0
base_model: team-lucid/deberta-v3-base-korean
tags:
- base_model:adapter:team-lucid/deberta-v3-base-korean
- lora
- transformers
metrics:
- f1
model-index:
- name: deberta-korean-multilabel_base-lora2
results: []
deberta-korean-multilabel_base-lora2
This model is a fine-tuned version of team-lucid/deberta-v3-base-korean on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1371
- F1: 0.9728
- Roc Auc: 0.8511
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: 0.0002
- train_batch_size: 96
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc |
|---|---|---|---|---|---|
| 0.1501 | 1.0 | 4173 | 0.1487 | 0.9712 | 0.8374 |
| 0.1411 | 2.0 | 8346 | 0.1427 | 0.9720 | 0.8515 |
| 0.1359 | 3.0 | 12519 | 0.1390 | 0.9726 | 0.8517 |
| 0.1319 | 4.0 | 16692 | 0.1374 | 0.9728 | 0.8509 |
| 0.1283 | 5.0 | 20865 | 0.1371 | 0.9728 | 0.8511 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2