metadata
library_name: transformers
license: apache-2.0
base_model: beomi/kcbert-base
tags:
- HHD
- 10_class
- multi_labels
- generated_from_trainer
model-index:
- name: bert_model
results: []
bert_model
This model is a fine-tuned version of beomi/kcbert-base on the unsmile_data dataset. It achieves the following results on the evaluation set:
- Loss: 0.1308
- Lrap: 0.8803
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Lrap |
|---|---|---|---|---|
| No log | 1.0 | 235 | 0.1478 | 0.8586 |
| No log | 2.0 | 470 | 0.1278 | 0.8726 |
| 0.1715 | 3.0 | 705 | 0.1246 | 0.8797 |
| 0.1715 | 4.0 | 940 | 0.1278 | 0.8800 |
| 0.079 | 5.0 | 1175 | 0.1308 | 0.8803 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.3.0
- Tokenizers 0.21.0