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_out
results: []
bert_model_out
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: 0.2393
- Lrap: 0.8715
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: 16
- eval_batch_size: 16
- seed: 42
- 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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Lrap |
|---|---|---|---|---|
| 0.0202 | 1.0 | 938 | 0.2017 | 0.8627 |
| 0.0157 | 2.0 | 1876 | 0.2041 | 0.8702 |
| 0.0112 | 3.0 | 2814 | 0.2157 | 0.8713 |
| 0.0055 | 4.0 | 3752 | 0.2221 | 0.8730 |
| 0.0039 | 5.0 | 4690 | 0.2327 | 0.8715 |
| 0.0035 | 6.0 | 5628 | 0.2384 | 0.8722 |
| 0.0024 | 7.0 | 6566 | 0.2393 | 0.8715 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0