metadata
tags:
- generated_from_trainer
model-index:
- name: kc-bert_finetuned_unsmile
results: []
kc-bert_finetuned_unsmile
This model is a fine-tuned version of beomi/kcbert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1330
- Lrap: 0.8759
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Lrap |
|---|---|---|---|---|
| No log | 1.0 | 235 | 0.1456 | 0.8618 |
| No log | 2.0 | 470 | 0.1264 | 0.8766 |
| 0.1691 | 3.0 | 705 | 0.1260 | 0.8800 |
| 0.1691 | 4.0 | 940 | 0.1282 | 0.8788 |
| 0.076 | 5.0 | 1175 | 0.1330 | 0.8759 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 1.17.0
- Tokenizers 0.12.1