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: 0.1326
- Lrap: 0.8753
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 | 0.1458 | 0.8612 |
No log | 2.0 | 470 | 0.1280 | 0.8738 |
0.1685 | 3.0 | 705 | 0.1257 | 0.8791 |
0.1685 | 4.0 | 940 | 0.1281 | 0.8777 |
0.0774 | 5.0 | 1175 | 0.1326 | 0.8753 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 1.17.0
- Tokenizers 0.12.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.