ko_Jeolla_test
This model is a fine-tuned version of gogamza/kobart-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6851
- Bleu: 88.1706
- Gen Len: 20.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.7147 | 1.0 | 15477 | 3.7012 | 87.5571 | 20.0 |
| 3.703 | 2.0 | 30954 | 3.6885 | 88.0637 | 20.0 |
| 3.6911 | 3.0 | 46431 | 3.6851 | 88.1706 | 20.0 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 29
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for yomilimi/ko_Jeolla_test
Base model
gogamza/kobart-base-v2