metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_keras_callback
model-index:
- name: madatnlp/sk-kogptv2-kormath-causal
results: []
madatnlp/sk-kogptv2-kormath-causal
This model is a fine-tuned version of skt/kogpt2-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2604
- Validation Loss: 1.7970
- Epoch: 14
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:
- optimizer: {'name': 'Adam', 'learning_rate': 0.00094450003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.1786 | 2.0114 | 0 |
| 1.7468 | 1.6093 | 1 |
| 1.3809 | 1.3738 | 2 |
| 1.1486 | 1.4108 | 3 |
| 0.9985 | 1.3539 | 4 |
| 0.8685 | 1.4534 | 5 |
| 0.7873 | 1.4854 | 6 |
| 0.7021 | 1.5091 | 7 |
| 0.6443 | 1.5531 | 8 |
| 0.6021 | 1.6022 | 9 |
| 0.5328 | 1.6028 | 10 |
| 0.4563 | 1.4180 | 11 |
| 0.3806 | 1.6496 | 12 |
| 0.3180 | 1.8589 | 13 |
| 0.2604 | 1.7970 | 14 |
Framework versions
- Transformers 4.19.1
- TensorFlow 2.8.0
- Datasets 2.2.1
- Tokenizers 0.12.1