grow_classification_kobert-lm
This model is a fine-tuned version of monologg/kobert-lm on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0751
- Accuracy: 0.6946
- F1: 0.6970
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8394 | 1.0 | 329 | 0.8209 | 0.6664 | 0.6719 |
| 0.5789 | 2.0 | 658 | 0.8653 | 0.6962 | 0.7018 |
| 0.5125 | 3.0 | 987 | 0.9554 | 0.6942 | 0.6919 |
| 0.4852 | 4.0 | 1316 | 0.9838 | 0.7057 | 0.7120 |
| 0.464 | 5.0 | 1645 | 0.9969 | 0.6910 | 0.6934 |
| 0.4519 | 6.0 | 1974 | 1.0354 | 0.6918 | 0.6973 |
| 0.4437 | 7.0 | 2303 | 1.0301 | 0.6871 | 0.6940 |
| 0.4342 | 8.0 | 2632 | 1.0676 | 0.6950 | 0.6972 |
| 0.4299 | 9.0 | 2961 | 1.0691 | 0.6962 | 0.6984 |
| 0.4276 | 10.0 | 3290 | 1.0751 | 0.6946 | 0.6970 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3