koelectra-base-v3-discriminator-KEmoFact-EFE-0927
This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5635
- Precision: 0.3754
- Recall: 0.4417
- F1: 0.4058
- Ov Accuracy: 0.8248
- Jaccard: 0.7349
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: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Ov Accuracy | Jaccard |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 414 | 0.4083 | 0.3175 | 0.3909 | 0.3504 | 0.8258 | 0.6953 |
| 0.4405 | 2.0 | 828 | 0.4039 | 0.3208 | 0.4078 | 0.3591 | 0.8256 | 0.7080 |
| 0.3005 | 3.0 | 1242 | 0.4682 | 0.3448 | 0.4123 | 0.3755 | 0.8251 | 0.7108 |
| 0.207 | 4.0 | 1656 | 0.5329 | 0.3451 | 0.4218 | 0.3797 | 0.8207 | 0.7076 |
| 0.1468 | 5.0 | 2070 | 0.5888 | 0.3456 | 0.4235 | 0.3806 | 0.8182 | 0.7093 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3