metadata
library_name: transformers
license: apache-2.0
base_model: monologg/koelectra-base-v3-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ynat-model
results: []
ynat-model
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: 0.4651
- Accuracy: 0.8459
- Precision: 0.8354
- Recall: 0.8655
- F1: 0.8492
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-06
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7213 | 1.0 | 714 | 0.8798 | 0.7424 | 0.7565 | 0.8240 | 0.7756 |
| 0.4888 | 2.0 | 1428 | 0.5669 | 0.8254 | 0.8110 | 0.8604 | 0.8321 |
| 0.4147 | 3.0 | 2142 | 0.5082 | 0.8376 | 0.8263 | 0.8659 | 0.8433 |
| 0.4093 | 4.0 | 2856 | 0.4712 | 0.8444 | 0.8299 | 0.8656 | 0.8464 |
| 0.3667 | 5.0 | 3570 | 0.4651 | 0.8459 | 0.8354 | 0.8655 | 0.8492 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4