metadata
license: mit
base_model: beomi/KcELECTRA-base-v2022
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: KcELECTRA-base-v2022-KEmoFact-0925
results: []
KcELECTRA-base-v2022-KEmoFact-0925
This model is a fine-tuned version of beomi/KcELECTRA-base-v2022 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3810
- Precision: 0.2344
- Recall: 0.2824
- F1: 0.2562
- Accuracy: 0.7161
- Jaccard Scores: 0.6958
- Cls Accuracy: 0.6348
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 | Accuracy | Jaccard Scores | Cls Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 414 | 1.0972 | 0.2070 | 0.2510 | 0.2269 | 0.7237 | 0.6675 | 0.6273 |
| 0.4703 | 2.0 | 828 | 1.1390 | 0.2038 | 0.2510 | 0.2249 | 0.7180 | 0.6755 | 0.6195 |
| 0.3437 | 3.0 | 1242 | 1.2184 | 0.1977 | 0.2510 | 0.2212 | 0.7121 | 0.6756 | 0.6340 |
| 0.2478 | 4.0 | 1656 | 1.2727 | 0.2035 | 0.2572 | 0.2272 | 0.7167 | 0.6779 | 0.6407 |
| 0.1769 | 5.0 | 2070 | 1.3348 | 0.2098 | 0.2572 | 0.2311 | 0.7209 | 0.6772 | 0.6407 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3