metadata
license: mit
base_model: beomi/KcELECTRA-base-v2022
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
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: 0.0795
- Precision: 0.4023
- Recall: 0.4558
- F1: 0.4274
- Ov Accuracy: 0.9755
- Jaccard: 0.7418
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 | 0.0588 | 0.3320 | 0.3756 | 0.3525 | 0.9750 | 0.6882 |
| 0.0728 | 2.0 | 828 | 0.0603 | 0.3501 | 0.4050 | 0.3755 | 0.9743 | 0.7056 |
| 0.0457 | 3.0 | 1242 | 0.0668 | 0.3675 | 0.4162 | 0.3904 | 0.9748 | 0.7164 |
| 0.031 | 4.0 | 1656 | 0.0760 | 0.3717 | 0.4208 | 0.3947 | 0.9746 | 0.7118 |
| 0.0212 | 5.0 | 2070 | 0.0844 | 0.3725 | 0.4287 | 0.3986 | 0.9740 | 0.7154 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3