|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: KcELECTRA-small-v2022-finetuned-in-vehicle |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# KcELECTRA-small-v2022-finetuned-in-vehicle |
|
|
|
This model is a fine-tuned version of [beomi/KcELECTRA-small-v2022](https://huggingface.co/beomi/KcELECTRA-small-v2022) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2620 |
|
- Accuracy: 0.4033 |
|
- F1: 0.2471 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 2.592 | 1.0 | 38 | 2.5666 | 0.18 | 0.0549 | |
|
| 2.5555 | 2.0 | 76 | 2.5247 | 0.19 | 0.0725 | |
|
| 2.5195 | 3.0 | 114 | 2.4783 | 0.3233 | 0.1821 | |
|
| 2.4729 | 4.0 | 152 | 2.4296 | 0.36 | 0.2079 | |
|
| 2.4326 | 5.0 | 190 | 2.3825 | 0.38 | 0.2220 | |
|
| 2.3876 | 6.0 | 228 | 2.3407 | 0.3967 | 0.2318 | |
|
| 2.3521 | 7.0 | 266 | 2.3069 | 0.3967 | 0.2331 | |
|
| 2.3246 | 8.0 | 304 | 2.2815 | 0.3967 | 0.2346 | |
|
| 2.3081 | 9.0 | 342 | 2.2669 | 0.4033 | 0.2468 | |
|
| 2.2913 | 10.0 | 380 | 2.2620 | 0.4033 | 0.2471 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
