|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ko-jeolla-nmt-v2 |
|
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. --> |
|
|
|
# ko-jeolla-nmt-v2 |
|
|
|
This model is a fine-tuned version of [leadawon/ko-jeolla-nmt-v1](https://huggingface.co/leadawon/ko-jeolla-nmt-v1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2911 |
|
|
|
## 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: 24 |
|
- eval_batch_size: 24 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 96 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.2926 | 0.17 | 500 | 0.3283 | |
|
| 0.3111 | 0.33 | 1000 | 0.3344 | |
|
| 0.3009 | 0.5 | 1500 | 0.3138 | |
|
| 0.2868 | 0.66 | 2000 | 0.3030 | |
|
| 0.2653 | 0.83 | 2500 | 0.2969 | |
|
| 0.2493 | 0.99 | 3000 | 0.2911 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Tokenizers 0.13.2 |
|
|
