|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: EleutherAI/polyglot-ko-1.3b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: reward-gpt-b6 |
|
|
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. --> |
|
|
|
|
|
# reward-gpt-b6 |
|
|
|
|
|
This model is a fine-tuned version of [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1224 |
|
|
- Accuracy: 0.0 |
|
|
|
|
|
## 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: 9e-06 |
|
|
- train_batch_size: 6 |
|
|
- eval_batch_size: 6 |
|
|
- seed: 2023 |
|
|
- gradient_accumulation_steps: 5 |
|
|
- total_train_batch_size: 30 |
|
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.124 | 0.07 | 500 | 0.1345 | 0.0 | |
|
|
| 0.1732 | 0.14 | 1000 | 0.1297 | 0.0 | |
|
|
| 0.1023 | 0.21 | 1500 | 0.1116 | 0.0 | |
|
|
| 0.0386 | 0.29 | 2000 | 0.1426 | 0.0 | |
|
|
| 0.0716 | 0.36 | 2500 | 0.1119 | 0.0 | |
|
|
| 0.0655 | 0.43 | 3000 | 0.1272 | 0.0 | |
|
|
| 0.0725 | 0.5 | 3500 | 0.0958 | 0.0 | |
|
|
| 0.0759 | 0.57 | 4000 | 0.0975 | 0.0 | |
|
|
| 0.061 | 0.64 | 4500 | 0.1277 | 0.0 | |
|
|
| 0.0804 | 0.71 | 5000 | 0.1055 | 0.0 | |
|
|
| 0.0886 | 0.78 | 5500 | 0.1099 | 0.0 | |
|
|
| 0.0591 | 0.86 | 6000 | 0.1273 | 0.0 | |
|
|
| 0.0424 | 0.93 | 6500 | 0.1212 | 0.0 | |
|
|
| 0.122 | 1.0 | 7000 | 0.1224 | 0.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.34.1 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.14.6 |
|
|
- Tokenizers 0.14.1 |
|
|
|
