| | --- |
| | base_model: beomi/llama-2-ko-7b |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: llama_2_ko_7b_wiki_QA |
| | 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. --> |
| |
|
| | # llama_2_ko_7b_wiki_QA |
| | |
| | This model is a fine-tuned version of [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 1.1703 |
| | |
| | ## 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: 0.0002 |
| | - train_batch_size: 4 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 2 |
| | - total_train_batch_size: 8 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 100 |
| | - training_steps: 300 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 1.8568 | 0.33 | 50 | 1.4294 | |
| | | 1.2307 | 0.67 | 100 | 1.2169 | |
| | | 1.1788 | 1.0 | 150 | 1.1865 | |
| | | 1.0837 | 1.33 | 200 | 1.1810 | |
| | | 1.1905 | 1.67 | 250 | 1.1740 | |
| | | 1.161 | 2.0 | 300 | 1.1703 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.33.0.dev0 |
| | - Pytorch 2.0.0+cu117 |
| | - Datasets 2.10.1 |
| | - Tokenizers 0.13.3 |
| | |
