metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
model-index:
- name: Gemma-7B-Finetuning-JCS-Ko-Ins
results: []
Gemma-7B-Finetuning-JCS-Ko-Ins
This model is a fine-tuned version of google/gemma-7b on an unknown dataset.
Model description
dataset : nlpai-lab/databricks-dolly-15k-ko + csujeong/Non_life_insurance
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 60
Training results
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 65.18 |
| AI2 Reasoning Challenge (25-Shot) | 62.46 |
| HellaSwag (10-Shot) | 82.78 |
| MMLU (5-Shot) | 66.23 |
| TruthfulQA (0-shot) | 48.60 |
| Winogrande (5-shot) | 79.08 |
| GSM8k (5-shot) | 51.93 |