---
pipeline_tag: text-generation
license: apache-2.0
language:
- en
tags:
- T3Q-ko-solar-sft-v2.0
- nlpai-lab/kullm-v2
base_model: davidkim205/nox-solar-10.7b-v4
datasets:
- nlpai-lab/kullm-v2
model-index:
- name: T3Q-ko-solar-sft-v2.0
  results: []
---
Update @ 2024.03.18

## T3Q-ko-solar-sft-v2.0

This model is a SFT fine-tuned version of davidkim205/nox-solar-10.7b-v4

**Model Developers** Chihoon Lee(chlee10), T3Q

## Training hyperparameters

The following hyperparameters were used during training:

```python
  # 데이터셋과 훈련 횟수와 관련된 하이퍼 파라미터
  batch_size = 16
  num_epochs = 1
  micro_batch = 1
  gradient_accumulation_steps = batch_size // micro_batch
  
  # 훈련 방법에 대한 하이퍼 파라미터
  cutoff_len = 4096
  lr_scheduler = 'cosine'
  warmup_ratio = 0.06 # warmup_steps = 100
  learning_rate = 4e-4
  optimizer = 'adamw_torch'
  weight_decay = 0.01
  max_grad_norm = 1.0
  
  # LoRA config(QLoRA)
  lora_r = 16
  lora_alpha = 16
  lora_dropout = 0.05
  lora_target_modules = ["gate_proj", "down_proj", "up_proj"]
  
  # Tokenizer에서 나오는 input값 설정 옵션
  train_on_inputs = False
  add_eos_token = False
  
  # NEFTune params
  noise_alpha: int = 5
```

## Framework versions

  - Transformers 4.34.1
  - Pytorch 2.1.0+cu121
  - Datasets 2.13.0
  - Tokenizers 0.14.1