Update @ 2024.03.19

T3Q-ko-solar-sft-v1.0

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:

 # 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

Base model