Update README.md

README.md

@@ -25,11 +25,28 @@ This model is a fine-tuned version of upstage/SOLAR-10.7B-v1.0
 
 The following hyperparameters were used during training:
 
-  - batch_size = 16
-  - num_epochs = 1
-  - micro_batch = 1
-  - cutoff_len = 4096
-  - learning_rate = 4e-4
+```python
+python finetune.py \
+    --base_model PracticeLLM/Twice-KoSOLAR-16.1B-test \
+    --data-path  kyujinpy/KOR-OpenOrca-Platypus-v3 \
+    --output_dir ./Twice-KoSOLAR-16.1B-instruct-test \
+    --batch_size 64 \
+    --micro_batch_size 1 \
+    --num_epochs 1 \
+    --learning_rate 3e-5 \
+    --cutoff_len 4096 \
+    --val_set_size 0 \
+    --lora_r 16 \
+    --lora_alpha 16 \
+    --lora_dropout 0.05 \
+    --lora_target_modules '[q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj, lm_head]' \
+    --train_on_inputs False \
+    --add_eos_token False \
+    --group_by_length False \
+    --prompt_template_name user_prompt \
+    --lr_scheduler 'cosine' \
+    #--warmup_steps 100 \
+```
 
 ## Framework versions