Update README.md (#1)

- Update README.md (551c6ea1dba24349afd174e54091a2b392252d21)


Co-authored-by: Souvik Datta <[email protected]>

README.md

@@ -1,9 +1,44 @@
 ---
 library_name: peft
+tags:
+- code
+- instruct
+- code-llama
+datasets:
+- ehartford/dolphin-2.5-mixtral-8x7b
+base_model: codellama/CodeLlama-7b-hf
+license: apache-2.0
 ---
-## Training procedure
 
-### Framework versions
+### Finetuning Overview:
 
+**Model Used:** codellama/CodeLlama-7b-hf 
 
-- PEFT 0.5.0
+**Dataset:** ehartford/dolphin-2.5-mixtral-8x7b  
+
+#### Dataset Insights:
+
+[No Robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots) is a high-quality dataset of 10,000 instructions and demonstrations created by skilled human annotators. This data can be used for supervised fine-tuning (SFT) to make language models follow instructions better.
+
+#### Finetuning Details:
+
+With the utilization of [MonsterAPI](https://monsterapi.ai)'s [no-code LLM finetuner](https://monsterapi.ai/finetuning), this finetuning:
+
+- Was achieved with great cost-effectiveness.
+- Completed in a total duration of 1h 15m 3s for 2 epochs using an A6000 48GB GPU.
+- Costed `$2.525` for the entire 2 epochs.
+
+#### Hyperparameters & Additional Details:
+
+- **Epochs:** 2
+- **Cost Per Epoch:** $1.26
+- **Total Finetuning Cost:** $2.525
+- **Model Path:** codellama/CodeLlama-7b-hf
+- **Learning Rate:** 0.0002
+- **Data Split:** 100% train 
+- **Gradient Accumulation Steps:** 64
+- **lora r:** 64
+- **lora alpha:** 16
+
+---
+license: apache-2.0