Update README.md

README.md

@@ -1,9 +1,34 @@
 ---
+datasets:
+- garage-bAInd/Open-Platypus
 library_name: peft
+tags:
+- meta-llama/Llama-2-7b-hf
+- code
+- instruct
+- instruct-code
+- logical-reasoning
+- Platypus2
 ---
-## Training procedure
 
-### Framework versions
+We finetuned Meta-Llama/Llama-2-7b-hf on the Open-Platypus dataset (garage-bAInd/Open-Platypus) for 5 epochs using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
 
+#### About OpenPlatypus Dataset
+OpenPlatypus is focused on improving LLM logical reasoning skills and was used to train the Platypus2 models. The dataset is comprised of various sub-datasets, including PRM800K, ScienceQA, SciBench, ReClor, TheoremQA, among others. These were filtered using keyword search and Sentence Transformers to remove questions with a similarity above 80%. The dataset includes contributions under various licenses like MIT, Creative Commons, and Apache 2.0.
 
-- PEFT 0.5.0
+The finetuning session got completed in 1 hour and 30 minutes and costed us only `$15` for the entire finetuning run!
+
+#### Hyperparameters & Run details:
+- Model Path: meta-llama/Llama-2-7b-hf
+- Dataset: garage-bAInd/Open-Platypus
+- Learning rate: 0.0003
+- Number of epochs: 5
+- Data split: Training: 90% / Validation: 10%
+- Gradient accumulation steps: 1
+
+Loss metrics:
+![training loss](train-loss.png "Training loss")
+
+---
+license: apache-2.0
+---