Update README.md

README.md

@@ -176,7 +176,7 @@ print(outputs[0]["generated_text"][len(prompt):])
 - train_batch_size: 12
 - eval_batch_size: 8
 - GPU: H100 80GB SXM5
-- num_devices: 8
+- num_devices: 1
 - optimizer: adamw_bnb_8bit
 - lr_scheduler_warmup_steps: 100
 - num_epochs: 4
@@ -220,7 +220,7 @@ print(outputs[0]["generated_text"][len(prompt):])
 
 # Benchmark Results
 
-🔥 OpenBioMed-8B demonstrates superior performance compared to larger models, such as GPT-3.5,  Gemini, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
+🔥 OpenBioMed-8B demonstrates superior performance compared to larger models, such as GPT-3.5,  Gemini, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
 
 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.