Update README.md

README.md

@@ -175,7 +175,14 @@ AI adoption is evident across various sectors, including:
 
 ## Training Details
 
-#### Training Hyperparameters
+### Training Hyperparameters
+- per_device_train_batch_size = 10
+- gradient_accumulation_steps = 4
+- optim = "paged_adamw_32bit"
+- warmup_steps = 100
+- learning_rate = 2e-4
+- max_grad_norm = 0.3
+- warmup_ratio = 0.03
 
 ## Model Limitations
 Potential Biases: With its fine-tuning centered on AI news sources, inherent biases from these sources may reflect in the model's outputs.
@@ -187,7 +194,16 @@ The Llama2-7B-AIVision360 model, developed in collaboration with CeADAR Connect
 For any further inquiries or feedback concerning Llama2-7B-AIVision360, please forward your communications to [email protected]
 
 ### Out-of-Scope Use
+Llama2-7B-AIVision360 is specifically tailored for AI news discussions. It is not optimized for:
 
-## Bias, Risks, and Limitations
+- General, non-AI-related conversations.
+- Domain-specific tasks outside AI news.
+- Direct interfacing with physical devices or applications.
 
-## Citation
+
+### Bias, Risks, and Limitations
+- Dataset Biases: The AIVision360-8k dataset may contain inherent biases that influence the model's outputs.
+- Over-reliance: The model is an aid, not a replacement for human expertise. Decisions should be made with careful consideration.
+- Content Understanding: The model lacks human-like understanding and cannot judge the veracity of news.
+- Language Limitations: The model's primary language is English. Performance may decrease with other languages.
+- Knowledge Cut-off: The model may not be aware of events or trends post its last training update.