Answered step by step
Verified Expert Solution
Question
1 Approved Answer
Take the phi - 2 LLM example. Adjust train _ test _ split function to generate approximately 4 0 0 positive and 4 0 0
Take the phi LLM example. Adjust traintestsplit function to generate approximately positive and negative sentiment feature vectors. Similarly, generate positive and negative test samples. Using a batchsize of :
a Build logistic regression classifier. Report your accuracy on train and test sets. Explain if there are any overfit or underfit observed?
b Build a neural network with two hidden layers. Use nodes in each layer. Use
RELU nonlinearity. Try three different learning rates. Explain if there are any overfit or underfit observed?
c Build an encoderonly transformer network. Use two heads in attention. Try two
different learning rates and number of layers. Explain if there are any overfit or underfit observed?
d Do the partc but remove residual connections and layer normalization.
Step by Step Solution
There are 3 Steps involved in it
Step: 1
Get Instant Access to Expert-Tailored Solutions
See step-by-step solutions with expert insights and AI powered tools for academic success
Step: 2
Step: 3
Ace Your Homework with AI
Get the answers you need in no time with our AI-driven, step-by-step assistance
Get Started