1. Represent data as tensors with explicit shape
TASK: Inspect tensor shapes and partition the first 24 rows for training, next eight for validation and last eight for final testing.
Your method:
Your evidence/result:
Limitations and next action:


2. Implement forward, backward and optimizer steps
TASK: Trace one training iteration and explain each of zero_grad, forward loss, backward and step. Run the worked script locally.
Your method:
Your evidence/result:
Limitations and next action:


3. Evaluate without changing the model
TASK: Explain eval versus no_grad and calculate the validation correct-count denominator. Record what the script does not score.
Your method:
Your evidence/result:
Limitations and next action: