Added Bert Baseline comparison training script and ignored unneccessary files

Updated Dockerfile and some model issues

Cleaned up code, added multiseed training wrapper, PyTorch profiler training option, updated gradio demo, made changes to research paper to match new changes and new training results from adding new training techniques, architecture.md now explains all designs and decisions

Added many new improvements based on feedback from others

Updated Research Paper, README, and old gradio about info, along with other docs.

Added separate academic and research versions of the research paper

Full training results & evaluation with BERTScore

Fixed compiling issue, added legnth penalty, and atttempting freezing encoder layers 0-5 to lower parameters and preserve T5's langauge understanding.

Clean up codebase and fix training bugs

Update LexiMind: improved training, model architecture, and evaluation

feat: Add FLAN-T5 compatibility with relative position bias

chore: snapshot current refinements

Reformatted Project Structure