Repository files navigation

Fine-tuning the Falcon 7B for the task of HTML code generation. The current model was selected based on its performance on complex reasoning benchmarks such as ARC and GSM8K and its compatibility with the available computational resources.

Usedhttps://huggingface.co/datasets/ttbui/html_alpaca dataset which contains:Size of data: 636 rows

1. Instructions- user prompts (textual)
2. Input-Further information needed as per the instruction could be html code or data points (textual+code)
3. Response- empty
4. Output- expected HTML code

1. Model selection
2. Dataset Preparation and Preprocessing
3. Model Fine tuning script(setting hyperparameters and choosing fine tuning techniques and regularization)
4. Model Evaluation
5. API development to serve the model

1. Understanding and implementing Parameter-Efficient Tuning (PeFT).
2. Managing the computational complexity and memory limitations of large models.
3. Ensuring reproducibility and consistency across training runs.
4. Dealing with long training times and optimizing model runtime.
5. Found ways to complete the training and evaluation without buying colab pro. Out of RAM error encountered during model training was solved by trying a different way to load my fine-tuned model rather than loading base model from scratch.

1. Adopting PeFT techniques like LoRA.
2. Utilizing quantization and model sharding to manage memory usage.
3. Setting a random seed for train-test splitting to ensure reproducibility.
4. Implementing precision training, early stopping and learning rate scheduling to improve convergence speed and solve GPU memory limitations.
5. Regularization techniques such as dropout and scaling factor were applied.
6. Training arguments were carefully set up to balance performance and resource usage.

1.learning_rate: 0.00022. train_batch_size:3. eval_batch_size: 84. seed: 425.gradient_accumulation_steps: 26.total_train_batch_size: 47.optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-088.lr_scheduler_type: cosine9.lr_scheduler_warmup_ratio: 0.0310.training_steps: 320

Model link-https://huggingface.co/PrincySinghal991/falcon-7b-sharded-bf16-finetuned-html-code-generation

1. BLEU score: 0.01782

1. LLMS more suited for code generation
2. Hyperparamter tuning to improve low evalution score