USC-Applied-NLP-Group
/

SQL-Generation

Model card Files Files and versions Metrics Training metrics Community

SQL-Generation / finetune_model.ipynb

Commit History

first cut at fine-tuning with masked training, working but very very slow for inference

a30a6cf

DeanGumas commited on Apr 7

Increasing LoRA rank to 32 and updating loss function

c78bae0

DeanGumas commited on Apr 7

First decent attempt, seems to generate valid queries after pre-training. Needs evaluation still

fdaf162

DeanGumas commited on Apr 3

First successful fine-tuning run, resulting model is no good but it does train successfully

1f9c86c

DeanGumas commited on Apr 3

Initial attempt at fine-tuning using LoRA with basic cross-entropy loss

8c47142

DeanGumas commited on Apr 3