def start()

in src/jobs/TuneGenTopicModel.py [0:0]

• 30 lines of code
• 2 McCabe index (conditional complexity)

    def start(self):
        # Distill fine tuned model
        DISTILLATION_CONFIG = {
            "learning_rate": 3e-4,
            "batch_size": 32,
            "model_name": "google/t5-efficient-tiny",
            "label_column": "output",
            "use_keywords": True,
            "single_tab_handling": False,
            "learning_rate_decay": False,
            "shorten_training_label_boost": 0.06,
            "shrink_decoder_index_remove": "2",
            "shrink_encoder_index_remove": "2",
            "teacher_model_artifact": "moso/tab_grouping/model-v40xoz3q:v0" # Revived-dust fine tuning run
            # Other Run artifacts tested sage-mountain-341  azure-frost-334 and noble-yogurt-330
        }

        # initial fine tuning of a large model. Artifiact is then distilled with distillation config
        _FINE_TUNING_CONFIG = {
                "learning_rate": 3e-4,
                "batch_size": 4,
                "model_name": "google/flan-t5-base",
                "label_column": "output",
                "use_keywords": True,
                "single_tab_handling": False,
                "learning_rate_decay": False,
                "shorten_training_label_boost": 0.05
            }

        self.configs = [
            DISTILLATION_CONFIG
        ]
        self._skip_configs = [

        ]

        self.next(self.train, foreach='configs')