The following is a list of suggestions to optimize pruning results. By adhering to these guidelines, developers have observed increased pruning ratios and minimized accuracy loss.
- Use as much data as possible to perform model analysis. Ideally, you should use all the data in the validation dataset, but this can be time-consuming. You can also use partial validation set data to ensure that at least half of the dataset is used.
- During the fine-tuning stage, experiment with a few hyperparameters, including the initial learning rate and the learning rate decay policy. Use the best result as the input for the next iteration.
- The data used in fine-tuning should be a subset of the original dataset used to train the baseline model.
- If the accuracy does not improve sufficiently after several fine-tuning experiments, try reducing the pruning rate and re-run pruning and fine-tuning.