Pycmtensor

Fix

- added f1 score to list of output statistics

Fix

- changed results output SD on the same row as param
- update model patience config option

Fix

- added optimal acceptance time recording to results

Refactor

- refactored run.py

Feat

- add `ones` init type to `Weight`

Fix

- remove watermark dependencies
- make watermark package optional
- changed precision to 4
- fix incorrect text display for model.config
- added assert checks for incorrect choice set numbering in dataset

Refactor

- fix argument name inconsistency

Feat

- **functions.py**: added `gelu` function

Fix

- **basic.py**: fix bug in `null_log_likelihood_fn` for givens
- **dataset.py**: fixed slice call when no `batch_size` argument is used
- **dataset.py**: fixed the `split` method to accept `None` as argument

Refactor

- **functions.py**: refactored method to covert list of utilities to tensor variables
- **dataset.py**: accept mixed `str` and `TensorVariable` types in `_make_tensor`
- **basic.py**: moved `build_gh_fn()` to `BaseModel`