Update CHANGELOG.md

Author: carmocca

CHANGELOG.md

@@ -218,18 +218,9 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Fixed `DataModule.prepare_data` could only be called on the global rank 0 process ([#7945](https://github.com/PyTorchLightning/pytorch-lightning/pull/7945))
 
 
-- Fixed `_check_training_step_output` to be called after `train_step_end` to support more flexible accomodations ([#7868](https://github.com/PyTorchLightning/pytorch-lightning/pull/7868))
-
-
-- Fixed `apply_to_collection` works on Custom Collections now ([#7851](https://github.com/PyTorchLightning/pytorch-lightning/pull/7851))
-
-
 - Fixed ambiguous warning when both overfit and train dataloader shuffling are enabled ([#7685](https://github.com/PyTorchLightning/pytorch-lightning/pull/7685))
 
 
-- Fixed dataloaders are not reset when tuning the model ([#7566](https://github.com/PyTorchLightning/pytorch-lightning/pull/7566))
-
-
 - Fixed dev debugger memory growing due to tracking events even when disabled ([#7875](https://github.com/PyTorchLightning/pytorch-lightning/pull/7875))