diff --git a/CHANGELOG.md b/CHANGELOG.md
index bf61cbfb6a094..6b170d3898172 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,78 +9,65 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
-- Added `dirpath` and `filename` parameter in `ModelCheckpoint` ([#4213](https://github.com/PyTorchLightning/pytorch-lightning/pull/4213))
+- Added "monitor" key to saved `ModelCheckpoints` ([#4383](https://github.com/PyTorchLightning/pytorch-lightning/pull/4383))
 
+- Added `ConfusionMatrix` class interface ([#4348](https://github.com/PyTorchLightning/pytorch-lightning/pull/4348))
 
-- Added plugins docs and DDPPlugin to customize ddp across all accelerators ([#4258](https://github.com/PyTorchLightning/pytorch-lightning/pull/4285))
+### Changed
 
+- W&B log in sync with Trainer step ([#4405](https://github.com/PyTorchLightning/pytorch-lightning/pull/4405))
 
-- Added `strict` option to the scheduler dictionary ([#3586](https://github.com/PyTorchLightning/pytorch-lightning/pull/3586))
+### Deprecated
 
+- Deprecated passing `ModelCheckpoint` instance to `checkpoint_callback` Trainer argument ([#4336](https://github.com/PyTorchLightning/pytorch-lightning/pull/4336))
 
-- Added `fsspec` support for profilers ([#4162](https://github.com/PyTorchLightning/pytorch-lightning/pull/4162))
+### Removed
 
+### Fixed
 
-- Added autogenerated helptext to `Trainer.add_argparse_args` ([#4344](https://github.com/PyTorchLightning/pytorch-lightning/pull/4344))
+- Fixed error using `auto_select_gpus=True` with `gpus=-1` ([#4209](https://github.com/PyTorchLightning/pytorch-lightning/pull/4209))
 
 
-- Added "monitor" key to saved `ModelCheckpoints` ([#4383](https://github.com/PyTorchLightning/pytorch-lightning/pull/4383))
+## [1.0.4] - 2020-10-27
+
+### Added
 
+- Added `dirpath` and `filename` parameter in `ModelCheckpoint` ([#4213](https://github.com/PyTorchLightning/pytorch-lightning/pull/4213))
 
-- Added support for string values in `Trainer`'s `profiler` parameter ([#3656](https://github.com/PyTorchLightning/pytorch-lightning/pull/3656))
+- Added plugins docs and DDPPlugin to customize ddp across all accelerators ([#4258](https://github.com/PyTorchLightning/pytorch-lightning/pull/4285))
 
+- Added `strict` option to the scheduler dictionary ([#3586](https://github.com/PyTorchLightning/pytorch-lightning/pull/3586))
 
-- Added `ConfusionMatrix` class interface ([#4348](https://github.com/PyTorchLightning/pytorch-lightning/pull/4348))
+- Added `fsspec` support for profilers ([#4162](https://github.com/PyTorchLightning/pytorch-lightning/pull/4162))
 
+- Added autogenerated helptext to `Trainer.add_argparse_args` ([#4344](https://github.com/PyTorchLightning/pytorch-lightning/pull/4344))
 
-### Changed
+- Added support for string values in `Trainer`'s `profiler` parameter ([#3656](https://github.com/PyTorchLightning/pytorch-lightning/pull/3656))
 
+### Changed
 
 - Improved error messages for invalid `configure_optimizers` returns ([#3587](https://github.com/PyTorchLightning/pytorch-lightning/pull/3587))
 
-
 - Allow changing the logged step value in `validation_step` ([#4130](https://github.com/PyTorchLightning/pytorch-lightning/pull/4130))
 
-
 - Allow setting `replace_sampler_ddp=True` with a distributed sampler already added ([#4273](https://github.com/PyTorchLightning/pytorch-lightning/pull/4273))
 
-
 - Fixed santized parameters for `WandbLogger.log_hyperparams` ([#4320](https://github.com/PyTorchLightning/pytorch-lightning/pull/4320))
 
-
-- W&B log in sync with Trainer step ([#4405](https://github.com/PyTorchLightning/pytorch-lightning/pull/4405))
-
-
 ### Deprecated
 
-
 - Deprecated `filepath` in `ModelCheckpoint` ([#4213](https://github.com/PyTorchLightning/pytorch-lightning/pull/4213))
 
-
 - Deprecated `reorder` parameter of the `auc` metric ([#4237](https://github.com/PyTorchLightning/pytorch-lightning/pull/4237))
 
-
 - Deprecated bool values in `Trainer`'s `profiler` parameter ([#3656](https://github.com/PyTorchLightning/pytorch-lightning/pull/3656))
 
-
-- Deprecated passing `ModelCheckpoint` instance to `checkpoint_callback` Trainer argument ([#4336](https://github.com/PyTorchLightning/pytorch-lightning/pull/4336))
-
-### Removed
-
-
-
 ### Fixed
 
-
-- Fixed error using `auto_select_gpus=True` with `gpus=-1` ([#4209](https://github.com/PyTorchLightning/pytorch-lightning/pull/4209))
-
-
 - Fixed setting device ids in DDP ([#4297](https://github.com/PyTorchLightning/pytorch-lightning/pull/4297))
 
-
 - Fixed synchronization of best model path in `ddp_accelerator` ([#4323](https://github.com/PyTorchLightning/pytorch-lightning/pull/4323))
 
-
 - Fixed WandbLogger not uploading checkpoint artifacts at the end of training ([#4341](https://github.com/PyTorchLightning/pytorch-lightning/pull/4341))