diff --git a/README.md b/README.md
index 2974756d..e50dd56c 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@
 
 This project is used for training PVNet and running PVnet on live data.
 
-PVNet2 largely inherits the same architecture from
+PVNet2 is a multi-modal late-fusion model that largely inherits the same architecture from
 [PVNet1.0](https://github.com/openclimatefix/predict_pv_yield). The NWP and
 satellite data are sent through some neural network which encodes them down to
 1D intermediate representations. These are concatenated together with the GSP
@@ -14,6 +14,12 @@ feature vector is put through an output network which outputs predictions of the
 future GSP yield. National forecasts are made by adding all the GSP forecasts
 together.
 
+
+## Experiments
+
+Some quite rough working notes on experiments training this model and running it in production are
+[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
+
 ## Setup / Installation
 
 ```bash
@@ -37,7 +43,8 @@ configs directory:
 cp -r configs.example configs
 ```
 
-You will be making local amendments to these configs
+You will be making local amendments to these configs. See the README in
+`configs.example` for more info.
 
 ### Datasets
 
@@ -108,16 +115,16 @@ input_data:
       forecast_minutes: 120
       time_resolution_minutes: 60
       nwp_channels: # comment out channels as appropriate
-        - t # live = t2m
-        - dswrf
-        - dlwrf
-        - hcc
-        - MCC
-        - lcc
-        - vis
-        - r # live = r2
-        - prate # live ~= rprate
-        - si10 # 10-metre wind speed | live = unknown
+        - t         # 2-metre temperature
+        - dswrf     # downwards short-wave radiation flux
+        - dlwrf     # downwards long-wave radiation flux
+        - hcc       # high cloud cover
+        - mcc       # medium cloud cover
+        - lcc       # low cloud cover
+        - vis       # visability
+        - r         # relative humidity
+        - prate     # precipitation rate
+        - si10      # 10-metre wind speed | live = unknown
       nwp_image_size_pixels_height: 24
       nwp_image_size_pixels_width: 24
       nwp_provider: ukv
@@ -332,8 +339,3 @@ python run.py
 ## Testing
 
 You can use `python -m pytest tests` to run tests
-
-## Experiments
-
-Notes on these experiments are
-[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
diff --git a/configs.example/callbacks/default.yaml b/configs.example/callbacks/default.yaml
index a832d219..999a5bf8 100644
--- a/configs.example/callbacks/default.yaml
+++ b/configs.example/callbacks/default.yaml
@@ -1,13 +1,3 @@
-#pretrain_early_stopping:
-#  _target_: pvnet.callbacks.PretrainEarlyStopping
-#  monitor: "MAE/val" # name of the logged metric which determines when model is improving
-#  mode: "min" # can be "max" or "min"
-#  patience: 10 # how many epochs (or val check periods) of not improving until training stops
-#  min_delta: 0.001 # minimum change in the monitored metric needed to qualify as an improvement
-
-#pretrain_encoder_freezing:
-#  _target_: pvnet.callbacks.PretrainFreeze
-
 early_stopping:
   _target_: pvnet.callbacks.MainEarlyStopping
   # name of the logged metric which determines when model is improving
@@ -34,9 +24,7 @@ model_checkpoint:
   every_n_epochs: 1
   verbose: False
   filename: "epoch={epoch}-step={step}"
-  dirpath: "checkpoints/pvnet2.1/${model_name}" #${..model_name}
+  # The path to where the model checkpoints will be stored
+  dirpath: "PLACEHOLDER/${model_name}" #${..model_name}
   auto_insert_metric_name: False
   save_on_train_epoch_end: False
-#device_stats_monitor:
-#  _target_: lightning.pytorch.callbacks.DeviceStatsMonitor
-#  cpu_stats: True
diff --git a/configs.example/config.yaml b/configs.example/config.yaml
index 1af74879..9ad3457b 100644
--- a/configs.example/config.yaml
+++ b/configs.example/config.yaml
@@ -2,6 +2,7 @@
 
 # specify here default training configuration
 defaults:
+  - _self_
   - trainer: default.yaml
   - model: multimodal.yaml
   - datamodule: ocf_datapipes.yaml
diff --git a/configs.example/datamodule/configuration/gcp_configuration.yaml b/configs.example/datamodule/configuration/gcp_configuration.yaml
index 27f00990..f297df10 100644
--- a/configs.example/datamodule/configuration/gcp_configuration.yaml
+++ b/configs.example/datamodule/configuration/gcp_configuration.yaml
@@ -1,23 +1,29 @@
 general:
-  description: Config for producing batches on GCP
-  name: gcp_pvnet
+  description: Example data config for creating PVNet batches
+  name: example_pvnet
 
 input_data:
   default_history_minutes: 120
   default_forecast_minutes: 480
 
   gsp:
-    gsp_zarr_path: /mnt/disks/nwp_rechunk/pv_gsp_temp.zarr
+    # Path to the GSP data. This should be a zarr file
+    # e.g. gs://solar-pv-nowcasting-data/PV/GSP/v7/pv_gsp.zarr
+    gsp_zarr_path: PLACEHOLDER.zarr
     history_minutes: 120
     forecast_minutes: 480
     time_resolution_minutes: 30
-    metadata_only: false
 
   pv:
     pv_files_groups:
       - label: solar_sheffield_passiv
-        pv_filename: /mnt/disks/nwp_rechunk/passive/v1.1/passiv.netcdf
-        pv_metadata_filename: /mnt/disks/nwp_rechunk/passive/v0/system_metadata_OCF_ONLY.csv
+        # Path to the site-level PV data. This should be a netcdf
+        # e.g gs://solar-pv-nowcasting-data/PV/Passive/ocf_formatted/v0/passiv.netcdf
+        pv_filename: PLACEHOLDER.netcdf
+        # Path to the site-level PV metadata. This choudl be a csv
+        # e.g gs://solar-pv-nowcasting-data/PV/Passive/ocf_formatted/v0/system_metadata.csv
+        pv_metadata_filename: PLACEHOLDER.csv
+    # This is the list of pv_ml_ids to be sliced from the PV site level data
     pv_ml_ids:
       [
         154,
@@ -377,33 +383,46 @@ input_data:
   nwp:
     ukv:
       nwp_zarr_path:
-        - /mnt/disks/nwp_rechunk/UKV_intermediate_version_7.1.zarr
-        - /mnt/disks/nwp_rechunk/UKV_2021_NWP_missing_chunked.zarr
-        - /mnt/disks/nwp_rechunk/UKV_2022_NWP_chunked.zarr
-        - /mnt/disks/nwp_rechunk/UKV_2023_chunked.zarr
+        # Path(s) to UKV NWP data in zarr format
+        # e.g. gs://solar-pv-nowcasting-data/NWP/UK_Met_Office/UKV_intermediate_version_7.zarr
+        - PLACEHOLDER.zarr
       history_minutes: 120
       forecast_minutes: 480
       time_resolution_minutes: 60
       nwp_channels:
-        - t # live = t2m
-        - dswrf
-        #- lcc
-        #- mcc
-        #- hcc
-        #- dlwrf
+        - t # 2-metre temperature
+        - dswrf # downwards short-wave radiation flux
+        - dlwrf # downwards long-wave radiation flux
+        - hcc # high cloud cover
+        - mcc # medium cloud cover
+        - lcc # low cloud cover
       nwp_image_size_pixels_height: 24
       nwp_image_size_pixels_width: 24
       nwp_provider: ukv
 
+    ecmwf:
+      # Path to ECMWF NWP data in zarr format
+      # n.b. It is not necessary to use multiple or any NWP data. These entries can be removed
+      nwp_zarr_path: PLACEHOLDER.zarr
+      history_minutes: 120
+      forecast_minutes: 480
+      time_resolution_minutes: 60
+      nwp_channels:
+        - t2m # 2-metre temperature
+        - dswrf # downwards short-wave radiation flux
+        - dlwrf # downwards long-wave radiation flux
+        - hcc # high cloud cover
+        - mcc # medium cloud cover
+        - lcc # low cloud cover
+      nwp_image_size_pixels_height: 12 # roughtly equivalent to ukv 24 pixels
+      nwp_image_size_pixels_width: 12
+      nwp_provider: ecmwf
+
   satellite:
     satellite_zarr_path:
-      - /mnt/disks/nwp_rechunk/filled_sat/2017_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2018_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2019_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2020_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2021_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2022_nonhrv.zarr
-      - /mnt/disks/nwp_rechunk/filled_sat/2023_nonhrv.zarr
+      # Path(s) to non-HRV satellite data in zarr format
+      # e.g. gs://solar-pv-nowcasting-data/satellite/EUMETSAT/SEVIRI_RSS/v4/2020_nonhrv.zarr
+      - PLACEHOLDER.zarr
     history_minutes: 90
     forecast_minutes: 0
     live_delay_minutes: 30
diff --git a/configs.example/datamodule/configuration/template_configuration.yaml b/configs.example/datamodule/configuration/template_configuration.yaml
index 4163ddba..559f9d7f 100644
--- a/configs.example/datamodule/configuration/template_configuration.yaml
+++ b/configs.example/datamodule/configuration/template_configuration.yaml
@@ -1,5 +1,5 @@
 general:
-  description: Template including all settings
+  description: Template including all possible settings
   name: template
 
 input_data:
@@ -13,7 +13,6 @@ input_data:
     time_resolution_minutes: 30
     start_datetime: "2020-01-01T00:00:00"
     end_datetime: "2021-09-01T00:00:00"
-    metadata_only: false
 
   nwp:
     nwp_zarr_path: gs://solar-pv-nowcasting-data/NWP/UK_Met_Office/UKV_intermediate_version_7.zarr
@@ -71,20 +70,5 @@ input_data:
     satellite_image_size_pixels_height: 24
     satellite_image_size_pixels_width: 24
 
-  hrvsatellite:
-    hrvsatellite_zarr_path: gs://solar-pv-nowcasting-data/satellite/EUMETSAT/SEVIRI_RSS/v4/2020_hrv.zarr
-    history_minutes: 60
-    forecast_minutes: 0
-    time_resolution_minutes: 5
-    hrvsatellite_channels:
-      - HRV
-    hrvsatellite_image_size_pixels_height: 128
-    hrvsatellite_image_size_pixels_width: 256
-
-  topographic:
-    topographic_filename: gs://solar-pv-nowcasting-data/Topographic/europe_dem_1km_osgb.tif
-    topographic_image_size_pixels_width: 300
-    topographic_image_size_pixels_height: 300
-
 output_data:
   filepath: "not-needed"
diff --git a/configs.example/datamodule/ocf_datapipes.yaml b/configs.example/datamodule/ocf_datapipes.yaml
deleted file mode 100644
index 1fe1a2dd..00000000
--- a/configs.example/datamodule/ocf_datapipes.yaml
+++ /dev/null
@@ -1,14 +0,0 @@
-_target_: pvnet.data.datamodule.DataModule
-configuration: "/home/jamesfulton/repos/PVNet/configs/datamodule/configuration/gcp_configuration.yaml"
-num_workers: 20
-prefetch_factor: 2
-batch_size: 8
-train_period:
-  - null
-  - 2020-12-31
-val_period:
-  - 2021-01-01
-  - 2021-12-31
-test_period:
-  - 2021-01-01
-  - 2021-12-31
diff --git a/configs.example/datamodule/premade_batches.yaml b/configs.example/datamodule/premade_batches.yaml
index d89de16c..f08f5af2 100644
--- a/configs.example/datamodule/premade_batches.yaml
+++ b/configs.example/datamodule/premade_batches.yaml
@@ -1,6 +1,8 @@
 _target_: pvnet.data.datamodule.DataModule
 configuration: null
-batch_dir: "/mnt/disks/batches2/batches_v3.1"
-num_workers: 20
+# The batch_dir is the location batches were saved to using the save_batches.py script
+# The batch_dir should contain train and val subdirectories with batches
+batch_dir: "PLACEHOLDER"
+num_workers: 10
 prefetch_factor: 2
 batch_size: 8
diff --git a/configs.example/datamodule/streamed_batches.yaml b/configs.example/datamodule/streamed_batches.yaml
new file mode 100644
index 00000000..1b05f323
--- /dev/null
+++ b/configs.example/datamodule/streamed_batches.yaml
@@ -0,0 +1,16 @@
+_target_: pvnet.data.datamodule.DataModule
+# Path to the data configuration yaml file. You can find examples in the configuration subdirectory
+# in configs.example/datamodule/configuration
+configuration: "PLACEHOLDER.yaml"
+num_workers: 20
+prefetch_factor: 2
+batch_size: 8
+train_period:
+  - null
+  - "2022-05-07"
+val_period:
+  - "2022-05-08"
+  - "2023-05-08"
+test_period:
+  - "2022-05-08"
+  - "2023-05-08"
diff --git a/configs.example/hydra/default.yaml b/configs.example/hydra/default.yaml
index a086d12f..fb8e779d 100644
--- a/configs.example/hydra/default.yaml
+++ b/configs.example/hydra/default.yaml
@@ -1,8 +1,10 @@
 # output paths for hydra logs
 run:
-  dir: logs/runs/${now:%Y-%m-%d}/${now:%H-%M-%S}
+  # Local log directory for hydra
+  dir: PLACEHOLDER/runs/${now:%Y-%m-%d}/${now:%H-%M-%S}
 sweep:
-  dir: logs/multiruns/${now:%Y-%m-%d_%H-%M-%S}
+  # Local log directory for hydra
+  dir: PLACEHOLDER/multiruns/${now:%Y-%m-%d_%H-%M-%S}
   subdir: ${hydra.job.num}
 
 # you can set here environment variables that are universal for all users
diff --git a/configs.example/logger/comet.yaml b/configs.example/logger/comet.yaml
deleted file mode 100644
index 07d2f5d5..00000000
--- a/configs.example/logger/comet.yaml
+++ /dev/null
@@ -1,7 +0,0 @@
-# https://www.comet.ml
-
-comet:
-  _target_: pytorch_lightning.loggers.comet.CometLogger
-  api_key: ${oc.env:COMET_API_TOKEN} # api key is laoded from environment variable
-  project_name: "template-tests"
-  experiment_name: null
diff --git a/configs.example/logger/csv.yaml b/configs.example/logger/csv.yaml
index 85a78a2a..784883d2 100644
--- a/configs.example/logger/csv.yaml
+++ b/configs.example/logger/csv.yaml
@@ -2,7 +2,8 @@
 
 csv:
   _target_: pytorch_lightning.loggers.csv_logs.CSVLogger
-  save_dir: "."
+  # local path to log training process
+  save_dir: "PLACEHOLDER"
   name: "csv/"
   version: null
   prefix: ""
diff --git a/configs.example/logger/many_loggers.yaml b/configs.example/logger/many_loggers.yaml
index cb5bc0c4..5ab9ca8c 100644
--- a/configs.example/logger/many_loggers.yaml
+++ b/configs.example/logger/many_loggers.yaml
@@ -1,10 +1,7 @@
 # train with many loggers at once
 
 defaults:
-  # - aim.yaml
-  # - comet.yaml
   - csv.yaml
-  # - mlflow.yaml
   # - neptune.yaml
   # - tensorboard.yaml
   - wandb.yaml
diff --git a/configs.example/logger/mlflow.yaml b/configs.example/logger/mlflow.yaml
deleted file mode 100644
index c7b4fdab..00000000
--- a/configs.example/logger/mlflow.yaml
+++ /dev/null
@@ -1,10 +0,0 @@
-# https://mlflow.org
-
-mlflow:
-  _target_: pytorch_lightning.loggers.mlflow.MLFlowLogger
-  experiment_name: default
-  tracking_uri: null
-  tags: null
-  save_dir: ./mlruns
-  prefix: ""
-  artifact_location: null
diff --git a/configs.example/logger/neptune.yaml b/configs.example/logger/neptune.yaml
index 00d2dfa0..abc78b31 100644
--- a/configs.example/logger/neptune.yaml
+++ b/configs.example/logger/neptune.yaml
@@ -3,5 +3,6 @@
 neptune:
   _target_: pytorch_lightning.loggers.NeptuneLogger
   api_key: ${oc.env:NEPTUNE_API_TOKEN} # api key is loaded from environment variable
-  project: OpenClimateFix/predict-pv-yield
+  # Neptune project placeholder
+  project: PLACEHOLDER
   prefix: ""
diff --git a/configs.example/logger/tensorboard.yaml b/configs.example/logger/tensorboard.yaml
index ff21d176..036c9559 100644
--- a/configs.example/logger/tensorboard.yaml
+++ b/configs.example/logger/tensorboard.yaml
@@ -2,7 +2,8 @@
 
 tensorboard:
   _target_: pytorch_lightning.loggers.tensorboard.TensorBoardLogger
-  save_dir: "/mnt/disks/batches/tensorboard"
+  # Path to use for tensorboard logs
+  save_dir: "PLACEHOLDER"
   name: "default"
   version: "${model_name}"
   log_graph: False
diff --git a/configs.example/logger/wandb.yaml b/configs.example/logger/wandb.yaml
index bfd4d574..0fe80aa1 100644
--- a/configs.example/logger/wandb.yaml
+++ b/configs.example/logger/wandb.yaml
@@ -2,9 +2,11 @@
 
 wandb:
   _target_: lightning.pytorch.loggers.wandb.WandbLogger
-  project: "pvnet2.1"
+  # wandb project to log to
+  project: "PLACEHOLDER"
   name: "${model_name}"
-  save_dir: "/mnt/disks/batches/"
+  # location to store the wandb local logs
+  save_dir: "PLACEHOLDER"
   offline: False # set True to store all logs only locally
   id: null # pass correct id to resume experiment!
   # entity: ""  # set to name of your wandb team or just remove it
diff --git a/configs.example/readme.md b/configs.example/readme.md
index 13cbbf26..36bddee5 100644
--- a/configs.example/readme.md
+++ b/configs.example/readme.md
@@ -1,7 +1,8 @@
-The following folders how the configuration files
-
-This idea is copied from
-https://github.com/ashleve/lightning-hydra-template/blob/main/configs/experiment/example_simple.yaml
+This directory contains example configuration files for the PVNet project. Many paths will need to
+be each user. YOu can find these paths by searching for PLACEHOLDER within these logs. Not all of
+the values with a placeholder need to be set. For example in the logger subdirectory there are
+many different loggers with PLACEHOLDERS. If only one logger is used, then only that placeholder
+need be set.
 
 run experiments by:
 `python run.py experiment=example_simple `
diff --git a/configs.example/trainer/default.yaml b/configs.example/trainer/default.yaml
index 5f051088..965c274c 100644
--- a/configs.example/trainer/default.yaml
+++ b/configs.example/trainer/default.yaml
@@ -1,7 +1,7 @@
 _target_: lightning.pytorch.trainer.trainer.Trainer
 
 # set `1` to train on GPU, `0` to train on CPU only
-accelerator: gpu
+accelerator: auto
 devices: auto
 
 min_epochs: null
@@ -9,9 +9,6 @@ max_epochs: null
 reload_dataloaders_every_n_epochs: 0
 num_sanity_val_steps: 8
 fast_dev_run: false
-#profiler: 'simple'
 
 accumulate_grad_batches: 4
-#val_check_interval: 800
-#limit_val_batches: 800
 log_every_n_steps: 50