Initial commit: FlowDock pipeline configured for WES execution

configs/callbacks/default.yaml

@@ -0,0 +1,21 @@
+defaults:
+  - ema
+  - last_model_checkpoint
+  - learning_rate_monitor
+  - model_checkpoint
+  - model_summary
+  - rich_progress_bar
+  - _self_
+
+last_model_checkpoint:
+  dirpath: ${paths.output_dir}/checkpoints
+  filename: "last"
+  monitor: null
+  verbose: True
+  auto_insert_metric_name: False
+  every_n_epochs: 1
+  save_on_train_epoch_end: True
+  enable_version_counter: False
+
+model_summary:
+  max_depth: -1

configs/callbacks/early_stopping.yaml

@@ -0,0 +1,15 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.EarlyStopping.html
+
+early_stopping:
+  _target_: lightning.pytorch.callbacks.EarlyStopping
+  monitor: ??? # quantity to be monitored, must be specified !!!
+  min_delta: 0. # minimum change in the monitored quantity to qualify as an improvement
+  patience: 3 # number of checks with no improvement after which training will be stopped
+  verbose: False # verbosity mode
+  mode: "min" # "max" means higher metric value is better, can be also "min"
+  strict: True # whether to crash the training if monitor is not found in the validation metrics
+  check_finite: True # when set True, stops training when the monitor becomes NaN or infinite
+  stopping_threshold: null # stop training immediately once the monitored quantity reaches this threshold
+  divergence_threshold: null # stop training as soon as the monitored quantity becomes worse than this threshold
+  check_on_train_epoch_end: null # whether to run early stopping at the end of the training epoch
+  # log_rank_zero_only: False  # this keyword argument isn't available in stable version

configs/callbacks/ema.yaml

@@ -0,0 +1,10 @@
+# https://github.com/NVIDIA/NeMo/blob/main/nemo/collections/common/callbacks/ema.py
+
+# Maintains an exponential moving average (EMA) of model weights.
+# Look at the above link for more detailed information regarding the original implementation.
+ema:
+  _target_: flowdock.models.components.callbacks.ema.EMA
+  decay: 0.999
+  validate_original_weights: false
+  every_n_steps: 4
+  cpu_offload: false

configs/callbacks/last_model_checkpoint.yaml

@@ -0,0 +1,21 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.ModelCheckpoint.html
+
+last_model_checkpoint:
+  # NOTE: this is a direct copy of `model_checkpoint`,
+  # which is necessary to make to work around the
+  # key-duplication limitations of YAML config files
+  _target_: flowdock.models.components.callbacks.ema.EMAModelCheckpoint
+  dirpath: null # directory to save the model file
+  filename: null # checkpoint filename
+  monitor: null # name of the logged metric which determines when model is improving
+  verbose: False # verbosity mode
+  save_last: null # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+  save_top_k: 1 # save k best models (determined by above metric)
+  mode: "min" # "max" means higher metric value is better, can be also "min"
+  auto_insert_metric_name: True # when True, the checkpoints filenames will contain the metric name
+  save_weights_only: False # if True, then only the model’s weights will be saved
+  every_n_train_steps: null # number of training steps between checkpoints
+  train_time_interval: null # checkpoints are monitored at the specified time interval
+  every_n_epochs: null # number of epochs between checkpoints
+  save_on_train_epoch_end: null # whether to run checkpointing at the end of the training epoch or the end of validation
+  enable_version_counter: True # enables versioning for checkpoint names

configs/callbacks/learning_rate_monitor.yaml

@@ -0,0 +1,7 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.LearningRateMonitor.html
+
+learning_rate_monitor:
+  _target_: lightning.pytorch.callbacks.LearningRateMonitor
+  logging_interval: null # set to `epoch` or `step` to log learning rate of all optimizers at the same interval, or set to `null` to log at individual interval according to the interval key of each scheduler
+  log_momentum: false # whether to also log the momentum values of the optimizer, if the optimizer has the `momentum` or `betas` attribute
+  log_weight_decay: false # whether to also log the weight decay values of the optimizer, if the optimizer has the `weight_decay` attribute

configs/callbacks/model_checkpoint.yaml

@@ -0,0 +1,18 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.ModelCheckpoint.html
+
+model_checkpoint:
+  _target_: flowdock.models.components.callbacks.ema.EMAModelCheckpoint
+  dirpath: null # directory to save the model file
+  filename: "best" # checkpoint filename
+  monitor: val_sampling/ligand_hit_score_2A_epoch # name of the logged metric which determines when model is improving
+  verbose: True # verbosity mode
+  save_last: False # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+  save_top_k: 1 # save k best models (determined by above metric)
+  mode: "max" # "max" means higher metric value is better, can be also "min"
+  auto_insert_metric_name: True # when True, the checkpoints filenames will contain the metric name
+  save_weights_only: False # if True, then only the model’s weights will be saved
+  every_n_train_steps: null # number of training steps between checkpoints
+  train_time_interval: null # checkpoints are monitored at the specified time interval
+  every_n_epochs: null # number of epochs between checkpoints
+  save_on_train_epoch_end: null # whether to run checkpointing at the end of the training epoch or the end of validation
+  enable_version_counter: False # enables versioning for checkpoint names

configs/callbacks/model_summary.yaml

@@ -0,0 +1,5 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.RichModelSummary.html
+
+model_summary:
+  _target_: lightning.pytorch.callbacks.RichModelSummary
+  max_depth: 1 # the maximum depth of layer nesting that the summary will include

configs/callbacks/rich_progress_bar.yaml

@@ -0,0 +1,4 @@
+# https://lightning.ai/docs/pytorch/latest/api/lightning.pytorch.callbacks.RichProgressBar.html
+
+rich_progress_bar:
+  _target_: lightning.pytorch.callbacks.RichProgressBar