basic testing of configs , remove targets for callbacks and loggers

configs/callbacks/default.yaml

@@ -18,4 +18,7 @@ early_stopping:
   mode: "min"
 
 model_summary:
-  max_depth: -1
+  max_depth: -1
+
+rich_progress_bar:
+  refresh_rate: 1

configs/callbacks/early_stopping.yaml

@@ -1,7 +1,6 @@
 # https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.EarlyStopping.html
 
 early_stopping:
-  _target_: lightning.pytorch.callbacks.EarlyStopping
   monitor: val_loss # 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

configs/callbacks/model_checkpoint.yaml

@@ -1,7 +1,6 @@
 # https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.ModelCheckpoint.html
 
 model_checkpoint:
-  _target_: lightning.pytorch.callbacks.ModelCheckpoint
   dirpath: null # directory to save the model file
   filename: best-checkpoint # checkpoint filename
   monitor: val_loss # name of the logged metric which determines when model is improving

configs/callbacks/model_summary.yaml

@@ -1,3 +1,2 @@
 model_summary:
-  _target_: lightning.pytorch.callbacks.RichModelSummary
-  max_depth: 2
+  max_depth: 1

configs/callbacks/rich_progress_bar.yaml

@@ -1,2 +1,2 @@
 rich_progress_bar:
-  _target_: lightning.pytorch.callbacks.RichProgressBar
+  refresh_rate: 1

configs/experiment/catdog_experiment.yaml

@@ -46,8 +46,16 @@ callbacks:
     mode: "max"
     save_top_k: 1
     save_last: True
+    verbose: True
 
   early_stopping:
     monitor: "val_acc"
     patience: 10
     mode: "max"
+    verbose: True
+
+  model_summary:
+    max_depth: 1
+
+  rich_progress_bar:
+    refresh_rate: 1

configs/logger/aim.yaml

@@ -1,5 +1,4 @@
 aim:
-  __target__: aim.pytorch_lightning.AimLogger
   experiment: ${name}
   train_metric_prefix: train_
   test_metric_prefix: test_

configs/logger/csv.yaml

@@ -1,7 +1,6 @@
 # csv logger built in lightning
 
 csv:
-  _target_: lightning.pytorch.loggers.csv_logs.CSVLogger
   save_dir: "${paths.output_dir}"
   name: "csv/"
   prefix: ""

configs/logger/default.yaml

@@ -2,6 +2,4 @@
 
 defaults:
   - csv
-  - tensorboard
-  - aim
-  - mlflow
+  - tensorboard

configs/logger/mlflow.yaml

@@ -1,7 +1,6 @@
 # MLflow logger configuration
 
 mlflow:
-  _target_: lightning.pytorch.loggers.MLFlowLogger
   experiment_name: ${name}
   tracking_uri: file:${paths.log_dir}/mlruns
   save_dir: ${paths.log_dir}/mlruns

configs/logger/tensorboard.yaml

@@ -1,7 +1,6 @@
 # https://www.tensorflow.org/tensorboard/
 
 tensorboard:
-  _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
   save_dir: "${paths.output_dir}/tensorboard/"
   name: null
   log_graph: False

configs/model/catdog_classifier.yaml

@@ -1,5 +1,6 @@
 
-_target_: src.models.catdog_classifier.ViTTinyClassifier
+# model class
+_target_: src.models.catdog_model.ViTTinyClassifier
 
 # model params
 img_size: 160

configs/train.yaml

@@ -7,7 +7,7 @@ defaults:
   - data: catdog
   - model: catdog_classifier
   - callbacks: default
-  - logger: null # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - logger: default # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
   - trainer: default
   - paths: catdog
   - hydra: default

logs/train/runs/{2024-11-08_14-32-38 → 2024-11-08_15-27-10}/.hydra/config.yaml

@@ -19,7 +19,7 @@ data:
   image_size: 160
   dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
 model:
-  _target_: src.models.catdog_classifier.ViTTinyClassifier
+  _target_: src.models.catdog_model.ViTTinyClassifier
   img_size: 160
   patch_size: 16
   num_classes: 2
@@ -35,7 +35,6 @@ model:
   min_lr: 1.0e-06
 callbacks:
   model_checkpoint:
-    _target_: lightning.pytorch.callbacks.ModelCheckpoint
     dirpath: ${paths.ckpt_dir}
     filename: best-checkpoint
     monitor: val_acc
@@ -50,7 +49,6 @@ callbacks:
     every_n_epochs: null
     save_on_train_epoch_end: null
   early_stopping:
-    _target_: lightning.pytorch.callbacks.EarlyStopping
     monitor: val_acc
     min_delta: 0.0
     patience: 10
@@ -62,36 +60,20 @@ callbacks:
     divergence_threshold: null
     check_on_train_epoch_end: null
   model_summary:
-    _target_: lightning.pytorch.callbacks.RichModelSummary
-    max_depth: -1
+    max_depth: 1
   rich_progress_bar:
-    _target_: lightning.pytorch.callbacks.RichProgressBar
+    refresh_rate: 1
 logger:
   csv:
-    _target_: lightning.pytorch.loggers.csv_logs.CSVLogger
     save_dir: ${paths.output_dir}
     name: csv/
     prefix: ''
   tensorboard:
-    _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
     save_dir: ${paths.output_dir}/tensorboard/
     name: null
     log_graph: false
     default_hp_metric: true
     prefix: ''
-  aim:
-    __target__: aim.pytorch_lightning.AimLogger
-    experiment: ${name}
-    train_metric_prefix: train_
-    test_metric_prefix: test_
-    val_metric_prefix: val_
-  mlflow:
-    _target_: lightning.pytorch.loggers.MLFlowLogger
-    experiment_name: ${name}
-    tracking_uri: file:${paths.log_dir}/mlruns
-    save_dir: ${paths.log_dir}/mlruns
-    log_model: false
-    prefix: ''
 trainer:
   _target_: lightning.Trainer
   default_root_dir: ${paths.output_dir}

logs/train/runs/{2024-11-08_14-29-05 → 2024-11-08_15-27-10}/.hydra/hydra.yaml

@@ -121,7 +121,7 @@ hydra:
     - hydra.mode=RUN
     task: []
   job:
-    name: catdog_datamodule
+    name: hydra_test
     chdir: null
     override_dirname: ''
     id: ???
@@ -136,7 +136,7 @@ hydra:
         exclude_keys: []
   runtime:
     version: 1.3.2
-    version_base: '1.3'
+    version_base: '1.1'
     cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
     config_sources:
     - path: hydra.conf
@@ -151,7 +151,7 @@ hydra:
     - path: ''
       schema: structured
       provider: schema
-    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_14-29-05
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-27-10
     choices:
       debug: null
       experiment: catdog_experiment

logs/train/runs/{2024-11-08_14-29-05 → 2024-11-08_15-29-07}/.hydra/config.yaml

@@ -12,13 +12,14 @@ data:
   url: ${paths.data_url}
   num_workers: 8
   batch_size: 64
-  splits:
+  train_val_split:
   - 0.8
   - 0.2
   pin_memory: true
   image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
 model:
-  _target_: src.models.catdog_classifier.ViTTinyClassifier
+  _target_: src.models.catdog_model.ViTTinyClassifier
   img_size: 160
   patch_size: 16
   num_classes: 2
@@ -34,7 +35,6 @@ model:
   min_lr: 1.0e-06
 callbacks:
   model_checkpoint:
-    _target_: lightning.pytorch.callbacks.ModelCheckpoint
     dirpath: ${paths.ckpt_dir}
     filename: best-checkpoint
     monitor: val_acc
@@ -49,7 +49,6 @@ callbacks:
     every_n_epochs: null
     save_on_train_epoch_end: null
   early_stopping:
-    _target_: lightning.pytorch.callbacks.EarlyStopping
     monitor: val_acc
     min_delta: 0.0
     patience: 10
@@ -61,36 +60,20 @@ callbacks:
     divergence_threshold: null
     check_on_train_epoch_end: null
   model_summary:
-    _target_: lightning.pytorch.callbacks.RichModelSummary
-    max_depth: -1
+    max_depth: 1
   rich_progress_bar:
-    _target_: lightning.pytorch.callbacks.RichProgressBar
+    refresh_rate: 1
 logger:
   csv:
-    _target_: lightning.pytorch.loggers.csv_logs.CSVLogger
     save_dir: ${paths.output_dir}
     name: csv/
     prefix: ''
   tensorboard:
-    _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
     save_dir: ${paths.output_dir}/tensorboard/
     name: null
     log_graph: false
     default_hp_metric: true
     prefix: ''
-  aim:
-    __target__: aim.pytorch_lightning.AimLogger
-    experiment: ${name}
-    train_metric_prefix: train_
-    test_metric_prefix: test_
-    val_metric_prefix: val_
-  mlflow:
-    _target_: lightning.pytorch.loggers.MLFlowLogger
-    experiment_name: ${name}
-    tracking_uri: file:${paths.log_dir}/mlruns
-    save_dir: ${paths.log_dir}/mlruns
-    log_model: false
-    prefix: ''
 trainer:
   _target_: lightning.Trainer
   default_root_dir: ${paths.output_dir}

logs/train/runs/{2024-11-08_14-32-38 → 2024-11-08_15-29-07}/.hydra/hydra.yaml

@@ -121,7 +121,7 @@ hydra:
     - hydra.mode=RUN
     task: []
   job:
-    name: catdog_datamodule
+    name: hydra_test
     chdir: null
     override_dirname: ''
     id: ???
@@ -136,7 +136,7 @@ hydra:
         exclude_keys: []
   runtime:
     version: 1.3.2
-    version_base: '1.3'
+    version_base: '1.1'
     cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
     config_sources:
     - path: hydra.conf
@@ -151,7 +151,7 @@ hydra:
     - path: ''
       schema: structured
       provider: schema
-    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_14-32-38
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-29-07
     choices:
       debug: null
       experiment: catdog_experiment

logs/train/runs/2024-11-08_15-29-42/.hydra/config.yaml

@@ -0,0 +1,95 @@
+task_name: train
+tags:
+- dev
+train: true
+test: false
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+seed: 42
+name: catdog_experiment
+data:
+  _target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+  data_dir: ${paths.data_dir}
+  url: ${paths.data_url}
+  num_workers: 8
+  batch_size: 64
+  train_val_split:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
+model:
+  _target_: src.models.catdog_model.ViTTinyClassifier
+  img_size: 160
+  patch_size: 16
+  num_classes: 2
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+  pre_norm: false
+  lr: 0.001
+  weight_decay: 1.0e-05
+  factor: 0.1
+  patience: 10
+  min_lr: 1.0e-06
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.ckpt_dir}
+    filename: best-checkpoint
+    monitor: val_acc
+    verbose: false
+    save_last: true
+    save_top_k: 1
+    mode: max
+    auto_insert_metric_name: false
+    save_weights_only: false
+    every_n_train_steps: null
+    train_time_interval: null
+    every_n_epochs: null
+    save_on_train_epoch_end: null
+  early_stopping:
+    monitor: val_acc
+    min_delta: 0.0
+    patience: 10
+    verbose: false
+    mode: max
+    strict: true
+    check_finite: true
+    stopping_threshold: null
+    divergence_threshold: null
+    check_on_train_epoch_end: null
+  model_summary:
+    max_depth: 1
+  rich_progress_bar:
+    refresh_rate: 1
+logger:
+  csv:
+    save_dir: ${paths.output_dir}
+    name: csv/
+    prefix: ''
+  tensorboard:
+    save_dir: ${paths.output_dir}/tensorboard/
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ''
+trainer:
+  _target_: lightning.Trainer
+  default_root_dir: ${paths.output_dir}
+  min_epochs: 1
+  max_epochs: 6
+  accelerator: auto
+  devices: auto
+  deterministic: true
+  log_every_n_steps: 10
+  fast_dev_run: false
+paths:
+  root_dir: ${oc.env:PROJECT_ROOT}
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  ckpt_dir: ${paths.root_dir}/checkpoints
+  artifact_dir: ${paths.root_dir}/artifacts/
+  data_url: https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}

logs/train/runs/2024-11-08_15-29-42/.hydra/hydra.yaml

@@ -0,0 +1,174 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s]
+          - %(message)s'
+        log_colors:
+          DEBUG: purple
+          INFO: green
+          WARNING: yellow
+          ERROR: red
+          CRITICAL: red
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: hydra_test
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/configs
+      schema: file
+      provider: main
+    - path: hydra_plugins.hydra_colorlog.conf
+      schema: pkg
+      provider: hydra-colorlog
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-29-42
+    choices:
+      debug: null
+      experiment: catdog_experiment
+      hydra: default
+      paths: catdog
+      trainer: default
+      logger: default
+      callbacks: default
+      model: catdog_classifier
+      data: catdog
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: colorlog
+      hydra/hydra_logging: colorlog
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

logs/train/runs/2024-11-08_15-29-42/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

logs/train/runs/2024-11-08_15-30-22/.hydra/config.yaml

@@ -0,0 +1,95 @@
+task_name: train
+tags:
+- dev
+train: true
+test: false
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+seed: 42
+name: catdog_experiment
+data:
+  _target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+  data_dir: ${paths.data_dir}
+  url: ${paths.data_url}
+  num_workers: 8
+  batch_size: 64
+  train_val_split:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
+model:
+  _target_: src.models.catdog_model.ViTTinyClassifier
+  img_size: 160
+  patch_size: 16
+  num_classes: 2
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+  pre_norm: false
+  lr: 0.001
+  weight_decay: 1.0e-05
+  factor: 0.1
+  patience: 10
+  min_lr: 1.0e-06
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.ckpt_dir}
+    filename: best-checkpoint
+    monitor: val_acc
+    verbose: false
+    save_last: true
+    save_top_k: 1
+    mode: max
+    auto_insert_metric_name: false
+    save_weights_only: false
+    every_n_train_steps: null
+    train_time_interval: null
+    every_n_epochs: null
+    save_on_train_epoch_end: null
+  early_stopping:
+    monitor: val_acc
+    min_delta: 0.0
+    patience: 10
+    verbose: false
+    mode: max
+    strict: true
+    check_finite: true
+    stopping_threshold: null
+    divergence_threshold: null
+    check_on_train_epoch_end: null
+  model_summary:
+    max_depth: 1
+  rich_progress_bar:
+    refresh_rate: 1
+logger:
+  csv:
+    save_dir: ${paths.output_dir}
+    name: csv/
+    prefix: ''
+  tensorboard:
+    save_dir: ${paths.output_dir}/tensorboard/
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ''
+trainer:
+  _target_: lightning.Trainer
+  default_root_dir: ${paths.output_dir}
+  min_epochs: 1
+  max_epochs: 6
+  accelerator: auto
+  devices: auto
+  deterministic: true
+  log_every_n_steps: 10
+  fast_dev_run: false
+paths:
+  root_dir: ${oc.env:PROJECT_ROOT}
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  ckpt_dir: ${paths.root_dir}/checkpoints
+  artifact_dir: ${paths.root_dir}/artifacts/
+  data_url: https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}

logs/train/runs/2024-11-08_15-30-22/.hydra/hydra.yaml

@@ -0,0 +1,174 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s]
+          - %(message)s'
+        log_colors:
+          DEBUG: purple
+          INFO: green
+          WARNING: yellow
+          ERROR: red
+          CRITICAL: red
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: hydra_test
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/configs
+      schema: file
+      provider: main
+    - path: hydra_plugins.hydra_colorlog.conf
+      schema: pkg
+      provider: hydra-colorlog
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-30-22
+    choices:
+      debug: null
+      experiment: catdog_experiment
+      hydra: default
+      paths: catdog
+      trainer: default
+      logger: default
+      callbacks: default
+      model: catdog_classifier
+      data: catdog
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: colorlog
+      hydra/hydra_logging: colorlog
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

logs/train/runs/2024-11-08_15-30-22/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

logs/train/runs/2024-11-08_15-35-40/.hydra/config.yaml

@@ -0,0 +1,95 @@
+task_name: train
+tags:
+- dev
+train: true
+test: false
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+seed: 42
+name: catdog_experiment
+data:
+  _target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+  data_dir: ${paths.data_dir}
+  url: ${paths.data_url}
+  num_workers: 8
+  batch_size: 64
+  train_val_split:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
+model:
+  _target_: src.models.catdog_model.ViTTinyClassifier
+  img_size: 160
+  patch_size: 16
+  num_classes: 2
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+  pre_norm: false
+  lr: 0.001
+  weight_decay: 1.0e-05
+  factor: 0.1
+  patience: 10
+  min_lr: 1.0e-06
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.ckpt_dir}
+    filename: best-checkpoint
+    monitor: val_acc
+    verbose: false
+    save_last: true
+    save_top_k: 1
+    mode: max
+    auto_insert_metric_name: false
+    save_weights_only: false
+    every_n_train_steps: null
+    train_time_interval: null
+    every_n_epochs: null
+    save_on_train_epoch_end: null
+  early_stopping:
+    monitor: val_acc
+    min_delta: 0.0
+    patience: 10
+    verbose: false
+    mode: max
+    strict: true
+    check_finite: true
+    stopping_threshold: null
+    divergence_threshold: null
+    check_on_train_epoch_end: null
+  model_summary:
+    max_depth: 1
+  rich_progress_bar:
+    refresh_rate: 1
+logger:
+  csv:
+    save_dir: ${paths.output_dir}
+    name: csv/
+    prefix: ''
+  tensorboard:
+    save_dir: ${paths.output_dir}/tensorboard/
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ''
+trainer:
+  _target_: lightning.Trainer
+  default_root_dir: ${paths.output_dir}
+  min_epochs: 1
+  max_epochs: 6
+  accelerator: auto
+  devices: auto
+  deterministic: true
+  log_every_n_steps: 10
+  fast_dev_run: false
+paths:
+  root_dir: ${oc.env:PROJECT_ROOT}
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  ckpt_dir: ${paths.root_dir}/checkpoints
+  artifact_dir: ${paths.root_dir}/artifacts/
+  data_url: https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}

logs/train/runs/2024-11-08_15-35-40/.hydra/hydra.yaml

@@ -0,0 +1,174 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s]
+          - %(message)s'
+        log_colors:
+          DEBUG: purple
+          INFO: green
+          WARNING: yellow
+          ERROR: red
+          CRITICAL: red
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: hydra_test2
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/configs
+      schema: file
+      provider: main
+    - path: hydra_plugins.hydra_colorlog.conf
+      schema: pkg
+      provider: hydra-colorlog
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-35-40
+    choices:
+      debug: null
+      experiment: catdog_experiment
+      hydra: default
+      paths: catdog
+      trainer: default
+      logger: default
+      callbacks: default
+      model: catdog_classifier
+      data: catdog
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: colorlog
+      hydra/hydra_logging: colorlog
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

logs/train/runs/2024-11-08_15-35-40/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

logs/train/runs/2024-11-08_15-35-57/.hydra/config.yaml

@@ -0,0 +1,95 @@
+task_name: train
+tags:
+- dev
+train: true
+test: false
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+seed: 42
+name: catdog_experiment
+data:
+  _target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+  data_dir: ${paths.data_dir}
+  url: ${paths.data_url}
+  num_workers: 8
+  batch_size: 64
+  train_val_split:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
+model:
+  _target_: src.models.catdog_model.ViTTinyClassifier
+  img_size: 160
+  patch_size: 16
+  num_classes: 2
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+  pre_norm: false
+  lr: 0.001
+  weight_decay: 1.0e-05
+  factor: 0.1
+  patience: 10
+  min_lr: 1.0e-06
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.ckpt_dir}
+    filename: best-checkpoint
+    monitor: val_acc
+    verbose: false
+    save_last: true
+    save_top_k: 1
+    mode: max
+    auto_insert_metric_name: false
+    save_weights_only: false
+    every_n_train_steps: null
+    train_time_interval: null
+    every_n_epochs: null
+    save_on_train_epoch_end: null
+  early_stopping:
+    monitor: val_acc
+    min_delta: 0.0
+    patience: 10
+    verbose: false
+    mode: max
+    strict: true
+    check_finite: true
+    stopping_threshold: null
+    divergence_threshold: null
+    check_on_train_epoch_end: null
+  model_summary:
+    max_depth: 1
+  rich_progress_bar:
+    refresh_rate: 1
+logger:
+  csv:
+    save_dir: ${paths.output_dir}
+    name: csv/
+    prefix: ''
+  tensorboard:
+    save_dir: ${paths.output_dir}/tensorboard/
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ''
+trainer:
+  _target_: lightning.Trainer
+  default_root_dir: ${paths.output_dir}
+  min_epochs: 1
+  max_epochs: 6
+  accelerator: auto
+  devices: auto
+  deterministic: true
+  log_every_n_steps: 10
+  fast_dev_run: false
+paths:
+  root_dir: ${oc.env:PROJECT_ROOT}
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  ckpt_dir: ${paths.root_dir}/checkpoints
+  artifact_dir: ${paths.root_dir}/artifacts/
+  data_url: https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}

logs/train/runs/2024-11-08_15-35-57/.hydra/hydra.yaml

@@ -0,0 +1,174 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s]
+          - %(message)s'
+        log_colors:
+          DEBUG: purple
+          INFO: green
+          WARNING: yellow
+          ERROR: red
+          CRITICAL: red
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: hydra_test2
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/configs
+      schema: file
+      provider: main
+    - path: hydra_plugins.hydra_colorlog.conf
+      schema: pkg
+      provider: hydra-colorlog
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-35-57
+    choices:
+      debug: null
+      experiment: catdog_experiment
+      hydra: default
+      paths: catdog
+      trainer: default
+      logger: default
+      callbacks: default
+      model: catdog_classifier
+      data: catdog
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: colorlog
+      hydra/hydra_logging: colorlog
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

logs/train/runs/2024-11-08_15-35-57/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

logs/train/runs/2024-11-08_15-37-45/.hydra/config.yaml

@@ -0,0 +1,95 @@
+task_name: train
+tags:
+- dev
+train: true
+test: false
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+seed: 42
+name: catdog_experiment
+data:
+  _target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+  data_dir: ${paths.data_dir}
+  url: ${paths.data_url}
+  num_workers: 8
+  batch_size: 64
+  train_val_split:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+  dataset_url: https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip
+model:
+  _target_: src.models.catdog_model.ViTTinyClassifier
+  img_size: 160
+  patch_size: 16
+  num_classes: 2
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+  pre_norm: false
+  lr: 0.001
+  weight_decay: 1.0e-05
+  factor: 0.1
+  patience: 10
+  min_lr: 1.0e-06
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.ckpt_dir}
+    filename: best-checkpoint
+    monitor: val_acc
+    verbose: true
+    save_last: true
+    save_top_k: 1
+    mode: max
+    auto_insert_metric_name: false
+    save_weights_only: false
+    every_n_train_steps: null
+    train_time_interval: null
+    every_n_epochs: null
+    save_on_train_epoch_end: null
+  early_stopping:
+    monitor: val_acc
+    min_delta: 0.0
+    patience: 10
+    verbose: true
+    mode: max
+    strict: true
+    check_finite: true
+    stopping_threshold: null
+    divergence_threshold: null
+    check_on_train_epoch_end: null
+  model_summary:
+    max_depth: 1
+  rich_progress_bar:
+    refresh_rate: 1
+logger:
+  csv:
+    save_dir: ${paths.output_dir}
+    name: csv/
+    prefix: ''
+  tensorboard:
+    save_dir: ${paths.output_dir}/tensorboard/
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ''
+trainer:
+  _target_: lightning.Trainer
+  default_root_dir: ${paths.output_dir}
+  min_epochs: 1
+  max_epochs: 6
+  accelerator: auto
+  devices: auto
+  deterministic: true
+  log_every_n_steps: 10
+  fast_dev_run: false
+paths:
+  root_dir: ${oc.env:PROJECT_ROOT}
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  ckpt_dir: ${paths.root_dir}/checkpoints
+  artifact_dir: ${paths.root_dir}/artifacts/
+  data_url: https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}

logs/train/runs/2024-11-08_15-37-45/.hydra/hydra.yaml

@@ -0,0 +1,174 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      colorlog:
+        (): colorlog.ColoredFormatter
+        format: '[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s]
+          - %(message)s'
+        log_colors:
+          DEBUG: purple
+          INFO: green
+          WARNING: yellow
+          ERROR: red
+          CRITICAL: red
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: colorlog
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: hydra_test2
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/configs
+      schema: file
+      provider: main
+    - path: hydra_plugins.hydra_colorlog.conf
+      schema: pkg
+      provider: hydra-colorlog
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /mnt/batch/tasks/shared/LS_root/mounts/clusters/soutrik-vm-dev/code/Users/Soutrik.Chowdhury/pytorch-template-aws/logs/train/runs/2024-11-08_15-37-45
+    choices:
+      debug: null
+      experiment: catdog_experiment
+      hydra: default
+      paths: catdog
+      trainer: default
+      logger: default
+      callbacks: default
+      model: catdog_classifier
+      data: catdog
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: colorlog
+      hydra/hydra_logging: colorlog
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

logs/train/runs/2024-11-08_15-37-45/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

src/hydra_test.py

@@ -0,0 +1,60 @@
+import hydra
+from omegaconf import DictConfig, OmegaConf
+import rootutils
+from dotenv import load_dotenv, find_dotenv
+
+# Load environment variables
+load_dotenv(find_dotenv(".env"))
+
+# Setup root directory
+root = rootutils.setup_root(__file__, indicator=".project-root", pythonpath=True)
+
+
+# Define separate functions for each sub-configuration
+def print_data(data_cfg: DictConfig):
+    print("Data Configuration:")
+    print(OmegaConf.to_yaml(data_cfg))
+
+
+def print_model(model_cfg: DictConfig):
+    print("Model Configuration:")
+    print(OmegaConf.to_yaml(model_cfg))
+
+
+def print_callbacks(callbacks_cfg: DictConfig):
+    print("Callbacks Configuration:")
+    print(OmegaConf.to_yaml(callbacks_cfg))
+
+
+def print_logger(logger_cfg: DictConfig):
+    print("Logger Configuration:")
+    print(OmegaConf.to_yaml(logger_cfg))
+
+
+def print_trainer(trainer_cfg: DictConfig):
+    print("Trainer Configuration:")
+    print(OmegaConf.to_yaml(trainer_cfg))
+
+
+def print_paths(paths_cfg: DictConfig):
+    print("Paths Configuration:")
+    print(OmegaConf.to_yaml(paths_cfg))
+
+
+@hydra.main(config_path="../configs", config_name="train", version_base="1.1")
+def hydra_test(cfg: DictConfig):
+    # Print the full configuration
+    print("Full Configuration:")
+    print(OmegaConf.to_yaml(cfg))
+
+    # Call each function with the corresponding sub-configuration
+    print_data(cfg.data)
+    print_model(cfg.model)
+    print_callbacks(cfg.callbacks)
+    print_logger(cfg.logger)
+    print_trainer(cfg.trainer)
+    print_paths(cfg.paths)
+
+
+if __name__ == "__main__":
+    hydra_test()

src/hydra_test2.py

@@ -0,0 +1,68 @@
+import hydra
+from omegaconf import DictConfig, OmegaConf
+import rootutils
+from dotenv import load_dotenv, find_dotenv
+
+# Load environment variables
+load_dotenv(find_dotenv(".env"))
+
+# Setup root directory
+root = rootutils.setup_root(__file__, indicator=".project-root", pythonpath=True)
+
+
+# Define a ModelCheckpoint class that takes in parameters as specified in cfg.callbacks.model_checkpoint
+class ModelCheckpoint:
+    def __init__(
+        self,
+        dirpath,
+        filename,
+        monitor,
+        verbose=False,
+        save_last=True,
+        save_top_k=1,
+        mode="max",
+        auto_insert_metric_name=False,
+        save_weights_only=False,
+        every_n_train_steps=None,
+        train_time_interval=None,
+        every_n_epochs=None,
+        save_on_train_epoch_end=None,
+    ):
+        self.dirpath = dirpath
+        self.filename = filename
+        self.monitor = monitor
+        self.verbose = verbose
+        self.save_last = save_last
+        self.save_top_k = save_top_k
+        self.mode = mode
+        self.auto_insert_metric_name = auto_insert_metric_name
+        self.save_weights_only = save_weights_only
+        self.every_n_train_steps = every_n_train_steps
+        self.train_time_interval = train_time_interval
+        self.every_n_epochs = every_n_epochs
+        self.save_on_train_epoch_end = save_on_train_epoch_end
+
+    def display(self):
+        print("Initialized ModelCheckpoint with the following configuration:")
+        for attr, value in self.__dict__.items():
+            print(f"{attr}: {value}")
+
+
+# Define func4 to initialize the ModelCheckpoint class using cfg.callbacks.model_checkpoint
+def func4(**kwargs):
+    # Initialize ModelCheckpoint with the kwargs
+    checkpoint = ModelCheckpoint(**kwargs)
+    checkpoint.display()  # Display the configuration for confirmation
+
+
+@hydra.main(config_path="../configs", config_name="train", version_base="1.1")
+def hydra_test(cfg: DictConfig):
+    # Print the full configuration
+    print("Full Configuration:")
+
+    # Call func4 with the model checkpoint configuration
+    func4(**cfg.callbacks.model_checkpoint)
+
+
+if __name__ == "__main__":
+    hydra_test()

src/models/catdog_model.py

@@ -0,0 +1,119 @@
+import lightning as L
+import torch
+from torch import nn, optim
+from torchmetrics import Accuracy, Precision, Recall, F1Score
+from timm.models import VisionTransformer
+
+
+class ViTTinyClassifier(L.LightningModule):
+    def __init__(
+        self,
+        img_size: int = 224,
+        num_classes: int = 2,
+        embed_dim: int = 64,
+        depth: int = 6,
+        num_heads: int = 2,
+        patch_size: int = 16,
+        mlp_ratio: float = 3.0,
+        pre_norm: bool = False,
+        lr: float = 1e-3,
+        weight_decay: float = 1e-5,
+        factor: float = 0.1,
+        patience: int = 10,
+        min_lr: float = 1e-6,
+    ):
+        super().__init__()
+        self.save_hyperparameters()
+
+        # Create ViT model
+        self.model = VisionTransformer(
+            img_size=img_size,
+            patch_size=patch_size,
+            in_chans=3,
+            num_classes=num_classes,
+            embed_dim=embed_dim,
+            depth=depth,
+            num_heads=num_heads,
+            mlp_ratio=mlp_ratio,
+            qkv_bias=False,
+            pre_norm=pre_norm,
+            global_pool="token",
+        )
+
+        # Metrics for multi-class classification
+        metrics = {
+            "accuracy": Accuracy(task="multiclass", num_classes=num_classes),
+            "precision": Precision(
+                task="multiclass", num_classes=num_classes, average="macro"
+            ),
+            "recall": Recall(
+                task="multiclass", num_classes=num_classes, average="macro"
+            ),
+            "f1": F1Score(task="multiclass", num_classes=num_classes, average="macro"),
+        }
+
+        # Initialize metrics for each stage
+        self.train_metrics = nn.ModuleDict(
+            {name: metric.clone() for name, metric in metrics.items()}
+        )
+        self.val_metrics = nn.ModuleDict(
+            {name: metric.clone() for name, metric in metrics.items()}
+        )
+        self.test_metrics = nn.ModuleDict(
+            {name: metric.clone() for name, metric in metrics.items()}
+        )
+
+        # Loss function
+        self.criterion = nn.CrossEntropyLoss()
+
+    def forward(self, x):
+        return self.model(x)
+
+    def _shared_step(self, batch, stage: str):
+        x, y = batch
+        logits = self(x)
+        loss = self.criterion(logits, y)
+        preds = logits.argmax(dim=1)
+
+        # Get appropriate metric dictionary based on stage
+        metrics = getattr(self, f"{stage}_metrics")
+        metric_logs = {
+            f"{stage}_{name}": metric(preds, y) for name, metric in metrics.items()
+        }
+
+        # Log metrics
+        self.log(f"{stage}_loss", loss, prog_bar=True)
+        self.log_dict(metric_logs, prog_bar=True, on_step=False, on_epoch=True)
+        return loss
+
+    def training_step(self, batch, batch_idx):
+        return self._shared_step(batch, "train")
+
+    def validation_step(self, batch, batch_idx):
+        self._shared_step(batch, "val")
+
+    def test_step(self, batch, batch_idx):
+        self._shared_step(batch, "test")
+
+    def configure_optimizers(self):
+        optimizer = optim.AdamW(
+            self.parameters(),
+            lr=self.hparams.lr,
+            weight_decay=self.hparams.weight_decay,
+        )
+
+        scheduler = optim.lr_scheduler.ReduceLROnPlateau(
+            optimizer,
+            factor=self.hparams.factor,
+            patience=self.hparams.patience,
+            min_lr=self.hparams.min_lr,
+        )
+
+        return {
+            "optimizer": optimizer,
+            "lr_scheduler": {
+                "scheduler": scheduler,
+                "monitor": "val_loss",
+                "interval": "epoch",
+            },
+        }

src/utils/logging_utils.py

@@ -0,0 +1,45 @@
+import sys
+import os
+from pathlib import Path
+from functools import wraps
+
+from loguru import logger
+from rich.progress import Progress, SpinnerColumn, TextColumn
+
+
+def setup_logger(log_file):
+    """Set up the logger with a file and console handler."""
+    os.makedirs(Path(log_file).parent, exist_ok=True)
+    logger.remove()
+    logger.add(
+        sys.stderr,
+        format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> - <level>{message}</level>",
+    )
+    logger.add(log_file, rotation="1MB")
+
+
+def task_wrapper(func):
+    """Wrapper to log the start and end of a task."""
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        func_name = func.__name__
+        logger.info(f"Starting {func_name}")
+        try:
+            result = func(*args, **kwargs)
+            logger.info(f"Finished {func_name}")
+            return result
+        except Exception as e:
+            logger.exception(f"Error in {func_name}: {str(e)}")
+            raise
+
+    return wrapper
+
+
+def get_rich_progress():
+    """Get a Rich Progress object."""
+    return Progress(
+        SpinnerColumn(),
+        TextColumn("[progress.description]{task.description}"),
+        transient=True,
+    )