added: hyra config copied from template

.gitignore

@@ -20,4 +20,4 @@ app/core/__pycache__/
 src/__pycache__/test_infra.cpython-310.pyc
 app/core/__pycache__/config.cpython-310.pyc
 data/
-/data
+!configs/data/

configs/callbacks/default.yaml

@@ -0,0 +1,21 @@
+defaults:
+  - model_checkpoint
+  - early_stopping
+  - model_summary
+  - rich_progress_bar
+  - _self_
+
+model_checkpoint:
+  dirpath: ${paths.ckpt_dir}
+  monitor: "val_loss"
+  mode: "min"
+  save_last: False
+  auto_insert_metric_name: False
+
+early_stopping:
+  monitor: "val_loss"
+  patience: 3
+  mode: "min"
+
+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: 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
+  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/model_checkpoint.yaml

@@ -0,0 +1,17 @@
+# 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
+  verbose: False # 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: "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

configs/callbacks/model_summary.yaml

@@ -0,0 +1,3 @@
+model_summary:
+  _target_: lightning.pytorch.callbacks.RichModelSummary
+  max_depth: 2

configs/callbacks/rich_progress_bar.yaml

@@ -0,0 +1,2 @@
+rich_progress_bar:
+  _target_: lightning.pytorch.callbacks.RichProgressBar

configs/data/catdog.yaml

@@ -0,0 +1,10 @@
+_target_: src.datamodules.catdog_datamodule.CatDogImageDataModule
+
+data_dir: ${paths.data_dir}
+url: ${paths.data_url}
+num_workers: 4
+batch_size: 32
+train_val_split: [0.8, 0.2]
+pin_memory: False
+image_size: 160
+dataset_url: "https://download.pytorch.org/tutorials/cats_and_dogs_filtered.zip"

configs/experiment/catdog_experiment.yaml

@@ -0,0 +1,53 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=catdog_ex
+
+defaults:
+  - override /paths: catdog
+  - override /data: catdog
+  - override /model: catdog_classifier
+  - override /callbacks: default
+  - override /logger: default
+  - override /trainer: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+seed: 42
+name: "catdog_experiment"
+
+data:
+  batch_size: 64
+  num_workers: 8
+  pin_memory: True
+  image_size: 160
+
+model:
+  lr: 1e-3
+  weight_decay: 1e-5
+  factor: 0.1
+  patience: 10
+  min_lr: 1e-6
+  num_classes: 2
+  patch_size: 16
+  embed_dim: 64
+  depth: 6
+  num_heads: 2
+  mlp_ratio: 3
+
+trainer:
+  min_epochs: 1
+  max_epochs: 6
+
+callbacks:
+  model_checkpoint:
+    monitor: "val_acc"
+    mode: "max"
+    save_top_k: 1
+    save_last: True
+
+  early_stopping:
+    monitor: "val_acc"
+    patience: 10
+    mode: "max"

configs/experiment/catdog_experiment_convnext.yaml

@@ -0,0 +1,60 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=catdog_ex
+
+defaults:
+  - override /paths: catdog
+  - override /data: catdog
+  - override /model: catdog_classifier_convnext
+  - override /callbacks: default
+  - override /logger: default
+  - override /trainer: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+seed: 42
+name: "catdog_experiment_convnext"
+
+# Logger-specific configurations
+logger:
+  aim:
+    experiment: ${name}
+  mlflow:
+    experiment_name: ${name}
+    tags:
+      model_type: "timm_classify"
+
+data:
+  batch_size: 64
+  num_workers: 8
+  pin_memory: True
+  image_size: 160
+
+model:
+  base_model: convnext_tiny.fb_in22k_ft_in1k
+  pretrained: True
+  lr: 1e-3
+  weight_decay: 1e-5
+  factor: 0.1
+  patience: 5
+  min_lr: 1e-6
+  num_classes: 2
+  kernel_sizes: 7
+
+trainer:
+  min_epochs: 1
+  max_epochs: 3
+
+callbacks:
+  model_checkpoint:
+    monitor: "val_acc"
+    mode: "max"
+    save_top_k: 1
+    save_last: True
+
+  early_stopping:
+    monitor: "val_acc"
+    patience: 3
+    mode: "max"

configs/hydra/default.yaml

@@ -0,0 +1,19 @@
+# https://hydra.cc/docs/configure_hydra/intro/
+
+# enable color logging
+defaults:
+  - override hydra_logging: colorlog
+  - override job_logging: colorlog
+
+# output directory, generated dynamically on each run
+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}
+
+job_logging:
+  handlers:
+    file:
+      # Incorporates fix from https://github.com/facebookresearch/hydra/pull/2242
+      filename: ${hydra.runtime.output_dir}/${task_name}.log

configs/infer.yaml

@@ -0,0 +1,42 @@
+# @package _global_
+
+# specify here default configuration
+# order of defaults determines the order in which configs override each other
+defaults:
+  - _self_
+  - data: dogbreed
+  - model: dogbreed_classifier
+  - callbacks: default
+  - logger: null # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - trainer: default
+  - paths: dogbreed
+  - hydra: default
+  # experiment configs allow for version control of specific hyperparameters
+  # e.g. best hyperparameters for given model and datamodule
+  - experiment: dogbreed_experiment
+  # debugging config (enable through command line, e.g. `python train.py debug=default)
+  - debug: null
+
+# task name, determines output directory path
+task_name: "infer"
+
+# tags to help you identify your experiments
+# you can overwrite this in experiment configs
+# overwrite from command line with `python train.py tags="[first_tag, second_tag]"`
+tags: ["dev"]
+
+# set False to skip model training
+train: False
+
+# evaluate on test set, using best model weights achieved during training
+# lightning chooses best weights based on the metric specified in checkpoint callback
+test: False
+
+# simply provide checkpoint path to resume training
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+
+# seed for random number generators in pytorch, numpy and python.random
+seed: 42
+
+# name of the experiment
+name: "dogbreed_experiment"

configs/logger/aim.yaml

@@ -0,0 +1,6 @@
+aim:
+  __target__: aim.pytorch_lightning.AimLogger
+  experiment: ${name}
+  train_metric_prefix: train_
+  test_metric_prefix: test_
+  val_metric_prefix: val_

configs/logger/csv.yaml

@@ -0,0 +1,7 @@
+# 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

@@ -0,0 +1,7 @@
+# train with many loggers at once
+
+defaults:
+  - csv
+  - tensorboard
+  - aim
+  - mlflow

configs/logger/mlflow.yaml

@@ -0,0 +1,9 @@
+# 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
+  log_model: False
+  prefix: ""

configs/logger/tensorboard.yaml

@@ -0,0 +1,10 @@
+# https://www.tensorflow.org/tensorboard/
+
+tensorboard:
+  _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
+  save_dir: "${paths.output_dir}/tensorboard/"
+  name: null
+  log_graph: False
+  default_hp_metric: True
+  prefix: ""
+  # version: ""

configs/model/catdog_classifier.yaml

@@ -0,0 +1,21 @@
+
+_target_: src.models.catdog_classifier.ViTTinyClassifier
+
+# model params
+img_size: 160
+patch_size: 16
+num_classes: 2
+embed_dim: 64
+depth: 6
+num_heads: 2
+mlp_ratio: 3.0
+pre_norm: False
+
+# optimizer params
+lr: 1e-3
+weight_decay: 1e-5
+
+# scheduler params
+factor: 0.1
+patience: 10
+min_lr: 1e-6

configs/model/catdog_classifier_convnext.yaml

@@ -0,0 +1,16 @@
+
+_target_: src.models.catdog_classifier_convnext.ConvNextClassifier
+
+# model params
+base_model: convnext_tiny.in12k_ft_in1k
+pretrained: True
+num_classes: 2
+kernel_sizes: 7
+# optimizer params
+lr: 1e-3
+weight_decay: 1e-5
+
+# scheduler params
+factor: 0.1
+patience: 10
+min_lr: 1e-6

configs/paths/catdog.yaml

@@ -0,0 +1,27 @@
+# path to root directory
+# this requires PROJECT_ROOT environment variable to exist
+# you can replace it with "." if you want the root to be the current working directory
+root_dir: ${oc.env:PROJECT_ROOT}
+
+# path to data directory
+data_dir: ${paths.root_dir}/data/
+
+# path to logging directory
+log_dir: ${paths.root_dir}/logs/
+
+# path to checkpoint directory
+ckpt_dir: ${paths.root_dir}/checkpoints
+
+# path to artifact directory
+artifact_dir: ${paths.root_dir}/artifacts/
+
+# download url for the dataset
+data_url: "https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip"
+
+# path to output directory, created dynamically by hydra
+# path generation pattern is specified in `configs/hydra/default.yaml`
+# use it to store all files generated during the run, like ckpts and metrics
+output_dir: ${hydra:runtime.output_dir}
+
+# path to working directory
+work_dir: ${hydra:runtime.cwd}

configs/test.yaml

@@ -0,0 +1,34 @@
+defaults:
+  - _self_
+  - data: dogbreed
+  - model: dogbreed_classifier
+  - callbacks: default
+  - logger: null
+  - trainer: default
+  - paths: default  # This should map to another config file if using hydra to merge
+
+task_name: train
+tags:
+  - dev
+train: true
+test: true
+ckpt_path: null
+seed: 42
+
+# Ensure paths section is present
+paths:
+  root_dir: ./  # Project root directory
+  data_dir: ./data  # Path to your dataset
+  log_dir: ./logs  # Path to logs directory
+  ckpt_dir: ./checkpoints  # Path to checkpoints
+  artifact_dir: ./artifacts  # Path to save artifacts
+  kaggle_dir: khushikhushikhushi/dog-breed-image-dataset  # Path for Kaggle dataset
+
+# Ensure data section is present
+data:
+  num_workers: 4
+  batch_size: 32
+  image_size: 224
+  train_split: 0.8
+  val_split: 0.1
+  test_split: 0.1

configs/train.yaml

@@ -0,0 +1,41 @@
+# @package _global_
+
+# specify here default configuration
+# order of defaults determines the order in which configs override each other
+defaults:
+  - _self_
+  - data: catdog
+  - model: catdog_classifier
+  - callbacks: default
+  - logger: null # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - trainer: default
+  - paths: catdog
+  - hydra: default
+
+  - experiment: catdog_experiment
+  # debugging config (enable through command line, e.g. `python train.py debug=default)
+  - debug: null
+
+# task name, determines output directory path
+task_name: "train"
+
+# tags to help you identify your experiments
+# you can overwrite this in experiment configs
+# overwrite from command line with `python train.py tags="[first_tag, second_tag]"`
+tags: ["dev"]
+
+# set False to skip model training
+train: True
+
+# evaluate on test set, using best model weights achieved during training
+# lightning chooses best weights based on the metric specified in checkpoint callback
+test: False
+
+# simply provide checkpoint path to resume training
+ckpt_path: ${paths.ckpt_dir}/best-checkpoint.ckpt
+
+# seed for random number generators in pytorch, numpy and python.random
+seed: 42
+
+# name of the experiment
+name: "dogbreed_experiment"

configs/trainer/default.yaml

@@ -0,0 +1,19 @@
+_target_: lightning.Trainer
+
+default_root_dir: ${paths.output_dir}
+min_epochs: 1
+max_epochs: 6
+
+accelerator: auto
+devices: auto
+
+# mixed precision for extra speed-up
+# precision: 16
+
+# set True to to ensure deterministic results
+# makes training slower but gives more reproducibility than just setting seeds
+deterministic: True
+
+# Log every N steps in training and validation
+log_every_n_steps: 10
+fast_dev_run: False

logs/train/runs/2024-11-08_14-29-05/.hydra/config.yaml

@@ -0,0 +1,112 @@
+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
+  splits:
+  - 0.8
+  - 0.2
+  pin_memory: true
+  image_size: 160
+model:
+  _target_: src.models.catdog_classifier.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:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    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:
+    _target_: lightning.pytorch.callbacks.EarlyStopping
+    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:
+    _target_: lightning.pytorch.callbacks.RichModelSummary
+    max_depth: -1
+  rich_progress_bar:
+    _target_: lightning.pytorch.callbacks.RichProgressBar
+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}
+  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_14-29-05/.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: catdog_datamodule
+    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: '1.3'
+    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_14-29-05
+    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_14-29-05/.hydra/overrides.yaml

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

logs/train/runs/2024-11-08_14-32-38/.hydra/config.yaml

@@ -0,0 +1,113 @@
+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_classifier.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:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    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:
+    _target_: lightning.pytorch.callbacks.EarlyStopping
+    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:
+    _target_: lightning.pytorch.callbacks.RichModelSummary
+    max_depth: -1
+  rich_progress_bar:
+    _target_: lightning.pytorch.callbacks.RichProgressBar
+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}
+  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_14-32-38/.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: catdog_datamodule
+    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: '1.3'
+    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_14-32-38
+    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_14-32-38/.hydra/overrides.yaml

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