add experiments for 10 unrolling steps

experiments/10_steps/config_16_layer_16_hidden_adaptive_refined.yaml

@@ -0,0 +1,71 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.adaptive_refined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 15
+        last_patience: 20
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.adaptive_refined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.basic.adaptive_refined"
+    n_elements: 100
+    batch_size: 32
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_adaptive_refined_combined.yaml

@@ -0,0 +1,74 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.adaptive_refined.combined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 15
+        last_patience: 20
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.adaptive_refined.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      - "4_stripes.basic.adaptive_refined"
+      - "3_stripes.basic.adaptive_refined"
+      - "2_stripes.basic.adaptive_refined"
+    n_elements: 100
+    batch_size: 32
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_refined.yaml

@@ -0,0 +1,71 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.refined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 15
+        last_patience: 20
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.basic.refined"
+    n_elements: 100
+    batch_size: 32
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_refined_combined.yaml

@@ -0,0 +1,74 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.refined.combined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 15
+        last_patience: 20
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      - "4_stripes.basic.refined"
+      - "3_stripes.basic.refined"
+      - "2_stripes.basic.refined"
+    n_elements: 100
+    batch_size: 32
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+optimizer: null
+lr_scheduler: null