add experiments

experiments/5_steps/config_16_layer_16_hidden_refined.yaml

@@ -10,8 +10,8 @@ trainer:
     - class_path: lightning.pytorch.loggers.WandbLogger
       init_args:
         save_dir: logs.autoregressive.wandb
-        project: "thermal-conduction-unsteady"
-        name: "16_refined"
+        project: "thermal-conduction-unsteady-5.steps"
+        name: "16_layer_16_hidden"
   callbacks:
     - class_path: lightning.pytorch.callbacks.ModelCheckpoint
       init_args:
@@ -24,16 +24,24 @@ trainer:
       init_args:
         monitor: val/loss
         mode: min
-        patience: 10
+        patience: 30
         verbose: false
+    # - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+    #   init_args:
+    #     increase_unrolling_steps_by: 5
+    #     patience: 10
+    #     last_patience: 15
+    #     max_unrolling_steps: 20
+    #     ckpt_path: logs.autoregressive.wandb/16_16_refined/checkpoints
   max_epochs: 1000
   min_epochs: null
   max_steps: -1
   min_steps: null
   overfit_batches: 0.0
-  log_every_n_steps: null
-  accumulate_grad_batches: 4
+  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
@@ -50,13 +58,14 @@ data:
   class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
   init_args:
     hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 8
+    split_name: "easy.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
-    start_unrolling_steps: 5
+    unrolling_steps: 5
 optimizer: null
 lr_scheduler: null

experiments/5_steps/config_32_layer_16_hidden_refined.yaml

@@ -10,12 +10,12 @@ trainer:
     - class_path: lightning.pytorch.loggers.WandbLogger
       init_args:
         save_dir: logs.autoregressive.wandb
-        project: "thermal-conduction-unsteady"
-        name: "standard"
+        project: "thermal-conduction-unsteady-5.steps"
+        name: "32_layer_16_hidden"
   callbacks:
     - class_path: lightning.pytorch.callbacks.ModelCheckpoint
       init_args:
-        dirpath: logs.autoregressive.wandb/standard/checkpoints
+        dirpath: logs.autoregressive.wandb/32_refined/checkpoints
         monitor: val/loss
         mode: min
         save_top_k: 1
@@ -24,16 +24,24 @@ trainer:
       init_args:
         monitor: val/loss
         mode: min
-        patience: 10
+        patience: 30
         verbose: false
+    # - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+    #   init_args:
+    #     increase_unrolling_steps_by: 5
+    #     patience: 10
+    #     last_patience: 15
+    #     max_unrolling_steps: 20
+    #     ckpt_path: logs.autoregressive.wandb/16_16_refined/checkpoints
   max_epochs: 1000
   min_epochs: null
   max_steps: -1
   min_steps: null
   overfit_batches: 0.0
-  log_every_n_steps: null
+  log_every_n_steps: 0
   accumulate_grad_batches: 2
   default_root_dir: null
+  gradient_clip_val: 1.0
 
 model: 
   class_path: ThermalSolver.autoregressive_module.GraphSolver
@@ -43,20 +51,21 @@ model:
       input_dim: 1
       hidden_dim: 16
       output_dim: 1
-      n_layers: 8
+      n_layers: 32
     unrolling_steps: 5
     
 data: 
   class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
   init_args:
     hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy"
+    split_name: "easy.refined"
+    n_elements: 100
     batch_size: 16
     train_size: 0.7
     val_size: 0.2
     test_size: 0.1
     build_radial_graph: false
     remove_boundary_edges: true
-    start_unrolling_steps: 5
+    unrolling_steps: 5
 optimizer: null
 lr_scheduler: null

experiments/5_steps/config_8_layer_16_hidden_refined.yaml

@@ -10,12 +10,12 @@ trainer:
     - class_path: lightning.pytorch.loggers.WandbLogger
       init_args:
         save_dir: logs.autoregressive.wandb
-        project: "thermal-conduction-unsteady"
-        name: "refined"
+        project: "thermal-conduction-unsteady-5.steps"
+        name: "8_layer_16_hidden"
   callbacks:
     - class_path: lightning.pytorch.callbacks.ModelCheckpoint
       init_args:
-        dirpath: logs.autoregressive.wandb/refined/checkpoints
+        dirpath: logs.autoregressive.wandb/8_refined/checkpoints
         monitor: val/loss
         mode: min
         save_top_k: 1
@@ -24,7 +24,7 @@ trainer:
       init_args:
         monitor: val/loss
         mode: min
-        patience: 10
+        patience: 20
         verbose: false
   max_epochs: 1000
   min_epochs: null
@@ -32,7 +32,7 @@ trainer:
   min_steps: null
   overfit_batches: 0.0
   log_every_n_steps: null
-  accumulate_grad_batches: 2
+  accumulate_grad_batches: 1
   default_root_dir: null
 
 model: 
@@ -50,13 +50,14 @@ data:
   class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
   init_args:
     hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 16
+    split_name: "easy.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
-    start_unrolling_steps: 5
+    unrolling_steps: 5
 optimizer: null
 lr_scheduler: null

experiments/config_16_layer_8_hidden_refined.yaml

@@ -1,62 +0,0 @@
-# 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"
-        name: "16_8_refined"
-  callbacks:
-    - class_path: lightning.pytorch.callbacks.ModelCheckpoint
-      init_args:
-        dirpath: logs.autoregressive.wandb/16_8_refined/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: 10
-        verbose: false
-  max_epochs: 1000
-  min_epochs: null
-  max_steps: -1
-  min_steps: null
-  overfit_batches: 0.0
-  log_every_n_steps: null
-  accumulate_grad_batches: 2
-  default_root_dir: null
-
-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: 8
-      output_dim: 1
-      n_layers: 16
-    unrolling_steps: 5
-
-data: 
-  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
-  init_args:
-    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 16
-    train_size: 0.7
-    val_size: 0.2
-    test_size: 0.1
-    build_radial_graph: false
-    remove_boundary_edges: true
-    start_unrolling_steps: 5
-optimizer: null
-lr_scheduler: null

experiments/config_4_layer_16_hidden.yaml

@@ -1,64 +0,0 @@
-# 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/wandb
-        project: "thermal-conduction-unsteady"
-        name: "5_step_4_layers_16_hidden"
-        #        retain: true
-  callbacks:
-    - class_path: lightning.pytorch.callbacks.ModelCheckpoint
-      init_args:
-        dirpath: logs.autoregressive.wandb/5_step_4_layers_16_hidden/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: 10
-        verbose: false
-  max_epochs: 1000
-  min_epochs: null
-  max_steps: -1
-  min_steps: null
-  overfit_batches: 0.0
-  log_every_n_steps: null
-  accumulate_grad_batches: 2
-  default_root_dir: null
-
-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: 4
-    unrolling_steps: 5
-
-data: 
-  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
-  init_args:
-    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 32
-    train_size: 0.7
-    val_size: 0.2
-    test_size: 0.1
-    build_radial_graph: true
-    radius: 0.5
-    remove_boundary_edges: true
-    start_unrolling_steps: 5
-optimizer: null
-lr_scheduler: null

experiments/config_4_layer_8_hidden.yaml

@@ -1,62 +0,0 @@
-# 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"
-        name: "5_step_4_layers_8_hidden"
-  callbacks:
-    - class_path: lightning.pytorch.callbacks.ModelCheckpoint
-      init_args:
-        dirpath: logs.autoregressive.wandb/5_step_4_layers_8_hidden_0.7_radius/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: 10
-        verbose: false
-  max_epochs: 1000
-  min_epochs: null
-  max_steps: -1
-  min_steps: null
-  overfit_batches: 0.0
-  log_every_n_steps: null
-  accumulate_grad_batches: 1
-  default_root_dir: null
-
-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: 8
-      output_dim: 1
-      n_layers: 4
-    unrolling_steps: 5
-
-data: 
-  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
-  init_args:
-    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 32
-    train_size: 0.7
-    val_size: 0.2
-    test_size: 0.1
-    build_radial_graph: false
-    remove_boundary_edges: true
-    start_unrolling_steps: 5
-optimizer: null
-lr_scheduler: null

experiments/config_8_layer_8_hidden.yaml

@@ -1,62 +0,0 @@
-# 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"
-        name: "standard"
-  callbacks:
-    - class_path: lightning.pytorch.callbacks.ModelCheckpoint
-      init_args:
-        dirpath: logs.autoregressive.wandb/standard/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: 10
-        verbose: false
-  max_epochs: 1000
-  min_epochs: null
-  max_steps: -1
-  min_steps: null
-  overfit_batches: 0.0
-  log_every_n_steps: null
-  accumulate_grad_batches: 1
-  default_root_dir: null
-
-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: 8
-      output_dim: 1
-      n_layers: 8
-    unrolling_steps: 5
-
-data: 
-  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
-  init_args:
-    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
-    split_name: "100_samples_easy_refined"
-    batch_size: 32
-    train_size: 0.7
-    val_size: 0.2
-    test_size: 0.1
-    build_radial_graph: false
-    remove_boundary_edges: true
-    start_unrolling_steps: 5
-optimizer: null
-lr_scheduler: null