kernel-elastic-autoencoder 3.3.2__tar.gz → 3.3.3__tar.gz

{kernel_elastic_autoencoder-3.3.2 → kernel_elastic_autoencoder-3.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kernel_elastic_autoencoder
-Version: 3.3.2
+Version: 3.3.3
 Summary: Implementation of Kernel-Elastic Autoencoder for Molecular Design (https://doi.org/10.1093/pnasnexus/pgae168)
 License: MIT
 Author: Felix Rotter-McCartney

{kernel_elastic_autoencoder-3.3.2 → kernel_elastic_autoencoder-3.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kernel_elastic_autoencoder"
-version = "3.3.2"
+version = "3.3.3"
 description = "Implementation of Kernel-Elastic Autoencoder for Molecular Design (https://doi.org/10.1093/pnasnexus/pgae168)"
 authors = [
     { name = "Felix Rotter-McCartney", email = "felix.rotter@mail.utoronto.ca" }

{kernel_elastic_autoencoder-3.3.2 → kernel_elastic_autoencoder-3.3.3}/src/kernel_elastic_autoencoder/training.py

@@ -94,13 +94,13 @@ class Trainer:
             dataset_train,
             batch_size=self.config_typed.common.batch_size,
             pin_memory=True,
-            num_workers=4,
+            num_workers=0,
         )
         dataloader_test = torch.utils.data.DataLoader(
             dataset_test,
             batch_size=self.config_typed.common.batch_size,
             pin_memory=True,
-            num_workers=4,
+            num_workers=0,
         )
         curr_epoch = 0
 
@@ -136,7 +136,7 @@ class Trainer:
                 )
                 accelerator.backward(loss)
                 optimizer.step()
-                torch.cat([train_loss, loss.detach().unsqueeze(-1)], dim=0)
+                train_loss = torch.cat([train_loss, loss.detach().unsqueeze(-1)], dim=0)
             accelerator.print(f"Avg. train loss: {train_loss.mean().item()}")
 
             model.eval()
@@ -154,7 +154,7 @@ class Trainer:
                     loss = loss_fn(
                         prediction, prediction_noise, input_ids[:, 1:], latents_noise
                     )
-                    torch.cat([test_loss, loss.detach().unsqueeze(-1)], dim=0)
+                    test_loss = torch.cat([test_loss, loss.detach().unsqueeze(-1)], dim=0)
             accelerator.print(f"Avg. test loss: {test_loss.mean().item()}")
 
             scheduler.step()