chore(debug): print tensor devices and CUDA availability for troubleshooting

train_abuse_model.py

@@ -8,6 +8,8 @@ import numpy as np
 import torch
 from torch.utils.data import Dataset
 
+print("torch.cuda.is_available():", torch.cuda.is_available())
+print("Using device:", device)
 print("PyTorch version:", torch.__version__)
 
 from sklearn.model_selection import train_test_split
@@ -46,7 +48,10 @@ class AbuseDataset(Dataset):
         item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
         item["labels"] = torch.tensor(self.labels[idx], dtype=torch.float)
         return item
-
+    def __getitem__(self, idx):
+        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
+        item["labels"] = torch.tensor(self.labels[idx], dtype=torch.float)
+        return item
 
 
 #  Convert label values to soft scores: "yes" = 1.0, "plausibly" = 0.5, others = 0.0
@@ -226,6 +231,12 @@ trainer = Trainer(
     eval_dataset=val_dataset
 )
 
+# This checks if any tensor is on GPU too early.
+print("🧪 Sample device check from train_dataset:")
+sample = train_dataset[0]
+for k, v in sample.items():
+    print(f"{k}: {v.device}")
+
 # Start training!
 trainer.train()