[bugfix]: validate GenRL prompt sampler dataset size

Author: Davids048

fastvideo/train/methods/rl/utils/data.py

@@ -149,7 +149,7 @@ def __init__(
     ):
         self.dataset = dataset
         self.batch_size = batch_size
-        self.k = k
+        self.k = k  # Repeats/videos per prompt.
         self.num_replicas = num_replicas
         self.rank = rank
         self.seed = seed
@@ -165,7 +165,13 @@ def __init__(
             f"num_replicas={num_replicas} "
             f"batch_size={batch_size}"
         )
-        self.m = self.total_samples // self.k
+        self.m = self.total_samples // self.k  # Unique prompts across ranks.
+        if len(self.dataset) < self.m:
+            raise ValueError(
+                "dataset must contain at least one prompt per global "
+                "prompt group. Got "
+                f"dataset_size={len(self.dataset)}, required={self.m}."
+            )
         self.groups_per_rank = self.batch_size // self.k
         self.epoch = 0