make sure the chunk size is an int

This commit is contained in:
Wing Lian
2023-08-03 00:27:33 -04:00
parent 98c9bc69de
commit 7e1edc662a

View File

@@ -183,7 +183,7 @@ class MultipackDistributedDataloader:
all_batches, _ = self.generate_batches(set_stats=True)
features = self.dataset.features.keys()
len_remaining = self._len_est()
for batches in chunk(all_batches, self.batch_size / self.seq_len_multiple):
for batches in chunk(all_batches, self.batch_size // self.seq_len_multiple):
chunked_data = []
attn_mask_cum_idx = 0
for batch in batches: