Fix trainer dataloader slow loading issue (#3219)
* Fix trainer dataloader handling in src/axolotl/core/trainers/base.py * update comment to reflect torch version --------- Co-authored-by: Wing Lian <wing.lian@gmail.com>
This commit is contained in:
@@ -225,17 +225,6 @@ class AxolotlTrainer(
|
||||
|
||||
data_collator = self.data_collator if is_training else self.eval_data_collator
|
||||
|
||||
if dataset.column_names and "length" in dataset.column_names:
|
||||
dataset = dataset.remove_columns(["length"])
|
||||
if (
|
||||
dataset.column_names
|
||||
and "position_ids" in dataset.column_names
|
||||
and "attention_mask" in dataset.column_names
|
||||
and self.args.sample_packing
|
||||
and self.args.sample_packing_drop_attention_mask
|
||||
):
|
||||
dataset = dataset.remove_columns(["attention_mask"])
|
||||
|
||||
if isinstance(dataset, datasets.Dataset):
|
||||
if is_training:
|
||||
if not self.args.sample_packing or self.args.pretraining:
|
||||
@@ -294,6 +283,18 @@ class AxolotlTrainer(
|
||||
):
|
||||
self.accelerator.even_batches = False
|
||||
|
||||
if dataset.column_names and "length" in dataset.column_names:
|
||||
dataset = dataset.remove_columns(["length"])
|
||||
|
||||
if (
|
||||
dataset.column_names
|
||||
and "position_ids" in dataset.column_names
|
||||
and "attention_mask" in dataset.column_names
|
||||
and self.args.sample_packing
|
||||
and self.args.sample_packing_drop_attention_mask
|
||||
):
|
||||
dataset = dataset.remove_columns(["attention_mask"])
|
||||
|
||||
dataloader = DataLoader(dataset, **dataloader_params)
|
||||
|
||||
# Accelerator.free_memory() will destroy the references, so
|
||||
|
||||
Reference in New Issue
Block a user