update descriptions

axolotl-ai-cloud · Jan 23, 2024 · efe1fb2 · efe1fb2
1 parent 8f04f14
commit efe1fb2
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/src/axolotl/utils/trainer.py b/src/axolotl/utils/trainer.py
@@ -143,23 +143,23 @@ def process_datasets_for_packing(cfg, train_dataset, eval_dataset, tokenizer):
                 add_length,
                 num_proc=cfg.dataset_processes,
                 load_from_cache_file=not cfg.is_preprocess,
-                desc="Packing (Group By Length)",
+                desc="Group By Length",
             )
 
         if cfg.sample_packing:
             train_dataset = train_dataset.map(
                 add_position_ids,
                 num_proc=cfg.dataset_processes,
                 load_from_cache_file=not cfg.is_preprocess,
-                desc="Packing (Sample Packing)",
+                desc="Add position_id column (Sample Packing)",
             )
             if cfg.eval_sample_packing is not False:
                 if eval_dataset:
                     eval_dataset = eval_dataset.map(
                         add_position_ids,
                         num_proc=cfg.dataset_processes,
                         load_from_cache_file=not cfg.is_preprocess,
-                        desc="Packing (Sample Packing)",
+                        desc="Add position_id column (Sample Packing)",
                     )
 
     return train_dataset, eval_dataset
@@ -174,7 +174,7 @@ def process_pretraining_datasets_for_packing(train_dataset, sequence_len):
     )
     train_dataset = train_dataset.map(
         add_position_ids,
-        desc="Packing Pretraining Dataset",
+        desc="Add position_id column (Pretraining Sample Packing)",
     )
     return train_dataset