diff --git a/optimum/intel/neural_compressor/trainer.py b/optimum/intel/neural_compressor/trainer.py
index ded6ac781a..5f1caf2ae5 100644
--- a/optimum/intel/neural_compressor/trainer.py
+++ b/optimum/intel/neural_compressor/trainer.py
@@ -179,7 +179,9 @@ def __init__(
     def _inner_training_loop(
         self, batch_size=None, args=None, resume_from_checkpoint=None, trial=None, ignore_keys_for_eval=None
     ):
+        self.accelerator.free_memory()
         self._train_batch_size = batch_size
+        logger.debug(f"Currently training with a batch size of: {self._train_batch_size}")
         # Data loader and number of training steps
         train_dataloader = self.get_train_dataloader()
 
@@ -190,6 +192,7 @@ def _inner_training_loop(
         total_train_batch_size = self._train_batch_size * args.gradient_accumulation_steps * args.world_size
 
         len_dataloader = None
+        num_train_tokens = None
         if has_length(train_dataloader):
             len_dataloader = len(train_dataloader)
             num_update_steps_per_epoch = len_dataloader // args.gradient_accumulation_steps