Fix tf boolean mask in graph mode (#6741)

src/transformers/modeling_tf_utils.py

@@ -137,7 +137,7 @@ class TFCausalLanguageModelingLoss:
         )
         # make sure only labels that are not equal to -100
         # are taken into account as loss
-        active_loss = tf.reshape(labels, (-1,)) != -100
+        active_loss = tf.not_equal(tf.reshape(labels, (-1,)), -100)
         reduced_logits = tf.boolean_mask(tf.reshape(logits, (-1, shape_list(logits)[2])), active_loss)
         labels = tf.boolean_mask(tf.reshape(labels, (-1,)), active_loss)
         return loss_fn(labels, reduced_logits)