Merge branch 'master' of github.com:huggingface/transformers

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -367,6 +367,8 @@ def preprocess_function(examples):
     # Get the metric function
     if args.task_name is not None:
         metric = load_metric("glue", args.task_name)
+    else:
+        metric = load_metric("accuracy")
 
     # Train!
     total_batch_size = args.per_device_train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps

src/transformers/models/bart/modeling_bart.py

@@ -296,7 +296,7 @@ def forward(
             attention_mask (:obj:`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (:obj:`torch.FloatTensor`): mask for attention heads in a given layer of size
-                `(config.encoder_attention_heads,)`.
+                `(encoder_attention_heads,)`.
             output_attentions (:obj:`bool`, `optional`):
                 Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under
                 returned tensors for more detail.
@@ -368,7 +368,7 @@ def forward(
         encoder_hidden_states: Optional[torch.Tensor] = None,
         encoder_attention_mask: Optional[torch.Tensor] = None,
         layer_head_mask: Optional[torch.Tensor] = None,
-        encoder_layer_head_mask: Optional[torch.Tensor] = None,
+        cross_attn_layer_head_mask: Optional[torch.Tensor] = None,
         past_key_value: Optional[Tuple[torch.Tensor]] = None,
         output_attentions: Optional[bool] = False,
         use_cache: Optional[bool] = True,
@@ -382,9 +382,9 @@ def forward(
             encoder_attention_mask (:obj:`torch.FloatTensor`): encoder attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (:obj:`torch.FloatTensor`): mask for attention heads in a given layer of size
-                `(config.encoder_attention_heads,)`.
-            encoder_layer_head_mask (:obj:`torch.FloatTensor`): mask for encoder attention heads in a given layer of
-                size `(config.encoder_attention_heads,)`.
+                `(encoder_attention_heads,)`.
+            cross_attn_layer_head_mask (:obj:`torch.FloatTensor`): mask for cross-attention heads in a given layer of
+                size `(decoder_attention_heads,)`.
             past_key_value (:obj:`Tuple(torch.FloatTensor)`): cached past key and value projection states
             output_attentions (:obj:`bool`, `optional`):
                 Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under
@@ -419,7 +419,7 @@ def forward(
                 hidden_states=hidden_states,
                 key_value_states=encoder_hidden_states,
                 attention_mask=encoder_attention_mask,
-                layer_head_mask=encoder_layer_head_mask,
+                layer_head_mask=cross_attn_layer_head_mask,
                 past_key_value=cross_attn_past_key_value,
                 output_attentions=output_attentions,
             )
@@ -598,18 +598,25 @@ def __init_subclass__(self):
             If you want to change padding behavior, you should read :func:`modeling_bart._prepare_decoder_inputs` and
             modify to your needs. See diagram 1 in `the paper <https://arxiv.org/abs/1910.13461>`__ for more
             information on the default strategy.
-        head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
+        head_mask (:obj:`torch.Tensor` of shape :obj:`(encoder_layers, encoder_attention_heads)`, `optional`):
             Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in ``[0, 1]``:
 
             - 1 indicates the head is **not masked**,
-            - 0 indicates the heas is **masked**.
+            - 0 indicates the head is **masked**.
 
-        decoder_head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
+        decoder_head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
             Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in ``[0, 1]``:
 
             - 1 indicates the head is **not masked**,
             - 0 indicates the head is **masked**.
 
+        cross_attn_head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
+            Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in ``[0,
+            1]``:
+
+            - 1 indicates the head is **not masked**,
+            - 0 indicates the head is **masked**.
+
         encoder_outputs (:obj:`tuple(tuple(torch.FloatTensor)`, `optional`):
             Tuple consists of (:obj:`last_hidden_state`, `optional`: :obj:`hidden_states`, `optional`:
             :obj:`attentions`) :obj:`last_hidden_state` of shape :obj:`(batch_size, sequence_length, hidden_size)`,
@@ -710,11 +717,11 @@ def forward(
                 - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
-            head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
+            head_mask (:obj:`torch.Tensor` of shape :obj:`(encoder_layers, encoder_attention_heads)`, `optional`):
                 Mask to nullify selected heads of the attention modules. Mask values selected in ``[0, 1]``:
 
                 - 1 indicates the head is **not masked**,
-                - 0 indicates the heas is **masked**.
+                - 0 indicates the head is **masked**.
 
             inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
                 Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded
@@ -875,7 +882,7 @@ def forward(
         encoder_hidden_states=None,
         encoder_attention_mask=None,
         head_mask=None,
-        encoder_head_mask=None,
+        cross_attn_head_mask=None,
         past_key_values=None,
         inputs_embeds=None,
         use_cache=None,
@@ -912,18 +919,18 @@ def forward(
                 - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
-            head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
+            head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
                 Mask to nullify selected heads of the attention modules. Mask values selected in ``[0, 1]``:
 
                 - 1 indicates the head is **not masked**,
-                - 0 indicates the heas is **masked**.
+                - 0 indicates the head is **masked**.
 
-            encoder_head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
-                Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention
-                on hidden heads. Mask values selected in ``[0, 1]``:
+            cross_attn_head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
+                Mask to nullify selected heads of the cross-attention modules in the decoder to avoid performing
+                cross-attention on hidden heads. Mask values selected in ``[0, 1]``:
 
                 - 1 indicates the head is **not masked**,
-                - 0 indicates the heas is **masked**.
+                - 0 indicates the head is **masked**.
 
             past_key_values (:obj:`Tuple[Tuple[torch.Tensor]]` of length :obj:`config.n_layers` with each tuple having 2 tuples each of which has 2 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
                 Contains precomputed key and value hidden-states of the attention blocks. Can be used to speed up
@@ -993,11 +1000,12 @@ def forward(
         all_cross_attentions = () if (output_attentions and encoder_hidden_states is not None) else None
         next_decoder_cache = () if use_cache else None
 
-        # check if head_mask has a correct number of layers specified if desired
-        if head_mask is not None:
-            assert head_mask.size()[0] == (
-                len(self.layers)
-            ), f"The head_mask should be specified for {len(self.layers)} layers, but it is for {head_mask.size()[0]}."
+        # check if head_mask/cross_attn_head_mask has a correct number of layers specified if desired
+        for attn_mask, mask_name in zip([head_mask, cross_attn_head_mask], ["head_mask", "cross_attn_head_mask"]):
+            if attn_mask is not None:
+                assert attn_mask.size()[0] == (
+                    len(self.layers)
+                ), f"The `{mask_name}` should be specified for {len(self.layers)} layers, but it is for {head_mask.size()[0]}."
         for idx, decoder_layer in enumerate(self.layers):
             # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
             if output_hidden_states:
@@ -1031,7 +1039,7 @@ def custom_forward(*inputs):
                     encoder_hidden_states,
                     encoder_attention_mask,
                     head_mask[idx] if head_mask is not None else None,
-                    encoder_head_mask[idx] if encoder_head_mask is not None else None,
+                    cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None,
                     None,
                 )
             else:
@@ -1042,7 +1050,9 @@ def custom_forward(*inputs):
                     encoder_hidden_states=encoder_hidden_states,
                     encoder_attention_mask=encoder_attention_mask,
                     layer_head_mask=(head_mask[idx] if head_mask is not None else None),
-                    encoder_layer_head_mask=(encoder_head_mask[idx] if encoder_head_mask is not None else None),
+                    cross_attn_layer_head_mask=(
+                        cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None
+                    ),
                     past_key_value=past_key_value,
                     output_attentions=output_attentions,
                     use_cache=use_cache,
@@ -1123,6 +1133,7 @@ def forward(
         decoder_attention_mask=None,
         head_mask=None,
         decoder_head_mask=None,
+        cross_attn_head_mask=None,
         encoder_outputs=None,
         past_key_values=None,
         inputs_embeds=None,
@@ -1172,7 +1183,7 @@ def forward(
             encoder_hidden_states=encoder_outputs[0],
             encoder_attention_mask=attention_mask,
             head_mask=decoder_head_mask,
-            encoder_head_mask=head_mask,
+            cross_attn_head_mask=cross_attn_head_mask,
             past_key_values=past_key_values,
             inputs_embeds=decoder_inputs_embeds,
             use_cache=use_cache,
@@ -1248,6 +1259,7 @@ def forward(
         decoder_attention_mask=None,
         head_mask=None,
         decoder_head_mask=None,
+        cross_attn_head_mask=None,
         encoder_outputs=None,
         past_key_values=None,
         inputs_embeds=None,
@@ -1282,6 +1294,7 @@ def forward(
             decoder_attention_mask=decoder_attention_mask,
             head_mask=head_mask,
             decoder_head_mask=decoder_head_mask,
+            cross_attn_head_mask=cross_attn_head_mask,
             past_key_values=past_key_values,
             inputs_embeds=inputs_embeds,
             decoder_inputs_embeds=decoder_inputs_embeds,
@@ -1386,6 +1399,7 @@ def forward(
         decoder_attention_mask=None,
         head_mask=None,
         decoder_head_mask=None,
+        cross_attn_head_mask=None,
         encoder_outputs=None,
         inputs_embeds=None,
         decoder_inputs_embeds=None,
@@ -1416,6 +1430,7 @@ def forward(
             decoder_attention_mask=decoder_attention_mask,
             head_mask=head_mask,
             decoder_head_mask=decoder_head_mask,
+            cross_attn_head_mask=cross_attn_head_mask,
             encoder_outputs=encoder_outputs,
             inputs_embeds=inputs_embeds,
             decoder_inputs_embeds=decoder_inputs_embeds,
@@ -1496,6 +1511,7 @@ def forward(
         decoder_attention_mask=None,
         head_mask=None,
         decoder_head_mask=None,
+        cross_attn_head_mask=None,
         encoder_outputs=None,
         start_positions=None,
         end_positions=None,
@@ -1527,6 +1543,7 @@ def forward(
             decoder_attention_mask=decoder_attention_mask,
             head_mask=head_mask,
             decoder_head_mask=decoder_head_mask,
+            cross_attn_head_mask=cross_attn_head_mask,
             encoder_outputs=encoder_outputs,
             inputs_embeds=inputs_embeds,
             decoder_inputs_embeds=decoder_inputs_embeds,
@@ -1633,7 +1650,7 @@ def forward(
         encoder_hidden_states=None,
         encoder_attention_mask=None,
         head_mask=None,
-        encoder_head_mask=None,
+        cross_attn_head_mask=None,
         past_key_values=None,
         inputs_embeds=None,
         labels=None,
@@ -1666,18 +1683,17 @@ def forward(
             encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
                 Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used
                 in the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``:
-            head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
+            head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
                 Mask to nullify selected heads of the attention modules. Mask values selected in ``[0, 1]``:
 
                 - 1 indicates the head is **not masked**,
-                - 0 indicates the heas is **masked**.
+                - 0 indicates the head is **masked**.
 
-            encoder_head_mask (:obj:`torch.Tensor` of shape :obj:`(num_layers, num_heads)`, `optional`):
-                Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention
-                on hidden heads. Mask values selected in ``[0, 1]``:
+            cross_attn_head_mask (:obj:`torch.Tensor` of shape :obj:`(decoder_layers, decoder_attention_heads)`, `optional`):
+                Mask to nullify selected heads of the cross-attention modules. Mask values selected in ``[0, 1]``:
 
                 - 1 indicates the head is **not masked**,
-                - 0 indicates the heas is **masked**.
+                - 0 indicates the head is **masked**.
 
             past_key_values (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
                 Contains precomputed key and value hidden-states of the attention blocks. Can be used to speed up
@@ -1734,7 +1750,7 @@ def forward(
             encoder_hidden_states=encoder_hidden_states,
             encoder_attention_mask=encoder_attention_mask,
             head_mask=head_mask,
-            encoder_head_mask=encoder_head_mask,
+            cross_attn_head_mask=cross_attn_head_mask,
             past_key_values=past_key_values,
             inputs_embeds=inputs_embeds,
             use_cache=use_cache,