add gradient checkpointing

modeling_mpt.py

@@ -1,7 +1,3 @@
-"""A simple, flexible implementation of a GPT model.
-
-Inspired by https://github.com/karpathy/minGPT/blob/master/mingpt/model.py
-"""
 import math
 import warnings
 from typing import List, Optional, Tuple, Union
@@ -23,13 +19,19 @@ Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
 class MPTPreTrainedModel(PreTrainedModel):
     config_class = MPTConfig
     base_model_prefix = 'model'
-    _no_split_modules=["MPTBlock"]
+    _no_split_modules = ["MPTBlock"]
+    supports_gradient_checkpointing = True
+
+    def _set_gradient_checkpointing(self, module, value=False):
+        if isinstance(module, MPTModel):
+            module.gradient_checkpointing = value
 
 class MPTModel(MPTPreTrainedModel):
 
     def __init__(self, config: MPTConfig):
         config._validate_config()
         super().__init__(config)
+        self.gradient_checkpointing = False
         self.attn_impl = config.attn_config['attn_impl']
         self.prefix_lm = config.attn_config['prefix_lm']
         self.attn_uses_sequence_id = config.attn_config['attn_uses_sequence_id']
@@ -47,7 +49,6 @@ class MPTModel(MPTPreTrainedModel):
         self.blocks = nn.ModuleList([MPTBlock(device=config.init_device, **config.to_dict()) for _ in range(config.n_layers)])
         self.norm_f = norm_class(config.d_model, device=config.init_device)
         if config.init_device != 'meta':
-            print(f'You are using config.init_device={config.init_device!r}, but you can also use config.init_device="meta" with Composer + FSDP for fast initialization.')
             self.apply(self.param_init_fn)
         self.is_causal = not self.prefix_lm
         self._attn_bias_initialized = False
@@ -129,19 +130,48 @@ class MPTModel(MPTPreTrainedModel):
         attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
         return attn_bias
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.FloatTensor] = None):
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
+        if self.gradient_checkpointing and self.training:
+            if use_cache:
+                use_cache = False
+        if input_ids is not None and inputs_embeds is not None:
+            raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
+        elif input_ids is not None:
+            batch_size, seq_length = input_ids.shape
+        elif inputs_embeds is not None:
+            batch_size, seq_length, _ = inputs_embeds.shape
+        else:
+            raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")
+
+        seq_length_with_past = seq_length
+        past_key_values_length = 0
+
+        if past_key_values is not None:
+            past_key_values_length = past_key_values[0][0].shape[2]
+            seq_length_with_past = seq_length_with_past + past_key_values_length
+
         if attention_mask is not None:
             attention_mask = attention_mask.bool()
+        else:
+            attention_mask = torch.ones(
+                (batch_size, seq_length_with_past), dtype=torch.bool, device=inputs_embeds.device
+            )
+
+        if inputs_embeds is None:
+            tok_emb = self.wte(input_ids)
+        else:
+            tok_emb = inputs_embeds
+
         if prefix_mask is not None:
             prefix_mask = prefix_mask.bool()
         if not return_dict:
             raise NotImplementedError('return_dict False is not implemented yet for MPT')
         if output_attentions:
             raise NotImplementedError('output_attentions is not implemented yet for MPT')
-        if attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0] and self.training:
-            raise NotImplementedError('MPT does not support training with left padding.')
+        #if attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0] and self.training:
+        #    raise NotImplementedError('MPT does not support training with left padding.')
         if self.prefix_lm and prefix_mask is None:
             raise ValueError('prefix_mask is a required argument when MPT is configured with prefix_lm=True.')
         if self.training:
@@ -149,9 +179,8 @@ class MPTModel(MPTPreTrainedModel):
                 raise ValueError('sequence_id is a required argument when MPT is configured with attn_uses_sequence_id=True ' + 'and the model is in train mode.')
             elif self.attn_uses_sequence_id is False and sequence_id is not None:
                 warnings.warn('MPT received non-None input for `sequence_id` but is configured with attn_uses_sequence_id=False. ' + 'This input will be ignored. If you want the model to use `sequence_id`, set attn_uses_sequence_id to True.')
-        S = input_ids.size(1)
+        S = seq_length
         assert S <= self.config.max_seq_len, f'Cannot forward input with seq_len={S}, this model only supports seq_len<={self.config.max_seq_len}'
-        tok_emb = self.wte(input_ids)
         if self.alibi:
             x = tok_emb
         else:
@@ -163,7 +192,7 @@ class MPTModel(MPTPreTrainedModel):
             if S + past_position > self.config.max_seq_len:
                 raise ValueError(f'Cannot forward input with past sequence length {past_position} and current sequence length {S + 1}, this model only supports total sequence length <= {self.config.max_seq_len}.')
             pos = torch.arange(past_position, S + past_position, dtype=torch.long, device=input_ids.device).unsqueeze(0)
-            if attention_mask is not None:
+            if attention_mask is not None and not self.training:
                 pos = torch.clamp(pos - torch.cumsum((~attention_mask).to(torch.int32), dim=1)[:, past_position:], min=0)
             pos_emb = self.wpe(pos)
             x = tok_emb + pos_emb
@@ -176,13 +205,34 @@ class MPTModel(MPTPreTrainedModel):
         (attn_bias, attention_mask) = self._attn_bias(device=x.device, dtype=x.dtype, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id)
         if use_cache and past_key_values is None:
             past_key_values = [() for _ in range(self.config.n_layers)]
+
         all_hidden_states = () if output_hidden_states else None
         for (b_idx, block) in enumerate(self.blocks):
             if output_hidden_states:
                 assert all_hidden_states is not None
                 all_hidden_states = all_hidden_states + (x,)
             past_key_value = past_key_values[b_idx] if past_key_values is not None else None
-            (x, past_key_value) = block(x, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=self.is_causal)
+
+            if self.gradient_checkpointing and self.training:
+
+                def create_custom_forward(module):
+                    def custom_forward(*inputs):
+                        # None for past_key_value
+                        return module(*inputs)
+
+                    return custom_forward
+
+                (x, past_key_value) = torch.utils.checkpoint.checkpoint(
+                    create_custom_forward(block),
+                    x,
+                    past_key_value,
+                    attn_bias,
+                    attention_mask,
+                    self.is_causal,
+                )
+            else:
+                (x, past_key_value) = block(x, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=self.is_causal)
+
             if past_key_values is not None:
                 past_key_values[b_idx] = past_key_value
         x = self.norm_f(x)
@@ -233,10 +283,10 @@ class MPTForCausalLM(MPTPreTrainedModel):
     def get_decoder(self):
         return self.transformer
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.FloatTensor] = None):
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
-        outputs = self.transformer(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id, return_dict=return_dict, output_attentions=output_attentions, output_hidden_states=output_hidden_states, use_cache=use_cache)
+        outputs = self.transformer(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id, return_dict=return_dict, output_attentions=output_attentions, output_hidden_states=output_hidden_states, use_cache=use_cache, inputs_embeds=inputs_embeds)
         logits = F.linear(outputs.last_hidden_state, self.transformer.wte.weight)
         if self.logit_scale is not None:
             if self.logit_scale == 0:
@@ -282,7 +332,6 @@ class MPTForCausalLM(MPTPreTrainedModel):
     @staticmethod
     def _reorder_cache(past_key_values, beam_idx):
         """Used by HuggingFace generate when using beam search with kv-caching.
-
         See https://github.com/huggingface/transformers/blob/3ec7a47664ebe40c40f4b722f6bb1cd30c3821ec/src/transformers/models/gpt2/modeling_gpt2.py#L1122-L1133
         for an example in transformers.
         """