change to blimp naming

app.py

@@ -1,6 +1,5 @@
 import evaluate
 from evaluate.utils import launch_gradio_widget
 
-
-module = evaluate.load("perplexity", module_type="metric")
+module = evaluate.load("pico-lm/blimp", module_type="metric")
 launch_gradio_widget(module)

perplexity.py → blimp.py

@@ -11,76 +11,51 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Perplexity Metric."""
+"""Blimp Metric."""
 
 import datasets
+import evaluate
 import numpy as np
 import torch
+from evaluate import logging
 from torch.nn import CrossEntropyLoss
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-import evaluate
-from evaluate import logging
-
-
 _CITATION = """\
-
+@article{warstadt2020blimp,
+    author = {Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei and Wang, Sheng-Fu and Bowman, Samuel R.},
+    title = {BLiMP: The Benchmark of Linguistic Minimal Pairs for English},
+    journal = {Transactions of the Association for Computational Linguistics},
+    volume = {8},
+    number = {},
+    pages = {377-392},
+    year = {2020},
+    doi = {10.1162/tacl\_a\_00321},
+    URL = {https://doi.org/10.1162/tacl_a_00321},
+    eprint = {https://doi.org/10.1162/tacl_a_00321},
+    abstract = { We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),1 a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4\%. We evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands. }
+}
 """
 
 _DESCRIPTION = """
-Perplexity (PPL) is one of the most common metrics for evaluating language models.
-It is defined as the exponentiated average negative log-likelihood of a sequence, calculated with exponent base `e`.
+BLiMP is a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English.
+BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics.
+The data is automatically generated according to expert-crafted grammars. Aggregate human agreement with the labels is 96.4%.
+We use BLiMP to evaluate an n-gram LM, LSTM LM, GPT-2, and Transformer-XL.
 
-For more information, see https://huggingface.co/docs/transformers/perplexity
+For more info see https://github.com/alexwarstadt/blimp.
 """
 
 _KWARGS_DESCRIPTION = """
 Args:
-    model_id (str): model used for calculating Perplexity
-            NOTE: Perplexity can only be calculated for causal language models.
-                    This includes models such as gpt2, causal variations of bert,
-                    causal versions of t5, and more (the full list can be found
-                    in the AutoModelForCausalLM documentation here:
-                    https://huggingface.co/docs/transformers/master/en/model_doc/auto#transformers.AutoModelForCausalLM )
-
-    predictions (list of str): input text, each separate text snippet
-        is one list entry.
+    model_id (str): model used for calculating Blimp
     batch_size (int): the batch size to run texts through the model. Defaults to 16.
-    add_start_token (bool): whether to add the start token to the texts,
-        so the perplexity can include the probability of the first word. Defaults to True.
     device (str): device to run on, defaults to 'cuda' when available
 Returns:
-    perplexity: dictionary containing the perplexity scores for the texts
-        in the input list, as well as the mean perplexity. If one of the input texts is
-        longer than the max input length of the model, then it is truncated to the
-        max length for the perplexity computation.
+    blimp: dictionary containing the blimp scores for each of the 67 sub-datasets, as well as the overall accuracy.
+    An LM’s overall accuracy on BLiMP is simply the proportion of the 67,000 minimal pairs in which the model assigns a higher probability to the acceptable sentence. 
 Examples:
-    Example 1:
-        >>> perplexity = evaluate.load("perplexity", module_type="metric")
-        >>> input_texts = ["lorem ipsum", "Happy Birthday!", "Bienvenue"]
-        >>> results = perplexity.compute(model_id='gpt2',
-        ...                              add_start_token=False,
-        ...                              predictions=input_texts) # doctest:+ELLIPSIS
-        >>> print(list(results.keys()))
-        ['perplexities', 'mean_perplexity']
-        >>> print(round(results["mean_perplexity"], 0))
-        647.0
-        >>> print(round(results["perplexities"][0], 0))
-        32.0
-
-    Example 2:
-        >>> from datasets import load_dataset
-        >>> perplexity = evaluate.load("perplexity", module_type="metric")
-        >>> input_texts = load_dataset("wikitext", "wikitext-2-raw-v1", split="test")["text"][:10] # doctest: +SKIP
-        >>> input_texts = [s for s in input_texts if s!='']
-        >>> results = perplexity.compute(model_id='gpt2',
-        ...                              predictions=input_texts)
-        >>> print(list(results.keys()))
-        ['perplexities', 'mean_perplexity']
-        >>> print(round(results["mean_perplexity"], 2)) # doctest: +SKIP
-        576.76
-        >>> print(round(results["perplexities"][0], 2)) # doctest: +SKIP
-        889.28
+    TODO: examples.
 """
 
 
@@ -97,19 +72,33 @@ class Perplexity(evaluate.Metric):
                     "predictions": datasets.Value("string"),
                 }
             ),
-            reference_urls=["https://huggingface.co/docs/transformers/perplexity"],
+            reference_urls=[
+                "https://github.com/alexwarstadt/blimp",
+                "https://huggingface.co/datasets/nyu-mll/blimp",
+            ],
         )
 
     def _compute(
-        self, predictions, model_id, batch_size: int = 16, add_start_token: bool = True, device=None, max_length=None
+        self,
+        predictions,
+        model_id,
+        batch_size: int = 16,
+        add_start_token: bool = True,
+        device=None,
+        max_length=None,
     ):
-
         if device is not None:
-            assert device in ["gpu", "cpu", "cuda"], "device should be either gpu or cpu."
+            assert device in ["gpu", "cpu", "cuda", "mps"], (
+                "device should be either gpu, cpu or mps."
+            )
             if device == "gpu":
                 device = "cuda"
         else:
-            device = "cuda" if torch.cuda.is_available() else "cpu"
+            device = (
+                "cuda"
+                if torch.cuda.is_available()
+                else ("mps" if torch.mps.is_available() else "cpu")
+            )
 
         model = AutoModelForCausalLM.from_pretrained(model_id)
         model = model.to(device)
@@ -120,19 +109,21 @@ class Perplexity(evaluate.Metric):
         # if there is not an already assigned pad_token, assign an existing
         # special token to also be the padding token
         if tokenizer.pad_token is None and batch_size > 1:
-            existing_special_tokens = list(tokenizer.special_tokens_map_extended.values())
+            existing_special_tokens = list(
+                tokenizer.special_tokens_map_extended.values()
+            )
             # check that the model already has at least one special token defined
-            assert (
-                len(existing_special_tokens) > 0
-            ), "If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1."
+            assert len(existing_special_tokens) > 0, (
+                "If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1."
+            )
             # assign one of the special tokens to also be the pad token
             tokenizer.add_special_tokens({"pad_token": existing_special_tokens[0]})
 
         if add_start_token and max_length:
             # leave room for <BOS> token to be added:
-            assert (
-                tokenizer.bos_token is not None
-            ), "Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False"
+            assert tokenizer.bos_token is not None, (
+                "Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False"
+            )
             max_tokenized_len = max_length - 1
         else:
             max_tokenized_len = max_length
@@ -152,11 +143,13 @@ class Perplexity(evaluate.Metric):
 
         # check that each input is long enough:
         if add_start_token:
-            assert torch.all(torch.ge(attn_masks.sum(1), 1)), "Each input text must be at least one token long."
+            assert torch.all(torch.ge(attn_masks.sum(1), 1)), (
+                "Each input text must be at least one token long."
+            )
         else:
-            assert torch.all(
-                torch.ge(attn_masks.sum(1), 2)
-            ), "When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings."
+            assert torch.all(torch.ge(attn_masks.sum(1), 2)), (
+                "When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings."
+            )
 
         ppls = []
         loss_fct = CrossEntropyLoss(reduction="none")
@@ -167,10 +160,18 @@ class Perplexity(evaluate.Metric):
             attn_mask = attn_masks[start_index:end_index]
 
             if add_start_token:
-                bos_tokens_tensor = torch.tensor([[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)).to(device)
+                bos_tokens_tensor = torch.tensor(
+                    [[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)
+                ).to(device)
                 encoded_batch = torch.cat([bos_tokens_tensor, encoded_batch], dim=1)
                 attn_mask = torch.cat(
-                    [torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(device), attn_mask], dim=1
+                    [
+                        torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(
+                            device
+                        ),
+                        attn_mask,
+                    ],
+                    dim=1,
                 )
 
             labels = encoded_batch
@@ -183,7 +184,10 @@ class Perplexity(evaluate.Metric):
             shift_attention_mask_batch = attn_mask[..., 1:].contiguous()
 
             perplexity_batch = torch.exp(
-                (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch).sum(1)
+                (
+                    loss_fct(shift_logits.transpose(1, 2), shift_labels)
+                    * shift_attention_mask_batch
+                ).sum(1)
                 / shift_attention_mask_batch.sum(1)
             )