Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into flan-benchmark

lm_eval/api/task.py

@@ -90,6 +90,12 @@ class TaskConfig(dict):
 
     def __post_init__(self):
 
+        if "." in self.dataset_path:
+            import inspect
+            from importlib import import_module
+
+            self.dataset_path = inspect.getfile(import_module(self.dataset_path))
+
         if self.generation_kwargs is not None:
             if self.output_type != "greedy_until":
                 eval_logger.warning(
@@ -792,7 +798,7 @@ class ConfigurableTask(Task):
                 return doc[doc_to_text]
             else:
                 text_string = utils.apply_template(doc_to_text, doc)
-                if text_string.isdigit():
+                if text_string.isdigit() and self._config.doc_to_choice is not None:
                     return ast.literal_eval(text_string)
                 else:
                     return text_string
@@ -827,7 +833,7 @@ class ConfigurableTask(Task):
                 return doc[doc_to_target]
             else:
                 target_string = utils.apply_template(doc_to_target, doc)
-                if target_string.isdigit():
+                if target_string.isdigit() and self._config.doc_to_choice is not None:
                     return ast.literal_eval(target_string)
                 elif (
                     len(target_string) >= 2
@@ -1014,18 +1020,36 @@ class ConfigurableTask(Task):
                 gold = self.doc_to_text(doc)
             else:
                 gold = self.doc_to_target(doc)
-                if type(gold) is str:
-                    gold = choices.index(gold)
+
+            gold_index_error = False
+            if type(gold) is list:
+                gold = [i if i < len(choices) else -100 for i in gold]
+                if -100 in gold:
+                    gold_index_error = True
+            else:
+                if type(gold) is int:
+                    gold = gold if gold < len(choices) else -100
+                elif type(gold) is str:
+                    gold = choices.index(gold) if gold in choices else -100
+
+                if gold == -100:
+                    gold_index_error = True
+
+            if gold_index_error:
+                eval_logger.warning(
+                    f"Label index was not in within range of available choices,"
+                    f"Sample:\n\n{doc}\n\n"
+                )
 
             if self.multiple_target:
                 acc = 1.0 if pred in gold else 0.0
                 acc_norm = 1.0 if pred_norm in gold else 0.0
-                exact_match = int(any([is_greedy[i] for i in gold]))
+                exact_match = int(any([is_greedy[i] if i != -100 else 0 for i in gold]))
             else:
                 acc = 1.0 if pred == gold else 0.0
                 acc_norm = 1.0 if pred_norm == gold else 0.0
                 # TODO: this gets score of 0 on arc_challenge for pythia-70m. need to test that this works properly
-                exact_match = int(is_greedy[gold])
+                exact_match = int(is_greedy[gold]) if gold != -100 else 0
 
             result_dict = {
                 **({"acc": acc} if "acc" in use_metric else {}),

lm_eval/tasks/README.md

@@ -5,8 +5,8 @@ Boxes should be checked iff tasks are implemented in the refactor and tested for
 
 - [x] Glue
 - [x] SuperGlue
-- [ ] CoQA (Lintang)
-- [ ] DROP (Lintang)
+- [x] CoQA
+- [x] DROP
 - [x] ~~Lambada~~
 - [x] Lambada (Cloze variants)
 - [x] ~~Lambada (Multilingual)~~
@@ -38,7 +38,7 @@ Boxes should be checked iff tasks are implemented in the refactor and tested for
 - [x] TruthfulQA (gen)
 - [ ] MuTual
 - [ ] Hendrycks Math (Hailey)
-- [ ] Asdiv
+- [x] Asdiv
 - [ ] GSM8k
 - [x] Arithmetic
 - [ ] MMMLU (Hailey)

lm_eval/tasks/asdiv/default.yaml

+task: asdiv
+dataset_path: EleutherAI/asdiv
+output_type: loglikelihood
+validation_split: validation
+doc_to_text: "{{body}}\nQuestion:{{question}}\nAnswer:"
+doc_to_target: "{{answer.split(' (')[0]}}"
+should_decontaminate: true
+doc_to_decontamination_query: "{{body}} {{question}}"
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/coqa/README.md

+# CoQA
+
+### Paper
+
+Title: `CoQA: A Conversational Question Answering Challenge`
+
+Abstract: https://arxiv.org/pdf/1808.07042.pdf
+
+CoQA is a large-scale dataset for building Conversational Question Answering
+systems. The goal of the CoQA challenge is to measure the ability of machines to
+understand a text passage and answer a series of interconnected questions that
+appear in a conversation.
+
+Homepage: https://stanfordnlp.github.io/coqa/
+
+### Citation
+
+```
+BibTeX-formatted citation goes here
+```
+
+### Groups and Tasks
+
+#### Groups
+
+* Not part of a group yet
+
+#### Tasks
+
+* `coqa`
+
+### Checklist
+
+For adding novel benchmarks/datasets to the library:
+* [ ] Is the task an existing benchmark in the literature?
+  * [ ] Have you referenced the original paper that introduced the task?
+  * [ ] If yes, does the original paper provide a reference implementation? If so, have you checked against the reference implementation and documented how to run such a test?
+
+
+If other tasks on this dataset are already supported:
+* [ ] Is the "Main" variant of this task clearly denoted?
+* [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
+* [ ] Have you noted which, if any, published evaluation setups are matched by this variant?

lm_eval/tasks/coqa/default.yaml

+task: coqa
+dataset_path: EleutherAI/coqa
+output_type: greedy_until
+training_split: train
+validation_split: validation
+doc_to_text: !function utils.doc_to_text
+doc_to_target: !function utils.doc_to_target
+process_results: !function utils.process_results
+should_decontaminate: true
+doc_to_decontamination_query: "{{story}} {{question.input_text|join('\n')}}"
+generation_kwargs:
+  until:
+    - "\nQ:"
+metric_list:
+  - metric: em
+    aggregation: mean
+    higher_is_better: true
+  - metric: f1
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/coqa/utils.py

+from itertools import zip_longest
+
+import transformers.data.metrics.squad_metrics as squad_metrics
+
+
+def doc_to_text(doc):
+    # Given a passage p, the conversation history {q1, a1, . . . qi−1, ai−1}
+    # and a question qi, the task is to predict the answer ai
+    doc_text = doc["story"] + "\n\n"
+    for (q, a) in zip_longest(
+        doc["questions"]["input_text"], doc["answers"]["input_text"][:-1]
+    ):  # omit target answer ai
+        question = f"Q: {q}\n\n"
+        answer = f"A: {a}\n\n" if a is not None else "A:"
+        doc_text += question + answer
+    return doc_text
+
+
+def doc_to_target(doc):
+
+    turn_id = len(doc["questions"]["input_text"])
+    # Returns unique answers and valid alternatives (Some questions in CoQA have multiple valid answers).
+    answers = []
+    answer_forturn = doc["answers"]["input_text"][turn_id - 1]
+    answers.append(answer_forturn)
+
+    additional_answers = doc.get("additional_answers")
+    if additional_answers:
+        for key in additional_answers:
+            additional_answer_for_turn = additional_answers[key]["input_text"][
+                turn_id - 1
+            ]
+            if additional_answer_for_turn.lower() not in map(str.lower, answers):
+                answers.append(additional_answer_for_turn)
+    return answers
+
+
+def em(gold_list, pred):
+    # tests for exact match and on the normalised answer (compute_exact)
+    em_sum = 0.0
+    if len(gold_list) > 1:
+        for i in range(len(gold_list)):
+            gold_answers = gold_list[0:i] + gold_list[i + 1 :]
+            # predictions compared against (n) golds and take maximum
+            em_sum += max(squad_metrics.compute_exact(a, pred) for a in gold_answers)
+    else:
+        em_sum += max(squad_metrics.compute_exact(a, pred) for a in gold_list)
+
+    return em_sum / max(1, len(gold_list))
+
+
+def compute_scores(gold_list, pred):
+    # tests for exact match and on the normalised answer (compute_exact)
+    # test for overlap (compute_f1)
+    f1_sum = 0.0
+    em_sum = 0.0
+    if len(gold_list) > 1:
+        for i in range(len(gold_list)):
+            gold_answers = gold_list[0:i] + gold_list[i + 1 :]
+            # predictions compared against (n) golds and take maximum
+            em_sum += max(squad_metrics.compute_exact(a, pred) for a in gold_answers)
+            f1_sum += max(squad_metrics.compute_f1(a, pred) for a in gold_answers)
+    else:
+        em_sum += max(squad_metrics.compute_exact(a, pred) for a in gold_list)
+        f1_sum += max(squad_metrics.compute_f1(a, pred) for a in gold_list)
+
+    return {
+        "em": em_sum / max(1, len(gold_list)),
+        "f1": f1_sum / max(1, len(gold_list)),
+    }
+
+
+def process_results(doc, results):
+
+    gold_list = doc_to_target(doc)
+    pred = results[0].strip().split("\n")[0]
+
+    scores = compute_scores(gold_list, pred)
+    return scores

lm_eval/tasks/drop/README.md

+# DROP
+
+### Paper
+
+Title: `DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs`
+
+Abstract: https://aclanthology.org/attachments/N19-1246.Supplementary.pdf
+
+DROP is a QA dataset which tests comprehensive understanding of paragraphs. In
+this crowdsourced, adversarially-created, 96k question-answering benchmark, a
+system must resolve multiple references in a question, map them onto a paragraph,
+and perform discrete operations over them (such as addition, counting, or sorting).
+
+Homepage: https://allenai.org/data/drop
+
+Acknowledgement: This implementation is based on the official evaluation for `DROP`:
+https://github.com/allenai/allennlp-reading-comprehension/blob/master/allennlp_rc/eval/drop_eval.py
+
+### Citation
+
+```
+@misc{dua2019drop,
+    title={DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs},
+    author={Dheeru Dua and Yizhong Wang and Pradeep Dasigi and Gabriel Stanovsky and Sameer Singh and Matt Gardner},
+    year={2019},
+    eprint={1903.00161},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+### Groups and Tasks
+
+#### Groups
+
+* Not part of a group yet.
+
+#### Tasks
+
+* `drop`
+
+### Checklist
+
+For adding novel benchmarks/datasets to the library:
+* [ ] Is the task an existing benchmark in the literature?
+  * [ ] Have you referenced the original paper that introduced the task?
+  * [ ] If yes, does the original paper provide a reference implementation? If so, have you checked against the reference implementation and documented how to run such a test?
+
+
+If other tasks on this dataset are already supported:
+* [ ] Is the "Main" variant of this task clearly denoted?
+* [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
+* [ ] Have you noted which, if any, published evaluation setups are matched by this variant?

lm_eval/tasks/drop/default.yaml

+task: drop
+dataset_path: EleutherAI/drop
+output_type: greedy_until
+training_split: train
+validation_split: validation
+process_docs: !function utils.process_docs
+doc_to_text: "{{passage}} {{question}}"
+doc_to_target: "{{ answer|join(',')}}"
+target_delimiter: ""
+process_results: !function utils.process_results
+should_decontaminate: true
+doc_to_decontamination_query: "{{passage}} {{question}}"
+generation_kwargs:
+  until:
+    - "."
+metric_list:
+  - metric: em
+    aggregation: mean
+    higher_is_better: true
+  - metric: f1
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/drop/utils.py

+import re
+import string
+
+import numpy as np
+from scipy.optimize import linear_sum_assignment
+
+_ARTICLES = re.compile(r"\b(a|an|the)\b", re.UNICODE)
+
+
+def process_docs(dataset):
+    def _process(doc):
+        return {
+            "id": doc["query_id"],
+            "passage": doc["passage"],
+            "question": doc["question"],
+            "answers": get_answers(doc),
+        }
+
+    return dataset.map(_process)
+
+
+def get_answers(doc):
+    def _flatten_validated_answers(validated_answers):
+        """Flattens a dict of lists of validated answers.
+        {"number": ['1', '8'], ...}
+        -> [{"number": ['1'], ...}, {"number": ['8'], ...}]
+        """
+        valid_answers = []
+        for i in range(len(validated_answers["number"])):
+            valid_answers.append(
+                {
+                    "number": validated_answers["number"][i],
+                    "date": validated_answers["date"][i],
+                    "spans": validated_answers["spans"][i],
+                }
+            )
+        return valid_answers
+
+    answers = []
+    answers_set = set()
+    candidates = [doc["answer"]] + _flatten_validated_answers(doc["validated_answers"])
+    for candidate in candidates:
+        answer = parse_answer(candidate)
+        if answer in answers_set:
+            continue
+        answers_set.add(answer)
+        answers.append(answer)
+    return answers
+
+
+def parse_answer(answer):
+    # NOTE: Everything is returned as a tuple for uniformity and hashability.
+    if answer["number"] != "":
+        return (str(answer["number"]),)
+    if answer["spans"] != []:
+        return tuple(answer["spans"])
+    return (
+        " ".join(
+            [answer["date"]["day"], answer["date"]["month"], answer["date"]["year"]]
+        ).strip(),
+    )
+
+
+def process_results(doc, results):
+
+    preds, golds = results, doc["answers"]
+    max_em = 0
+    max_f1 = 0
+    for gold_answer in golds:
+        exact_match, f1_score = get_metrics(preds, gold_answer)
+        if gold_answer[0].strip():
+            max_em = max(max_em, exact_match)
+            max_f1 = max(max_f1, f1_score)
+    return {"em": max_em, "f1": max_f1}
+
+
+def get_metrics(predicted, gold):
+    """
+    Takes a predicted answer and a gold answer (that are both either a string or a list of
+    strings), and returns exact match and the DROP F1 metric for the prediction.  If you are
+    writing a script for evaluating objects in memory (say, the output of predictions during
+    validation, or while training), this is the function you want to call, after using
+    :func:`answer_json_to_strings` when reading the gold answer from the released data file.
+    """
+    predicted_bags = _answer_to_bags(predicted)
+    gold_bags = _answer_to_bags(gold)
+
+    if set(predicted_bags[0]) == set(gold_bags[0]) and len(predicted_bags[0]) == len(
+        gold_bags[0]
+    ):
+        exact_match = 1.0
+    else:
+        exact_match = 0.0
+
+    f1_per_bag = _align_bags(predicted_bags[1], gold_bags[1])
+    f1 = np.mean(f1_per_bag)
+    f1 = round(f1, 2)
+    return exact_match, f1
+
+
+def _answer_to_bags(answer):
+    if isinstance(answer, (list, tuple)):
+        raw_spans = answer
+    else:
+        raw_spans = [answer]
+    normalized_spans = []
+    token_bags = []
+    for raw_span in raw_spans:
+        normalized_span = _normalize(raw_span)
+        normalized_spans.append(normalized_span)
+        token_bags.append(set(normalized_span.split()))
+    return normalized_spans, token_bags
+
+
+def _align_bags(predicted, gold):
+    """
+    Takes gold and predicted answer sets and first finds the optimal 1-1 alignment
+    between them and gets maximum metric values over all the answers.
+    """
+    scores = np.zeros([len(gold), len(predicted)])
+    for gold_index, gold_item in enumerate(gold):
+        for pred_index, pred_item in enumerate(predicted):
+            if _match_numbers_if_present(gold_item, pred_item):
+                scores[gold_index, pred_index] = _compute_f1(pred_item, gold_item)
+    row_ind, col_ind = linear_sum_assignment(-scores)
+
+    max_scores = np.zeros([max(len(gold), len(predicted))])
+    for row, column in zip(row_ind, col_ind):
+        max_scores[row] = max(max_scores[row], scores[row, column])
+    return max_scores
+
+
+def _compute_f1(predicted_bag, gold_bag):
+    intersection = len(gold_bag.intersection(predicted_bag))
+    if not predicted_bag:
+        precision = 1.0
+    else:
+        precision = intersection / float(len(predicted_bag))
+    if not gold_bag:
+        recall = 1.0
+    else:
+        recall = intersection / float(len(gold_bag))
+    f1 = (
+        (2 * precision * recall) / (precision + recall)
+        if not (precision == 0.0 and recall == 0.0)
+        else 0.0
+    )
+    return f1
+
+
+def _match_numbers_if_present(gold_bag, predicted_bag):
+    gold_numbers = set()
+    predicted_numbers = set()
+    for word in gold_bag:
+        if _is_number(word):
+            gold_numbers.add(word)
+    for word in predicted_bag:
+        if _is_number(word):
+            predicted_numbers.add(word)
+    if (not gold_numbers) or gold_numbers.intersection(predicted_numbers):
+        return True
+    return False
+
+
+def _is_number(text):
+    try:
+        float(text)
+        return True
+    except ValueError:
+        return False
+
+
+def _remove_articles(text):
+    return _ARTICLES.sub(" ", text)
+
+
+def _white_space_fix(text):
+    return " ".join(text.split())
+
+
+def _remove_punc(text):
+    exclude = set(string.punctuation)
+    if not _is_number(text):
+        return "".join(ch for ch in text if ch not in exclude)
+    else:
+        return text
+
+
+def _fix_number(text):
+    return str(float(text)) if _is_number(text) else text
+
+
+def _tokenize(text):
+    return re.split(" |-", text)
+
+
+def _normalize(answer):
+    tokens = [
+        _white_space_fix(_remove_articles(_fix_number(_remove_punc(token.lower()))))
+        for token in _tokenize(answer)
+    ]
+    tokens = [token for token in tokens if token.strip()]
+    normalized = " ".join(tokens).strip()
+    return normalized