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

.github/workflows/new_tasks.yml

@@ -50,6 +50,7 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: 3.9
+          cache: 'pip'
       - name: Install dependencies
         if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
         run: |

.github/workflows/pull_request.yml

-name: Pull Request
-
-on: [pull_request]
-
-jobs:
-  pre-commit:
-    runs-on: ubuntu-20.04
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
-        with:
-          python-version: 3.9
-      - uses: pre-commit/action@v2.0.3

.github/workflows/unit_tests.yml

@@ -6,10 +6,10 @@ name: Unit Tests
 on:
   push:
     branches:
-      - big-refactor
+      - 'big-refactor*'
   pull_request:
     branches:
-      - big-refactor
+      - 'big-refactor*'
   workflow_dispatch:
 # Jobs run concurrently and steps run sequentially within a job.
 # jobs: linter and cpu_tests. Add more jobs/steps as required.
@@ -26,8 +26,11 @@ jobs:
       uses: actions/setup-python@v4
       with:
         python-version: 3.9
+        cache: 'pip'
     - name: Install dependencies
       run: pip install -e '.[linting,testing]' --extra-index-url https://download.pytorch.org/whl/cpu
+    - name: Pre-Commit
+      uses: pre-commit/action@v3.0.0
     - name: Lint with pylint
       run: python -m pylint --disable=all -e W0311 --jobs=0 --indent-string='    ' **/*.py
     - name: Lint with flake8
@@ -52,6 +55,7 @@ jobs:
       uses: actions/setup-python@v4
       with:
         python-version: 3.9
+        cache: 'pip'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
@@ -60,4 +64,4 @@ jobs:
 #                pip install bleurt@https://github.com/google-research/bleurt/archive/b610120347ef22b494b6d69b4316e303f5932516.zip#egg=bleurt
 #        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Test with pytest
-      run: python -m pytest -s -v -n=auto --ignore=tests/tests_master --ignore=tests/extra
+      run: python -m pytest --showlocals -s -vv -n=auto --ignore=tests/tests_master --ignore=tests/extra

README.md

@@ -33,7 +33,6 @@ To install the `lm-eval` refactor branch from the github repository, run:
 ```bash
 git clone https://github.com/EleutherAI/lm-evaluation-harness
 cd lm-evaluation-harness
-git checkout big-refactor
 pip install -e .
 ```
 
@@ -49,6 +48,13 @@ To support loading GPTQ quantized models, install the package with the `gptq` ex
 pip install -e ".[gptq]"
 ```
 
+
+To install the package with all extras, run
+```bash
+pip install -e ".[all]"
+```
+
+
 ## Support
 
 The best way to get support is to open an issue on this repo or join the EleutherAI discord server](discord.gg/eleutherai). The `#lm-thunderdome` channel is dedicated to developing this project and the `#release-discussion` channel is for receiving support for our releases.
@@ -93,6 +99,8 @@ python main.py \
     --batch_size auto:4
 ```
 
+Alternatively, you can use `lm-eval` instead of `python main.py` to call lm eval from anywhere.
+
 ### Multi-GPU Evaluation with Hugging Face `accelerate`
 
 To parallelize evaluation of HuggingFace models across multiple GPUs, we allow for two different types of multi-GPU evaluation.
@@ -128,30 +136,43 @@ Using this setting helps for massive models like BLOOM which require, or to avoi
 
 **Note that this option requires launching evaluation via `python main.py` rather than `accelerate launch main.py`.**
 
+To use `accelerate` with the `lm-eval` command, use
+```
+accelerate launch --no_python lm-eval --model ...
+```
+
 ### Commercial APIs
 
-Our library also supports language models served via the OpenAI API:
+Our library also supports the evaluation of models served via several commercial APIs, and hope to implement support for common performant local/self-hosted inference servers.
+
+A full accounting of the supported and planned libraries + APIs can be seen below:
+
+| API or Inference Server     | Implemented?                    | `--model <xxx>` name                                                             | Models supported:                    | Request Types:                                           |
+|-----------------------------|---------------------------------|----------------------------------------------------------------------------------|--------------------------------------|----------------------------------------------------------|
+| OpenAI Completions          | :heavy_check_mark:              | `openai`, `openai-completions`, `gooseai`                                        | up to `code-davinci-002`             | `greedy_until`, `loglikelihood`, `loglikelihood_rolling` |
+| OpenAI ChatCompletions      | :x: Not yet - needs help!       | N/A                                                                              | (link here?)                         | `greedy_until` (no logprobs)                             |
+| Anthropic                   | :heavy_check_mark:              | `anthropic`                                                                      | [Supported Anthropic Engines](https://docs.anthropic.com/claude/reference/selecting-a-model)         | `greedy_until` (no logprobs)                             |
+| GooseAI                     | :heavy_check_mark: (not separately maintained)  | `openai`, `openai-completions`, `gooseai` (same interface as OpenAI Completions) |                                      | `greedy_until`, `loglikelihood`, `loglikelihood_rolling` |
+| Textsynth                   | Needs testing                   | `textsynth`                                                                      | ???                                  | `greedy_until`, `loglikelihood`, `loglikelihood_rolling` |
+| Cohere                      | :hourglass: - blocked on Cohere API bug | N/A                                                                              | [All `cohere.generate()` engines](https://docs.cohere.com/docs/models) | `greedy_until`, `loglikelihood`, `loglikelihood_rolling` |
+| GGML                        | :hourglass: [PR](https://github.com/EleutherAI/lm-evaluation-harness/pull/617)              | N/A                                                                              | ???                                  | `greedy_until`, `loglikelihood`, `loglikelihood_rolling` |
+| vLLM                        | :x: Not yet - needs help!       | N/A                                                                              | All HF models                        | `greedy_until` (no logprobs)                             |
+| Your inference server here! | ...                             | ...                                                                              | ...                                  | ...                                                      |                                | ...                                                      |
+
+It is on our roadmap to create task variants designed to enable models which do not serve logprobs/loglikelihoods to be compared with generation performance of open-source models.
+
+Our library supports language models served via the OpenAI Completions API as follows:
 
 ```bash
 export OPENAI_API_SECRET_KEY=YOUR_KEY_HERE
 python main.py \
-    --model openai \
+    --model openai-completions \
     --model_args engine=davinci \
     --tasks lambada_openai,hellaswag
 ```
 
 While this functionality is only officially maintained for the official OpenAI API, it tends to also work for other hosting services that use the same API such as [goose.ai](goose.ai) with minor modification. We also have an implementation for the [TextSynth](https://textsynth.com/index.html) API, using `--model textsynth`.
 
-To verify the data integrity of the tasks you're performing in addition to running the tasks themselves, you can use the `--check_integrity` flag:
-
-```bash
-python main.py \
-    --model openai \
-    --model_args engine=davinci \
-    --tasks lambada_openai,hellaswag \
-    --check_integrity
-```
-
 ### Other Frameworks
 
 A number of other libraries contain scripts for calling the eval harness through their library. These include [GPT-NeoX](https://github.com/EleutherAI/gpt-neox/blob/main/eval_tasks/eval_adapter.py), [Megatron-DeepSpeed](https://github.com/microsoft/Megatron-DeepSpeed/blob/main/examples/MoE/readme_evalharness.md), and [mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax/blob/master/eval_harness.py).
@@ -172,6 +193,16 @@ python write_out.py \
 
 This will write out one text file for each task.
 
+To verify the data integrity of the tasks you're performing in addition to running the tasks themselves, you can use the `--check_integrity` flag:
+
+```bash
+python main.py \
+    --model openai \
+    --model_args engine=davinci \
+    --tasks lambada_openai,hellaswag \
+    --check_integrity
+```
+
 ## Advanced Usage
 
 For models loaded with the HuggingFace  `transformers` library, any arguments provided via `--model_args` get passed to the relevant constructor directly. This means that anything you can do with `AutoModel` can be done with our library. For example, you can pass a local path via `pretrained=` or use models finetuned with [PEFT](https://github.com/huggingface/peft) by taking the call you would run to evaluate the base model and add `,peft=PATH` to the `model_args` argument:
@@ -201,6 +232,14 @@ To implement a new task in the eval harness, see [this guide](./docs/new_task_gu
 
 As a start, we currently only support one prompt per task, which we strive to make the "standard" as defined by the benchmark's authors. If you would like to study how varying prompts causes changes in the evaluation score, we support prompts authored in the [Promptsource Library](https://github.com/bigscience-workshop/promptsource/tree/main) as described further in https://github.com/EleutherAI/lm-evaluation-harness/blob/big-refactor/lm_eval/docs/new_task_guide.md and https://github.com/EleutherAI/lm-evaluation-harness/blob/big-refactor/lm_eval/docs/advanced_task_guide.md and welcome contributions of novel task templates and task variants.
 
+## How to Contribute or Learn More?
+
+For more information on the library and how everything fits together, check out all of our [documentation pages](https://github.com/EleutherAI/lm-evaluation-harness/tree/big-refactor/docs)! We plan to post a larger roadmap of desired + planned library improvements soon, with more information on how contributors can help.
+
+
+You can also ask for help, or discuss new features with the maintainers in the #lm-thunderdome channel of the EleutherAI discord! If you've used the library and have had a positive (or negative) experience, we'd love to hear from you!
+
+
 ## Cite as
 
 ```

docs/advanced_task_guide.md

@@ -236,3 +236,89 @@ Generative tasks:
 
 Tasks using complex filtering:
 - GSM8k with CoT (+ with Self-Consistency): (`lm_eval/tasks/gsm8k/gsm8k-cot.yaml` ; `lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml`)
+
+
+## Benchmarks
+
+When evaluating a language model, it's is not unusual to test across a number of tasks that may not be related to one another in order to assess a variety of capabilities. To this end, it may be combursome to have to list the set of tasks or add a new group name to each yaml of each individual task.
+
+To solve this, we can create a benchmark yaml config. This is a config that contains the names of the tasks that should be included in a particular benchmark. The config consists of two main keys `group` which denotes the name of the benchmark and `task` which is where we can list the tasks. The tasks listed in `task` are the task names that have been registered. A good example would be the list of tasks used to evaluate the Pythia Suite.
+
+```yaml
+group: pythia
+task:
+  - lambada_openai
+  - wikitext
+  - piqa
+  - sciq
+  - wsc
+  - winogrande
+  - arc
+  - logiqa
+  - blimp
+  - hendrycksTest*
+```
+
+Alternatively, benchmarks can have tasks that are customizable for each task. They can be defined like how a yaml task is usually set.
+
+```yaml
+group: t0_eval
+task:
+  # Coreference Resolution
+  - dataset_path: super_glue
+    dataset_name: wsc.fixed
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Coreference Resolution
+  - dataset_path: winogrande
+    dataset_name: winogrande_xl
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  ...
+```
+
+If the benchmark contains the same dataset but with different configurations, use `task` to differentiate between them. For example, T0-Eval evaluates on 3 versions of ANLI but the huggingface dataset collects them in one dataset.
+
+```YAML
+group: t0_eval
+task:
+  ...
+  - task: anli_r1
+    dataset_path: anli
+    use_prompt: promptsource:*
+    training_split: train_r1
+    validation_split: dev_r1
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  - task: anli_r2
+    dataset_path: anli
+    use_prompt: promptsource:*
+    training_split: train_r2
+    validation_split: dev_r2
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+```
+
+Calling the benchmark is done the same way we would call any task with `--tasks`. Benchmarks can be added in `lm_eval/benchmarks/`

lm_eval/api/samplers.py

@@ -48,7 +48,9 @@ class Sampler:
                     )
                     + self.target_delimiter
                     + (
-                        self.doc_to_target(doc)
+                        self.doc_to_target(doc)[0]
+                        if type(self.doc_to_target(doc)) is list
+                        else self.doc_to_target(doc)
                         if (
                             self.config.doc_to_choice is None
                             or type(self.doc_to_target(doc)) is str

lm_eval/api/task.py

@@ -465,8 +465,11 @@ class Task(abc.ABC):
         elif type(example) == list:
             return [labeled_examples + ex for ex in example]
         elif type(example) == int:
+            if self._config.doc_to_choice is not None:
                 choices = self.doc_to_choice(doc)
                 return labeled_examples + choices[example]
+            else:
+                return labeled_examples + str(example)
 
     def apply_filters(self):
 
@@ -649,9 +652,36 @@ class ConfigurableTask(Task):
 
             if type(test_text) is int:
                 self.multiple_input = num_choice
+        else:
+            test_choice = None
 
         if type(test_target) is list:
             self.multiple_target = len(test_target)
+        else:
+            if (type(test_target) is int) and (test_choice is not None):
+                test_target = [self.doc_to_choice(test_target)[test_target]]
+            else:
+                test_target = [test_target]
+
+        if test_choice is not None:
+            check_choices = test_choice
+        else:
+            check_choices = test_target
+
+        for choice in check_choices:
+            choice_has_whitespace = True if " " in choice else False
+            delimiter_has_whitespace = (
+                True if " " in self._config.target_delimiter else False
+            )
+
+            if delimiter_has_whitespace and choice_has_whitespace:
+                eval_logger.warning(
+                    f'Both target_delimiter and target choice: "{choice}" have whitespace'
+                )
+            elif (not delimiter_has_whitespace) and (not choice_has_whitespace):
+                eval_logger.warning(
+                    f'Both target_delimiter and target choice: "{choice}" does not have whitespace, ignore if the language you are evaluating on does not require/use whitespace'
+                )
 
     def download(self, dataset_kwargs=None):
 
@@ -761,12 +791,17 @@ class ConfigurableTask(Task):
             return doc_to_text(doc)
         # Used when applying a Promptsource template
         elif hasattr(doc_to_text, "apply"):
-            return doc_to_text.apply(doc)[0]
+            applied_prompt = doc_to_text.apply(doc)
+            if len(applied_prompt) == 2:
+                return applied_prompt[0]
+            else:
+                eval_logger.warning("Applied prompt returns empty string")
+                return self._config.fewshot_delimiter
         else:
             print(type(doc_to_text))
             raise TypeError
 
-    def doc_to_target(self, doc: dict) -> Union[int, str]:
+    def doc_to_target(self, doc: dict) -> Union[int, str, list]:
 
         if self.prompt is not None:
             doc_to_target = self.prompt
@@ -785,13 +820,26 @@ class ConfigurableTask(Task):
                 target_string = utils.apply_template(doc_to_target, doc)
                 if target_string.isdigit():
                     return ast.literal_eval(target_string)
+                elif (
+                    len(target_string) >= 2
+                    and (target_string[0] == "[")
+                    and (target_string[-1] == "]")
+                ):
+                    return ast.literal_eval(target_string)
                 else:
                     return target_string
+        elif type(doc_to_target) == list:
+            return doc_to_target
         elif callable(doc_to_target):
             return doc_to_target(doc)
         # Used when applying a Promptsource template
         elif hasattr(doc_to_target, "apply"):
-            return doc_to_target.apply(doc)[1]
+            applied_prompt = doc_to_target.apply(doc)
+            if len(applied_prompt) == 2:
+                return applied_prompt[1]
+            else:
+                eval_logger.warning("Applied prompt returns empty string")
+                return self._config.fewshot_delimiter
         else:
             raise TypeError
 
@@ -988,9 +1036,13 @@ class ConfigurableTask(Task):
         elif self.OUTPUT_TYPE == "greedy_until":
 
             gold = self.doc_to_target(doc)
-            if type(gold) == int:
+            if self._config.doc_to_choice is not None:
+                # If you set doc_to_choice,
+                # it assumes that doc_to_target returns a number.
                 choices = self.doc_to_choice(doc)
                 gold = choices[gold]
+            else:
+                gold = str(gold)
 
             for key, result in zip(self._metric_fn_list.keys(), results):
                 if self.multiple_target:
@@ -1009,20 +1061,20 @@ class ConfigurableTask(Task):
                             res = res[key]
                         scores.append(res)
                     if any(scores):
-                        result = 1.0
+                        result_score = 1.0
                     else:
-                        result = 0.0
+                        result_score = 0.0
                 else:
-                    result = self._metric_fn_list[key](
+                    result_score = self._metric_fn_list[key](
                         references=[gold],
                         predictions=[result],
                         **self._metric_fn_kwargs[key],
                     )
 
-                if isinstance(result, dict):
-                    result_dict.update(result)
+                if isinstance(result_score, dict):
+                    result_dict.update(result_score)
                 else:
-                    result_dict[key] = result
+                    result_dict[key] = result_score
         else:
             raise ValueError(
                 f"Passed invalid output_type '{self.OUTPUT_TYPE}' ! Please use one of ",

lm_eval/benchmarks/__init__.py

+import os
+import yaml
+
+from lm_eval import utils
+from lm_eval.tasks import register_configurable_task, check_prompt_config
+from lm_eval.logger import eval_logger
+from lm_eval.api.registry import (
+    TASK_REGISTRY,
+    GROUP_REGISTRY,
+    ALL_TASKS,
+)
+
+
+def include_benchmarks(task_dir):
+
+    for root, subdirs, file_list in os.walk(task_dir):
+        if (subdirs == [] or subdirs == ["__pycache__"]) and (len(file_list) > 0):
+            for f in file_list:
+                if f.endswith(".yaml"):
+                    try:
+                        benchmark_path = os.path.join(root, f)
+
+                        with open(benchmark_path, "rb") as file:
+                            yaml_config = yaml.full_load(file)
+
+                        assert "group" in yaml_config
+                        group = yaml_config["group"]
+                        all_task_list = yaml_config["task"]
+                        config_list = [
+                            task for task in all_task_list if type(task) != str
+                        ]
+                        task_list = [
+                            task for task in all_task_list if type(task) == str
+                        ]
+
+                        for task_config in config_list:
+                            var_configs = check_prompt_config(
+                                {
+                                    **task_config,
+                                    **{"group": group},
+                                }
+                            )
+                            for config in var_configs:
+                                register_configurable_task(config)
+
+                        task_names = utils.pattern_match(task_list, ALL_TASKS)
+                        for task in task_names:
+                            if task in TASK_REGISTRY:
+                                if group in GROUP_REGISTRY:
+                                    GROUP_REGISTRY[group].append(task)
+                                else:
+                                    GROUP_REGISTRY[group] = [task]
+                                    ALL_TASKS.add(group)
+                    except Exception as error:
+                        eval_logger.warning(
+                            "Failed to load benchmark in\n"
+                            f"                                 {benchmark_path}\n"
+                            "                                 Benchmark will not be added to registry\n"
+                            f"                                 Error: {error}"
+                        )
+
+
+task_dir = os.path.dirname(os.path.abspath(__file__)) + "/"
+include_benchmarks(task_dir)

lm_eval/tasks/benchmarks/pythia.yaml → lm_eval/benchmarks/pythia.yaml

@@ -6,7 +6,7 @@ task:
   - sciq
   - wsc
   - winogrande
-  - arc_*
-  # - logiqa
-  # - blimp_*
-  # - hendrycksTest*
+  - arc
+  - logiqa
+  - blimp
+  - hendrycksTest*

lm_eval/benchmarks/t0_eval.yaml

+group: t0_eval
+task:
+  # Coreference Resolution
+  - dataset_path: super_glue
+    dataset_name: wsc.fixed
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Coreference Resolution
+  - dataset_path: winogrande
+    dataset_name: winogrande_xl
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Natural Language Inference
+  - dataset_path: super_glue
+    dataset_name: cb
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    output_type: greedy_until
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  - dataset_path: super_glue
+    dataset_name: rte
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  - task: anli_r1
+    dataset_path: anli
+    use_prompt: promptsource:*
+    training_split: train_r1
+    validation_split: dev_r1
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  - task: anli_r2
+    dataset_path: anli
+    use_prompt: promptsource:*
+    training_split: train_r2
+    validation_split: dev_r2
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  - task: anli_r3
+    dataset_path: anli
+    use_prompt: promptsource:*
+    training_split: train_r3
+    validation_split: dev_r3
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Sentence Completion
+  - dataset_path: super_glue
+    dataset_name: copa
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Natural Language Inference
+  - dataset_path: hellaswag
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true
+  # Word Sense Disambiguation
+  - dataset_path: super_glue
+    dataset_name: wic
+    use_prompt: promptsource:*
+    training_split: train
+    validation_split: validation
+    metric_list:
+      - metric: exact_match
+        aggregation: mean
+        higher_is_better: true
+        ignore_case: true
+        ignore_punctuation: true

lm_eval/evaluator.py

@@ -11,6 +11,7 @@ import numpy as np
 
 import lm_eval.api
 import lm_eval.tasks
+import lm_eval.benchmarks
 import lm_eval.models
 import lm_eval.api.metrics
 import lm_eval.api.registry

lm_eval/filters/__init__.py

@@ -8,6 +8,7 @@ FILTER_REGISTRY = {
     "regex": extraction.RegexFilter,
     "majority_vote": selection.MajorityVoteFilter,
     "take_first_k": selection.TakeKFilter,
+    "remove_whitespace": extraction.WhitespaceFilter,
     # TODO: implement this filter. either it should take in an arbitrary "scoring"/reward function
     # that takes an input and returns a scalar and then should select the max reward,
     # or should implement different filters for different ways of handling a reward model's inference.

lm_eval/filters/extraction.py

@@ -36,3 +36,26 @@ class RegexFilter(Filter):
         # print(filtered_resps)
 
         return filtered_resps
+
+
+class WhitespaceFilter(Filter):
+    """ """
+
+    def __init__(self):
+        pass
+
+    def apply(self, resps):
+        def filter_set(inst):
+
+            filtered_resp = []
+            for resp in inst:
+                if resp.startswith(" "):
+                    resp = resp[1:]
+
+                filtered_resp.append(resp)
+
+            return filtered_resp
+
+        filtered_resps = [filter_set(resp) for resp in resps]
+
+        return filtered_resps

lm_eval/models/huggingface.py

@@ -292,7 +292,9 @@ class HFLM(LM):
                         "Failed to place model onto specified device. This may be because the model is quantized via `bitsandbytes`. If the desired GPU is being used, this message is safe to ignore."
                     )
             else:
-                self._model = accelerator.prepare(self.model)
+                self._model = accelerator.prepare_model(
+                    self.model, evaluation_mode=True
+                )
                 self._device = torch.device(f"cuda:{accelerator.local_process_index}")
                 self.accelerator = accelerator
 

lm_eval/tasks/README.md

@@ -3,7 +3,7 @@ This list keeps track of which tasks' implementations have been ported to YAML /
 
 Boxes should be checked iff tasks are implemented in the refactor and tested for regression. Tasks should be struck through if checked *against original introducing paper* implementation or popularizing implementation. (WIP) Denotes that there exists a PR or person working on this task already.
 
-- [ ] Glue (Lintang)
+- [x] Glue
 - [x] SuperGlue
 - [ ] CoQA (Lintang)
 - [ ] DROP (Lintang)
@@ -13,12 +13,12 @@ Boxes should be checked iff tasks are implemented in the refactor and tested for
 - [x] Wikitext
 - [x] PiQA
 - [x] PROST
-- [ ] MCTACO (Lintang)
+- [x] MCTACO
 - [x] Pubmed QA
 - [x] SciQ
 - [ ] QASPER
 - [x] QA4MRE
-- [ ] TriviaQA (Lintang)
+- [x] TriviaQA
 - [x] AI2 ARC
 - [x] LogiQA
 - [x] HellaSwag
@@ -33,9 +33,9 @@ Boxes should be checked iff tasks are implemented in the refactor and tested for
 - [x] Winogrande
 - [x] ANLI
 - [x] Hendrycks Ethics (missing some tasks/metrics, see PR 660: <https://github.com/EleutherAI/lm-evaluation-harness/pull/660> for more info)
-- [x] TruthfulQA (mc1) (Lintang)
-- [ ] TruthfulQA (mc2) (Lintang)
-- [ ] TruthfulQA (gen) (Lintang)
+- [x] TruthfulQA (mc1)
+- [x] TruthfulQA (mc2)
+- [x] TruthfulQA (gen)
 - [ ] MuTual
 - [ ] Hendrycks Math (Hailey)
 - [ ] Asdiv
@@ -45,17 +45,17 @@ Boxes should be checked iff tasks are implemented in the refactor and tested for
 - [ ] Translation (WMT) suite (Hailey)
 - [x] Unscramble
 - [x] ~~Pile (perplexity)~~
-- [ ] BLiMP (Lintang)
+- [x] BLiMP
 - [x] ToxiGen
-- [ ] StoryCloze (Lintang)
+- [x] StoryCloze
 - [ ] NaturalQs (Hailey)
 - [x] CrowS-Pairs
 - [x] XCopa
 - [ ] BIG-Bench (Hailey)
-- [ ] XStoryCloze (Lintang)
+- [x] XStoryCloze
 - [x] XWinograd
-- [ ] PAWS-X (Lintang)
-- [ ] XNLI (Lintang)
+- [x] PAWS-X
+- [x] XNLI
 - [ ] MGSM (Lintang)
 - [ ] SCROLLS
 - [x] Babi

lm_eval/tasks/__init__.py

@@ -44,7 +44,7 @@ def check_prompt_config(config):
         prompt_list = prompts.load_prompt_list(
             use_prompt=config["use_prompt"],
             dataset_name=config["dataset_path"],
-            subset_name=config["dataset_name"],
+            subset_name=config["dataset_name"] if "dataset_name" in config else None,
         )
         for idx, prompt_variation in enumerate(prompt_list):
             all_configs.append(
@@ -54,7 +54,9 @@ def check_prompt_config(config):
                     **{
                         "task": "_".join(
                             [
-                                get_task_name_from_config(config),
+                                config["task"]
+                                if "task" in config
+                                else get_task_name_from_config(config),
                                 prompt_variation,
                             ]
                         )
@@ -98,58 +100,8 @@ def include_task_folder(task_dir):
                         )
 
 
-def include_benchmarks(task_dir, benchmark_dir="benchmarks"):
-
-    for root, subdirs, file_list in os.walk(os.path.join(task_dir, benchmark_dir)):
-        if (subdirs == [] or subdirs == ["__pycache__"]) and (len(file_list) > 0):
-            for f in file_list:
-                if f.endswith(".yaml"):
-                    try:
-                        benchmark_path = os.path.join(root, f)
-
-                        with open(benchmark_path, "rb") as file:
-                            yaml_config = yaml.full_load(file)
-
-                        assert "group" in yaml_config
-                        group = yaml_config["group"]
-                        all_task_list = yaml_config["task"]
-                        config_list = [
-                            task for task in all_task_list if type(task) != str
-                        ]
-                        task_list = [
-                            task for task in all_task_list if type(task) == str
-                        ]
-
-                        for task_config in config_list:
-                            var_configs = check_prompt_config(
-                                {
-                                    **task_config,
-                                    **{"group": group},
-                                }
-                            )
-                            for config in var_configs:
-                                register_configurable_task(config)
-
-                        task_names = utils.pattern_match(task_list, ALL_TASKS)
-                        for task in task_names:
-                            if task in TASK_REGISTRY:
-                                if group in GROUP_REGISTRY:
-                                    GROUP_REGISTRY[group].append(task)
-                                else:
-                                    GROUP_REGISTRY[group] = [task]
-                                    ALL_TASKS.add(group)
-                    except Exception as error:
-                        eval_logger.warning(
-                            "Failed to load benchmark in\n"
-                            f"                                 {benchmark_path}\n"
-                            "                                 Benchmark will not be added to registry\n"
-                            f"                                 Error: {error}"
-                        )
-
-
 task_dir = os.path.dirname(os.path.abspath(__file__)) + "/"
 include_task_folder(task_dir)
-include_benchmarks(task_dir)
 
 
 def get_task(task_name, config):

lm_eval/tasks/anli/README.md

-# Task-name
+# ANLI
 
 ### Paper
 
 Title: `Adversarial NLI: A New Benchmark for Natural Language Understanding`
 
-Abstract: `https://arxiv.org/pdf/1910.14599.pdf`
+Paper Link: https://arxiv.org/abs/1910.14599
 
 Adversarial NLI (ANLI) is a dataset collected via an iterative, adversarial
 human-and-model-in-the-loop procedure. It consists of three rounds that progressively
 increase in difficulty and complexity, and each question-answer includes annotator-
 provided explanations.
 
-Homepage: `https://github.com/facebookresearch/anli`
-
+Homepage: https://github.com/facebookresearch/anli
 
 ### Citation
 
@@ -31,13 +30,18 @@ Homepage: `https://github.com/facebookresearch/anli`
 }
 ```
 
-### Subtasks
+### Groups and Tasks
+
+#### Groups
 
-List or describe tasks defined in this folder, and their names here:
+* `anli`: Evaluates `anli_r1`, `anli_r2`, and `anli_r3`
+
+#### Tasks
 * `anli_r1`: The data collected adversarially in the first round.
 * `anli_r2`: The data collected adversarially in the second round, after training on the previous round's data.
 * `anli_r3`: The data collected adversarially in the third round, after training on the previous multiple rounds of data.
 
+
 ### Checklist
 
 For adding novel benchmarks/datasets to the library:

lm_eval/tasks/anli/anli_r1.yaml

 group:
-  - multiple_choice
-  - natural_language_inference
-  - nli
-  - adverserial
+  - anli
 task: anli_r1
 dataset_path: anli
 dataset_name: null

lm_eval/tasks/anli/anli_r2.yaml

-group:
-  - multiple_choice
-  - natural_language_inference
-  - nli
-  - adverserial
+include: anli_r1.yaml
 task: anli_r2
-dataset_path: anli
-dataset_name: null
-output_type: multiple_choice
 training_split: train_r2
 validation_split: dev_r2
 test_split: test_r2
-doc_to_text: "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither?\nAnswer:"
-# True = entailment
-# False = contradiction
-# Neither = neutral
-doc_to_target: "{{['True', 'Neither', 'False'][label]}}"
-doc_to_choice:
-  - "True"
-  - "Neither"
-  - "False"
-should_decontaminate: true
-doc_to_decontamination_query: premise
-metric_list:
-  - metric: acc
-    aggregation: mean
-    higher_is_better: true

lm_eval/tasks/anli/anli_r3.yaml

-group:
-  - multiple_choice
-  - natural_language_inference
-  - nli
-  - adverserial
+include: anli_r1.yaml
 task: anli_r3
-dataset_path: anli
-dataset_name: null
-output_type: multiple_choice
 training_split: train_r3
 validation_split: dev_r3
 test_split: test_r3
-doc_to_text: "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither?\nAnswer:"
-# True = entailment
-# False = contradiction
-# Neither = neutral
-doc_to_target: "{{['True', 'Neither', 'False'][label]}}"
-doc_to_choice:
-  - "True"
-  - "Neither"
-  - "False"
-should_decontaminate: true
-doc_to_decontamination_query: premise
-metric_list:
-  - metric: acc
-    aggregation: mean
-    higher_is_better: true