Merge branch 'big-refactor' of...

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

.github/workflows/unit_tests.yml

@@ -43,7 +43,7 @@ jobs:
 #       # mypy turned off for now
 #    - name: Lint with mypy
 #      run: mypy . --ignore-missing-imports --check-untyped-defs --explicit-package-bases --warn-unreachable
-Job 2:
+# Job 2
   testcpu:
     name: CPU Tests
     runs-on: ubuntu-latest

README.md

@@ -23,8 +23,12 @@ Features:
 - Many tasks implemented, 200+ tasks [implemented in the old framework](https://github.com/EleutherAI/lm-evaluation-harness/blob/master/docs/task_table.md) which require porting to the new setup as described in [the new task guide](https://github.com/EleutherAI/lm-evaluation-harness/blob/big-refactor/docs/new_task_guide.md).
 - Support for models loaded via [transformers](https://github.com/huggingface/transformers/) (including quantization via [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ)), [GPT-NeoX](https://github.com/EleutherAI/gpt-neox), and [Megatron-DeepSpeed](https://github.com/microsoft/Megatron-DeepSpeed/), with a flexible tokenization-agnostic interface.
 - Support for commercial APIs including [OpenAI](https://openai.com), [goose.ai](https://goose.ai), and [TextSynth](https://textsynth.com/).
-- Support for evaluation on adapters (e.g. LoRa) supported in [HuggingFace's PEFT library](https://github.com/huggingface/peft).
-- Evaluating with publicly available prompts ensures reproducibility and comparability between papers.
+- Support for evaluation on adapters (e.g. LoRA) supported in [HuggingFace's PEFT library](https://github.com/huggingface/peft).
+- Support for local models and benchmarks.
+- Evaluation with publicly available prompts ensures reproducibility and comparability between papers.
+
+The Language Model Evaluation Harness is the backend for 🤗 Hugging Face's popular [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and is used internally by dozens of companies including NVIDIA, Cohere, Booz Allen Hamilton, and Mosaic ML.
+
 
 ## Install
 

lm_eval/__main__.py

@@ -97,6 +97,12 @@ def parse_eval_args() -> argparse.Namespace:
         default=None,
         help="Additional path to include if there are external tasks to include.",
     )
+    parser.add_argument(
+        "--verbosity",
+        type=str,
+        default="INFO",
+        help="Log error when tasks are not registered.",
+    )
     return parser.parse_args()
 
 
@@ -105,6 +111,7 @@ def cli_evaluate(args: Union[argparse.Namespace, None] = None) -> None:
         # we allow for args to be passed externally, else we parse them ourselves
         args = parse_eval_args()
 
+    eval_logger.setLevel(getattr(logging, f"{args.verbosity}"))
     os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
     if args.limit:

lm_eval/api/task.py

@@ -44,7 +44,7 @@ ALL_OUTPUT_TYPES = [
     "loglikelihood",
     "multiple_choice",
     "loglikelihood_rolling",
-    "greedy_until",
+    "generate_until",
 ]
 
 
@@ -80,7 +80,7 @@ class TaskConfig(dict):
     num_fewshot: int = 0
     # scoring options
     metric_list: list = None
-    output_type: str = "greedy_until"
+    output_type: str = "generate_until"
     generation_kwargs: dict = None
     repeats: int = 1
     filter_list: Union[str, list] = None
@@ -97,11 +97,11 @@ class TaskConfig(dict):
             self.dataset_path = inspect.getfile(import_module(self.dataset_path))
 
         if self.generation_kwargs is not None:
-            if self.output_type != "greedy_until":
+            if self.output_type != "generate_until":
                 eval_logger.warning(
-                    f"[{self.task}] passed `generation_kwargs`, but not using `output_type: greedy_until`!"
+                    f"[{self.task}] passed `generation_kwargs`, but not using `output_type: generate_until`!"
                 )
-                assert self.output_type != "greedy_until"
+                assert self.output_type != "generate_until"
 
             if "temperature" in self.generation_kwargs:
                 self.generation_kwargs["temperature"] = float(
@@ -111,7 +111,7 @@ class TaskConfig(dict):
             if "until" not in self.generation_kwargs:
                 self.generation_kwargs["until"] = [self.fewshot_delimiter]
         else:
-            if self.output_type == "greedy_until":
+            if self.output_type == "generate_until":
                 # ensure that we greedily generate in absence of explicit arguments otherwise
                 self.generation_kwargs = {
                     "until": None
@@ -958,7 +958,7 @@ class ConfigurableTask(Task):
                 )
             return request_list
 
-        elif self.OUTPUT_TYPE == "greedy_until":
+        elif self.OUTPUT_TYPE == "generate_until":
             arguments = (ctx, self.config.generation_kwargs)
 
         return Instance(
@@ -1070,7 +1070,7 @@ class ConfigurableTask(Task):
                 acc_mutual_info = 1.0 if np.argmax(lls_mutual_info) == gold else 0.0
                 result_dict["acc_mutual_info"] = acc_mutual_info
 
-        elif self.OUTPUT_TYPE == "greedy_until":
+        elif self.OUTPUT_TYPE == "generate_until":
             gold = self.doc_to_target(doc)
             result = results[0]
             if self.config.doc_to_choice is not None:
@@ -1134,7 +1134,7 @@ class ConfigurableTask(Task):
         else:
             raise ValueError(
                 f"Passed invalid output_type '{self.OUTPUT_TYPE}' ! Please use one of ",
-                "'loglikelihood', 'loglikelihood_rolling', 'greedy_until' or 'multiple_choice'",
+                "'loglikelihood', 'loglikelihood_rolling', 'generate_until' or 'multiple_choice'",
             )
 
         return result_dict

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: str) -> None:
-    for root, subdirs, file_list in os.walk(task_dir):
-        if (subdirs == [] or "__pycache__" in subdirs) 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)
-
-                        if "prompts" in yaml_config:
-                            continue  # Skip it
-
-                        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:
-                            yaml_dir = os.path.dirname(benchmark_path)
-                            task_config = utils.load_yaml_config(
-                                yaml_config=task_config, yaml_dir=yaml_dir
-                            )
-                            if "use_prompt" in task_config:
-                                if "yaml" in task_config["use_prompt"]:
-                                    task_config["use_prompt"] = os.path.join(
-                                        root, task_config["use_prompt"]
-                                    )
-
-                            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/models/anthropic_llms.py

@@ -138,7 +138,7 @@ please install anthropic via `pip install lm-eval[anthropic]` or `pip install -e
     def _loglikelihood_tokens(self, requests, disable_tqdm: bool = False):
         raise NotImplementedError("No support for logits.")
 
-    def greedy_until(self, requests) -> List[str]:
+    def generate_until(self, requests) -> List[str]:
         if not requests:
             return []
 
@@ -164,7 +164,7 @@ please install anthropic via `pip install lm-eval[anthropic]` or `pip install -e
                 )
                 res.append(response)
 
-                self.cache_hook.add_partial("greedy_until", request, response)
+                self.cache_hook.add_partial("generate_until", request, response)
             except anthropic.APIConnectionError as e:  # type: ignore # noqa: F821
                 eval_logger.critical(f"Server unreachable: {e.__cause__}")
                 break
@@ -179,7 +179,7 @@ please install anthropic via `pip install lm-eval[anthropic]` or `pip install -e
         raise NotImplementedError()
 
     def _model_generate(self, context, max_length, eos_token_id):
-        # Isn't used because we override greedy_until
+        # Isn't used because we override generate_until
         raise NotImplementedError()
 
     def loglikelihood(self, requests):

lm_eval/models/dummy.py

@@ -20,7 +20,7 @@ class DummyLM(LM):
 
         return res
 
-    def greedy_until(self, requests):
+    def generate_until(self, requests):
         res = []
 
         for ctx, _ in requests:

lm_eval/models/huggingface.py

@@ -813,7 +813,7 @@ class HFLM(LM):
 
         return re_ord.get_original(res)
 
-    def greedy_until(self, requests):
+    def generate_until(self, requests):
         res = defaultdict(list)
         re_ords = {}
 
@@ -930,7 +930,7 @@ class HFLM(LM):
                     res[key].append(s)
 
                     self.cache_hook.add_partial(
-                        "greedy_until", (context, gen_kwargs), s
+                        "generate_until", (context, gen_kwargs), s
                     )
                     pbar.update(1)
             # reorder this group of results back to original unsorted form

lm_eval/models/openai_completions.py

@@ -203,7 +203,7 @@ class OpenaiCompletionsLM(LM):
                     self.cache_hook.add_partial("loglikelihood", cache_key, answer)
         return re_ord.get_original(res)
 
-    def greedy_until(self, requests) -> List[str]:
+    def generate_until(self, requests) -> List[str]:
         if not requests:
             return []
         res = []
@@ -260,7 +260,7 @@ class OpenaiCompletionsLM(LM):
 
                 # partial caching
                 self.cache_hook.add_partial(
-                    "greedy_until", (context, {"until": until_}), s
+                    "generate_until", (context, {"until": until_}), s
                 )
 
                 res.append(s)
@@ -271,7 +271,7 @@ class OpenaiCompletionsLM(LM):
         raise NotImplementedError()
 
     def _model_generate(self, context, max_length, eos_token_id):
-        # Isn't used because we override greedy_until
+        # Isn't used because we override generate_until
         raise NotImplementedError()
 
     def loglikelihood_rolling(self, requests) -> List[float]:

lm_eval/models/textsynth.py

@@ -58,7 +58,7 @@ class TextSynthLM(LM):
 
     @property
     def eot_token_id(self):
-        # Isn't used because we override loglikelihood, loglikelihood_rolling and greedy_until
+        # Isn't used because we override loglikelihood, loglikelihood_rolling and generate_until
         raise NotImplementedError()
 
     @property
@@ -72,20 +72,20 @@ class TextSynthLM(LM):
 
     @property
     def batch_size(self):
-        # Isn't used because we override loglikelihood, loglikelihood_rolling and greedy_until
+        # Isn't used because we override loglikelihood, loglikelihood_rolling and generate_until
         raise NotImplementedError()
 
     @property
     def device(self):
-        # Isn't used because we override loglikelihood, loglikelihood_rolling and greedy_until
+        # Isn't used because we override loglikelihood, loglikelihood_rolling and generate_until
         raise NotImplementedError()
 
     def tok_encode(self, string: str):
-        # Isn't used because we override loglikelihood, loglikelihood_rolling and greedy_until
+        # Isn't used because we override loglikelihood, loglikelihood_rolling and generate_until
         raise NotImplementedError()
 
     def tok_decode(self, tokens):
-        # Isn't used because we override loglikelihood, loglikelihood_rolling and greedy_until
+        # Isn't used because we override loglikelihood, loglikelihood_rolling and generate_until
         raise NotImplementedError()
 
     def loglikelihood(self, requests):
@@ -122,7 +122,7 @@ class TextSynthLM(LM):
             "input tokenization support from TextSynth."
         )
 
-    def greedy_until(self, requests):
+    def generate_until(self, requests):
         if not requests:
             return []
 
@@ -146,7 +146,7 @@ class TextSynthLM(LM):
                 s = resp["text"]
                 res.append(s)
 
-                self.cache_hook.add_partial("greedy_until", (inp, request_args), s)
+                self.cache_hook.add_partial("generate_until", (inp, request_args), s)
             else:
                 logger.error(
                     f"The following response does not contain generated `text`. "
@@ -160,5 +160,5 @@ class TextSynthLM(LM):
         raise NotImplementedError()
 
     def _model_generate(self, context, max_length, eos_token_id):
-        # Isn't used because we override greedy_until
+        # Isn't used because we override generate_until
         raise NotImplementedError()

lm_eval/tasks/__init__.py

@@ -4,7 +4,6 @@ from typing import List, Union, Dict
 
 from lm_eval import utils
 from lm_eval import prompts
-from lm_eval.logger import eval_logger
 from lm_eval.api.task import TaskConfig, Task, ConfigurableTask
 from lm_eval.api.registry import (
     register_task,
@@ -14,6 +13,9 @@ from lm_eval.api.registry import (
     ALL_TASKS,
 )
 
+import logging
+
+eval_logger = logging.getLogger('lm-eval')
 
 def register_configurable_task(config: Dict[str, str]) -> int:
     SubClass = type(
@@ -98,7 +100,7 @@ def check_prompt_config(
                             ]
                         )
                     },
-                    **{"output_type": "greedy_until"},
+                    **{"output_type": "generate_until"},
                 }
             )
     else:
@@ -145,7 +147,7 @@ def include_task_folder(task_dir: str, register_task: bool = True) -> None:
                 except Exception as error:
                     import traceback
 
-                    eval_logger.warning(
+                    eval_logger.debug(
                         "Failed to load config in\n"
                         f"                                 {yaml_path}\n"
                         "                                 Config will not be added to registry\n"

lm_eval/tasks/babi/babi.yaml

 task: babi
 dataset_path: Muennighoff/babi
 dataset_name: null
-output_type: greedy_until
+output_type: generate_until
 training_split: train
 validation_split: valid
 test_split: test

lm_eval/tasks/bbh/flan_cot_fewshot/_flan_cot_fewshot_template_yaml

 group: bbh_flan_cot_fewshot
 dataset_path: lukaemon/bbh
-output_type: greedy_until
+output_type: generate_until
 test_split: test
 doc_to_target: "{{target}}"
 metric_list:

lm_eval/tasks/bbh/flan_cot_zeroshot/_flan_cot_zeroshot_template_yaml

 group: bbh_flan_cot_zeroshot
 dataset_path: lukaemon/bbh
-output_type: greedy_until
+output_type: generate_until
 test_split: test
 doc_to_target: "{{target}}"
 metric_list:

lm_eval/tasks/bbh/flan_fewshot/_flan_fewshot_template_yaml

 group: bbh_flan_fewshot
 dataset_path: lukaemon/bbh
-output_type: greedy_until
+output_type: generate_until
 test_split: test
 doc_to_target: "{{target}}"
 metric_list:

lm_eval/tasks/bbh/flan_zeroshot/_flan_zeroshot_template_yaml

 group: bbh_flan_zeroshot
 dataset_path: lukaemon/bbh
-output_type: greedy_until
+output_type: generate_until
 test_split: test
 doc_to_target: "{{target}}"
 metric_list:

lm_eval/tasks/belebele/README.md

@@ -13,7 +13,7 @@ Homepage: https://github.com/facebookresearch/belebele
 
 ```bibtex
 @misc{bandarkar2023belebele,
-      title={The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants}, 
+      title={The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants},
       author={Lucas Bandarkar and Davis Liang and Benjamin Muller and Mikel Artetxe and Satya Narayan Shukla and Donald Husa and Naman Goyal and Abhinandan Krishnan and Luke Zettlemoyer and Madian Khabsa},
       year={2023},
       eprint={2308.16884},

lm_eval/tasks/benchmarks/flan/yaml_templates/cot_template_yaml

 group: flan-cot
-output_type: greedy_until
+output_type: generate_until
 validation_split: validation
 doc_to_target: "{{answer}}"
 metric_list:

lm_eval/tasks/benchmarks/flan/yaml_templates/held_in_template_yaml

-output_type: greedy_until
+output_type: generate_until
 validation_split: validation
 metric_list:
   - metric: exact_match