src/llmtuner/eval/evaluator.py

# Inspired by: https://github.com/hendrycks/test/blob/master/evaluate_flan.py

import inspect
import json
import os
from typing import Any, Dict, List, Optional

import numpy as np
import torch
from datasets import load_dataset
from tqdm import tqdm, trange
from transformers.utils import cached_file

from ..data import get_template_and_fix_tokenizer
from ..extras.constants import CHOICES, SUBJECTS
from ..hparams import get_eval_args
from ..model import dispatch_model, load_model_and_tokenizer
from .template import get_eval_template


class Evaluator:
    def __init__(self, args: Optional[Dict[str, Any]] = None) -> None:
        self.model_args, self.data_args, self.eval_args, finetuning_args = get_eval_args(args)
        self.model, self.tokenizer = load_model_and_tokenizer(self.model_args, finetuning_args)
        self.tokenizer.padding_side = "right"  # avoid overflow issue in batched inference for llama2
        self.model = dispatch_model(self.model)
        self.template = get_template_and_fix_tokenizer(self.data_args.template, self.tokenizer)
        self.eval_template = get_eval_template(self.eval_args.lang)
        self.choice_inputs = [
            self.tokenizer.encode(self.eval_template.prefix + ch, add_special_tokens=False)[-1] for ch in CHOICES
        ]

    @torch.inference_mode()
    def batch_inference(self, batch_input: Dict[str, torch.Tensor]) -> List[str]:
        logits = self.model(**batch_input).logits
        lengths = torch.sum(batch_input["attention_mask"], dim=-1)
        word_probs = torch.stack([logits[i, lengths[i] - 1] for i in range(len(lengths))], dim=0)
        choice_probs = torch.nn.functional.softmax(word_probs[:, self.choice_inputs], dim=-1).detach()
        return [chr(ord("A") + offset.item()) for offset in torch.argmax(choice_probs, dim=-1)]

    def eval(self) -> None:
        mapping = cached_file(
            path_or_repo_id=os.path.join(self.eval_args.task_dir, self.eval_args.task),
            filename="mapping.json",
            cache_dir=self.model_args.cache_dir,
            token=self.model_args.hf_hub_token,
        )

        with open(mapping, "r", encoding="utf-8") as f:
            categorys: Dict[str, Dict[str, str]] = json.load(f)

        category_corrects = {subj: np.array([], dtype="bool") for subj in SUBJECTS}
        pbar = tqdm(categorys.keys(), desc="Processing subjects", position=0)
        results = {}
        for subject in pbar:
            if "trust_remote_code" in inspect.signature(load_dataset).parameters:  # for datasets==2.16.0
                kwargs = {"trust_remote_code": True}
            else:
                kwargs = {}

            dataset = load_dataset(
                path=os.path.join(self.eval_args.task_dir, self.eval_args.task),
                name=subject,
                cache_dir=self.model_args.cache_dir,
                download_mode=self.eval_args.download_mode,
                token=self.model_args.hf_hub_token,
                **kwargs,
            )
            pbar.set_postfix_str(categorys[subject]["name"])
            inputs, outputs, labels = [], [], []
            for i in trange(len(dataset[self.data_args.split]), desc="Formatting batches", position=1, leave=False):
                support_set = (
                    dataset["train"].shuffle().select(range(min(self.eval_args.n_shot, len(dataset["train"]))))
                )
                messages = self.eval_template.format_example(
                    target_data=dataset[self.data_args.split][i],
                    support_set=support_set,
                    subject_name=categorys[subject]["name"],
                )

                input_ids, _ = self.template.encode_oneturn(tokenizer=self.tokenizer, messages=messages)
                inputs.append({"input_ids": input_ids, "attention_mask": [1] * len(input_ids)})
                labels.append(messages[-1]["content"])

            for i in trange(
                0, len(inputs), self.eval_args.batch_size, desc="Predicting batches", position=1, leave=False
            ):
                batch_input = self.tokenizer.pad(
                    inputs[i : i + self.eval_args.batch_size], return_attention_mask=True, return_tensors="pt"
                ).to(self.model.device)
                preds = self.batch_inference(batch_input)
                outputs += preds

            corrects = np.array(outputs) == np.array(labels)
            category_name = categorys[subject]["category"]
            category_corrects[category_name] = np.concatenate([category_corrects[category_name], corrects], axis=0)
            category_corrects["Average"] = np.concatenate([category_corrects["Average"], corrects], axis=0)
            results[subject] = {str(i): outputs[i] for i in range(len(outputs))}

        pbar.close()
        self._save_results(category_corrects, results)

    def _save_results(self, category_corrects: Dict[str, np.ndarray], results: Dict[str, Dict[int, str]]) -> None:
        score_info = "\n".join(
            [
                "{:>15}: {:.2f}".format(category_name, 100 * np.mean(category_correct))
                for category_name, category_correct in category_corrects.items()
                if len(category_correct)
            ]
        )
        print(score_info)
        if self.eval_args.save_dir is not None:
            os.makedirs(self.eval_args.save_dir, exist_ok=False)
            with open(os.path.join(self.eval_args.save_dir, "results.json"), "w", encoding="utf-8", newline="\n") as f:
                json.dump(results, f, indent=2)

            with open(os.path.join(self.eval_args.save_dir, "results.log"), "w", encoding="utf-8", newline="\n") as f:
                f.write(score_info)


if __name__ == "__main__":
    evaluator = Evaluator()
    evaluator.eval()