Function preprocess_function_eval

codes/main.py:221–274

(examples)

    max_target_length = data_args.max_target_length

    def preprocess_function_eval(examples):
        inputs, targets = [], []
        for i in range(len(examples[prompt_column])):
            if examples[prompt_column][i] and examples[response_column][i]:
                query = examples[prompt_column][i]
                history = (
                    examples[history_column][i] if history_column is not None else None
                )
                if 'gsm8k' in data_args.test_file or 'mawps' in data_args.test_file:
                    pre_prompt = "Please analyze and solve the following problem step by step: "
                    # prompt = tokenizer.build_single_message("user", "", message=prefix + pre_prompt + query)
                    # prompt = [tokenizer.get_command("<|user|>")] + tokenizer.encode(
                    #     text=prefix + pre_prompt + query,
                    #     add_special_tokens=False,
                    #     truncation=True,
                    #     max_length=data_args.max_source_length,
                    # )
                    prompt = tokenizer.build_single_message('user', "", prefix + pre_prompt + query)
                    prompt += [tokenizer.get_command("<|assistant|>")]
                else:
                    prompt = tokenizer.build_prompt(query, history)
                inputs.append(prompt)
                targets.append(examples[response_column][i])

        if 'gsm8k' in data_args.test_file or 'mawps' in data_args.test_file:
            model_inputs = tokenizer.batch_encode_plus(
                inputs,
                is_split_into_words=True,
                padding=True,
                truncation=True,
                max_length=data_args.max_source_length
            )
            # pass
        else:
            inputs = [prefix + inp for inp in inputs]
            model_inputs = tokenizer(
                inputs,
                max_length=data_args.max_source_length,
                truncation=True,
                padding=True,
            )

        labels = tokenizer(
            text_target=targets, max_length=max_target_length, truncation=True
        )

        if data_args.ignore_pad_token_for_loss:
            labels["input_ids"] = [
                [(l if l != tokenizer.pad_token_id else -100) for l in label]
                for label in labels["input_ids"]
            ]
        model_inputs["labels"] = labels["input_ids"]

        return model_inputs

    def preprocess_function_train(examples):
        max_seq_length = data_args.max_source_length + data_args.max_target_length + 1