def loglikelihood_rolling()

in lm_eval/models/neuron_optimum.py [0:0]

• 39 lines of code
• 12 McCabe index (conditional complexity)

    def loglikelihood_rolling(self, requests, disable_tqdm: bool = False):
        loglikelihoods = []

        adaptive_batch_size = None

        for (string,) in tqdm(
            [req.args for req in requests], disable=(disable_tqdm or (self.rank != 0))
        ):
            rolling_token_windows = list(
                map(
                    utils.make_disjoint_window,
                    utils.get_rolling_token_windows(
                        token_list=self.tok_encode(string),
                        prefix_token=self.prefix_token_id,
                        max_seq_len=self.max_length,
                        context_len=1,
                    ),
                )
            )

            # TODO: Right now, we pass single EOT token to the Encoder and the full context to the decoder, in seq2seq case
            rolling_token_windows = [(None,) + x for x in rolling_token_windows]

            pad_amnt = 0
            if self.world_size > 1:
                # We pad out the external document-level iterator so the inner iterator doesn't hang
                mytensor = torch.tensor(len(rolling_token_windows), device=self.device)
                gathered = (
                    self.accelerator.gather(mytensor).cpu().detach().numpy().tolist()
                )

                pad_amnt = max(gathered) - gathered[self.rank]
                if pad_amnt > 0:
                    rolling_token_windows += pad_amnt * [rolling_token_windows[0]]

            string_nll = self._loglikelihood_tokens(
                rolling_token_windows,
                disable_tqdm=True,
                override_bs=adaptive_batch_size,
            )

            if (self.world_size > 1) and (pad_amnt > 0):
                string_nll = [x[0] for x in string_nll[:-pad_amnt]]
            else:
                # discard is_greedy
                string_nll = [x[0] for x in string_nll]

            string_nll = sum(string_nll)
            loglikelihoods.append(string_nll)

        return loglikelihoods