def eval_qa_s2s_epoch()

in longform-qa/lfqa_utils.py [0:0]

• 24 lines of code
• 3 McCabe index (conditional complexity)

def eval_qa_s2s_epoch(model, dataset, tokenizer, args):
    model.eval()
    # make iterator
    train_sampler = SequentialSampler(dataset)
    model_collate_fn = functools.partial(
        make_qa_s2s_batch, tokenizer=tokenizer, max_len=args.max_length, device="cuda:0"
    )
    data_loader = DataLoader(dataset, batch_size=args.batch_size, sampler=train_sampler, collate_fn=model_collate_fn)
    epoch_iterator = tqdm(data_loader, desc="Iteration", disable=True)
    # accumulate loss since last print
    loc_steps = 0
    loc_loss = 0.0
    st_time = time()
    with torch.no_grad():
        for step, batch_inputs in enumerate(epoch_iterator):
            pre_loss = model(**batch_inputs)[0]
            loss = pre_loss.sum() / pre_loss.shape[0]
            loc_loss += loss.item()
            loc_steps += 1
            if step % args.print_freq == 0:
                print(
                    "{:5d} of {:5d} \t L: {:.3f} \t -- {:.3f}".format(
                        step, len(dataset) // args.batch_size, loc_loss / loc_steps, time() - st_time,
                    )
                )
    print("Total \t L: {:.3f} \t -- {:.3f}".format(loc_loss / loc_steps, time() - st_time,))