What are the "input_ids" in this code?

[phalexo]

Trainer

class ModifiedTrainer(Trainer):
def compute_loss(self, model, inputs, return_outputs=False):
return model(
input_ids=inputs["input_ids"],
labels=inputs["labels"],
).loss

def prediction_step(self, model: torch.nn.Module, inputs, prediction_loss_only: bool, ignore_keys = None):
    with torch.no_grad():
        res = model(
            input_ids=inputs["input_ids"].to(model.device),
            labels=inputs["labels"].to(model.device),
        ).loss
    return (res, None, None)

def save_model(self, output_dir=None, _internal_call=False):
    from transformers.trainer import TRAINING_ARGS_NAME

    os.makedirs(output_dir, exist_ok=True)
    torch.save(self.args, os.path.join(output_dir, TRAINING_ARGS_NAME))
    saved_params = {
        k: v.to("cpu") for k, v in self.model.named_parameters() if v.requires_grad
    }
    torch.save(saved_params, os.path.join(output_dir, "adapter_model.bin"))

def data_collator(features: list) -> dict:
len_ids = [len(feature["input_ids"]) for feature in features]
longest = max(len_ids)
input_ids = []
labels_list = []
for ids_l, feature in sorted(zip(len_ids, features), key=lambda x: -x[0]):
ids = feature["input_ids"]
seq_len = feature["seq_len"]
labels = (
[tokenizer.pad_token_id] * (seq_len - 1) + ids[(seq_len - 1) :] + [tokenizer.pad_token_id] * (longest - ids_l)
)
ids = ids + [tokenizer.pad_token_id] * (longest - ids_l)
_ids = torch.LongTensor(ids)
labels_list.append(torch.LongTensor(labels))
input_ids.append(_ids)
input_ids = torch.stack(input_ids)
labels = torch.stack(labels_list)
return {
"input_ids": input_ids,
"labels": labels,
}