| labels = list(set(data["train"]["label"])) | |
| label2id = {l: i for i, l in enumerate(labels)} | |
| id2label = {i: l for l, i in label2id.items()} | |
| def encode_labels(batch): | |
| batch["label"] = label2id[batch["label"]] | |
| return batch | |
| tokenized = tokenized.map(encode_labels) | |