Open monisha08041998 opened 4 years ago
for utterance in dialog["utterances"]: history = utterance["history"][-(2*args.max_history+1):] for j, candidate in enumerate(utterance["candidates"][-num_candidates:]): lm_labels = bool(j == num_candidates-1) instance = build_input_from_segments(persona, history, candidate, tokenizer, lm_labels)
Hello, can you teach me how to understand these sentences?
Hi Iam facing error for dataset_name, dataset in personachat.items():
num_candidates = len(dataset[0]["utterances"][0]["candidates"])
in this part of the train.py and also have anyone tried to train it with your own data.Please guide the steps