如何从Huggingface的管道方法中获得损失，以完善模型？

Question

我正试图在QA的拥抱面上使用这个模型。它的代码在链接中：

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-squad2"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

print(res)
>>>
{'score': 0.2117144614458084,
 'start': 59,
 'end': 84,
 'answer': 'gives freedom to the user'}

然而，我不知道如何得到一个损失，所以我可以完善这个模型。我正在查看拥抱脸教程，但除了在链接中使用Trainer方法或其他培训方法(这不是QA)之外，没有看到其他任何东西：

import torch
from transformers import AdamW, AutoTokenizer, AutoModelForSequenceClassification

# Same as before
checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
sequences = [
    "I've been waiting for a HuggingFace course my whole life.",
    "This course is amazing!",
]
batch = tokenizer(sequences, padding=True, truncation=True, return_tensors="pt")

# This is new
batch["labels"] = torch.tensor([1, 1])

optimizer = AdamW(model.parameters())
loss = model(**batch).loss
loss.backward()
optimizer.step()

假设真正的答案是freedom to the user而不是gives freedom to the user

Answer 1

你不必承受损失。Hugginface中有Trainer类，您可以使用它来训练您的模型。它还为拥抱面模型进行了优化，并包含了您可能感兴趣的许多不同类型的深度学习最佳实践。见此处：课程/培训师