这就是最后的部分，关于语言建模、多选、问答系统、文本分类、命名实体识别等任务的模型微调，这一块我也是直接看人家笔记本总结的。按照这三个部分，这个库基本就弄熟了
语言建模
主要有这两种方式进行建模
- 因果语言建模：模型必须预测句子中的下一个标记（因此标签与向右移动的输入相同）。为确保模型不作弊，当尝试预测句子中的标记i + 1时，它将获得一个注意掩码，以防止其访问标记i之后的标记。
- 屏蔽语言建模：模型必须预测输入中被屏蔽的一些标记。它仍然可以访问整个句子，因此它可以在屏蔽标记之前和之后使用标记来预测其值。
数据加载
from datasets import load_dataset
datasets = load_dataset('wikitext', 'wikitext-2-raw-v1')
#可以替换成如下的，取消注释即可，只需取消注释以下单元格，然后将路径替换为本地地址即可：
# datasets = load_dataset("text", data_files={"train": path_to_train.txt, "validation": path_to_validation.txt}
datasets["train"][10]
from datasets import ClassLabel
import random
import pandas as pd
from IPython.display import display, HTML
def show_random_elements(dataset, num_examples=10):
assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
picks = []
for _ in range(num_examples):
pick = random.randint(0, len(dataset)-1)
while pick in picks:
pick = random.randint(0, len(dataset)-1)
picks.append(pick)
df = pd.DataFrame(dataset[picks])
for column, typ in dataset.features.items():
if isinstance(typ, ClassLabel):
df[column] = df[column].transform(lambda i: typ.names[i])
display(HTML(df.to_html()))
show_random_elements(datasets["train"])
因果建模
model_path="H:\\code\\Model\\distilgpt2\\"
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
def tokenize_function(examples):
return tokenizer(examples["text"])
tokenized_datasets = datasets.map(tokenize_function, batched=True, num_proc=4, remove_columns=["text"])
tokenized_datasets["train"][1]
# block_size = tokenizer.model_max_length
block_size = 128
#数据预处理
def group_texts(examples):
# Concatenate all texts.
concatenated_examples = {k: sum(examples[k], []) for k in examples.keys()}
total_length = len(concatenated_examples[list(examples.keys())[0]])
# We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
# customize this part to your needs.
total_length = (total_length // block_size) * block_size
# Split by chunks of max_len.
result = {
k: [t[i : i + block_size] for i in range(0, total_length, block_size)]
for k, t in concatenated_examples.items()
}
result["labels"] = result["input_ids"].copy()
return result
lm_datasets = tokenized_datasets.map(
group_texts,
batched=True,
batch_size=1000,
num_proc=4,
)
tokenizer.decode(lm_datasets["train"][1]["input_ids"])
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(model_path)
from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(
"test-clm",
evaluation_strategy = "epoch",
learning_rate=2e-5,
weight_decay=0.01,
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=lm_datasets["train"],
eval_dataset=lm_datasets["validation"],
)
trainer.train()
import math
eval_results = trainer.evaluate()
print(f"Perplexity: {math.exp(eval_results['eval_loss']):.2f}")
掩盖语言建模
model_path="H:\\code\\Model\\distilroberta-base\\"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
tokenized_datasets = datasets.map(tokenize_function, batched=True, num_proc=4, remove_columns=["text"])
lm_datasets = tokenized_datasets.map(
group_texts,
batched=True,
batch_size=1000,
num_proc=4,
)
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained(model_path)
from transformers import DataCollatorForLanguageModeling
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm_probability=0.15)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=lm_datasets["train"],
eval_dataset=lm_datasets["validation"],
data_collator=data_collator,
)
trainer.train()
eval_results = trainer.evaluate()
print(f"Perplexity: {math.exp(eval_results['eval_loss']):.2f}")多项选择任务
model_checkpoint ="H:\\code\\Model\\bert-base-uncased\\"
batch_size = 16
from datasets import load_dataset, load_metric
datasets = load_dataset("swag", "regular")
datasets
datasets["train"][0]
from datasets import ClassLabel
import random
import pandas as pd
from IPython.display import display, HTML
def show_random_elements(dataset, num_examples=10):
assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
picks = []
for _ in range(num_examples):
pick = random.randint(0, len(dataset)-1)
while pick in picks:
pick = random.randint(0, len(dataset)-1)
picks.append(pick)
df = pd.DataFrame(dataset[picks])
for column, typ in dataset.features.items():
if isinstance(typ, ClassLabel):
df[column] = df[column].transform(lambda i: typ.names[i])
display(HTML(df.to_html()))
show_random_elements(datasets["train"])
def show_one(example):
print(f"Context: {example['sent1']}")
print(f" A - {example['sent2']} {example['ending0']}")
print(f" B - {example['sent2']} {example['ending1']}")
print(f" C - {example['sent2']} {example['ending2']}")
print(f" D - {example['sent2']} {example['ending3']}")
print(f"\nGround truth: option {['A', 'B', 'C', 'D'][example['label']]}")
#预处理数据
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, use_fast=True)
ending_names = ["ending0", "ending1", "ending2", "ending3"]
def preprocess_function(examples):
# Repeat each first sentence four times to go with the four possibilities of second sentences.
first_sentences = [[context] * 4 for context in examples["sent1"]]
# Grab all second sentences possible for each context.
question_headers = examples["sent2"]
second_sentences = [[f"{header} {examples[end][i]}" for end in ending_names] for i, header in enumerate(question_headers)]
# Flatten everything
first_sentences = sum(first_sentences, [])
second_sentences = sum(second_sentences, [])
# Tokenize
tokenized_examples = tokenizer(first_sentences, second_sentences, truncation=True)
# Un-flatten
return {k: [v[i:i+4] for i in range(0, len(v), 4)] for k, v in tokenized_examples.items()}
examples = datasets["train"][:5]
features = preprocess_function(examples)
print(len(features["input_ids"]), len(features["input_ids"][0]), [len(x) for x in features["input_ids"][0]])
idx = 3
[tokenizer.decode(features["input_ids"][idx][i]) for i in range(4)]
show_one(datasets["train"][3])
encoded_datasets = datasets.map(preprocess_function, batched=True)
#微调模型
from transformers import AutoModelForMultipleChoice, TrainingArguments, Trainer
model = AutoModelForMultipleChoice.from_pretrained(model_checkpoint)
args = TrainingArguments(
"test-glue",
evaluation_strategy = "epoch",
learning_rate=5e-5,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
num_train_epochs=3,
weight_decay=0.01,
)
from dataclasses import dataclass
from transformers.tokenization_utils_base import PreTrainedTokenizerBase, PaddingStrategy
from typing import Optional, Union
import torch
@dataclass
class DataCollatorForMultipleChoice:
"""
Data collator that will dynamically pad the inputs for multiple choice received.
"""
tokenizer: PreTrainedTokenizerBase
padding: Union[bool, str, PaddingStrategy] = True
max_length: Optional[int] = None
pad_to_multiple_of: Optional[int] = None
def __call__(self, features):
label_name = "label" if "label" in features[0].keys() else "labels"
labels = [feature.pop(label_name) for feature in features]
batch_size = len(features)
num_choices = len(features[0]["input_ids"])
flattened_features = [[{k: v[i] for k, v in feature.items()} for i in range(num_choices)] for feature in features]
flattened_features = sum(flattened_features, [])
batch = self.tokenizer.pad(
flattened_features,
padding=self.padding,
max_length=self.max_length,
pad_to_multiple_of=self.pad_to_multiple_of,
return_tensors="pt",
)
# Un-flatten
batch = {k: v.view(batch_size, num_choices, -1) for k, v in batch.items()}
# Add back labels
batch["labels"] = torch.tensor(labels, dtype=torch.int64)
return batch
accepted_keys = ["input_ids", "attention_mask", "label"]
features = [{k: v for k, v in encoded_datasets["train"][i].items() if k in accepted_keys} for i in range(10)]
batch = DataCollatorForMultipleChoice(tokenizer)(features)
import numpy as np
def compute_metrics(eval_predictions):
predictions, label_ids = eval_predictions
preds = np.argmax(predictions, axis=1)
return {"accuracy": (preds == label_ids).astype(np.float32).mean().item()}
trainer = Trainer(
model,
args,
train_dataset=encoded_datasets["train"],
eval_dataset=encoded_datasets["validation"],
tokenizer=tokenizer,
data_collator=DataCollatorForMultipleChoice(tokenizer),
compute_metrics=compute_metrics,
)
trainer.train()
问答系统
# This flag is the difference between SQUAD v1 or 2 (if you're using another dataset, it indicates if impossible
# answers are allowed or not).
squad_v2 = False
model_checkpoint="H:\\code\\Model\\distilbert-base-cased\\"
batch_size = 16
from datasets import load_dataset, load_metric
datasets = load_dataset("squad_v2" if squad_v2 else "squad")
datasets
from datasets import ClassLabel, Sequence
import random
import pandas as pd
from IPython.display import display, HTML
def show_random_elements(dataset, num_examples=10):
assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
picks = []
for _ in range(num_examples):
pick = random.randint(0, len(dataset)-1)
while pick in picks:
pick = random.randint(0, len(dataset)-1)
picks.append(pick)
df = pd.DataFrame(dataset[picks])
for column, typ in dataset.features.items():
if isinstance(typ, ClassLabel):
df[column] = df[column].transform(lambda i: typ.names[i])
elif isinstance(typ, Sequence) and isinstance(typ.feature, ClassLabel):
df[column] = df[column].transform(lambda x: [typ.feature.names[i] for i in x])
display(HTML(df.to_html()))
show_random_elements(datasets["train"])
#预处理训练数据
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
import transformers
assert isinstance(tokenizer, transformers.PreTrainedTokenizerFast)
tokenizer("What is your name?", "My name is Sylvain.")
max_length = 384 # The maximum length of a feature (question and context)
doc_stride = 128 # The authorized overlap between two part of the context when splitting it is needed.
for i, example in enumerate(datasets["train"]):
if len(tokenizer(example["question"], example["context"])["input_ids"]) > 384:
break
example = datasets["train"][i]
len(tokenizer(example["question"], example["context"])["input_ids"])
len(tokenizer(example["question"], example["context"], max_length=max_length, truncation="only_second")["input_ids"])
tokenized_example = tokenizer(
example["question"],
example["context"],
max_length=max_length,
truncation="only_second",
return_overflowing_tokens=True,
return_offsets_mapping=True,
stride=doc_stride
)
print(tokenized_example["offset_mapping"][0][:100])
first_token_id = tokenized_example["input_ids"][0][1]
offsets = tokenized_example["offset_mapping"][0][1]
print(tokenizer.convert_ids_to_tokens([first_token_id])[0], example["question"][offsets[0]:offsets[1]])
sequence_ids = tokenized_example.sequence_ids()
print(sequence_ids)
answers = example["answers"]
start_char = answers["answer_start"][0]
end_char = start_char + len(answers["text"][0])
# Start token index of the current span in the text.
token_start_index = 0
while sequence_ids[token_start_index] != 1:
token_start_index += 1
# End token index of the current span in the text.
token_end_index = len(tokenized_example["input_ids"][0]) - 1
while sequence_ids[token_end_index] != 1:
token_end_index -= 1
# Detect if the answer is out of the span (in which case this feature is labeled with the CLS index).
offsets = tokenized_example["offset_mapping"][0]
if (offsets[token_start_index][0] <= start_char and offsets[token_end_index][1] >= end_char):
# Move the token_start_index and token_end_index to the two ends of the answer.
# Note: we could go after the last offset if the answer is the last word (edge case).
while token_start_index < len(offsets) and offsets[token_start_index][0] <= start_char:
token_start_index += 1
start_position = token_start_index - 1
while offsets[token_end_index][1] >= end_char:
token_end_index -= 1
end_position = token_end_index + 1
print(start_position, end_position)
else:
print("The answer is not in this feature.")
print(tokenizer.decode(tokenized_example["input_ids"][0][start_position: end_position+1]))
print(answers["text"][0])
pad_on_right = tokenizer.padding_side == "right"
def prepare_train_features(examples):
# Tokenize our examples with truncation and padding, but keep the overflows using a stride. This results
# in one example possible giving several features when a context is long, each of those features having a
# context that overlaps a bit the context of the previous feature.
tokenized_examples = tokenizer(
examples["question" if pad_on_right else "context"],
examples["context" if pad_on_right else "question"],
truncation="only_second" if pad_on_right else "only_first",
max_length=max_length,
stride=doc_stride,
return_overflowing_tokens=True,
return_offsets_mapping=True,
padding="max_length",
)
# Since one example might give us several features if it has a long context, we need a map from a feature to
# its corresponding example. This key gives us just that.
sample_mapping = tokenized_examples.pop("overflow_to_sample_mapping")
# The offset mappings will give us a map from token to character position in the original context. This will
# help us compute the start_positions and end_positions.
offset_mapping = tokenized_examples.pop("offset_mapping")
# Let's label those examples!
tokenized_examples["start_positions"] = []
tokenized_examples["end_positions"] = []
for i, offsets in enumerate(offset_mapping):
# We will label impossible answers with the index of the CLS token.
input_ids = tokenized_examples["input_ids"][i]
cls_index = input_ids.index(tokenizer.cls_token_id)
# Grab the sequence corresponding to that example (to know what is the context and what is the question).
sequence_ids = tokenized_examples.sequence_ids(i)
# One example can give several spans, this is the index of the example containing this span of text.
sample_index = sample_mapping[i]
answers = examples["answers"][sample_index]
# If no answers are given, set the cls_index as answer.
if len(answers["answer_start"]) == 0:
tokenized_examples["start_positions"].append(cls_index)
tokenized_examples["end_positions"].append(cls_index)
else:
# Start/end character index of the answer in the text.
start_char = answers["answer_start"][0]
end_char = start_char + len(answers["text"][0])
# Start token index of the current span in the text.
token_start_index = 0
while sequence_ids[token_start_index] != (1 if pad_on_right else 0):
token_start_index += 1
# End token index of the current span in the text.
token_end_index = len(input_ids) - 1
while sequence_ids[token_end_index] != (1 if pad_on_right else 0):
token_end_index -= 1
# Detect if the answer is out of the span (in which case this feature is labeled with the CLS index).
if not (offsets[token_start_index][0] <= start_char and offsets[token_end_index][1] >= end_char):
tokenized_examples["start_positions"].append(cls_index)
tokenized_examples["end_positions"].append(cls_index)
else:
# Otherwise move the token_start_index and token_end_index to the two ends of the answer.
# Note: we could go after the last offset if the answer is the last word (edge case).
while token_start_index < len(offsets) and offsets[token_start_index][0] <= start_char:
token_start_index += 1
tokenized_examples["start_positions"].append(token_start_index - 1)
while offsets[token_end_index][1] >= end_char:
token_end_index -= 1
tokenized_examples["end_positions"].append(token_end_index + 1)
return tokenized_examples
features = prepare_train_features(datasets['train'][:5])
tokenized_datasets = datasets.map(prepare_train_features, batched=True, remove_columns=datasets["train"].column_names)
#微调模型
from transformers import AutoModelForQuestionAnswering, TrainingArguments, Trainer
model = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)
args = TrainingArguments(
f"test-squad",
evaluation_strategy = "epoch",
learning_rate=2e-5,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
num_train_epochs=3,
weight_decay=0.01,
)
from transformers import default_data_collator
data_collator = default_data_collator
trainer = Trainer(
model,
args,
train_dataset=tokenized_datasets["train"],
eval_dataset=tokenized_datasets["validation"],
data_collator=data_collator,
tokenizer=tokenizer,
)
trainer.train()
trainer.save_model("test-squad-trained")
#评估
import torch
for batch in trainer.get_eval_dataloader():
break
batch = {k: v.to(trainer.args.device) for k, v in batch.items()}
with torch.no_grad():
output = trainer.model(**batch)
output.keys()
output.start_logits.shape, output.end_logits.shape
output.start_logits.argmax(dim=-1), output.end_logits.argmax(dim=-1)
n_best_size = 20
import numpy as np
start_logits = output.start_logits[0].cpu().numpy()
end_logits = output.end_logits[0].cpu().numpy()
# Gather the indices the best start/end logits:
start_indexes = np.argsort(start_logits)[-1 : -n_best_size - 1 : -1].tolist()
end_indexes = np.argsort(end_logits)[-1 : -n_best_size - 1 : -1].tolist()
valid_answers = []
for start_index in start_indexes:
for end_index in end_indexes:
if start_index <= end_index: # We need to refine that test to check the answer is inside the context
valid_answers.append(
{
"score": start_logits[start_index] + end_logits[end_index],
"text": "" # We need to find a way to get back the original substring corresponding to the answer in the context
}
)
def prepare_validation_features(examples):
# Tokenize our examples with truncation and maybe padding, but keep the overflows using a stride. This results
# in one example possible giving several features when a context is long, each of those features having a
# context that overlaps a bit the context of the previous feature.
tokenized_examples = tokenizer(
examples["question" if pad_on_right else "context"],
examples["context" if pad_on_right else "question"],
truncation="only_second" if pad_on_right else "only_first",
max_length=max_length,
stride=doc_stride,
return_overflowing_tokens=True,
return_offsets_mapping=True,
padding="max_length",
)
# Since one example might give us several features if it has a long context, we need a map from a feature to
# its corresponding example. This key gives us just that.
sample_mapping = tokenized_examples.pop("overflow_to_sample_mapping")
# We keep the example_id that gave us this feature and we will store the offset mappings.
tokenized_examples["example_id"] = []
for i in range(len(tokenized_examples["input_ids"])):
# Grab the sequence corresponding to that example (to know what is the context and what is the question).
sequence_ids = tokenized_examples.sequence_ids(i)
context_index = 1 if pad_on_right else 0
# One example can give several spans, this is the index of the example containing this span of text.
sample_index = sample_mapping[i]
tokenized_examples["example_id"].append(examples["id"][sample_index])
# Set to None the offset_mapping that are not part of the context so it's easy to determine if a token
# position is part of the context or not.
tokenized_examples["offset_mapping"][i] = [
(o if sequence_ids[k] == context_index else None)
for k, o in enumerate(tokenized_examples["offset_mapping"][i])
]
return tokenized_examples
validation_features = datasets["validation"].map(
prepare_validation_features,
batched=True,
remove_columns=datasets["validation"].column_names
)
raw_predictions = trainer.predict(validation_features)
validation_features.set_format(type=validation_features.format["type"], columns=list(validation_features.features.keys()))
max_answer_length = 30
start_logits = output.start_logits[0].cpu().numpy()
end_logits = output.end_logits[0].cpu().numpy()
offset_mapping = validation_features[0]["offset_mapping"]
# The first feature comes from the first example. For the more general case, we will need to be match the example_id to
# an example index
context = datasets["validation"][0]["context"]
# Gather the indices the best start/end logits:
start_indexes = np.argsort(start_logits)[-1 : -n_best_size - 1 : -1].tolist()
end_indexes = np.argsort(end_logits)[-1 : -n_best_size - 1 : -1].tolist()
valid_answers = []
for start_index in start_indexes:
for end_index in end_indexes:
# Don't consider out-of-scope answers, either because the indices are out of bounds or correspond
# to part of the input_ids that are not in the context.
if (
start_index >= len(offset_mapping)
or end_index >= len(offset_mapping)
or offset_mapping[start_index] is None
or offset_mapping[end_index] is None
):
continue
# Don't consider answers with a length that is either < 0 or > max_answer_length.
if end_index < start_index or end_index - start_index + 1 > max_answer_length:
continue
if start_index <= end_index: # We need to refine that test to check the answer is inside the context
start_char = offset_mapping[start_index][0]
end_char = offset_mapping[end_index][1]
valid_answers.append(
{
"score": start_logits[start_index] + end_logits[end_index],
"text": context[start_char: end_char]
}
)
valid_answers = sorted(valid_answers, key=lambda x: x["score"], reverse=True)[:n_best_size]
valid_answers
import collections
examples = datasets["validation"]
features = validation_features
example_id_to_index = {k: i for i, k in enumerate(examples["id"])}
features_per_example = collections.defaultdict(list)
for i, feature in enumerate(features):
features_per_example[example_id_to_index[feature["example_id"]]].append(i)
from tqdm.auto import tqdm
def postprocess_qa_predictions(examples, features, raw_predictions, n_best_size = 20, max_answer_length = 30):
all_start_logits, all_end_logits = raw_predictions
# Build a map example to its corresponding features.
example_id_to_index = {k: i for i, k in enumerate(examples["id"])}
features_per_example = collections.defaultdict(list)
for i, feature in enumerate(features):
features_per_example[example_id_to_index[feature["example_id"]]].append(i)
# The dictionaries we have to fill.
predictions = collections.OrderedDict()
# Logging.
print(f"Post-processing {len(examples)} example predictions split into {len(features)} features.")
# Let's loop over all the examples!
for example_index, example in enumerate(tqdm(examples)):
# Those are the indices of the features associated to the current example.
feature_indices = features_per_example[example_index]
min_null_score = None # Only used if squad_v2 is True.
valid_answers = []
context = example["context"]
# Looping through all the features associated to the current example.
for feature_index in feature_indices:
# We grab the predictions of the model for this feature.
start_logits = all_start_logits[feature_index]
end_logits = all_end_logits[feature_index]
# This is what will allow us to map some the positions in our logits to span of texts in the original
# context.
offset_mapping = features[feature_index]["offset_mapping"]
# Update minimum null prediction.
cls_index = features[feature_index]["input_ids"].index(tokenizer.cls_token_id)
feature_null_score = start_logits[cls_index] + end_logits[cls_index]
if min_null_score is None or min_null_score < feature_null_score:
min_null_score = feature_null_score
# Go through all possibilities for the `n_best_size` greater start and end logits.
start_indexes = np.argsort(start_logits)[-1 : -n_best_size - 1 : -1].tolist()
end_indexes = np.argsort(end_logits)[-1 : -n_best_size - 1 : -1].tolist()
for start_index in start_indexes:
for end_index in end_indexes:
# Don't consider out-of-scope answers, either because the indices are out of bounds or correspond
# to part of the input_ids that are not in the context.
if (
start_index >= len(offset_mapping)
or end_index >= len(offset_mapping)
or offset_mapping[start_index] is None
or offset_mapping[end_index] is None
):
continue
# Don't consider answers with a length that is either < 0 or > max_answer_length.
if end_index < start_index or end_index - start_index + 1 > max_answer_length:
continue
start_char = offset_mapping[start_index][0]
end_char = offset_mapping[end_index][1]
valid_answers.append(
{
"score": start_logits[start_index] + end_logits[end_index],
"text": context[start_char: end_char]
}
)
if len(valid_answers) > 0:
best_answer = sorted(valid_answers, key=lambda x: x["score"], reverse=True)[0]
else:
# In the very rare edge case we have not a single non-null prediction, we create a fake prediction to avoid
# failure.
best_answer = {"text": "", "score": 0.0}
# Let's pick our final answer: the best one or the null answer (only for squad_v2)
if not squad_v2:
predictions[example["id"]] = best_answer["text"]
else:
answer = best_answer["text"] if best_answer["score"] > min_null_score else ""
predictions[example["id"]] = answer
return predictions
final_predictions = postprocess_qa_predictions(datasets["validation"], validation_features, raw_predictions.predictions)
metric = load_metric("squad_v2" if squad_v2 else "squad")
if squad_v2:
formatted_predictions = [{"id": k, "prediction_text": v, "no_answer_probability": 0.0} for k, v in predictions.items()]
else:
formatted_predictions = [{"id": k, "prediction_text": v} for k, v in final_predictions.items()]
references = [{"id": ex["id"], "answers": ex["answers"]} for ex in datasets["validation"]]
metric.compute(predictions=formatted_predictions, references=references)文本分类
GLUE_TASKS = ["cola", "mnli", "mnli-mm", "mrpc", "qnli", "qqp", "rte", "sst2", "stsb", "wnli"]
task = "cola"
model_checkpoint="H:\\code\\Model\\distilbert-base-cased\\"
batch_size = 16
from datasets import load_dataset, load_metric
actual_task = "mnli" if task == "mnli-mm" else task
dataset = load_dataset("glue", actual_task)
metric = load_metric('glue', actual_task)
import datasets
import random
import pandas as pd
from IPython.display import display, HTML
def show_random_elements(dataset, num_examples=10):
assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
picks = []
for _ in range(num_examples):
pick = random.randint(0, len(dataset)-1)
while pick in picks:
pick = random.randint(0, len(dataset)-1)
picks.append(pick)
df = pd.DataFrame(dataset[picks])
for column, typ in dataset.features.items():
if isinstance(typ, datasets.ClassLabel):
df[column] = df[column].transform(lambda i: typ.names[i])
display(HTML(df.to_html()))
show_random_elements(dataset["train"])
import numpy as np
fake_preds = np.random.randint(0, 2, size=(64,))
fake_labels = np.random.randint(0, 2, size=(64,))
metric.compute(predictions=fake_preds, references=fake_labels)
#预处理数据
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, use_fast=True)
tokenizer("Hello, this one sentence!", "And this sentence goes with it.")
task_to_keys = {
"cola": ("sentence", None),
"mnli": ("premise", "hypothesis"),
"mnli-mm": ("premise", "hypothesis"),
"mrpc": ("sentence1", "sentence2"),
"qnli": ("question", "sentence"),
"qqp": ("question1", "question2"),
"rte": ("sentence1", "sentence2"),
"sst2": ("sentence", None),
"stsb": ("sentence1", "sentence2"),
"wnli": ("sentence1", "sentence2"),
}
sentence1_key, sentence2_key = task_to_keys[task]
if sentence2_key is None:
print(f"Sentence: {dataset['train'][0][sentence1_key]}")
else:
print(f"Sentence 1: {dataset['train'][0][sentence1_key]}")
print(f"Sentence 2: {dataset['train'][0][sentence2_key]}")
def preprocess_function(examples):
if sentence2_key is None:
return tokenizer(examples[sentence1_key], truncation=True)
return tokenizer(examples[sentence1_key], examples[sentence2_key], truncation=True)
preprocess_function(dataset['train'][:5])
encoded_dataset = dataset.map(preprocess_function, batched=True)
#微调模型
from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
num_labels = 3 if task.startswith("mnli") else 1 if task=="stsb" else 2
model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint, num_labels=num_labels)
metric_name = "pearson" if task == "stsb" else "matthews_correlation" if task == "cola" else "accuracy"
args = TrainingArguments(
"test-glue",
evaluation_strategy = "epoch",
learning_rate=2e-5,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
num_train_epochs=5,
weight_decay=0.01,
load_best_model_at_end=True,
metric_for_best_model=metric_name,
)
def compute_metrics(eval_pred):
predictions, labels = eval_pred
if task != "stsb":
predictions = np.argmax(predictions, axis=1)
else:
predictions = predictions[:, 0]
return metric.compute(predictions=predictions, references=labels)
validation_key = "validation_mismatched" if task == "mnli-mm" else "validation_matched" if task == "mnli" else "validation"
trainer = Trainer(
model,
args,
train_dataset=encoded_dataset["train"],
eval_dataset=encoded_dataset[validation_key],
tokenizer=tokenizer,
compute_metrics=compute_metrics
)
trainer.train()
trainer.evaluate()
#超参数搜索
def model_init():
return AutoModelForSequenceClassification.from_pretrained(model_checkpoint, num_labels=num_labels)
trainer = Trainer(
model_init=model_init,
args=args,
train_dataset=encoded_dataset["train"],
eval_dataset=encoded_dataset[validation_key],
tokenizer=tokenizer,
compute_metrics=compute_metrics
)
best_run = trainer.hyperparameter_search(n_trials=10, direction="maximize")
best_run
for n, v in best_run.hyperparameters.items():
setattr(trainer.args, n, v)
trainer.train()
命名实体识别
task = "ner" # Should be one of "ner", "pos" or "chunk"
model_checkpoint="H:\\code\\Model\\distilbert-base-cased\\"
batch_size = 16
from datasets import load_dataset, load_metric
datasets = load_dataset("conll2003")
datasets
label_list = datasets["train"].features[f"{task}_tags"].feature.names
label_list
from datasets import ClassLabel, Sequence
import random
import pandas as pd
from IPython.display import display, HTML
def show_random_elements(dataset, num_examples=10):
assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
picks = []
for _ in range(num_examples):
pick = random.randint(0, len(dataset)-1)
while pick in picks:
pick = random.randint(0, len(dataset)-1)
picks.append(pick)
df = pd.DataFrame(dataset[picks])
for column, typ in dataset.features.items():
if isinstance(typ, ClassLabel):
df[column] = df[column].transform(lambda i: typ.names[i])
elif isinstance(typ, Sequence) and isinstance(typ.feature, ClassLabel):
df[column] = df[column].transform(lambda x: [typ.feature.names[i] for i in x])
display(HTML(df.to_html()))
show_random_elements(datasets["train"])
#预处理数据
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
import transformers
assert isinstance(tokenizer, transformers.PreTrainedTokenizerFast)
tokenizer("Hello, this is one sentence!")
example = datasets["train"][4]
print(example["tokens"])
tokenized_input = tokenizer(example["tokens"], is_split_into_words=True)
tokens = tokenizer.convert_ids_to_tokens(tokenized_input["input_ids"])
print(tokens)
word_ids = tokenized_input.word_ids()
aligned_labels = [-100 if i is None else example[f"{task}_tags"][i] for i in word_ids]
print(len(aligned_labels), len(tokenized_input["input_ids"]))
label_all_tokens = True
def tokenize_and_align_labels(examples):
tokenized_inputs = tokenizer(examples["tokens"], truncation=True, is_split_into_words=True)
labels = []
for i, label in enumerate(examples[f"{task}_tags"]):
word_ids = tokenized_inputs.word_ids(batch_index=i)
previous_word_idx = None
label_ids = []
for word_idx in word_ids:
# Special tokens have a word id that is None. We set the label to -100 so they are automatically
# ignored in the loss function.
if word_idx is None:
label_ids.append(-100)
# We set the label for the first token of each word.
elif word_idx != previous_word_idx:
label_ids.append(label[word_idx])
# For the other tokens in a word, we set the label to either the current label or -100, depending on
# the label_all_tokens flag.
else:
label_ids.append(label[word_idx] if label_all_tokens else -100)
previous_word_idx = word_idx
labels.append(label_ids)
tokenized_inputs["labels"] = labels
return tokenized_inputs
tokenize_and_align_labels(datasets['train'][:5])
tokenized_datasets = datasets.map(tokenize_and_align_labels, batched=True)
#微调模型
from transformers import AutoModelForTokenClassification, TrainingArguments, Trainer
model = AutoModelForTokenClassification.from_pretrained(model_checkpoint, num_labels=len(label_list))
args = TrainingArguments(
f"test-{task}",
evaluation_strategy = "epoch",
learning_rate=2e-5,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
num_train_epochs=3,
weight_decay=0.01,
)
from transformers import DataCollatorForTokenClassification
data_collator = DataCollatorForTokenClassification(tokenizer)
metric = load_metric("seqeval")
labels = [label_list[i] for i in example[f"{task}_tags"]]
metric.compute(predictions=[labels], references=[labels])
import numpy as np
def compute_metrics(p):
predictions, labels = p
predictions = np.argmax(predictions, axis=2)
# Remove ignored index (special tokens)
true_predictions = [
[label_list[p] for (p, l) in zip(prediction, label) if l != -100]
for prediction, label in zip(predictions, labels)
]
true_labels = [
[label_list[l] for (p, l) in zip(prediction, label) if l != -100]
for prediction, label in zip(predictions, labels)
]
results = metric.compute(predictions=true_predictions, references=true_labels)
return {
"precision": results["overall_precision"],
"recall": results["overall_recall"],
"f1": results["overall_f1"],
"accuracy": results["overall_accuracy"],
}
trainer = Trainer(
model,
args,
train_dataset=tokenized_datasets["train"],
eval_dataset=tokenized_datasets["validation"],
data_collator=data_collator,
tokenizer=tokenizer,
compute_metrics=compute_metrics
)
trainer.train()
trainer.evaluate()
predictions, labels, _ = trainer.predict(tokenized_datasets["validation"])
predictions = np.argmax(predictions, axis=2)
# Remove ignored index (special tokens)
true_predictions = [
[label_list[p] for (p, l) in zip(prediction, label) if l != -100]
for prediction, label in zip(predictions, labels)
]
true_labels = [
[label_list[l] for (p, l) in zip(prediction, label) if l != -100]
for prediction, label in zip(predictions, labels)
]
results = metric.compute(predictions=true_predictions, references=true_labels)
results
408
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
