File size: 2,365 Bytes
fa1b8fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import os
os.environ["HF_HOME"] = "/home/jovyan/work/learn-ml/huggingface"
import torch
from torch.utils.data import DataLoader
from transformers import AdamW, AutoTokenizer, AutoModelForSequenceClassification, DataCollatorWithPadding, get_scheduler
from datasets import load_dataset, load_metric
from accelerate import Accelerator
from tqdm.auto import tqdm
checkpoint = 'bert-base-uncased'
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
raw_datasets = load_dataset("glue", "mrpc")
def tokenize_function(example):
return tokenizer(example["sentence1"], example["sentence2"], truncation=True)
tokenized_dataset = raw_datasets.map(tokenize_function, batched=True)
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
samples = tokenized_dataset["train"][:8]
samples = {k: v for k,v in samples.items() if k not in ["idx", "sentence1", "sentence2"]}
print([len(x) for x in samples["input_ids"]])
tokenized_dataset = tokenized_dataset.remove_columns(["sentence1","sentence2","idx"])
tokenized_dataset = tokenized_dataset.rename_column("label", "labels")
tokenized_dataset.set_format("torch")
tokenized_dataset.column_names["train"]
train_dataloader = DataLoader(
tokenized_dataset["train"], shuffle=True, batch_size=8, collate_fn=data_collator,
)
eval_dataloader = DataLoader(
tokenized_dataset["validation"], batch_size=8, collate_fn=data_collator,
)
accelerator = Accelerator()
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
optimizer = AdamW(model.parameters(), lr=3e-5)
train_dataloader, eval_dataloader, model, optimizer = accelerator.prepare(train_dataloader, eval_dataloader, model, optimizer)
num_epochs = 3
num_training_steps = num_epochs * len(train_dataloader)
lr_scheduler = get_scheduler(
"linear",
optimizer=optimizer,
num_warmup_steps=0,
num_training_steps=num_training_steps,
)
print(num_training_steps)
progress_bar = tqdm(range(num_training_steps))
model.train()
for epoch in range(num_epochs):
for batch in train_dataloader:
outputs = model(**batch)
loss = outputs.loss
accelerator.backward(loss)
optimizer.step()
lr_scheduler.step()
optimizer.zero_grad()
progress_bar.update(1)
|