#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/Dh9CL8fyG80?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

! pip install datasets transformers[sentencepiece]

from datasets import load_dataset
from transformers import AutoTokenizer, DataCollatorWithPadding

raw_datasets = load_dataset("glue", "mrpc")
checkpoint = "bert-base-cased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)

def tokenize_function(examples):
    return tokenizer(examples["sentence1"], examples["sentence2"], truncation=True)

tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
tokenized_datasets = tokenized_datasets.remove_columns(["sentence1", "sentence2", "idx"])
tokenized_datasets = tokenized_datasets.rename_column("label", "labels")
tokenized_datasets.set_format("torch")

data_collator = DataCollatorWithPadding(tokenizer)

from torch.utils.data import DataLoader

train_dataloader = DataLoader(
  tokenized_datasets["train"], shuffle=True, batch_size=8, collate_fn=data_collator
)
eval_dataloader = DataLoader(
  tokenized_datasets["validation"], batch_size=8, collate_fn=data_collator
)

for batch in train_dataloader:
    break
print({k: v.shape for k, v in batch.items()})

from transformers import AutoModelForSequenceClassification

checkpoint = "bert-base-cased"
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)

outputs = model(**batch)
print(outputs.loss, outputs.logits.shape)

from transformers import AdamW

optimizer = AdamW(model.parameters(), lr=5e-5)

loss = outputs.loss
loss.backward()
optimizer.step()

# Don't forget to zero your gradients once your optimizer step is done!
optimizer.zero_grad()

from transformers import get_scheduler

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
)

import torch

device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model.to(device)
print(device)

optimizer = AdamW(model.parameters(), lr=5e-5)

from tqdm.auto import tqdm

progress_bar = tqdm(range(num_training_steps))

model.train()
for epoch in range(num_epochs):
    for batch in train_dataloader:
        batch = {k: v.to(device) for k, v in batch.items()}
        outputs = model(**batch)
        loss = outputs.loss
        loss.backward()
        
        optimizer.step()
        lr_scheduler.step()
        optimizer.zero_grad()
        progress_bar.update(1)

from datasets import load_metric

metric= load_metric("glue", "mrpc")
model.eval()
for batch in eval_dataloader:
    batch = {k: v.to(device) for k, v in batch.items()}
    with torch.no_grad():
        outputs = model(**batch)
    
    logits = outputs.logits
    predictions = torch.argmax(logits, dim=-1)
    metric.add_batch(predictions=predictions, references=batch["labels"])

metric.compute()