!pip install datasets evaluate transformers[sentencepiece]
!pip install accelerate
# To run the training on TPU, you will need to uncomment the following line:
# !pip install cloud-tpu-client==0.10 torch==1.9.0 https://storage.googleapis.com/tpu-pytorch/wheels/torch_xla-1.9-cp37-cp37m-linux_x86_64.whl
!apt install git-lfs

!git config --global user.email "you@example.com"
!git config --global user.name "Your Name"

from huggingface_hub import notebook_login

notebook_login()

from datasets import load_dataset

raw_datasets = load_dataset("squad")

raw_datasets

print("Context: ", raw_datasets["train"][0]["context"])
print("Question: ", raw_datasets["train"][0]["question"])
print("Answer: ", raw_datasets["train"][0]["answers"])

raw_datasets["train"].filter(lambda x: len(x["answers"]["text"]) != 1)

print(raw_datasets["validation"][0]["answers"])
print(raw_datasets["validation"][2]["answers"])

print(raw_datasets["validation"][2]["context"])
print(raw_datasets["validation"][2]["question"])

from transformers import AutoTokenizer

model_checkpoint = "bert-base-cased"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

tokenizer.is_fast

context = raw_datasets["train"][0]["context"]
question = raw_datasets["train"][0]["question"]

inputs = tokenizer(question, context)
tokenizer.decode(inputs["input_ids"])

inputs = tokenizer(
    question,
    context,
    max_length=100,
    truncation="only_second",
    stride=50,
    return_overflowing_tokens=True,
)

for ids in inputs["input_ids"]:
    print(tokenizer.decode(ids))

inputs = tokenizer(
    question,
    context,
    max_length=100,
    truncation="only_second",
    stride=50,
    return_overflowing_tokens=True,
    return_offsets_mapping=True,
)
inputs.keys()

inputs["overflow_to_sample_mapping"]

inputs = tokenizer(
    raw_datasets["train"][2:6]["question"],
    raw_datasets["train"][2:6]["context"],
    max_length=100,
    truncation="only_second",
    stride=50,
    return_overflowing_tokens=True,
    return_offsets_mapping=True,
)

print(f"The 4 examples gave {len(inputs['input_ids'])} features.")
print(f"Here is where each comes from: {inputs['overflow_to_sample_mapping']}.")

answers = raw_datasets["train"][2:6]["answers"]
start_positions = []
end_positions = []

for i, offset in enumerate(inputs["offset_mapping"]):
    sample_idx = inputs["overflow_to_sample_mapping"][i]
    answer = answers[sample_idx]
    start_char = answer["answer_start"][0]
    end_char = answer["answer_start"][0] + len(answer["text"][0])
    sequence_ids = inputs.sequence_ids(i)

    # Find the start and end of the context
    idx = 0
    while sequence_ids[idx] != 1:
        idx += 1
    context_start = idx
    while sequence_ids[idx] == 1:
        idx += 1
    context_end = idx - 1

    # If the answer is not fully inside the context, label is (0, 0)
    if offset[context_start][0] > start_char or offset[context_end][1] < end_char:
        start_positions.append(0)
        end_positions.append(0)
    else:
        # Otherwise it's the start and end token positions
        idx = context_start
        while idx <= context_end and offset[idx][0] <= start_char:
            idx += 1
        start_positions.append(idx - 1)

        idx = context_end
        while idx >= context_start and offset[idx][1] >= end_char:
            idx -= 1
        end_positions.append(idx + 1)

start_positions, end_positions

idx = 0
sample_idx = inputs["overflow_to_sample_mapping"][idx]
answer = answers[sample_idx]["text"][0]

start = start_positions[idx]
end = end_positions[idx]
labeled_answer = tokenizer.decode(inputs["input_ids"][idx][start : end + 1])

print(f"Theoretical answer: {answer}, labels give: {labeled_answer}")

idx = 4
sample_idx = inputs["overflow_to_sample_mapping"][idx]
answer = answers[sample_idx]["text"][0]

decoded_example = tokenizer.decode(inputs["input_ids"][idx])
print(f"Theoretical answer: {answer}, decoded example: {decoded_example}")

max_length = 384
stride = 128


def preprocess_training_examples(examples):
    questions = [q.strip() for q in examples["question"]]
    inputs = tokenizer(
        questions,
        examples["context"],
        max_length=max_length,
        truncation="only_second",
        stride=stride,
        return_overflowing_tokens=True,
        return_offsets_mapping=True,
        padding="max_length",
    )

    offset_mapping = inputs.pop("offset_mapping")
    sample_map = inputs.pop("overflow_to_sample_mapping")
    answers = examples["answers"]
    start_positions = []
    end_positions = []

    for i, offset in enumerate(offset_mapping):
        sample_idx = sample_map[i]
        answer = answers[sample_idx]
        start_char = answer["answer_start"][0]
        end_char = answer["answer_start"][0] + len(answer["text"][0])
        sequence_ids = inputs.sequence_ids(i)

        # Find the start and end of the context
        idx = 0
        while sequence_ids[idx] != 1:
            idx += 1
        context_start = idx
        while sequence_ids[idx] == 1:
            idx += 1
        context_end = idx - 1

        # If the answer is not fully inside the context, label is (0, 0)
        if offset[context_start][0] > start_char or offset[context_end][1] < end_char:
            start_positions.append(0)
            end_positions.append(0)
        else:
            # Otherwise it's the start and end token positions
            idx = context_start
            while idx <= context_end and offset[idx][0] <= start_char:
                idx += 1
            start_positions.append(idx - 1)

            idx = context_end
            while idx >= context_start and offset[idx][1] >= end_char:
                idx -= 1
            end_positions.append(idx + 1)

    inputs["start_positions"] = start_positions
    inputs["end_positions"] = end_positions
    return inputs

train_dataset = raw_datasets["train"].map(
    preprocess_training_examples,
    batched=True,
    remove_columns=raw_datasets["train"].column_names,
)
len(raw_datasets["train"]), len(train_dataset)

def preprocess_validation_examples(examples):
    questions = [q.strip() for q in examples["question"]]
    inputs = tokenizer(
        questions,
        examples["context"],
        max_length=max_length,
        truncation="only_second",
        stride=stride,
        return_overflowing_tokens=True,
        return_offsets_mapping=True,
        padding="max_length",
    )

    sample_map = inputs.pop("overflow_to_sample_mapping")
    example_ids = []

    for i in range(len(inputs["input_ids"])):
        sample_idx = sample_map[i]
        example_ids.append(examples["id"][sample_idx])

        sequence_ids = inputs.sequence_ids(i)
        offset = inputs["offset_mapping"][i]
        inputs["offset_mapping"][i] = [
            o if sequence_ids[k] == 1 else None for k, o in enumerate(offset)
        ]

    inputs["example_id"] = example_ids
    return inputs

validation_dataset = raw_datasets["validation"].map(
    preprocess_validation_examples,
    batched=True,
    remove_columns=raw_datasets["validation"].column_names,
)
len(raw_datasets["validation"]), len(validation_dataset)

small_eval_set = raw_datasets["validation"].select(range(100))
trained_checkpoint = "distilbert-base-cased-distilled-squad"

tokenizer = AutoTokenizer.from_pretrained(trained_checkpoint)
eval_set = small_eval_set.map(
    preprocess_validation_examples,
    batched=True,
    remove_columns=raw_datasets["validation"].column_names,
)

tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

import torch
from transformers import AutoModelForQuestionAnswering

eval_set_for_model = eval_set.remove_columns(["example_id", "offset_mapping"])
eval_set_for_model.set_format("torch")

device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
batch = {k: eval_set_for_model[k].to(device) for k in eval_set_for_model.column_names}
trained_model = AutoModelForQuestionAnswering.from_pretrained(trained_checkpoint).to(
    device
)

with torch.no_grad():
    outputs = trained_model(**batch)

start_logits = outputs.start_logits.cpu().numpy()
end_logits = outputs.end_logits.cpu().numpy()

import collections

example_to_features = collections.defaultdict(list)
for idx, feature in enumerate(eval_set):
    example_to_features[feature["example_id"]].append(idx)

import numpy as np

n_best = 20
max_answer_length = 30
predicted_answers = []

for example in small_eval_set:
    example_id = example["id"]
    context = example["context"]
    answers = []

    for feature_index in example_to_features[example_id]:
        start_logit = start_logits[feature_index]
        end_logit = end_logits[feature_index]
        offsets = eval_set["offset_mapping"][feature_index]

        start_indexes = np.argsort(start_logit)[-1 : -n_best - 1 : -1].tolist()
        end_indexes = np.argsort(end_logit)[-1 : -n_best - 1 : -1].tolist()
        for start_index in start_indexes:
            for end_index in end_indexes:
                # Skip answers that are not fully in the context
                if offsets[start_index] is None or offsets[end_index] is None:
                    continue
                # Skip 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

                answers.append(
                    {
                        "text": context[offsets[start_index][0] : offsets[end_index][1]],
                        "logit_score": start_logit[start_index] + end_logit[end_index],
                    }
                )

    best_answer = max(answers, key=lambda x: x["logit_score"])
    predicted_answers.append({"id": example_id, "prediction_text": best_answer["text"]})

import evaluate

metric = evaluate.load("squad")

theoretical_answers = [
    {"id": ex["id"], "answers": ex["answers"]} for ex in small_eval_set
]

print(predicted_answers[0])
print(theoretical_answers[0])

metric.compute(predictions=predicted_answers, references=theoretical_answers)

from tqdm.auto import tqdm


def compute_metrics(start_logits, end_logits, features, examples):
    example_to_features = collections.defaultdict(list)
    for idx, feature in enumerate(features):
        example_to_features[feature["example_id"]].append(idx)

    predicted_answers = []
    for example in tqdm(examples):
        example_id = example["id"]
        context = example["context"]
        answers = []

        # Loop through all features associated with that example
        for feature_index in example_to_features[example_id]:
            start_logit = start_logits[feature_index]
            end_logit = end_logits[feature_index]
            offsets = features[feature_index]["offset_mapping"]

            start_indexes = np.argsort(start_logit)[-1 : -n_best - 1 : -1].tolist()
            end_indexes = np.argsort(end_logit)[-1 : -n_best - 1 : -1].tolist()
            for start_index in start_indexes:
                for end_index in end_indexes:
                    # Skip answers that are not fully in the context
                    if offsets[start_index] is None or offsets[end_index] is None:
                        continue
                    # Skip 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

                    answer = {
                        "text": context[offsets[start_index][0] : offsets[end_index][1]],
                        "logit_score": start_logit[start_index] + end_logit[end_index],
                    }
                    answers.append(answer)

        # Select the answer with the best score
        if len(answers) > 0:
            best_answer = max(answers, key=lambda x: x["logit_score"])
            predicted_answers.append(
                {"id": example_id, "prediction_text": best_answer["text"]}
            )
        else:
            predicted_answers.append({"id": example_id, "prediction_text": ""})

    theoretical_answers = [{"id": ex["id"], "answers": ex["answers"]} for ex in examples]
    return metric.compute(predictions=predicted_answers, references=theoretical_answers)

compute_metrics(start_logits, end_logits, eval_set, small_eval_set)

model = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)

from huggingface_hub import notebook_login

notebook_login()

from transformers import TrainingArguments

args = TrainingArguments(
    "bert-finetuned-squad",
    evaluation_strategy="no",
    save_strategy="epoch",
    learning_rate=2e-5,
    num_train_epochs=3,
    weight_decay=0.01,
    fp16=True,
    push_to_hub=True,
)

from transformers import Trainer

trainer = Trainer(
    model=model,
    args=args,
    train_dataset=train_dataset,
    eval_dataset=validation_dataset,
    tokenizer=tokenizer,
)
trainer.train()

predictions, _, _ = trainer.predict(validation_dataset)
start_logits, end_logits = predictions
compute_metrics(start_logits, end_logits, validation_dataset, raw_datasets["validation"])

trainer.push_to_hub(commit_message="Training complete")

from torch.utils.data import DataLoader
from transformers import default_data_collator

train_dataset.set_format("torch")
validation_set = validation_dataset.remove_columns(["example_id", "offset_mapping"])
validation_set.set_format("torch")

train_dataloader = DataLoader(
    train_dataset,
    shuffle=True,
    collate_fn=default_data_collator,
    batch_size=8,
)
eval_dataloader = DataLoader(
    validation_set, collate_fn=default_data_collator, batch_size=8
)

model = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)

from torch.optim import AdamW

optimizer = AdamW(model.parameters(), lr=2e-5)

from accelerate import Accelerator

accelerator = Accelerator(fp16=True)
model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(
    model, optimizer, train_dataloader, eval_dataloader
)

from transformers import get_scheduler

num_train_epochs = 3
num_update_steps_per_epoch = len(train_dataloader)
num_training_steps = num_train_epochs * num_update_steps_per_epoch

lr_scheduler = get_scheduler(
    "linear",
    optimizer=optimizer,
    num_warmup_steps=0,
    num_training_steps=num_training_steps,
)

from huggingface_hub import Repository, get_full_repo_name

model_name = "bert-finetuned-squad-accelerate"
repo_name = get_full_repo_name(model_name)
repo_name

output_dir = "bert-finetuned-squad-accelerate"
repo = Repository(output_dir, clone_from=repo_name)

from tqdm.auto import tqdm
import torch

progress_bar = tqdm(range(num_training_steps))

for epoch in range(num_train_epochs):
    # Training
    model.train()
    for step, batch in enumerate(train_dataloader):
        outputs = model(**batch)
        loss = outputs.loss
        accelerator.backward(loss)

        optimizer.step()
        lr_scheduler.step()
        optimizer.zero_grad()
        progress_bar.update(1)

    # Evaluation
    model.eval()
    start_logits = []
    end_logits = []
    accelerator.print("Evaluation!")
    for batch in tqdm(eval_dataloader):
        with torch.no_grad():
            outputs = model(**batch)

        start_logits.append(accelerator.gather(outputs.start_logits).cpu().numpy())
        end_logits.append(accelerator.gather(outputs.end_logits).cpu().numpy())

    start_logits = np.concatenate(start_logits)
    end_logits = np.concatenate(end_logits)
    start_logits = start_logits[: len(validation_dataset)]
    end_logits = end_logits[: len(validation_dataset)]

    metrics = compute_metrics(
        start_logits, end_logits, validation_dataset, raw_datasets["validation"]
    )
    print(f"epoch {epoch}:", metrics)

    # Save and upload
    accelerator.wait_for_everyone()
    unwrapped_model = accelerator.unwrap_model(model)
    unwrapped_model.save_pretrained(output_dir, save_function=accelerator.save)
    if accelerator.is_main_process:
        tokenizer.save_pretrained(output_dir)
        repo.push_to_hub(
            commit_message=f"Training in progress epoch {epoch}", blocking=False
        )

accelerator.wait_for_everyone()
unwrapped_model = accelerator.unwrap_model(model)
unwrapped_model.save_pretrained(output_dir, save_function=accelerator.save)

from transformers import pipeline

# Replace this with your own checkpoint
model_checkpoint = "huggingface-course/bert-finetuned-squad"
question_answerer = pipeline("question-answering", model=model_checkpoint)

context = """
🤗 Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration
between them. It's straightforward to train your models with one before loading them for inference with the other.
"""
question = "Which deep learning libraries back 🤗 Transformers?"
question_answerer(question=question, context=context)