"""
This examples trains BERT (or any other transformer model like RoBERTa, DistilBERT etc.) for the STSbenchmark from scratch.
It uses MatryoshkaLoss with the powerful CoSENTLoss to train models that perform well at output dimensions [768, 512, 256, 128, 64].
It generates sentence embeddings that can be compared using cosine-similarity to measure the similarity.

Usage:
python matryoshka_sts.py

OR
python matryoshka_sts.py pretrained_transformer_model_name
"""

from torch.utils.data import DataLoader
import math
from sentence_transformers import SentenceTransformer, LoggingHandler, losses, models, util
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator
from sentence_transformers.readers import InputExample
import logging
from datetime import datetime
import sys
import os
import gzip
import csv

#### Just some code to print debug information to stdout
logging.basicConfig(
    format="%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S", level=logging.INFO, handlers=[LoggingHandler()]
)
#### /print debug information to stdout


# Check if dataset exists. If not, download and extract  it
sts_dataset_path = "datasets/stsbenchmark.tsv.gz"

if not os.path.exists(sts_dataset_path):
    util.http_get("https://sbert.net/datasets/stsbenchmark.tsv.gz", sts_dataset_path)


# You can specify any huggingface/transformers pre-trained model here, for example, bert-base-uncased, roberta-base, xlm-roberta-base
model_name = sys.argv[1] if len(sys.argv) > 1 else "distilbert-base-uncased"

# Read the dataset
train_batch_size = 16
num_epochs = 4
model_save_path = (
    "output/matryoshka_sts_" + model_name.replace("/", "-") + "-" + datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
)

# Use Huggingface/transformers model (like BERT, RoBERTa, XLNet, XLM-R) for mapping tokens to embeddings
word_embedding_model = models.Transformer(model_name)

# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(
    word_embedding_model.get_word_embedding_dimension(),
    pooling_mode_mean_tokens=True,
    pooling_mode_cls_token=False,
    pooling_mode_max_tokens=False,
)

model = SentenceTransformer(modules=[word_embedding_model, pooling_model])

# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")

train_samples = []
dev_samples = []
test_samples = []
with gzip.open(sts_dataset_path, "rt", encoding="utf8") as fIn:
    reader = csv.DictReader(fIn, delimiter="\t", quoting=csv.QUOTE_NONE)
    for row in reader:
        score = float(row["score"]) / 5.0  # Normalize score to range 0 ... 1
        inp_example = InputExample(texts=[row["sentence1"], row["sentence2"]], label=score)

        if row["split"] == "dev":
            dev_samples.append(inp_example)
        elif row["split"] == "test":
            test_samples.append(inp_example)
        else:
            train_samples.append(inp_example)


train_dataloader = DataLoader(train_samples, shuffle=True, batch_size=train_batch_size)
train_loss = losses.CoSENTLoss(model=model)
train_loss = losses.MatryoshkaLoss(model, train_loss, [768, 512, 256, 128, 64])


logging.info("Read STSbenchmark dev dataset")
evaluator = EmbeddingSimilarityEvaluator.from_input_examples(dev_samples, name="sts-dev")


# Configure the training. We skip evaluation in this example
warmup_steps = math.ceil(len(train_dataloader) * num_epochs * 0.1)  # 10% of train data for warm-up
logging.info("Warmup-steps: {}".format(warmup_steps))


# Train the model
model.fit(
    train_objectives=[(train_dataloader, train_loss)],
    evaluator=evaluator,
    epochs=num_epochs,
    evaluation_steps=1000,
    warmup_steps=warmup_steps,
    output_path=model_save_path,
)


##############################################################################
#
# Load the stored model and evaluate its performance on STS benchmark dataset
#
##############################################################################

model = SentenceTransformer(model_save_path)
test_evaluator = EmbeddingSimilarityEvaluator.from_input_examples(test_samples, name="sts-test")
test_evaluator(model, output_path=model_save_path)

# Optionally, save the model to the Hugging Face Hub!
# It is recommended to run `huggingface-cli login` to log into your Hugging Face account first
model_name = model_name if "/" not in model_name else model_name.split("/")[-1]
try:
    model.push_to_hub(f"{model_name}-sts-matryoshka")
except Exception:
    logging.error(
        "Error uploading model to the Hugging Face Hub. To upload it manually, you can run "
        f"`huggingface-cli login`, followed by loading the model using `model = SentenceTransformer({model_save_path!r})` "
        f"and saving it using `model.push_to_hub('{model_name}-sts-matryoshka')`."
    )