train_script.py

import random
import logging
from datasets import load_dataset, Dataset
from sentence_transformers import (
    SentenceTransformer,
    SentenceTransformerTrainer,
    SentenceTransformerTrainingArguments,
    SentenceTransformerModelCardData,
)
from sentence_transformers.losses import MultipleNegativesRankingLoss
from sentence_transformers.training_args import BatchSamplers
from sentence_transformers.evaluation import InformationRetrievalEvaluator

logging.basicConfig(
    format="%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S", level=logging.INFO
)

# 1. Load a model to finetune with 2. (Optional) model card data
model = SentenceTransformer(
    "microsoft/mpnet-base",
    model_card_data=SentenceTransformerModelCardData(
        language="en",
        license="apache-2.0",
        model_name="MPNet base trained on GooAQ triplets",
    ),
)

# 3. Load a dataset to finetune on
dataset = load_dataset("sentence-transformers/gooaq", split="train")
dataset = dataset.add_column("id", range(len(dataset)))
dataset_dict = dataset.train_test_split(test_size=10_000, seed=12)
train_dataset: Dataset = dataset_dict["train"]
eval_dataset: Dataset = dataset_dict["test"]

# 4. Define a loss function
loss = MultipleNegativesRankingLoss(model)

# 5. (Optional) Specify training arguments
args = SentenceTransformerTrainingArguments(
    # Required parameter:
    output_dir="models/mpnet-base-gooaq",
    # Optional training parameters:
    num_train_epochs=1,
    per_device_train_batch_size=64,
    per_device_eval_batch_size=64,
    learning_rate=2e-5,
    warmup_ratio=0.1,
    fp16=False,  # Set to False if you get an error that your GPU can't run on FP16
    bf16=True,  # Set to True if you have a GPU that supports BF16
    batch_sampler=BatchSamplers.NO_DUPLICATES,  # MultipleNegativesRankingLoss benefits from no duplicate samples in a batch
    # Optional tracking/debugging parameters:
    eval_strategy="steps",
    eval_steps=1000,
    save_strategy="steps",
    save_steps=1000,
    save_total_limit=2,
    logging_steps=250,
    logging_first_step=True,
    run_name="mpnet-base-gooaq",  # Will be used in W&B if `wandb` is installed
)

# 6. (Optional) Create an evaluator & evaluate the base model
# The full corpus, but only the evaluation queries
# corpus = dict(zip(dataset["id"], dataset["answer"]))
random.seed(12)
queries = dict(zip(eval_dataset["id"], eval_dataset["question"]))
corpus = (
    {qid: dataset[qid]["answer"] for qid in queries} |
    {qid: dataset[qid]["answer"] for qid in random.sample(range(len(dataset)), 20_000)}
)
relevant_docs = {qid: {qid} for qid in eval_dataset["id"]}
dev_evaluator = InformationRetrievalEvaluator(
    corpus=corpus,
    queries=queries,
    relevant_docs=relevant_docs,
    show_progress_bar=True,
    name="gooaq-dev",
)
dev_evaluator(model)

# 7. Create a trainer & train
trainer = SentenceTransformerTrainer(
    model=model,
    args=args,
    train_dataset=train_dataset.remove_columns("id"),
    eval_dataset=eval_dataset.remove_columns("id"),
    loss=loss,
    evaluator=dev_evaluator,
)
trainer.train()

# (Optional) Evaluate the trained model on the evaluator after training
dev_evaluator(model)

# 8. Save the trained model
model.save_pretrained("models/mpnet-base-gooaq/final")

# 9. (Optional) Push it to the Hugging Face Hub
model.push_to_hub("mpnet-base-gooaq")