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 MatryoshkaLoss, MultipleNegativesRankingLoss
from sentence_transformers.training_args import BatchSamplers
from sentence_transformers.evaluation import InformationRetrievalEvaluator, SequentialEvaluator
from sentence_transformers.models.StaticEmbedding import StaticEmbedding

from transformers import AutoTokenizer

from sentence_transformers.util import cos_sim
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
static_embedding = StaticEmbedding(AutoTokenizer.from_pretrained("bert-base-uncased"), embedding_dim=1024)
model = SentenceTransformer(
    modules=[static_embedding],
    model_card_data=SentenceTransformerModelCardData(
        language="en",
        license="apache-2.0",
        model_name="Static Embeddings with BERT uncased tokenizer finetuned on GooAQ pairs",
    ),
)

# 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)
loss = MatryoshkaLoss(model, loss, matryoshka_dims=[32, 64, 128, 256, 512, 1024])

# 5. (Optional) Specify training arguments
run_name = "static-bert-uncased-gooaq"
args = SentenceTransformerTrainingArguments(
    # Required parameter:
    output_dir=f"models/{run_name}",
    # Optional training parameters:
    num_train_epochs=1,
    per_device_train_batch_size=2048,
    per_device_eval_batch_size=2048,
    learning_rate=2e-1,
    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=250,
    save_strategy="steps",
    save_steps=250,
    save_total_limit=2,
    logging_steps=100,
    logging_first_step=True,
    run_name=run_name,  # 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
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"]}
evaluators = []
for dim in loss.matryoshka_dims:
    evaluators.append(InformationRetrievalEvaluator(
        corpus=corpus,
        queries=queries,
        relevant_docs=relevant_docs,
        show_progress_bar=True,
        name=f"gooaq-{dim}-dev",
        truncate_dim=dim,
        score_functions={"cosine": cos_sim},
    ))
dev_evaluator = SequentialEvaluator(evaluators)
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(f"models/{run_name}/final")

# 9. (Optional) Push it to the Hugging Face Hub
model.push_to_hub(run_name, private=True)