Add the training script

train_script.py

@@ -0,0 +1,98 @@
+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)
+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"]))
+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")