Create train_script.py

train_script.py

@@ -0,0 +1,97 @@
+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(
+    "jinaai/jina-embeddings-v2-base-en",
+    trust_remote_code=True,
+    model_card_data=SentenceTransformerModelCardData(
+        language="en",
+        license="apache-2.0",
+        model_name="jina-embeddings-v2-base-en trained on Natural Questions pairs",
+    ),
+)
+model_name = "jina-v2-base-natural-questions"
+
+# 3. Load a dataset to finetune on
+dataset = load_dataset("sentence-transformers/natural-questions", split="train")
+dataset = dataset.add_column("id", range(len(dataset)))
+train_dataset: Dataset = dataset.select(range(90_000))
+eval_dataset: Dataset = dataset.select(range(90_000, len(dataset)))
+
+# 4. Define a loss function
+loss = MultipleNegativesRankingLoss(model)
+
+
+# 5. (Optional) Specify training arguments
+args = SentenceTransformerTrainingArguments(
+    # Required parameter:
+    output_dir=f"models/{model_name}",
+    # Optional training parameters:
+    num_train_epochs=1,
+    per_device_train_batch_size=16,
+    per_device_eval_batch_size=16,
+    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=200,
+    save_strategy="steps",
+    save_steps=200,
+    save_total_limit=2,
+    logging_steps=200,
+    logging_first_step=True,
+    run_name=model_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
+queries = dict(zip(eval_dataset["id"], eval_dataset["query"]))
+corpus = {cid: dataset[cid]["answer"] for cid in range(10_000)} | {cid: dataset[cid]["answer"] for cid in eval_dataset["id"]}
+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="natural-questions-dev",
+    batch_size=8,
+)
+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/{model_name}/final")
+
+# 9. (Optional) Push it to the Hugging Face Hub
+model.push_to_hub(f"{model_name}")