tomaarsen
/

span-marker-bert-base-uncased-keyphrase-inspec

Token Classification

named-entity-recognition

generated_from_span_marker_trainer

Carbon Emissions

Model card Files Files and versions Metrics Training metrics Community

span-marker-bert-base-uncased-keyphrase-inspec / train.py

tomaarsen's picture

tomaarsen HF staff

Upload train.py with huggingface_hub

9b02706 8 months ago

raw history blame contribute delete

No virus

2.99 kB

	from pathlib import Path
	import shutil
	from datasets import load_dataset, concatenate_datasets
	from transformers import TrainingArguments
	from span_marker import SpanMarkerModel, Trainer
	from span_marker.model_card import SpanMarkerModelCardData

	import os

	os.environ["CODECARBON_LOG_LEVEL"] = "error"


	def main() -> None:
	# Load the dataset, ensure "tokens" and "ner_tags" columns, and get a list of labels
	dataset_id = "midas/inspec"
	dataset_name = "Inspec"
	dataset = load_dataset(dataset_id, "extraction")
	dataset = dataset.rename_columns({"document": "tokens", "doc_bio_tags": "ner_tags"})
	# Map string labels to integer labels instead
	real_labels = ["O", "B", "I"]
	dataset = dataset.map(lambda sample: {"ner_tags": [real_labels.index(tag) for tag in sample]}, input_columns="ner_tags")
	# Use more readable labels
	labels = ["O", "B-KEY", "I-KEY"]
	# Train using train + validation set.
	train_dataset = concatenate_datasets((dataset["train"], dataset["validation"]))

	# Initialize a SpanMarker model using a pretrained BERT-style encoder
	encoder_id = "bert-base-uncased"
	model_id = "tomaarsen/span-marker_bert-base-uncased-keyphrase-inspec"
	model = SpanMarkerModel.from_pretrained(
	encoder_id,
	labels=labels,
	# SpanMarker hyperparameters:
	model_max_length=256,
	marker_max_length=128,
	entity_max_length=8,
	# Model card variables
	model_card_data=SpanMarkerModelCardData(
	model_id=model_id,
	encoder_id=encoder_id,
	dataset_name=dataset_name,
	dataset_id=dataset_id,
	license="apache-2.0",
	language="en",
	),
	)

	# Prepare the 🤗 transformers training arguments
	output_dir = Path("models") / model_id
	args = TrainingArguments(
	output_dir=output_dir,
	hub_model_id=model_id,
	run_name=f"bbu_keyphrase",
	# Training Hyperparameters:
	learning_rate=5e-5,
	per_device_train_batch_size=32,
	per_device_eval_batch_size=32,
	num_train_epochs=3,
	weight_decay=0.01,
	warmup_ratio=0.1,
	bf16=True, # Replace `bf16` with `fp16` if your hardware can't use bf16.
	# Other Training parameters
	logging_first_step=True,
	logging_steps=50,
	evaluation_strategy="no",
	save_total_limit=2,
	dataloader_num_workers=2,
	)

	# Initialize the trainer using our model, training args & dataset, and train
	trainer = Trainer(
	model=model,
	args=args,
	train_dataset=train_dataset
	)
	trainer.train()

	# Compute & save the metrics on the test set
	metrics = trainer.evaluate(dataset["test"], metric_key_prefix="test")
	trainer.save_metrics("test", metrics)

	trainer.save_model(output_dir / "checkpoint-final")
	shutil.copy2(__file__, output_dir / "checkpoint-final" / "train.py")


	if __name__ == "__main__":
	main()