File size: 3,376 Bytes
09f6214 0bed352 09f6214 0bed352 09f6214 0bed352 09f6214 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
from pathlib import Path
import random
import shutil
from datasets import load_dataset, concatenate_datasets, Features, Sequence, ClassLabel, Value, DatasetDict
from transformers import TrainingArguments
from span_marker import SpanMarkerModel, Trainer
from span_marker.model_card import SpanMarkerModelCardData
from huggingface_hub import upload_folder, upload_file
def main() -> None:
# Load the dataset, ensure "tokens" and "ner_tags" columns, and get a list of labels
labels = ["O", "B-ORG", "I-ORG"]
dataset_id = "tomaarsen/ner-orgs"
dataset = load_dataset(dataset_id)
train_dataset = dataset["train"]
eval_dataset = dataset["validation"]
eval_dataset = eval_dataset.select(random.sample(range(len(eval_dataset)), k=3000))
test_dataset = dataset["test"]
# Initialize a SpanMarker model using a pretrained BERT-style encoder
encoder_id = "bert-base-cased"
model_id = f"tomaarsen/span-marker-bert-base-orgs"
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,
dataset_id=dataset_id,
encoder_id=encoder_id,
dataset_name="FewNERD, CoNLL2003, and OntoNotes v5",
license="cc-by-sa-4.0",
language=["en"],
),
)
# Prepare the 🤗 transformers training arguments
output_dir = Path("models") / model_id
args = TrainingArguments(
output_dir=output_dir,
run_name=model_id,
# 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=100,
evaluation_strategy="steps",
save_strategy="steps",
eval_steps=3000,
save_total_limit=1,
dataloader_num_workers=4,
)
# Initialize the trainer using our model, training args & dataset, and train
trainer = Trainer(
model=model,
args=args,
train_dataset=train_dataset,
eval_dataset=eval_dataset,
)
trainer.train()
# Compute & save the metrics on the test set
metrics = trainer.evaluate(test_dataset, metric_key_prefix="test")
trainer.save_metrics("test", metrics)
# Save the model & training script locally
trainer.save_model(output_dir / "checkpoint-final")
shutil.copy2(__file__, output_dir / "checkpoint-final" / "train.py")
# Upload everything to the Hub
breakpoint()
model.push_to_hub(model_id, private=True)
upload_folder(folder_path=output_dir / "runs", path_in_repo="runs", repo_id=model_id)
upload_file(path_or_fileobj=__file__, path_in_repo="train.py", repo_id=model_id)
upload_file(path_or_fileobj=output_dir / "all_results.json", path_in_repo="all_results.json", repo_id=model_id)
upload_file(path_or_fileobj=output_dir / "emissions.csv", path_in_repo="emissions.csv", repo_id=model_id)
if __name__ == "__main__":
main() |