Upload train.py with huggingface_hub

train.py

@@ -0,0 +1,85 @@
+from pathlib import Path
+import shutil
+from typing import Any, Dict
+from datasets import load_dataset
+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 = "EMBO/SourceData"
+    dataset_name = "SourceData"
+    dataset = load_dataset(dataset_id, version="1.0.1").rename_columns({"labels": "ner_tags", "words": "tokens"})
+    labels = dataset["train"].features["ner_tags"].feature.names
+
+    # Initialize a SpanMarker model using a pretrained BERT-style encoder
+    encoder_id = "bert-base-uncased"
+    model_id = f"tomaarsen/span-marker-{encoder_id}-sourcedata"
+    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="cc-by-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=50,
+        evaluation_strategy="steps",
+        save_strategy="steps",
+        eval_steps=3000,
+        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=dataset["train"],
+        eval_dataset=dataset["validation"],
+    )
+    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()
+
+# TODO: Embedding resizing & SpanMarkerModelCardData docs