File size: 2,694 Bytes
6fe7180 |
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 |
import pandas as pd
from datasets import Dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
import numpy as np
# Load data
dev_df = pd.read_csv("./data/DISAPERE-main/SELFExtractedData/disapere_topic_dev.csv")
train_df = pd.read_csv("./data/DISAPERE-main/SELFExtractedData/disapere_topic_train.csv")
test_df = pd.read_csv("./data/DISAPERE-main/SELFExtractedData/disapere_topic_test.csv")
# Convert to HuggingFace Datasets
train_ds = Dataset.from_pandas(train_df)
dev_ds = Dataset.from_pandas(dev_df)
test_ds = Dataset.from_pandas(test_df)
# Tokenize
model_name = "microsoft/deberta-v3-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
def tokenize(batch):
return tokenizer(batch["text"], padding="max_length", truncation=True, max_length=256)
train_ds = train_ds.map(tokenize, batched=True)
dev_ds = dev_ds.map(tokenize, batched=True)
test_ds = test_ds.map(tokenize, batched=True)
# Set format for PyTorch
train_ds.set_format(type="torch", columns=["input_ids", "attention_mask", "label"])
dev_ds.set_format(type="torch", columns=["input_ids", "attention_mask", "label"])
test_ds.set_format(type="torch", columns=["input_ids", "attention_mask", "label"])
print(train_df['label'].value_counts().sort_index())
# Load model
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=8)
# Metrics
def compute_metrics(eval_pred):
logits, labels = eval_pred
preds = np.argmax(logits, axis=1)
precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average="macro")
acc = accuracy_score(labels, preds)
return {"accuracy": acc, "f1": f1, "precision": precision, "recall": recall}
# Training arguments
args = TrainingArguments(
output_dir="./alternative_topic/deberta/checkpoints",
eval_strategy="epoch",
save_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=8,
per_device_eval_batch_size=16,
num_train_epochs=4,
weight_decay=0.01,
load_best_model_at_end=True,
metric_for_best_model="f1"
)
# Trainer
trainer = Trainer(
model=model,
args=args,
train_dataset=train_ds,
eval_dataset=dev_ds,
tokenizer=tokenizer,
compute_metrics=compute_metrics
)
# Train
trainer.train()
# Evaluate on test
results = trainer.evaluate(test_ds)
print("Test results:", results)
# Save the model and tokenizer
model.save_pretrained("./alternative_topic/deberta/final_model")
tokenizer.save_pretrained("./alternative_topic/deberta/final_model") |