Added basic Bart fine tuning logic

Dockerfile

@@ -0,0 +1,14 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

bart-run.py

@@ -0,0 +1,82 @@
+
+# Loading the Data.
+import torch
+import pandas as pd
+from transformers import BartTokenizer, BartForSequenceClassification
+
+# Set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load data from names.csv
+# train_data_full = pd.read_csv('names_balanced_train.csv',header=None,names=["name","country"])
+# test_data = pd.read_csv('names_balanced_test.csv',header=None,names=["name","country"])
+
+joke_data = pd.read_csv('jokes.csv', sep='|', names=["joke", "label"], skiprows=1)
+noJoke_data = pd.read_csv('not_jokes.csv', sep='|', names=["joke", "label"], skiprows=1)
+frames = [joke_data, noJoke_data]
+train_data = pd.concat(frames)
+
+test_data = pd.read_csv('test_jokes.csv', sep='|', names=["joke", "label"], skiprows=1)
+
+numCategories = 2
+tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
+model = BartForSequenceClassification.from_pretrained('facebook/bart-large', num_labels=numCategories)
+model = model.to(device)
+
+# Convert country column to one-hot encoding
+one_hot_train = pd.get_dummies(train_data['label'])
+one_hot_test = pd.get_dummies(test_data['label'])
+
+# Tokenize names and convert to PyTorch dataset
+inputs_train = tokenizer(list(train_data['joke']), return_tensors='pt', padding=True)
+labels_train = torch.tensor(one_hot_train.values, dtype=torch.float32)
+dataset_train = torch.utils.data.TensorDataset(inputs_train['input_ids'], inputs_train['attention_mask'], labels_train)
+inputs_test = tokenizer(list(test_data['joke']), return_tensors='pt', padding=True)
+labels_test = torch.tensor(one_hot_test.values, dtype=torch.float32)
+dataset_test = torch.utils.data.TensorDataset(inputs_test['input_ids'], inputs_test['attention_mask'], labels_test)
+
+
+# Define training parameters
+epochs = 10
+batch_size = 32
+learning_rate = 1e-5
+
+# Train model
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+data_loader_train = torch.utils.data.DataLoader(dataset_train, batch_size=batch_size, shuffle=True)
+data_loader_test = torch.utils.data.DataLoader(dataset_test, batch_size=batch_size)
+
+print(f"\nTraining on {len(train_data)} examples\n")
+print("Num. Parameters:", sum(p.numel() for p in model.parameters() if p.requires_grad))
+
+for epoch in range(epochs):
+    # Compute average loss after 100 steps
+    avg_loss = 0
+    for step, batch in enumerate(data_loader_train):
+        input_ids, attention_mask, labels = batch
+        input_ids, attention_mask, labels = input_ids.to(device), attention_mask.to(device), labels.to(device)
+        outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
+        loss = outputs[0]
+        avg_loss += loss.item()
+        if step % 100 == 0:
+            print(f"Step {step}/{len(data_loader_train)} Loss {loss} Avg Train Loss {avg_loss / (step + 1)}")
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+    loss = avg_loss / len(data_loader_train)
+    # Print loss after every epoch
+    print(f"Epoch {epoch+1} Test Loss {loss}")
+    # Compute accuracy after every epoch
+    correct = 0
+    total = 0
+    for step, batch in enumerate(data_loader_test):
+        input_ids, attention_mask, labels = batch
+        input_ids, attention_mask, labels = input_ids.to(device), attention_mask.to(device), labels.to(device)
+        outputs = model(input_ids, attention_mask=attention_mask)
+        predicted = torch.argmax(outputs[0], dim=1)
+        total += labels.size(0)
+        correct += (predicted == torch.argmax(labels, dim=1)).sum().item()
+    print(f"Test Accuracy {100*correct/total}%\n")
+
+# Save model
+model.save_pretrained('fine-tuned-bart_countries')

requirements.txt

@@ -0,0 +1,4 @@
+transformers==4.12.0
+torch==1.8.2
+pandas==1.3.3
+numpy==1.21.2