Create app.py

app.py

@@ -0,0 +1,95 @@
+import gradio as gr
+import torch
+from datasets import load_dataset
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification, Trainer, TrainingArguments
+import numpy as np
+
+# Load the sentiment dataset
+dataset = load_dataset('k1tub/sentiment_dataset')
+print(f"Dataset loaded with {len(dataset['train'])} training examples")
+
+# Load tokenizer and model
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+model = DistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased', num_labels=3)
+
+def preprocess_function(examples):
+    # Tokenize the text
+    encoding = tokenizer(examples['text'], truncation=True, padding='max_length', max_length=128)
+    # Map label to indices
+    encoding['labels'] = examples['label']
+    return encoding
+
+# Preprocess the dataset
+tokenized_dataset = dataset.map(preprocess_function, batched=True, remove_columns=['text'])
+
+def train_model(epochs, batch_size, learning_rate):
+    """Fine-tune DistilBERT on the sentiment dataset"""
+    try:
+        training_args = TrainingArguments(
+            output_dir='./results',
+            num_train_epochs=int(epochs),
+            per_device_train_batch_size=int(batch_size),
+            per_device_eval_batch_size=int(batch_size),
+            learning_rate=float(learning_rate),
+            weight_decay=0.01,
+            save_strategy='epoch',
+            logging_steps=50,
+        )
+        
+        trainer = Trainer(
+            model=model,
+            args=training_args,
+            train_dataset=tokenized_dataset['train'],
+            eval_dataset=tokenized_dataset['validation'] if 'validation' in tokenized_dataset else tokenized_dataset['train'],
+        )
+        
+        # Start training
+        trainer.train()
+        
+        return "\u270d✅ Training completed successfully!\n" + \
+                f"Model saved to ./results\nFinal learning rate: {learning_rate}\nEpochs: {epochs}\nBatch size: {batch_size}"
+    except Exception as e:
+        return f"❌ Error during training: {str(e)}"
+
+# Create Gradio interface
+with gr.Blocks(title="DistilBERT Sentiment Training") as demo:
+    gr.Markdown("""
+    # 🚀 DistilBERT Sentiment Analysis Training
+    
+    Fine-tune **DistilBERT** model on the **k1tub/sentiment_dataset** (290k examples)
+    
+    ### Model Info:
+    - **Base Model**: distilbert-base-uncased (67M parameters)
+    - **Task**: Text Classification (Sentiment Analysis)
+    - **Dataset**: k1tub/sentiment_dataset
+    - **Framework**: Hugging Face Transformers
+    """)
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Training Configuration")
+            epochs = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="Number of Epochs")
+            batch_size = gr.Slider(minimum=8, maximum=64, value=32, step=8, label="Batch Size")
+            learning_rate = gr.Slider(minimum=1e-5, maximum=1e-3, value=2e-5, step=1e-5, label="Learning Rate")
+            
+        with gr.Column():
+            gr.Markdown("### Training Status")
+            output_text = gr.Textbox(label="Output", lines=10, interactive=False)
+    
+    train_button = gr.Button("🔥 Start Training", variant="primary", scale=2)
+    train_button.click(
+        fn=train_model,
+        inputs=[epochs, batch_size, learning_rate],
+        outputs=output_text
+    )
+    
+    gr.Markdown("""
+    ### Training Details:
+    - **Free Hardware**: CPU Basic on Hugging Face Spaces
+    - **Training Time**: Depends on dataset size and hardware
+    - **Model Output**: Saved to ./results folder
+    - **Inference**: Can be deployed as a separate Space
+    """)
+
+if __name__ == "__main__":
+    demo.launch()