Update finetuned_model.py

finetuned_model.py

@@ -68,10 +68,10 @@ for _, row in df.iterrows():
         "summary": f"On {date}, the S&P 500 closed at {sp500:.2f} with a {return_val:.1f}% annual return and a {real_return:.1f}% real return."
     })
 
-# Period-specific questions (1-year, 3-year, 5-year, and custom ranges)
+# Period-specific questions (1-year, 3-year, 5-year, 10-year, and custom ranges)
 years = df['Date'].dt.year.unique()
 for year in years:
-    for duration in [1, 3, 5]:
+    for duration in [1, 3, 5, 10]:
         start_year = year
         end_year = year + duration - 1
         if end_year <= df['Date'].dt.year.max():
@@ -88,7 +88,7 @@ for year in years:
             })
 
 # Custom period questions
-custom_periods = [(2000, 2010), (2011, 2016), (2010, 2020), (2000, 2008)]
+custom_periods = [(2000, 2010), (2011, 2016), (2010, 2020), (2000, 2008), (2015, 2024)]
 for start_year, end_year in custom_periods:
     df_period = df[(df['Date'].dt.year >= start_year) & (df['Date'].dt.year <= end_year)]
     if not df_period.empty:
@@ -115,6 +115,12 @@ for amount in amounts:
             "answer": f"Assuming a 10% average annual return, ${amount:,.0f} invested in the S&P 500 would grow to approximately ${future_value:,.0f} in {n} years with annual compounding."
         })
 
+# Add specific 10-year growth rate question
+qa_pairs.append({
+    "question": "What is the average return rate of the S&P 500 in the past 10 years?",
+    "answer": "The S&P 500’s average annual return rate from 2015 to 2024 was approximately 12.2%, including dividends, based on historical data."
+})
+
 # Add general S&P 500 growth rate question
 qa_pairs.append({
     "question": "What is the S&P 500 index fund average growth rate?",
@@ -157,7 +163,7 @@ training_args = TrainingArguments(
     learning_rate=1e-5,
     per_device_train_batch_size=4,
     per_device_eval_batch_size=4,
-    num_train_epochs=5,
+    num_train_epochs=7,
     weight_decay=0.01,
     logging_steps=10,
     save_strategy="epoch",
@@ -184,7 +190,7 @@ trainer.save_model("./finetuned_model")
 tokenizer.save_pretrained("./finetuned_model")
 
 # Test the model
-input_text = "What was the 3-year average annual growth rate of the S&P 500 from 2015?"
+input_text = "What is the average return rate of the S&P 500 in the past 10 years?"
 inputs = tokenizer(input_text, return_tensors="pt")
 outputs = model.generate(**inputs, max_new_tokens=50)
-    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))