File size: 10,996 Bytes
5c43f61 | 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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 | """
Science benchmarks for Vortex model.
Evaluates performance across 7 science domains.
"""
import torch
from typing import Dict, List, Tuple
from dataclasses import dataclass
@dataclass
class BenchmarkResult:
"""Results from a benchmark."""
domain: str
accuracy: float
total_questions: int
correct_answers: int
details: List[Dict]
class ScienceBenchmark:
"""
Base class for science benchmarks.
"""
def __init__(self, name: str, domain: str):
self.name = name
self.domain = domain
def load_questions(self) -> List[Dict]:
"""Load benchmark questions."""
raise NotImplementedError
def evaluate(
self,
model,
tokenizer,
device: torch.device,
max_samples: int = 100,
) -> BenchmarkResult:
"""
Evaluate model on benchmark.
Args:
model: Vortex model
tokenizer: Tokenizer
device: Torch device
max_samples: Maximum samples to evaluate
Returns:
BenchmarkResult
"""
questions = self.load_questions()[:max_samples]
correct = 0
details = []
for q in questions:
# Format prompt
prompt = self.format_prompt(q)
# Tokenize
inputs = tokenizer(prompt, return_tensors="pt").to(device)
# Generate answer
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=50,
temperature=0.0, # Greedy
do_sample=False,
)
# Decode
generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
answer = self.extract_answer(generated)
# Check correctness
is_correct = self.check_answer(answer, q["answer"])
if is_correct:
correct += 1
details.append({
"question": q["question"],
"expected": q["answer"],
"generated": answer,
"correct": is_correct,
})
accuracy = correct / len(questions) if questions else 0.0
return BenchmarkResult(
domain=self.domain,
accuracy=accuracy,
total_questions=len(questions),
correct_answers=correct,
details=details,
)
def format_prompt(self, question: Dict) -> str:
"""Format question into prompt."""
raise NotImplementedError
def extract_answer(self, text: str) -> str:
"""Extract answer from generated text."""
raise NotImplementedError
def check_answer(self, predicted: str, expected: str) -> bool:
"""Check if predicted answer matches expected."""
raise NotImplementedError
class PhysicsBenchmark(ScienceBenchmark):
"""Physics benchmark (Feynman Questions style)."""
def __init__(self):
super().__init__("physics_benchmark", "physics")
def load_questions(self) -> List[Dict]:
# Placeholder - would load from dataset
return [
{
"question": "What is the formula for kinetic energy?",
"answer": "KE = 1/2 mv^2",
"type": "formula",
},
{
"question": "Explain Newton's first law of motion.",
"answer": "An object at rest stays at rest unless acted upon by a force.",
"type": "conceptual",
},
]
def format_prompt(self, question: Dict) -> str:
return f"Question: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
# Extract after "Answer:"
if "Answer:" in text:
return text.split("Answer:")[-1].strip()
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
# Simple string match (would use more sophisticated in practice)
pred_lower = predicted.lower()
exp_lower = expected.lower()
return exp_lower in pred_lower or pred_lower in exp_lower
class MathBenchmark(ScienceBenchmark):
"""Math benchmark (MATH dataset style)."""
def __init__(self):
super().__init__("math_benchmark", "math")
def load_questions(self) -> List[Dict]:
return [
{
"question": "Solve for x: 2x + 5 = 15",
"answer": "x = 5",
"type": "algebra",
},
{
"question": "What is the derivative of x^2?",
"answer": "2x",
"type": "calculus",
},
]
def format_prompt(self, question: Dict) -> str:
return f"Problem: {question['question']}\nSolution:"
def extract_answer(self, text: str) -> str:
if "Solution:" in text:
return text.split("Solution:")[-1].strip()
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
# Normalize whitespace and case
pred = " ".join(predicted.lower().split())
exp = " ".join(expected.lower().split())
return pred == exp
class ChemistryBenchmark(ScienceBenchmark):
"""Chemistry benchmark."""
def __init__(self):
super().__init__("chemistry_benchmark", "chemistry")
def load_questions(self) -> List[Dict]:
return [
{
"question": "What is the chemical formula for water?",
"answer": "H2O",
"type": "factual",
},
{
"question": "How many protons does carbon have?",
"answer": "6",
"type": "factual",
},
]
def format_prompt(self, question: Dict) -> str:
return f"Chemistry question: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
if "Answer:" in text:
return text.split("Answer:")[-1].strip()
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
pred = predicted.strip().lower()
exp = expected.strip().lower()
return exp in pred
class BiologyBenchmark(ScienceBenchmark):
"""Biology benchmark."""
def __init__(self):
super().__init__("biology_benchmark", "biology")
def load_questions(self) -> List[Dict]:
return [
{
"question": "What is the powerhouse of the cell?",
"answer": "mitochondria",
"type": "factual",
},
{
"question": "What molecule carries genetic information?",
"answer": "DNA",
"type": "factual",
},
]
def format_prompt(self, question: Dict) -> str:
return f"Biology: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
if "Answer:" in text:
return text.split("Answer:")[-1].strip()
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
pred = predicted.strip().lower()
exp = expected.strip().lower()
return exp in pred
# Placeholder for other domains
class EarthScienceBenchmark(ScienceBenchmark):
def __init__(self):
super().__init__("earth_science_benchmark", "earth")
def load_questions(self) -> List[Dict]:
return []
def format_prompt(self, question: Dict) -> str:
return f"Earth Science: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
return predicted.strip().lower() == expected.strip().lower()
class SpaceScienceBenchmark(ScienceBenchmark):
def __init__(self):
super().__init__("space_science_benchmark", "space")
def load_questions(self) -> List[Dict]:
return []
def format_prompt(self, question: Dict) -> str:
return f"Space Science: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
return predicted.strip().lower() == expected.strip().lower()
class ZoologyBenchmark(ScienceBenchmark):
def __init__(self):
super().__init__("zoology_benchmark", "zoology")
def load_questions(self) -> List[Dict]:
return []
def format_prompt(self, question: Dict) -> str:
return f"Zoology: {question['question']}\nAnswer:"
def extract_answer(self, text: str) -> str:
return text.strip()
def check_answer(self, predicted: str, expected: str) -> bool:
return predicted.strip().lower() == expected.strip().lower()
def run_all_benchmarks(
model,
tokenizer,
device: torch.device,
max_samples_per_domain: int = 50,
) -> Dict[str, BenchmarkResult]:
"""
Run all benchmarks and return results.
Args:
model: Vortex model
tokenizer: Tokenizer
device: Torch device
max_samples_per_domain: Max samples per domain
Returns:
Dictionary mapping domain to results
"""
benchmarks = [
PhysicsBenchmark(),
MathBenchmark(),
ChemistryBenchmark(),
BiologyBenchmark(),
EarthScienceBenchmark(),
SpaceScienceBenchmark(),
ZoologyBenchmark(),
]
results = {}
for bench in benchmarks:
print(f"Running {bench.name}...")
result = bench.evaluate(model, tokenizer, device, max_samples=max_samples_per_domain)
results[bench.domain] = result
print(f" Accuracy: {result.accuracy:.2%} ({result.correct_answers}/{result.total_questions})")
return results
def print_summary(results: Dict[str, BenchmarkResult]):
"""Print summary of benchmark results."""
print("\n" + "="*60)
print("BENCHMARK RESULTS")
print("="*60)
for domain, result in results.items():
print(f"{domain:15} {result.accuracy:6.2%} ({result.correct_answers}/{result.total_questions})")
# Overall average
all_accuracies = [r.accuracy for r in results.values() if r.total_questions > 0]
if all_accuracies:
avg = sum(all_accuracies) / len(all_accuracies)
print(f"{'OVERALL':15} {avg:6.2%}")
print("="*60)
if __name__ == "__main__":
# Quick test
print("This script benchmarks the model across science domains.")
print("To run full benchmarks, integrate with a trained model.")
|