File size: 13,378 Bytes
4f0238f | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | """
Tests for TouchGrass Trainer.
"""
import pytest
import torch
from unittest.mock import MagicMock, patch
from TouchGrass.training.trainer import TouchGrassTrainer
class TestTouchGrassTrainer:
"""Test suite for TouchGrassTrainer."""
def setup_method(self):
"""Set up test fixtures."""
self.device = "cpu"
self.d_model = 768
self.vocab_size = 32000
# Mock model
self.model = MagicMock()
self.model.parameters.return_value = [torch.randn(10, requires_grad=True)]
# Mock tokenizer
self.tokenizer = MagicMock()
self.tokenizer.pad_token_id = 0
# Mock loss function
self.loss_fn = MagicMock()
self.loss_fn.return_value = {"total_loss": torch.tensor(0.5)}
# Mock optimizer
self.optimizer = MagicMock()
self.optimizer.step = MagicMock()
self.optimizer.zero_grad = MagicMock()
# Mock scheduler
self.scheduler = MagicMock()
self.scheduler.step = MagicMock()
# Create trainer config
self.config = {
"batch_size": 4,
"gradient_accumulation_steps": 1,
"learning_rate": 2e-4,
"max_grad_norm": 1.0,
"num_epochs": 1,
"save_steps": 100,
"eval_steps": 50,
"output_dir": "test_output"
}
def test_trainer_initialization(self):
"""Test trainer initialization."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
scheduler=self.scheduler,
config=self.config,
device=self.device
)
assert trainer.model == self.model
assert trainer.tokenizer == self.tokenizer
assert trainer.loss_fn == self.loss_fn
assert trainer.optimizer == self.optimizer
assert trainer.scheduler == self.scheduler
assert trainer.config == self.config
def test_trainer_required_components(self):
"""Test that all required components are present."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
assert hasattr(trainer, "train")
assert hasattr(trainer, "evaluate")
assert hasattr(trainer, "save_checkpoint")
assert hasattr(trainer, "load_checkpoint")
def test_prepare_batch(self):
"""Test batch preparation."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {
"input_ids": torch.randint(0, self.vocab_size, (4, 10)),
"attention_mask": torch.ones(4, 10),
"labels": torch.randint(0, self.vocab_size, (4, 10))
}
prepared = trainer._prepare_batch(batch)
assert "input_ids" in prepared
assert "attention_mask" in prepared
assert "labels" in prepared
def test_training_step(self):
"""Test single training step."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {
"input_ids": torch.randint(0, self.vocab_size, (4, 10)),
"attention_mask": torch.ones(4, 10),
"labels": torch.randint(0, self.vocab_size, (4, 10))
}
loss = trainer._training_step(batch)
assert isinstance(loss, torch.Tensor) or loss is not None
def test_evaluation_step(self):
"""Test single evaluation step."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {
"input_ids": torch.randint(0, self.vocab_size, (4, 10)),
"attention_mask": torch.ones(4, 10),
"labels": torch.randint(0, self.vocab_size, (4, 10))
}
metrics = trainer._evaluation_step(batch)
assert isinstance(metrics, dict)
def test_gradient_accumulation(self):
"""Test gradient accumulation."""
config = self.config.copy()
config["gradient_accumulation_steps"] = 2
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=config,
device=self.device
)
assert trainer.gradient_accumulation_steps == 2
def test_checkpoint_saving(self, tmp_path):
"""Test checkpoint saving."""
config = self.config.copy()
config["output_dir"] = str(tmp_path / "checkpoints")
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=config,
device=self.device
)
trainer.save_checkpoint(step=100)
# Should create checkpoint files
# (actual file creation would depend on implementation)
def test_learning_rate_scheduler_step(self):
"""Test that scheduler is stepped correctly."""
config = self.config.copy()
config["learning_rate"] = 1e-3
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
scheduler=self.scheduler,
config=config,
device=self.device
)
# After training step, scheduler should be called
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._training_step(batch)
# Scheduler step should be called (depending on implementation)
# This is a simple check - actual behavior may vary
def test_gradient_clipping(self):
"""Test gradient clipping."""
config = self.config.copy()
config["max_grad_norm"] = 1.0
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=config,
device=self.device
)
assert trainer.max_grad_norm == 1.0
def test_mixed_precision_flag(self):
"""Test mixed precision training flag."""
config = self.config.copy()
config["mixed_precision"] = True
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=config,
device=self.device
)
assert trainer.mixed_precision is True
def test_device_assignment(self):
"""Test that model and data are moved to correct device."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device="cpu"
)
assert trainer.device == "cpu"
def test_optimizer_zero_grad_called(self):
"""Test that optimizer.zero_grad is called."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._training_step(batch)
self.optimizer.zero_grad.assert_called()
def test_optimizer_step_called(self):
"""Test that optimizer.step is called."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._training_step(batch)
self.optimizer.step.assert_called()
def test_loss_fn_called_with_outputs(self):
"""Test that loss function is called with model outputs."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._training_step(batch)
# Loss function should be called
self.loss_fn.assert_called()
def test_training_loop(self):
"""Test full training loop (simplified)."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
# Mock dataloader
train_dataloader = [{"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}]
eval_dataloader = [{"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}]
# Run a single epoch (with mocked data)
metrics = trainer.train(train_dataloader, eval_dataloader)
assert isinstance(metrics, dict)
def test_evaluation_loop(self):
"""Test evaluation loop."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
eval_dataloader = [{"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}]
metrics = trainer.evaluate(eval_dataloader)
assert isinstance(metrics, dict)
def test_config_validation(self):
"""Test that config has required keys."""
required_keys = ["batch_size", "learning_rate", "num_epochs", "output_dir"]
for key in required_keys:
config = self.config.copy()
del config[key]
with pytest.raises(ValueError, match=key):
TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=config,
device=self.device
)
def test_model_mode_training(self):
"""Test that model is set to training mode."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._training_step(batch)
self.model.train.assert_called()
def test_model_mode_evaluation(self):
"""Test that model is set to eval mode during evaluation."""
trainer = TouchGrassTrainer(
model=self.model,
tokenizer=self.tokenizer,
loss_fn=self.loss_fn,
optimizer=self.optimizer,
config=self.config,
device=self.device
)
batch = {"input_ids": torch.randint(0, self.vocab_size, (4, 10)), "attention_mask": torch.ones(4, 10), "labels": torch.randint(0, self.vocab_size, (4, 10))}
trainer._evaluation_step(batch)
self.model.eval.assert_called()
if __name__ == "__main__":
pytest.main([__file__, "-v"])
|