refactor: 训练循环改为两重迭代并统一参数命名

- 训练循环从三重(epoch→batched→batch)改为二重(epoch→batch)
- batch_size → batch_per_device, accumulation_steps → grad_accum_steps
- scheduler 移入 step block 对齐 optimizer 更新步
- GradientClippingCallback 改用 on_step_begin 避免零梯度裁剪
- 移除 _train_impl 误导性的 -> Checkpoint 标注
- total_steps 修除为向下取整并精简为一行
- warmup_steps 改为 warmup_ratio (默认0.05)

tests/trainer/test_trainer.py

@@ -7,45 +7,45 @@ def test_different_batch_sizes(base_test_env, random_dataset, train_config_facto
     """Test training with different batch sizes"""
     batch_sizes = [1, 2, 4, 8]
 
-    for batch_size in batch_sizes:
+    for batch_per_device in batch_sizes:
         train_config = train_config_factory(
             model=base_test_env["model"],
             dataset=random_dataset,
             test_dir=base_test_env["test_dir"],
             device=base_test_env["device"],
-            batch_size=batch_size,
+            batch_per_device=batch_per_device,
         )
 
-        assert train_config.batch_size == batch_size
+        assert train_config.batch_per_device == batch_per_device
 
 
 def test_gradient_accumulation(base_test_env, random_dataset, train_config_factory):
     """Test training with different gradient accumulation steps"""
-    accumulation_steps_list = [1, 2, 4]
+    grad_accum_steps_list = [1, 2, 4]
 
-    for accumulation_steps in accumulation_steps_list:
+    for grad_accum_steps in grad_accum_steps_list:
         train_config = train_config_factory(
             model=base_test_env["model"],
             dataset=random_dataset,
             test_dir=base_test_env["test_dir"],
             device=base_test_env["device"],
-            batch_size=2,
-            accumulation_steps=accumulation_steps,
+            batch_per_device=2,
+            grad_accum_steps=grad_accum_steps,
         )
 
         trainer = Trainer(train_config)
         trainer.train()
 
-        assert train_config.accumulation_steps == accumulation_steps
+        assert train_config.grad_accum_steps == grad_accum_steps
 
 
 def test_memory_efficient_training(base_test_env, random_dataset, train_config_factory):
     """Test training with memory-efficient configurations"""
     # Test with smaller batch sizes and gradient checkpointing
     small_batch_configs = [
-        {"batch_size": 1, "accumulation_steps": 8},
-        {"batch_size": 2, "accumulation_steps": 4},
-        {"batch_size": 4, "accumulation_steps": 2},
+        {"batch_per_device": 1, "grad_accum_steps": 8},
+        {"batch_per_device": 2, "grad_accum_steps": 4},
+        {"batch_per_device": 4, "grad_accum_steps": 2},
     ]
 
     for config in small_batch_configs:
@@ -54,8 +54,9 @@ def test_memory_efficient_training(base_test_env, random_dataset, train_config_f
             dataset=random_dataset,
             test_dir=base_test_env["test_dir"],
             device=base_test_env["device"],
-            batch_size=config["batch_size"],
-            accumulation_steps=config["accumulation_steps"],
+            batch_per_device=config["batch_per_device"],
+            grad_accum_steps=config["grad_accum_steps"],
         )
 
-        assert train_config.accumulation_steps == config["accumulation_steps"]
+        assert train_config.grad_accum_steps == config["grad_accum_steps"]
+        assert train_config.batch_per_device == config["batch_per_device"]