Warum behält die Feinabstimmung eines MLP-Modells anhand eines kleinen Datensatzes immer noch die gleiche Testgenauigkeit bei wie vorab trainierte Gewichte?

class mlp(nn.module):
    def __init__(self,input_dim=92, hidden_dim = 150, num_classes=2):
        super().__init__()
        self.input_dim = input_dim
        self.num_classes = num_classes
        self.hidden_dim = hidden_dim
        #self.softmax = nn.softmax(dim=1)

        self.layers = nn.sequential(
            nn.linear(self.input_dim, self.hidden_dim),
            nn.relu(),
            nn.linear(self.hidden_dim, self.hidden_dim),
            nn.relu(),
            nn.linear(self.hidden_dim, self.hidden_dim),
            nn.relu(),
            nn.linear(self.hidden_dim, self.num_classes),

        )

    def forward(self, x):
        x = self.layers(x)
        return x

model = mlp(input_dim=input_dim, hidden_dim=hidden_dim, num_classes=num_classes).to(device)

optimizer = optimizer.adam(model.parameters(), lr=learning_rate, weight_decay=1e-4)
criterion = nn.crossentropyloss()

num_epoch = 300   # 200e3//len(train_loader)
learning_rate = 1e-3
batch_size = 64
device = torch.device("cuda")
seed = 42
torch.manual_seed(42)

model_finetune = MLP()
model_finetune.load_state_dict(torch.load('model_weights.pth'))
model_finetune.to(device)
model_finetune.train()
# train the network
for t in tqdm(range(num_epoch)):
  for i, data in enumerate(finetune_loader, 0):
    #def closure():
      # Get and prepare inputs
      inputs, targets = data
      inputs, targets = inputs.float(), targets.long()
      inputs, targets = inputs.to(device), targets.to(device)
      
      # Zero the gradients
      optimizer.zero_grad()
      # Perform forward pass
      outputs = model_finetune(inputs)
      # Compute loss
      loss = criterion(outputs, targets)
      # Perform backward pass
      loss.backward()
      #return loss
      optimizer.step()     # a

model_finetune.eval()
with torch.no_grad():
    outputs2 = model_finetune(test_data)
    #predicted_labels = outputs.squeeze().tolist()

    _, preds = torch.max(outputs2, 1)
    prediction_test = np.array(preds.cpu())
    accuracy_test_finetune = accuracy_score(y_test, prediction_test)
    accuracy_test_finetune
    
    Output: 0.9680851063829787