fix: Timegan loss training (#100)

Co-authored-by: Francisco Santos <36741643+jfsantos-ds@users.noreply.github.com>
Co-authored-by: Arunn Thevapalan <arunn.work@gmail.com>
Co-authored-by: Miguel Campos <mgl.mcampos@gmail.com>

Author: 4 people

src/ydata_synthetic/synthesizers/timeseries/timegan/model.py

@@ -34,6 +34,9 @@ def make_net(model, n_layers, hidden_units, output_units, net_type='GRU'):
 
 
 class TimeGAN(BaseModel):
+
+    __MODEL__='TimeGAN'
+
     def __init__(self, model_parameters, hidden_dim, seq_len, n_seq, gamma):
         self.seq_len=seq_len
         self.n_seq=n_seq