[time series] updated expected values for integration test. (#21762)

* updated expected

* prediction_length fix

* prediction_length default value

* default prediction_length 24

* revert back prediction_length default

* move prediction_length test

src/transformers/models/time_series_transformer/configuration_time_series_transformer.py

@@ -44,7 +44,8 @@ class TimeSeriesTransformerConfig(PretrainedConfig):
 
     Args:
         prediction_length (`int`):
-            The prediction length for the decoder. In other words, the prediction horizon of the model.
+            The prediction length for the decoder. In other words, the prediction horizon of the model. This value is
+            typically dictated by the dataset and we recommend to set it appropriately.
         context_length (`int`, *optional*, defaults to `prediction_length`):
             The context length for the encoder. If `None`, the context length will be the same as the
             `prediction_length`.
@@ -60,8 +61,8 @@ class TimeSeriesTransformerConfig(PretrainedConfig):
             Whether to scale the input targets via "mean" scaler, "std" scaler or no scaler if `None`. If `True`, the
             scaler is set to "mean".
         lags_sequence (`list[int]`, *optional*, defaults to `[1, 2, 3, 4, 5, 6, 7]`):
-            The lags of the input time series as covariates often dictated by the frequency. Default is `[1, 2, 3, 4,
-            5, 6, 7]`.
+            The lags of the input time series as covariates often dictated by the frequency of the data. Default is
+            `[1, 2, 3, 4, 5, 6, 7]` but we recommend to change it based on the dataset appropriately.
         num_time_features (`int`, *optional*, defaults to 0):
             The number of time features in the input time series.
         num_dynamic_real_features (`int`, *optional*, defaults to 0):
@@ -117,8 +118,8 @@ class TimeSeriesTransformerConfig(PretrainedConfig):
     ```python
     >>> from transformers import TimeSeriesTransformerConfig, TimeSeriesTransformerModel
 
-    >>> # Initializing a default Time Series Transformer configuration
-    >>> configuration = TimeSeriesTransformerConfig()
+    >>> # Initializing a Time Series Transformer configuration with 12 time steps for prediction
+    >>> configuration = TimeSeriesTransformerConfig(prediction_length=12)
 
     >>> # Randomly initializing a model (with random weights) from the configuration
     >>> model = TimeSeriesTransformerModel(configuration)

src/transformers/models/time_series_transformer/modeling_time_series_transformer.py

@@ -1176,6 +1176,8 @@ class TimeSeriesTransformerEncoder(TimeSeriesTransformerPreTrainedModel):
 
         self.dropout = config.dropout
         self.layerdrop = config.encoder_layerdrop
+        if config.prediction_length is None:
+            raise ValueError("The `prediction_length` config needs to be specified.")
 
         self.value_embedding = ValueEmbedding(feature_size=config.feature_size, d_model=config.d_model)
         self.embed_positions = TimeSeriesSinusoidalPositionalEmbedding(
@@ -1311,6 +1313,8 @@ class TimeSeriesTransformerDecoder(TimeSeriesTransformerPreTrainedModel):
         super().__init__(config)
         self.dropout = config.dropout
         self.layerdrop = config.decoder_layerdrop
+        if config.prediction_length is None:
+            raise ValueError("The `prediction_length` config needs to be specified.")
 
         self.value_embedding = ValueEmbedding(feature_size=config.feature_size, d_model=config.d_model)
         self.embed_positions = TimeSeriesSinusoidalPositionalEmbedding(

tests/models/time_series_transformer/test_modeling_time_series_transformer.py

@@ -401,7 +401,7 @@ class TimeSeriesTransformerModelIntegrationTests(unittest.TestCase):
         self.assertEqual(output.shape, expected_shape)
 
         expected_slice = torch.tensor(
-            [[-0.6322, -1.5771, -0.9340], [-0.1011, -1.0263, -0.7208], [0.4979, -0.6487, -0.7189]], device=torch_device
+            [[0.8196, -1.5131, 1.4620], [1.1268, -1.3238, 1.5997], [1.5098, -1.0715, 1.7359]], device=torch_device
         )
         self.assertTrue(torch.allclose(output[0, :3, :3], expected_slice, atol=TOLERANCE))
 
@@ -423,7 +423,7 @@ class TimeSeriesTransformerModelIntegrationTests(unittest.TestCase):
         self.assertEqual(output.shape, expected_shape)
 
         expected_slice = torch.tensor(
-            [[0.8177, -1.7989, -0.3127], [1.6964, -1.0607, -0.1749], [1.8395, 0.1110, 0.0263]], device=torch_device
+            [[-1.2957, -1.0280, -0.6045], [-0.7017, -0.8193, -0.3717], [-1.0449, -0.8149, 0.1405]], device=torch_device
         )
         self.assertTrue(torch.allclose(output[0, :3, :3], expected_slice, atol=TOLERANCE))
 
@@ -444,6 +444,6 @@ class TimeSeriesTransformerModelIntegrationTests(unittest.TestCase):
         expected_shape = torch.Size((64, model.config.num_parallel_samples, model.config.prediction_length))
         self.assertEqual(outputs.sequences.shape, expected_shape)
 
-        expected_slice = torch.tensor([3883.5037, 4630.2251, 7562.1338], device=torch_device)
+        expected_slice = torch.tensor([2825.2749, 3584.9207, 6763.9951], device=torch_device)
         mean_prediction = outputs.sequences.mean(dim=1)
         self.assertTrue(torch.allclose(mean_prediction[0, -3:], expected_slice, rtol=1e-1))