Skip to content

[ENH] Add forecaster support and remove _pkg class for new API #4829

[ENH] Add forecaster support and remove _pkg class for new API

[ENH] Add forecaster support and remove _pkg class for new API #4829

Triggered via pull request September 28, 2026 10:54
Status Failure
Total duration 48m 21s
Artifacts –

test.yml

on: pull_request
code-quality
33s
code-quality
Matrix: no-softdeps
Run notebook tutorials
4m 53s
Run notebook tutorials
Matrix: Run pytest
Matrix: test-deps-2025
Fit to window
Zoom out
Zoom in

Annotations

136 errors, 150 warnings, and 7 notices
Run notebook tutorials
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.10)
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (ubuntu-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.11)
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (ubuntu-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.13)
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (ubuntu-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.14)
Process completed with exit code 1.
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (macos-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.11)
Process completed with exit code 1.
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (windows-latest, 3.11): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.14)
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (ubuntu-latest, 3.14): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.13)
Process completed with exit code 1.
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (macos-latest, 3.13): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.11)
Process completed with exit code 1.
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (macos-latest, 3.11): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.10)
Process completed with exit code 1.
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (macos-latest, 3.10): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.14)
Process completed with exit code 1.
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (windows-latest, 3.14): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.12)
Process completed with exit code 1.
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (macos-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.12)
Process completed with exit code 1.
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (ubuntu-latest, 3.12): pytorch_forecasting/tests/test_all_v2/test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.12)
Process completed with exit code 1.
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (windows-latest, 3.12): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.13)
Process completed with exit code 1.
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (windows-latest, 3.13): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.10)
Process completed with exit code 1.
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-6] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([12, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 12]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([12, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 12]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([12, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([48, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([48, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([48, 12]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([36, 12]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-5] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([24, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 24]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([24, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 24]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([24, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([96, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([96, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([96, 24]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([72, 24]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-3] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-2] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([16, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 16]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([16, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 16]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([16, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([64, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([64, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([64, 16]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([48, 16]) from checkpoint, the shape in current model is t
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[TFT-1] RuntimeError: Error(s) in loading state_dict for TFT: size mismatch for encoder_var_selection.0.weight: copying a param with shape torch.Size([25, 14]) from checkpoint, the shape in current model is torch.Size([64, 14]). size mismatch for encoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for encoder_var_selection.2.weight: copying a param with shape torch.Size([14, 25]) from checkpoint, the shape in current model is torch.Size([14, 64]). size mismatch for decoder_var_selection.0.weight: copying a param with shape torch.Size([25, 8]) from checkpoint, the shape in current model is torch.Size([64, 8]). size mismatch for decoder_var_selection.0.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for decoder_var_selection.2.weight: copying a param with shape torch.Size([8, 25]) from checkpoint, the shape in current model is torch.Size([8, 64]). size mismatch for static_context_linear.weight: copying a param with shape torch.Size([25, 2]) from checkpoint, the shape in current model is torch.Size([64, 2]). size mismatch for static_context_linear.bias: copying a param with shape torch.Size([25]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lstm_encoder.weight_ih_l0: copying a param with shape torch.Size([100, 14]) from checkpoint, the shape in current model is torch.Size([256, 14]). size mismatch for lstm_encoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_encoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_encoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l0: copying a param with shape torch.Size([100, 8]) from checkpoint, the shape in current model is torch.Size([256, 8]). size mismatch for lstm_decoder.weight_hh_l0: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l0: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.weight_ih_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.weight_hh_l1: copying a param with shape torch.Size([100, 25]) from checkpoint, the shape in current model is torch.Size([256, 64]). size mismatch for lstm_decoder.bias_ih_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for lstm_decoder.bias_hh_l1: copying a param with shape torch.Size([100]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for self_attention.in_proj_weight: copying a param with shape torch.Size([75, 25]) from checkpoint, the shape in cu
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-2] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-1] RuntimeError: Error(s) in loading state_dict for Samformer: size mismatch for compute_keys.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_keys.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for compute_queries.weight: copying a param with shape torch.Size([16, 4]) from checkpoint, the shape in current model is torch.Size([32, 4]). size mismatch for compute_queries.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
no-softdeps (windows-latest, 3.10): pytorch_forecasting\tests\test_all_v2\test_all_estimators_v2.py#L66
TestAllPtForecastersV2.test_checkpointing[Samformer-0] RuntimeError: Error(s) in loading state_dict for Samformer: Missing key(s) in state_dict: "revin.affine_weight", "revin.affine_bias".
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.10): ../../../../../opt/hostedtoolcache/Python/3.10.21/x64/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.11): ../../../../../opt/hostedtoolcache/Python/3.11.16/x64/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.13): ../../../../../opt/hostedtoolcache/Python/3.13.15/x64/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.14): ../../../../../Library/Frameworks/Python.framework/Versions/3.14/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.11): C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.14): ../../../../../opt/hostedtoolcache/Python/3.14.7/x64/lib/python3.14/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.13): ../../../../../Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.11): ../../../../../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (macos-latest, 3.10): ../../../../../Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/numpy/_core/fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.14): C:\hostedtoolcache\windows\Python\3.14.7\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (macos-latest, 3.12): ../../../../../Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (ubuntu-latest, 3.12): ../../../../../opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.12): C:\hostedtoolcache\windows\Python\3.12.10\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.13): C:\hostedtoolcache\windows\Python\3.13.15\x64\Lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\lightning\pytorch\utilities\_pytree.py#L21
`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
no-softdeps (windows-latest, 3.10): C:\hostedtoolcache\windows\Python\3.10.11\x64\lib\site-packages\numpy\_core\fromnumeric.py#L4062
The behavior of DataFrame.std with axis=None is deprecated, in a future version this will reduce over both axes and return a scalar. To retain the old behavior, pass axis=0 (or do not pass axis)
code-quality
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
Run notebook tutorials
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
no-softdeps (ubuntu-latest, 3.10)
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
no-softdeps (ubuntu-latest, 3.11)
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
no-softdeps (ubuntu-latest, 3.13)
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
no-softdeps (ubuntu-latest, 3.14)
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
no-softdeps (ubuntu-latest, 3.12)
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"