runtime error

Exit code: 1. Reason: able `TF_ENABLE_ONEDNN_OPTS=0`. 2026-01-27 05:45:38.835965: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-01-27 05:45:41.171711: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-01-27 05:45:42.399114: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303) WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model. Traceback (most recent call last): File "/app/app.py", line 50, in <module> decoder_lstm_outputs,state_h, state_c = decoder_lstm(dec_emb2, initial_state=(dec_state_input_h, dec_state_input_c)) ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler raise e.with_traceback(filtered_tb) from None File "/usr/local/lib/python3.13/site-packages/keras/src/layers/input_spec.py", line 161, in assert_input_compatibility raise ValueError( ...<3 lines>... ) ValueError: Layer "lstm_1" expects 1 input(s), but it received 3 input tensors. Inputs received: [<KerasTensor shape=(None, 256), dtype=float32, sparse=False, ragged=False, name=keras_tensor_25>, <KerasTensor shape=(None, 256), dtype=float32, sparse=False, ragged=False, name=keras_tensor_26>, <KerasTensor shape=(None, 256), dtype=float32, sparse=False, ragged=False, name=keras_tensor_27>]

Container logs: