Hi All, Facing issue while using AI Center after creating the pipeline

Train only of invoice_mlpkg 23.10.3.0 launched - Run 38056316-4051-455c-8ee6-4fb29bed3bf1
Train only of invoice_mlpkg 23.10.3.0 started - Run 38056316-4051-455c-8ee6-4fb29bed3bf1
Train only of invoice_mlpkg 23.10.3.0 scheduled - Run 38056316-4051-455c-8ee6-4fb29bed3bf1
Train only of invoice_mlpkg 23.10.3.0 failed - Run 38056316-4051-455c-8ee6-4fb29bed3bf1

Error Details : Pipeline failed due to ML Package Issue

2024-04-03 10:54:05,260 - UiPath_core.trainer_run:main:83 - INFO: Starting training job…
2024-04-03 10:54:07,527 - matplotlib:_get_config_or_cache_dir:531 - WARNING: Matplotlib created a temporary cache directory at /tmp/matplotlib-j71im7ia because the default path (/.config/matplotlib) is not a writable directory; it is highly recommended to set the MPLCONFIGDIR environment variable to a writable directory, in particular to speed up the import of Matplotlib and to better support multiprocessing.
2024-04-03 10:54:07,778 - matplotlib.font_manager:_load_fontmanager:1547 - INFO: generated new fontManager
2024-04-03 10:54:13,228 - UiPath_core.storage.azure_storage_client:download:118 - INFO: Dataset from bucket folder training-062a796d-d428-484b-8445-9ca136a286c0/debf9b51-dc89-4cc6-86ae-ad282680c465/dcf1af27-a937-4029-a417-1af9351e1a91/InvoiceExport_24-04-03T103138 with size 52 downloaded successfully
2024-04-03 10:54:13,229 - UiPath_core.training_plugin:train_model:129 - INFO: Start model training…
2024-04-03 10:54:13,229 - UiPath_core.training_plugin:initialize_model:123 - INFO: Start model initialization…
2024-04-03 10:54:13,229 - root:initialize_package:208 - INFO: Using package type provided by runtime argument with value: invoices
2024-04-03 10:54:13,229 - root:initialize_package:217 - INFO: Initializing invoices package options …
2024-04-03 10:54:13,231 - root:configure_options:196 - INFO: Document type invoices language: en
2024-04-03 10:54:13,231 - root:configure_options:215 - INFO: Training with random slices: True
2024-04-03 10:54:13,232 - root:configure_options:216 - INFO: Sample by size: True
2024-04-03 10:54:13,232 - root:initialize_package:222 - INFO: System-Level Configuration:
2024-04-03 10:54:13,232 - root:initialize_package:223 - INFO: ATen/Parallel:
at::get_num_threads() : 15
at::get_num_interop_threads() : 15
OpenMP 201511 (a.k.a. OpenMP 4.5)
omp_get_max_threads() : 15
Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
mkl_get_max_threads() : 15
Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
std::thread::hardware_concurrency() : 16
Environment variables:
OMP_NUM_THREADS : 15
MKL_NUM_THREADS : [not set]
ATen parallel backend: OpenMP

2024-04-03 10:54:13,232 - root:init:28 - INFO: Pipeline Type: TRAIN_ONLY
2024-04-03 10:54:13,232 - UiPath_core.training_plugin:initialize_model:126 - INFO: Model initialized successfully
2024-04-03 10:54:13,232 - root:log_data_version_info:13 - INFO: =========Data version information=========
2024-04-03 10:54:13,234 - root:log_data_version_info:17 - WARNING: Unknown data version:
2024-04-03 10:54:13,234 - root:log_data_version_info:None - INFO: ==========================================
2024-04-03 10:54:13,234 - root:preprocess_data:706 - INFO: Creating dataset for document type invoices…
2024-04-03 10:54:13,258 - root:preprocess_data:710 - INFO: Doctype invoices Statistics:
2024-04-03 10:54:13,258 - root:preprocess_data:714 - INFO:
Extraction fields:
tag[description] = 977
tag[unit-price] = 233
tag[quantity] = 162
tag[line-amount] = 162
tag[billing-address] = 84
tag[vendor-address] = 69
tag[shipping-address] = 69
tag[billing-name] = 28
tag[invoice-date] = 22
tag[net-amount] = 13
tag[invoice-number] = 13
tag[vendor-name] = 12
tag[tax-amount] = 12
tag[total-amount] = 12
tag[shipping-charges] = 6

Subsets:
subset[TEST] = 12

2024-04-03 10:54:13,258 - root:create_processor:60 - INFO: Loading LayoutLMv3 processor from HuggingFace …
2024-04-03 10:54:13,422 - root:create_multiprocessing_pool:None - INFO: Creating pool with 4 processes …
2024-04-03 10:54:14,785 - root:preprocess_data:791 - INFO: train: (0, 12) pages of (0, 7) documents
2024-04-03 10:54:14,785 - root:preprocess_data:792 - INFO: test: (0, 12) pages of (0, 7) documents
2024-04-03 10:54:14,795 - UiPath_core.training_plugin:model_run:189 - ERROR: Training failed for pipeline type: TRAIN_ONLY, error: division by zero
2024-04-03 10:54:14,805 - UiPath_core.trainer_run:main:100 - ERROR: Training Job failed, error: division by zero
Traceback (most recent call last):
File “/model/bin/UiPath_core/trainer_run.py”, line 95, in main
wrapper.run()
File “/workspace/model/microservice/training_wrapper.py”, line 65, in run
return self.training_plugin.model_run()
File “/model/bin/UiPath_core/training_plugin.py”, line 205, in model_run
raise ex
File “/model/bin/UiPath_core/training_plugin.py”, line 181, in model_run
self.run_train_only()
File “/model/bin/UiPath_core/training_plugin.py”, line 268, in run_train_only
score = self.train_model(self.local_dataset_directory)
File “/model/bin/UiPath_core/training_plugin.py”, line 131, in train_model
response = self.model.train(directory)
File “/workspace/model/microservice/train.py”, line 53, in train
self.process_data()
File “/workspace/model/microservice/train.py”, line 101, in process_data
self.dataset = dataset.Dataset(self.opt)
File “”, line 237, in init
File “”, line 75, in init
File “”, line 794, in preprocess_data
ZeroDivisionError: division by zero
2024-04-03 10:54:14,805 - UiPath_core.trainer_run:main:107 - INFO: Job run stopped.

@abhishek.singh1 , it is very important in AIC center that whatever version of ML skill you are using for making pipeline. The pipeline should also has same lower version otherwise it will fail.

Thanks

Hi @Dr_Anand_Upadhyay I am using the same or lower version of ML skills in Pipeline, still having the same issue. Can you Please explain it in a broader way or any example would be really helpful.