kevin-rice/ticket-similarity-finetuned

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Maximum Sequence Length: 384 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'MPNetModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): Normalize({})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    "Order shows success message but not created when assignee has no assigned warehousen Demo WeComm, while placing a POS Order, select Mary Yed as the Assignee in the Enter Warehouse Pick Details popup.\\nAfter submission, the system displays:\\nOrder placed successfully\\nError message: User doesn't have assigned Warehouse\\nThis is contradictory behavior. Even though a success message is shown, the POS order/order number cannot be found in Customer Orders > Manage Customer Orders.",
    'POS order allows quantity greater than available stock and marks order as deliveredIn Demo WeComm, under Manage Products, the product Viktos Taculus MX Chest Rig Bag shows available stock as 2.\\nHowever, the system allows creation of a POS Order for 3 units of the same product without showing any validation or out-of-stock error. The order is then processed and marked as Delivered.\\nThis indicates inventory validation is not enforced during POS order placement.',
    'Incorrect order number displayed and wrong delivery status message shown in notificationsNavigate to Warehouse > Orders > Customer Orders and open the Notifications panel.\\nTwo issues are observed in order notifications:\\nNotification order number does not match the actual order number shown in the Customer Orders grid.\\nAfter the product/order status is marked as Delivered, the notification message still says \\"Ready for shipping\\" instead of confirming delivery.\\nThis causes confusion for users regarding actual order references and shipment status.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.0924, 0.1173],
#         [0.0924, 1.0000, 0.0839],
#         [0.1173, 0.0839, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 242 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 242 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 23 tokens mean: 90.52 tokens max: 157 tokens	min: 23 tokens mean: 90.52 tokens max: 157 tokens	min: 0.04 mean: 0.21 max: 0.62

• Samples:

  sentence_0	sentence_1	label
  [Admin] HTTP 500 / Permission denied error when creating product from Manage ProductsNavigate to Manage Products and click Create Product to open the Create Product UI. After filling all mandatory fields and clicking the Create button, the system throws an HTTP 500 Internal Server Error instead of creating the product successfully.\n \n Observed Error:\n The stream or file "/home/assets.wecomm.info/public_html/storage/logs/activity/laravel-2024-10-01.log" could not be opened in append mode: Failed to open stream: Permission denied	[Admin] Permission denied / Failed to open stream error when submitting Manual Product InboundNavigate to Manage Assets > Manage Products > Products Inbound and select Manual Inbound. Click Create Inbound to open the Product Inbound UI. In the Scan or Search Barcode section, enter a barcode and fill in all required fields. After clicking the Submit button, the system throws an error instead of creating the inbound record successfully.\n \n Observed Error:\n The stream or file "/home/assets.wecomm.info/public_html/storage/logs/activity/laravel-2024-10-01.log" could not be opened in append mode: Failed to open stream: Permission denied	0.4869
  Accounting Template Column Displays Incorrect/Random DataWhen navigating to Reports > Customer Orders and opening the Customer Order Details report, the Accounting Template column is displaying random or irrelevant text instead of the actual accounting template associated with the order.	Update Returned/Exchanged Items section in View Warehouse Return UI to show Accounting Template and Requisition NumberIn the Warehouse > Manage Inventory > Return Items module, selecting the eye icon in the Action column opens the View Warehouse Return UI.\nUnder the Returned/Exchanged Items section, the table should be updated to include the Accounting Template and Requisition Number related to the order.\nAdditionally, the SKU and Condition columns should be removed if they are not required for business operations.	0.1521
  Product stock becomes negative after POS delivery and stock count displayed as -1In Demo WeComm > Manage Products, after a POS order was processed and marked as Delivered for Viktos Taculus MX Chest Rig Bag, the product stock updated to -1.\nInventory stock should never become negative. The system allowed fulfillment beyond available quantity and reduced stock below zero.\nAdditionally, the product price is displayed as $95.00 after the transaction.	[Admin] Available product quantity not updated after adding stock at product locationAs an Admin, create a product and update the Product Location with stock levels. Even though the selected location shows the product as In Stock, the Available Quantity field does not get updated and remains incorrect.	0.16879999999999998

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss",
      "cos_score_transformation": "torch.nn.modules.linear.Identity"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 10
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: None
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Time

• Training: 2.6 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.4.0
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}