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

<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->

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

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

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

  	sentence_0	sentence_1	label
  type	string	string	float
  details	<ul><li>min: 23 tokens</li><li>mean: 90.52 tokens</li><li>max: 157 tokens</li></ul>	<ul><li>min: 23 tokens</li><li>mean: 90.52 tokens</li><li>max: 157 tokens</li></ul>	<ul><li>min: 0.04</li><li>mean: 0.21</li><li>max: 0.62</li></ul>

• Samples:

  sentence_0	sentence_1	label
  <code>[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</code>	<code>[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</code>	<code>0.4869</code>
  <code>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.</code>	<code>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.</code>	<code>0.1521</code>
  <code>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.</code>	<code>[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.</code>	<code>0.16879999999999998</code>

• Loss: <code>CosineSimilarityLoss</code> 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

<details><summary>Click to expand</summary>

• 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: {}

</details>

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",
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->