deepali1021/finetuned_arctic_ft

SentenceTransformer based on Snowflake/snowflake-arctic-embed-l

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Snowflake/snowflake-arctic-embed-l
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, '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("deepali1021/finetuned_arctic_ft")
# Run inference
sentences = [
    'Who should you contact if you have questions or need further information regarding the Transportation Department Policy Manual?',
    "for familiarizing themselves with the latest version of the manual. \n \nConclusion \nThank you for reviewing the Transportation Department Policy Manual. Your commitment to safety, \ncustomer service, and compliance plays a crucial role in our department's success. If you have any \nquestions or need further information, please reach out to your supervisor or the department \nmanager. Your dedication and professionalism are appreciated.",
    'Transportation Department Policy Manual \n \nTable of Contents: \n \n• \nIntroduction \n• \nDepartment Overview \n• \nSafety and Vehicle Maintenance \n• \nDriver Responsibilities \n• \nRoute Planning and Optimization \n• \nCustomer Service \n• \nIncident Reporting and Investigation \n• \nCompliance with Regulations \n• \nTraining and Development \n• \nCommunication and Collaboration \n• \nFare Collection and Fee Structure \n• \nRoute Information and Rules \n• \nAmendments to the Policy Manual \n• \nConclusion \nIntroduction \nWelcome to the Transportation Department Policy Manual! This manual serves as a comprehensive \nguide to the policies, procedures, and expectations for employees working in the transportation',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9375
cosine_accuracy@3	0.9792
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9375
cosine_precision@3	0.3264
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9375
cosine_recall@3	0.9792
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9718
cosine_mrr@10	0.9625
cosine_map@100	0.9625

Training Details

Training Dataset

Unnamed Dataset

• Size: 20 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 20 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 12 tokens mean: 16.3 tokens max: 21 tokens	min: 34 tokens mean: 95.1 tokens max: 122 tokens

• Samples:

  sentence_0	sentence_1
  What topics are covered in the Transportation Department Policy Manual?	Transportation Department Policy Manual Table of Contents: • Introduction • Department Overview • Safety and Vehicle Maintenance • Driver Responsibilities • Route Planning and Optimization • Customer Service • Incident Reporting and Investigation • Compliance with Regulations • Training and Development • Communication and Collaboration • Fare Collection and Fee Structure • Route Information and Rules • Amendments to the Policy Manual • Conclusion Introduction Welcome to the Transportation Department Policy Manual! This manual serves as a comprehensive guide to the policies, procedures, and expectations for employees working in the transportation
  What is the purpose of the Transportation Department Policy Manual?	Transportation Department Policy Manual Table of Contents: • Introduction • Department Overview • Safety and Vehicle Maintenance • Driver Responsibilities • Route Planning and Optimization • Customer Service • Incident Reporting and Investigation • Compliance with Regulations • Training and Development • Communication and Collaboration • Fare Collection and Fee Structure • Route Information and Rules • Amendments to the Policy Manual • Conclusion Introduction Welcome to the Transportation Department Policy Manual! This manual serves as a comprehensive guide to the policies, procedures, and expectations for employees working in the transportation
  What is the primary focus of the Transportation Department as outlined in the manual?	department. It provides guidelines to ensure safe, efficient, and customer-focused transportation services. Please read this manual carefully and consult with your supervisor or the department manager if you have any questions or need further clarification. Department Overview The Transportation Department plays a critical role in providing reliable transportation services to our customers. Our department consists of 50 drivers, 10 dispatchers, and 5 maintenance technicians. In the past year, we transported over 500,000 passengers across various routes, ensuring their safety and satisfaction. Safety and Vehicle Maintenance Safety is our top priority. All vehicles undergo regular inspections and maintenance to ensure they

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 10
• per_device_eval_batch_size: 10
• num_train_epochs: 10
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 10
• per_device_eval_batch_size: 10
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• 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: {}
• warmup_ratio: 0.0
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• 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
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_ndcg@10
1.0	2	0.8107
2.0	4	0.9292
3.0	6	0.9623
4.0	8	0.9712
5.0	10	0.9642
6.0	12	0.9642
7.0	14	0.9642
8.0	16	0.9642
9.0	18	0.9718
10.0	20	0.9718

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}