midterm-compare-arctic-embed-m-ft

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

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-m. It maps sentences & paragraphs to a 768-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-m <!-- at revision fc74610d18462d218e312aa986ec5c8a75a98152 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **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({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("drewgenai/midterm-compare-arctic-embed-m-ft")
# Run inference
sentences = [
    'How does the Work-Related Stress Scale (WRSS-8) assess the impact of workplace stress?',
    'Linked Psychological & Physical Assessment\nPain Coping Strategy Scale (PCSS-9)\nThe PCSS-9 measures how individuals adjust to chronic pain and its impact on their lifestyle, using\na structured 9-item scale.\nAssessment Questions:\nI change my daily routine to reduce pain impact. (Scale: 0-5)\nI mentally prepare myself before engaging in painful activities. (Scale: 0-5)\nI use relaxation techniques to minimize pain perception. (Scale: 0-5)\nI focus on positive thinking to help manage pain. (Scale: 0-5)\nWork-Related Stress Scale (WRSS-8)\nThe WRSS-8 evaluates work-induced stress and its psychological effects.\nAssessment Questions:\nI feel exhausted after a standard workday. (Scale: 0-3)\nI struggle to stay motivated due to workplace stress. (Scale: 0-3)\nI feel overwhelmed when handling multiple responsibilities. (Scale: 0-3)\nI find it difficult to disconnect from work-related concerns. (Scale: 0-3)\nDecision-Making Confidence Scale (DMCS-6)\nThe DMCS-6 evaluates confidence in making personal and professional decisions.\nAssessment Questions:\nI feel confident when making important decisions. (Scale: 0-3)\nI second-guess myself often when making choices. (Scale: 0-3)\nI trust my instincts when faced with uncertainty. (Scale: 0-3)',
    'Linked Psychological & Physical Assessment\nPain Coping Strategy Scale (PCSS-9)\nThe PCSS-9 measures how individuals adjust to chronic pain and its impact on their lifestyle, using\na structured 9-item scale.\nAssessment Questions:\nI change my daily routine to reduce pain impact. (Scale: 0-5)\nI mentally prepare myself before engaging in painful activities. (Scale: 0-5)\nI use relaxation techniques to minimize pain perception. (Scale: 0-5)\nI focus on positive thinking to help manage pain. (Scale: 0-5)\nWork-Related Stress Scale (WRSS-8)\nThe WRSS-8 evaluates work-induced stress and its psychological effects.\nAssessment Questions:\nI feel exhausted after a standard workday. (Scale: 0-3)\nI struggle to stay motivated due to workplace stress. (Scale: 0-3)\nI feel overwhelmed when handling multiple responsibilities. (Scale: 0-3)\nI find it difficult to disconnect from work-related concerns. (Scale: 0-3)\nDecision-Making Confidence Scale (DMCS-6)\nThe DMCS-6 evaluates confidence in making personal and professional decisions.\nAssessment Questions:\nI feel confident when making important decisions. (Scale: 0-3)\nI second-guess myself often when making choices. (Scale: 0-3)\nI trust my instincts when faced with uncertainty. (Scale: 0-3)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

<!-- ### 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.* -->

Evaluation

Metrics

Information Retrieval

• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## 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: 8 training samples
• Columns: <code>sentence_0</code> and <code>sentence_1</code>
• Approximate statistics based on the first 8 samples:

  	sentence_0	sentence_1
  type	string	string
  details	<ul><li>min: 13 tokens</li><li>mean: 21.25 tokens</li><li>max: 30 tokens</li></ul>	<ul><li>min: 272 tokens</li><li>mean: 283.5 tokens</li><li>max: 296 tokens</li></ul>

• Samples:

  sentence_0	sentence_1
  <code>What does the ERI-9 assess in individuals?</code>	<code>The ERI-9 assesses an individual's ability to regulate emotions under stress.<br>Assessment Questions:<br>I can calm myself down after getting upset. (Scale: 0-3)<br>I tend to overreact to small inconveniences. (Scale: 0-3)<br>I struggle to manage my emotions under pressure. (Scale: 0-3)<br>I practice deep breathing exercises to stay emotionally stable. (Scale: 0-3)<br>Social Confidence Measure (SCM-6)<br>The SCM-6 evaluates levels of confidence in social interactions and public speaking.<br>Assessment Questions:<br>I feel comfortable introducing myself to new people. (Scale: 0-3)<br>I feel anxious in large social gatherings. (Scale: 0-3)<br>I express myself clearly in conversations. (Scale: 0-3)<br>I maintain eye contact while speaking. (Scale: 0-3)<br>Memory Retention Index (MRI-6)<br>The MRI-6 evaluates short-term and long-term memory recall abilities.<br>Assessment Questions:<br>I easily remember names and faces. (Scale: 0-3)<br>I often forget where I placed important items. (Scale: 0-3)<br>I have difficulty recalling specific details...</code>
  <code>How does the SCM-6 measure confidence in social interactions?</code>	<code>The ERI-9 assesses an individual's ability to regulate emotions under stress.<br>Assessment Questions:<br>I can calm myself down after getting upset. (Scale: 0-3)<br>I tend to overreact to small inconveniences. (Scale: 0-3)<br>I struggle to manage my emotions under pressure. (Scale: 0-3)<br>I practice deep breathing exercises to stay emotionally stable. (Scale: 0-3)<br>Social Confidence Measure (SCM-6)<br>The SCM-6 evaluates levels of confidence in social interactions and public speaking.<br>Assessment Questions:<br>I feel comfortable introducing myself to new people. (Scale: 0-3)<br>I feel anxious in large social gatherings. (Scale: 0-3)<br>I express myself clearly in conversations. (Scale: 0-3)<br>I maintain eye contact while speaking. (Scale: 0-3)<br>Memory Retention Index (MRI-6)<br>The MRI-6 evaluates short-term and long-term memory recall abilities.<br>Assessment Questions:<br>I easily remember names and faces. (Scale: 0-3)<br>I often forget where I placed important items. (Scale: 0-3)<br>I have difficulty recalling specific details...</code>
  <code>What is the purpose of the Pain Coping Strategy Scale (PCSS-9)?</code>	<code>Linked Psychological & Physical Assessment<br>Pain Coping Strategy Scale (PCSS-9)<br>The PCSS-9 measures how individuals adjust to chronic pain and its impact on their lifestyle, using<br>a structured 9-item scale.<br>Assessment Questions:<br>I change my daily routine to reduce pain impact. (Scale: 0-5)<br>I mentally prepare myself before engaging in painful activities. (Scale: 0-5)<br>I use relaxation techniques to minimize pain perception. (Scale: 0-5)<br>I focus on positive thinking to help manage pain. (Scale: 0-5)<br>Work-Related Stress Scale (WRSS-8)<br>The WRSS-8 evaluates work-induced stress and its psychological effects.<br>Assessment Questions:<br>I feel exhausted after a standard workday. (Scale: 0-3)<br>I struggle to stay motivated due to workplace stress. (Scale: 0-3)<br>I feel overwhelmed when handling multiple responsibilities. (Scale: 0-3)<br>I find it difficult to disconnect from work-related concerns. (Scale: 0-3)<br>Decision-Making Confidence Scale (DMCS-6)<br>The DMCS-6 evaluates confidence in making personal and pr...</code>

• Loss: <code>MatryoshkaLoss</code> 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: 5
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

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

• 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: 5
• 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

</details>

Training Logs

Framework Versions

• Python: 3.13.1
• Sentence Transformers: 3.4.1
• Transformers: 4.49.0
• PyTorch: 2.6.0+cu124
• Accelerate: 1.4.0
• 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}
}

<!-- ## 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.* -->