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("chelleboyer/llm-mm-good-eb8e3f60-56f2-4729-8934-2428ca568d27")
# Run inference
sentences = [
    'How do Dong et al. (2022) contribute to the understanding of in-context learning in their survey?',
    'Dong et\xa0al. (2024a)\n\nQingxiu Dong, Li Dong, Xingxing Zhang, Zhifang Sui, and Furu Wei. 2024a.\n\n\nSelf-Boosting Large Language Models with Synthetic Preference Data.\n\n\narXiv preprint arXiv:2410.06961 (2024).\n\n\n\n\n\n\nDong et\xa0al. (2022)\n\nQingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Tianyu Liu, et\xa0al. 2022.\n\n\nA survey on in-context learning.\n\n\narXiv preprint arXiv:2301.00234 (2022).\n\n\n\n\n\n\nDong et\xa0al. (2024b)\n\nYijiang\xa0River Dong, Tiancheng Hu, and Nigel Collier. 2024b.\n\n\nCan LLM be a Personalized Judge?\n\n\narXiv preprint arXiv:2406.11657 (2024).\n\n\n\n\n\n\nDorner et\xa0al. (2024)\n\nFlorian\xa0E. Dorner, Vivian\xa0Y. Nastl, and Moritz Hardt. 2024.',
    'Additionally, the LLMAAA\xa0(Zhang et\xa0al., 2023a) framework incorporates an active learning strategy to efficiently select high-information samples for annotation, thereby mitigating the effects of noisy labels and reducing the reliance on costly human annotation. These approach not only enhance the performance of task-specific models but also offer new perspectives on the efficient application of LLMs in annotation workflows.',
]
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

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,334 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 5 tokensmean: 23.14 tokensmax: 69 tokens	min: 3 tokensmean: 132.04 tokensmax: 306 tokens

• Samples:

  sentence_0	sentence_1
  What are the key components of the evaluation function ( E ) as described in the preliminaries section?	LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods1 Introduction2 PRELIMINARIES2.1 Evaluation Function E𝐸Eitalic_E2.2 Evaluation Input2.2.1 Evaluation Type 𝒯𝒯\mathcal{T}caligraphic_T2.2.2 Evaluation Criteria 𝒞𝒞\mathcal{C}caligraphic_C.2.2.3 Evaluation References ℛℛ\mathcal{R}caligraphic_R.2.3 Evaluation Output3 Functionality3.1 Performance Evaluation3.1.1 Responses Evaluation3.1.2 Model Evaluation3.2 Model Enhancement3.2.1 Reward Modeling During Training3.2.2 Acting as Verifier During Inference3.2.3 Feedback for Refinement3.3 Data Construction3.3.1 Data Annotation3.3.2 Data Synthesize4 Methodology
  How do LLMs contribute to model enhancement according to the functionalities outlined in the survey?	LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods1 Introduction2 PRELIMINARIES2.1 Evaluation Function E𝐸Eitalic_E2.2 Evaluation Input2.2.1 Evaluation Type 𝒯𝒯\mathcal{T}caligraphic_T2.2.2 Evaluation Criteria 𝒞𝒞\mathcal{C}caligraphic_C.2.2.3 Evaluation References ℛℛ\mathcal{R}caligraphic_R.2.3 Evaluation Output3 Functionality3.1 Performance Evaluation3.1.1 Responses Evaluation3.1.2 Model Evaluation3.2 Model Enhancement3.2.1 Reward Modeling During Training3.2.2 Acting as Verifier During Inference3.2.3 Feedback for Refinement3.3 Data Construction3.3.1 Data Annotation3.3.2 Data Synthesize4 Methodology
  What are the different approaches discussed under the Single-LLM System methodology?	4 Methodology4.1 Single-LLM System4.1.1 Prompt-based4.1.2 Tuning-based4.1.3 Post-processing4.2 Multi-LLM System4.2.1 Communication4.2.2 Aggregation4.3 Human-AI Collaboration System5 Application5.1 General5.2 Multimodal5.3 Medical5.4 Legal5.5 Financial5.6 Education5.7 Information Retrieval5.8 Others5.8.1 Soft Engineering5.8.2 Biology5.8.3 Social Science6 Meta-evaluation6.1 Benchmarks6.1.1 Code Generation6.1.2 Machine Translation6.1.3 Text Summarization6.1.4 Dialogue Generation6.1.5 Automatic Story Generation6.1.6 Values Alignment6.1.7 Recommendation6.1.8 Search6.1.9 Comprehensive Data6.2 Metric

• 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: 50
• per_device_eval_batch_size: 50
• num_train_epochs: 10
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 50
• per_device_eval_batch_size: 50
• 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}
• tp_size: 0
• 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
• 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

Framework Versions

• Python: 3.11.12
• Sentence Transformers: 3.4.1
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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}
}