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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("chelleboyer/llm-mm-good-309e6f79-505b-4c23-8452-37cc854e67df")
# Run inference
sentences = [
    'What metrics does the LLMS (2025) framework introduce to investigate position bias in pairwise comparisons?',
    'Recent studies have further examined position bias in the LLMs-as-judges context.\nFor instance, a framework\xa0(LLMS, 2025) is proposed to investigate position bias in pairwise comparisons, introducing metrics such as repetition stability, position consistency, and preference fairness to better understand how positions affect LLM judgments.\nAnother study\xa0(Zheng et\xa0al., 2023a) explores the limitations of LLMs-as-judges, including position biases, and verifies agreement between LLM judgments and human preferences across multiple benchmarks.\nThese findings underscore the need for robust debiasing strategies to enhance the fairness and reliableness of LLMs-as-judges.',
    'Overconfidence bias\xa0(Khan et\xa0al., 2024; Jung et\xa0al., 2024) in the context of LLMs-as-judges refers to the tendency of models to exhibit an inflated level of confidence in their judgments, often resulting in overly assertive evaluations that may not accurately reflect the true reliability of the answer. This bias is particularly concerning in evaluative contexts, as it can lead LLMs-as-judges to overstate the correctness of certain outputs, compromising the objectivity and dependability of assessments.',
]
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	0.93
cosine_accuracy@3	0.99
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.93
cosine_precision@3	0.33
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.93
cosine_recall@3	0.99
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9704
cosine_mrr@10	0.9603
cosine_map@100	0.9603

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 tokens
mean: 23.12 tokens
max: 72 tokens
min: 3 tokens
mean: 132.04 tokens
max: 306 tokens

Samples:

sentence_0	sentence_1
`What are the main components of the evaluation function ( E ) as described in the preliminaries section?`	LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods[object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object]1 Introduction[object Object][object Object]2 PRELIMINARIES[object Object][object Object]2.1 Evaluation Function E𝐸Eitalic_E[object Object][object Object]2.2 Evaluation Input[object Object][object Object]2.2.1 Evaluation Type 𝒯𝒯\mathcal{T}caligraphic_T[object Object]2.2.2 Evaluation Criteria 𝒞𝒞\mathcal{C}caligraphic_C.[object Object]2.2.3 Evaluation References ℛℛ\mathcal{R}caligraphic_R.[object Object][object Object][object Object]2.3 Evaluation Output[object Object][object Object][object Object][object Object]3 Functionality[object Object][object Object][object Object]3.1 Performance Evaluation[object Object][object Object]3.1.1 Responses Evaluation[object Object]3.1.2 Model Evaluation[object Object][object Object][object Object][object Object]3.2 Model Enhancement[object Object][object Object]3.2.1 Reward Modeling During Training[object Object]3.2.2 Acting as Verifier During Inference[object Object]3.2.3 Feedback for Refinement[object Object][object Object][object Object][object Object]3.3 Data Construction[object Object][object Object]3.3.1 Data Annotation[object Object]3.3.2 Data Synthesize[object Object][object Object][object Object][object Object][object Object][object Object]4 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 Methods[object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object]1 Introduction[object Object][object Object]2 PRELIMINARIES[object Object][object Object]2.1 Evaluation Function E𝐸Eitalic_E[object Object][object Object]2.2 Evaluation Input[object Object][object Object]2.2.1 Evaluation Type 𝒯𝒯\mathcal{T}caligraphic_T[object Object]2.2.2 Evaluation Criteria 𝒞𝒞\mathcal{C}caligraphic_C.[object Object]2.2.3 Evaluation References ℛℛ\mathcal{R}caligraphic_R.[object Object][object Object][object Object]2.3 Evaluation Output[object Object][object Object][object Object][object Object]3 Functionality[object Object][object Object][object Object]3.1 Performance Evaluation[object Object][object Object]3.1.1 Responses Evaluation[object Object]3.1.2 Model Evaluation[object Object][object Object][object Object][object Object]3.2 Model Enhancement[object Object][object Object]3.2.1 Reward Modeling During Training[object Object]3.2.2 Acting as Verifier During Inference[object Object]3.2.3 Feedback for Refinement[object Object][object Object][object Object][object Object]3.3 Data Construction[object Object][object Object]3.3.1 Data Annotation[object Object]3.3.2 Data Synthesize[object Object][object Object][object Object][object Object][object Object][object Object]4 Methodology
`What are the different approaches discussed under the Single-LLM System methodology?`	4 Methodology[object Object][object Object][object Object]4.1 Single-LLM System[object Object][object Object]4.1.1 Prompt-based[object Object]4.1.2 Tuning-based[object Object]4.1.3 Post-processing[object Object][object Object][object Object][object Object]4.2 Multi-LLM System[object Object][object Object]4.2.1 Communication[object Object]4.2.2 Aggregation[object Object][object Object][object Object]4.3 Human-AI Collaboration System[object Object][object Object][object Object][object Object]5 Application[object Object][object Object]5.1 General[object Object]5.2 Multimodal[object Object]5.3 Medical[object Object]5.4 Legal[object Object]5.5 Financial[object Object]5.6 Education[object Object]5.7 Information Retrieval[object Object][object Object]5.8 Others[object Object][object Object]5.8.1 Soft Engineering[object Object]5.8.2 Biology[object Object]5.8.3 Social Science[object Object][object Object][object Object][object Object][object Object][object Object]6 Meta-evaluation[object Object][object Object][object Object]6.1 Benchmarks[object Object][object Object]6.1.1 Code Generation[object Object]6.1.2 Machine Translation[object Object]6.1.3 Text Summarization[object Object]6.1.4 Dialogue Generation[object Object]6.1.5 Automatic Story Generation[object Object]6.1.6 Values Alignment[object Object]6.1.7 Recommendation[object Object]6.1.8 Search[object Object]6.1.9 Comprehensive Data[object Object][object Object][object Object][object Object]6.2 Metric

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

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

Click to expand

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

Epoch	Step	cosine_ndcg@10
1.0	27	0.9697
1.8519	50	0.9788
2.0	54	0.9775
3.0	81	0.9741
3.7037	100	0.9791
4.0	108	0.9741
5.0	135	0.9782
5.5556	150	0.9782
6.0	162	0.9782
7.0	189	0.9782
7.4074	200	0.9741
8.0	216	0.9741
9.0	243	0.9704
9.2593	250	0.9704
10.0	270	0.9704

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: 2.14.4
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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

bibtex

@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}
}

	sentence_0	sentence_1
type	string	string
details	min: 5 tokens mean: 23.12 tokens max: 72 tokens	min: 3 tokens mean: 132.04 tokens max: 306 tokens