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 tokens
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("jeevanions/finetuned_arctic-embedd-l")
# Run inference
sentences = [
    'How should risks or trustworthiness characteristics that cannot be measured be documented?',
    'MEASURE 1.1: Approaches and metrics for measurement of AI risks enumerated during the MAP function are selected for \nimplementation starting with the most signiﬁcant AI risks. The risks or trustworthiness characteristics that will not – or cannot – be \nmeasured are properly documented. \nAction ID \nSuggested Action \nGAI Risks \nMS-1.1-001 Employ methods to trace the origin and modiﬁcations of digital content. \nInformation Integrity \nMS-1.1-002 \nIntegrate tools designed to analyze content provenance and detect data \nanomalies, verify the authenticity of digital signatures, and identify patterns \nassociated with misinformation or manipulation. \nInformation Integrity \nMS-1.1-003 \nDisaggregate evaluation metrics by demographic factors to identify any \ndiscrepancies in how content provenance mechanisms work across diverse \npopulations. \nInformation Integrity; Harmful \nBias and Homogenization \nMS-1.1-004 Develop a suite of metrics to evaluate structured public feedback exercises',
    'existing human performance considered as a performance baseline for the algorithm to meet pre-deployment, \nand as a lifecycle minimum performance standard. Decision possibilities resulting from performance testing \nshould include the possibility of not deploying the system. \nRisk identification and mitigation. Before deployment, and in a proactive and ongoing manner, poten\xad\ntial risks of the automated system should be identified and mitigated. Identified risks should focus on the \npotential for meaningful impact on people’s rights, opportunities, or access and include those to impacted \ncommunities that may not be direct users of the automated system, risks resulting from purposeful misuse of \nthe system, and other concerns identified via the consultation process. Assessment and, where possible, mea\xad\nsurement of the impact of risks should be included and balanced such that high impact risks receive attention',
]
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	0.2807
cosine_accuracy@3	0.4649
cosine_accuracy@5	0.5351
cosine_accuracy@10	0.7193
cosine_precision@1	0.2807
cosine_precision@3	0.155
cosine_precision@5	0.107
cosine_precision@10	0.0719
cosine_recall@1	0.2807
cosine_recall@3	0.4649
cosine_recall@5	0.5351
cosine_recall@10	0.7193
cosine_ndcg@10	0.4797
cosine_mrr@10	0.4064
cosine_map@100	0.4236
dot_accuracy@1	0.2807
dot_accuracy@3	0.4649
dot_accuracy@5	0.5351
dot_accuracy@10	0.7193
dot_precision@1	0.2807
dot_precision@3	0.155
dot_precision@5	0.107
dot_precision@10	0.0719
dot_recall@1	0.2807
dot_recall@3	0.4649
dot_recall@5	0.5351
dot_recall@10	0.7193
dot_ndcg@10	0.4797
dot_mrr@10	0.4064
dot_map@100	0.4236

Training Details

Training Dataset

Unnamed Dataset

Size: 3,430 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: 8 tokens
mean: 17.71 tokens
max: 36 tokens

min: 7 tokens
mean: 172.72 tokens
max: 356 tokens

	sentence_0	sentence_1
type	string	string
details	min: 8 tokens mean: 17.71 tokens max: 36 tokens	min: 7 tokens mean: 172.72 tokens max: 356 tokens

Samples:

sentence_0	sentence_1
`What are the key steps to obtain input from stakeholder communities to identify unacceptable use in AI systems?`	15 GV-1.3-004 Obtain input from stakeholder communities to identify unacceptable use, in accordance with activities in the AI RMF Map function. CBRN Information or Capabilities; Obscene, Degrading, and/or Abusive Content; Harmful Bias and Homogenization; Dangerous, Violent, or Hateful Content GV-1.3-005 Maintain an updated hierarchy of identiﬁed and expected GAI risks connected to contexts of GAI model advancement and use, potentially including specialized risk levels for GAI systems that address issues such as model collapse and algorithmic monoculture. Harmful Bias and Homogenization GV-1.3-006 Reevaluate organizational risk tolerances to account for unacceptable negative risk (such as where signiﬁcant negative impacts are imminent, severe harms are actually occurring, or large-scale risks could occur); and broad GAI negative risks, including: Immature safety or risk cultures related to AI and GAI design, development and deployment, public information integrity risks, including impacts
`How can organizations maintain an updated hierarchy of identified and expected GAI risks?`	15 GV-1.3-004 Obtain input from stakeholder communities to identify unacceptable use, in accordance with activities in the AI RMF Map function. CBRN Information or Capabilities; Obscene, Degrading, and/or Abusive Content; Harmful Bias and Homogenization; Dangerous, Violent, or Hateful Content GV-1.3-005 Maintain an updated hierarchy of identiﬁed and expected GAI risks connected to contexts of GAI model advancement and use, potentially including specialized risk levels for GAI systems that address issues such as model collapse and algorithmic monoculture. Harmful Bias and Homogenization GV-1.3-006 Reevaluate organizational risk tolerances to account for unacceptable negative risk (such as where signiﬁcant negative impacts are imminent, severe harms are actually occurring, or large-scale risks could occur); and broad GAI negative risks, including: Immature safety or risk cultures related to AI and GAI design, development and deployment, public information integrity risks, including impacts
`What are some examples of unacceptable uses of AI as identified by stakeholder communities?`	15 GV-1.3-004 Obtain input from stakeholder communities to identify unacceptable use, in accordance with activities in the AI RMF Map function. CBRN Information or Capabilities; Obscene, Degrading, and/or Abusive Content; Harmful Bias and Homogenization; Dangerous, Violent, or Hateful Content GV-1.3-005 Maintain an updated hierarchy of identiﬁed and expected GAI risks connected to contexts of GAI model advancement and use, potentially including specialized risk levels for GAI systems that address issues such as model collapse and algorithmic monoculture. Harmful Bias and Homogenization GV-1.3-006 Reevaluate organizational risk tolerances to account for unacceptable negative risk (such as where signiﬁcant negative impacts are imminent, severe harms are actually occurring, or large-scale risks could occur); and broad GAI negative risks, including: Immature safety or risk cultures related to AI and GAI design, development and deployment, public information integrity risks, including impacts

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: 1
per_device_eval_batch_size: 1
num_train_epochs: 5
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: 1
per_device_eval_batch_size: 1
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs