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("DiamondCutter88/astrology-ft-c8cd64c7-86a1-4203-ac38-826b510e436f")
# Run inference
sentences = [
    'According to the context, why is it unhelpful to follow popular media’s definition of a great girlfriend or rigid dating tips?',
    'There is not one universal definition of a good relationship or lover. Ladies, it’s a waste of time to try and fit the mold of the popular media’s definition of a great girlfriend because that definition may not attract the man that satisfies you. Men, it’s a waste of time to follow rigid dating tips that may not appeal to the woman of your dreams.\nSo how do know what attracts or appeals to the lover of your dreams? More importantly, what attracts or appeals to you? What type of man/woman is the lover of your dreams? What do you need in a lover, in a relationship, in a spouse? You may think you know the answer to these questions. However, popular media may be influencing you to seek qualities that are not your natural preferences.\nThat ultimately results in failed relationships.',
    'Interpreting Planets in the Signs\nLook at the birth chart and take note of what sign and house each planet is in. (Check here if you need help remembering what the symbols/glyphs mean.) Here is a handy, printable worksheet that will help you keep track of your birth chart information. Also take note of the Ascendant\'s sign (Rising Sign), and which house the Ascendant\'s ruler occupies.\nNow you can look up the "Chart Interpretations" of each of your planets and Rising Sign. The Chart Interpretations on the linked page are only general meanings of what each item represents. As you get a feel for the basic energy of each planet, and of the qualities of each sign, you can add your own insight.',
]
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	0.9167
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9167
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9167
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9638
cosine_mrr@10	0.9514
cosine_map@100	0.9514

Training Details

Training Dataset

Unnamed Dataset

Size: 288 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 288 samples:
sentence_0 sentence_1
type string string
details
min: 10 tokens
mean: 19.75 tokens
max: 37 tokens
min: 10 tokens
mean: 147.1 tokens
max: 263 tokens

Samples:

sentence_0	sentence_1
`How does Sagittarius perceive life's possibilities according to the context?`	`Sagittarius has a continually changing view of life's possibilities; Pisces adapts itself superficially to its environment (like a chameleon) and reflects it like a mirror. Sometimes they compromise so much that they sacrifice their own interests. The four Mutable signs are at the final month of each season.`
`What characteristic behavior is attributed to Pisces in adapting to its environment?`	`Sagittarius has a continually changing view of life's possibilities; Pisces adapts itself superficially to its environment (like a chameleon) and reflects it like a mirror. Sometimes they compromise so much that they sacrifice their own interests. The four Mutable signs are at the final month of each season.`
`How long can a moving planet stay in aspect during a transit?`	A moving planet can stay in aspect anywhere from a few hours up to a few years. The moon, because she moves so fast, makes aspects only for a short hour or two. And then she’s gone. Neptune and Pluto, because they move so slowly (relative motion), can stay in aspect for 2 or 3 years. Use an orb of 1 degree to consider transits (but use a 2 degree orb to plan ahead!) While a moving planet is in aspect to a natal planetary position, the moving planet is said to be “transiting” the natal planet. [object Object]The transit has an influence over you during the entire time that it’s transiting, but it also has a point at which it becomes “exact.” This is the day when it reaches the exact degree, minute, and second of your birth planet. Some transits can become exact three times because of retrograde motion: the transiting planet passes over the point once, then the planet goes retrograde and backtracks over the point, then the planet goes back into direct motion and passes over the point a third time.

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: 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}
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	29	0.9484
1.7241	50	0.9283
2.0	58	0.9424
3.0	87	0.9283
3.4483	100	0.9484
4.0	116	0.9437
5.0	145	0.9301
5.1724	150	0.9385
6.0	174	0.9539
6.8966	200	0.9484
7.0	203	0.9484
8.0	232	0.9638
8.6207	250	0.9638
9.0	261	0.9638
10.0	290	0.9638

Framework Versions

Python: 3.11.12
Sentence Transformers: 4.1.0
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

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: 10 tokens mean: 19.75 tokens max: 37 tokens	min: 10 tokens mean: 147.1 tokens max: 263 tokens