This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-s. It maps sentences & paragraphs to a 384-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-s
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 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': 384, '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("LucaZilli/model-snowflake-s_20250226_145351_finalmodel")
# Run inference
sentences = [
    'materiali isolanti per sistemi radianti a soffitto',
    'materiali isolanti per edifici',
    'privacy and data protection training',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Semantic Similarity

Datasets: custom_dataset and stsbenchmark
Evaluated with EmbeddingSimilarityEvaluator

Metric	custom_dataset	stsbenchmark
pearson_cosine	0.7037	0.7477
spearman_cosine	0.7287	0.7432

Triplet

Dataset: all_nli_dataset
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.8163

Training Details

Training Dataset

Unnamed Dataset

Size: 25,310 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 4 tokens
mean: 13.32 tokens
max: 31 tokens
min: 4 tokens
mean: 11.06 tokens
max: 31 tokens
min: 0.0
mean: 0.49
max: 1.0

Samples:

sentence1	sentence2	score
`ottimizzazione dei tempi di produzione per capi sartoriali di lusso`	`strumenti per l'ottimizzazione dei tempi di produzione`	`0.6`
`software di programmazione robotica per lucidatura`	`software gestionale generico`	`0.4`
`rete di sensori per l'analisi del suolo in tempo reale`	`software per gestione aziendale`	`0.0`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Evaluation Dataset

Unnamed Dataset

Size: 3,164 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 13.61 tokens
max: 31 tokens
min: 4 tokens
mean: 11.39 tokens
max: 27 tokens
min: 0.0
mean: 0.49
max: 1.0

Samples:

sentence1	sentence2	score
`ispezioni regolari per camion aziendali`	`ispezioni regolari per camion di consegna`	`1.0`
`blister packaging machines GMP compliant`	`food packaging machines`	`0.4`
`EMI shielding paints for electronics`	`Vernici per schermatura elettromagnetica dispositivi elettronici`	`0.8`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 5
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 1.0
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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: True
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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	custom_dataset_spearman_cosine	all_nli_dataset_cosine_accuracy	stsbenchmark_spearman_cosine
-1	-1	-	-	0.7287	0.8163	0.7432
0.1264	200	0.0671	0.0434	-	-	-
0.2528	400	0.0401	0.0344	-	-	-
0.3793	600	0.0342	0.0307	-	-	-
0.5057	800	0.0347	0.0327	-	-	-
0.6321	1000	0.0322	0.0287	-	-	-
0.7585	1200	0.032	0.0279	-	-	-
0.8850	1400	0.0307	0.0282	-	-	-
1.0114	1600	0.0267	0.0279	-	-	-
1.1378	1800	0.0244	0.0266	-	-	-
1.2642	2000	0.0227	0.0282	-	-	-
1.3906	2200	0.0237	0.0249	-	-	-
1.5171	2400	0.0222	0.0273	-	-	-
1.6435	2600	0.0235	0.0246	-	-	-
1.7699	2800	0.0228	0.0247	-	-	-
1.8963	3000	0.0225	0.0241	-	-	-
2.0228	3200	0.0213	0.0244	-	-	-
2.1492	3400	0.0169	0.0234	-	-	-
2.2756	3600	0.0178	0.0257	-	-	-
2.4020	3800	0.018	0.0236	-	-	-
2.5284	4000	0.0177	0.0230	-	-	-
2.6549	4200	0.0176	0.0234	-	-	-
2.7813	4400	0.0182	0.0229	-	-	-
2.9077	4600	0.0173	0.0221	-	-	-
3.0341	4800	0.0157	0.0232	-	-	-
3.1606	5000	0.0139	0.0225	-	-	-
3.2870	5200	0.0137	0.0222	-	-	-
3.4134	5400	0.0142	0.0224	-	-	-
3.5398	5600	0.0143	0.0224	-	-	-
3.6662	5800	0.0135	0.0225	-	-	-
3.7927	6000	0.0143	0.0223	-	-	-
3.9191	6200	0.0143	0.0234	-	-	-
4.0455	6400	0.0128	0.0219	-	-	-
4.1719	6600	0.0117	0.0222	-	-	-
4.2984	6800	0.0113	0.0217	-	-	-
4.4248	7000	0.0115	0.0220	-	-	-
4.5512	7200	0.012	0.0217	-	-	-
4.6776	7400	0.0113	0.0221	-	-	-
4.8040	7600	0.012	0.0217	-	-	-
4.9305	7800	0.0105	0.0217	-	-	-

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.2
Tokenizers: 0.21.0

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",
}

	sentence1	sentence2	score
type	string	string	float
details	min: 4 tokens mean: 13.32 tokens max: 31 tokens	min: 4 tokens mean: 11.06 tokens max: 31 tokens	min: 0.0 mean: 0.49 max: 1.0