metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1363306
  - loss:CoSENTLoss
widget:
  - source_sentence: labneh
    sentences:
      - iftar
      - bathing suit
      - coffee cup
  - source_sentence: Velvet flock Veil
    sentences:
      - mermaid purse
      - veil
      - mobile bag
  - source_sentence: Red lipstick
    sentences:
      - chemise dress
      - tote
      - rouge
  - source_sentence: Unisex Travel bag
    sentences:
      - spf
      - basic vega ring
      - travel backpack
  - source_sentence: jeremy hush book
    sentences:
      - chinese jumper
      - perfume
      - home automation device
model-index:
  - name: all-MiniLM-L6-v5-pair_score-syn-fr
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.45976967432661087
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.44063948938599923
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.41341637785801416
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.4372479132617008
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.4145493812051541
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.44063932299328573
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.45976967600824187
            name: Pearson Dot
          - type: spearman_dot
            value: 0.44063967285735406
            name: Spearman Dot
          - type: pearson_max
            value: 0.45976967600824187
            name: Pearson Max
          - type: spearman_max
            value: 0.44063967285735406
            name: Spearman Max

all-MiniLM-L6-v5-pair_score-syn-fr

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 tokens
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'jeremy hush book',
    'chinese jumper',
    'perfume',
]
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

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4598
spearman_cosine	0.4406
pearson_manhattan	0.4134
spearman_manhattan	0.4372
pearson_euclidean	0.4145
spearman_euclidean	0.4406
pearson_dot	0.4598
spearman_dot	0.4406
pearson_max	0.4598
spearman_max	0.4406

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 4
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
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: 2e-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: 4
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: 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
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	sts-dev_spearman_cosine
0	0	-	-	0.4406
0.0094	100	17.0727	-	-
0.0188	200	16.8813	-	-
0.0282	300	16.5085	-	-
0.0376	400	15.5716	-	-
0.0469	500	14.5542	-	-
0.0563	600	13.1478	-	-
0.0657	700	11.3662	-	-
0.0751	800	9.5649	-	-
0.0845	900	8.536	-	-
0.0939	1000	8.2589	-	-
0.1033	1100	8.1649	-	-
0.1127	1200	8.134	-	-
0.1221	1300	8.1331	-	-
0.1314	1400	8.0893	-	-
0.1408	1500	8.0706	-	-
0.1502	1600	8.0786	-	-
0.1596	1700	8.058	-	-
0.1690	1800	8.0768	-	-
0.1784	1900	8.0834	-	-
0.1878	2000	8.0714	-	-
0.1972	2100	8.0671	-	-
0.2066	2200	8.051	-	-
0.2159	2300	8.0287	-	-
0.2253	2400	8.0445	-	-
0.2347	2500	8.0444	-	-
0.2441	2600	8.0679	-	-
0.2535	2700	8.0472	-	-
0.2629	2800	8.0151	-	-
0.2723	2900	8.0599	-	-
0.2817	3000	8.0304	-	-
0.2911	3100	8.0373	-	-
0.3004	3200	8.0382	-	-
0.3098	3300	8.0112	-	-
0.3192	3400	8.0209	-	-
0.3286	3500	8.0487	-	-
0.3380	3600	8.0138	-	-
0.3474	3700	8.046	-	-
0.3568	3800	7.9876	-	-
0.3662	3900	7.997	-	-
0.3756	4000	8.0462	-	-
0.3849	4100	7.9882	-	-
0.3943	4200	7.9949	-	-
0.4037	4300	7.9951	-	-
0.4131	4400	8.0202	-	-
0.4225	4500	8.0126	-	-
0.4319	4600	8.0351	-	-
0.4413	4700	8.0419	-	-
0.4507	4800	7.9959	-	-
0.4601	4900	8.0076	-	-
0.4694	5000	8.0022	8.0125	-
0.4788	5100	7.9819	-	-
0.4882	5200	7.9836	-	-
0.4976	5300	7.9996	-	-
0.5070	5400	8.0221	-	-
0.5164	5500	8.0854	-	-
0.5258	5600	8.0306	-	-
0.5352	5700	7.9924	-	-
0.5445	5800	7.9884	-	-
0.5539	5900	8.0253	-	-
0.5633	6000	7.9773	-	-
0.5727	6100	7.9878	-	-
0.5821	6200	8.0495	-	-
0.5915	6300	7.9908	-	-
0.6009	6400	7.9886	-	-
0.6103	6500	8.0232	-	-
0.6197	6600	7.9933	-	-
0.6290	6700	8.0143	-	-
0.6384	6800	7.9956	-	-
0.6478	6900	7.9755	-	-
0.6572	7000	7.9814	-	-
0.6666	7100	7.9849	-	-
0.6760	7200	8.0076	-	-
0.6854	7300	8.0071	-	-
0.6948	7400	8.003	-	-
0.7042	7500	7.9966	-	-
0.7135	7600	8.0052	-	-
0.7229	7700	8.0226	-	-
0.7323	7800	7.9809	-	-
0.7417	7900	7.9802	-	-
0.7511	8000	8.0008	-	-
0.7605	8100	7.9876	-	-
0.7699	8200	8.0295	-	-
0.7793	8300	7.9992	-	-
0.7887	8400	7.9942	-	-
0.7980	8500	7.9872	-	-
0.8074	8600	7.9757	-	-
0.8168	8700	7.9835	-	-
0.8262	8800	8.0555	-	-
0.8356	8900	8.0055	-	-
0.8450	9000	7.9817	-	-
0.8544	9100	7.9952	-	-
0.8638	9200	8.0083	-	-
0.8732	9300	7.984	-	-
0.8825	9400	7.9918	-	-
0.8919	9500	7.9816	-	-
0.9013	9600	8.0167	-	-
0.9107	9700	7.9747	-	-
0.9201	9800	7.9882	-	-
0.9295	9900	8.0003	-	-
0.9389	10000	8.0067	7.9823	-
0.9483	10100	8.017	-	-
0.9577	10200	7.9763	-	-
0.9670	10300	7.9553	-	-
0.9764	10400	7.9525	-	-
0.9858	10500	7.9987	-	-
0.9952	10600	7.9715	-	-
1.0046	10700	7.947	-	-
1.0140	10800	8.0298	-	-
1.0234	10900	7.9756	-	-
1.0328	11000	7.979	-	-
1.0422	11100	8.0417	-	-
1.0515	11200	7.9936	-	-
1.0609	11300	7.971	-	-
1.0703	11400	7.99	-	-
1.0797	11500	7.9562	-	-
1.0891	11600	7.9541	-	-
1.0985	11700	7.9788	-	-
1.1079	11800	7.9883	-	-
1.1173	11900	7.9643	-	-
1.1267	12000	7.9806	-	-
1.1360	12100	7.9543	-	-
1.1454	12200	7.9684	-	-
1.1548	12300	7.9492	-	-
1.1642	12400	7.984	-	-
1.1736	12500	7.9817	-	-
1.1830	12600	7.9621	-	-
1.1924	12700	7.9782	-	-
1.2018	12800	7.9748	-	-
1.2112	12900	7.9606	-	-
1.2205	13000	7.9654	-	-
1.2299	13100	7.9708	-	-
1.2393	13200	7.9832	-	-
1.2487	13300	7.9482	-	-
1.2581	13400	7.9717	-	-
1.2675	13500	7.9667	-	-
1.2769	13600	7.9653	-	-
1.2863	13700	7.969	-	-
1.2957	13800	7.9416	-	-
1.3050	13900	7.994	-	-
1.3144	14000	7.9821	-	-
1.3238	14100	7.9656	-	-
1.3332	14200	7.9763	-	-
1.3426	14300	7.9708	-	-
1.3520	14400	7.9713	-	-
1.3614	14500	8.0128	-	-
1.3708	14600	7.9914	-	-
1.3802	14700	7.9839	-	-
1.3895	14800	7.9485	-	-
1.3989	14900	7.9564	-	-
1.4083	15000	7.9646	7.9795	-
1.4177	15100	7.9443	-	-
1.4271	15200	8.002	-	-
1.4365	15300	7.9493	-	-
1.4459	15400	7.9561	-	-
1.4553	15500	7.9571	-	-
1.4647	15600	7.9634	-	-
1.4740	15700	7.9348	-	-
1.4834	15800	7.9476	-	-
1.4928	15900	7.9373	-	-
1.5022	16000	7.9985	-	-
1.5116	16100	7.9518	-	-
1.5210	16200	7.9751	-	-
1.5304	16300	7.9677	-	-
1.5398	16400	7.9538	-	-
1.5492	16500	7.9894	-	-
1.5585	16600	7.9832	-	-
1.5679	16700	7.9582	-	-
1.5773	16800	7.975	-	-
1.5867	16900	7.9379	-	-
1.5961	17000	7.9434	-	-
1.6055	17100	7.9805	-	-
1.6149	17200	7.946	-	-
1.6243	17300	7.9613	-	-
1.6336	17400	7.9687	-	-
1.6430	17500	7.9612	-	-
1.6524	17600	7.9614	-	-
1.6618	17700	7.95	-	-
1.6712	17800	7.9874	-	-
1.6806	17900	7.9665	-	-
1.6900	18000	7.9562	-	-
1.6994	18100	7.9777	-	-
1.7088	18200	7.9771	-	-
1.7181	18300	7.9405	-	-
1.7275	18400	7.9516	-	-
1.7369	18500	8.0012	-	-
1.7463	18600	7.9464	-	-
1.7557	18700	7.9623	-	-
1.7651	18800	7.9478	-	-
1.7745	18900	7.9528	-	-
1.7839	19000	7.9617	-	-
1.7933	19100	7.966	-	-
1.8026	19200	7.9718	-	-
1.8120	19300	7.9679	-	-
1.8214	19400	7.9448	-	-
1.8308	19500	7.9299	-	-
1.8402	19600	7.967	-	-
1.8496	19700	7.9327	-	-
1.8590	19800	7.9602	-	-
1.8684	19900	7.9515	-	-
1.8778	20000	7.9447	7.9457	-
1.8871	20100	7.9487	-	-
1.8965	20200	7.9438	-	-
1.9059	20300	7.9821	-	-
1.9153	20400	7.9485	-	-
1.9247	20500	7.9251	-	-
1.9341	20600	7.982	-	-
1.9435	20700	7.9508	-	-
1.9529	20800	7.9511	-	-
1.9623	20900	7.9747	-	-
1.9716	21000	7.9365	-	-
1.9810	21100	7.9845	-	-
1.9904	21200	8.0186	-	-
1.9998	21300	8.0228	-	-
2.0092	21400	7.949	-	-
2.0186	21500	7.9371	-	-
2.0280	21600	7.9355	-	-
2.0374	21700	7.9528	-	-
2.0468	21800	7.9246	-	-
2.0561	21900	7.9721	-	-
2.0655	22000	7.9438	-	-
2.0749	22100	7.9349	-	-
2.0843	22200	7.9315	-	-
2.0937	22300	7.9398	-	-
2.1031	22400	7.9232	-	-
2.1125	22500	7.9189	-	-
2.1219	22600	7.9296	-	-
2.1313	22700	7.9658	-	-
2.1406	22800	7.922	-	-
2.1500	22900	7.9247	-	-
2.1594	23000	7.9748	-	-
2.1688	23100	7.9632	-	-
2.1782	23200	7.9416	-	-
2.1876	23300	8.0063	-	-
2.1970	23400	7.9347	-	-
2.2064	23500	7.9242	-	-
2.2158	23600	7.9537	-	-
2.2251	23700	7.9281	-	-
2.2345	23800	7.9417	-	-
2.2439	23900	7.9699	-	-
2.2533	24000	7.9919	-	-
2.2627	24100	7.9322	-	-
2.2721	24200	7.9702	-	-
2.2815	24300	7.9421	-	-
2.2909	24400	7.9453	-	-
2.3003	24500	7.9485	-	-
2.3096	24600	7.9491	-	-
2.3190	24700	7.9575	-	-
2.3284	24800	7.9481	-	-
2.3378	24900	7.9261	-	-
2.3472	25000	7.9347	7.9455	-
2.3566	25100	7.9434	-	-
2.3660	25200	7.9627	-	-
2.3754	25300	7.9303	-	-
2.3848	25400	7.9455	-	-
2.3941	25500	7.9228	-	-
2.4035	25600	7.9492	-	-
2.4129	25700	7.9384	-	-
2.4223	25800	7.9408	-	-
2.4317	25900	7.9497	-	-
2.4411	26000	7.9159	-	-
2.4505	26100	7.941	-	-
2.4599	26200	7.937	-	-
2.4693	26300	7.9484	-	-
2.4786	26400	7.9238	-	-
2.4880	26500	7.9329	-	-
2.4974	26600	7.9506	-	-
2.5068	26700	7.9568	-	-
2.5162	26800	7.9548	-	-
2.5256	26900	7.9097	-	-
2.5350	27000	7.9085	-	-
2.5444	27100	7.9368	-	-
2.5538	27200	7.9546	-	-
2.5631	27300	7.9255	-	-
2.5725	27400	7.9536	-	-
2.5819	27500	7.919	-	-
2.5913	27600	7.917	-	-
2.6007	27700	7.937	-	-
2.6101	27800	7.9159	-	-
2.6195	27900	7.9306	-	-
2.6289	28000	7.9592	-	-
2.6382	28100	7.9375	-	-
2.6476	28200	7.9225	-	-
2.6570	28300	7.958	-	-
2.6664	28400	7.9059	-	-
2.6758	28500	7.936	-	-
2.6852	28600	7.9138	-	-
2.6946	28700	7.9565	-	-
2.7040	28800	7.926	-	-
2.7134	28900	7.9365	-	-
2.7227	29000	7.9122	-	-
2.7321	29100	7.9196	-	-
2.7415	29200	7.9533	-	-
2.7509	29300	7.925	-	-
2.7603	29400	7.9594	-	-
2.7697	29500	7.9115	-	-
2.7791	29600	7.956	-	-
2.7885	29700	7.9394	-	-
2.7979	29800	7.9165	-	-
2.8072	29900	7.9471	-	-
2.8166	30000	7.9724	7.9237	-
2.8260	30100	7.9205	-	-
2.8354	30200	7.9513	-	-
2.8448	30300	7.9101	-	-
2.8542	30400	7.9237	-	-
2.8636	30500	7.9428	-	-
2.8730	30600	7.9408	-	-
2.8824	30700	7.956	-	-
2.8917	30800	7.9196	-	-
2.9011	30900	7.9262	-	-
2.9105	31000	7.9516	-	-
2.9199	31100	7.9086	-	-
2.9293	31200	7.9339	-	-
2.9387	31300	7.9334	-	-
2.9481	31400	7.9308	-	-
2.9575	31500	7.9569	-	-
2.9669	31600	7.9256	-	-
2.9762	31700	7.9108	-	-
2.9856	31800	7.9409	-	-
2.9950	31900	7.9159	-	-
3.0044	32000	7.8975	-	-
3.0138	32100	7.9583	-	-
3.0232	32200	7.9031	-	-
3.0326	32300	7.9448	-	-
3.0420	32400	7.9438	-	-
3.0514	32500	7.9284	-	-
3.0607	32600	7.9124	-	-
3.0701	32700	7.9153	-	-
3.0795	32800	7.9188	-	-
3.0889	32900	7.9358	-	-
3.0983	33000	7.9436	-	-
3.1077	33100	7.9492	-	-
3.1171	33200	7.9032	-	-
3.1265	33300	7.922	-	-
3.1359	33400	7.9677	-	-
3.1452	33500	7.9127	-	-
3.1546	33600	7.9381	-	-
3.1640	33700	7.9198	-	-
3.1734	33800	7.9183	-	-
3.1828	33900	7.9182	-	-
3.1922	34000	7.9261	-	-
3.2016	34100	7.9091	-	-
3.2110	34200	7.941	-	-
3.2204	34300	7.9239	-	-
3.2297	34400	7.9208	-	-
3.2391	34500	7.9499	-	-
3.2485	34600	7.9251	-	-
3.2579	34700	7.9219	-	-
3.2673	34800	7.9344	-	-
3.2767	34900	7.9496	-	-
3.2861	35000	7.9184	7.9239	-
3.2955	35100	7.9053	-	-
3.3049	35200	7.931	-	-
3.3142	35300	7.9347	-	-
3.3236	35400	7.9575	-	-
3.3330	35500	7.9259	-	-
3.3424	35600	7.9262	-	-
3.3518	35700	7.9206	-	-
3.3612	35800	7.9445	-	-
3.3706	35900	7.9043	-	-
3.3800	36000	7.9164	-	-
3.3894	36100	7.9199	-	-
3.3987	36200	7.9132	-	-
3.4081	36300	7.9163	-	-
3.4175	36400	7.9203	-	-
3.4269	36500	7.9491	-	-
3.4363	36600	7.9093	-	-
3.4457	36700	7.9271	-	-
3.4551	36800	7.9202	-	-
3.4645	36900	7.9193	-	-
3.4739	37000	7.9041	-	-
3.4832	37100	7.9284	-	-
3.4926	37200	7.9633	-	-
3.5020	37300	7.9078	-	-
3.5114	37400	7.9144	-	-
3.5208	37500	7.9011	-	-
3.5302	37600	7.9101	-	-
3.5396	37700	7.9331	-	-
3.5490	37800	7.9349	-	-
3.5584	37900	7.9272	-	-
3.5677	38000	7.9033	-	-
3.5771	38100	7.895	-	-
3.5865	38200	7.9082	-	-
3.5959	38300	7.9544	-	-
3.6053	38400	7.9063	-	-
3.6147	38500	7.9249	-	-
3.6241	38600	7.9124	-	-
3.6335	38700	7.9174	-	-
3.6429	38800	7.9275	-	-
3.6522	38900	7.9045	-	-
3.6616	39000	7.9327	-	-
3.6710	39100	7.9383	-	-
3.6804	39200	7.9134	-	-
3.6898	39300	7.925	-	-
3.6992	39400	7.9214	-	-
3.7086	39500	7.9207	-	-
3.7180	39600	7.9192	-	-
3.7273	39700	7.9194	-	-
3.7367	39800	7.9242	-	-
3.7461	39900	7.905	-	-
3.7555	40000	7.9278	7.9185	-
3.7649	40100	7.9147	-	-
3.7743	40200	7.9194	-	-
3.7837	40300	7.9004	-	-
3.7931	40400	7.9549	-	-
3.8025	40500	7.9326	-	-
3.8118	40600	7.9124	-	-
3.8212	40700	7.9355	-	-
3.8306	40800	7.926	-	-
3.8400	40900	7.9491	-	-
3.8494	41000	7.9163	-	-
3.8588	41100	7.9554	-	-
3.8682	41200	7.9162	-	-
3.8776	41300	7.8916	-	-
3.8870	41400	7.8969	-	-
3.8963	41500	7.9131	-	-
3.9057	41600	7.9272	-	-
3.9151	41700	7.9482	-	-
3.9245	41800	7.9168	-	-
3.9339	41900	7.9062	-	-
3.9433	42000	7.9238	-	-
3.9527	42100	7.9407	-	-
3.9621	42200	7.9482	-	-
3.9715	42300	7.9221	-	-
3.9808	42400	7.9221	-	-
3.9902	42500	7.9313	-	-
3.9996	42600	7.9441	-	-

Framework Versions

Python: 3.8.10
Sentence Transformers: 3.1.1
Transformers: 4.45.2
PyTorch: 2.4.1+cu118
Accelerate: 1.0.1
Datasets: 3.0.1
Tokenizers: 0.20.3

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}