all-MiniLM-L6-v82-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v66 dataset. 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 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- pairs_with_scores_v66
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, 'architecture': '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 = [
    'jupe dry soft femme - dry 500 noir',
    'pastrami pastrami pastrami',
    'ricotta spinach panzerotti mushrooms panzerotti panzerotti ricotta panzerotti spinach panzerotti panzerotti ricotta panzerotti spinach panzerotti',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.1955,  0.0171],
#         [-0.1955,  1.0000,  0.0070],
#         [ 0.0171,  0.0070,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v66

Dataset: pairs_with_scores_v66 at 408b50a
Size: 55,014,339 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 3 tokens
mean: 6.67 tokens
max: 21 tokens

min: 5 tokens
mean: 46.56 tokens
max: 256 tokens

min: 0.0
mean: 0.01
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 3 tokens mean: 6.67 tokens max: 21 tokens	min: 5 tokens mean: 46.56 tokens max: 256 tokens	min: 0.0 mean: 0.01 max: 1.0

Samples:

sentence1	sentence2	score
`piqu belt -`	`white sneakers jump 5 sneakers sneakers jump sneakers sneakers jump`	`0.0`
`blade`	`white x black acrylic tawla set acrylic game board acrylic playing chips acrylic dice breakage resistance tawla set printing tawla set antiscratch tawla set waterproof tawla set portable tawla set acrylic tawla set tawla set acrylic tawla set tawla set`	`0.0`
`solo`	`climbing harness easy 3 blue beginner climbing harness group climbing harness club climbing harness intuitive design harness visible tiein loop harness outdoor harness harness`	`0.0`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Evaluation Dataset

pairs_with_scores_v66

Dataset: pairs_with_scores_v66 at 408b50a
Size: 276,454 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 3 tokens
mean: 6.65 tokens
max: 25 tokens

min: 5 tokens
mean: 44.66 tokens
max: 256 tokens

min: 0.0
mean: 0.02
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 3 tokens mean: 6.65 tokens max: 25 tokens	min: 5 tokens mean: 44.66 tokens max: 256 tokens	min: 0.0 mean: 0.02 max: 1.0

Samples:

sentence1	sentence2	score
`crackers box eid mubarak`	`romana - pizza meat lovers pizza pizza meat lovers romana romana pizza pizza pizza meat lovers romana romana pizza`	`0.0`
`good france ilou mayonnaise sandwich sauce - 200 gr`	`mint bucket hat mint hat women hat bucket hat hat bucket hat hat`	`0.0`
`beef bone stok soup`	`oven mitten mitten oven mitten stove mitten mitten oven mitten stove mitten`	`0.0`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

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: 1
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: 1
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
hub_revision: None
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
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.8774	377100	0.8228	-
0.8776	377200	0.4753	-
0.8779	377300	0.448	-
0.8781	377400	0.7374	-
0.8783	377500	0.5178	-
0.8785	377600	0.6454	-
0.8788	377700	0.3006	-
0.8790	377800	0.3742	-
0.8792	377900	0.4484	-
0.8795	378000	0.5975	-
0.8797	378100	0.4562	-
0.8799	378200	0.8615	-
0.8802	378300	0.456	-
0.8804	378400	0.6364	-
0.8806	378500	0.5395	-
0.8809	378600	0.4403	-
0.8811	378700	0.488	-
0.8813	378800	0.7056	-
0.8816	378900	0.6037	-
0.8818	379000	0.4867	-
0.8820	379100	0.6573	-
0.8823	379200	0.4785	-
0.8825	379300	0.4318	-
0.8827	379400	0.7051	-
0.8830	379500	0.6398	-
0.8832	379600	0.6794	-
0.8834	379700	0.4193	-
0.8837	379800	0.509	-
0.8839	379900	0.1704	-
0.8841	380000	0.6385	-
0.8844	380100	0.4294	-
0.8846	380200	0.5308	-
0.8848	380300	0.7605	-
0.8851	380400	0.2874	-
0.8853	380500	0.7396	-
0.8855	380600	0.5158	-
0.8858	380700	0.4002	-
0.8860	380800	0.4971	-
0.8862	380900	0.4748	-
0.8865	381000	0.6869	-
0.8867	381100	0.5027	-
0.8869	381200	0.7624	-
0.8872	381300	0.6324	-
0.8874	381400	0.6612	-
0.8876	381500	0.3387	-
0.8879	381600	0.7287	-
0.8881	381700	0.6816	-
0.8883	381800	0.595	-
0.8886	381900	0.4171	-
0.8888	382000	0.7484	-
0.8890	382100	0.8825	-
0.8893	382200	0.6297	-
0.8895	382300	0.6812	-
0.8897	382400	0.6184	-
0.8899	382500	0.7474	-
0.8902	382600	0.592	-
0.8904	382700	0.5952	-
0.8906	382800	0.483	-
0.8909	382900	0.5716	-
0.8911	383000	0.6266	-
0.8913	383100	0.4727	-
0.8916	383200	0.4923	-
0.8918	383300	0.4098	-
0.8920	383400	0.4673	-
0.8923	383500	0.4711	-
0.8925	383600	0.639	-
0.8927	383700	0.483	-
0.8930	383800	0.4154	-
0.8932	383900	0.3817	-
0.8934	384000	0.7604	-
0.8937	384100	0.4499	-
0.8939	384200	0.5768	-
0.8941	384300	0.4261	-
0.8944	384400	0.3208	-
0.8946	384500	0.6611	-
0.8948	384600	0.7067	-
0.8951	384700	0.6588	-
0.8953	384800	0.4715	-
0.8955	384900	0.6741	-
0.8958	385000	0.5522	-
0.8960	385100	0.5437	-
0.8962	385200	0.7599	-
0.8965	385300	0.3223	-
0.8967	385400	0.2705	-
0.8969	385500	0.8656	-
0.8972	385600	0.2889	-
0.8974	385700	0.301	-
0.8976	385800	0.3845	-
0.8979	385900	0.6989	-
0.8981	386000	0.649	-
0.8983	386100	0.6816	-
0.8986	386200	0.5368	-
0.8988	386300	0.5258	-
0.8990	386400	0.8942	-
0.8993	386500	0.4466	-
0.8995	386600	0.4626	-
0.8997	386700	0.3674	-
0.9000	386800	0.3972	-
0.9002	386900	0.5314	-
0.9004	387000	0.4395	-
0.9007	387100	0.7384	-
0.9009	387200	0.7386	-
0.9011	387300	0.3846	-
0.9013	387400	0.5222	-
0.9016	387500	0.494	-
0.9018	387600	0.6157	-
0.9020	387700	0.5595	-
0.9023	387800	0.4771	-
0.9025	387900	0.5407	-
0.9027	388000	0.4756	-
0.9030	388100	0.5035	-
0.9032	388200	0.761	-
0.9034	388300	0.7049	-
0.9037	388400	0.3754	-
0.9039	388500	0.436	-
0.9041	388600	0.6573	-
0.9044	388700	0.7622	-
0.9046	388800	0.6078	-
0.9048	388900	0.4591	-
0.9051	389000	0.2952	-
0.9053	389100	0.5796	-
0.9055	389200	0.8245	-
0.9058	389300	0.4374	-
0.9060	389400	0.5207	-
0.9062	389500	0.5439	-
0.9065	389600	0.7844	-
0.9067	389700	0.7184	-
0.9069	389800	0.6166	-
0.9072	389900	0.6533	-
0.9074	390000	0.4537	-
0.9076	390100	0.6072	-
0.9079	390200	0.555	-
0.9081	390300	0.6889	-
0.9083	390400	0.6428	-
0.9086	390500	0.6998	-
0.9088	390600	0.65	-
0.9090	390700	0.538	-
0.9093	390800	0.4264	-
0.9095	390900	0.3686	-
0.9097	391000	0.4314	-
0.9100	391100	0.4392	-
0.9102	391200	0.7683	-
0.9104	391300	0.6959	-
0.9107	391400	0.3922	-
0.9109	391500	0.2392	-
0.9111	391600	0.4767	-
0.9114	391700	0.7225	-
0.9116	391800	0.6432	-
0.9118	391900	0.7269	-
0.9121	392000	0.8267	-
0.9123	392100	0.3969	-
0.9125	392200	0.4307	-
0.9128	392300	0.6491	-
0.9130	392400	0.6159	-
0.9132	392500	0.2706	-
0.9134	392600	0.7364	-
0.9137	392700	0.6714	-
0.9139	392800	0.4214	-
0.9141	392900	0.4105	-
0.9144	393000	0.4472	-
0.9146	393100	0.4595	-
0.9148	393200	0.5995	-
0.9151	393300	0.7416	-
0.9153	393400	0.426	-
0.9155	393500	0.9978	-
0.9158	393600	0.9414	-
0.9160	393700	0.4642	-
0.9162	393800	0.4974	-
0.9165	393900	0.3704	-
0.9167	394000	0.4958	-
0.9169	394100	0.3589	-
0.9172	394200	0.3444	-
0.9174	394300	0.7675	-
0.9176	394400	0.4758	-
0.9179	394500	0.6563	-
0.9181	394600	0.8285	-
0.9183	394700	0.4163	-
0.9186	394800	0.3538	-
0.9188	394900	0.5246	-
0.9190	395000	0.7103	-
0.9193	395100	0.7639	-
0.9195	395200	0.6245	-
0.9197	395300	0.7683	-
0.9200	395400	0.5116	-
0.9202	395500	0.2613	-
0.9204	395600	0.4709	-
0.9207	395700	0.5722	-
0.9209	395800	0.5951	-
0.9211	395900	0.6508	-
0.9214	396000	0.6274	-
0.9216	396100	0.6647	-
0.9218	396200	0.5148	-
0.9221	396300	0.6891	-
0.9223	396400	0.6209	-
0.9225	396500	0.5997	-
0.9228	396600	0.4801	-
0.9230	396700	0.5293	-
0.9232	396800	0.6937	-
0.9235	396900	0.4032	-
0.9237	397000	0.6126	-
0.9239	397100	0.4899	-
0.9242	397200	0.7244	-
0.9244	397300	0.6326	-
0.9246	397400	0.3763	-
0.9248	397500	0.3513	-
0.9251	397600	0.3962	-
0.9253	397700	0.8995	-
0.9255	397800	0.6549	-
0.9258	397900	0.4811	-
0.9260	398000	0.4395	-
0.9262	398100	0.5922	-
0.9265	398200	0.726	-
0.9267	398300	0.4093	-
0.9269	398400	0.615	-
0.9272	398500	0.4034	-
0.9274	398600	0.5934	-
0.9276	398700	0.5606	-
0.9279	398800	0.3263	-
0.9281	398900	0.7172	-
0.9283	399000	0.7893	-
0.9286	399100	0.6156	-
0.9288	399200	0.7152	-
0.9290	399300	0.3813	-
0.9293	399400	0.3901	-
0.9295	399500	0.6371	-
0.9297	399600	0.6982	-
0.9300	399700	0.6316	-
0.9302	399800	0.5633	-
0.9304	399900	0.5489	-
0.9307	400000	0.383	0.5135
0.9309	400100	0.4798	-
0.9311	400200	0.4807	-
0.9314	400300	0.3796	-
0.9316	400400	0.6959	-
0.9318	400500	0.6579	-
0.9321	400600	0.4543	-
0.9323	400700	0.48	-
0.9325	400800	0.616	-
0.9328	400900	0.818	-
0.9330	401000	0.2747	-
0.9332	401100	0.3347	-
0.9335	401200	0.8078	-
0.9337	401300	0.4013	-
0.9339	401400	0.6152	-
0.9342	401500	0.4347	-
0.9344	401600	0.4976	-
0.9346	401700	0.6882	-
0.9349	401800	0.4896	-
0.9351	401900	0.7423	-
0.9353	402000	0.592	-
0.9356	402100	0.441	-
0.9358	402200	0.6611	-
0.9360	402300	0.5756	-
0.9362	402400	0.3538	-
0.9365	402500	0.5888	-
0.9367	402600	0.5051	-
0.9369	402700	0.6206	-
0.9372	402800	0.4562	-
0.9374	402900	0.5712	-
0.9376	403000	0.4565	-
0.9379	403100	0.4357	-
0.9381	403200	0.5399	-
0.9383	403300	0.7435	-
0.9386	403400	0.3272	-
0.9388	403500	0.868	-
0.9390	403600	0.4821	-
0.9393	403700	0.7091	-
0.9395	403800	0.3434	-
0.9397	403900	0.544	-
0.9400	404000	0.5484	-
0.9402	404100	0.3502	-
0.9404	404200	0.6372	-
0.9407	404300	0.4861	-
0.9409	404400	0.6416	-
0.9411	404500	0.623	-
0.9414	404600	0.6144	-
0.9416	404700	0.6614	-
0.9418	404800	0.4927	-
0.9421	404900	0.7293	-
0.9423	405000	0.4793	-
0.9425	405100	0.3851	-
0.9428	405200	0.2645	-
0.9430	405300	0.6439	-
0.9432	405400	0.4375	-
0.9435	405500	0.597	-
0.9437	405600	0.5925	-
0.9439	405700	0.2914	-
0.9442	405800	0.3872	-
0.9444	405900	0.628	-
0.9446	406000	0.453	-
0.9449	406100	0.4781	-
0.9451	406200	0.5762	-
0.9453	406300	0.5714	-
0.9456	406400	0.4592	-
0.9458	406500	0.448	-
0.9460	406600	0.5215	-
0.9463	406700	0.6561	-
0.9465	406800	0.6236	-
0.9467	406900	0.5279	-
0.9470	407000	0.4916	-
0.9472	407100	0.5098	-
0.9474	407200	0.6663	-
0.9477	407300	0.5204	-
0.9479	407400	0.5816	-
0.9481	407500	0.9367	-
0.9483	407600	0.6641	-
0.9486	407700	0.4851	-
0.9488	407800	0.6385	-
0.9490	407900	0.4849	-
0.9493	408000	0.3671	-
0.9495	408100	0.588	-
0.9497	408200	0.6873	-
0.9500	408300	0.3978	-
0.9502	408400	0.6828	-
0.9504	408500	0.4542	-
0.9507	408600	0.378	-
0.9509	408700	0.5383	-
0.9511	408800	0.5439	-
0.9514	408900	0.7296	-
0.9516	409000	0.5981	-
0.9518	409100	0.6369	-
0.9521	409200	0.6636	-
0.9523	409300	0.5311	-
0.9525	409400	0.6119	-
0.9528	409500	0.4854	-
0.9530	409600	0.6694	-
0.9532	409700	0.7032	-
0.9535	409800	0.4525	-
0.9537	409900	0.4585	-
0.9539	410000	0.3537	-
0.9542	410100	0.5425	-
0.9544	410200	0.5096	-
0.9546	410300	0.566	-
0.9549	410400	0.6005	-
0.9551	410500	0.3909	-
0.9553	410600	0.6961	-
0.9556	410700	0.5936	-
0.9558	410800	0.8308	-
0.9560	410900	0.7371	-
0.9563	411000	0.3298	-
0.9565	411100	0.4226	-
0.9567	411200	0.5009	-
0.9570	411300	0.4229	-
0.9572	411400	0.9834	-
0.9574	411500	0.3231	-
0.9577	411600	0.6333	-
0.9579	411700	0.6367	-
0.9581	411800	0.5979	-
0.9584	411900	0.3648	-
0.9586	412000	0.4454	-
0.9588	412100	0.4954	-
0.9591	412200	0.2817	-
0.9593	412300	0.6391	-
0.9595	412400	0.5604	-
0.9597	412500	0.5778	-
0.9600	412600	0.6871	-
0.9602	412700	0.9481	-
0.9604	412800	0.4	-
0.9607	412900	0.3143	-
0.9609	413000	0.6584	-
0.9611	413100	0.4846	-
0.9614	413200	0.5946	-
0.9616	413300	0.4479	-
0.9618	413400	0.5276	-
0.9621	413500	0.3645	-
0.9623	413600	0.642	-
0.9625	413700	0.4733	-
0.9628	413800	0.3985	-
0.9630	413900	0.4297	-
0.9632	414000	0.7243	-
0.9635	414100	0.5832	-
0.9637	414200	0.6388	-
0.9639	414300	0.7865	-
0.9642	414400	0.7296	-
0.9644	414500	0.685	-
0.9646	414600	0.3503	-
0.9649	414700	0.3843	-
0.9651	414800	0.4523	-
0.9653	414900	0.6861	-
0.9656	415000	0.6599	-
0.9658	415100	0.7082	-
0.9660	415200	0.4906	-
0.9663	415300	0.5244	-
0.9665	415400	0.3348	-
0.9667	415500	0.3688	-
0.9670	415600	0.6577	-
0.9672	415700	0.7494	-
0.9674	415800	0.3354	-
0.9677	415900	0.3825	-
0.9679	416000	0.5764	-
0.9681	416100	0.6068	-
0.9684	416200	0.6882	-
0.9686	416300	0.6113	-
0.9688	416400	0.4707	-
0.9691	416500	0.6538	-
0.9693	416600	0.4443	-
0.9695	416700	0.4843	-
0.9698	416800	0.6167	-
0.9700	416900	0.4868	-
0.9702	417000	0.4102	-
0.9705	417100	0.4711	-
0.9707	417200	0.3247	-
0.9709	417300	0.4275	-
0.9711	417400	0.582	-
0.9714	417500	0.2713	-
0.9716	417600	0.783	-
0.9718	417700	0.7774	-
0.9721	417800	0.3721	-
0.9723	417900	0.4973	-
0.9725	418000	0.8411	-
0.9728	418100	0.4046	-
0.9730	418200	0.4052	-
0.9732	418300	0.4746	-
0.9735	418400	0.5832	-
0.9737	418500	0.4416	-
0.9739	418600	0.5787	-
0.9742	418700	0.4466	-
0.9744	418800	0.2802	-
0.9746	418900	0.5967	-
0.9749	419000	0.487	-
0.9751	419100	0.4598	-
0.9753	419200	0.2168	-
0.9756	419300	0.6222	-
0.9758	419400	0.6868	-
0.9760	419500	0.4405	-
0.9763	419600	0.3568	-
0.9765	419700	0.6097	-
0.9767	419800	0.5538	-
0.9770	419900	0.579	-
0.9772	420000	0.2911	-
0.9774	420100	0.46	-
0.9777	420200	0.4625	-
0.9779	420300	0.4325	-
0.9781	420400	0.3619	-
0.9784	420500	0.5093	-
0.9786	420600	0.69	-
0.9788	420700	0.455	-
0.9791	420800	0.5571	-
0.9793	420900	0.602	-
0.9795	421000	0.4377	-
0.9798	421100	0.4387	-
0.9800	421200	0.3258	-
0.9802	421300	0.4117	-
0.9805	421400	0.4693	-
0.9807	421500	0.6	-
0.9809	421600	0.5227	-
0.9812	421700	0.4066	-
0.9814	421800	0.3969	-
0.9816	421900	0.3324	-
0.9819	422000	0.3962	-
0.9821	422100	0.5911	-
0.9823	422200	0.5177	-
0.9826	422300	0.5165	-
0.9828	422400	0.6326	-
0.9830	422500	0.4568	-
0.9832	422600	0.3953	-
0.9835	422700	0.3668	-
0.9837	422800	0.3823	-
0.9839	422900	0.5832	-
0.9842	423000	0.4664	-
0.9844	423100	0.5498	-
0.9846	423200	0.7509	-
0.9849	423300	0.7746	-
0.9851	423400	0.7761	-
0.9853	423500	0.4898	-
0.9856	423600	0.4759	-
0.9858	423700	0.5844	-
0.9860	423800	0.6257	-
0.9863	423900	0.377	-
0.9865	424000	0.8176	-
0.9867	424100	0.4973	-
0.9870	424200	0.5534	-
0.9872	424300	0.6498	-
0.9874	424400	0.1818	-
0.9877	424500	0.3865	-
0.9879	424600	0.6435	-
0.9881	424700	0.4777	-
0.9884	424800	0.531	-
0.9886	424900	0.4877	-
0.9888	425000	0.534	-
0.9891	425100	0.64	-
0.9893	425200	0.4985	-
0.9895	425300	0.7725	-
0.9898	425400	0.4574	-
0.9900	425500	0.4788	-
0.9902	425600	0.3573	-
0.9905	425700	0.6843	-
0.9907	425800	0.6033	-
0.9909	425900	0.3263	-
0.9912	426000	0.7542	-
0.9914	426100	0.6818	-
0.9916	426200	0.4283	-
0.9919	426300	0.6007	-
0.9921	426400	0.3186	-
0.9923	426500	0.4427	-
0.9926	426600	0.4144	-
0.9928	426700	0.6011	-
0.9930	426800	0.6969	-
0.9933	426900	0.5045	-
0.9935	427000	0.489	-
0.9937	427100	0.4614	-
0.9940	427200	0.4189	-
0.9942	427300	0.3524	-
0.9944	427400	0.4475	-
0.9946	427500	0.4901	-
0.9949	427600	0.6397	-
0.9951	427700	0.4337	-
0.9953	427800	0.4758	-
0.9956	427900	0.5044	-
0.9958	428000	0.2651	-
0.9960	428100	0.7529	-
0.9963	428200	0.3475	-
0.9965	428300	0.4441	-
0.9967	428400	0.4093	-
0.9970	428500	0.5875	-
0.9972	428600	0.352	-
0.9974	428700	0.4624	-
0.9977	428800	0.7066	-
0.9979	428900	0.6167	-
0.9981	429000	0.4447	-
0.9984	429100	0.5141	-
0.9986	429200	0.5907	-
0.9988	429300	0.2852	-
0.9991	429400	0.4066	-
0.9993	429500	0.8943	-
0.9995	429600	0.4167	-
0.9998	429700	0.5968	-
1.0	429800	0.6068	-

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.0
Transformers: 4.55.4
PyTorch: 2.6.0+cu124
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.21.4

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},
}