metadata

base_model: sentence-transformers/all-MiniLM-L12-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:510287
  - loss:CoSENTLoss
widget:
  - source_sentence: bag
    sentences:
      - bag
      - summer colors bag
      - carry all bag
  - source_sentence: bean bag
    sentences:
      - bag
      - havan bag
      - black yellow shoes
  - source_sentence: pyramid shaped cushion mattress
    sentences:
      - dress
      - silver bag
      - women shoes
  - source_sentence: handcrafted rug
    sentences:
      - amaga  cross bag - white
      - handcrafted boots
      - polyester top
  - source_sentence: bean bag
    sentences:
      - bag
      - v-neck dress
      - bag
model-index:
  - name: all-MiniLM-L12-v2-pair_score
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: -0.10403022864037037
            name: Pearson Cosine
          - type: spearman_cosine
            value: -0.1437799564130218
            name: Spearman Cosine
          - type: pearson_manhattan
            value: -0.10847915569723102
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: -0.14274368509273366
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: -0.11064121359722408
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: -0.14377964610318103
            name: Spearman Euclidean
          - type: pearson_dot
            value: -0.10403015819885228
            name: Pearson Dot
          - type: spearman_dot
            value: -0.14377961300118045
            name: Spearman Dot
          - type: pearson_max
            value: -0.10403015819885228
            name: Pearson Max
          - type: spearman_max
            value: -0.14274368509273366
            name: Spearman Max

all-MiniLM-L12-v2-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L12-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-L12-v2
Maximum Sequence Length: 128 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': 128, '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 = [
    'bean bag',
    'bag',
    'v-neck dress',
]
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	-0.104
spearman_cosine	-0.1438
pearson_manhattan	-0.1085
spearman_manhattan	-0.1427
pearson_euclidean	-0.1106
spearman_euclidean	-0.1438
pearson_dot	-0.104
spearman_dot	-0.1438
pearson_max	-0.104
spearman_max	-0.1427

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 32
per_device_eval_batch_size: 32
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	-	-	-0.1438
0.0063	100	11.9171	-	-
0.0125	200	11.0074	-	-
0.0188	300	10.1073	-	-
0.0251	400	8.6232	-	-
0.0314	500	7.5947	7.2720	-
0.0376	600	6.3883	-	-
0.0439	700	5.6165	-	-
0.0502	800	4.8254	-	-
0.0564	900	4.5595	-	-
0.0627	1000	4.2965	4.1720	-
0.0690	1100	4.063	-	-
0.0752	1200	4.0861	-	-
0.0815	1300	3.9703	-	-
0.0878	1400	3.8222	-	-
0.0941	1500	3.927	3.6404	-
0.1003	1600	3.6892	-	-
0.1066	1700	3.9166	-	-
0.1129	1800	3.7162	-	-
0.1191	1900	3.4866	-	-
0.1254	2000	3.5202	3.4226	-
0.1317	2100	3.6876	-	-
0.1380	2200	3.4884	-	-
0.1442	2300	3.4407	-	-
0.1505	2400	3.2658	-	-
0.1568	2500	3.2973	3.0777	-
0.1630	2600	3.2087	-	-
0.1693	2700	3.4316	-	-
0.1756	2800	3.3372	-	-
0.1819	2900	3.161	-	-
0.1881	3000	3.0232	2.8805	-
0.1944	3100	3.2897	-	-
0.2007	3200	3.2576	-	-
0.2069	3300	2.7636	-	-
0.2132	3400	3.1788	-	-
0.2195	3500	2.6269	2.6237	-
0.2257	3600	2.9352	-	-
0.2320	3700	2.847	-	-
0.2383	3800	2.8001	-	-
0.2446	3900	2.6048	-	-
0.2508	4000	2.5976	2.5250	-
0.2571	4100	2.5211	-	-
0.2634	4200	2.7812	-	-
0.2696	4300	2.6822	-	-
0.2759	4400	2.4779	-	-
0.2822	4500	2.6242	2.6365	-
0.2885	4600	2.5655	-	-
0.2947	4700	2.9998	-	-
0.3010	4800	2.679	-	-
0.3073	4900	2.5719	-	-
0.3135	5000	2.6913	2.6934	-
0.3198	5100	2.8346	-	-
0.3261	5200	2.7453	-	-
0.3324	5300	2.4492	-	-
0.3386	5400	2.9389	-	-
0.3449	5500	2.6002	2.6182	-
0.3512	5600	2.2592	-	-
0.3574	5700	2.3822	-	-
0.3637	5800	2.4771	-	-
0.3700	5900	3.5914	-	-
0.3762	6000	2.3525	2.5605	-
0.3825	6100	2.2667	-	-
0.3888	6200	2.4671	-	-
0.3951	6300	2.6816	-	-
0.4013	6400	2.2303	-	-
0.4076	6500	2.3153	2.4245	-
0.4139	6600	2.7969	-	-
0.4201	6700	2.61	-	-
0.4264	6800	2.5267	-	-
0.4327	6900	2.532	-	-
0.4390	7000	2.6088	2.4666	-
0.4452	7100	1.848	-	-
0.4515	7200	2.1369	-	-
0.4578	7300	2.185	-	-
0.4640	7400	2.0279	-	-
0.4703	7500	2.5593	2.3958	-
0.4766	7600	2.339	-	-
0.4828	7700	2.2122	-	-
0.4891	7800	2.7878	-	-
0.4954	7900	2.3005	-	-
0.5017	8000	2.2922	2.5408	-
0.5079	8100	2.3731	-	-
0.5142	8200	2.1879	-	-
0.5205	8300	2.1598	-	-
0.5267	8400	2.2292	-	-
0.5330	8500	1.958	2.0935	-
0.5393	8600	2.1152	-	-
0.5456	8700	1.9725	-	-
0.5518	8800	2.1106	-	-
0.5581	8900	2.06	-	-
0.5644	9000	1.7624	2.1509	-
0.5706	9100	2.3793	-	-
0.5769	9200	1.9322	-	-
0.5832	9300	1.8355	-	-
0.5895	9400	2.1425	-	-
0.5957	9500	2.2191	1.9984	-
0.6020	9600	2.3245	-	-
0.6083	9700	2.1206	-	-
0.6145	9800	2.0957	-	-
0.6208	9900	2.5276	-	-
0.6271	10000	1.5383	1.9509	-
0.6333	10100	2.111	-	-
0.6396	10200	1.893	-	-
0.6459	10300	1.8961	-	-
0.6522	10400	1.6599	-	-
0.6584	10500	2.3409	1.8286	-
0.6647	10600	1.9741	-	-
0.6710	10700	2.0438	-	-
0.6772	10800	1.814	-	-
0.6835	10900	2.1819	-	-
0.6898	11000	1.8547	1.9461	-
0.6961	11100	2.5979	-	-
0.7023	11200	1.9309	-	-
0.7086	11300	1.6247	-	-
0.7149	11400	2.1107	-	-
0.7211	11500	2.1264	1.8004	-
0.7274	11600	1.7397	-	-
0.7337	11700	1.9569	-	-
0.7400	11800	1.4769	-	-
0.7462	11900	1.6222	-	-
0.7525	12000	1.5354	1.6811	-
0.7588	12100	2.2645	-	-
0.7650	12200	1.8662	-	-
0.7713	12300	1.5327	-	-
0.7776	12400	1.9501	-	-
0.7838	12500	2.0923	1.6134	-
0.7901	12600	1.8887	-	-
0.7964	12700	1.7207	-	-
0.8027	12800	1.8589	-	-
0.8089	12900	1.7602	-	-
0.8152	13000	2.2405	1.5030	-
0.8215	13100	1.6249	-	-
0.8277	13200	1.6814	-	-
0.8340	13300	1.4072	-	-
0.8403	13400	1.6286	-	-
0.8466	13500	2.2081	1.6078	-
0.8528	13600	1.7387	-	-
0.8591	13700	1.5268	-	-
0.8654	13800	1.5693	-	-
0.8716	13900	1.2473	-	-
0.8779	14000	1.361	1.7168	-
0.8842	14100	1.5246	-	-
0.8904	14200	1.7266	-	-
0.8967	14300	0.9221	-	-
0.9030	14400	1.6397	-	-
0.9093	14500	1.3139	1.5492	-
0.9155	14600	1.7942	-	-
0.9218	14700	1.5206	-	-
0.9281	14800	1.5868	-	-
0.9343	14900	1.2131	-	-
0.9406	15000	1.8765	1.4192	-
0.9469	15100	1.624	-	-
0.9532	15200	1.4692	-	-
0.9594	15300	1.5426	-	-
0.9657	15400	1.3668	-	-
0.9720	15500	1.3951	1.6835	-
0.9782	15600	1.1567	-	-
0.9845	15700	1.8634	-	-
0.9908	15800	1.641	-	-
0.9971	15900	1.6458	-	-
1.0033	16000	1.1369	1.5746	-
1.0096	16100	1.1913	-	-
1.0159	16200	1.5563	-	-
1.0221	16300	1.4081	-	-
1.0284	16400	1.8157	-	-
1.0347	16500	1.6405	1.5235	-
1.0409	16600	0.9207	-	-
1.0472	16700	1.4301	-	-
1.0535	16800	1.4566	-	-
1.0598	16900	1.5397	-	-
1.0660	17000	1.3417	1.3883	-
1.0723	17100	0.9769	-	-
1.0786	17200	1.3734	-	-
1.0848	17300	1.0874	-	-
1.0911	17400	1.2601	-	-
1.0974	17500	1.4799	1.4361	-
1.1037	17600	1.1086	-	-
1.1099	17700	1.3731	-	-
1.1162	17800	1.0515	-	-
1.1225	17900	1.7916	-	-
1.1287	18000	1.7606	1.3792	-
1.1350	18100	1.3844	-	-
1.1413	18200	1.3567	-	-
1.1476	18300	1.4322	-	-
1.1538	18400	1.9509	-	-
1.1601	18500	1.0303	1.3425	-
1.1664	18600	1.6484	-	-
1.1726	18700	1.1177	-	-
1.1789	18800	1.0295	-	-
1.1852	18900	1.4364	-	-
1.1914	19000	1.1954	1.3385	-
1.1977	19100	1.1944	-	-
1.2040	19200	0.9109	-	-
1.2103	19300	1.4191	-	-
1.2165	19400	1.5755	-	-
1.2228	19500	1.0958	1.2872	-
1.2291	19600	0.9054	-	-
1.2353	19700	1.0892	-	-
1.2416	19800	1.4455	-	-
1.2479	19900	1.3273	-	-
1.2542	20000	1.6442	1.2880	-
1.2604	20100	1.1901	-	-
1.2667	20200	0.9871	-	-
1.2730	20300	1.6448	-	-
1.2792	20400	1.1899	-	-
1.2855	20500	1.3454	1.3303	-
1.2918	20600	1.4376	-	-
1.2980	20700	1.0356	-	-
1.3043	20800	1.7588	-	-
1.3106	20900	1.0993	-	-
1.3169	21000	1.3673	1.2607	-
1.3231	21100	1.3326	-	-
1.3294	21200	1.3618	-	-
1.3357	21300	1.3123	-	-
1.3419	21400	0.9771	-	-
1.3482	21500	1.1626	1.2873	-
1.3545	21600	1.41	-	-
1.3608	21700	1.6998	-	-
1.3670	21800	0.8335	-	-
1.3733	21900	1.579	-	-
1.3796	22000	1.6073	1.2164	-
1.3858	22100	1.0534	-	-
1.3921	22200	1.0045	-	-
1.3984	22300	1.4195	-	-
1.4047	22400	1.4409	-	-
1.4109	22500	1.3942	1.2018	-
1.4172	22600	1.6013	-	-
1.4235	22700	1.139	-	-
1.4297	22800	0.7062	-	-
1.4360	22900	1.1948	-	-
1.4423	23000	1.6784	1.1736	-
1.4485	23100	1.1618	-	-
1.4548	23200	0.827	-	-
1.4611	23300	1.0041	-	-
1.4674	23400	0.7447	-	-
1.4736	23500	1.1531	1.0797	-
1.4799	23600	1.0904	-	-
1.4862	23700	1.0648	-	-
1.4924	23800	1.1863	-	-
1.4987	23900	0.893	-	-
1.5050	24000	1.2528	1.0737	-
1.5113	24100	0.9333	-	-
1.5175	24200	1.3404	-	-
1.5238	24300	0.8959	-	-
1.5301	24400	0.6898	-	-
1.5363	24500	0.9896	1.1813	-
1.5426	24600	0.7928	-	-
1.5489	24700	1.4153	-	-
1.5552	24800	1.2393	-	-
1.5614	24900	0.744	-	-
1.5677	25000	0.7545	1.0823	-
1.5740	25100	1.1936	-	-
1.5802	25200	0.8755	-	-
1.5865	25300	1.063	-	-
1.5928	25400	0.8634	-	-
1.5990	25500	1.2905	1.0718	-
1.6053	25600	1.0906	-	-
1.6116	25700	1.1594	-	-
1.6179	25800	1.108	-	-
1.6241	25900	1.2538	-	-
1.6304	26000	1.3377	1.1370	-
1.6367	26100	0.8156	-	-
1.6429	26200	0.9753	-	-
1.6492	26300	1.0909	-	-
1.6555	26400	1.0029	-	-
1.6618	26500	0.6841	1.0385	-
1.6680	26600	1.1673	-	-
1.6743	26700	1.3606	-	-
1.6806	26800	0.4306	-	-
1.6868	26900	1.0989	-	-
1.6931	27000	1.3283	1.0136	-
1.6994	27100	1.0206	-	-
1.7056	27200	0.6866	-	-
1.7119	27300	0.9168	-	-
1.7182	27400	0.9472	-	-
1.7245	27500	0.7866	1.0890	-
1.7307	27600	1.481	-	-
1.7370	27700	1.0311	-	-
1.7433	27800	1.3346	-	-
1.7495	27900	0.8331	-	-
1.7558	28000	1.3056	0.9919	-
1.7621	28100	0.9692	-	-
1.7684	28200	0.9337	-	-
1.7746	28300	1.1588	-	-
1.7809	28400	1.0859	-	-
1.7872	28500	0.9939	1.0109	-
1.7934	28600	1.4019	-	-
1.7997	28700	0.9404	-	-
1.8060	28800	0.7085	-	-
1.8123	28900	1.1423	-	-
1.8185	29000	0.8389	0.9510	-
1.8248	29100	1.3947	-	-
1.8311	29200	0.8909	-	-
1.8373	29300	1.3824	-	-
1.8436	29400	0.6364	-	-
1.8499	29500	1.2197	0.9501	-
1.8561	29600	0.6353	-	-
1.8624	29700	1.3453	-	-
1.8687	29800	1.1069	-	-
1.8750	29900	0.9873	-	-
1.8812	30000	0.9291	1.0391	-
1.8875	30100	1.3971	-	-
1.8938	30200	1.0569	-	-
1.9000	30300	0.6731	-	-
1.9063	30400	1.0216	-	-
1.9126	30500	1.295	0.9819	-
1.9189	30600	1.1641	-	-
1.9251	30700	0.9199	-	-
1.9314	30800	0.9774	-	-
1.9377	30900	0.8242	-	-
1.9439	31000	1.4039	0.9666	-
1.9502	31100	0.7112	-	-
1.9565	31200	0.846	-	-
1.9628	31300	1.0952	-	-
1.9690	31400	1.0372	-	-
1.9753	31500	0.9585	0.8983	-
1.9816	31600	1.1527	-	-
1.9878	31700	0.7675	-	-
1.9941	31800	0.8359	-	-
2.0004	31900	1.1224	-	-
2.0066	32000	1.3421	0.9575	-
2.0129	32100	0.9171	-	-
2.0192	32200	0.5865	-	-
2.0255	32300	0.9239	-	-
2.0317	32400	0.7426	-	-
2.0380	32500	0.8965	0.9158	-
2.0443	32600	0.6605	-	-
2.0505	32700	0.8507	-	-
2.0568	32800	0.7288	-	-
2.0631	32900	0.6888	-	-
2.0694	33000	0.8745	0.9568	-
2.0756	33100	0.7972	-	-
2.0819	33200	0.6211	-	-
2.0882	33300	1.0126	-	-
2.0944	33400	0.8268	-	-
2.1007	33500	0.9723	0.8551	-
2.1070	33600	0.6366	-	-
2.1133	33700	0.6773	-	-
2.1195	33800	0.7676	-	-
2.1258	33900	0.9192	-	-
2.1321	34000	0.7054	0.8941	-
2.1383	34100	0.7349	-	-
2.1446	34200	0.6288	-	-
2.1509	34300	0.799	-	-
2.1571	34400	0.7492	-	-
2.1634	34500	1.0967	0.8746	-
2.1697	34600	0.7628	-	-
2.1760	34700	0.7697	-	-
2.1822	34800	0.7458	-	-
2.1885	34900	0.7868	-	-
2.1948	35000	0.9526	0.8620	-
2.2010	35100	0.6087	-	-
2.2073	35200	0.8602	-	-
2.2136	35300	0.8906	-	-
2.2199	35400	0.6012	-	-
2.2261	35500	0.9625	0.9094	-
2.2324	35600	0.8622	-	-
2.2387	35700	0.9015	-	-
2.2449	35800	1.0395	-	-
2.2512	35900	0.5582	-	-
2.2575	36000	0.7266	0.8666	-
2.2637	36100	0.6806	-	-
2.2700	36200	0.9246	-	-
2.2763	36300	0.7452	-	-
2.2826	36400	0.7886	-	-
2.2888	36500	0.9288	0.8529	-
2.2951	36600	1.2166	-	-
2.3014	36700	0.9566	-	-
2.3076	36800	0.7842	-	-
2.3139	36900	0.6815	-	-
2.3202	37000	0.78	0.8212	-
2.3265	37100	0.8306	-	-
2.3327	37200	0.8073	-	-
2.3390	37300	0.7565	-	-
2.3453	37400	0.8478	-	-
2.3515	37500	1.0159	0.8735	-
2.3578	37600	0.8126	-	-
2.3641	37700	0.751	-	-
2.3704	37800	0.7185	-	-
2.3766	37900	0.7429	-	-
2.3829	38000	0.7149	0.7997	-
2.3892	38100	0.6867	-	-
2.3954	38200	0.608	-	-
2.4017	38300	0.5687	-	-
2.4080	38400	0.6623	-	-
2.4142	38500	0.7751	0.7834	-
2.4205	38600	0.6537	-	-
2.4268	38700	0.7121	-	-
2.4331	38800	0.7864	-	-
2.4393	38900	0.296	-	-
2.4456	39000	0.4544	0.8051	-
2.4519	39100	0.4543	-	-
2.4581	39200	0.9965	-	-
2.4644	39300	0.4595	-	-
2.4707	39400	0.7557	-	-
2.4770	39500	0.6006	0.8437	-
2.4832	39600	0.695	-	-
2.4895	39700	0.6292	-	-
2.4958	39800	0.7392	-	-
2.5020	39900	0.6547	-	-
2.5083	40000	0.739	0.8443	-
2.5146	40100	0.5618	-	-
2.5209	40200	0.861	-	-
2.5271	40300	0.7318	-	-
2.5334	40400	0.9021	-	-
2.5397	40500	0.7329	0.8595	-
2.5459	40600	0.9691	-	-
2.5522	40700	1.0524	-	-
2.5585	40800	0.4546	-	-
2.5647	40900	0.8917	-	-
2.5710	41000	0.6644	0.8664	-
2.5773	41100	0.5167	-	-
2.5836	41200	0.6499	-	-
2.5898	41300	0.8096	-	-
2.5961	41400	0.7269	-	-
2.6024	41500	0.8561	0.8173	-
2.6086	41600	0.761	-	-
2.6149	41700	1.0167	-	-
2.6212	41800	0.763	-	-
2.6275	41900	0.6659	-	-
2.6337	42000	0.7299	0.8343	-
2.6400	42100	0.7045	-	-
2.6463	42200	0.9054	-	-
2.6525	42300	0.3002	-	-
2.6588	42400	0.7728	-	-
2.6651	42500	0.8214	0.8112	-
2.6713	42600	0.6762	-	-
2.6776	42700	0.8863	-	-
2.6839	42800	0.7438	-	-
2.6902	42900	0.5968	-	-
2.6964	43000	0.5292	0.7920	-
2.7027	43100	0.429	-	-
2.7090	43200	0.6001	-	-
2.7152	43300	0.7253	-	-
2.7215	43400	0.9268	-	-
2.7278	43500	0.9536	0.8434	-
2.7341	43600	0.6164	-	-
2.7403	43700	0.8411	-	-
2.7466	43800	1.0441	-	-
2.7529	43900	0.6473	-	-
2.7591	44000	0.8697	0.8089	-
2.7654	44100	0.7743	-	-
2.7717	44200	0.9118	-	-
2.7780	44300	0.7464	-	-
2.7842	44400	0.7195	-	-
2.7905	44500	0.9814	0.8122	-
2.7968	44600	0.5812	-	-
2.8030	44700	0.5095	-	-
2.8093	44800	0.7771	-	-
2.8156	44900	0.6714	-	-
2.8218	45000	0.5836	0.7786	-
2.8281	45100	1.0708	-	-
2.8344	45200	0.576	-	-
2.8407	45300	0.9657	-	-
2.8469	45400	0.8103	-	-
2.8532	45500	0.4644	0.7895	-
2.8595	45600	0.7485	-	-
2.8657	45700	0.9843	-	-
2.8720	45800	0.8462	-	-
2.8783	45900	0.9025	-	-
2.8846	46000	0.7014	0.8031	-
2.8908	46100	0.5638	-	-
2.8971	46200	0.6016	-	-
2.9034	46300	0.7257	-	-
2.9096	46400	1.1182	-	-
2.9159	46500	1.0352	0.8031	-
2.9222	46600	0.8413	-	-
2.9285	46700	0.7341	-	-
2.9347	46800	0.7115	-	-
2.9410	46900	0.9124	-	-
2.9473	47000	0.7988	0.7591	-
2.9535	47100	0.8373	-	-
2.9598	47200	0.8587	-	-
2.9661	47300	0.4961	-	-
2.9723	47400	0.7349	-	-
2.9786	47500	0.5285	0.7255	-
2.9849	47600	0.3715	-	-
2.9912	47700	0.811	-	-
2.9974	47800	0.6716	-	-
3.0037	47900	0.4408	-	-
3.0100	48000	0.7449	0.7503	-
3.0162	48100	0.4491	-	-
3.0225	48200	0.5995	-	-
3.0288	48300	0.6073	-	-
3.0351	48400	0.5753	-	-
3.0413	48500	0.6204	0.7650	-
3.0476	48600	0.9864	-	-
3.0539	48700	0.6648	-	-
3.0601	48800	0.4662	-	-
3.0664	48900	0.5638	-	-
3.0727	49000	0.6692	0.7381	-
3.0789	49100	0.6403	-	-
3.0852	49200	0.5042	-	-
3.0915	49300	0.4447	-	-
3.0978	49400	0.5983	-	-
3.1040	49500	0.6961	0.7289	-
3.1103	49600	0.8092	-	-
3.1166	49700	0.4172	-	-
3.1228	49800	0.6542	-	-
3.1291	49900	0.8016	-	-
3.1354	50000	0.3927	0.7370	-
3.1417	50100	0.4724	-	-
3.1479	50200	0.46	-	-
3.1542	50300	0.4258	-	-
3.1605	50400	0.5053	-	-
3.1667	50500	0.3406	0.7210	-
3.1730	50600	0.6276	-	-
3.1793	50700	0.5913	-	-
3.1856	50800	0.3902	-	-
3.1918	50900	0.5063	-	-
3.1981	51000	0.7909	0.7442	-
3.2044	51100	0.5071	-	-
3.2106	51200	0.5611	-	-
3.2169	51300	0.545	-	-
3.2232	51400	0.4359	-	-
3.2294	51500	0.5249	0.7148	-
3.2357	51600	0.6759	-	-
3.2420	51700	0.5458	-	-
3.2483	51800	0.5195	-	-
3.2545	51900	0.292	-	-
3.2608	52000	0.4826	0.7129	-
3.2671	52100	0.2496	-	-
3.2733	52200	0.6702	-	-
3.2796	52300	0.3192	-	-
3.2859	52400	0.66	-	-
3.2922	52500	0.6472	0.7146	-
3.2984	52600	0.4482	-	-
3.3047	52700	0.6618	-	-
3.3110	52800	0.4424	-	-
3.3172	52900	0.6157	-	-
3.3235	53000	0.5087	0.7036	-
3.3298	53100	0.5148	-	-
3.3361	53200	0.386	-	-
3.3423	53300	0.3552	-	-
3.3486	53400	0.5609	-	-
3.3549	53500	0.3549	0.7148	-
3.3611	53600	0.3099	-	-
3.3674	53700	0.2903	-	-
3.3737	53800	0.7385	-	-
3.3799	53900	0.7025	-	-
3.3862	54000	0.5625	0.7014	-
3.3925	54100	0.7545	-	-
3.3988	54200	0.4371	-	-
3.4050	54300	0.4588	-	-
3.4113	54400	0.4973	-	-
3.4176	54500	0.4534	0.7010	-
3.4238	54600	0.6761	-	-
3.4301	54700	0.6559	-	-
3.4364	54800	0.6087	-	-
3.4427	54900	0.601	-	-
3.4489	55000	0.4894	0.6706	-
3.4552	55100	0.6524	-	-
3.4615	55200	0.8268	-	-
3.4677	55300	0.1795	-	-
3.4740	55400	0.5667	-	-
3.4803	55500	0.4185	0.6823	-
3.4865	55600	0.615	-	-
3.4928	55700	0.6231	-	-
3.4991	55800	0.3809	-	-
3.5054	55900	0.6747	-	-
3.5116	56000	0.6484	0.6736	-
3.5179	56100	0.6208	-	-
3.5242	56200	0.2345	-	-
3.5304	56300	0.4494	-	-
3.5367	56400	0.327	-	-
3.5430	56500	0.5614	0.6762	-
3.5493	56600	0.8796	-	-
3.5555	56700	0.6068	-	-
3.5618	56800	0.4918	-	-
3.5681	56900	0.7352	-	-
3.5743	57000	0.4149	0.6881	-
3.5806	57100	0.3746	-	-
3.5869	57200	0.7055	-	-
3.5932	57300	0.5557	-	-
3.5994	57400	0.7734	-	-
3.6057	57500	0.5263	0.6800	-
3.6120	57600	0.4527	-	-
3.6182	57700	0.8339	-	-
3.6245	57800	0.7004	-	-
3.6308	57900	0.5068	-	-
3.6370	58000	0.6601	0.6667	-
3.6433	58100	0.8452	-	-
3.6496	58200	0.2345	-	-
3.6559	58300	0.6034	-	-
3.6621	58400	0.8962	-	-
3.6684	58500	0.5844	0.6755	-
3.6747	58600	0.6827	-	-
3.6809	58700	0.4087	-	-
3.6872	58800	0.6221	-	-
3.6935	58900	0.777	-	-
3.6998	59000	0.572	0.6737	-
3.7060	59100	0.5479	-	-
3.7123	59200	0.5078	-	-
3.7186	59300	0.6982	-	-
3.7248	59400	0.2223	-	-
3.7311	59500	0.5361	0.6709	-
3.7374	59600	0.6072	-	-
3.7437	59700	0.35	-	-
3.7499	59800	0.8802	-	-
3.7562	59900	0.6216	-	-
3.7625	60000	0.2514	0.6836	-
3.7687	60100	0.6285	-	-
3.7750	60200	0.9845	-	-
3.7813	60300	0.5355	-	-
3.7875	60400	0.495	-	-
3.7938	60500	0.6905	0.6725	-
3.8001	60600	0.563	-	-
3.8064	60700	0.6067	-	-
3.8126	60800	0.7585	-	-
3.8189	60900	0.4283	-	-
3.8252	61000	0.4758	0.6600	-
3.8314	61100	0.5462	-	-
3.8377	61200	0.649	-	-
3.8440	61300	0.5576	-	-
3.8503	61400	0.6717	-	-
3.8565	61500	0.2951	0.6613	-
3.8628	61600	0.457	-	-
3.8691	61700	0.473	-	-
3.8753	61800	0.5181	-	-
3.8816	61900	0.4581	-	-
3.8879	62000	0.6875	0.6669	-
3.8941	62100	0.3821	-	-
3.9004	62200	0.5039	-	-
3.9067	62300	0.6809	-	-
3.9130	62400	0.3591	-	-
3.9192	62500	0.6695	0.6654	-
3.9255	62600	0.5352	-	-
3.9318	62700	0.8635	-	-
3.9380	62800	0.73	-	-
3.9443	62900	0.4138	-	-
3.9506	63000	0.3704	0.6620	-
3.9569	63100	0.4831	-	-
3.9631	63200	0.5405	-	-
3.9694	63300	0.6123	-	-
3.9757	63400	0.5167	-	-
3.9819	63500	0.6967	0.6613	-
3.9882	63600	0.338	-	-
3.9945	63700	0.515	-	-

Framework Versions

Python: 3.8.10
Sentence Transformers: 3.1.1
Transformers: 4.45.1
PyTorch: 2.4.0+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
Tokenizers: 0.20.0

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},
}