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: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-L6-v2-pair_score
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: -0.13726370961372045
            name: Pearson Cosine
          - type: spearman_cosine
            value: -0.16645918619928507
            name: Spearman Cosine
          - type: pearson_manhattan
            value: -0.1405300294713842
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: -0.16334559546016153
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: -0.1432496898556385
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: -0.16645904911745338
            name: Spearman Euclidean
          - type: pearson_dot
            value: -0.13726370008450378
            name: Pearson Dot
          - type: spearman_dot
            value: -0.1664594964294906
            name: Spearman Dot
          - type: pearson_max
            value: -0.13726370008450378
            name: Pearson Max
          - type: spearman_max
            value: -0.16334559546016153
            name: Spearman Max

all-MiniLM-L6-v2-pair_score

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 = [
    '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	-0.1373
spearman_cosine	-0.1665
pearson_manhattan	-0.1405
spearman_manhattan	-0.1633
pearson_euclidean	-0.1432
spearman_euclidean	-0.1665
pearson_dot	-0.1373
spearman_dot	-0.1665
pearson_max	-0.1373
spearman_max	-0.1633

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	-	-	-0.1665
0.0063	100	11.9622	-	-
0.0125	200	11.265	-	-
0.0188	300	10.5195	-	-
0.0251	400	9.4744	-	-
0.0314	500	8.4815	8.6217	-
0.0376	600	7.6105	-	-
0.0439	700	6.8023	-	-
0.0502	800	6.1258	-	-
0.0564	900	5.5032	-	-
0.0627	1000	5.0397	5.1949	-
0.0690	1100	4.6909	-	-
0.0752	1200	4.5716	-	-
0.0815	1300	4.3983	-	-
0.0878	1400	4.2073	-	-
0.0941	1500	4.2164	4.1422	-
0.1003	1600	4.0921	-	-
0.1066	1700	4.1785	-	-
0.1129	1800	4.0503	-	-
0.1191	1900	3.8969	-	-
0.1254	2000	3.8538	3.9109	-
0.1317	2100	3.872	-	-
0.1380	2200	3.851	-	-
0.1442	2300	3.6301	-	-
0.1505	2400	3.5202	-	-
0.1568	2500	3.6759	3.6389	-
0.1630	2600	3.4106	-	-
0.1693	2700	3.69	-	-
0.1756	2800	3.6336	-	-
0.1819	2900	3.4715	-	-
0.1881	3000	3.2166	3.2739	-
0.1944	3100	3.3844	-	-
0.2007	3200	3.4449	-	-
0.2069	3300	3.0811	-	-
0.2132	3400	3.2777	-	-
0.2195	3500	2.9505	3.0865	-
0.2257	3600	3.1534	-	-
0.2320	3700	2.9669	-	-
0.2383	3800	2.9416	-	-
0.2446	3900	2.9637	-	-
0.2508	4000	2.9322	2.8447	-
0.2571	4100	2.6926	-	-
0.2634	4200	2.9353	-	-
0.2696	4300	2.635	-	-
0.2759	4400	2.5692	-	-
0.2822	4500	3.0283	2.9033	-
0.2885	4600	2.5804	-	-
0.2947	4700	3.1374	-	-
0.3010	4800	2.8479	-	-
0.3073	4900	2.6809	-	-
0.3135	5000	2.8267	2.6946	-
0.3198	5100	2.7341	-	-
0.3261	5200	2.8157	-	-
0.3324	5300	2.5867	-	-
0.3386	5400	2.8622	-	-
0.3449	5500	2.9063	2.6115	-
0.3512	5600	2.1514	-	-
0.3574	5700	2.3755	-	-
0.3637	5800	2.5055	-	-
0.3700	5900	3.3237	-	-
0.3762	6000	2.561	2.7512	-
0.3825	6100	2.4351	-	-
0.3888	6200	2.8472	-	-
0.3951	6300	2.76	-	-
0.4013	6400	2.1947	-	-
0.4076	6500	2.6409	2.5367	-
0.4139	6600	2.7262	-	-
0.4201	6700	2.7781	-	-
0.4264	6800	2.4718	-	-
0.4327	6900	2.567	-	-
0.4390	7000	2.4215	2.3409	-
0.4452	7100	1.9308	-	-
0.4515	7200	2.1232	-	-
0.4578	7300	2.421	-	-
0.4640	7400	2.3232	-	-
0.4703	7500	2.8543	2.3706	-
0.4766	7600	2.4276	-	-
0.4828	7700	2.4507	-	-
0.4891	7800	2.1963	-	-
0.4954	7900	2.4247	-	-
0.5017	8000	2.1948	2.5729	-
0.5079	8100	2.4069	-	-
0.5142	8200	2.4328	-	-
0.5205	8300	2.2198	-	-
0.5267	8400	2.1746	-	-
0.5330	8500	2.2618	2.3459	-
0.5393	8600	2.3909	-	-
0.5456	8700	2.035	-	-
0.5518	8800	2.2626	-	-
0.5581	8900	2.1541	-	-
0.5644	9000	1.9424	2.1625	-
0.5706	9100	2.5152	-	-
0.5769	9200	2.0462	-	-
0.5832	9300	1.6124	-	-
0.5895	9400	2.2236	-	-
0.5957	9500	2.4706	2.0569	-
0.6020	9600	2.4612	-	-
0.6083	9700	2.2784	-	-
0.6145	9800	1.9335	-	-
0.6208	9900	2.3779	-	-
0.6271	10000	1.6778	2.1123	-
0.6333	10100	2.4721	-	-
0.6396	10200	1.7822	-	-
0.6459	10300	2.077	-	-
0.6522	10400	1.9223	-	-
0.6584	10500	2.3513	1.8403	-
0.6647	10600	2.1387	-	-
0.6710	10700	2.1853	-	-
0.6772	10800	1.8715	-	-
0.6835	10900	1.8581	-	-
0.6898	11000	2.0076	2.0063	-
0.6961	11100	2.3144	-	-
0.7023	11200	2.0942	-	-
0.7086	11300	1.9117	-	-
0.7149	11400	2.2214	-	-
0.7211	11500	1.9678	1.9029	-
0.7274	11600	1.7459	-	-
0.7337	11700	2.0616	-	-
0.7400	11800	1.6169	-	-
0.7462	11900	1.5674	-	-
0.7525	12000	1.4956	1.8267	-
0.7588	12100	2.3816	-	-
0.7650	12200	2.2387	-	-
0.7713	12300	1.4625	-	-
0.7776	12400	2.028	-	-
0.7838	12500	2.151	1.7581	-
0.7901	12600	1.6896	-	-
0.7964	12700	1.8526	-	-
0.8027	12800	1.9745	-	-
0.8089	12900	2.1042	-	-
0.8152	13000	1.83	1.5667	-
0.8215	13100	1.7451	-	-
0.8277	13200	1.568	-	-
0.8340	13300	1.4432	-	-
0.8403	13400	1.9172	-	-
0.8466	13500	1.9438	1.6055	-
0.8528	13600	1.6488	-	-
0.8591	13700	1.8166	-	-
0.8654	13800	1.5929	-	-
0.8716	13900	1.2476	-	-
0.8779	14000	1.5236	1.8921	-
0.8842	14100	1.6538	-	-
0.8904	14200	1.8689	-	-
0.8967	14300	1.0831	-	-
0.9030	14400	1.7765	-	-
0.9093	14500	1.3548	1.6683	-
0.9155	14600	1.7792	-	-
0.9218	14700	1.73	-	-
0.9281	14800	1.5979	-	-
0.9343	14900	1.3678	-	-
0.9406	15000	2.0664	1.5161	-
0.9469	15100	1.4472	-	-
0.9532	15200	1.447	-	-
0.9594	15300	1.7261	-	-
0.9657	15400	1.4881	-	-
0.9720	15500	1.313	1.6227	-
0.9782	15600	1.4587	-	-
0.9845	15700	2.0982	-	-
0.9908	15800	1.4854	-	-
0.9971	15900	1.343	-	-
1.0033	16000	1.1795	1.5639	-
1.0096	16100	1.4001	-	-
1.0159	16200	1.3867	-	-
1.0221	16300	1.5191	-	-
1.0284	16400	1.4693	-	-
1.0347	16500	1.628	1.4716	-
1.0409	16600	1.0041	-	-
1.0472	16700	1.7728	-	-
1.0535	16800	1.5586	-	-
1.0598	16900	1.7229	-	-
1.0660	17000	1.5556	1.4676	-
1.0723	17100	1.2529	-	-
1.0786	17200	1.4787	-	-
1.0848	17300	1.1947	-	-
1.0911	17400	1.3014	-	-
1.0974	17500	1.3743	1.4624	-
1.1037	17600	1.3397	-	-
1.1099	17700	1.3062	-	-
1.1162	17800	1.3288	-	-
1.1225	17900	2.0002	-	-
1.1287	18000	2.0294	1.4185	-
1.1350	18100	1.5053	-	-
1.1413	18200	1.3657	-	-
1.1476	18300	1.3877	-	-
1.1538	18400	1.9034	-	-
1.1601	18500	1.4001	1.3813	-
1.1664	18600	1.7503	-	-
1.1726	18700	1.1482	-	-
1.1789	18800	1.0958	-	-
1.1852	18900	1.2657	-	-
1.1914	19000	1.3721	1.4702	-
1.1977	19100	1.2361	-	-
1.2040	19200	1.003	-	-
1.2103	19300	1.3677	-	-
1.2165	19400	1.668	-	-
1.2228	19500	1.2026	1.3641	-
1.2291	19600	1.1754	-	-
1.2353	19700	1.3196	-	-
1.2416	19800	1.4766	-	-
1.2479	19900	1.389	-	-
1.2542	20000	1.6974	1.3344	-
1.2604	20100	1.5036	-	-
1.2667	20200	1.1728	-	-
1.2730	20300	1.6058	-	-
1.2792	20400	1.5191	-	-
1.2855	20500	1.4516	1.3210	-
1.2918	20600	1.3485	-	-
1.2980	20700	1.2598	-	-
1.3043	20800	1.5871	-	-
1.3106	20900	1.1965	-	-
1.3169	21000	1.3983	1.2517	-
1.3231	21100	1.2605	-	-
1.3294	21200	1.5629	-	-
1.3357	21300	1.0668	-	-
1.3419	21400	1.1879	-	-
1.3482	21500	1.132	1.3881	-
1.3545	21600	1.7231	-	-
1.3608	21700	1.7636	-	-
1.3670	21800	1.1193	-	-
1.3733	21900	1.4662	-	-
1.3796	22000	2.0394	1.1927	-
1.3858	22100	1.1535	-	-
1.3921	22200	1.4592	-	-
1.3984	22300	1.276	-	-
1.4047	22400	1.2984	-	-
1.4109	22500	0.9741	1.2707	-
1.4172	22600	1.4253	-	-
1.4235	22700	1.0769	-	-
1.4297	22800	0.8276	-	-
1.4360	22900	1.2689	-	-
1.4423	23000	1.4817	1.2095	-
1.4485	23100	1.1522	-	-
1.4548	23200	0.8978	-	-
1.4611	23300	1.015	-	-
1.4674	23400	1.0351	-	-
1.4736	23500	1.3959	1.1969	-
1.4799	23600	1.2879	-	-
1.4862	23700	1.0651	-	-
1.4924	23800	1.1601	-	-
1.4987	23900	1.0034	-	-
1.5050	24000	1.3386	1.1590	-
1.5113	24100	1.142	-	-
1.5175	24200	1.3495	-	-
1.5238	24300	0.9993	-	-
1.5301	24400	0.9363	-	-
1.5363	24500	1.4402	1.2178	-
1.5426	24600	1.0648	-	-
1.5489	24700	1.5102	-	-
1.5552	24800	1.3415	-	-
1.5614	24900	0.7441	-	-
1.5677	25000	0.901	1.1982	-
1.5740	25100	1.3147	-	-
1.5802	25200	0.971	-	-
1.5865	25300	0.9988	-	-
1.5928	25400	1.1445	-	-
1.5990	25500	1.1018	1.1423	-
1.6053	25600	1.0902	-	-
1.6116	25700	1.2577	-	-
1.6179	25800	1.2005	-	-
1.6241	25900	1.2839	-	-
1.6304	26000	1.4122	1.1125	-
1.6367	26100	0.7832	-	-
1.6429	26200	1.3278	-	-
1.6492	26300	1.2055	-	-
1.6555	26400	1.5814	-	-
1.6618	26500	1.0393	1.0946	-
1.6680	26600	1.4531	-	-
1.6743	26700	1.4162	-	-
1.6806	26800	0.8498	-	-
1.6868	26900	1.1318	-	-
1.6931	27000	1.3287	1.0439	-
1.6994	27100	1.0886	-	-
1.7056	27200	0.8991	-	-
1.7119	27300	0.7563	-	-
1.7182	27400	0.9284	-	-
1.7245	27500	1.3388	1.0940	-
1.7307	27600	1.2951	-	-
1.7370	27700	0.9789	-	-
1.7433	27800	1.2898	-	-
1.7495	27900	0.9915	-	-
1.7558	28000	1.5349	1.0266	-
1.7621	28100	1.124	-	-
1.7684	28200	0.809	-	-
1.7746	28300	0.9617	-	-
1.7809	28400	1.3061	-	-
1.7872	28500	1.1323	1.0488	-
1.7934	28600	1.2991	-	-
1.7997	28700	0.8708	-	-
1.8060	28800	0.7493	-	-
1.8123	28900	1.004	-	-
1.8185	29000	1.1477	1.0206	-
1.8248	29100	1.1826	-	-
1.8311	29200	1.0961	-	-
1.8373	29300	1.4743	-	-
1.8436	29400	0.8413	-	-
1.8499	29500	1.2623	1.0047	-
1.8561	29600	0.8486	-	-
1.8624	29700	1.4481	-	-
1.8687	29800	1.2704	-	-
1.8750	29900	1.1913	-	-
1.8812	30000	0.9369	1.0277	-
1.8875	30100	1.2427	-	-
1.8938	30200	1.0576	-	-
1.9000	30300	0.9188	-	-
1.9063	30400	1.3227	-	-
1.9126	30500	1.4614	1.0550	-
1.9189	30600	1.2316	-	-
1.9251	30700	0.9487	-	-
1.9314	30800	1.1651	-	-
1.9377	30900	1.1622	-	-
1.9439	31000	1.1801	0.9981	-
1.9502	31100	0.8798	-	-
1.9565	31200	0.7196	-	-
1.9628	31300	1.2003	-	-
1.9690	31400	1.1823	-	-
1.9753	31500	1.1453	1.0320	-
1.9816	31600	1.4751	-	-
1.9878	31700	0.8502	-	-
1.9941	31800	0.8757	-	-
2.0004	31900	1.0489	-	-
2.0066	32000	1.4672	1.0571	-
2.0129	32100	0.9474	-	-
2.0192	32200	0.8037	-	-
2.0255	32300	0.9782	-	-
2.0317	32400	0.6943	-	-
2.0380	32500	1.0097	0.9797	-
2.0443	32600	0.9067	-	-
2.0505	32700	1.09	-	-
2.0568	32800	0.8464	-	-
2.0631	32900	0.9359	-	-
2.0694	33000	0.813	0.9907	-
2.0756	33100	0.8738	-	-
2.0819	33200	0.8178	-	-
2.0882	33300	1.1704	-	-
2.0944	33400	1.0073	-	-
2.1007	33500	1.1849	0.9582	-
2.1070	33600	0.7795	-	-
2.1133	33700	0.7688	-	-
2.1195	33800	0.9465	-	-
2.1258	33900	1.0883	-	-
2.1321	34000	0.7711	0.9557	-
2.1383	34100	0.9767	-	-
2.1446	34200	0.6702	-	-
2.1509	34300	0.9444	-	-
2.1571	34400	0.8741	-	-
2.1634	34500	1.0717	0.9526	-
2.1697	34600	0.8584	-	-
2.1760	34700	0.8926	-	-
2.1822	34800	0.8567	-	-
2.1885	34900	0.71	-	-
2.1948	35000	1.1285	0.9589	-
2.2010	35100	0.8999	-	-
2.2073	35200	0.8459	-	-
2.2136	35300	1.0608	-	-
2.2199	35400	0.6115	-	-
2.2261	35500	1.2468	0.9769	-
2.2324	35600	0.9987	-	-
2.2387	35700	0.9186	-	-
2.2449	35800	1.0505	-	-
2.2512	35900	0.6253	-	-
2.2575	36000	0.6523	0.9501	-
2.2637	36100	0.8252	-	-
2.2700	36200	0.9793	-	-
2.2763	36300	0.8845	-	-
2.2826	36400	1.0121	-	-
2.2888	36500	0.9849	0.9245	-
2.2951	36600	1.2937	-	-
2.3014	36700	1.0484	-	-
2.3076	36800	0.8801	-	-
2.3139	36900	0.7552	-	-
2.3202	37000	0.7641	0.9280	-
2.3265	37100	0.883	-	-
2.3327	37200	0.77	-	-
2.3390	37300	1.2699	-	-
2.3453	37400	0.8766	-	-
2.3515	37500	1.1154	0.9623	-
2.3578	37600	1.0634	-	-
2.3641	37700	0.8822	-	-
2.3704	37800	0.839	-	-
2.3766	37900	0.684	-	-
2.3829	38000	0.8051	0.9198	-
2.3892	38100	0.9585	-	-
2.3954	38200	0.7156	-	-
2.4017	38300	0.5271	-	-
2.4080	38400	0.805	-	-
2.4142	38500	0.7898	0.8785	-
2.4205	38600	0.6935	-	-
2.4268	38700	0.8011	-	-
2.4331	38800	0.9812	-	-
2.4393	38900	0.4427	-	-
2.4456	39000	0.492	0.9313	-
2.4519	39100	0.47	-	-
2.4581	39200	1.1876	-	-
2.4644	39300	0.5778	-	-
2.4707	39400	0.6763	-	-
2.4770	39500	0.6896	0.8978	-
2.4832	39600	0.8905	-	-
2.4895	39700	0.7845	-	-
2.4958	39800	0.8691	-	-
2.5020	39900	0.55	-	-
2.5083	40000	0.6978	0.9054	-
2.5146	40100	0.6378	-	-
2.5209	40200	0.895	-	-
2.5271	40300	0.9683	-	-
2.5334	40400	0.9373	-	-
2.5397	40500	0.7406	0.9128	-
2.5459	40600	0.8917	-	-
2.5522	40700	1.0552	-	-
2.5585	40800	0.5281	-	-
2.5647	40900	0.9064	-	-
2.5710	41000	0.6886	0.9049	-
2.5773	41100	0.7166	-	-
2.5836	41200	0.8343	-	-
2.5898	41300	0.9468	-	-
2.5961	41400	0.8529	-	-
2.6024	41500	0.8092	0.8954	-
2.6086	41600	0.8501	-	-
2.6149	41700	0.9877	-	-
2.6212	41800	0.8592	-	-
2.6275	41900	0.8632	-	-
2.6337	42000	0.6766	0.8707	-
2.6400	42100	0.7587	-	-
2.6463	42200	0.8949	-	-
2.6525	42300	0.4173	-	-
2.6588	42400	0.5995	-	-
2.6651	42500	0.8157	0.8681	-
2.6713	42600	0.92	-	-
2.6776	42700	0.9118	-	-
2.6839	42800	0.7446	-	-
2.6902	42900	0.6835	-	-
2.6964	43000	0.6157	0.8691	-
2.7027	43100	0.5423	-	-
2.7090	43200	0.8098	-	-
2.7152	43300	0.8908	-	-
2.7215	43400	1.1275	-	-
2.7278	43500	1.0345	0.8884	-
2.7341	43600	0.6198	-	-
2.7403	43700	0.8315	-	-
2.7466	43800	0.9317	-	-
2.7529	43900	0.516	-	-
2.7591	44000	0.8229	0.8659	-
2.7654	44100	0.7989	-	-
2.7717	44200	0.9291	-	-
2.7780	44300	0.5954	-	-
2.7842	44400	0.8537	-	-
2.7905	44500	0.9506	0.8657	-
2.7968	44600	0.5789	-	-
2.8030	44700	0.4861	-	-
2.8093	44800	0.9614	-	-
2.8156	44900	1.0069	-	-
2.8218	45000	0.5599	0.8619	-
2.8281	45100	1.3747	-	-
2.8344	45200	0.5638	-	-
2.8407	45300	1.2095	-	-
2.8469	45400	0.7364	-	-
2.8532	45500	0.5692	0.8818	-
2.8595	45600	0.8848	-	-
2.8657	45700	0.9063	-	-
2.8720	45800	0.8675	-	-
2.8783	45900	0.9703	-	-
2.8846	46000	0.6657	0.8424	-
2.8908	46100	0.6564	-	-
2.8971	46200	0.7945	-	-
2.9034	46300	0.6341	-	-
2.9096	46400	1.042	-	-
2.9159	46500	1.0812	0.8510	-
2.9222	46600	0.9787	-	-
2.9285	46700	0.8732	-	-
2.9347	46800	1.1872	-	-
2.9410	46900	0.989	-	-
2.9473	47000	0.874	0.8215	-
2.9535	47100	1.0229	-	-
2.9598	47200	0.9888	-	-
2.9661	47300	0.4883	-	-
2.9723	47400	0.7474	-	-
2.9786	47500	0.7615	0.8218	-
2.9849	47600	0.6208	-	-
2.9912	47700	0.8332	-	-
2.9974	47800	0.6734	-	-
3.0037	47900	0.5095	-	-
3.0100	48000	0.7709	0.8220	-
3.0162	48100	0.5449	-	-
3.0225	48200	0.772	-	-
3.0288	48300	0.8582	-	-
3.0351	48400	0.5742	-	-
3.0413	48500	0.5584	0.8493	-
3.0476	48600	0.9766	-	-
3.0539	48700	0.6473	-	-
3.0601	48800	0.5861	-	-
3.0664	48900	0.6377	-	-
3.0727	49000	0.8393	0.8430	-
3.0789	49100	0.8385	-	-
3.0852	49200	0.5523	-	-
3.0915	49300	0.6217	-	-
3.0978	49400	0.5515	-	-
3.1040	49500	0.851	0.8000	-
3.1103	49600	0.9247	-	-
3.1166	49700	0.655	-	-
3.1228	49800	0.4979	-	-
3.1291	49900	0.7521	-	-
3.1354	50000	0.53	0.8105	-
3.1417	50100	0.5943	-	-
3.1479	50200	0.4659	-	-
3.1542	50300	0.4843	-	-
3.1605	50400	0.7577	-	-
3.1667	50500	0.3448	0.8055	-
3.1730	50600	0.8392	-	-
3.1793	50700	0.75	-	-
3.1856	50800	0.5195	-	-
3.1918	50900	0.617	-	-
3.1981	51000	0.6892	0.8293	-
3.2044	51100	0.497	-	-
3.2106	51200	0.6793	-	-
3.2169	51300	0.7251	-	-
3.2232	51400	0.6471	-	-
3.2294	51500	0.775	0.8013	-
3.2357	51600	0.7289	-	-
3.2420	51700	0.6894	-	-
3.2483	51800	0.5677	-	-
3.2545	51900	0.317	-	-
3.2608	52000	0.5376	0.7853	-
3.2671	52100	0.4582	-	-
3.2733	52200	0.8505	-	-
3.2796	52300	0.6236	-	-
3.2859	52400	0.7388	-	-
3.2922	52500	0.7061	0.7863	-
3.2984	52600	0.5411	-	-
3.3047	52700	0.9511	-	-
3.3110	52800	0.5364	-	-
3.3172	52900	0.5795	-	-
3.3235	53000	0.5305	0.7876	-
3.3298	53100	0.8051	-	-
3.3361	53200	0.5342	-	-
3.3423	53300	0.4567	-	-
3.3486	53400	0.9751	-	-
3.3549	53500	0.4413	0.8008	-
3.3611	53600	0.6011	-	-
3.3674	53700	0.4708	-	-
3.3737	53800	0.6167	-	-
3.3799	53900	0.7653	-	-
3.3862	54000	0.7781	0.7897	-
3.3925	54100	0.9323	-	-
3.3988	54200	0.6003	-	-
3.4050	54300	0.5268	-	-
3.4113	54400	0.6639	-	-
3.4176	54500	0.388	0.7855	-
3.4238	54600	0.7258	-	-
3.4301	54700	0.6475	-	-
3.4364	54800	0.795	-	-
3.4427	54900	0.4978	-	-
3.4489	55000	0.6259	0.7705	-
3.4552	55100	0.791	-	-
3.4615	55200	0.7602	-	-
3.4677	55300	0.2236	-	-
3.4740	55400	0.5577	-	-
3.4803	55500	0.4214	0.7683	-
3.4865	55600	0.7335	-	-
3.4928	55700	0.7536	-	-
3.4991	55800	0.4577	-	-
3.5054	55900	0.5869	-	-
3.5116	56000	0.8563	0.7587	-
3.5179	56100	0.9291	-	-
3.5242	56200	0.4387	-	-
3.5304	56300	0.4491	-	-
3.5367	56400	0.506	-	-
3.5430	56500	0.6626	0.7634	-
3.5493	56600	0.8654	-	-
3.5555	56700	0.4455	-	-
3.5618	56800	0.4593	-	-
3.5681	56900	0.878	-	-
3.5743	57000	0.3737	0.7617	-
3.5806	57100	0.377	-	-
3.5869	57200	0.6894	-	-
3.5932	57300	0.6635	-	-
3.5994	57400	0.9224	-	-
3.6057	57500	0.635	0.7669	-
3.6120	57600	0.6797	-	-
3.6182	57700	0.9814	-	-
3.6245	57800	0.9893	-	-
3.6308	57900	0.6753	-	-
3.6370	58000	0.8349	0.7501	-
3.6433	58100	0.8523	-	-
3.6496	58200	0.2962	-	-
3.6559	58300	0.6585	-	-
3.6621	58400	1.0247	-	-
3.6684	58500	0.8638	0.7577	-
3.6747	58600	0.9456	-	-
3.6809	58700	0.5401	-	-
3.6872	58800	0.6602	-	-
3.6935	58900	0.7543	-	-
3.6998	59000	0.7893	0.7600	-
3.7060	59100	0.7746	-	-
3.7123	59200	0.6539	-	-
3.7186	59300	0.8083	-	-
3.7248	59400	0.3429	-	-
3.7311	59500	0.5005	0.7445	-
3.7374	59600	0.6238	-	-
3.7437	59700	0.4343	-	-
3.7499	59800	0.8189	-	-
3.7562	59900	0.6272	-	-
3.7625	60000	0.2982	0.7597	-
3.7687	60100	0.7028	-	-
3.7750	60200	0.9447	-	-
3.7813	60300	0.6175	-	-
3.7875	60400	0.5856	-	-
3.7938	60500	0.8249	0.7505	-
3.8001	60600	0.6617	-	-
3.8064	60700	0.5767	-	-
3.8126	60800	1.0094	-	-
3.8189	60900	0.471	-	-
3.8252	61000	0.6313	0.7489	-
3.8314	61100	0.6545	-	-
3.8377	61200	0.699	-	-
3.8440	61300	0.6272	-	-
3.8503	61400	0.7375	-	-
3.8565	61500	0.4213	0.7490	-
3.8628	61600	0.6631	-	-
3.8691	61700	0.552	-	-
3.8753	61800	0.7041	-	-
3.8816	61900	0.8457	-	-
3.8879	62000	0.8104	0.7477	-
3.8941	62100	0.4494	-	-
3.9004	62200	0.6947	-	-
3.9067	62300	0.8061	-	-
3.9130	62400	0.416	-	-
3.9192	62500	0.7359	0.7468	-
3.9255	62600	0.7408	-	-
3.9318	62700	0.6255	-	-
3.9380	62800	0.7865	-	-
3.9443	62900	0.4879	-	-
3.9506	63000	0.5196	0.7485	-
3.9569	63100	0.5683	-	-
3.9631	63200	0.5141	-	-
3.9694	63300	0.6068	-	-
3.9757	63400	0.5929	-	-
3.9819	63500	0.7513	0.7482	-
3.9882	63600	0.5053	-	-
3.9945	63700	0.5707	-	-

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},
}