metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:449904
  - loss:CosineSimilarityLoss
base_model: x2bee/ModernBERT-SimCSE-multitask_v03
widget:
  - source_sentence: 우리는 움직이는 동행 우주 정지 좌표계에 비례하여 이동하고 있습니다 ... 약 371km / s에서 별자리 leo 쪽으로. "
    sentences:
      - 두 마리의 독수리가 가지에 앉는다.
      - 다른 물체와는 관련이 없는 '정지'는 없다.
      - 소녀는 버스의 열린 문 앞에 서 있다.
  - source_sentence: 숲에는 개들이 있다.
    sentences:
      - 양을 보는 아이들.
      - 여왕의 배우자를 "왕"이라고 부르지 않는 것은 아주 좋은 이유가 있다. 왜냐하면 그들은 왕이 아니기 때문이다.
      - 개들은 숲속에 혼자 있다.
  - source_sentence: '첫째, 두 가지 다른 종류의 대시가 있다는 것을 알아야 합니다 : en 대시와 em 대시.'
    sentences:
      - 그들은 그 물건들을 집 주변에 두고 가거나 집의 정리를 해칠 의도가 없다.
      - 세미콜론은 혼자 있을 수 있는 문장에 참여하는데 사용되지만, 그들의 관계를 강조하기 위해 결합됩니다.
      - 그의 남동생이 지켜보는 동안 집 앞에서 트럼펫을 연주하는 금발의 아이.
  - source_sentence: 한 여성이 생선 껍질을 벗기고 있다.
    sentences:
      - 한 남자가 수영장으로 뛰어들었다.
      - 한 여성이 프라이팬에 노란 혼합물을 부어 넣고 있다.
      - 두 마리의 갈색 개가 눈 속에서 서로 놀고 있다.
  - source_sentence: 버스가 바쁜 길을 따라 운전한다.
    sentences:
      - 우리와 같은 태양계가 은하계 밖에서 존재할 수도 있을 것입니다.
      - 그 여자는 데이트하러 가는 중이다.
      - 녹색 버스가 도로를 따라 내려간다.
datasets:
  - x2bee/misc_sts_pairs_v2_kor_kosimcse
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_euclidean
  - spearman_euclidean
  - pearson_manhattan
  - spearman_manhattan
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
model-index:
  - name: SentenceTransformer based on x2bee/ModernBERT-SimCSE-multitask_v03
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts_dev
        metrics:
          - type: pearson_cosine
            value: 0.8319192467999278
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8396159085327265
            name: Spearman Cosine
          - type: pearson_euclidean
            value: 0.8198226408074469
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8285927601564604
            name: Spearman Euclidean
          - type: pearson_manhattan
            value: 0.8199114649719743
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8295556212626334
            name: Spearman Manhattan
          - type: pearson_dot
            value: 0.7234705763545461
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7094397491074207
            name: Spearman Dot
          - type: pearson_max
            value: 0.8319192467999278
            name: Pearson Max
          - type: spearman_max
            value: 0.8396159085327265
            name: Spearman Max

SentenceTransformer based on x2bee/ModernBERT-SimCSE-multitask_v03

This is a sentence-transformers model finetuned from x2bee/ModernBERT-SimCSE-multitask_v03 on the misc_sts_pairs_v2_kor_kosimcse dataset. It maps sentences & paragraphs to a 768-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: x2bee/ModernBERT-SimCSE-multitask_v03
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- misc_sts_pairs_v2_kor_kosimcse

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: ModernBertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("x2bee/ModernBERT-SimCSE-multitask_v03-beta")
# Run inference
sentences = [
    '버스가 바쁜 길을 따라 운전한다.',
    '녹색 버스가 도로를 따라 내려간다.',
    '그 여자는 데이트하러 가는 중이다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 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	0.8319
spearman_cosine	0.8396
pearson_euclidean	0.8198
spearman_euclidean	0.8286
pearson_manhattan	0.8199
spearman_manhattan	0.8296
pearson_dot	0.7235
spearman_dot	0.7094
pearson_max	0.8319
spearman_max	0.8396

Training Details

Training Dataset

misc_sts_pairs_v2_kor_kosimcse

Dataset: misc_sts_pairs_v2_kor_kosimcse at e747415
Size: 449,904 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 18.3 tokens
max: 69 tokens

min: 6 tokens
mean: 18.69 tokens
max: 66 tokens

min: 0.11
mean: 0.77
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 18.3 tokens max: 69 tokens	min: 6 tokens mean: 18.69 tokens max: 66 tokens	min: 0.11 mean: 0.77 max: 1.0

Samples:

sentence1	sentence2	score
`주홍글씨는 언제 출판되었습니까?`	`《주홍글씨》는 몇 년에 출판되었습니까?`	`0.8638778924942017`
`폴란드에서 빨간색과 흰색은 무엇을 의미합니까?`	`폴란드 국기의 색상은 무엇입니까?`	`0.6773715019226074`
`노르만인들은 방어를 위해 모트와 베일리 성을 어떻게 사용했는가?`	`11세기에는 어떻게 모트와 베일리 성을 만들었습니까?`	`0.7460665702819824`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Evaluation Dataset

Unnamed Dataset

Size: 1,500 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 7 tokens
mean: 20.38 tokens
max: 52 tokens

min: 6 tokens
mean: 20.52 tokens
max: 54 tokens

min: 0.0
mean: 0.42
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 7 tokens mean: 20.38 tokens max: 52 tokens	min: 6 tokens mean: 20.52 tokens max: 54 tokens	min: 0.0 mean: 0.42 max: 1.0

Samples:

sentence1	sentence2	score
`안전모를 가진 한 남자가 춤을 추고 있다.`	`안전모를 쓴 한 남자가 춤을 추고 있다.`	`1.0`
`어린아이가 말을 타고 있다.`	`아이가 말을 타고 있다.`	`0.95`
`한 남자가 뱀에게 쥐를 먹이고 있다.`	`남자가 뱀에게 쥐를 먹이고 있다.`	`1.0`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

overwrite_output_dir: True
eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 8
learning_rate: 8e-05
num_train_epochs: 2.0
warmup_ratio: 0.2
push_to_hub: True
hub_model_id: x2bee/ModernBERT-SimCSE-multitask_v03-beta
hub_strategy: checkpoint
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: True
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: 8
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 8e-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: 2.0
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.2
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: False
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: True
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: True
resume_from_checkpoint: None
hub_model_id: x2bee/ModernBERT-SimCSE-multitask_v03-beta
hub_strategy: checkpoint
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

Click to expand

Epoch	Step	Training Loss	Validation Loss	sts_dev_spearman_max
0.0028	10	0.0216	-	-
0.0057	20	0.0204	-	-
0.0085	30	0.0194	-	-
0.0114	40	0.0195	-	-
0.0142	50	0.0182	-	-
0.0171	60	0.0161	-	-
0.0199	70	0.015	-	-
0.0228	80	0.0153	-	-
0.0256	90	0.0137	-	-
0.0285	100	0.014	-	-
0.0313	110	0.0122	-	-
0.0341	120	0.0114	-	-
0.0370	130	0.0109	-	-
0.0398	140	0.0097	-	-
0.0427	150	0.0085	-	-
0.0455	160	0.0084	-	-
0.0484	170	0.0083	-	-
0.0512	180	0.0078	-	-
0.0541	190	0.008	-	-
0.0569	200	0.0073	-	-
0.0597	210	0.0079	-	-
0.0626	220	0.0073	-	-
0.0654	230	0.0079	-	-
0.0683	240	0.0068	-	-
0.0711	250	0.0068	0.0333	0.8229
0.0740	260	0.0073	-	-
0.0768	270	0.0077	-	-
0.0797	280	0.0067	-	-
0.0825	290	0.007	-	-
0.0854	300	0.0065	-	-
0.0882	310	0.0072	-	-
0.0910	320	0.0068	-	-
0.0939	330	0.0064	-	-
0.0967	340	0.0074	-	-
0.0996	350	0.0071	-	-
0.1024	360	0.0065	-	-
0.1053	370	0.0067	-	-
0.1081	380	0.0063	-	-
0.1110	390	0.0062	-	-
0.1138	400	0.0068	-	-
0.1166	410	0.0064	-	-
0.1195	420	0.0064	-	-
0.1223	430	0.0064	-	-
0.1252	440	0.0074	-	-
0.1280	450	0.0069	-	-
0.1309	460	0.0065	-	-
0.1337	470	0.0067	-	-
0.1366	480	0.0068	-	-
0.1394	490	0.0057	-	-
0.1423	500	0.0065	0.0343	0.8284
0.1451	510	0.0069	-	-
0.1479	520	0.0068	-	-
0.1508	530	0.0065	-	-
0.1536	540	0.0065	-	-
0.1565	550	0.0063	-	-
0.1593	560	0.0058	-	-
0.1622	570	0.0064	-	-
0.1650	580	0.0062	-	-
0.1679	590	0.0061	-	-
0.1707	600	0.0062	-	-
0.1735	610	0.0057	-	-
0.1764	620	0.0066	-	-
0.1792	630	0.0061	-	-
0.1821	640	0.0054	-	-
0.1849	650	0.0066	-	-
0.1878	660	0.0059	-	-
0.1906	670	0.0063	-	-
0.1935	680	0.0065	-	-
0.1963	690	0.0065	-	-
0.1992	700	0.0058	-	-
0.2020	710	0.006	-	-
0.2048	720	0.0062	-	-
0.2077	730	0.0058	-	-
0.2105	740	0.0058	-	-
0.2134	750	0.0056	0.0356	0.8302
0.2162	760	0.0067	-	-
0.2191	770	0.0063	-	-
0.2219	780	0.0063	-	-
0.2248	790	0.0063	-	-
0.2276	800	0.0056	-	-
0.2304	810	0.0058	-	-
0.2333	820	0.0053	-	-
0.2361	830	0.0057	-	-
0.2390	840	0.0055	-	-
0.2418	850	0.0054	-	-
0.2447	860	0.0065	-	-
0.2475	870	0.0054	-	-
0.2504	880	0.0051	-	-
0.2532	890	0.0057	-	-
0.2561	900	0.0056	-	-
0.2589	910	0.0055	-	-
0.2617	920	0.0051	-	-
0.2646	930	0.0055	-	-
0.2674	940	0.0059	-	-
0.2703	950	0.005	-	-
0.2731	960	0.0058	-	-
0.2760	970	0.005	-	-
0.2788	980	0.0055	-	-
0.2817	990	0.0054	-	-
0.2845	1000	0.0055	0.0360	0.8319
0.2874	1010	0.0059	-	-
0.2902	1020	0.0049	-	-
0.2930	1030	0.0052	-	-
0.2959	1040	0.0051	-	-
0.2987	1050	0.006	-	-
0.3016	1060	0.0048	-	-
0.3044	1070	0.0055	-	-
0.3073	1080	0.0052	-	-
0.3101	1090	0.0051	-	-
0.3130	1100	0.0051	-	-
0.3158	1110	0.005	-	-
0.3186	1120	0.0054	-	-
0.3215	1130	0.0051	-	-
0.3243	1140	0.0054	-	-
0.3272	1150	0.0056	-	-
0.3300	1160	0.0053	-	-
0.3329	1170	0.0052	-	-
0.3357	1180	0.0051	-	-
0.3386	1190	0.0051	-	-
0.3414	1200	0.0048	-	-
0.3443	1210	0.005	-	-
0.3471	1220	0.0055	-	-
0.3499	1230	0.0049	-	-
0.3528	1240	0.0053	-	-
0.3556	1250	0.0052	0.0364	0.8330
0.3585	1260	0.0051	-	-
0.3613	1270	0.005	-	-
0.3642	1280	0.005	-	-
0.3670	1290	0.0045	-	-
0.3699	1300	0.0055	-	-
0.3727	1310	0.0049	-	-
0.3755	1320	0.0049	-	-
0.3784	1330	0.0053	-	-
0.3812	1340	0.005	-	-
0.3841	1350	0.0048	-	-
0.3869	1360	0.0049	-	-
0.3898	1370	0.0046	-	-
0.3926	1380	0.0049	-	-
0.3955	1390	0.0052	-	-
0.3983	1400	0.005	-	-
0.4012	1410	0.0052	-	-
0.4040	1420	0.0052	-	-
0.4068	1430	0.0045	-	-
0.4097	1440	0.0046	-	-
0.4125	1450	0.0056	-	-
0.4154	1460	0.0056	-	-
0.4182	1470	0.005	-	-
0.4211	1480	0.0051	-	-
0.4239	1490	0.0049	-	-
0.4268	1500	0.0048	0.0374	0.8334
0.4296	1510	0.0053	-	-
0.4324	1520	0.0054	-	-
0.4353	1530	0.0048	-	-
0.4381	1540	0.005	-	-
0.4410	1550	0.0045	-	-
0.4438	1560	0.0046	-	-
0.4467	1570	0.0045	-	-
0.4495	1580	0.0049	-	-
0.4524	1590	0.0048	-	-
0.4552	1600	0.005	-	-
0.4581	1610	0.0045	-	-
0.4609	1620	0.0049	-	-
0.4637	1630	0.0044	-	-
0.4666	1640	0.0048	-	-
0.4694	1650	0.0049	-	-
0.4723	1660	0.0048	-	-
0.4751	1670	0.0051	-	-
0.4780	1680	0.0047	-	-
0.4808	1690	0.0048	-	-
0.4837	1700	0.0047	-	-
0.4865	1710	0.0044	-	-
0.4893	1720	0.0049	-	-
0.4922	1730	0.0049	-	-
0.4950	1740	0.0051	-	-
0.4979	1750	0.0043	0.0392	0.8352
0.5007	1760	0.0043	-	-
0.5036	1770	0.0045	-	-
0.5064	1780	0.0046	-	-
0.5093	1790	0.0042	-	-
0.5121	1800	0.0047	-	-
0.5150	1810	0.0047	-	-
0.5178	1820	0.0046	-	-
0.5206	1830	0.0044	-	-
0.5235	1840	0.0046	-	-
0.5263	1850	0.0047	-	-
0.5292	1860	0.0044	-	-
0.5320	1870	0.0047	-	-
0.5349	1880	0.0049	-	-
0.5377	1890	0.0049	-	-
0.5406	1900	0.0047	-	-
0.5434	1910	0.0045	-	-
0.5462	1920	0.0044	-	-
0.5491	1930	0.0048	-	-
0.5519	1940	0.0041	-	-
0.5548	1950	0.004	-	-
0.5576	1960	0.0048	-	-
0.5605	1970	0.0042	-	-
0.5633	1980	0.0048	-	-
0.5662	1990	0.0045	-	-
0.5690	2000	0.0043	0.0375	0.8359
0.5719	2010	0.005	-	-
0.5747	2020	0.0049	-	-
0.5775	2030	0.0044	-	-
0.5804	2040	0.0045	-	-
0.5832	2050	0.0043	-	-
0.5861	2060	0.0045	-	-
0.5889	2070	0.004	-	-
0.5918	2080	0.0042	-	-
0.5946	2090	0.0044	-	-
0.5975	2100	0.0043	-	-
0.6003	2110	0.0041	-	-
0.6032	2120	0.0046	-	-
0.6060	2130	0.0048	-	-
0.6088	2140	0.0048	-	-
0.6117	2150	0.0041	-	-
0.6145	2160	0.0044	-	-
0.6174	2170	0.0045	-	-
0.6202	2180	0.0044	-	-
0.6231	2190	0.0044	-	-
0.6259	2200	0.0046	-	-
0.6288	2210	0.0048	-	-
0.6316	2220	0.0045	-	-
0.6344	2230	0.004	-	-
0.6373	2240	0.0041	-	-
0.6401	2250	0.0044	0.0391	0.8369
0.6430	2260	0.0044	-	-
0.6458	2270	0.0045	-	-
0.6487	2280	0.0041	-	-
0.6515	2290	0.0042	-	-
0.6544	2300	0.0043	-	-
0.6572	2310	0.004	-	-
0.6601	2320	0.0042	-	-
0.6629	2330	0.0041	-	-
0.6657	2340	0.0045	-	-
0.6686	2350	0.0045	-	-
0.6714	2360	0.0042	-	-
0.6743	2370	0.0045	-	-
0.6771	2380	0.0044	-	-
0.6800	2390	0.0044	-	-
0.6828	2400	0.0041	-	-
0.6857	2410	0.0045	-	-
0.6885	2420	0.0046	-	-
0.6913	2430	0.0041	-	-
0.6942	2440	0.0048	-	-
0.6970	2450	0.0041	-	-
0.6999	2460	0.0043	-	-
0.7027	2470	0.0043	-	-
0.7056	2480	0.0037	-	-
0.7084	2490	0.0042	-	-
0.7113	2500	0.0043	0.0405	0.8365
0.7141	2510	0.0045	-	-
0.7170	2520	0.0044	-	-
0.7198	2530	0.0042	-	-
0.7226	2540	0.0042	-	-
0.7255	2550	0.0041	-	-
0.7283	2560	0.0042	-	-
0.7312	2570	0.0041	-	-
0.7340	2580	0.0042	-	-
0.7369	2590	0.0041	-	-
0.7397	2600	0.0047	-	-
0.7426	2610	0.0038	-	-
0.7454	2620	0.0041	-	-
0.7482	2630	0.0042	-	-
0.7511	2640	0.0042	-	-
0.7539	2650	0.0042	-	-
0.7568	2660	0.0041	-	-
0.7596	2670	0.0042	-	-
0.7625	2680	0.0044	-	-
0.7653	2690	0.0039	-	-
0.7682	2700	0.0037	-	-
0.7710	2710	0.0044	-	-
0.7739	2720	0.0043	-	-
0.7767	2730	0.0042	-	-
0.7795	2740	0.0041	-	-
0.7824	2750	0.0039	0.0387	0.8376
0.7852	2760	0.0047	-	-
0.7881	2770	0.004	-	-
0.7909	2780	0.0039	-	-
0.7938	2790	0.0039	-	-
0.7966	2800	0.0039	-	-
0.7995	2810	0.0039	-	-
0.8023	2820	0.0039	-	-
0.8051	2830	0.0041	-	-
0.8080	2840	0.0037	-	-
0.8108	2850	0.0044	-	-
0.8137	2860	0.0043	-	-
0.8165	2870	0.0041	-	-
0.8194	2880	0.0043	-	-
0.8222	2890	0.0039	-	-
0.8251	2900	0.0041	-	-
0.8279	2910	0.0044	-	-
0.8308	2920	0.004	-	-
0.8336	2930	0.0042	-	-
0.8364	2940	0.0039	-	-
0.8393	2950	0.004	-	-
0.8421	2960	0.0042	-	-
0.8450	2970	0.004	-	-
0.8478	2980	0.0039	-	-
0.8507	2990	0.0037	-	-
0.8535	3000	0.0039	0.0386	0.8386
0.8564	3010	0.0041	-	-
0.8592	3020	0.0043	-	-
0.8621	3030	0.0041	-	-
0.8649	3040	0.0041	-	-
0.8677	3050	0.0043	-	-
0.8706	3060	0.0042	-	-
0.8734	3070	0.0039	-	-
0.8763	3080	0.004	-	-
0.8791	3090	0.0039	-	-
0.8820	3100	0.0039	-	-
0.8848	3110	0.004	-	-
0.8877	3120	0.0039	-	-
0.8905	3130	0.0038	-	-
0.8933	3140	0.0036	-	-
0.8962	3150	0.0039	-	-
0.8990	3160	0.0039	-	-
0.9019	3170	0.0038	-	-
0.9047	3180	0.0039	-	-
0.9076	3190	0.0041	-	-
0.9104	3200	0.004	-	-
0.9133	3210	0.0041	-	-
0.9161	3220	0.0042	-	-
0.9190	3230	0.004	-	-
0.9218	3240	0.0041	-	-
0.9246	3250	0.0041	0.0420	0.8408
0.9275	3260	0.0041	-	-
0.9303	3270	0.004	-	-
0.9332	3280	0.0042	-	-
0.9360	3290	0.004	-	-
0.9389	3300	0.0037	-	-
0.9417	3310	0.0038	-	-
0.9446	3320	0.0039	-	-
0.9474	3330	0.004	-	-
0.9502	3340	0.0037	-	-
0.9531	3350	0.0038	-	-
0.9559	3360	0.0037	-	-
0.9588	3370	0.0042	-	-
0.9616	3380	0.0042	-	-
0.9645	3390	0.0042	-	-
0.9673	3400	0.0037	-	-
0.9702	3410	0.0038	-	-
0.9730	3420	0.0039	-	-
0.9759	3430	0.0038	-	-
0.9787	3440	0.0041	-	-
0.9815	3450	0.004	-	-
0.9844	3460	0.0039	-	-
0.9872	3470	0.0036	-	-
0.9901	3480	0.0037	-	-
0.9929	3490	0.0039	-	-
0.9958	3500	0.0036	0.0403	0.8396

Framework Versions

Python: 3.11.10
Sentence Transformers: 3.3.1
Transformers: 4.48.0.dev0
PyTorch: 2.5.1+cu121
Accelerate: 1.1.0
Datasets: 3.1.0
Tokenizers: 0.21.0

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",
}