README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:11664
  - loss:CosineSimilarityLoss
base_model: klue/roberta-base
widget:
  - source_sentence: Multi-Class, Multi-Label 중 BCE 가 좋은 task -> 이건 분명 멀티라벨이지.
    sentences:
      - 기본 경험
      - 면접 시작 인사
      - 좋아하는 아이돌
  - source_sentence: >-
      Loss Function 관련 실무 경험 -> [기본 경험] 확률 예측에서 MSE Loss, MAE Loss 써 봤어! 엄청 혼났다
      ㅠㅠ
    sentences:
      - Loss Function 예시
      - Multi-Label 에서 CE + Softmax 적용 문제점
      - 용어 질문
  - source_sentence: >-
      Loss Function 관련 실무 경험 -> [상세 경험] 필수적인 Loss Term 인 Cross-Entropy Loss 가
      빠졌더라! 그래서 그거 해결해서 성능 20% 개선했지!
    sentences:
      - LLM Fine-Tuning 의 PEFT
      - Loss Function 예시
      - 마지막 할 말
  - source_sentence: 거대 언어 모델 정의 -> 수백억 파라미터로 구성된 언어 모델!
    sentences:
      - BCE 가 좋은 task
      - LoRA 와 QLoRA 의 차이
      - 기본 경험
  - source_sentence: PEFT 방법 5가지 -> Adapter Layer 추가하는 거랑 음 그리고 PEFT! 그거 알지?
    sentences:
      - 머신러닝
      - LoRA 와 QLoRA 의 차이
      - 용어 질문
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on klue/roberta-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: valid evaluator
          type: valid_evaluator
        metrics:
          - type: pearson_cosine
            value: 0.9999519237820663
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.3303596809565949
            name: Spearman Cosine

SentenceTransformer based on klue/roberta-base

This is a sentence-transformers model finetuned from klue/roberta-base. 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: klue/roberta-base
• Maximum Sequence Length: 64 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

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': 64, 'do_lower_case': True}) with Transformer model: RobertaModel 
  (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})
)

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 = [
    'PEFT 방법 5가지 -> Adapter Layer 추가하는 거랑 음 그리고 PEFT! 그거 알지?',
    'LoRA 와 QLoRA 의 차이',
    '용어 질문',
]
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: valid_evaluator
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	1.0
spearman_cosine	0.3304

Training Details

Training Dataset

Unnamed Dataset

• Size: 11,664 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 7 tokens mean: 29.04 tokens max: 64 tokens	min: 3 tokens mean: 6.85 tokens max: 18 tokens	min: 0.0 mean: 0.03 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Loss Function 정의 -> 모델이 잘못 예측한 것에 대한 패널티를 수식으로 정의한 거 아니야? 맞지?	MSE Loss 설명	0.0
  인공지능, 머신러닝, 딥러닝 차이 -> 딥러닝은 신경망이라는 걸 이용해서 머신러닝을 하는 거지!	좋아하는 아이돌	0.0
  MSE Loss 설명 -> 각 데이터별로 오차를 구하고 그 제곱을 평균한 거야!	거대 언어 모델 정의	0.0

• Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 40
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• 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: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 40
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: 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}
• tp_size: 0
• 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
• 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
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss	valid_evaluator_spearman_cosine
0.1001	73	-	0.0133
0.2003	146	-	-0.0061
0.3004	219	-	0.0476
0.4005	292	-	0.1975
0.5007	365	-	0.2232
0.6008	438	-	0.2484
0.6859	500	0.0952	-
0.7010	511	-	0.2631
0.8011	584	-	0.2481
0.9012	657	-	0.2594
1.0	729	-	0.2798
1.0014	730	-	0.2792
1.1015	803	-	0.2875
1.2016	876	-	0.2941
1.3018	949	-	0.2897
1.3717	1000	0.0285	-
1.4019	1022	-	0.3089
1.5021	1095	-	0.3130
1.6022	1168	-	0.3121
1.7023	1241	-	0.3170
1.8025	1314	-	0.2639
1.9026	1387	-	0.3031
2.0	1458	-	0.3203
2.0027	1460	-	0.3200
2.0576	1500	0.0215	-
2.1029	1533	-	0.3205
2.2030	1606	-	0.3180
2.3032	1679	-	0.3009
2.4033	1752	-	0.2967
2.5034	1825	-	0.3215
2.6036	1898	-	0.3187
2.7037	1971	-	0.3230
2.7435	2000	0.0141	-
2.8038	2044	-	0.3216
2.9040	2117	-	0.3152
3.0	2187	-	0.3206
3.0041	2190	-	0.3202
3.1043	2263	-	0.3272
3.2044	2336	-	0.3270
3.3045	2409	-	0.3251
3.4047	2482	-	0.3291
3.4294	2500	0.0105	-
3.5048	2555	-	0.3267
3.6049	2628	-	0.3214
3.7051	2701	-	0.3275
3.8052	2774	-	0.3275
3.9053	2847	-	0.3295
4.0	2916	-	0.3288
4.0055	2920	-	0.3296
4.1056	2993	-	0.3293
4.1152	3000	0.0078	-
4.2058	3066	-	0.3280
4.3059	3139	-	0.3117
4.4060	3212	-	0.3250
4.5062	3285	-	0.3212
4.6063	3358	-	0.3277
4.7064	3431	-	0.3208
4.8011	3500	0.0033	-
4.8066	3504	-	0.3177
4.9067	3577	-	0.3260
5.0	3645	-	0.3246
5.0069	3650	-	0.3259
5.1070	3723	-	0.3298
5.2071	3796	-	0.3199
5.3073	3869	-	0.3297
5.4074	3942	-	0.3256
5.4870	4000	0.0035	-
5.5075	4015	-	0.3286
5.6077	4088	-	0.3251
5.7078	4161	-	0.3269
5.8080	4234	-	0.3298
5.9081	4307	-	0.3265
6.0	4374	-	0.3047
6.0082	4380	-	0.3181
6.1084	4453	-	0.3301
6.1728	4500	0.0023	-
6.2085	4526	-	0.3301
6.3086	4599	-	0.3296
6.4088	4672	-	0.3251
6.5089	4745	-	0.3291
6.6091	4818	-	0.3295
6.7092	4891	-	0.3289
6.8093	4964	-	0.3254
6.8587	5000	0.0011	-
6.9095	5037	-	0.3271
7.0	5103	-	0.3300
7.0096	5110	-	0.3300
7.1097	5183	-	0.3287
7.2099	5256	-	0.3285
7.3100	5329	-	0.3291
7.4102	5402	-	0.3289
7.5103	5475	-	0.3246
7.5446	5500	0.0008	-
7.6104	5548	-	0.3283
7.7106	5621	-	0.3287
7.8107	5694	-	0.3243
7.9108	5767	-	0.3297
8.0	5832	-	0.3278
8.0110	5840	-	0.3280
8.1111	5913	-	0.3289
8.2112	5986	-	0.3250
8.2305	6000	0.0014	-
8.3114	6059	-	0.3225
8.4115	6132	-	0.3290
8.5117	6205	-	0.3260
8.6118	6278	-	0.3248
8.7119	6351	-	0.3285
8.8121	6424	-	0.3163
8.9122	6497	-	0.3295
8.9163	6500	0.0029	-
9.0	6561	-	0.3299
9.0123	6570	-	0.3299
9.1125	6643	-	0.3283
9.2126	6716	-	0.3115
9.3128	6789	-	0.3150
9.4129	6862	-	0.3281
9.5130	6935	-	0.3279
9.6022	7000	0.0021	-
9.6132	7008	-	0.3279
9.7133	7081	-	0.3285
9.8134	7154	-	0.3263
9.9136	7227	-	0.3301
10.0	7290	-	0.3291
10.0137	7300	-	0.3286
10.1139	7373	-	0.3271
10.2140	7446	-	0.3292
10.2881	7500	0.0022	-
10.3141	7519	-	0.3302
10.4143	7592	-	0.3026
10.5144	7665	-	0.3007
10.6145	7738	-	0.3099
10.7147	7811	-	0.3301
10.8148	7884	-	0.3247
10.9150	7957	-	0.3287
10.9739	8000	0.0027	-
11.0	8019	-	0.3289
11.0151	8030	-	0.3289
11.1152	8103	-	0.3297
11.2154	8176	-	0.3303
11.3155	8249	-	0.3299
11.4156	8322	-	0.3301
11.5158	8395	-	0.3292
11.6159	8468	-	0.3295
11.6598	8500	0.0008	-
11.7160	8541	-	0.3286
11.8162	8614	-	0.3283
11.9163	8687	-	0.3303
12.0	8748	-	0.3302
12.0165	8760	-	0.3301
12.1166	8833	-	0.3302
12.2167	8906	-	0.3301
12.3169	8979	-	0.3300
12.3457	9000	0.0008	-
12.4170	9052	-	0.3301
12.5171	9125	-	0.3301
12.6173	9198	-	0.3299
12.7174	9271	-	0.3296
12.8176	9344	-	0.3297
12.9177	9417	-	0.3304
13.0	9477	-	0.3301
13.0178	9490	-	0.3301
13.0316	9500	0.0003	-
13.1180	9563	-	0.3301
13.2181	9636	-	0.3302
13.3182	9709	-	0.3301
13.4184	9782	-	0.3302
13.5185	9855	-	0.3303
13.6187	9928	-	0.3303
13.7174	10000	0.0003	-
13.7188	10001	-	0.3302
13.8189	10074	-	0.3302
13.9191	10147	-	0.3302
14.0	10206	-	0.3295
14.0192	10220	-	0.3297
14.1193	10293	-	0.3296
14.2195	10366	-	0.3302
14.3196	10439	-	0.3190
14.4033	10500	0.0013	-
14.4198	10512	-	0.3301
14.5199	10585	-	0.3281
14.6200	10658	-	0.3297
14.7202	10731	-	0.3288
14.8203	10804	-	0.3291
14.9204	10877	-	0.3294
15.0	10935	-	0.3303
15.0206	10950	-	0.3303
15.0892	11000	0.0013	-
15.1207	11023	-	0.3303
15.2209	11096	-	0.3304
15.3210	11169	-	0.3304
15.4211	11242	-	0.3304
15.5213	11315	-	0.3304
15.6214	11388	-	0.3304
15.7215	11461	-	0.3304
15.7750	11500	0.0006	-
15.8217	11534	-	0.3304
15.9218	11607	-	0.3304
16.0	11664	-	0.3304
16.0219	11680	-	0.3304
16.1221	11753	-	0.3304
16.2222	11826	-	0.3304
16.3224	11899	-	0.3304
16.4225	11972	-	0.3304
16.4609	12000	0.0001	-
16.5226	12045	-	0.3304
16.6228	12118	-	0.3304
16.7229	12191	-	0.3304
16.8230	12264	-	0.3304
16.9232	12337	-	0.3304
17.0	12393	-	0.3304
17.0233	12410	-	0.3304
17.1235	12483	-	0.3304
17.1468	12500	0.0001	-
17.2236	12556	-	0.3304
17.3237	12629	-	0.3304
17.4239	12702	-	0.3304
17.5240	12775	-	0.3304
17.6241	12848	-	0.3304
17.7243	12921	-	0.3304
17.8244	12994	-	0.3304
17.8326	13000	0.0001	-
17.9246	13067	-	0.3304
18.0	13122	-	0.3304
18.0247	13140	-	0.3304
18.1248	13213	-	0.3304
18.2250	13286	-	0.3304
18.3251	13359	-	0.3304
18.4252	13432	-	0.3304
18.5185	13500	0.0001	-
18.5254	13505	-	0.3304
18.6255	13578	-	0.3304
18.7257	13651	-	0.3304
18.8258	13724	-	0.3304
18.9259	13797	-	0.3304
19.0	13851	-	0.3304
19.0261	13870	-	0.3304
19.1262	13943	-	0.3304
19.2044	14000	0.0001	-
19.2263	14016	-	0.3304
19.3265	14089	-	0.3304
19.4266	14162	-	0.3304
19.5267	14235	-	0.3304
19.6269	14308	-	0.3304
19.7270	14381	-	0.3304
19.8272	14454	-	0.3304
19.8903	14500	0.0001	-
19.9273	14527	-	0.3304
20.0	14580	-	0.3304
20.0274	14600	-	0.3304
20.1276	14673	-	0.3304
20.2277	14746	-	0.3304
20.3278	14819	-	0.3304
20.4280	14892	-	0.3304
20.5281	14965	-	0.3304
20.5761	15000	0.0001	-
20.6283	15038	-	0.3304
20.7284	15111	-	0.3304
20.8285	15184	-	0.3304
20.9287	15257	-	0.3304
21.0	15309	-	0.3304
21.0288	15330	-	0.3304
21.1289	15403	-	0.3304
21.2291	15476	-	0.3304
21.2620	15500	0.0001	-
21.3292	15549	-	0.3304
21.4294	15622	-	0.3304
21.5295	15695	-	0.3304
21.6296	15768	-	0.3304
21.7298	15841	-	0.3304
21.8299	15914	-	0.3304
21.9300	15987	-	0.3304
21.9479	16000	0.0001	-
22.0	16038	-	0.3304
22.0302	16060	-	0.3304
22.1303	16133	-	0.3304
22.2305	16206	-	0.3304
22.3306	16279	-	0.3304
22.4307	16352	-	0.3304
22.5309	16425	-	0.3304
22.6310	16498	-	0.3304
22.6337	16500	0.0001	-
22.7311	16571	-	0.3304
22.8313	16644	-	0.3304
22.9314	16717	-	0.3304
23.0	16767	-	0.3304
23.0316	16790	-	0.3304
23.1317	16863	-	0.3304
23.2318	16936	-	0.3304
23.3196	17000	0.0001	-
23.3320	17009	-	0.3304
23.4321	17082	-	0.3304
23.5322	17155	-	0.3304
23.6324	17228	-	0.3304
23.7325	17301	-	0.3304
23.8326	17374	-	0.3304
23.9328	17447	-	0.3304
24.0	17496	-	0.3304
24.0055	17500	0.0001	-
24.0329	17520	-	0.3304
24.1331	17593	-	0.3304
24.2332	17666	-	0.3304
24.3333	17739	-	0.3304
24.4335	17812	-	0.3304
24.5336	17885	-	0.3304
24.6337	17958	-	0.3304
24.6914	18000	0.0001	-
24.7339	18031	-	0.3304
24.8340	18104	-	0.3304
24.9342	18177	-	0.3304
25.0	18225	-	0.3304
25.0343	18250	-	0.3304
25.1344	18323	-	0.3299
25.2346	18396	-	0.3266
25.3347	18469	-	0.3304
25.3772	18500	0.0014	-
25.4348	18542	-	0.3304
25.5350	18615	-	0.3304
25.6351	18688	-	0.3304
25.7353	18761	-	0.3304
25.8354	18834	-	0.3304
25.9355	18907	-	0.3304
26.0	18954	-	0.3304
26.0357	18980	-	0.3304
26.0631	19000	0.0003	-
26.1358	19053	-	0.3303
26.2359	19126	-	0.3303
26.3361	19199	-	0.3304
26.4362	19272	-	0.3303
26.5364	19345	-	0.3303
26.6365	19418	-	0.3303
26.7366	19491	-	0.3304
26.7490	19500	0.0006	-
26.8368	19564	-	0.3304
26.9369	19637	-	0.3304
27.0	19683	-	0.3304
27.0370	19710	-	0.3304
27.1372	19783	-	0.3304
27.2373	19856	-	0.3304
27.3374	19929	-	0.3304
27.4348	20000	0.0001	-
27.4376	20002	-	0.3304
27.5377	20075	-	0.3304
27.6379	20148	-	0.3304
27.7380	20221	-	0.3304
27.8381	20294	-	0.3303
27.9383	20367	-	0.3303
28.0	20412	-	0.3303
28.0384	20440	-	0.3303
28.1207	20500	0.0001	-
28.1385	20513	-	0.3303
28.2387	20586	-	0.3303
28.3388	20659	-	0.3303
28.4390	20732	-	0.3303
28.5391	20805	-	0.3303
28.6392	20878	-	0.3303
28.7394	20951	-	0.3303
28.8066	21000	0.0001	-
28.8395	21024	-	0.3303
28.9396	21097	-	0.3303
29.0	21141	-	0.3303
29.0398	21170	-	0.3303
29.1399	21243	-	0.3303
29.2401	21316	-	0.3303
29.3402	21389	-	0.3303
29.4403	21462	-	0.3303
29.4925	21500	0.0001	-
29.5405	21535	-	0.3303
29.6406	21608	-	0.3303
29.7407	21681	-	0.3303
29.8409	21754	-	0.3303
29.9410	21827	-	0.3303
30.0	21870	-	0.3303
30.0412	21900	-	0.3303
30.1413	21973	-	0.3303
30.1783	22000	0.0001	-
30.2414	22046	-	0.3303
30.3416	22119	-	0.3303
30.4417	22192	-	0.3303
30.5418	22265	-	0.3303
30.6420	22338	-	0.3303
30.7421	22411	-	0.3303
30.8422	22484	-	0.3303
30.8642	22500	0.0001	-
30.9424	22557	-	0.3304
31.0	22599	-	0.3304
31.0425	22630	-	0.3304
31.1427	22703	-	0.3304
31.2428	22776	-	0.3304
31.3429	22849	-	0.3304
31.4431	22922	-	0.3304
31.5432	22995	-	0.3304
31.5501	23000	0.0001	-
31.6433	23068	-	0.3304
31.7435	23141	-	0.3304
31.8436	23214	-	0.3304
31.9438	23287	-	0.3304
32.0	23328	-	0.3304
32.0439	23360	-	0.3304
32.1440	23433	-	0.3304
32.2359	23500	0.0001	-
32.2442	23506	-	0.3304
32.3443	23579	-	0.3304
32.4444	23652	-	0.3304
32.5446	23725	-	0.3304
32.6447	23798	-	0.3304
32.7449	23871	-	0.3304
32.8450	23944	-	0.3304
32.9218	24000	0.0001	-
32.9451	24017	-	0.3304
33.0	24057	-	0.3304
33.0453	24090	-	0.3304
33.1454	24163	-	0.3304
33.2455	24236	-	0.3304
33.3457	24309	-	0.3304
33.4458	24382	-	0.3304
33.5460	24455	-	0.3304
33.6077	24500	0.0	-
33.6461	24528	-	0.3304
33.7462	24601	-	0.3304
33.8464	24674	-	0.3304
33.9465	24747	-	0.3304
34.0	24786	-	0.3304
34.0466	24820	-	0.3304
34.1468	24893	-	0.3304
34.2469	24966	-	0.3304
34.2936	25000	0.0	-
34.3471	25039	-	0.3304
34.4472	25112	-	0.3304
34.5473	25185	-	0.3304
34.6475	25258	-	0.3304
34.7476	25331	-	0.3304
34.8477	25404	-	0.3304
34.9479	25477	-	0.3304
34.9794	25500	0.0	-
35.0	25515	-	0.3304
35.0480	25550	-	0.3304
35.1481	25623	-	0.3304
35.2483	25696	-	0.3304
35.3484	25769	-	0.3304
35.4486	25842	-	0.3304
35.5487	25915	-	0.3304
35.6488	25988	-	0.3304
35.6653	26000	0.0	-
35.7490	26061	-	0.3304
35.8491	26134	-	0.3304
35.9492	26207	-	0.3304
36.0	26244	-	0.3304
36.0494	26280	-	0.3304
36.1495	26353	-	0.3304
36.2497	26426	-	0.3304
36.3498	26499	-	0.3304
36.3512	26500	0.0	-
36.4499	26572	-	0.3304
36.5501	26645	-	0.3304
36.6502	26718	-	0.3304
36.7503	26791	-	0.3304
36.8505	26864	-	0.3304
36.9506	26937	-	0.3304
37.0	26973	-	0.3304
37.0370	27000	0.0	-
37.0508	27010	-	0.3304
37.1509	27083	-	0.3304
37.2510	27156	-	0.3304
37.3512	27229	-	0.3304
37.4513	27302	-	0.3304
37.5514	27375	-	0.3304
37.6516	27448	-	0.3304
37.7229	27500	0.0	-
37.7517	27521	-	0.3304
37.8519	27594	-	0.3304
37.9520	27667	-	0.3304
38.0	27702	-	0.3304
38.0521	27740	-	0.3304
38.1523	27813	-	0.3304
38.2524	27886	-	0.3304
38.3525	27959	-	0.3304
38.4088	28000	0.0	-
38.4527	28032	-	0.3304
38.5528	28105	-	0.3304
38.6529	28178	-	0.3304
38.7531	28251	-	0.3304
38.8532	28324	-	0.3304
38.9534	28397	-	0.3304
39.0	28431	-	0.3304
39.0535	28470	-	0.3304
39.0947	28500	0.0	-
39.1536	28543	-	0.3304
39.2538	28616	-	0.3304
39.3539	28689	-	0.3304
39.4540	28762	-	0.3304
39.5542	28835	-	0.3304

Framework Versions

• Python: 3.10.11
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.0.1
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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",
}