whybe-choi/Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.7

Qwen3-VL-Embedding-2B model trained on Korean Visual Document Retrieval query-document screenshot pairs

This is a sentence-transformers model finetuned from Qwen/Qwen3-VL-Embedding-2B on the whybe-choi/ko-vdr-hn and whybe-choi/en-vdr-hn datasets. It maps sentences & paragraphs to a 2048-dimensional dense vector space and can be used for retrieval.

The evaluation results reported in this README were obtained using sentence-transformers with max_pixels = 1280 * 32 * 32. The following results were evaluated using MTEB with max_pixels = 1800 * 32 * 32.

KoViDoRe v2 (NDCG@10)

Model	Cybersecurity	Energy	HR	Economic	Average
Qwen/Qwen3-VL-Embedding-2B	0.6111	0.4123	0.1842	0.1592	0.3417
Qwen/Qwen3-VL-Embedding-8B	0.7809	0.6360	0.3613	0.2373	0.5039
Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.7 (ours)	0.7444	0.6506	0.5002	0.2797	0.5437

SDS KoPub-VDR (NDCG@10)

Model	Average
Qwen/Qwen3-VL-Embedding-2B	0.4285
Qwen/Qwen3-VL-Embedding-8B	0.7293
Qwen3-VL-Embedding-2B-ko-vdr-preview-v0.7 (ours)	0.7214

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Qwen/Qwen3-VL-Embedding-2B
• Maximum Sequence Length: 262144 tokens
• Output Dimensionality: 2048 dimensions
• Similarity Function: Cosine Similarity
• Supported Modalities: Text, Image, Video, Message
• Training Datasets:
  • whybe-choi/ko-vdr-hn
  • whybe-choi/en-vdr-hn
• Language: ko
• 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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'image': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'video': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'message': {'method': 'forward', 'method_output_name': 'last_hidden_state', 'format': 'structured'}}, 'module_output_name': 'token_embeddings', 'processing_kwargs': {'chat_template': {'add_generation_prompt': True}}, 'unpad_inputs': False, 'architecture': 'Qwen3VLModel'})
  (1): Pooling({'embedding_dimension': 2048, 'pooling_mode': 'lasttoken', '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 = [
    '공공 부문 비중 감소 비율과 시니어클럽 종사자 수 증가 비율을 비교하라.',
    'data/images/ko/ko-vdr-public/710.png',
    'data/images/ko/ko-vdr-public/6429.png',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 2048]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4656, 0.1822],
#         [0.4656, 1.0000, 0.0852],
#         [0.1822, 0.0852, 1.0000]])

Evaluation

Metrics

Information Retrieval

• Datasets: kovidore-v2-cybersecurity-beir-eval, kovidore-v2-hr-beir-eval, kovidore-v2-energy-beir-eval and kovidore-v2-economic-beir-eval
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "query_prompt": "Find a document image that matches the given query.",
      "corpus_prompt": "Represent the user's input."
  }
  

Metric	kovidore-v2-cybersecurity-beir-eval	kovidore-v2-hr-beir-eval	kovidore-v2-energy-beir-eval	kovidore-v2-economic-beir-eval
cosine_accuracy@1	0.7315	0.4389	0.6358	0.2515
cosine_accuracy@3	0.9195	0.6833	0.8555	0.4724
cosine_accuracy@5	0.9463	0.7783	0.8786	0.5767
cosine_accuracy@10	0.9732	0.8914	0.9422	0.6748
cosine_precision@1	0.7315	0.4389	0.6358	0.2515
cosine_precision@3	0.472	0.3469	0.4624	0.1718
cosine_precision@5	0.349	0.267	0.3422	0.1325
cosine_precision@10	0.2081	0.1833	0.2087	0.0877
cosine_recall@1	0.3632	0.1541	0.2474	0.106
cosine_recall@3	0.603	0.3363	0.5101	0.2252
cosine_recall@5	0.7138	0.4265	0.6043	0.2931
cosine_recall@10	0.8151	0.5806	0.7204	0.3826
cosine_ndcg@5	0.6927	0.4159	0.5931	0.2578
cosine_ndcg@10	0.7394	0.4821	0.6448	0.2952
cosine_mrr@10	0.8281	0.5845	0.7472	0.3845
cosine_map@100	0.6612	0.3995	0.568	0.2311

Training Details

Training Datasets

whybe-choi/ko-vdr-hn

• Dataset: whybe-choi/ko-vdr-hn at 74a01af
• Size: 406,945 training samples
• Columns: anchor, positive, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, and negative_7
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7
  type	string	string	string	string	string	string	string	string	string
  details	min: 36 tokens mean: 66.87 tokens max: 118 tokens	min: 1240 tokens mean: 1272.48 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.4 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.51 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.28 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.3 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.69 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.49 tokens max: 1298 tokens	min: 1240 tokens mean: 1272.36 tokens max: 1298 tokens

• Samples:

  anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7
  30인 이상 상용근로자를 보유한 기업의 1인당 평균 월별 법정외 복지비용이 10~29인 규모 기업보다 높은지 판단해 주세요.	data/images/ko/ko-vdr-public/3818.png	data/images/ko/ko-vdr-public/3763.png	data/images/ko/ko-vdr-public/7798.png	data/images/ko/ko-vdr-public/3752.png	data/images/ko/ko-vdr-public/3770.png	data/images/ko/ko-vdr-public/3773.png	data/images/ko/ko-vdr-public/7805.png	data/images/ko/ko-vdr-public/3785.png
  CAP 기반 조정이 Jensen‑Shannon 발산을 활용한 분포 유사성 검증에 어떤 영향을 미치는가?	data/images/ko/ko-vdr-public/3950.png	data/images/ko/ko-vdr-public/3934.png	data/images/ko/ko-vdr-public/5252.png	data/images/ko/ko-vdr-public/3959.png	data/images/ko/ko-vdr-public/5096.png	data/images/ko/ko-vdr-public/3960.png	data/images/ko/ko-vdr-public/5196.png	data/images/ko/ko-vdr-public/891.png
  소상공인 음식점업 체감경기 회복세가 온라인 음식서비스 성장률 확대와 소매판매액 내 비내구재 성장세 강화에 기여했는가?	data/images/ko/ko-vdr-public/6891.png	data/images/ko/ko-vdr-public/6886.png	data/images/ko/ko-vdr-public/6919.png	data/images/ko/ko-vdr-public/6883.png	data/images/ko/ko-vdr-public/6948.png	data/images/ko/ko-vdr-public/6882.png	data/images/ko/ko-vdr-public/6915.png	data/images/ko/ko-vdr-public/6921.png

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "SelfGuideCachedMultipleNegativesRankingLoss",
      "matryoshka_dims": [
          2048,
          1024,
          768,
          512,
          256,
          128
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

whybe-choi/en-vdr-hn

• Dataset: whybe-choi/en-vdr-hn at c8c903e
• Size: 301,784 training samples
• Columns: anchor, positive, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, and negative_7
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7
  type	string	string	string	string	string	string	string	string	string
  details	min: 26 tokens mean: 37.72 tokens max: 75 tokens	min: 246 tokens mean: 1215.73 tokens max: 1302 tokens	min: 126 tokens mean: 1199.3 tokens max: 1302 tokens	min: 174 tokens mean: 1205.24 tokens max: 1302 tokens	min: 118 tokens mean: 1205.7 tokens max: 1302 tokens	min: 126 tokens mean: 1210.24 tokens max: 1302 tokens	min: 134 tokens mean: 1209.33 tokens max: 1302 tokens	min: 100 tokens mean: 1211.77 tokens max: 1302 tokens	min: 70 tokens mean: 1191.3 tokens max: 1302 tokens

• Samples:

  anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7
  What is the primary purpose of the PTC in lithium batteries?	data/images/en/colpali/23d41ee76deaf320b9b7556c965caf7e.jpg	data/images/en/colpali/5a713f00d599b2bfddd115a67808de66.jpg	data/images/en/colpali/59c8e47f68536ba395df914e39029cec.jpg	data/images/en/colpali/73d6ab0da1b8290e6b5b1ed67a4a6885.jpg	data/images/en/colpali/dd1cd6682696b6ad9bdaa6da18da3a84.jpg	data/images/en/colpali/842382d0ea0cff88578e96904e652c6c.jpg	data/images/en/colpali/dd1ce2f3a4e7df95e98ef2cde8e4e7f1.jpg	data/images/en/colpali/719e704bce4e95da3e177a3b5db2dc2b.jpg
  How is the baseline CO2 emissions calculated for affected EGUs in the low load natural gas-fired or oil-fired subcategories?	data/images/en/colpali/bfd3dd15e306b6ed4ce26cef3956fa95.jpg	data/images/en/colpali/aaaa2c2811f72ac8ec402726c6578b13.jpg	data/images/en/colpali/1a570a15beb0d27a505db8a4634448a6.jpg	data/images/en/colpali/6a50944dae78a15c400dacfe9f2a9145.jpg	data/images/en/colpali/997f4d2e956f5ea37c8b174f43585f3d.jpg	data/images/en/colpali/3290c06c7e864b4e2e1c4cbd86592de2.jpg	data/images/en/colpali/dc09dbce746b4df935a6ff623471e839.jpg	data/images/en/colpali/00039af9d06cf667e28455ea3d33d4e2.jpg
  What are some suggestions Liberty Medical Group should consider to improve their accounts receivable turnover and days sales in receivables ratios?	data/images/en/colpali/09232c2534e9bcca51ef284a6153a974.jpg	data/images/en/colpali/e07a0cd87bd36ea9bedd44b48061e86a.jpg	data/images/en/colpali/56cc228953990c3d5b84ff67fb141872.jpg	data/images/en/colpali/b1eb0643c43238e35329bd2ec03ace8d.jpg	data/images/en/colpali/c19a0b262d75dd5790f1ac26aa0bd836.jpg	data/images/en/colpali/aa22a1ee2f4565656969fde81c7280c2.jpg	data/images/en/colpali/ab749e1287df0e66b7b2092eb4d20fc1.jpg	data/images/en/colpali/8d7b8a908e0d11d58c3d39146831a1f5.jpg

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "SelfGuideCachedMultipleNegativesRankingLoss",
      "matryoshka_dims": [
          2048,
          1024,
          768,
          512,
          256,
          128
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 128
• num_train_epochs: 1.0
• learning_rate: 2e-05
• lr_scheduler_type: cosine
• warmup_steps: 0.1
• gradient_accumulation_steps: 2
• bf16: True
• per_device_eval_batch_size: 128
• eval_on_start: True
• ddp_find_unused_parameters: True
• prompts: {'whybe-choi/ko-vdr-hn': {'anchor': 'Find a document image that matches the given query.', 'positive': "Represent the user's input.", 'negative_1': "Represent the user's input.", 'negative_2': "Represent the user's input.", 'negative_3': "Represent the user's input.", 'negative_4': "Represent the user's input.", 'negative_5': "Represent the user's input.", 'negative_6': "Represent the user's input.", 'negative_7': "Represent the user's input."}, 'whybe-choi/en-vdr-hn': {'anchor': 'Find a document image that matches the given query.', 'positive': "Represent the user's input.", 'negative_1': "Represent the user's input.", 'negative_2': "Represent the user's input.", 'negative_3': "Represent the user's input.", 'negative_4': "Represent the user's input.", 'negative_5': "Represent the user's input.", 'negative_6': "Represent the user's input.", 'negative_7': "Represent the user's input."}}
• batch_sampler: no_duplicates_hashed

All Hyperparameters

Click to expand

• per_device_train_batch_size: 128
• num_train_epochs: 1.0
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: cosine
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 2
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: trackio
• per_device_eval_batch_size: 128
• prediction_loss_only: True
• eval_on_start: True
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: True
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: True
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: {'whybe-choi/ko-vdr-hn': {'anchor': 'Find a document image that matches the given query.', 'positive': "Represent the user's input.", 'negative_1': "Represent the user's input.", 'negative_2': "Represent the user's input.", 'negative_3': "Represent the user's input.", 'negative_4': "Represent the user's input.", 'negative_5': "Represent the user's input.", 'negative_6': "Represent the user's input.", 'negative_7': "Represent the user's input."}, 'whybe-choi/en-vdr-hn': {'anchor': 'Find a document image that matches the given query.', 'positive': "Represent the user's input.", 'negative_1': "Represent the user's input.", 'negative_2': "Represent the user's input.", 'negative_3': "Represent the user's input.", 'negative_4': "Represent the user's input.", 'negative_5': "Represent the user's input.", 'negative_6': "Represent the user's input.", 'negative_7': "Represent the user's input."}}
• batch_sampler: no_duplicates_hashed
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}
• mix_languages: False
• query_prompt: Find a document image that matches the given query.
• document_prompt: Represent the user's input.
• mini_batch_size: 8
• matryoshka_dims: [2048, 1024, 768, 512, 256, 128]
• use_lora: False
• lora_r: 32
• lora_alpha: 32
• lora_dropout: 0.05
• lora_target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
• use_self_guide: True
• self_guide_margin: -0.1
• hardness_strength: 2.0
• hardness_mode: hard_negatives

Training Logs

Click to expand

Epoch	Step	Training Loss	kovidore-v2-cybersecurity-beir-eval_cosine_ndcg@10	kovidore-v2-hr-beir-eval_cosine_ndcg@10	kovidore-v2-energy-beir-eval_cosine_ndcg@10	kovidore-v2-economic-beir-eval_cosine_ndcg@10
0	0	-	0.6074	0.1825	0.4090	0.1452
0.0007	1	17.7314	-	-	-	-
0.0014	2	17.6709	-	-	-	-
0.0022	3	24.3959	-	-	-	-
0.0029	4	14.5426	-	-	-	-
0.0036	5	17.7672	-	-	-	-
0.0043	6	14.4337	-	-	-	-
0.0051	7	17.6978	-	-	-	-
0.0058	8	24.0514	-	-	-	-
0.0065	9	20.9827	-	-	-	-
0.0072	10	18.1331	-	-	-	-
0.0079	11	14.1817	-	-	-	-
0.0087	12	20.7161	-	-	-	-
0.0094	13	23.9924	-	-	-	-
0.0101	14	11.3340	-	-	-	-
0.0108	15	13.8883	-	-	-	-
0.0116	16	19.5442	-	-	-	-
0.0123	17	14.2727	-	-	-	-
0.0130	18	16.6546	-	-	-	-
0.0137	19	22.3526	-	-	-	-
0.0145	20	19.4269	-	-	-	-
0.0152	21	13.6914	-	-	-	-
0.0159	22	13.2280	-	-	-	-
0.0166	23	16.5391	-	-	-	-
0.0173	24	21.5922	-	-	-	-
0.0181	25	15.6736	-	-	-	-
0.0188	26	16.1779	-	-	-	-
0.0195	27	15.3272	-	-	-	-
0.0202	28	21.1679	-	-	-	-
0.0210	29	20.9074	-	-	-	-
0.0217	30	20.1692	-	-	-	-
0.0224	31	14.4421	-	-	-	-
0.0231	32	17.1339	-	-	-	-
0.0238	33	14.4854	-	-	-	-
0.0246	34	17.4870	-	-	-	-
0.0253	35	12.1085	-	-	-	-
0.0260	36	16.4500	-	-	-	-
0.0267	37	14.2126	-	-	-	-
0.0275	38	19.0722	-	-	-	-
0.0282	39	16.2735	-	-	-	-
0.0289	40	16.4944	-	-	-	-
0.0296	41	13.9315	-	-	-	-
0.0303	42	18.1817	-	-	-	-
0.0311	43	14.1505	-	-	-	-
0.0318	44	16.0226	-	-	-	-
0.0325	45	15.9602	-	-	-	-
0.0332	46	15.5241	-	-	-	-
0.0340	47	17.4479	-	-	-	-
0.0347	48	17.2013	-	-	-	-
0.0354	49	9.3294	-	-	-	-
0.0361	50	11.5976	-	-	-	-
0.0368	51	13.3493	-	-	-	-
0.0376	52	13.0765	-	-	-	-
0.0383	53	11.2657	-	-	-	-
0.0390	54	15.0255	-	-	-	-
0.0397	55	15.3285	-	-	-	-
0.0405	56	11.5967	-	-	-	-
0.0412	57	12.2805	-	-	-	-
0.0419	58	10.0358	-	-	-	-
0.0426	59	11.0561	-	-	-	-
0.0434	60	12.5827	-	-	-	-
0.0441	61	12.3116	-	-	-	-
0.0448	62	12.7483	-	-	-	-
0.0455	63	12.1779	-	-	-	-
0.0462	64	12.3299	-	-	-	-
0.0470	65	16.4080	-	-	-	-
0.0477	66	16.2987	-	-	-	-
0.0484	67	15.9655	-	-	-	-
0.0491	68	12.2400	-	-	-	-
0.0499	69	15.3707	-	-	-	-
0.0506	70	8.9167	-	-	-	-
0.0513	71	13.9068	-	-	-	-
0.0520	72	12.2629	-	-	-	-
0.0527	73	10.7973	-	-	-	-
0.0535	74	14.5914	-	-	-	-
0.0542	75	10.7596	-	-	-	-
0.0549	76	11.8518	-	-	-	-
0.0556	77	11.6243	-	-	-	-
0.0564	78	13.5927	-	-	-	-
0.0571	79	13.7686	-	-	-	-
0.0578	80	11.6944	-	-	-	-
0.0585	81	10.0980	-	-	-	-
0.0592	82	14.7785	-	-	-	-
0.0600	83	11.5772	-	-	-	-
0.0607	84	11.7891	-	-	-	-
0.0614	85	11.4046	-	-	-	-
0.0621	86	11.3294	-	-	-	-
0.0629	87	7.9583	-	-	-	-
0.0636	88	11.5153	-	-	-	-
0.0643	89	10.0413	-	-	-	-
0.0650	90	11.2492	-	-	-	-
0.0658	91	14.1833	-	-	-	-
0.0665	92	13.1593	-	-	-	-
0.0672	93	11.6430	-	-	-	-
0.0679	94	9.6262	-	-	-	-
0.0686	95	11.4553	-	-	-	-
0.0694	96	11.2482	-	-	-	-
0.0701	97	13.3602	-	-	-	-
0.0708	98	13.0426	-	-	-	-
0.0715	99	10.0139	-	-	-	-
0.0723	100	14.2655	0.6907	0.3391	0.5451	0.2156
0.0730	101	12.4820	-	-	-	-
0.0737	102	11.0105	-	-	-	-
0.0744	103	11.2853	-	-	-	-
0.0751	104	14.1087	-	-	-	-
0.0759	105	9.6929	-	-	-	-
0.0766	106	11.3037	-	-	-	-
0.0773	107	10.8366	-	-	-	-
0.0780	108	11.4011	-	-	-	-
0.0788	109	10.9307	-	-	-	-
0.0795	110	12.5221	-	-	-	-
0.0802	111	12.5656	-	-	-	-
0.0809	112	13.3085	-	-	-	-
0.0816	113	11.3770	-	-	-	-
0.0824	114	10.9969	-	-	-	-
0.0831	115	12.5585	-	-	-	-
0.0838	116	10.6675	-	-	-	-
0.0845	117	11.5300	-	-	-	-
0.0853	118	11.7824	-	-	-	-
0.0860	119	10.9247	-	-	-	-
0.0867	120	9.6649	-	-	-	-
0.0874	121	11.1850	-	-	-	-
0.0882	122	9.7569	-	-	-	-
0.0889	123	13.3692	-	-	-	-
0.0896	124	10.8060	-	-	-	-
0.0903	125	9.6474	-	-	-	-
0.0910	126	12.1341	-	-	-	-
0.0918	127	12.7102	-	-	-	-
0.0925	128	12.0221	-	-	-	-
0.0932	129	11.7702	-	-	-	-
0.0939	130	9.7205	-	-	-	-
0.0947	131	13.3691	-	-	-	-
0.0954	132	11.0705	-	-	-	-
0.0961	133	10.7126	-	-	-	-
0.0968	134	12.1737	-	-	-	-
0.0975	135	10.4830	-	-	-	-
0.0983	136	9.4912	-	-	-	-
0.0990	137	11.3637	-	-	-	-
0.0997	138	11.2609	-	-	-	-
0.1004	139	10.2216	-	-	-	-
0.1012	140	10.5942	-	-	-	-
0.1019	141	12.6748	-	-	-	-
0.1026	142	12.0277	-	-	-	-
0.1033	143	11.2156	-	-	-	-
0.1040	144	9.9200	-	-	-	-
0.1048	145	12.3882	-	-	-	-
0.1055	146	11.4778	-	-	-	-
0.1062	147	8.8077	-	-	-	-
0.1069	148	11.5094	-	-	-	-
0.1077	149	10.4625	-	-	-	-
0.1084	150	9.9815	-	-	-	-
0.1091	151	9.7997	-	-	-	-
0.1098	152	9.1574	-	-	-	-
0.1105	153	11.6425	-	-	-	-
0.1113	154	11.4965	-	-	-	-
0.1120	155	9.9263	-	-	-	-
0.1127	156	10.0194	-	-	-	-
0.1134	157	10.0276	-	-	-	-
0.1142	158	10.8875	-	-	-	-
0.1149	159	10.0816	-	-	-	-
0.1156	160	11.4227	-	-	-	-
0.1163	161	10.5401	-	-	-	-
0.1171	162	10.2970	-	-	-	-
0.1178	163	10.9184	-	-	-	-
0.1185	164	9.6992	-	-	-	-
0.1192	165	9.7553	-	-	-	-
0.1199	166	8.7048	-	-	-	-
0.1207	167	9.8723	-	-	-	-
0.1214	168	12.0860	-	-	-	-
0.1221	169	10.7051	-	-	-	-
0.1228	170	10.8313	-	-	-	-
0.1236	171	9.7867	-	-	-	-
0.1243	172	9.5684	-	-	-	-
0.125	173	9.5008	-	-	-	-
0.1257	174	8.8494	-	-	-	-
0.1264	175	9.7925	-	-	-	-
0.1272	176	9.6504	-	-	-	-
0.1279	177	10.0302	-	-	-	-
0.1286	178	10.6459	-	-	-	-
0.1293	179	10.1380	-	-	-	-
0.1301	180	7.4243	-	-	-	-
0.1308	181	7.7410	-	-	-	-
0.1315	182	9.2349	-	-	-	-
0.1322	183	9.8367	-	-	-	-
0.1329	184	6.9811	-	-	-	-
0.1337	185	10.5248	-	-	-	-
0.1344	186	8.7278	-	-	-	-
0.1351	187	10.8839	-	-	-	-
0.1358	188	12.0160	-	-	-	-
0.1366	189	8.7785	-	-	-	-
0.1373	190	8.4755	-	-	-	-
0.1380	191	11.5206	-	-	-	-
0.1387	192	8.7303	-	-	-	-
0.1395	193	8.6276	-	-	-	-
0.1402	194	10.4396	-	-	-	-
0.1409	195	9.0238	-	-	-	-
0.1416	196	9.4830	-	-	-	-
0.1423	197	10.6982	-	-	-	-
0.1431	198	11.0013	-	-	-	-
0.1438	199	10.0782	-	-	-	-
0.1445	200	11.1777	0.7238	0.4011	0.5778	0.2265
0.1452	201	8.3479	-	-	-	-
0.1460	202	9.2607	-	-	-	-
0.1467	203	11.1014	-	-	-	-
0.1474	204	9.4054	-	-	-	-
0.1481	205	8.9530	-	-	-	-
0.1488	206	8.8994	-	-	-	-
0.1496	207	11.6011	-	-	-	-
0.1503	208	11.2486	-	-	-	-
0.1510	209	10.7180	-	-	-	-
0.1517	210	10.7015	-	-	-	-
0.1525	211	10.1297	-	-	-	-
0.1532	212	9.7532	-	-	-	-
0.1539	213	9.3618	-	-	-	-
0.1546	214	10.2734	-	-	-	-
0.1553	215	8.2948	-	-	-	-
0.1561	216	8.4837	-	-	-	-
0.1568	217	8.5607	-	-	-	-
0.1575	218	10.6564	-	-	-	-
0.1582	219	10.0190	-	-	-	-
0.1590	220	10.4515	-	-	-	-
0.1597	221	10.3502	-	-	-	-
0.1604	222	10.3286	-	-	-	-
0.1611	223	10.4949	-	-	-	-
0.1618	224	9.6301	-	-	-	-
0.1626	225	8.3568	-	-	-	-
0.1633	226	9.2099	-	-	-	-
0.1640	227	10.2555	-	-	-	-
0.1647	228	8.3302	-	-	-	-
0.1655	229	10.1760	-	-	-	-
0.1662	230	9.4756	-	-	-	-
0.1669	231	7.5440	-	-	-	-
0.1676	232	9.9567	-	-	-	-
0.1684	233	8.8959	-	-	-	-
0.1691	234	9.3286	-	-	-	-
0.1698	235	9.1852	-	-	-	-
0.1705	236	10.8267	-	-	-	-
0.1712	237	8.7722	-	-	-	-
0.1720	238	10.0908	-	-	-	-
0.1727	239	9.8169	-	-	-	-
0.1734	240	9.8890	-	-	-	-
0.1741	241	10.4694	-	-	-	-
0.1749	242	9.1145	-	-	-	-
0.1756	243	9.4147	-	-	-	-
0.1763	244	10.0850	-	-	-	-
0.1770	245	10.0486	-	-	-	-
0.1777	246	10.2285	-	-	-	-
0.1785	247	7.5933	-	-	-	-
0.1792	248	10.5853	-	-	-	-
0.1799	249	8.4684	-	-	-	-
0.1806	250	9.9920	-	-	-	-
0.1814	251	8.5907	-	-	-	-
0.1821	252	9.0045	-	-	-	-
0.1828	253	8.1093	-	-	-	-
0.1835	254	8.5917	-	-	-	-
0.1842	255	8.8837	-	-	-	-
0.1850	256	8.3218	-	-	-	-
0.1857	257	9.0086	-	-	-	-
0.1864	258	7.9651	-	-	-	-
0.1871	259	9.1210	-	-	-	-
0.1879	260	9.4857	-	-	-	-
0.1886	261	10.0600	-	-	-	-
0.1893	262	9.8456	-	-	-	-
0.1900	263	9.3120	-	-	-	-
0.1908	264	8.1314	-	-	-	-
0.1915	265	8.1997	-	-	-	-
0.1922	266	9.8101	-	-	-	-
0.1929	267	8.0789	-	-	-	-
0.1936	268	9.2850	-	-	-	-
0.1944	269	9.5261	-	-	-	-
0.1951	270	8.5575	-	-	-	-
0.1958	271	8.9399	-	-	-	-
0.1965	272	9.9385	-	-	-	-
0.1973	273	8.2594	-	-	-	-
0.1980	274	8.9676	-	-	-	-
0.1987	275	10.2038	-	-	-	-
0.1994	276	10.1318	-	-	-	-
0.2001	277	9.1765	-	-	-	-
0.2009	278	8.1022	-	-	-	-
0.2016	279	9.8626	-	-	-	-
0.2023	280	9.8847	-	-	-	-
0.2030	281	9.2022	-	-	-	-
0.2038	282	9.7332	-	-	-	-
0.2045	283	7.5860	-	-	-	-
0.2052	284	8.5780	-	-	-	-
0.2059	285	8.6566	-	-	-	-
0.2066	286	9.3355	-	-	-	-
0.2074	287	10.2896	-	-	-	-
0.2081	288	10.0537	-	-	-	-
0.2088	289	8.2433	-	-	-	-
0.2095	290	8.2263	-	-	-	-
0.2103	291	8.0526	-	-	-	-
0.2110	292	9.6761	-	-	-	-
0.2117	293	8.8752	-	-	-	-
0.2124	294	9.3111	-	-	-	-
0.2132	295	8.8289	-	-	-	-
0.2139	296	9.0700	-	-	-	-
0.2146	297	8.6080	-	-	-	-
0.2153	298	9.9135	-	-	-	-
0.2160	299	8.5825	-	-	-	-
0.2168	300	9.5082	0.7234	0.4227	0.6114	0.2771
0.2175	301	10.5331	-	-	-	-
0.2182	302	9.2341	-	-	-	-
0.2189	303	9.2584	-	-	-	-
0.2197	304	8.0718	-	-	-	-
0.2204	305	9.9312	-	-	-	-
0.2211	306	9.5201	-	-	-	-
0.2218	307	8.7057	-	-	-	-
0.2225	308	9.9972	-	-	-	-
0.2233	309	9.9834	-	-	-	-
0.2240	310	8.0921	-	-	-	-
0.2247	311	7.9919	-	-	-	-
0.2254	312	10.0251	-	-	-	-
0.2262	313	8.7798	-	-	-	-
0.2269	314	8.5805	-	-	-	-
0.2276	315	10.7220	-	-	-	-
0.2283	316	8.9273	-	-	-	-
0.2290	317	8.3291	-	-	-	-
0.2298	318	9.6182	-	-	-	-
0.2305	319	10.9208	-	-	-	-
0.2312	320	7.8888	-	-	-	-
0.2319	321	8.6042	-	-	-	-
0.2327	322	8.0339	-	-	-	-
0.2334	323	8.8964	-	-	-	-
0.2341	324	9.3657	-	-	-	-
0.2348	325	10.5106	-	-	-	-
0.2355	326	9.9869	-	-	-	-
0.2363	327	8.4480	-	-	-	-
0.2370	328	8.8682	-	-	-	-
0.2377	329	9.2955	-	-	-	-
0.2384	330	7.7706	-	-	-	-
0.2392	331	9.7297	-	-	-	-
0.2399	332	10.0692	-	-	-	-
0.2406	333	8.1762	-	-	-	-
0.2413	334	7.7009	-	-	-	-
0.2421	335	9.4079	-	-	-	-
0.2428	336	8.0058	-	-	-	-
0.2435	337	9.1029	-	-	-	-
0.2442	338	8.0388	-	-	-	-
0.2449	339	10.0602	-	-	-	-
0.2457	340	8.0448	-	-	-	-
0.2464	341	8.9665	-	-	-	-
0.2471	342	8.4084	-	-	-	-
0.2478	343	9.0403	-	-	-	-
0.2486	344	8.3110	-	-	-	-
0.2493	345	8.9458	-	-	-	-
0.25	346	8.1556	-	-	-	-
0.2507	347	8.6242	-	-	-	-
0.2514	348	8.0796	-	-	-	-
0.2522	349	8.0135	-	-	-	-
0.2529	350	7.8333	-	-	-	-
0.2536	351	9.3693	-	-	-	-
0.2543	352	8.8929	-	-	-	-
0.2551	353	8.4246	-	-	-	-
0.2558	354	7.6970	-	-	-	-
0.2565	355	7.5657	-	-	-	-
0.2572	356	9.6568	-	-	-	-
0.2579	357	8.1176	-	-	-	-
0.2587	358	8.0797	-	-	-	-
0.2594	359	8.2599	-	-	-	-
0.2601	360	8.4130	-	-	-	-
0.2608	361	7.8396	-	-	-	-
0.2616	362	9.1881	-	-	-	-
0.2623	363	7.5012	-	-	-	-
0.2630	364	8.2706	-	-	-	-
0.2637	365	8.3879	-	-	-	-
0.2645	366	9.9850	-	-	-	-
0.2652	367	7.6026	-	-	-	-
0.2659	368	8.1962	-	-	-	-
0.2666	369	8.0221	-	-	-	-
0.2673	370	9.3973	-	-	-	-
0.2681	371	9.4123	-	-	-	-
0.2688	372	7.3984	-	-	-	-
0.2695	373	7.9623	-	-	-	-
0.2702	374	7.2954	-	-	-	-
0.2710	375	9.7867	-	-	-	-
0.2717	376	8.5156	-	-	-	-
0.2724	377	9.0666	-	-	-	-
0.2731	378	8.9092	-	-	-	-
0.2738	379	7.7228	-	-	-	-
0.2746	380	7.6278	-	-	-	-
0.2753	381	8.3778	-	-	-	-
0.2760	382	8.8008	-	-	-	-
0.2767	383	8.2100	-	-	-	-
0.2775	384	7.9280	-	-	-	-
0.2782	385	8.6558	-	-	-	-
0.2789	386	7.7334	-	-	-	-
0.2796	387	9.4835	-	-	-	-
0.2803	388	10.0010	-	-	-	-
0.2811	389	8.6757	-	-	-	-
0.2818	390	9.7316	-	-	-	-
0.2825	391	9.4038	-	-	-	-
0.2832	392	9.6708	-	-	-	-
0.2840	393	9.0675	-	-	-	-
0.2847	394	8.8261	-	-	-	-
0.2854	395	9.2000	-	-	-	-
0.2861	396	9.7885	-	-	-	-
0.2868	397	7.8999	-	-	-	-
0.2876	398	7.6257	-	-	-	-
0.2883	399	8.2606	-	-	-	-
0.2890	400	8.1576	0.7194	0.4506	0.6176	0.2573
0.2897	401	8.8662	-	-	-	-
0.2905	402	8.5617	-	-	-	-
0.2912	403	9.5809	-	-	-	-
0.2919	404	8.2307	-	-	-	-
0.2926	405	8.5751	-	-	-	-
0.2934	406	7.8720	-	-	-	-
0.2941	407	8.9772	-	-	-	-
0.2948	408	8.6077	-	-	-	-
0.2955	409	8.0114	-	-	-	-
0.2962	410	7.0058	-	-	-	-
0.2970	411	8.0939	-	-	-	-
0.2977	412	8.0197	-	-	-	-
0.2984	413	9.2630	-	-	-	-
0.2991	414	8.1726	-	-	-	-
0.2999	415	7.8612	-	-	-	-
0.3006	416	8.0124	-	-	-	-
0.3013	417	7.6413	-	-	-	-
0.3020	418	7.9803	-	-	-	-
0.3027	419	8.1318	-	-	-	-
0.3035	420	8.2589	-	-	-	-
0.3042	421	7.9021	-	-	-	-
0.3049	422	8.6951	-	-	-	-
0.3056	423	8.5223	-	-	-	-
0.3064	424	8.2772	-	-	-	-
0.3071	425	8.2167	-	-	-	-
0.3078	426	9.4205	-	-	-	-
0.3085	427	7.5704	-	-	-	-
0.3092	428	8.4682	-	-	-	-
0.3100	429	7.9613	-	-	-	-
0.3107	430	7.6679	-	-	-	-
0.3114	431	8.6727	-	-	-	-
0.3121	432	8.6008	-	-	-	-
0.3129	433	8.0516	-	-	-	-
0.3136	434	7.2824	-	-	-	-
0.3143	435	7.4188	-	-	-	-
0.3150	436	8.5630	-	-	-	-
0.3158	437	8.3755	-	-	-	-
0.3165	438	7.6529	-	-	-	-
0.3172	439	9.0125	-	-	-	-
0.3179	440	8.7605	-	-	-	-
0.3186	441	7.9988	-	-	-	-
0.3194	442	8.2557	-	-	-	-
0.3201	443	8.3574	-	-	-	-
0.3208	444	7.7545	-	-	-	-
0.3215	445	8.4518	-	-	-	-
0.3223	446	7.1982	-	-	-	-
0.3230	447	8.6810	-	-	-	-
0.3237	448	8.0817	-	-	-	-
0.3244	449	8.1662	-	-	-	-
0.3251	450	8.6337	-	-	-	-
0.3259	451	8.1885	-	-	-	-
0.3266	452	9.0659	-	-	-	-
0.3273	453	8.6045	-	-	-	-
0.3280	454	7.3979	-	-	-	-
0.3288	455	9.0661	-	-	-	-
0.3295	456	8.3930	-	-	-	-
0.3302	457	7.1150	-	-	-	-
0.3309	458	8.7953	-	-	-	-
0.3316	459	8.1700	-	-	-	-
0.3324	460	8.2912	-	-	-	-
0.3331	461	9.3303	-	-	-	-
0.3338	462	9.0791	-	-	-	-
0.3345	463	8.1770	-	-	-	-
0.3353	464	7.8256	-	-	-	-
0.3360	465	8.4121	-	-	-	-
0.3367	466	8.0520	-	-	-	-
0.3374	467	8.0105	-	-	-	-
0.3382	468	9.3248	-	-	-	-
0.3389	469	8.2912	-	-	-	-
0.3396	470	9.3977	-	-	-	-
0.3403	471	8.2517	-	-	-	-
0.3410	472	8.2516	-	-	-	-
0.3418	473	7.7780	-	-	-	-
0.3425	474	7.8586	-	-	-	-
0.3432	475	7.6331	-	-	-	-
0.3439	476	8.2923	-	-	-	-
0.3447	477	7.3848	-	-	-	-
0.3454	478	8.0293	-	-	-	-
0.3461	479	8.4023	-	-	-	-
0.3468	480	8.8823	-	-	-	-
0.3475	481	8.3210	-	-	-	-
0.3483	482	7.8237	-	-	-	-
0.3490	483	8.1519	-	-	-	-
0.3497	484	8.1342	-	-	-	-
0.3504	485	7.1318	-	-	-	-
0.3512	486	8.5340	-	-	-	-
0.3519	487	7.5906	-	-	-	-
0.3526	488	8.3306	-	-	-	-
0.3533	489	7.1065	-	-	-	-
0.3540	490	8.5389	-	-	-	-
0.3548	491	8.3787	-	-	-	-
0.3555	492	7.4683	-	-	-	-
0.3562	493	8.7707	-	-	-	-
0.3569	494	8.3458	-	-	-	-
0.3577	495	8.1725	-	-	-	-
0.3584	496	8.3133	-	-	-	-
0.3591	497	8.2490	-	-	-	-
0.3598	498	7.9564	-	-	-	-
0.3605	499	7.8053	-	-	-	-
0.3613	500	8.4833	0.7238	0.4355	0.6244	0.2700
0.3620	501	7.7875	-	-	-	-
0.3627	502	7.7738	-	-	-	-
0.3634	503	7.8349	-	-	-	-
0.3642	504	8.3810	-	-	-	-
0.3649	505	7.3185	-	-	-	-
0.3656	506	7.8604	-	-	-	-
0.3663	507	7.6827	-	-	-	-
0.3671	508	7.6726	-	-	-	-
0.3678	509	8.4541	-	-	-	-
0.3685	510	7.2326	-	-	-	-
0.3692	511	8.6613	-	-	-	-
0.3699	512	7.9544	-	-	-	-
0.3707	513	7.8007	-	-	-	-
0.3714	514	8.7982	-	-	-	-
0.3721	515	7.7777	-	-	-	-
0.3728	516	8.5674	-	-	-	-
0.3736	517	8.2744	-	-	-	-
0.3743	518	7.0476	-	-	-	-
0.375	519	7.5052	-	-	-	-
0.3757	520	6.9018	-	-	-	-
0.3764	521	7.9064	-	-	-	-
0.3772	522	8.0225	-	-	-	-
0.3779	523	7.1236	-	-	-	-
0.3786	524	7.0931	-	-	-	-
0.3793	525	7.6283	-	-	-	-
0.3801	526	7.2890	-	-	-	-
0.3808	527	8.4381	-	-	-	-
0.3815	528	7.8869	-	-	-	-
0.3822	529	7.2110	-	-	-	-
0.3829	530	7.9312	-	-	-	-
0.3837	531	6.7715	-	-	-	-
0.3844	532	8.1547	-	-	-	-
0.3851	533	7.9176	-	-	-	-
0.3858	534	7.2403	-	-	-	-
0.3866	535	8.0285	-	-	-	-
0.3873	536	8.1567	-	-	-	-
0.3880	537	8.6571	-	-	-	-
0.3887	538	8.1630	-	-	-	-
0.3895	539	8.4178	-	-	-	-
0.3902	540	7.4946	-	-	-	-
0.3909	541	7.4387	-	-	-	-
0.3916	542	7.4160	-	-	-	-
0.3923	543	8.3448	-	-	-	-
0.3931	544	6.2377	-	-	-	-
0.3938	545	8.1367	-	-	-	-
0.3945	546	7.1685	-	-	-	-
0.3952	547	7.1526	-	-	-	-
0.3960	548	8.4130	-	-	-	-
0.3967	549	7.4078	-	-	-	-
0.3974	550	8.3617	-	-	-	-
0.3981	551	8.6907	-	-	-	-
0.3988	552	7.6503	-	-	-	-
0.3996	553	8.3953	-	-	-	-
0.4003	554	7.6647	-	-	-	-
0.4010	555	6.7413	-	-	-	-
0.4017	556	7.2645	-	-	-	-
0.4025	557	7.2387	-	-	-	-
0.4032	558	8.4087	-	-	-	-
0.4039	559	7.4975	-	-	-	-
0.4046	560	7.3596	-	-	-	-
0.4053	561	8.6524	-	-	-	-
0.4061	562	7.8777	-	-	-	-
0.4068	563	7.4538	-	-	-	-
0.4075	564	8.4186	-	-	-	-
0.4082	565	7.0462	-	-	-	-
0.4090	566	8.6154	-	-	-	-
0.4097	567	6.9096	-	-	-	-
0.4104	568	7.1839	-	-	-	-
0.4111	569	7.9476	-	-	-	-
0.4118	570	7.4400	-	-	-	-
0.4126	571	6.7115	-	-	-	-
0.4133	572	8.5446	-	-	-	-
0.4140	573	8.7890	-	-	-	-
0.4147	574	7.9439	-	-	-	-
0.4155	575	6.9787	-	-	-	-
0.4162	576	7.0749	-	-	-	-
0.4169	577	6.8827	-	-	-	-
0.4176	578	8.0618	-	-	-	-
0.4184	579	8.6649	-	-	-	-
0.4191	580	7.2719	-	-	-	-
0.4198	581	7.4368	-	-	-	-
0.4205	582	7.4322	-	-	-	-
0.4212	583	8.5017	-	-	-	-
0.4220	584	8.4113	-	-	-	-
0.4227	585	6.9112	-	-	-	-
0.4234	586	6.5427	-	-	-	-
0.4241	587	7.2845	-	-	-	-
0.4249	588	7.2644	-	-	-	-
0.4256	589	7.7088	-	-	-	-
0.4263	590	7.1716	-	-	-	-
0.4270	591	7.9033	-	-	-	-
0.4277	592	7.0766	-	-	-	-
0.4285	593	7.6995	-	-	-	-
0.4292	594	6.9699	-	-	-	-
0.4299	595	7.1035	-	-	-	-
0.4306	596	7.7222	-	-	-	-
0.4314	597	6.4498	-	-	-	-
0.4321	598	7.7006	-	-	-	-
0.4328	599	7.8926	-	-	-	-
0.4335	600	7.5089	0.7273	0.4746	0.6237	0.2669
0.4342	601	7.6090	-	-	-	-
0.4350	602	8.4444	-	-	-	-
0.4357	603	7.7756	-	-	-	-
0.4364	604	8.2640	-	-	-	-
0.4371	605	7.7521	-	-	-	-
0.4379	606	7.3901	-	-	-	-
0.4386	607	7.4393	-	-	-	-
0.4393	608	6.5070	-	-	-	-
0.4400	609	7.5768	-	-	-	-
0.4408	610	8.2122	-	-	-	-
0.4415	611	8.1515	-	-	-	-
0.4422	612	7.9178	-	-	-	-
0.4429	613	8.4987	-	-	-	-
0.4436	614	7.1377	-	-	-	-
0.4444	615	8.4738	-	-	-	-
0.4451	616	8.4375	-	-	-	-
0.4458	617	7.9653	-	-	-	-
0.4465	618	7.5035	-	-	-	-
0.4473	619	7.4002	-	-	-	-
0.4480	620	8.1151	-	-	-	-
0.4487	621	8.4934	-	-	-	-
0.4494	622	7.8822	-	-	-	-
0.4501	623	6.9771	-	-	-	-
0.4509	624	7.7505	-	-	-	-
0.4516	625	7.3345	-	-	-	-
0.4523	626	7.9587	-	-	-	-
0.4530	627	7.4467	-	-	-	-
0.4538	628	7.9764	-	-	-	-
0.4545	629	7.2720	-	-	-	-
0.4552	630	6.7293	-	-	-	-
0.4559	631	7.5552	-	-	-	-
0.4566	632	6.9937	-	-	-	-
0.4574	633	6.5343	-	-	-	-
0.4581	634	6.7014	-	-	-	-
0.4588	635	7.8587	-	-	-	-
0.4595	636	7.2476	-	-	-	-
0.4603	637	7.3340	-	-	-	-
0.4610	638	6.8358	-	-	-	-
0.4617	639	7.9300	-	-	-	-
0.4624	640	7.0121	-	-	-	-
0.4632	641	8.4795	-	-	-	-
0.4639	642	7.5933	-	-	-	-
0.4646	643	6.2443	-	-	-	-
0.4653	644	8.1354	-	-	-	-
0.4660	645	7.3165	-	-	-	-
0.4668	646	8.6436	-	-	-	-
0.4675	647	6.5427	-	-	-	-
0.4682	648	7.1162	-	-	-	-
0.4689	649	7.6553	-	-	-	-
0.4697	650	7.9501	-	-	-	-
0.4704	651	7.4572	-	-	-	-
0.4711	652	8.2903	-	-	-	-
0.4718	653	7.2616	-	-	-	-
0.4725	654	7.1124	-	-	-	-
0.4733	655	7.8941	-	-	-	-
0.4740	656	7.7947	-	-	-	-
0.4747	657	6.8933	-	-	-	-
0.4754	658	6.8590	-	-	-	-
0.4762	659	7.5596	-	-	-	-
0.4769	660	6.6670	-	-	-	-
0.4776	661	8.1072	-	-	-	-
0.4783	662	7.0305	-	-	-	-
0.4790	663	7.6628	-	-	-	-
0.4798	664	6.9900	-	-	-	-
0.4805	665	7.1122	-	-	-	-
0.4812	666	8.2952	-	-	-	-
0.4819	667	7.3085	-	-	-	-
0.4827	668	7.1687	-	-	-	-
0.4834	669	7.5962	-	-	-	-
0.4841	670	8.1160	-	-	-	-
0.4848	671	8.1729	-	-	-	-
0.4855	672	7.2021	-	-	-	-
0.4863	673	7.7019	-	-	-	-
0.4870	674	6.9293	-	-	-	-
0.4877	675	7.5951	-	-	-	-
0.4884	676	7.7914	-	-	-	-
0.4892	677	7.7036	-	-	-	-
0.4899	678	6.7734	-	-	-	-
0.4906	679	7.0497	-	-	-	-
0.4913	680	6.8173	-	-	-	-
0.4921	681	7.6200	-	-	-	-
0.4928	682	8.4407	-	-	-	-
0.4935	683	7.0739	-	-	-	-
0.4942	684	8.8349	-	-	-	-
0.4949	685	6.9559	-	-	-	-
0.4957	686	7.6070	-	-	-	-
0.4964	687	7.6109	-	-	-	-
0.4971	688	7.0861	-	-	-	-
0.4978	689	6.8501	-	-	-	-
0.4986	690	7.1597	-	-	-	-
0.4993	691	6.9578	-	-	-	-
0.5	692	7.8570	-	-	-	-
0.5007	693	7.8730	-	-	-	-
0.5014	694	6.7911	-	-	-	-
0.5022	695	7.8491	-	-	-	-
0.5029	696	7.5524	-	-	-	-
0.5036	697	8.0739	-	-	-	-
0.5043	698	8.5662	-	-	-	-
0.5051	699	7.3622	-	-	-	-
0.5058	700	7.3835	0.7272	0.4773	0.6377	0.2803
0.5065	701	8.5150	-	-	-	-
0.5072	702	7.7958	-	-	-	-
0.5079	703	6.2944	-	-	-	-
0.5087	704	6.1115	-	-	-	-
0.5094	705	7.8226	-	-	-	-
0.5101	706	7.6744	-	-	-	-
0.5108	707	6.7690	-	-	-	-
0.5116	708	6.8332	-	-	-	-
0.5123	709	7.6136	-	-	-	-
0.5130	710	7.5713	-	-	-	-
0.5137	711	8.0085	-	-	-	-
0.5145	712	7.3826	-	-	-	-
0.5152	713	7.2971	-	-	-	-
0.5159	714	7.9334	-	-	-	-
0.5166	715	7.2919	-	-	-	-
0.5173	716	7.1592	-	-	-	-
0.5181	717	7.3261	-	-	-	-
0.5188	718	6.7150	-	-	-	-
0.5195	719	8.5499	-	-	-	-
0.5202	720	7.7304	-	-	-	-
0.5210	721	7.5069	-	-	-	-
0.5217	722	7.7904	-	-	-	-
0.5224	723	6.9922	-	-	-	-
0.5231	724	6.3935	-	-	-	-
0.5238	725	7.2567	-	-	-	-
0.5246	726	8.5631	-	-	-	-
0.5253	727	6.9862	-	-	-	-
0.5260	728	6.6001	-	-	-	-
0.5267	729	7.0219	-	-	-	-
0.5275	730	7.7605	-	-	-	-
0.5282	731	7.3577	-	-	-	-
0.5289	732	6.6677	-	-	-	-
0.5296	733	6.8653	-	-	-	-
0.5303	734	7.3375	-	-	-	-
0.5311	735	7.6258	-	-	-	-
0.5318	736	6.4578	-	-	-	-
0.5325	737	7.0162	-	-	-	-
0.5332	738	7.8475	-	-	-	-
0.5340	739	7.9454	-	-	-	-
0.5347	740	7.5788	-	-	-	-
0.5354	741	7.7249	-	-	-	-
0.5361	742	7.4702	-	-	-	-
0.5368	743	7.0135	-	-	-	-
0.5376	744	7.8161	-	-	-	-
0.5383	745	7.3332	-	-	-	-
0.5390	746	6.5297	-	-	-	-
0.5397	747	7.0312	-	-	-	-
0.5405	748	7.1721	-	-	-	-
0.5412	749	8.0897	-	-	-	-
0.5419	750	7.1752	-	-	-	-
0.5426	751	7.7495	-	-	-	-
0.5434	752	7.0791	-	-	-	-
0.5441	753	7.1923	-	-	-	-
0.5448	754	5.9893	-	-	-	-
0.5455	755	6.9869	-	-	-	-
0.5462	756	8.1204	-	-	-	-
0.5470	757	7.3832	-	-	-	-
0.5477	758	6.7538	-	-	-	-
0.5484	759	8.1324	-	-	-	-
0.5491	760	7.9239	-	-	-	-
0.5499	761	7.7020	-	-	-	-
0.5506	762	8.7253	-	-	-	-
0.5513	763	7.0535	-	-	-	-
0.5520	764	7.9313	-	-	-	-
0.5527	765	7.9381	-	-	-	-
0.5535	766	7.8330	-	-	-	-
0.5542	767	6.0990	-	-	-	-
0.5549	768	7.1618	-	-	-	-
0.5556	769	8.2060	-	-	-	-
0.5564	770	7.4535	-	-	-	-
0.5571	771	7.0464	-	-	-	-
0.5578	772	6.2910	-	-	-	-
0.5585	773	8.1528	-	-	-	-
0.5592	774	7.5924	-	-	-	-
0.5600	775	7.4485	-	-	-	-
0.5607	776	7.6996	-	-	-	-
0.5614	777	7.3904	-	-	-	-
0.5621	778	7.2580	-	-	-	-
0.5629	779	7.8013	-	-	-	-
0.5636	780	8.0360	-	-	-	-
0.5643	781	6.5123	-	-	-	-
0.5650	782	7.6283	-	-	-	-
0.5658	783	6.6200	-	-	-	-
0.5665	784	7.4103	-	-	-	-
0.5672	785	7.0024	-	-	-	-
0.5679	786	7.6000	-	-	-	-
0.5686	787	6.9320	-	-	-	-
0.5694	788	7.4983	-	-	-	-
0.5701	789	7.1964	-	-	-	-
0.5708	790	8.2904	-	-	-	-
0.5715	791	6.9544	-	-	-	-
0.5723	792	7.7949	-	-	-	-
0.5730	793	7.7746	-	-	-	-
0.5737	794	6.8510	-	-	-	-
0.5744	795	7.6516	-	-	-	-
0.5751	796	7.8113	-	-	-	-
0.5759	797	7.1703	-	-	-	-
0.5766	798	7.7590	-	-	-	-
0.5773	799	8.2946	-	-	-	-
0.5780	800	7.7451	0.7347	0.4800	0.6430	0.3064
0.5788	801	8.4531	-	-	-	-
0.5795	802	7.5427	-	-	-	-
0.5802	803	7.0634	-	-	-	-
0.5809	804	6.4301	-	-	-	-
0.5816	805	7.1618	-	-	-	-
0.5824	806	7.3589	-	-	-	-
0.5831	807	7.3546	-	-	-	-
0.5838	808	6.7180	-	-	-	-
0.5845	809	7.5502	-	-	-	-
0.5853	810	6.6981	-	-	-	-
0.5860	811	7.8738	-	-	-	-
0.5867	812	6.8062	-	-	-	-
0.5874	813	6.7916	-	-	-	-
0.5882	814	6.5940	-	-	-	-
0.5889	815	6.8790	-	-	-	-
0.5896	816	7.0481	-	-	-	-
0.5903	817	7.8366	-	-	-	-
0.5910	818	6.8461	-	-	-	-
0.5918	819	7.4625	-	-	-	-
0.5925	820	7.0115	-	-	-	-
0.5932	821	7.1417	-	-	-	-
0.5939	822	8.0153	-	-	-	-
0.5947	823	7.5028	-	-	-	-
0.5954	824	6.9183	-	-	-	-
0.5961	825	7.0681	-	-	-	-
0.5968	826	7.4485	-	-	-	-
0.5975	827	6.9607	-	-	-	-
0.5983	828	8.6324	-	-	-	-
0.5990	829	7.1151	-	-	-	-
0.5997	830	7.0974	-	-	-	-
0.6004	831	7.4849	-	-	-	-
0.6012	832	6.6123	-	-	-	-
0.6019	833	7.1641	-	-	-	-
0.6026	834	7.4719	-	-	-	-
0.6033	835	7.9637	-	-	-	-
0.6040	836	7.3089	-	-	-	-
0.6048	837	7.9267	-	-	-	-
0.6055	838	7.9179	-	-	-	-
0.6062	839	7.9091	-	-	-	-
0.6069	840	6.8322	-	-	-	-
0.6077	841	7.5822	-	-	-	-
0.6084	842	8.0908	-	-	-	-
0.6091	843	7.7618	-	-	-	-
0.6098	844	6.8142	-	-	-	-
0.6105	845	7.1276	-	-	-	-
0.6113	846	7.6463	-	-	-	-
0.6120	847	7.6375	-	-	-	-
0.6127	848	6.5987	-	-	-	-
0.6134	849	7.6656	-	-	-	-
0.6142	850	7.6862	-	-	-	-
0.6149	851	7.2357	-	-	-	-
0.6156	852	6.6887	-	-	-	-
0.6163	853	8.0645	-	-	-	-
0.6171	854	7.7621	-	-	-	-
0.6178	855	7.3832	-	-	-	-
0.6185	856	6.6585	-	-	-	-
0.6192	857	7.2359	-	-	-	-
0.6199	858	7.7114	-	-	-	-
0.6207	859	7.2987	-	-	-	-
0.6214	860	8.0552	-	-	-	-
0.6221	861	7.1842	-	-	-	-
0.6228	862	6.2554	-	-	-	-
0.6236	863	7.7739	-	-	-	-
0.6243	864	6.5568	-	-	-	-
0.625	865	6.5618	-	-	-	-
0.6257	866	7.8200	-	-	-	-
0.6264	867	7.5513	-	-	-	-
0.6272	868	7.6365	-	-	-	-
0.6279	869	7.0561	-	-	-	-
0.6286	870	7.3309	-	-	-	-
0.6293	871	7.8576	-	-	-	-
0.6301	872	8.8530	-	-	-	-
0.6308	873	7.3862	-	-	-	-
0.6315	874	7.2541	-	-	-	-
0.6322	875	7.0142	-	-	-	-
0.6329	876	7.3001	-	-	-	-
0.6337	877	8.2459	-	-	-	-
0.6344	878	7.3193	-	-	-	-
0.6351	879	7.6507	-	-	-	-
0.6358	880	8.1390	-	-	-	-
0.6366	881	6.7043	-	-	-	-
0.6373	882	7.0646	-	-	-	-
0.6380	883	6.9948	-	-	-	-
0.6387	884	7.6454	-	-	-	-
0.6395	885	6.9063	-	-	-	-
0.6402	886	7.7426	-	-	-	-
0.6409	887	7.1590	-	-	-	-
0.6416	888	7.9728	-	-	-	-
0.6423	889	6.6188	-	-	-	-
0.6431	890	7.7155	-	-	-	-
0.6438	891	7.1005	-	-	-	-
0.6445	892	7.5475	-	-	-	-
0.6452	893	7.4704	-	-	-	-
0.6460	894	7.4684	-	-	-	-
0.6467	895	6.5519	-	-	-	-
0.6474	896	7.1642	-	-	-	-
0.6481	897	7.9273	-	-	-	-
0.6488	898	8.5027	-	-	-	-
0.6496	899	7.3934	-	-	-	-
0.6503	900	6.4447	0.7394	0.4821	0.6448	0.2952

Training Time

• Training: 4.0 days
• Evaluation: 1.2 hours
• Total: 4.1 days

Framework Versions

• Python: 3.10.20
• Sentence Transformers: 5.4.1
• Transformers: 5.5.4
• PyTorch: 2.11.0+cu130
• Accelerate: 1.13.0
• Datasets: 4.8.4
• Tokenizers: 0.22.2

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

SelfGuideCachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}