metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1087179
  - loss:TripletLoss
widget:
  - source_sentence: hyperactive impulsive adhd
    sentences:
      - Claw Clip
      - egyptian postage
      - mug
  - source_sentence: Work of Madness Hoodie
    sentences:
      - t-shirt
      - towel
      - men hoodie
  - source_sentence: E7Lam Hoodie
    sentences:
      - Al Mady Hoodie
      - waterfall cup
      - hoodie
  - source_sentence: Tote bag
    sentences:
      - Waterfall Mug
      - hoodie
      - linen tote bag
  - source_sentence: Kimono
    sentences:
      - mug
      - fringe kaftan
      - shoes
model-index:
  - name: all-MiniLM-L6-v2-triplet-loss
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli dev
          type: all-nli-dev
        metrics:
          - type: cosine_accuracy
            value: 0.9168454165823506
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.08315458341764934
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.9135451351202193
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.9168454165823506
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.9168454165823506
            name: Max Accuracy

all-MiniLM-L6-v2-triplet-loss

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 = [
    'Kimono',
    'fringe kaftan',
    'mug',
]
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

Triplet

Dataset: all-nli-dev
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9168
dot_accuracy	0.0832
manhattan_accuracy	0.9135
euclidean_accuracy	0.9168
max_accuracy	0.9168

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	all-nli-dev_max_accuracy
0	0	-	-	0.9168
0.0029	100	4.7115	-	-
0.0059	200	4.6948	-	-
0.0088	300	4.6548	-	-
0.0118	400	4.6055	-	-
0.0147	500	4.5234	4.3878	-
0.0177	600	4.4338	-	-
0.0206	700	4.2938	-	-
0.0235	800	4.1176	-	-
0.0265	900	3.9373	-	-
0.0294	1000	3.7241	3.4721	-
0.0324	1100	3.5965	-	-
0.0353	1200	3.4949	-	-
0.0383	1300	3.4542	-	-
0.0412	1400	3.4345	-	-
0.0442	1500	3.3955	3.2453	-
0.0471	1600	3.3818	-	-
0.0500	1700	3.3608	-	-
0.0530	1800	3.3377	-	-
0.0559	1900	3.326	-	-
0.0589	2000	3.3061	3.1692	-
0.0618	2100	3.308	-	-
0.0648	2200	3.2887	-	-
0.0677	2300	3.2963	-	-
0.0706	2400	3.2744	-	-
0.0736	2500	3.2601	3.1416	-
0.0765	2600	3.271	-	-
0.0795	2700	3.2501	-	-
0.0824	2800	3.2536	-	-
0.0854	2900	3.2689	-	-
0.0883	3000	3.2362	3.1196	-
0.0912	3100	3.2281	-	-
0.0942	3200	3.2351	-	-
0.0971	3300	3.2173	-	-
0.1001	3400	3.2055	-	-
0.1030	3500	3.2198	3.1081	-
0.1060	3600	3.2116	-	-
0.1089	3700	3.2088	-	-
0.1118	3800	3.2043	-	-
0.1148	3900	3.1943	-	-
0.1177	4000	3.1897	3.1027	-
0.1207	4100	3.2131	-	-
0.1236	4200	3.198	-	-
0.1266	4300	3.1892	-	-
0.1295	4400	3.1753	-	-
0.1325	4500	3.1722	3.0840	-
0.1354	4600	3.1599	-	-
0.1383	4700	3.166	-	-
0.1413	4800	3.1585	-	-
0.1442	4900	3.1698	-	-
0.1472	5000	3.1766	3.0782	-
0.1501	5100	3.1515	-	-
0.1531	5200	3.1487	-	-
0.1560	5300	3.1579	-	-
0.1589	5400	3.1533	-	-
0.1619	5500	3.1433	3.0735	-
0.1648	5600	3.1454	-	-
0.1678	5700	3.1397	-	-
0.1707	5800	3.1422	-	-
0.1737	5900	3.1372	-	-
0.1766	6000	3.137	3.0710	-
0.1795	6100	3.1297	-	-
0.1825	6200	3.1202	-	-
0.1854	6300	3.1256	-	-
0.1884	6400	3.1185	-	-
0.1913	6500	3.1266	3.0667	-
0.1943	6600	3.1197	-	-
0.1972	6700	3.1286	-	-
0.2001	6800	3.1239	-	-
0.2031	6900	3.1166	-	-
0.2060	7000	3.1054	3.0664	-
0.2090	7100	3.1103	-	-
0.2119	7200	3.0929	-	-
0.2149	7300	3.1051	-	-
0.2178	7400	3.1023	-	-
0.2208	7500	3.0946	3.0636	-
0.2237	7600	3.0958	-	-
0.2266	7700	3.0907	-	-
0.2296	7800	3.1051	-	-
0.2325	7900	3.0965	-	-
0.2355	8000	3.0954	3.0617	-
0.2384	8100	3.0693	-	-
0.2414	8200	3.0906	-	-
0.2443	8300	3.0881	-	-
0.2472	8400	3.0867	-	-
0.2502	8500	3.0867	3.0610	-
0.2531	8600	3.0909	-	-
0.2561	8700	3.0877	-	-
0.2590	8800	3.0837	-	-
0.2620	8900	3.0865	-	-
0.2649	9000	3.0846	3.0607	-
0.2678	9100	3.0798	-	-
0.2708	9200	3.0928	-	-
0.2737	9300	3.0794	-	-
0.2767	9400	3.0797	-	-
0.2796	9500	3.0685	3.0623	-
0.2826	9600	3.0768	-	-
0.2855	9700	3.0657	-	-
0.2884	9800	3.0838	-	-
0.2914	9900	3.0775	-	-
0.2943	10000	3.0667	3.0587	-
0.2973	10100	3.088	-	-
0.3002	10200	3.0824	-	-
0.3032	10300	3.0754	-	-
0.3061	10400	3.064	-	-
0.3091	10500	3.0637	3.0578	-
0.3120	10600	3.0754	-	-
0.3149	10700	3.0703	-	-
0.3179	10800	3.0697	-	-
0.3208	10900	3.0635	-	-
0.3238	11000	3.0872	3.0573	-
0.3267	11100	3.0722	-	-
0.3297	11200	3.0633	-	-
0.3326	11300	3.058	-	-
0.3355	11400	3.0601	-	-
0.3385	11500	3.0732	3.0583	-
0.3414	11600	3.0565	-	-
0.3444	11700	3.0735	-	-
0.3473	11800	3.0656	-	-
0.3503	11900	3.0583	-	-
0.3532	12000	3.0714	3.0574	-
0.3561	12100	3.0647	-	-
0.3591	12200	3.0522	-	-
0.3620	12300	3.0668	-	-
0.3650	12400	3.071	-	-
0.3679	12500	3.0667	3.0556	-
0.3709	12600	3.0568	-	-
0.3738	12700	3.0642	-	-
0.3767	12800	3.0607	-	-
0.3797	12900	3.0679	-	-
0.3826	13000	3.0547	3.0547	-
0.3856	13100	3.0714	-	-
0.3885	13200	3.0692	-	-
0.3915	13300	3.0597	-	-
0.3944	13400	3.067	-	-
0.3974	13500	3.0626	3.0551	-
0.4003	13600	3.0708	-	-
0.4032	13700	3.065	-	-
0.4062	13800	3.0619	-	-
0.4091	13900	3.0556	-	-
0.4121	14000	3.0708	3.0524	-
0.4150	14100	3.0634	-	-
0.4180	14200	3.0605	-	-
0.4209	14300	3.0555	-	-
0.4238	14400	3.0624	-	-
0.4268	14500	3.0468	3.0510	-
0.4297	14600	3.0534	-	-
0.4327	14700	3.0671	-	-
0.4356	14800	3.0714	-	-
0.4386	14900	3.0493	-	-
0.4415	15000	3.0457	3.0467	-
0.4444	15100	3.0599	-	-
0.4474	15200	3.0554	-	-
0.4503	15300	3.0466	-	-
0.4533	15400	3.0471	-	-
0.4562	15500	3.0465	3.0500	-
0.4592	15600	3.0556	-	-
0.4621	15700	3.0444	-	-
0.4650	15800	3.0468	-	-
0.4680	15900	3.0554	-	-
0.4709	16000	3.0573	3.0469	-
0.4739	16100	3.049	-	-
0.4768	16200	3.0539	-	-
0.4798	16300	3.052	-	-
0.4827	16400	3.0538	-	-
0.4857	16500	3.045	3.0444	-
0.4886	16600	3.0381	-	-
0.4915	16700	3.0517	-	-
0.4945	16800	3.0598	-	-
0.4974	16900	3.046	-	-
0.5004	17000	3.0478	3.0447	-
0.5033	17100	3.054	-	-
0.5063	17200	3.0471	-	-
0.5092	17300	3.0383	-	-
0.5121	17400	3.0539	-	-
0.5151	17500	3.0457	3.0432	-
0.5180	17600	3.05	-	-
0.5210	17700	3.05	-	-
0.5239	17800	3.0512	-	-
0.5269	17900	3.0399	-	-
0.5298	18000	3.048	3.0431	-
0.5327	18100	3.0367	-	-
0.5357	18200	3.0442	-	-
0.5386	18300	3.0472	-	-
0.5416	18400	3.0335	-	-
0.5445	18500	3.0465	3.0459	-
0.5475	18600	3.054	-	-
0.5504	18700	3.0489	-	-
0.5533	18800	3.037	-	-
0.5563	18900	3.0432	-	-
0.5592	19000	3.0401	3.0426	-
0.5622	19100	3.0369	-	-
0.5651	19200	3.0561	-	-
0.5681	19300	3.0469	-	-
0.5710	19400	3.0468	-	-
0.5740	19500	3.0455	3.0433	-
0.5769	19600	3.0512	-	-
0.5798	19700	3.0474	-	-
0.5828	19800	3.043	-	-
0.5857	19900	3.0473	-	-
0.5887	20000	3.0448	3.0415	-
0.5916	20100	3.0441	-	-
0.5946	20200	3.0403	-	-
0.5975	20300	3.0516	-	-
0.6004	20400	3.0459	-	-
0.6034	20500	3.0415	3.0415	-
0.6063	20600	3.034	-	-
0.6093	20700	3.0483	-	-
0.6122	20800	3.0538	-	-
0.6152	20900	3.0458	-	-
0.6181	21000	3.0445	3.0372	-
0.6210	21100	3.0414	-	-
0.6240	21200	3.0476	-	-
0.6269	21300	3.0638	-	-
0.6299	21400	3.0375	-	-
0.6328	21500	3.0425	3.0397	-
0.6358	21600	3.0394	-	-
0.6387	21700	3.0443	-	-
0.6416	21800	3.0381	-	-
0.6446	21900	3.0387	-	-
0.6475	22000	3.0255	3.0381	-
0.6505	22100	3.0355	-	-
0.6534	22200	3.0411	-	-
0.6564	22300	3.0436	-	-
0.6593	22400	3.038	-	-
0.6623	22500	3.0336	3.0325	-
0.6652	22600	3.0404	-	-
0.6681	22700	3.0374	-	-
0.6711	22800	3.0342	-	-
0.6740	22900	3.0385	-	-
0.6770	23000	3.0329	3.0342	-
0.6799	23100	3.0391	-	-
0.6829	23200	3.0366	-	-
0.6858	23300	3.0284	-	-
0.6887	23400	3.0328	-	-
0.6917	23500	3.0322	3.0333	-
0.6946	23600	3.0353	-	-
0.6976	23700	3.0371	-	-
0.7005	23800	3.0321	-	-
0.7035	23900	3.0365	-	-
0.7064	24000	3.0302	3.0342	-
0.7093	24100	3.0352	-	-
0.7123	24200	3.0277	-	-
0.7152	24300	3.0402	-	-
0.7182	24400	3.0364	-	-
0.7211	24500	3.0439	3.0336	-
0.7241	24600	3.0396	-	-
0.7270	24700	3.0475	-	-
0.7299	24800	3.0258	-	-
0.7329	24900	3.0345	-	-
0.7358	25000	3.0326	3.0350	-
0.7388	25100	3.0357	-	-
0.7417	25200	3.0413	-	-
0.7447	25300	3.0326	-	-
0.7476	25400	3.0401	-	-
0.7506	25500	3.0313	3.0365	-
0.7535	25600	3.04	-	-
0.7564	25700	3.0382	-	-
0.7594	25800	3.0344	-	-
0.7623	25900	3.0325	-	-
0.7653	26000	3.0475	3.0340	-
0.7682	26100	3.0256	-	-
0.7712	26200	3.0331	-	-
0.7741	26300	3.0325	-	-
0.7770	26400	3.0431	-	-
0.7800	26500	3.04	3.0372	-
0.7829	26600	3.0393	-	-
0.7859	26700	3.0374	-	-
0.7888	26800	3.0406	-	-
0.7918	26900	3.0343	-	-
0.7947	27000	3.0374	3.0325	-
0.7976	27100	3.0262	-	-
0.8006	27200	3.0393	-	-
0.8035	27300	3.0255	-	-
0.8065	27400	3.0305	-	-
0.8094	27500	3.0324	3.0323	-
0.8124	27600	3.0317	-	-
0.8153	27700	3.0267	-	-
0.8182	27800	3.0299	-	-
0.8212	27900	3.0305	-	-
0.8241	28000	3.0336	3.0319	-
0.8271	28100	3.0373	-	-
0.8300	28200	3.0342	-	-
0.8330	28300	3.0436	-	-
0.8359	28400	3.0354	-	-
0.8389	28500	3.0373	3.0291	-
0.8418	28600	3.0292	-	-
0.8447	28700	3.0229	-	-
0.8477	28800	3.0348	-	-
0.8506	28900	3.041	-	-
0.8536	29000	3.031	3.0324	-
0.8565	29100	3.0354	-	-
0.8595	29200	3.0242	-	-
0.8624	29300	3.026	-	-
0.8653	29400	3.0373	-	-
0.8683	29500	3.0298	3.0276	-
0.8712	29600	3.0341	-	-
0.8742	29700	3.0304	-	-
0.8771	29800	3.0241	-	-
0.8801	29900	3.0304	-	-
0.8830	30000	3.0279	3.0278	-
0.8859	30100	3.026	-	-
0.8889	30200	3.0272	-	-
0.8918	30300	3.0372	-	-
0.8948	30400	3.0241	-	-
0.8977	30500	3.0347	3.0276	-
0.9007	30600	3.0335	-	-
0.9036	30700	3.0316	-	-
0.9065	30800	3.0372	-	-
0.9095	30900	3.0234	-	-
0.9124	31000	3.0303	3.0278	-
0.9154	31100	3.0466	-	-
0.9183	31200	3.0391	-	-
0.9213	31300	3.0334	-	-
0.9242	31400	3.029	-	-
0.9272	31500	3.0322	3.0280	-
0.9301	31600	3.0272	-	-
0.9330	31700	3.0315	-	-
0.9360	31800	3.0297	-	-
0.9389	31900	3.0228	-	-
0.9419	32000	3.0246	3.0272	-
0.9448	32100	3.0215	-	-
0.9478	32200	3.0246	-	-
0.9507	32300	3.0333	-	-
0.9536	32400	3.0334	-	-
0.9566	32500	3.029	3.0271	-
0.9595	32600	3.0328	-	-
0.9625	32700	3.0284	-	-
0.9654	32800	3.0327	-	-
0.9684	32900	3.0228	-	-
0.9713	33000	3.0321	3.0267	-
0.9742	33100	3.0277	-	-
0.9772	33200	3.0309	-	-
0.9801	33300	3.0265	-	-
0.9831	33400	3.029	-	-
0.9860	33500	3.0315	3.0257	-
0.9890	33600	3.0233	-	-
0.9919	33700	3.0208	-	-
0.9948	33800	3.0296	-	-
0.9978	33900	3.0271	-	-
1.0007	34000	3.0258	3.0261	-
1.0037	34100	3.0233	-	-
1.0066	34200	3.0283	-	-
1.0096	34300	3.0277	-	-
1.0125	34400	3.0233	-	-
1.0155	34500	3.0296	3.0270	-
1.0184	34600	3.0321	-	-
1.0213	34700	3.0314	-	-
1.0243	34800	3.0458	-	-
1.0272	34900	3.0415	-	-
1.0302	35000	3.0271	3.0261	-
1.0331	35100	3.0252	-	-
1.0361	35200	3.0327	-	-
1.0390	35300	3.0302	-	-
1.0419	35400	3.0264	-	-
1.0449	35500	3.0314	3.0269	-
1.0478	35600	3.0252	-	-
1.0508	35700	3.0302	-	-
1.0537	35800	3.0339	-	-
1.0567	35900	3.0277	-	-
1.0596	36000	3.0314	3.0232	-
1.0625	36100	3.0339	-	-
1.0655	36200	3.0233	-	-
1.0684	36300	3.0264	-	-
1.0714	36400	3.0246	-	-
1.0743	36500	3.0252	3.0242	-
1.0773	36600	3.027	-	-
1.0802	36700	3.0202	-	-
1.0831	36800	3.0245	-	-
1.0861	36900	3.0239	-	-
1.0890	37000	3.022	3.0229	-
1.0920	37100	3.0164	-	-
1.0949	37200	3.0289	-	-
1.0979	37300	3.012	-	-
1.1008	37400	3.027	-	-
1.1038	37500	3.0283	3.0229	-
1.1067	37600	3.0289	-	-
1.1096	37700	3.0264	-	-
1.1126	37800	3.0295	-	-
1.1155	37900	3.0245	-	-
1.1185	38000	3.0301	3.0226	-
1.1214	38100	3.0276	-	-
1.1244	38200	3.0264	-	-
1.1273	38300	3.0264	-	-
1.1302	38400	3.022	-	-
1.1332	38500	3.0308	3.0243	-
1.1361	38600	3.022	-	-
1.1391	38700	3.027	-	-
1.1420	38800	3.0189	-	-
1.1450	38900	3.0282	-	-
1.1479	39000	3.0226	3.0228	-
1.1508	39100	3.0257	-	-
1.1538	39200	3.0201	-	-
1.1567	39300	3.0282	-	-
1.1597	39400	3.0395	-	-
1.1626	39500	3.042	3.0340	-
1.1656	39600	3.0432	-	-
1.1685	39700	3.0214	-	-
1.1714	39800	3.022	-	-
1.1744	39900	3.0245	-	-
1.1773	40000	3.032	3.0276	-
1.1803	40100	3.0389	-	-
1.1832	40200	3.0332	-	-
1.1862	40300	3.0689	-	-
1.1891	40400	3.0476	-	-
1.1921	40500	3.0626	3.0399	-
1.1950	40600	3.0357	-	-
1.1979	40700	3.0282	-	-
1.2009	40800	3.0276	-	-
1.2038	40900	3.032	-	-
1.2068	41000	3.0189	3.0256	-
1.2097	41100	3.0276	-	-
1.2127	41200	3.0276	-	-
1.2156	41300	3.0276	-	-
1.2185	41400	3.0301	-	-
1.2215	41500	3.0238	3.0262	-
1.2244	41600	3.0326	-	-
1.2274	41700	3.0295	-	-
1.2303	41800	3.0307	-	-
1.2333	41900	3.0351	-	-
1.2362	42000	3.0301	3.0242	-
1.2391	42100	3.0238	-	-
1.2421	42200	3.0232	-	-
1.2450	42300	3.0301	-	-
1.2480	42400	3.0201	-	-
1.2509	42500	3.0295	3.0242	-
1.2539	42600	3.0326	-	-
1.2568	42700	3.0232	-	-
1.2597	42800	3.0213	-	-
1.2627	42900	3.0263	-	-
1.2656	43000	3.0351	3.0236	-
1.2686	43100	3.0295	-	-
1.2715	43200	3.0232	-	-
1.2745	43300	3.0207	-	-
1.2774	43400	3.027	-	-
1.2804	43500	3.0276	3.0234	-
1.2833	43600	3.0257	-	-
1.2862	43700	3.0263	-	-
1.2892	43800	3.0163	-	-
1.2921	43900	3.0282	-	-
1.2951	44000	3.0276	3.0270	-
1.2980	44100	3.032	-	-
1.3010	44200	3.0326	-	-
1.3039	44300	3.0288	-	-
1.3068	44400	3.0263	-	-
1.3098	44500	3.0251	3.0231	-
1.3127	44600	3.0188	-	-
1.3157	44700	3.0213	-	-
1.3186	44800	3.0157	-	-
1.3216	44900	3.0238	-	-
1.3245	45000	3.0263	3.0214	-
1.3274	45100	3.0194	-	-
1.3304	45200	3.0301	-	-
1.3333	45300	3.0232	-	-
1.3363	45400	3.0163	-	-
1.3392	45500	3.0157	3.0214	-
1.3422	45600	3.0219	-	-
1.3451	45700	3.0169	-	-
1.3481	45800	3.0232	-	-
1.3510	45900	3.0344	-	-
1.3539	46000	3.0219	3.0209	-
1.3569	46100	3.0183	-	-
1.3598	46200	3.0207	-	-
1.3628	46300	3.0351	-	-
1.3657	46400	3.0244	-	-
1.3687	46500	3.0194	3.0208	-
1.3716	46600	3.0176	-	-
1.3745	46700	3.0244	-	-
1.3775	46800	3.0263	-	-
1.3804	46900	3.0151	-	-
1.3834	47000	3.0226	3.0208	-
1.3863	47100	3.0213	-	-
1.3893	47200	3.0307	-	-
1.3922	47300	3.0244	-	-
1.3951	47400	3.0238	-	-
1.3981	47500	3.0276	3.0207	-
1.4010	47600	3.0282	-	-
1.4040	47700	3.0201	-	-
1.4069	47800	3.0226	-	-
1.4099	47900	3.0263	-	-
1.4128	48000	3.0213	3.0208	-
1.4157	48100	3.0201	-	-
1.4187	48200	3.0207	-	-
1.4216	48300	3.0288	-	-
1.4246	48400	3.0182	-	-
1.4275	48500	3.0263	3.0200	-
1.4305	48600	3.0207	-	-
1.4334	48700	3.0332	-	-
1.4364	48800	3.0201	-	-
1.4393	48900	3.0182	-	-
1.4422	49000	3.0188	3.0200	-
1.4452	49100	3.0213	-	-
1.4481	49200	3.0144	-	-
1.4511	49300	3.0257	-	-
1.4540	49400	3.0201	-	-
1.4570	49500	3.0238	3.0191	-
1.4599	49600	3.0294	-	-
1.4628	49700	3.0226	-	-
1.4658	49800	3.0194	-	-
1.4687	49900	3.0169	-	-
1.4717	50000	3.0207	3.0189	-
1.4746	50100	3.0219	-	-
1.4776	50200	3.0194	-	-
1.4805	50300	3.0126	-	-
1.4834	50400	3.0194	-	-
1.4864	50500	3.0163	3.0208	-
1.4893	50600	3.0182	-	-
1.4923	50700	3.0169	-	-
1.4952	50800	3.0188	-	-
1.4982	50900	3.0219	-	-
1.5011	51000	3.0169	3.0200	-
1.5040	51100	3.0294	-	-
1.5070	51200	3.0207	-	-
1.5099	51300	3.02	-	-
1.5129	51400	3.0207	-	-
1.5158	51500	3.0175	3.0196	-
1.5188	51600	3.0225	-	-
1.5217	51700	3.0213	-	-
1.5247	51800	3.02	-	-
1.5276	51900	3.0232	-	-
1.5305	52000	3.0275	3.0188	-
1.5335	52100	3.0169	-	-
1.5364	52200	3.02	-	-
1.5394	52300	3.0232	-	-
1.5423	52400	3.0125	-	-
1.5453	52500	3.0163	3.0188	-
1.5482	52600	3.0163	-	-
1.5511	52700	3.0269	-	-
1.5541	52800	3.0194	-	-
1.5570	52900	3.0238	-	-
1.5600	53000	3.02	3.0183	-
1.5629	53100	3.0175	-	-
1.5659	53200	3.0157	-	-
1.5688	53300	3.0157	-	-
1.5717	53400	3.0232	-	-
1.5747	53500	3.0238	3.0182	-
1.5776	53600	3.0207	-	-
1.5806	53700	3.0182	-	-
1.5835	53800	3.0213	-	-
1.5865	53900	3.0213	-	-
1.5894	54000	3.0125	3.0181	-
1.5923	54100	3.0119	-	-
1.5953	54200	3.0194	-	-
1.5982	54300	3.0125	-	-
1.6012	54400	3.0257	-	-
1.6041	54500	3.02	3.0181	-
1.6071	54600	3.0232	-	-
1.6100	54700	3.025	-	-
1.6130	54800	3.0263	-	-
1.6159	54900	3.0144	-	-
1.6188	55000	3.0138	3.0177	-
1.6218	55100	3.0207	-	-
1.6247	55200	3.015	-	-
1.6277	55300	3.0175	-	-
1.6306	55400	3.0163	-	-
1.6336	55500	3.0157	3.0172	-
1.6365	55600	3.01	-	-
1.6394	55700	3.0132	-	-
1.6424	55800	3.0232	-	-
1.6453	55900	3.02	-	-
1.6483	56000	3.0163	3.0145	-
1.6512	56100	3.0132	-	-
1.6542	56200	3.0219	-	-
1.6571	56300	3.0188	-	-
1.6600	56400	3.015	-	-
1.6630	56500	3.0157	3.0146	-
1.6659	56600	3.0188	-	-
1.6689	56700	3.0225	-	-
1.6718	56800	3.0094	-	-
1.6748	56900	3.0163	-	-
1.6777	57000	3.0244	3.0158	-
1.6806	57100	3.0157	-	-
1.6836	57200	3.0157	-	-
1.6865	57300	3.015	-	-
1.6895	57400	3.0125	-	-
1.6924	57500	3.0169	3.0151	-
1.6954	57600	3.02	-	-
1.6983	57700	3.0138	-	-
1.7013	57800	3.0163	-	-
1.7042	57900	3.0169	-	-
1.7071	58000	3.0169	3.0153	-
1.7101	58100	3.0119	-	-
1.7130	58200	3.0132	-	-
1.7160	58300	3.0138	-	-
1.7189	58400	3.0225	-	-
1.7219	58500	3.02	3.0148	-
1.7248	58600	3.015	-	-
1.7277	58700	3.0188	-	-
1.7307	58800	3.015	-	-
1.7336	58900	3.015	-	-
1.7366	59000	3.0082	3.0148	-
1.7395	59100	3.0213	-	-
1.7425	59200	3.0094	-	-
1.7454	59300	3.0188	-	-
1.7483	59400	3.0138	-	-
1.7513	59500	3.0138	3.0148	-
1.7542	59600	3.0188	-	-
1.7572	59700	3.0107	-	-
1.7601	59800	3.0119	-	-
1.7631	59900	3.015	-	-
1.7660	60000	3.0194	3.0147	-
1.7689	60100	3.0144	-	-
1.7719	60200	3.0182	-	-
1.7748	60300	3.0213	-	-
1.7778	60400	3.0144	-	-
1.7807	60500	3.0157	3.0147	-
1.7837	60600	3.0132	-	-
1.7866	60700	3.0163	-	-
1.7896	60800	3.0182	-	-
1.7925	60900	3.015	-	-
1.7954	61000	3.0088	3.0148	-
1.7984	61100	3.015	-	-
1.8013	61200	3.0144	-	-
1.8043	61300	3.0113	-	-
1.8072	61400	3.0182	-	-
1.8102	61500	3.0194	3.0147	-
1.8131	61600	3.02	-	-
1.8160	61700	3.0125	-	-
1.8190	61800	3.015	-	-
1.8219	61900	3.0175	-	-
1.8249	62000	3.0119	3.0146	-
1.8278	62100	3.0169	-	-
1.8308	62200	3.0225	-	-
1.8337	62300	3.0207	-	-
1.8366	62400	3.0169	-	-
1.8396	62500	3.0125	3.0170	-
1.8425	62600	3.0188	-	-
1.8455	62700	3.0157	-	-
1.8484	62800	3.0182	-	-
1.8514	62900	3.01	-	-
1.8543	63000	3.0138	3.0148	-
1.8572	63100	3.0094	-	-
1.8602	63200	3.0157	-	-
1.8631	63300	3.02	-	-
1.8661	63400	3.0094	-	-
1.8690	63500	3.0182	3.0145	-
1.8720	63600	3.0157	-	-
1.8749	63700	3.0138	-	-
1.8779	63800	3.0125	-	-
1.8808	63900	3.015	-	-
1.8837	64000	3.0075	3.0144	-
1.8867	64100	3.0157	-	-
1.8896	64200	3.0088	-	-
1.8926	64300	3.0225	-	-
1.8955	64400	3.0175	-	-
1.8985	64500	3.0232	3.0179	-
1.9014	64600	3.0257	-	-
1.9043	64700	3.0175	-	-
1.9073	64800	3.0188	-	-
1.9102	64900	3.0125	-	-
1.9132	65000	3.0225	3.0170	-
1.9161	65100	3.02	-	-
1.9191	65200	3.0213	-	-
1.9220	65300	3.0113	-	-
1.9249	65400	3.0182	-	-
1.9279	65500	3.0232	3.0169	-
1.9308	65600	3.0225	-	-
1.9338	65700	3.0181	-	-
1.9367	65800	3.0181	-	-
1.9397	65900	3.0194	-	-
1.9426	66000	3.0175	3.0168	-
1.9455	66100	3.0181	-	-
1.9485	66200	3.0157	-	-
1.9514	66300	3.0169	-	-
1.9544	66400	3.0181	-	-
1.9573	66500	3.0138	3.0152	-
1.9603	66600	3.0175	-	-
1.9632	66700	3.0156	-	-
1.9662	66800	3.0106	-	-
1.9691	66900	3.01	-	-
1.9720	67000	3.0175	3.0141	-
1.9750	67100	3.0144	-	-
1.9779	67200	3.0131	-	-
1.9809	67300	3.0113	-	-
1.9838	67400	3.0113	-	-
1.9868	67500	3.0125	3.0140	-
1.9897	67600	3.0119	-	-
1.9926	67700	3.02	-	-
1.9956	67800	3.0125	-	-
1.9985	67900	3.01	-	-
2.0015	68000	3.0156	3.0139	-
2.0044	68100	3.0131	-	-
2.0074	68200	3.015	-	-
2.0103	68300	3.0169	-	-
2.0132	68400	3.0169	-	-
2.0162	68500	3.0119	3.0139	-
2.0191	68600	3.0138	-	-
2.0221	68700	3.0138	-	-
2.0250	68800	3.0163	-	-
2.0280	68900	3.0188	-	-
2.0309	69000	3.0188	3.0139	-
2.0338	69100	3.01	-	-
2.0368	69200	3.015	-	-
2.0397	69300	3.0175	-	-
2.0427	69400	3.0144	-	-
2.0456	69500	3.0188	3.0139	-
2.0486	69600	3.0119	-	-
2.0515	69700	3.0131	-	-
2.0545	69800	3.0131	-	-
2.0574	69900	3.0144	-	-
2.0603	70000	3.0144	3.0139	-
2.0633	70100	3.0163	-	-
2.0662	70200	3.0069	-	-
2.0692	70300	3.0213	-	-
2.0721	70400	3.0188	-	-
2.0751	70500	3.0131	3.0108	-
2.0780	70600	3.0131	-	-
2.0809	70700	3.0094	-	-
2.0839	70800	3.0131	-	-
2.0868	70900	3.0119	-	-
2.0898	71000	3.0106	3.0117	-
2.0927	71100	3.015	-	-
2.0957	71200	3.0106	-	-
2.0986	71300	3.0106	-	-
2.1015	71400	3.0113	-	-
2.1045	71500	3.01	3.0117	-
2.1074	71600	3.01	-	-
2.1104	71700	3.0138	-	-
2.1133	71800	3.0088	-	-
2.1163	71900	3.0106	-	-
2.1192	72000	3.0069	3.0111	-
2.1221	72100	3.0056	-	-
2.1251	72200	3.0156	-	-
2.1280	72300	3.0094	-	-
2.1310	72400	3.0081	-	-
2.1339	72500	3.0125	3.0112	-
2.1369	72600	3.0125	-	-
2.1398	72700	3.0144	-	-
2.1428	72800	3.0156	-	-
2.1457	72900	3.0094	-	-
2.1486	73000	3.0075	3.0112	-
2.1516	73100	3.0119	-	-
2.1545	73200	3.0088	-	-
2.1575	73300	3.0119	-	-
2.1604	73400	3.0131	-	-
2.1634	73500	3.0094	3.0110	-
2.1663	73600	3.0063	-	-
2.1692	73700	3.0138	-	-
2.1722	73800	3.0094	-	-
2.1751	73900	3.0144	-	-
2.1781	74000	3.0081	3.0109	-
2.1810	74100	3.0138	-	-
2.1840	74200	3.0144	-	-
2.1869	74300	3.0094	-	-
2.1898	74400	3.0106	-	-
2.1928	74500	3.01	3.0110	-
2.1957	74600	3.0088	-	-
2.1987	74700	3.0081	-	-
2.2016	74800	3.0094	-	-
2.2046	74900	3.01	-	-
2.2075	75000	3.0181	3.0108	-
2.2104	75100	3.0088	-	-
2.2134	75200	3.0144	-	-
2.2163	75300	3.0131	-	-
2.2193	75400	3.01	-	-
2.2222	75500	3.0125	3.0112	-
2.2252	75600	3.0131	-	-
2.2281	75700	3.0125	-	-
2.2311	75800	3.01	-	-
2.2340	75900	3.01	-	-
2.2369	76000	3.0175	3.0112	-
2.2399	76100	3.0094	-	-
2.2428	76200	3.015	-	-
2.2458	76300	3.0075	-	-
2.2487	76400	3.0125	-	-
2.2517	76500	3.0131	3.0109	-
2.2546	76600	3.0175	-	-
2.2575	76700	3.0063	-	-
2.2605	76800	3.0113	-	-
2.2634	76900	3.0106	-	-
2.2664	77000	3.0106	3.0109	-
2.2693	77100	3.0125	-	-
2.2723	77200	3.0163	-	-
2.2752	77300	3.0081	-	-
2.2781	77400	3.0131	-	-
2.2811	77500	3.0119	3.0107	-
2.2840	77600	3.015	-	-
2.2870	77700	3.0125	-	-
2.2899	77800	3.0094	-	-
2.2929	77900	3.01	-	-
2.2958	78000	3.0125	3.0107	-
2.2987	78100	3.0113	-	-
2.3017	78200	3.01	-	-
2.3046	78300	3.0119	-	-
2.3076	78400	3.0131	-	-
2.3105	78500	3.0106	3.0109	-
2.3135	78600	3.0063	-	-
2.3164	78700	3.0113	-	-
2.3194	78800	3.01	-	-
2.3223	78900	3.0131	-	-
2.3252	79000	3.0088	3.0118	-
2.3282	79100	3.0088	-	-
2.3311	79200	3.0106	-	-
2.3341	79300	3.0081	-	-
2.3370	79400	3.0144	-	-
2.3400	79500	3.0138	3.0107	-
2.3429	79600	3.01	-	-
2.3458	79700	3.01	-	-
2.3488	79800	3.0144	-	-
2.3517	79900	3.01	-	-
2.3547	80000	3.0125	3.0104	-
2.3576	80100	3.005	-	-
2.3606	80200	3.0106	-	-
2.3635	80300	3.0094	-	-
2.3664	80400	3.0131	-	-
2.3694	80500	3.0125	3.0104	-
2.3723	80600	3.0106	-	-
2.3753	80700	3.01	-	-
2.3782	80800	3.0119	-	-
2.3812	80900	3.0088	-	-
2.3841	81000	3.0113	3.0103	-
2.3870	81100	3.0094	-	-
2.3900	81200	3.0094	-	-
2.3929	81300	3.0119	-	-
2.3959	81400	3.0094	-	-
2.3988	81500	3.0088	3.0103	-
2.4018	81600	3.0106	-	-
2.4047	81700	3.0088	-	-
2.4077	81800	3.005	-	-
2.4106	81900	3.0113	-	-
2.4135	82000	3.0138	3.0103	-
2.4165	82100	3.0106	-	-
2.4194	82200	3.0094	-	-
2.4224	82300	3.0069	-	-
2.4253	82400	3.0106	-	-
2.4283	82500	3.0106	3.0104	-
2.4312	82600	3.0156	-	-
2.4341	82700	3.0138	-	-
2.4371	82800	3.0113	-	-
2.4400	82900	3.01	-	-
2.4430	83000	3.0138	3.0104	-
2.4459	83100	3.0194	-	-
2.4489	83200	3.0075	-	-
2.4518	83300	3.0088	-	-
2.4547	83400	3.0081	-	-
2.4577	83500	3.0138	3.0104	-
2.4606	83600	3.0081	-	-
2.4636	83700	3.0163	-	-
2.4665	83800	3.0113	-	-
2.4695	83900	3.0063	-	-
2.4724	84000	3.0144	3.0103	-
2.4753	84100	3.0088	-	-
2.4783	84200	3.0144	-	-
2.4812	84300	3.0131	-	-
2.4842	84400	3.0094	-	-
2.4871	84500	3.015	3.0103	-
2.4901	84600	3.0106	-	-
2.4930	84700	3.0119	-	-
2.4960	84800	3.0125	-	-
2.4989	84900	3.0125	-	-
2.5018	85000	3.015	3.0113	-
2.5048	85100	3.0156	-	-
2.5077	85200	3.0194	-	-
2.5107	85300	3.0119	-	-
2.5136	85400	3.0075	-	-
2.5166	85500	3.0156	3.0103	-
2.5195	85600	3.0131	-	-
2.5224	85700	3.0044	-	-
2.5254	85800	3.0075	-	-
2.5283	85900	3.0113	-	-
2.5313	86000	3.0144	3.0103	-
2.5342	86100	3.0144	-	-
2.5372	86200	3.0113	-	-
2.5401	86300	3.0163	-	-
2.5430	86400	3.0169	-	-
2.5460	86500	3.01	3.0101	-
2.5489	86600	3.01	-	-
2.5519	86700	3.0113	-	-
2.5548	86800	3.0138	-	-
2.5578	86900	3.0113	-	-
2.5607	87000	3.0113	3.0101	-
2.5636	87100	3.0081	-	-
2.5666	87200	3.0069	-	-
2.5695	87300	3.0069	-	-
2.5725	87400	3.0088	-	-
2.5754	87500	3.0094	3.0101	-
2.5784	87600	3.0088	-	-
2.5813	87700	3.0119	-	-
2.5843	87800	3.01	-	-
2.5872	87900	3.0119	-	-
2.5901	88000	3.0125	3.0101	-
2.5931	88100	3.0088	-	-
2.5960	88200	3.0138	-	-
2.5990	88300	3.01	-	-
2.6019	88400	3.0119	-	-
2.6049	88500	3.0119	3.0102	-
2.6078	88600	3.0063	-	-
2.6107	88700	3.01	-	-
2.6137	88800	3.0125	-	-
2.6166	88900	3.0175	-	-
2.6196	89000	3.0113	3.0118	-
2.6225	89100	3.02	-	-
2.6255	89200	3.0194	-	-
2.6284	89300	3.0088	-	-
2.6313	89400	3.0144	-	-
2.6343	89500	3.0125	3.0105	-
2.6372	89600	3.0144	-	-
2.6402	89700	3.0163	-	-
2.6431	89800	3.0106	-	-
2.6461	89900	3.0131	-	-
2.6490	90000	3.0119	3.0101	-
2.6519	90100	3.0175	-	-
2.6549	90200	3.0106	-	-
2.6578	90300	3.0138	-	-
2.6608	90400	3.0069	-	-
2.6637	90500	3.0138	3.0100	-
2.6667	90600	3.0044	-	-
2.6696	90700	3.0131	-	-
2.6726	90800	3.01	-	-
2.6755	90900	3.0094	-	-
2.6784	91000	3.0094	3.0100	-
2.6814	91100	3.0156	-	-
2.6843	91200	3.01	-	-
2.6873	91300	3.01	-	-
2.6902	91400	3.01	-	-
2.6932	91500	3.0075	3.0098	-
2.6961	91600	3.0125	-	-
2.6990	91700	3.01	-	-
2.7020	91800	3.0081	-	-
2.7049	91900	3.01	-	-
2.7079	92000	3.0169	3.0097	-
2.7108	92100	3.01	-	-
2.7138	92200	3.0125	-	-
2.7167	92300	3.0131	-	-
2.7196	92400	3.0138	-	-
2.7226	92500	3.0156	3.0099	-
2.7255	92600	3.0113	-	-
2.7285	92700	3.0106	-	-
2.7314	92800	3.0125	-	-
2.7344	92900	3.0038	-	-
2.7373	93000	3.0088	3.0100	-
2.7403	93100	3.0081	-	-
2.7432	93200	3.0119	-	-
2.7461	93300	3.0138	-	-
2.7491	93400	3.0131	-	-
2.7520	93500	3.0106	3.0100	-
2.7550	93600	3.0081	-	-
2.7579	93700	3.0056	-	-
2.7609	93800	3.0106	-	-
2.7638	93900	3.0119	-	-
2.7667	94000	3.0075	3.0099	-
2.7697	94100	3.0119	-	-
2.7726	94200	3.0075	-	-
2.7756	94300	3.0094	-	-
2.7785	94400	3.0119	-	-
2.7815	94500	3.01	3.0099	-
2.7844	94600	3.0106	-	-
2.7873	94700	3.0131	-	-
2.7903	94800	3.0094	-	-
2.7932	94900	3.0075	-	-
2.7962	95000	3.0119	3.0098	-
2.7991	95100	3.0094	-	-
2.8021	95200	3.0138	-	-
2.8050	95300	3.0094	-	-
2.8079	95400	3.0125	-	-
2.8109	95500	3.0081	3.0100	-
2.8138	95600	3.0081	-	-
2.8168	95700	3.0088	-	-
2.8197	95800	3.0113	-	-
2.8227	95900	3.0075	-	-
2.8256	96000	3.0138	3.0097	-
2.8286	96100	3.0106	-	-
2.8315	96200	3.01	-	-
2.8344	96300	3.0119	-	-
2.8374	96400	3.0144	-	-
2.8403	96500	3.0106	3.0099	-
2.8433	96600	3.0094	-	-
2.8462	96700	3.0131	-	-
2.8492	96800	3.0088	-	-
2.8521	96900	3.005	-	-
2.8550	97000	3.0156	3.0099	-
2.8580	97100	3.0094	-	-
2.8609	97200	3.0081	-	-
2.8639	97300	3.0113	-	-
2.8668	97400	3.0138	-	-
2.8698	97500	3.0119	3.0096	-
2.8727	97600	3.0125	-	-
2.8756	97700	3.0094	-	-
2.8786	97800	3.0119	-	-
2.8815	97900	3.0081	-	-
2.8845	98000	3.0106	3.0096	-
2.8874	98100	3.0081	-	-
2.8904	98200	3.0125	-	-
2.8933	98300	3.0075	-	-
2.8962	98400	3.0119	-	-
2.8992	98500	3.0106	3.0096	-
2.9021	98600	3.0081	-	-
2.9051	98700	3.0094	-	-
2.9080	98800	3.0081	-	-
2.9110	98900	3.0144	-	-
2.9139	99000	3.0094	3.0091	-
2.9169	99100	3.0094	-	-
2.9198	99200	3.0094	-	-
2.9227	99300	3.0106	-	-
2.9257	99400	3.01	-	-
2.9286	99500	3.0113	3.0091	-
2.9316	99600	3.0106	-	-
2.9345	99700	3.0106	-	-
2.9375	99800	3.0094	-	-
2.9404	99900	3.0081	-	-
2.9433	100000	3.01	3.0091	-
2.9463	100100	3.0119	-	-
2.9492	100200	3.0106	-	-
2.9522	100300	3.0113	-	-
2.9551	100400	3.0075	-	-
2.9581	100500	3.0094	3.0098	-
2.9610	100600	3.0119	-	-
2.9639	100700	3.0106	-	-
2.9669	100800	3.0088	-	-
2.9698	100900	3.015	-	-
2.9728	101000	3.0106	3.0096	-
2.9757	101100	3.0075	-	-
2.9787	101200	3.0188	-	-
2.9816	101300	3.0088	-	-
2.9845	101400	3.0081	-	-
2.9875	101500	3.0075	3.0097	-
2.9904	101600	3.0119	-	-
2.9934	101700	3.01	-	-
2.9963	101800	3.0075	-	-
2.9993	101900	3.0094	-	-
3.0022	102000	3.0119	3.0097	-
3.0052	102100	3.0113	-	-
3.0081	102200	3.0088	-	-
3.0110	102300	3.0106	-	-
3.0140	102400	3.0113	-	-
3.0169	102500	3.015	3.0097	-
3.0199	102600	3.0088	-	-
3.0228	102700	3.0088	-	-
3.0258	102800	3.0106	-	-
3.0287	102900	3.0113	-	-
3.0316	103000	3.01	3.0094	-
3.0346	103100	3.0113	-	-
3.0375	103200	3.0125	-	-
3.0405	103300	3.0056	-	-
3.0434	103400	3.01	-	-
3.0464	103500	3.01	3.0094	-
3.0493	103600	3.01	-	-
3.0522	103700	3.01	-	-
3.0552	103800	3.0075	-	-
3.0581	103900	3.0063	-	-
3.0611	104000	3.015	3.0096	-
3.0640	104100	3.0063	-	-
3.0670	104200	3.0119	-	-
3.0699	104300	3.0088	-	-
3.0728	104400	3.0113	-	-
3.0758	104500	3.01	3.0095	-
3.0787	104600	3.0081	-	-
3.0817	104700	3.0094	-	-
3.0846	104800	3.0075	-	-
3.0876	104900	3.0113	-	-
3.0905	105000	3.0131	3.0095	-
3.0935	105100	3.0131	-	-
3.0964	105200	3.0131	-	-
3.0993	105300	3.0075	-	-
3.1023	105400	3.0119	-	-
3.1052	105500	3.0094	3.0092	-
3.1082	105600	3.0069	-	-
3.1111	105700	3.0063	-	-
3.1141	105800	3.0094	-	-
3.1170	105900	3.01	-	-
3.1199	106000	3.0113	3.0097	-
3.1229	106100	3.0056	-	-
3.1258	106200	3.01	-	-
3.1288	106300	3.0081	-	-
3.1317	106400	3.0106	-	-
3.1347	106500	3.01	3.0096	-
3.1376	106600	3.0069	-	-
3.1405	106700	3.0119	-	-
3.1435	106800	3.0081	-	-
3.1464	106900	3.0075	-	-
3.1494	107000	3.0081	3.0097	-
3.1523	107100	3.0075	-	-
3.1553	107200	3.0081	-	-
3.1582	107300	3.0125	-	-
3.1611	107400	3.0094	-	-
3.1641	107500	3.0094	3.0092	-
3.1670	107600	3.0175	-	-
3.1700	107700	3.01	-	-
3.1729	107800	3.0113	-	-
3.1759	107900	3.0094	-	-
3.1788	108000	3.0125	3.0091	-
3.1818	108100	3.0069	-	-
3.1847	108200	3.0119	-	-
3.1876	108300	3.0144	-	-
3.1906	108400	3.0075	-	-
3.1935	108500	3.0094	3.0097	-
3.1965	108600	3.0106	-	-
3.1994	108700	3.0144	-	-
3.2024	108800	3.0075	-	-
3.2053	108900	3.0156	-	-
3.2082	109000	3.0044	3.0095	-
3.2112	109100	3.01	-	-
3.2141	109200	3.0106	-	-
3.2171	109300	3.0081	-	-
3.2200	109400	3.0069	-	-
3.2230	109500	3.01	3.0096	-
3.2259	109600	3.01	-	-
3.2288	109700	3.0125	-	-
3.2318	109800	3.0069	-	-
3.2347	109900	3.0081	-	-
3.2377	110000	3.0088	3.0097	-
3.2406	110100	3.0119	-	-
3.2436	110200	3.0131	-	-
3.2465	110300	3.0119	-	-
3.2494	110400	3.0094	-	-
3.2524	110500	3.0094	3.0096	-
3.2553	110600	3.0144	-	-
3.2583	110700	3.0069	-	-
3.2612	110800	3.0131	-	-
3.2642	110900	3.0081	-	-
3.2671	111000	3.01	3.0096	-
3.2701	111100	3.01	-	-
3.2730	111200	3.01	-	-
3.2759	111300	3.0125	-	-
3.2789	111400	3.0113	-	-
3.2818	111500	3.0088	3.0095	-
3.2848	111600	3.0131	-	-
3.2877	111700	3.0125	-	-
3.2907	111800	3.01	-	-
3.2936	111900	3.0113	-	-
3.2965	112000	3.0044	3.0095	-
3.2995	112100	3.0144	-	-
3.3024	112200	3.0081	-	-
3.3054	112300	3.0106	-	-
3.3083	112400	3.0094	-	-
3.3113	112500	3.005	3.0095	-
3.3142	112600	3.0131	-	-
3.3171	112700	3.0081	-	-
3.3201	112800	3.0094	-	-
3.3230	112900	3.0075	-	-
3.3260	113000	3.0113	3.0095	-
3.3289	113100	3.0081	-	-
3.3319	113200	3.0094	-	-
3.3348	113300	3.0081	-	-
3.3377	113400	3.0106	-	-
3.3407	113500	3.0169	3.0095	-
3.3436	113600	3.0056	-	-
3.3466	113700	3.0081	-	-
3.3495	113800	3.0069	-	-
3.3525	113900	3.0094	-	-
3.3554	114000	3.0031	3.0095	-
3.3584	114100	3.0069	-	-
3.3613	114200	3.0075	-	-
3.3642	114300	3.015	-	-
3.3672	114400	3.0081	-	-
3.3701	114500	3.0094	3.0095	-
3.3731	114600	3.0056	-	-
3.3760	114700	3.0081	-	-
3.3790	114800	3.0119	-	-
3.3819	114900	3.0075	-	-
3.3848	115000	3.0063	3.0098	-
3.3878	115100	3.0144	-	-
3.3907	115200	3.0138	-	-
3.3937	115300	3.0081	-	-
3.3966	115400	3.0113	-	-
3.3996	115500	3.0138	3.0098	-
3.4025	115600	3.0081	-	-
3.4054	115700	3.0106	-	-
3.4084	115800	3.0088	-	-
3.4113	115900	3.0106	-	-
3.4143	116000	3.0156	3.0095	-
3.4172	116100	3.0119	-	-
3.4202	116200	3.01	-	-
3.4231	116300	3.0144	-	-
3.4260	116400	3.0131	-	-
3.4290	116500	3.0131	3.0097	-
3.4319	116600	3.0088	-	-
3.4349	116700	3.0113	-	-
3.4378	116800	3.0044	-	-
3.4408	116900	3.01	-	-
3.4437	117000	3.0069	3.0094	-
3.4467	117100	3.0081	-	-
3.4496	117200	3.0125	-	-
3.4525	117300	3.0069	-	-
3.4555	117400	3.0063	-	-
3.4584	117500	3.0044	3.0095	-
3.4614	117600	3.0119	-	-
3.4643	117700	3.0081	-	-
3.4673	117800	3.0081	-	-
3.4702	117900	3.0106	-	-
3.4731	118000	3.0125	3.0095	-
3.4761	118100	3.0138	-	-
3.4790	118200	3.0106	-	-
3.4820	118300	3.0144	-	-
3.4849	118400	3.0081	-	-
3.4879	118500	3.01	3.0095	-
3.4908	118600	3.0075	-	-
3.4937	118700	3.0056	-	-
3.4967	118800	3.0069	-	-
3.4996	118900	3.0094	-	-
3.5026	119000	3.0119	3.0095	-
3.5055	119100	3.0038	-	-
3.5085	119200	3.025	-	-
3.5114	119300	3.0081	-	-
3.5143	119400	3.0119	-	-
3.5173	119500	3.005	3.0095	-
3.5202	119600	3.01	-	-
3.5232	119700	3.0025	-	-
3.5261	119800	3.0088	-	-
3.5291	119900	3.0106	-	-
3.5320	120000	3.0138	3.0095	-
3.5350	120100	3.0056	-	-
3.5379	120200	3.0088	-	-
3.5408	120300	3.0125	-	-
3.5438	120400	3.0125	-	-
3.5467	120500	3.0056	3.0095	-
3.5497	120600	3.0131	-	-
3.5526	120700	3.0119	-	-
3.5556	120800	3.0094	-	-
3.5585	120900	3.0106	-	-
3.5614	121000	3.0113	3.0095	-
3.5644	121100	3.0106	-	-
3.5673	121200	3.0156	-	-
3.5703	121300	3.0069	-	-
3.5732	121400	3.0125	-	-
3.5762	121500	3.0069	3.0095	-
3.5791	121600	3.01	-	-
3.5820	121700	3.0119	-	-
3.5850	121800	3.0088	-	-
3.5879	121900	3.0119	-	-
3.5909	122000	3.0069	3.0095	-
3.5938	122100	3.0069	-	-
3.5968	122200	3.0138	-	-
3.5997	122300	3.01	-	-
3.6026	122400	3.0106	-	-
3.6056	122500	3.0113	3.0095	-
3.6085	122600	3.01	-	-
3.6115	122700	3.005	-	-
3.6144	122800	3.0069	-	-
3.6174	122900	3.0094	-	-
3.6203	123000	3.0119	3.0095	-
3.6233	123100	3.0056	-	-
3.6262	123200	3.0075	-	-
3.6291	123300	3.0106	-	-
3.6321	123400	3.005	-	-
3.6350	123500	3.0081	3.0095	-
3.6380	123600	3.02	-	-
3.6409	123700	3.0094	-	-
3.6439	123800	3.0119	-	-
3.6468	123900	3.0106	-	-
3.6497	124000	3.0125	3.0095	-
3.6527	124100	3.0125	-	-
3.6556	124200	3.0188	-	-
3.6586	124300	3.01	-	-
3.6615	124400	3.0088	-	-
3.6645	124500	3.0169	3.0095	-
3.6674	124600	3.0113	-	-
3.6703	124700	3.0063	-	-
3.6733	124800	3.0094	-	-
3.6762	124900	3.0038	-	-
3.6792	125000	3.0106	3.0091	-
3.6821	125100	3.005	-	-
3.6851	125200	3.0081	-	-
3.6880	125300	3.0075	-	-
3.6909	125400	3.0131	-	-
3.6939	125500	3.0075	3.0091	-
3.6968	125600	3.0131	-	-
3.6998	125700	3.01	-	-
3.7027	125800	3.0075	-	-
3.7057	125900	3.0113	-	-
3.7086	126000	3.0094	3.0091	-
3.7116	126100	3.0081	-	-
3.7145	126200	3.0119	-	-
3.7174	126300	3.0088	-	-
3.7204	126400	3.0063	-	-
3.7233	126500	3.0081	3.0091	-
3.7263	126600	3.0125	-	-
3.7292	126700	3.0125	-	-
3.7322	126800	3.0131	-	-
3.7351	126900	3.0106	-	-
3.7380	127000	3.0088	3.0091	-
3.7410	127100	3.0113	-	-
3.7439	127200	3.0125	-	-
3.7469	127300	3.0094	-	-
3.7498	127400	3.0069	-	-
3.7528	127500	3.0088	3.0091	-
3.7557	127600	3.0163	-	-
3.7586	127700	3.0094	-	-
3.7616	127800	3.0069	-	-
3.7645	127900	3.0063	-	-
3.7675	128000	3.0094	3.0091	-
3.7704	128100	3.01	-	-
3.7734	128200	3.015	-	-
3.7763	128300	3.0163	-	-
3.7792	128400	3.0106	-	-
3.7822	128500	3.0113	3.0091	-
3.7851	128600	3.0069	-	-
3.7881	128700	3.0113	-	-
3.7910	128800	3.0063	-	-
3.7940	128900	3.0088	-	-
3.7969	129000	3.0019	3.0091	-
3.7999	129100	3.0094	-	-
3.8028	129200	3.0038	-	-
3.8057	129300	3.0044	-	-
3.8087	129400	3.0088	-	-
3.8116	129500	3.0113	3.0091	-
3.8146	129600	3.0094	-	-
3.8175	129700	3.0088	-	-
3.8205	129800	3.0113	-	-
3.8234	129900	3.0094	-	-
3.8263	130000	3.0069	3.0091	-
3.8293	130100	3.0113	-	-
3.8322	130200	3.0081	-	-
3.8352	130300	3.0125	-	-
3.8381	130400	3.0156	-	-
3.8411	130500	3.0069	3.0091	-
3.8440	130600	3.0131	-	-
3.8469	130700	3.0131	-	-
3.8499	130800	3.005	-	-
3.8528	130900	3.0106	-	-
3.8558	131000	3.0119	3.0089	-
3.8587	131100	3.0081	-	-
3.8617	131200	3.0088	-	-
3.8646	131300	3.0075	-	-
3.8675	131400	3.0056	-	-

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",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}