Hugging Face's logo

youssefkhalil320
/
gte-small-pairscore

Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:510287
loss:CoSENTLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
gte-small-pairscore / README.md
youssefkhalil320's picture
youssefkhalil320
Upload folder using huggingface_hub
01cce3b verified
preview code
|
raw
history blame contribute delete
38 kB
metadata
base_model: thenlper/gte-small
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:510287
  - loss:CoSENTLoss
widget:
  - source_sentence: bag
    sentences:
      - bag
      - summer colors bag
      - carry all bag
  - source_sentence: bean bag
    sentences:
      - bag
      - havan bag
      - black yellow shoes
  - source_sentence: pyramid shaped cushion mattress
    sentences:
      - dress
      - silver bag
      - women shoes
  - source_sentence: handcrafted rug
    sentences:
      - amaga  cross bag - white
      - handcrafted boots
      - polyester top
  - source_sentence: bean bag
    sentences:
      - bag
      - v-neck dress
      - bag
model-index:
  - name: gte-small-pair_score
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: -0.17233834277204704
            name: Pearson Cosine
          - type: spearman_cosine
            value: -0.2198666606268324
            name: Spearman Cosine
          - type: pearson_manhattan
            value: -0.18762372004757433
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: -0.2263824285497944
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: -0.1815229012953811
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: -0.21986651824620543
            name: Spearman Euclidean
          - type: pearson_dot
            value: -0.17233841453151344
            name: Pearson Dot
          - type: spearman_dot
            value: -0.21986648743251272
            name: Spearman Dot
          - type: pearson_max
            value: -0.17233834277204704
            name: Pearson Max
          - type: spearman_max
            value: -0.21986648743251272
            name: Spearman Max

gte-small-pair_score

This is a sentence-transformers model finetuned from thenlper/gte-small. 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: thenlper/gte-small
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 384 tokens
  • Similarity Function: Cosine Similarity
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'bean bag',
    'bag',
    'v-neck dress',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Metric Value
pearson_cosine -0.1723
spearman_cosine -0.2199
pearson_manhattan -0.1876
spearman_manhattan -0.2264
pearson_euclidean -0.1815
spearman_euclidean -0.2199
pearson_dot -0.1723
spearman_dot -0.2199
pearson_max -0.1723
spearman_max -0.2199

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
  • load_best_model_at_end: 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: True
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • dispatch_batches: None
  • split_batches: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • eval_use_gather_object: False
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional

Training Logs

Click to expand
Epoch Step Training Loss loss sts-dev_spearman_cosine
0 0 - - -0.2199
0.0063 100 6.3669 6.6513 -
0.0125 200 6.1795 6.2541 -
0.0188 300 5.893 5.7733 -
0.0251 400 5.5099 5.3626 -
0.0314 500 5.1589 4.9902 -
0.0376 600 4.8599 4.6523 -
0.0439 700 4.6075 4.4233 -
0.0502 800 4.3831 4.2431 -
0.0564 900 4.1737 4.1350 -
0.0627 1000 4.0266 4.0327 -
0.0690 1100 3.9526 3.9281 -
0.0752 1200 3.8773 3.8735 -
0.0815 1300 3.7856 3.7779 -
0.0878 1400 3.5994 3.7054 -
0.0941 1500 3.7067 3.6155 -
0.1003 1600 3.5471 3.5798 -
0.1066 1700 3.6679 3.4654 -
0.1129 1800 3.4484 3.4175 -
0.1191 1900 3.377 3.4129 -
0.1254 2000 3.4259 3.3347 -
0.1317 2100 3.4832 3.2113 -
0.1380 2200 3.3043 3.1641 -
0.1442 2300 3.2344 3.1529 -
0.1505 2400 3.1238 3.2577 -
0.1568 2500 3.1456 3.0678 -
0.1630 2600 3.0223 3.0006 -
0.1693 2700 3.2046 2.9682 -
0.1756 2800 3.0866 3.0524 -
0.1819 2900 2.9271 3.0573 -
0.1881 3000 2.7692 3.0558 -
0.1944 3100 3.1498 2.7866 -
0.2007 3200 3.0683 2.8478 -
0.2069 3300 2.5776 2.9459 -
0.2132 3400 2.9394 2.7133 -
0.2195 3500 2.6996 2.8582 -
0.2257 3600 2.569 2.8092 -
0.2320 3700 2.6535 2.7977 -
0.2383 3800 2.6679 2.8578 -
0.2446 3900 2.592 2.8251 -
0.2508 4000 2.4931 2.5976 -
0.2571 4100 2.3012 2.9260 -
0.2634 4200 2.4728 2.7869 -
0.2696 4300 2.4391 2.8987 -
0.2759 4400 2.3825 2.7804 -
0.2822 4500 2.6257 2.8309 -
0.2885 4600 2.4304 3.2419 -
0.2947 4700 3.0246 2.5732 -
0.3010 4800 2.6894 2.8058 -
0.3073 4900 2.5333 2.4582 -
0.3135 5000 2.3268 2.8622 -
0.3198 5100 2.6996 2.7515 -
0.3261 5200 2.8175 2.5842 -
0.3324 5300 2.1244 2.7252 -
0.3386 5400 2.7331 2.5053 -
0.3449 5500 2.3226 2.2430 -
0.3512 5600 2.0706 2.6055 -
0.3574 5700 2.2461 2.8949 -
0.3637 5800 2.6365 2.5272 -
0.3700 5900 2.7119 2.4331 -
0.3762 6000 2.6146 2.3858 -
0.3825 6100 2.1998 2.6891 -
0.3888 6200 2.5076 2.3827 -
0.3951 6300 2.5244 2.6522 -
0.4013 6400 2.0613 2.4750 -
0.4076 6500 2.465 2.5254 -
0.4139 6600 2.3201 2.2249 -
0.4201 6700 2.234 2.5168 -
0.4264 6800 2.1277 2.5358 -
0.4327 6900 2.3801 2.4992 -
0.4390 7000 2.1443 2.4043 -
0.4452 7100 1.9136 2.3874 -
0.4515 7200 2.3067 2.6475 -
0.4578 7300 2.1464 2.4704 -
0.4640 7400 2.2151 2.5199 -
0.4703 7500 2.4653 2.5293 -
0.4766 7600 2.4425 2.1264 -
0.4828 7700 2.3138 2.1810 -
0.4891 7800 2.247 2.1404 -
0.4954 7900 2.1621 2.2123 -
0.5017 8000 2.1338 2.5108 -
0.5079 8100 2.1846 2.1493 -
0.5142 8200 2.1167 2.2879 -
0.5205 8300 2.2143 2.1664 -
0.5267 8400 2.3152 2.1072 -
0.5330 8500 1.7618 2.0324 -
0.5393 8600 2.0777 2.4468 -
0.5456 8700 2.1573 2.2053 -
0.5518 8800 1.9831 2.3277 -
0.5581 8900 1.9083 1.9949 -
0.5644 9000 1.932 1.9848 -
0.5706 9100 2.3223 1.9192 -
0.5769 9200 1.7583 2.0066 -
0.5832 9300 1.6394 2.0322 -
0.5895 9400 1.973 2.1010 -
0.5957 9500 2.2377 2.1176 -
0.6020 9600 2.2269 2.0027 -
0.6083 9700 1.971 1.9329 -
0.6145 9800 1.8982 1.9797 -
0.6208 9900 2.2853 1.8433 -
0.6271 10000 1.6657 2.0091 -
0.6333 10100 2.0732 1.7602 -
0.6396 10200 1.6951 1.8849 -
0.6459 10300 1.6548 2.0066 -
0.6522 10400 1.7187 1.9644 -
0.6584 10500 2.1948 1.8392 -
0.6647 10600 1.9756 1.8404 -
0.6710 10700 1.7644 1.9101 -
0.6772 10800 1.6295 1.9440 -
0.6835 10900 1.7687 1.9031 -
0.6898 11000 1.8203 1.9650 -
0.6961 11100 2.3055 1.8432 -
0.7023 11200 1.8294 1.7364 -
0.7086 11300 2.0026 1.7894 -
0.7149 11400 1.9916 1.8343 -
0.7211 11500 1.8698 1.8079 -
0.7274 11600 1.5213 1.6849 -
0.7337 11700 1.7462 1.7328 -
0.7400 11800 1.3519 1.8370 -
0.7462 11900 1.4935 1.7247 -
0.7525 12000 1.1721 1.6529 -
0.7588 12100 2.2432 1.6329 -
0.7650 12200 1.6931 1.6563 -
0.7713 12300 1.2736 1.6984 -
0.7776 12400 1.7063 1.6574 -
0.7838 12500 1.7921 1.7760 -
0.7901 12600 1.875 1.7149 -
0.7964 12700 1.4435 1.8085 -
0.8027 12800 1.5271 1.7247 -
0.8089 12900 1.618 1.6542 -
0.8152 13000 1.9788 1.5686 -
0.8215 13100 1.8213 1.5603 -
0.8277 13200 1.3661 1.6376 -
0.8340 13300 1.3852 1.5953 -
0.8403 13400 1.4673 1.6346 -
0.8466 13500 1.6684 1.5818 -
0.8528 13600 1.686 1.5840 -
0.8591 13700 1.4397 1.5855 -
0.8654 13800 1.5973 1.7207 -
0.8716 13900 1.221 1.6381 -
0.8779 14000 1.2082 1.6335 -
0.8842 14100 1.5399 1.6434 -
0.8904 14200 1.5265 1.7266 -
0.8967 14300 0.9321 1.5981 -
0.9030 14400 1.1133 1.6126 -
0.9093 14500 1.0754 1.6227 -
0.9155 14600 1.3486 1.6143 -
0.9218 14700 1.6338 1.5452 -
0.9281 14800 1.389 1.6099 -
0.9343 14900 1.3776 1.6435 -
0.9406 15000 1.8714 1.5377 -
0.9469 15100 1.1286 1.6326 -
0.9532 15200 1.4029 1.6256 -
0.9594 15300 1.7772 1.5221 -
0.9657 15400 1.3415 1.5604 -
0.9720 15500 1.1088 1.5749 -
0.9782 15600 1.4602 1.4941 -
0.9845 15700 1.867 1.3731 -
0.9908 15800 1.4541 1.4206 -
0.9971 15900 1.1966 1.4982 -
1.0033 16000 1.1447 1.5121 -
1.0096 16100 1.1266 1.4103 -
1.0159 16200 1.1971 1.5044 -
1.0221 16300 1.3376 1.5337 -
1.0284 16400 1.7977 1.5712 -
1.0347 16500 1.6946 1.5323 -
1.0409 16600 0.8674 1.4462 -
1.0472 16700 1.6447 1.4831 -
1.0535 16800 1.2709 1.5756 -
1.0598 16900 1.5217 1.5060 -
1.0660 17000 1.2986 1.4834 -
1.0723 17100 0.9976 1.4841 -
1.0786 17200 1.3457 1.4228 -
1.0848 17300 0.987 1.3807 -
1.0911 17400 1.2714 1.3471 -
1.0974 17500 1.298 1.4134 -
1.1037 17600 0.9522 1.4225 -
1.1099 17700 1.0634 1.4474 -
1.1162 17800 1.2889 1.4679 -
1.1225 17900 1.7532 1.3757 -
1.1287 18000 1.6613 1.3808 -
1.1350 18100 1.1765 1.3903 -
1.1413 18200 1.2787 1.3921 -
1.1476 18300 1.2532 1.3519 -
1.1538 18400 1.8056 1.2984 -
1.1601 18500 1.0985 1.3322 -
1.1664 18600 1.8665 1.4060 -
1.1726 18700 1.2427 1.3775 -
1.1789 18800 1.1241 1.3168 -
1.1852 18900 1.2348 1.3539 -
1.1914 19000 1.1709 1.3540 -
1.1977 19100 0.8844 1.3142 -
1.2040 19200 1.0035 1.3781 -
1.2103 19300 1.4279 1.2615 -
1.2165 19400 1.3327 1.2696 -
1.2228 19500 0.993 1.3170 -
1.2291 19600 0.7869 1.2967 -
1.2353 19700 0.985 1.3057 -
1.2416 19800 1.1603 1.2797 -
1.2479 19900 1.2469 1.2394 -
1.2542 20000 1.521 1.2309 -
1.2604 20100 1.2632 1.2353 -
1.2667 20200 1.3621 1.2433 -
1.2730 20300 1.5145 1.3065 -
1.2792 20400 1.3708 1.2423 -
1.2855 20500 1.1716 1.2923 -
1.2918 20600 1.419 1.2194 -
1.2980 20700 1.1644 1.2369 -
1.3043 20800 1.6589 1.1971 -
1.3106 20900 1.0299 1.2343 -
1.3169 21000 1.3452 1.2725 -
1.3231 21100 1.4234 1.2416 -
1.3294 21200 1.2496 1.3609 -
1.3357 21300 1.2133 1.2893 -
1.3419 21400 0.8682 1.2353 -
1.3482 21500 0.9499 1.2423 -
1.3545 21600 1.2896 1.1797 -
1.3608 21700 1.2392 1.1962 -
1.3670 21800 0.9206 1.2483 -
1.3733 21900 1.174 1.2328 -
1.3796 22000 1.6361 1.1558 -
1.3858 22100 0.8284 1.2711 -
1.3921 22200 1.2814 1.2462 -
1.3984 22300 1.1595 1.2613 -
1.4047 22400 1.3129 1.1816 -
1.4109 22500 1.1353 1.2454 -
1.4172 22600 1.3302 1.1398 -
1.4235 22700 1.1591 1.2936 -
1.4297 22800 0.6551 1.2345 -
1.4360 22900 1.2884 1.1629 -
1.4423 23000 1.1769 1.2340 -
1.4485 23100 1.1331 1.2036 -
1.4548 23200 1.1008 1.1685 -
1.4611 23300 1.1487 1.1274 -
1.4674 23400 0.7753 1.1738 -
1.4736 23500 1.3236 1.2377 -
1.4799 23600 0.919 1.2018 -
1.4862 23700 0.8516 1.2297 -
1.4924 23800 1.092 1.1629 -
1.4987 23900 0.673 1.2162 -
1.5050 24000 0.994 1.1778 -
1.5113 24100 0.8766 1.1902 -
1.5175 24200 1.3818 1.1638 -
1.5238 24300 1.1215 1.1666 -
1.5301 24400 0.8485 1.1907 -
1.5363 24500 1.1033 1.2318 -
1.5426 24600 0.9001 1.2113 -
1.5489 24700 1.3256 1.2309 -
1.5552 24800 0.8162 1.2139 -
1.5614 24900 0.5741 1.2375 -
1.5677 25000 0.883 1.2039 -
1.5740 25100 1.1212 1.1428 -
1.5802 25200 0.8229 1.2338 -
1.5865 25300 0.8856 1.1461 -
1.5928 25400 1.2323 1.1569 -
1.5990 25500 0.9724 1.1549 -
1.6053 25600 1.0791 1.1161 -
1.6116 25700 0.9845 1.1061 -
1.6179 25800 1.1591 1.1103 -
1.6241 25900 1.116 1.1405 -
1.6304 26000 1.2221 1.1528 -
1.6367 26100 0.9085 1.1396 -
1.6429 26200 0.9543 1.1953 -
1.6492 26300 1.1855 1.1792 -
1.6555 26400 1.0583 1.1666 -
1.6618 26500 0.6583 1.1152 -
1.6680 26600 1.3067 1.0397 -
1.6743 26700 1.5336 1.1244 -
1.6806 26800 0.614 1.1273 -
1.6868 26900 1.0336 1.0680 -
1.6931 27000 1.462 1.0983 -
1.6994 27100 0.8858 1.0672 -
1.7056 27200 0.7494 1.1624 -
1.7119 27300 0.8152 1.0928 -
1.7182 27400 0.7785 1.0952 -
1.7245 27500 1.0471 1.0999 -
1.7307 27600 1.0994 0.9880 -
1.7370 27700 1.0706 1.0416 -
1.7433 27800 1.1158 1.0676 -
1.7495 27900 0.9893 1.0289 -
1.7558 28000 1.2939 1.0150 -
1.7621 28100 0.9543 1.0767 -
1.7684 28200 0.7907 1.0717 -
1.7746 28300 0.92 1.1133 -
1.7809 28400 0.8636 1.0702 -
1.7872 28500 0.9118 1.0536 -
1.7934 28600 1.2643 1.1354 -
1.7997 28700 0.8284 1.0715 -
1.8060 28800 0.8447 1.0458 -
1.8123 28900 1.2102 1.1001 -
1.8185 29000 1.1042 1.0364 -
1.8248 29100 0.9638 1.0947 -
1.8311 29200 0.6847 1.0312 -
1.8373 29300 1.7671 1.0470 -
1.8436 29400 0.7525 1.1158 -
1.8499 29500 1.2843 1.0140 -
1.8561 29600 0.6844 1.1604 -
1.8624 29700 1.2824 1.0052 -
1.8687 29800 1.314 1.0323 -
1.8750 29900 1.0796 1.0885 -
1.8812 30000 1.0012 1.0267 -
1.8875 30100 1.4932 1.0438 -
1.8938 30200 1.0404 1.0163 -
1.9000 30300 0.614 1.0367 -
1.9063 30400 1.2676 1.0803 -
1.9126 30500 1.2431 1.0428 -
1.9189 30600 1.4063 1.0319 -
1.9251 30700 0.7787 0.9666 -
1.9314 30800 1.0311 1.0376 -
1.9377 30900 1.0353 0.9869 -
1.9439 31000 1.2221 0.9686 -
1.9502 31100 0.5806 0.9663 -
1.9565 31200 0.6919 0.9838 -
1.9628 31300 0.8028 0.9759 -
1.9690 31400 0.8365 0.9641 -
1.9753 31500 0.7518 1.0081 -
1.9816 31600 1.0654 0.9843 -
1.9878 31700 0.8637 0.9635 -
1.9941 31800 0.8663 0.9538 -
2.0004 31900 0.8524 0.9628 -
2.0066 32000 1.2748 0.9382 -
2.0129 32100 0.8138 0.9461 -
2.0192 32200 0.4484 0.9221 -
2.0255 32300 0.8839 0.9567 -
2.0317 32400 0.7599 0.9440 -
2.0380 32500 0.8665 0.9652 -
2.0443 32600 0.5802 0.9475 -
2.0505 32700 0.7731 0.9197 -
2.0568 32800 0.7913 1.0024 -
2.0631 32900 0.7758 0.9257 -
2.0694 33000 0.7468 0.9663 -
2.0756 33100 0.9947 0.9788 -
2.0819 33200 0.5618 0.9480 -
2.0882 33300 0.8805 0.9520 -
2.0944 33400 0.9755 0.9288 -
2.1007 33500 0.8942 0.9234 -
2.1070 33600 0.7242 0.9413 -
2.1133 33700 0.6231 0.9660 -
2.1195 33800 0.7144 0.8901 -
2.1258 33900 0.7139 0.9536 -
2.1321 34000 0.6378 0.9370 -
2.1383 34100 0.7607 0.9209 -
2.1446 34200 0.8667 0.9734 -
2.1509 34300 0.8533 0.9177 -
2.1571 34400 0.6395 0.9285 -
2.1634 34500 0.7377 0.9047 -
2.1697 34600 0.7787 0.9968 -
2.1760 34700 0.6561 0.9653 -
2.1822 34800 0.6169 0.9404 -
2.1885 34900 0.7643 0.9397 -
2.1948 35000 0.998 0.9152 -
2.2010 35100 0.8246 0.9513 -
2.2073 35200 0.6655 0.9354 -
2.2136 35300 0.9279 0.9034 -
2.2199 35400 0.4239 0.9607 -
2.2261 35500 1.0023 0.8732 -
2.2324 35600 0.7426 0.8883 -
2.2387 35700 0.8675 0.9296 -
2.2449 35800 0.9226 0.9146 -
2.2512 35900 0.4944 0.9145 -
2.2575 36000 0.9663 0.8893 -
2.2637 36100 0.6455 0.9238 -
2.2700 36200 0.9673 0.8943 -
2.2763 36300 0.7974 0.8620 -
2.2826 36400 0.9777 0.8812 -
2.2888 36500 0.8741 0.8862 -
2.2951 36600 0.9642 0.9157 -
2.3014 36700 0.9225 0.8784 -
2.3076 36800 0.6789 0.9066 -
2.3139 36900 0.6726 0.9091 -
2.3202 37000 0.7326 0.9203 -
2.3265 37100 1.007 0.9125 -
2.3327 37200 0.6134 0.8837 -
2.3390 37300 0.9051 0.8945 -
2.3453 37400 0.837 0.8740 -
2.3515 37500 0.7615 0.9165 -
2.3578 37600 0.8304 0.9107 -
2.3641 37700 0.6255 0.8891 -
2.3704 37800 0.6775 0.8908 -
2.3766 37900 0.7159 0.8590 -
2.3829 38000 0.6422 0.8559 -
2.3892 38100 0.7773 0.8601 -
2.3954 38200 0.5457 0.8856 -
2.4017 38300 0.4997 0.8785 -
2.4080 38400 0.6319 0.8850 -
2.4142 38500 0.7096 0.8234 -

Framework Versions

  • Python: 3.8.10
  • Sentence Transformers: 3.1.1
  • Transformers: 4.45.1
  • PyTorch: 2.4.0+cu121
  • Accelerate: 0.34.2
  • Datasets: 3.0.1
  • Tokenizers: 0.20.0

Citation

BibTeX

Sentence Transformers 

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

CoSENTLoss 

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}