Hugging Face's logo

dejasi5459
/
clip-fashionAssign-embeddings-final

Sentence Similarity
sentence-transformers
Safetensors
clip
feature-extraction
dense
Generated from Trainer
dataset_size:1600
loss:MultipleNegativesRankingLoss
Eval Results
Model card Files
xet
Community
clip-fashionAssign-embeddings-final / README.md
dejasi5459's picture
dejasi5459
Add new SentenceTransformer model
2c7cad1 verified
preview code
|
raw
history blame contribute delete
76.6 kB
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:1600
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/clip-ViT-L-14
widget:
  - source_sentence: >-
      Women , Accessories , Jewellery , Jewellery Set , Blue , Winter , Casual ,
      Adrika Purple Teracotta  Jewellery Set
    sentences:
      - Men , Eyeshadow , Summer , Smart Casual
      - Men , Shoe Accessories , Fall , Formal
      - Women , Capris , Winter , Travel
  - source_sentence: >-
      Men , Footwear , Shoes , Sports Shoes , White , Summer , Sports , Puma
      Men's Tarun White Navy Silver Red Shoe
    sentences:
      - Unisex , Shoe Laces , Spring , Casual
      - Women , Sandals , Winter , Formal
      - Women , Leggings , Winter , Formal
  - source_sentence: >-
      Boys , Apparel , Topwear , Tshirts , Navy Blue , Fall , Casual , Chhota
      Bheem Kids Boys I Like to Paint Navy Blue T-shirt
    sentences:
      - Men , Boxers , Fall , Smart Casual
      - Girls , Rain Trousers , Spring , Sports
      - Women , Blazers , Fall , Smart Casual
  - source_sentence: >-
      Women , Apparel , Innerwear , Bra , Black , Winter , Casual , Hanes Women
      Black Concealing Petals Wirefree Moulded Bra
    sentences:
      - Men , Bangle , Spring , Smart Casual
      - Men , Tablet Sleeve , Winter , Smart Casual
      - Women , Laptop Bag , Fall , Travel
  - source_sentence: >-
      Men , Footwear , Shoes , Casual Shoes , White , Fall , Casual , Lee Cooper
      Men White Shoes
    sentences:
      - Women , Basketballs , Winter , Smart Casual
      - Men , Mobile Pouch , Spring , Smart Casual
      - Men , Bangle , Summer , Smart Casual
datasets:
  - dejasi5459/fashion-product-images-small
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on sentence-transformers/clip-ViT-L-14
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: fashion train
          type: fashion-train
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: fashion valid
          type: fashion-valid
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy

SentenceTransformer based on sentence-transformers/clip-ViT-L-14

This is a sentence-transformers model finetuned from sentence-transformers/clip-ViT-L-14 on the fashion-product-images-small dataset. It maps sentences & paragraphs to a None-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 Sources

Full Model Architecture 

SentenceTransformer(
  (0): CLIPModel()
)

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("dejasi5459/clip-fashionAssign-embeddings-final")
# Run inference
sentences = [
    'Men , Footwear , Shoes , Casual Shoes , White , Fall , Casual , Lee Cooper Men White Shoes',
    'Women , Basketballs , Winter , Smart Casual',
    'Men , Bangle , Summer , Smart Casual',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.3406, 0.3490],
#         [0.3406, 1.0000, 0.5437],
#         [0.3490, 0.5437, 1.0000]])

Evaluation

Metrics

Triplet

Metric fashion-train fashion-valid
cosine_accuracy 1.0 1.0

Training Details

Training Dataset

fashion-product-images-small

  • Dataset: fashion-product-images-small at b19f176
  • Size: 1,600 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type PIL.PngImagePlugin.PngImageFile string string
    details
    • min: 19 tokens
    • mean: 24.39 tokens
    • max: 44 tokens
    • min: 9 tokens
    • mean: 10.34 tokens
    • max: 14 tokens
  • Samples:
    anchor positive negative
    Men , Apparel , Topwear , Tshirts , White , Summer , Casual , Reid & Taylor Men White T-shirt Women , Leggings , Spring , Smart Casual
    Men , Accessories , Watches , Watches , White , Winter , Casual , Titan Men White Watch Women , Shoe Laces , Spring , Smart Casual
    Unisex , Footwear , Sandal , Sandals , Purple , Fall , Casual , Crocs Kids Band Club Purple Floater Unisex , Basketballs , Winter , Smart Casual
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

fashion-product-images-small

  • Dataset: fashion-product-images-small at b19f176
  • Size: 200 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 200 samples:
    anchor positive negative
    type PIL.PngImagePlugin.PngImageFile string string
    details
    • min: 19 tokens
    • mean: 24.66 tokens
    • max: 47 tokens
    • min: 9 tokens
    • mean: 10.27 tokens
    • max: 14 tokens
  • Samples:
    anchor positive negative
    Unisex , Accessories , Watches , Watches , Black , Winter , Casual , ADIDAS Unisex Digital Black Watch Unisex , Umbrellas , Fall , Smart Casual
    Men , Apparel , Topwear , Shirts , Yellow , Summer , Casual , Lee Men Check Yellow Shirts Women , Jeggings , Winter , Smart Casual
    Men , Apparel , Topwear , Shirts , Black , Fall , Casual , Highlander Men Black Check Shirt Women , Trousers , Summer , Smart Casual
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: epoch
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 32
  • learning_rate: 1e-05
  • num_train_epochs: 10

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: epoch
  • 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: 1e-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: 10
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.0
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: False
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • hub_revision: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • liger_kernel_config: None
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Click to expand
Epoch Step Training Loss Validation Loss fashion-train_cosine_accuracy fashion-valid_cosine_accuracy
-1 -1 - - 1.0 0.9900
0.02 1 1.9163 - - -
0.04 2 2.0686 - - -
0.06 3 2.0331 - - -
0.08 4 1.8132 - - -
0.1 5 1.9042 - - -
0.12 6 1.7977 - - -
0.14 7 2.0628 - - -
0.16 8 1.9983 - - -
0.18 9 1.7732 - - -
0.2 10 1.8224 - - -
0.22 11 1.727 - - -
0.24 12 1.6821 - - -
0.26 13 1.688 - - -
0.28 14 1.7912 - - -
0.3 15 1.7011 - - -
0.32 16 1.518 - - -
0.34 17 1.6247 - - -
0.36 18 1.5795 - - -
0.38 19 1.7838 - - -
0.4 20 1.7153 - - -
0.42 21 1.6448 - - -
0.44 22 1.5956 - - -
0.46 23 1.5494 - - -
0.48 24 1.3828 - - -
0.5 25 1.434 - - -
0.52 26 1.5452 - - -
0.54 27 1.5098 - - -
0.56 28 1.472 - - -
0.58 29 1.5855 - - -
0.6 30 1.4831 - - -
0.62 31 1.4432 - - -
0.64 32 1.364 - - -
0.66 33 1.4233 - - -
0.68 34 1.5127 - - -
0.7 35 1.6147 - - -
0.72 36 1.3725 - - -
0.74 37 1.4327 - - -
0.76 38 1.3983 - - -
0.78 39 1.5343 - - -
0.8 40 1.3662 - - -
0.82 41 1.3356 - - -
0.84 42 1.4722 - - -
0.86 43 1.3679 - - -
0.88 44 1.2656 - - -
0.9 45 1.4959 - - -
0.92 46 1.3207 - - -
0.94 47 1.3888 - - -
0.96 48 1.259 - - -
0.98 49 1.2591 - - -
1.0 50 1.3237 1.2671 - -
1.02 51 1.2336 - - -
1.04 52 1.3364 - - -
1.06 53 1.3251 - - -
1.08 54 1.2173 - - -
1.1 55 1.2668 - - -
1.12 56 1.0908 - - -
1.1400 57 1.1957 - - -
1.16 58 1.2633 - - -
1.18 59 1.2269 - - -
1.2 60 1.2083 - - -
1.22 61 1.0891 - - -
1.24 62 1.11 - - -
1.26 63 1.2721 - - -
1.28 64 1.3018 - - -
1.3 65 1.1657 - - -
1.32 66 1.3642 - - -
1.34 67 1.3166 - - -
1.3600 68 1.2567 - - -
1.38 69 1.2287 - - -
1.4 70 1.2056 - - -
1.42 71 1.0841 - - -
1.44 72 0.9462 - - -
1.46 73 1.2305 - - -
1.48 74 1.1221 - - -
1.5 75 0.9881 - - -
1.52 76 1.0558 - - -
1.54 77 1.0167 - - -
1.56 78 1.3791 - - -
1.58 79 1.341 - - -
1.6 80 1.1092 - - -
1.62 81 1.1882 - - -
1.6400 82 0.9997 - - -
1.6600 83 1.2135 - - -
1.6800 84 0.9958 - - -
1.7 85 1.0348 - - -
1.72 86 1.106 - - -
1.74 87 1.0195 - - -
1.76 88 1.3001 - - -
1.78 89 1.0954 - - -
1.8 90 1.0328 - - -
1.8200 91 1.0133 - - -
1.8400 92 1.0182 - - -
1.8600 93 1.0294 - - -
1.88 94 1.0227 - - -
1.9 95 1.0773 - - -
1.92 96 1.0337 - - -
1.94 97 1.1762 - - -
1.96 98 0.8714 - - -
1.98 99 0.9945 - - -
2.0 100 1.1825 1.0181 - -
2.02 101 0.9557 - - -
2.04 102 1.07 - - -
2.06 103 0.8845 - - -
2.08 104 1.1158 - - -
2.1 105 1.0213 - - -
2.12 106 0.9394 - - -
2.14 107 1.0508 - - -
2.16 108 0.8876 - - -
2.18 109 0.8878 - - -
2.2 110 1.0269 - - -
2.22 111 0.8653 - - -
2.24 112 0.9637 - - -
2.26 113 0.968 - - -
2.2800 114 0.9857 - - -
2.3 115 0.9416 - - -
2.32 116 1.0107 - - -
2.34 117 0.9104 - - -
2.36 118 1.003 - - -
2.38 119 1.0253 - - -
2.4 120 0.9514 - - -
2.42 121 0.9381 - - -
2.44 122 0.9415 - - -
2.46 123 0.8456 - - -
2.48 124 0.7915 - - -
2.5 125 1.0228 - - -
2.52 126 0.9115 - - -
2.54 127 0.8338 - - -
2.56 128 0.9415 - - -
2.58 129 0.8198 - - -
2.6 130 1.095 - - -
2.62 131 1.1151 - - -
2.64 132 0.7885 - - -
2.66 133 0.9445 - - -
2.68 134 0.867 - - -
2.7 135 0.8746 - - -
2.7200 136 0.9319 - - -
2.74 137 0.9741 - - -
2.76 138 1.0035 - - -
2.7800 139 0.9835 - - -
2.8 140 0.8572 - - -
2.82 141 1.0152 - - -
2.84 142 1.1073 - - -
2.86 143 0.9225 - - -
2.88 144 0.719 - - -
2.9 145 0.7328 - - -
2.92 146 0.7631 - - -
2.94 147 0.8256 - - -
2.96 148 0.8285 - - -
2.98 149 0.8175 - - -
3.0 150 1.0522 0.8857 - -
3.02 151 1.001 - - -
3.04 152 0.8184 - - -
3.06 153 0.7647 - - -
3.08 154 0.8648 - - -
3.1 155 0.7486 - - -
3.12 156 0.8201 - - -
3.14 157 0.8933 - - -
3.16 158 0.7511 - - -
3.18 159 0.8493 - - -
3.2 160 0.787 - - -
3.22 161 0.798 - - -
3.24 162 0.8613 - - -
3.26 163 0.8167 - - -
3.2800 164 0.9566 - - -
3.3 165 0.9089 - - -
3.32 166 0.5744 - - -
3.34 167 1.2298 - - -
3.36 168 0.7741 - - -
3.38 169 0.7265 - - -
3.4 170 0.5814 - - -
3.42 171 0.8753 - - -
3.44 172 0.812 - - -
3.46 173 0.8883 - - -
3.48 174 0.8091 - - -
3.5 175 0.729 - - -
3.52 176 0.8884 - - -
3.54 177 0.8049 - - -
3.56 178 0.93 - - -
3.58 179 0.7467 - - -
3.6 180 0.6481 - - -
3.62 181 0.8336 - - -
3.64 182 0.7265 - - -
3.66 183 0.7028 - - -
3.68 184 0.8973 - - -
3.7 185 0.8358 - - -
3.7200 186 1.015 - - -
3.74 187 0.8058 - - -
3.76 188 0.7062 - - -
3.7800 189 0.6524 - - -
3.8 190 0.7342 - - -
3.82 191 0.7001 - - -
3.84 192 0.9632 - - -
3.86 193 0.9068 - - -
3.88 194 0.7152 - - -
3.9 195 0.7028 - - -
3.92 196 0.8554 - - -
3.94 197 0.581 - - -
3.96 198 0.7586 - - -
3.98 199 0.773 - - -
4.0 200 0.8258 0.8043 - -
4.02 201 0.9255 - - -
4.04 202 0.6212 - - -
4.06 203 1.1683 - - -
4.08 204 0.6404 - - -
4.1 205 0.789 - - -
4.12 206 0.7202 - - -
4.14 207 0.8416 - - -
4.16 208 0.7614 - - -
4.18 209 0.754 - - -
4.2 210 0.6494 - - -
4.22 211 0.8913 - - -
4.24 212 0.8046 - - -
4.26 213 0.7114 - - -
4.28 214 0.8174 - - -
4.3 215 0.8075 - - -
4.32 216 0.7038 - - -
4.34 217 0.7458 - - -
4.36 218 0.6574 - - -
4.38 219 0.6443 - - -
4.4 220 0.6845 - - -
4.42 221 0.6008 - - -
4.44 222 0.7027 - - -
4.46 223 1.0495 - - -
4.48 224 0.9002 - - -
4.5 225 0.6933 - - -
4.52 226 0.8672 - - -
4.54 227 0.6823 - - -
4.5600 228 0.6828 - - -
4.58 229 0.7485 - - -
4.6 230 0.6692 - - -
4.62 231 0.6804 - - -
4.64 232 0.6779 - - -
4.66 233 0.7076 - - -
4.68 234 0.8468 - - -
4.7 235 0.5841 - - -
4.72 236 0.7031 - - -
4.74 237 0.6809 - - -
4.76 238 0.8763 - - -
4.78 239 0.7846 - - -
4.8 240 0.7742 - - -
4.82 241 0.6602 - - -
4.84 242 0.5466 - - -
4.86 243 0.6964 - - -
4.88 244 0.8074 - - -
4.9 245 0.6704 - - -
4.92 246 0.6502 - - -
4.9400 247 0.6901 - - -
4.96 248 0.8786 - - -
4.98 249 0.6718 - - -
5.0 250 0.714 0.7518 - -
5.02 251 0.803 - - -
5.04 252 0.6007 - - -
5.06 253 0.9205 - - -
5.08 254 0.6226 - - -
5.1 255 0.6515 - - -
5.12 256 0.5465 - - -
5.14 257 0.6086 - - -
5.16 258 0.8689 - - -
5.18 259 0.7302 - - -
5.2 260 0.5103 - - -
5.22 261 0.6379 - - -
5.24 262 0.7859 - - -
5.26 263 0.6445 - - -
5.28 264 0.7541 - - -
5.3 265 0.6807 - - -
5.32 266 0.8424 - - -
5.34 267 0.5556 - - -
5.36 268 0.5292 - - -
5.38 269 0.6275 - - -
5.4 270 0.5637 - - -
5.42 271 0.8736 - - -
5.44 272 0.6416 - - -
5.46 273 0.7914 - - -
5.48 274 0.8647 - - -
5.5 275 0.6192 - - -
5.52 276 0.7312 - - -
5.54 277 0.6522 - - -
5.5600 278 0.6333 - - -
5.58 279 0.6222 - - -
5.6 280 0.583 - - -
5.62 281 0.7436 - - -
5.64 282 0.6998 - - -
5.66 283 0.579 - - -
5.68 284 0.7935 - - -
5.7 285 0.566 - - -
5.72 286 0.6156 - - -
5.74 287 0.8793 - - -
5.76 288 0.6694 - - -
5.78 289 0.5666 - - -
5.8 290 0.5288 - - -
5.82 291 0.6879 - - -
5.84 292 0.5784 - - -
5.86 293 0.8357 - - -
5.88 294 0.6114 - - -
5.9 295 0.6998 - - -
5.92 296 0.7603 - - -
5.9400 297 0.6598 - - -
5.96 298 0.768 - - -
5.98 299 0.6153 - - -
6.0 300 0.8114 0.7178 - -
6.02 301 0.5707 - - -
6.04 302 0.8128 - - -
6.06 303 0.6975 - - -
6.08 304 0.7205 - - -
6.1 305 0.5987 - - -
6.12 306 0.6822 - - -
6.14 307 0.567 - - -
6.16 308 0.4776 - - -
6.18 309 0.651 - - -
6.2 310 0.626 - - -
6.22 311 0.7653 - - -
6.24 312 0.7728 - - -
6.26 313 0.5846 - - -
6.28 314 0.5164 - - -
6.3 315 0.7453 - - -
6.32 316 0.7956 - - -
6.34 317 0.7468 - - -
6.36 318 0.627 - - -
6.38 319 0.3958 - - -
6.4 320 0.7394 - - -
6.42 321 0.8124 - - -
6.44 322 0.7593 - - -
6.46 323 0.5382 - - -
6.48 324 0.7733 - - -
6.5 325 0.7539 - - -
6.52 326 0.5988 - - -
6.54 327 0.6218 - - -
6.5600 328 0.5294 - - -
6.58 329 0.5019 - - -
6.6 330 0.7233 - - -
6.62 331 0.6016 - - -
6.64 332 0.4056 - - -
6.66 333 0.508 - - -
6.68 334 0.5945 - - -
6.7 335 0.6626 - - -
6.72 336 0.6478 - - -
6.74 337 0.6447 - - -
6.76 338 0.5704 - - -
6.78 339 0.4938 - - -
6.8 340 0.6515 - - -
6.82 341 0.7325 - - -
6.84 342 0.6743 - - -
6.86 343 0.483 - - -
6.88 344 0.8484 - - -
6.9 345 0.6259 - - -
6.92 346 0.5538 - - -
6.9400 347 0.6483 - - -
6.96 348 0.4833 - - -
6.98 349 0.509 - - -
7.0 350 0.6843 0.6944 - -
7.02 351 0.5322 - - -
7.04 352 0.881 - - -
7.06 353 0.6108 - - -
7.08 354 0.5224 - - -
7.1 355 0.5953 - - -
7.12 356 0.7344 - - -
7.14 357 0.6669 - - -
7.16 358 0.6784 - - -
7.18 359 0.6312 - - -
7.2 360 0.8127 - - -
7.22 361 0.6002 - - -
7.24 362 0.4413 - - -
7.26 363 0.6409 - - -
7.28 364 0.677 - - -
7.3 365 0.4528 - - -
7.32 366 0.7866 - - -
7.34 367 0.5485 - - -
7.36 368 0.5949 - - -
7.38 369 0.6055 - - -
7.4 370 0.6179 - - -
7.42 371 0.7909 - - -
7.44 372 0.5334 - - -
7.46 373 0.6682 - - -
7.48 374 0.5925 - - -
7.5 375 0.7132 - - -
7.52 376 0.5729 - - -
7.54 377 0.8313 - - -
7.5600 378 0.6091 - - -
7.58 379 0.6929 - - -
7.6 380 0.5816 - - -
7.62 381 0.5816 - - -
7.64 382 0.5768 - - -
7.66 383 0.5584 - - -
7.68 384 0.4927 - - -
7.7 385 0.5489 - - -
7.72 386 0.6972 - - -
7.74 387 0.7099 - - -
7.76 388 0.5739 - - -
7.78 389 0.5394 - - -
7.8 390 0.5834 - - -
7.82 391 0.5081 - - -
7.84 392 0.5846 - - -
7.86 393 0.5713 - - -
7.88 394 0.8048 - - -
7.9 395 0.6146 - - -
7.92 396 0.5793 - - -
7.9400 397 0.6225 - - -
7.96 398 0.6097 - - -
7.98 399 0.6231 - - -
8.0 400 0.4974 0.6788 - -
8.02 401 0.4963 - - -
8.04 402 0.6387 - - -
8.06 403 0.6995 - - -
8.08 404 0.6847 - - -
8.1 405 0.7246 - - -
8.12 406 0.6532 - - -
8.14 407 0.612 - - -
8.16 408 0.6512 - - -
8.18 409 0.4676 - - -
8.2 410 0.656 - - -
8.22 411 0.6624 - - -
8.24 412 0.6024 - - -
8.26 413 0.4858 - - -
8.28 414 0.6221 - - -
8.3 415 0.5251 - - -
8.32 416 0.7109 - - -
8.34 417 0.6428 - - -
8.36 418 0.5752 - - -
8.38 419 0.7455 - - -
8.4 420 0.6478 - - -
8.42 421 0.609 - - -
8.44 422 0.6297 - - -
8.46 423 0.4464 - - -
8.48 424 0.6169 - - -
8.5 425 0.9958 - - -
8.52 426 0.6064 - - -
8.54 427 0.7579 - - -
8.56 428 0.7164 - - -
8.58 429 0.4353 - - -
8.6 430 0.5481 - - -
8.62 431 0.8304 - - -
8.64 432 0.5091 - - -
8.66 433 0.4245 - - -
8.68 434 0.5595 - - -
8.7 435 0.6432 - - -
8.72 436 0.539 - - -
8.74 437 0.5388 - - -
8.76 438 0.6111 - - -
8.78 439 0.6063 - - -
8.8 440 0.6886 - - -
8.82 441 0.5961 - - -
8.84 442 0.6632 - - -
8.86 443 0.4702 - - -
8.88 444 0.4392 - - -
8.9 445 0.6432 - - -
8.92 446 0.5324 - - -
8.94 447 0.4695 - - -
8.96 448 0.6815 - - -
8.98 449 0.6599 - - -
9.0 450 0.6482 0.6704 - -
9.02 451 0.759 - - -
9.04 452 0.5211 - - -
9.06 453 0.5451 - - -
9.08 454 0.4266 - - -
9.1 455 0.6988 - - -
9.12 456 0.6712 - - -
9.14 457 0.6157 - - -
9.16 458 0.7611 - - -
9.18 459 0.5724 - - -
9.2 460 0.5893 - - -
9.22 461 0.6938 - - -
9.24 462 0.5091 - - -
9.26 463 0.5931 - - -
9.28 464 0.5522 - - -
9.3 465 0.541 - - -
9.32 466 0.5728 - - -
9.34 467 0.5663 - - -
9.36 468 0.6938 - - -
9.38 469 0.5606 - - -
9.4 470 0.6168 - - -
9.42 471 0.5904 - - -
9.44 472 0.7011 - - -
9.46 473 0.7389 - - -
9.48 474 0.5821 - - -
9.5 475 0.6894 - - -
9.52 476 0.4491 - - -
9.54 477 0.5093 - - -
9.56 478 0.6265 - - -
9.58 479 0.383 - - -
9.6 480 0.5199 - - -
9.62 481 0.5039 - - -
9.64 482 0.5531 - - -
9.66 483 0.7229 - - -
9.68 484 0.6617 - - -
9.7 485 0.5928 - - -
9.72 486 0.5856 - - -
9.74 487 0.6063 - - -
9.76 488 0.5973 - - -
9.78 489 0.5237 - - -
9.8 490 0.6722 - - -
9.82 491 0.5947 - - -
9.84 492 0.3775 - - -
9.86 493 0.4027 - - -
9.88 494 0.6215 - - -
9.9 495 0.4161 - - -
9.92 496 0.6457 - - -
9.94 497 0.5051 - - -
9.96 498 0.7163 - - -
9.98 499 0.5732 - - -
10.0 500 0.637 0.6677 - -
-1 -1 - - 1.0 1.0

Framework Versions

  • Python: 3.12.5
  • Sentence Transformers: 5.0.0
  • Transformers: 4.54.0
  • PyTorch: 2.7.1+cu126
  • Accelerate: 1.9.0
  • Datasets: 4.0.0
  • Tokenizers: 0.21.2

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",
}

MultipleNegativesRankingLoss 

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}