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

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}
}
Downloads last month
4
Safetensors
Model size
428M params
Tensor type
F32
·
Inference Providers NEW
Sentence Similarity
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dejasi5459/clip-fashionAssign-embeddings-final

Base model

sentence-transformers/clip-ViT-L-14
Finetuned
(8)
this model

Dataset used to train dejasi5459/clip-fashionAssign-embeddings-final

Evaluation results

View on Papers With Code