--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:6113 - loss:MultipleNegativesRankingLoss base_model: sentence-transformers/clip-ViT-B-32 widget: - source_sentence: Some buildings and many green trees are located in an average residential area.some buildings and many green trees are located in an average residential area.some buildings and many green trees are located in an average residential area.some buildings and many green trees are in an average residential area.some buildings and many green trees are in a medium residential area . sentences: - Seawater in the wind triggered layers of white spray.a pedestrian are on the shore of the sea .a lot of people on the beach .water is dark blue light blue .sea water in the wind set off layers of white spray . - the brown roof stage is located in the middle of the road.Many large trees were planted around the stadium.many tall trees were planted around the stadium .the brown roof stadium is located in the middle of the road.the brown roof stadium is located in the middle of the road . - Seawater in the wind triggered layers of white spray.a pedestrian are on the shore of the sea .a lot of people on the beach .water is dark blue light blue .sea water in the wind set off layers of white spray . - source_sentence: Many white snows cover the irregular mountain.Many white snows cover irregular mountain.Many white snows cover the irregular mountain.Many white snows cover irregular mountain.many white snows cover irregular mountain . sentences: - Cylinder storage tanks are built on two square concrete fields near some trees and a parking lot.Cylinder storage tanks are built on two square concrete grounds near some trees and a parking lot.cylinder storage tanks are built on two square concrete ground near some trees and a parking lot .these storage tanks are painted in different colors located next to the wood .many storage tanks are near some green trees . - Seawater in the wind triggered layers of white spray.a pedestrian are on the shore of the sea .Many people are in a beach near a piece of ocean with waves.many people are in a beach near a piece of ocean with waves .sea water in the wind set off layers of white spray . - 19 oil storage tanks are there.the storage tank is next to the green sea .Many storage tanks are located between a river and a road.many storage tanks are between a river and a road .19 oil storage tanks are there . - source_sentence: this piece of forest is green yellow and dense.this piece of the yellow green forest is dense .Many green trees are in a piece of forest.many green trees are in a piece of forest .this piece of the forest is yellow green and dense . sentences: - Many ordered ships are in a port.Many ordered ships are in a port.Many ordered boats are in a port.Many ordered boats are in a port.many orderly boats are in a port . - a swimming pool is located between a road and a beach in a seaside resort.a swimming pool is located between a road and a beach in a complex.a swimming pool is located between a street and a beach in a resort.a swimming pool is between a road and a beach in a resort.a swimming pool is between a road and a beach in a resort . - You can see the dendritic texture on the desert.we can see dendritic texture on the desert .there is a desert with the figure of blood vessel .lots of lines stretches across this yellow desert .many ripples are in a piece of yellow desert . - source_sentence: a parking lot and many green trees are close to a viaduct with a circle like a ring track.a parking lot and many green trees are close to a viaduct with a circle like a ring track.a parking lot and many green trees are close to a viaduct with a circle like a ring track.a parking lot and many green trees are close to a viaduct with a circle like a ring track.a parking lot and many green trees are near a viaduct with a circle like a ring runway . sentences: - Many aircraft are parked next to the terminals near the runways of an airport.Many aircraft are parked next to terminals near airstrips at an airport.Many planes are parked next to the terminals near the runways in an airport.many planes are parked next to terminals near runways at an airport.many planes are parked next to terminals near runways in an airport . - many buildings are close to a port with many boats.it is practical that the industrial zone is located next to the port.it is convenient that the industrial area is located next to the port .Many buildings are close to a port with many boats.many buildings are near a port with many boats . - a clear sea and a quiet beach.the dark blue sea is very beautiful .Yellow beach is near a piece of green ocean.yellow beach is near a piece of green ocean .a clear sea and a quiet beach . - source_sentence: It's a mountainous area.it is white, brown and green .It's a piece of green mountains.it is a piece of green mountains .this is mountainous region . sentences: - yellow ribbon beach is between green trees and dark green ocean with white waves.yellow ribbon beach lies between green trees and dark green ocean with white waves.Yellow ribbon beach is between green trees and dark green ocean with white waves.Yellow ribbon beach is between green trees and dark green ocean with white waves.yellow ribbon beach is between green trees and dark green ocean with white waves . - Many aircraft are parked next to the terminals near the runways of an airport.Many aircraft are parked next to terminals near airstrips at an airport.Many planes are parked next to the terminals near the runways in an airport.many planes are parked next to terminals near runways at an airport.many planes are parked next to terminals near runways in an airport . - several buildings are around a church.The church seems very grand.the church seems very grandear .several buildings are around a church.several buildings are around a church . pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy model-index: - name: SentenceTransformer based on sentence-transformers/clip-ViT-B-32 results: - task: type: triplet name: Triplet dataset: name: clip valid triplet type: clip-valid-triplet metrics: - type: cosine_accuracy value: 0.9992366433143616 name: Cosine Accuracy - task: type: triplet name: Triplet dataset: name: clip train triplet type: clip-train-triplet metrics: - type: cosine_accuracy value: 0.9996728301048279 name: Cosine Accuracy - task: type: triplet name: Triplet dataset: name: clip test triplet type: clip-test-triplet metrics: - type: cosine_accuracy value: 0.9992372393608093 name: Cosine Accuracy --- # SentenceTransformer based on sentence-transformers/clip-ViT-B-32 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/clip-ViT-B-32](https://huggingface.co/sentence-transformers/clip-ViT-B-32). 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 Type:** Sentence Transformer - **Base model:** [sentence-transformers/clip-ViT-B-32](https://huggingface.co/sentence-transformers/clip-ViT-B-32) - **Maximum Sequence Length:** 77 tokens - **Output Dimensionality:** None dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): CLIPModel() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("WorkStation0/clip-finetuned-satellite-v.0.11") # Run inference sentences = [ "It's a mountainous area.it is white, brown and green .It's a piece of green mountains.it is a piece of green mountains .this is mountainous region .", 'Many aircraft are parked next to the terminals near the runways of an airport.Many aircraft are parked next to terminals near airstrips at an airport.Many planes are parked next to the terminals near the runways in an airport.many planes are parked next to terminals near runways at an airport.many planes are parked next to terminals near runways in an airport .', 'yellow ribbon beach is between green trees and dark green ocean with white waves.yellow ribbon beach lies between green trees and dark green ocean with white waves.Yellow ribbon beach is between green trees and dark green ocean with white waves.Yellow ribbon beach is between green trees and dark green ocean with white waves.yellow ribbon beach is between green trees and dark green ocean with white waves .', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Triplet * Datasets: `clip-valid-triplet`, `clip-train-triplet` and `clip-test-triplet` * Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) | Metric | clip-valid-triplet | clip-train-triplet | clip-test-triplet | |:--------------------|:-------------------|:-------------------|:------------------| | **cosine_accuracy** | **0.9992** | **0.9997** | **0.9992** | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 6,113 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 | | | | * Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | | Many buildings and some green trees are located in an industrial area.there are many parking cars on the area next to the buildings in the industrial region.there are many cars parking on the region beside the buildings in the industrial region .many buildings and some green trees are located in an industrial area.many buildings and some green trees are in an industrial area . | It's a piece of white snow mountain.It's a piece of snow white mountain.It's a piece of white snow mountain.It's a piece of white snow mountain.it is a piece of white snow mountain . | | | Many buildings are located in a commercial area.Many buildings are located in a commercial area.Many buildings are located in a commercial area.Many buildings are in a commercial area.many buildings are in a commercial area . | The mountain of yellow and green has a vein texture.the mountain of yellow and green has a vein texture.the mountain of yellow and green has a texture of vein .mountains with long and narrow ridges traverse in this range .it is a piece of irregular green mountains . | | | There's a strong bridge over the river.There are many houses on both sides of the river.there are many houses on both sides of the river .There's a strong bridge over the river.there is a strong bridge over the river . | many small green spots are scattered in a piece of kaki nueland.Many small green spots are scattered in a piece of naked khaki.Many small green spots are scattered in a piece of khaki stripe.many small green spots are scattered in a piece of khaki bareland.many small green spots are scattered in a piece of khaki bareland . | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 1,310 evaluation samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:--------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | PIL.PngImagePlugin.PngImageFile | string | string | | details | | | | * Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | | Many trees are planted around the playground.There's a green football pitch on the red track.there's a green football field on the red track .a lot of trees are planted around the playground.a lot of trees are planted around the playground . | It's a piece of uneven kaki nueland.It's a piece of uneven naked khaki.It's a piece of irregular Kaki stripping.It's a piece of unequally brazen khaki.it is a piece of uneven khaki bareland . | | | It's a big bridge and a few buildings with some grass.the roads are grey and the ground is brown .two parallel bridges on a black river are close to many green plants and several buildings.two parallel bridges on a black river are near many green plants and several buildings .this is a big bridge and some buildings with a little grass . | Cylinder storage tanks are built on two square concrete fields near some trees and a parking lot.Cylinder storage tanks are built on two square concrete grounds near some trees and a parking lot.cylinder storage tanks are built on two square concrete ground near some trees and a parking lot .these storage tanks are painted in different colors located next to the wood .many storage tanks are near some green trees . | | | the lake with borders is surrounded by roads a parking lot and rows of houses.the lake with edges is surrounded by roads a parking lot and rows of houses.the lake with bylands is surrounded by roads a parking lot and rows of houses .green ponds sit in this resort surrounded by rows of red houses .some buildings and green trees are in a resort with several green ponds . | many storage tanks of different sizes are in a factory.Many storage tanks in different sizes are in a factory.Many storage tanks in different sizes are in a factory.many storage tanks in different sizes are in a factory.many storage tanks in different sizes are in a factory . | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 2 - `per_device_eval_batch_size`: 2 - `gradient_accumulation_steps`: 4 - `fp16`: True - `dataloader_num_workers`: 2 - `load_best_model_at_end`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 2 - `per_device_eval_batch_size`: 2 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 4 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-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`: 3 - `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`: 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`: 2 - `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`: None - `hub_always_push`: False - `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 - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | clip-valid-triplet_cosine_accuracy | clip-train-triplet_cosine_accuracy | clip-test-triplet_cosine_accuracy | |:------:|:----:|:-------------:|:---------------:|:----------------------------------:|:----------------------------------:|:---------------------------------:| | -1 | -1 | - | - | 0.9863 | - | - | | 0.0994 | 76 | 1.3892 | - | - | - | - | | 0.1989 | 152 | 0.7274 | - | - | - | - | | 0.2983 | 228 | 0.5566 | - | - | - | - | | 0.3978 | 304 | 0.4034 | - | - | - | - | | 0.4972 | 380 | 0.4335 | - | - | - | - | | 0.5967 | 456 | 0.4176 | - | - | - | - | | 0.6961 | 532 | 0.3955 | - | - | - | - | | 0.7956 | 608 | 0.3396 | - | - | - | - | | 0.8950 | 684 | 0.306 | - | - | - | - | | 0.9944 | 760 | 0.2526 | - | - | - | - | | 1.0 | 765 | - | 0.0786 | 1.0 | - | - | | 1.0929 | 836 | 0.2531 | - | - | - | - | | 1.1923 | 912 | 0.3303 | - | - | - | - | | 1.2918 | 988 | 0.2122 | - | - | - | - | | 1.3912 | 1064 | 0.2478 | - | - | - | - | | 1.4907 | 1140 | 0.3588 | - | - | - | - | | 1.5901 | 1216 | 0.2023 | - | - | - | - | | 1.6896 | 1292 | 0.2395 | - | - | - | - | | 1.7890 | 1368 | 0.1154 | - | - | - | - | | 1.8885 | 1444 | 0.2729 | - | - | - | - | | 1.9879 | 1520 | 0.1708 | - | - | - | - | | 2.0 | 1530 | - | 0.0700 | 0.9992 | - | - | | 2.0864 | 1596 | 0.1841 | - | - | - | - | | 2.1858 | 1672 | 0.1382 | - | - | - | - | | 2.2852 | 1748 | 0.1452 | - | - | - | - | | 2.3847 | 1824 | 0.2616 | - | - | - | - | | 2.4841 | 1900 | 0.2024 | - | - | - | - | | 2.5836 | 1976 | 0.2883 | - | - | - | - | | 2.6830 | 2052 | 0.2461 | - | - | - | - | | 2.7825 | 2128 | 0.3249 | - | - | - | - | | 2.8819 | 2204 | 0.1299 | - | - | - | - | | 2.9814 | 2280 | 0.2171 | - | - | - | - | | 3.0 | 2295 | - | 0.0652 | 0.9992 | - | - | | -1 | -1 | - | - | 0.9992 | 0.9997 | 0.9992 | ### Framework Versions - Python: 3.11.12 - Sentence Transformers: 4.1.0 - Transformers: 4.52.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.7.0 - Datasets: 2.14.4 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @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 ```bibtex @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} } ```