--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:149460 - loss:ContrastiveLoss base_model: sentence-transformers/clip-ViT-B-32 widget: - source_sentence: Meltdown sentences: - Ancient Imperiosaur - https://cards.scryfall.io/normal/front/1/9/192ccc7f-ffb1-4f78-8cf0-a220df612be7.jpg?1682536817 - https://cards.scryfall.io/normal/front/5/6/56301392-3496-48d0-8d91-6b82e1164c98.jpg?1721427942 - source_sentence: Etali, Primal Storm sentences: - https://cards.scryfall.io/normal/front/4/8/4874388e-0227-4b89-a986-d86c14482c81.jpg?1594065427 - Battle of Wits - https://cards.scryfall.io/normal/front/1/d/1d3d8bb4-0430-45bb-930d-5d6db6521945.jpg?1587309687 - source_sentence: Chrome Prowler sentences: - https://cards.scryfall.io/normal/front/a/2/a263f594-621e-46af-8561-f7eee565a19a.jpg?1562643297 - https://cards.scryfall.io/normal/front/3/d/3dff363d-7e9f-4764-a9ee-ec2f23239df6.jpg?1562907900 - https://cards.scryfall.io/normal/front/2/1/21121857-85b8-4ba8-9363-beafdb1005c2.jpg?1730486782 - source_sentence: Beastbreaker of Bala Ged sentences: - https://cards.scryfall.io/normal/front/2/8/287ca034-9cea-4b84-98ba-76c24f038edb.jpg?1599709496 - https://cards.scryfall.io/normal/front/5/4/547f2641-bcd6-4536-ba5a-f46170dd2803.jpg?1573513110 - https://cards.scryfall.io/normal/front/4/c/4c29f6a1-42a5-433f-9c09-c160b096f8e1.jpg?1562542378 - source_sentence: Against All Odds sentences: - https://cards.scryfall.io/normal/front/4/a/4ab2f81a-fcbe-44d1-8281-04dd78bb9ea3.jpg?1593274931 - https://cards.scryfall.io/normal/front/3/c/3cd8dd4e-6892-49d7-8fae-97d04f9f6c84.jpg?1675956885 - Sheltering Prayers pipeline_tag: sentence-similarity library_name: sentence-transformers --- # 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/huggingface/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("philipp-zettl/MTGEmb-small") # Run inference sentences = [ 'Against All Odds', 'https://cards.scryfall.io/normal/front/3/c/3cd8dd4e-6892-49d7-8fae-97d04f9f6c84.jpg?1675956885', 'https://cards.scryfall.io/normal/front/4/a/4ab2f81a-fcbe-44d1-8281-04dd78bb9ea3.jpg?1593274931', ] 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, 0.9248, 0.6695], # [0.9248, 1.0000, 0.6947], # [0.6695, 0.6947, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 149,460 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:----------------------------------|:------------------------------------------------------------------------------------------------------------|:---------------| | Comparative Analysis | https://cards.scryfall.io/normal/front/d/d/dd83129b-7e8c-4cc5-a7b3-e0ae221d7ad4.jpg?1562939549 | 1 | | Breathkeeper Seraph | https://cards.scryfall.io/normal/front/1/b/1bdd3ecb-8c11-4a4c-a503-bc29f79a9dcb.jpg?1682204691 | 0 | | Wei Infantry | https://cards.scryfall.io/normal/front/7/2/72c6465f-3144-4faf-b248-a9fb941dc002.jpg?1562257016 | 1 | * Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `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`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `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`: 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 - `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 - `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 - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 0.2140 | 500 | 0.0342 | | 0.4281 | 1000 | 0.0311 | | 0.6421 | 1500 | 0.0306 | | 0.8562 | 2000 | 0.0302 | | 1.0702 | 2500 | 0.0287 | | 1.2842 | 3000 | 0.0262 | | 1.4983 | 3500 | 0.025 | | 1.7123 | 4000 | 0.0236 | | 1.9264 | 4500 | 0.022 | | 2.1404 | 5000 | 0.016 | | 2.3545 | 5500 | 0.0128 | | 2.5685 | 6000 | 0.0119 | | 2.7825 | 6500 | 0.0108 | | 2.9966 | 7000 | 0.0103 | ### Framework Versions - Python: 3.13.7 - Sentence Transformers: 5.1.2 - Transformers: 4.49.0 - PyTorch: 2.8.0+cu128 - Accelerate: 1.10.1 - Datasets: 4.1.1 - Tokenizers: 0.21.4 ## 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", } ``` #### ContrastiveLoss ```bibtex @inproceedings{hadsell2006dimensionality, author={Hadsell, R. and Chopra, S. and LeCun, Y.}, booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, title={Dimensionality Reduction by Learning an Invariant Mapping}, year={2006}, volume={2}, number={}, pages={1735-1742}, doi={10.1109/CVPR.2006.100} } ```