README.md

---
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) <!-- at revision 327ab6726d33c0e22f920c83f2ff9e4bd38ca37f -->
- **Maximum Sequence Length:** 77 tokens
- **Output Dimensionality:** None dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### 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]])
```

<!--
### Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details>
-->

<!--
### Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details>
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Dataset

#### Unnamed Dataset

* Size: 149,460 training samples
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
  |         | sentence_0                                                                        | sentence_1                                                                        | label                                           |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
  | type    | string                                                                            | string                                                                            | int                                             |
  | details | <ul><li>min: 3 tokens</li><li>mean: 17.16 tokens</li><li>max: 69 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 54.64 tokens</li><li>max: 69 tokens</li></ul> | <ul><li>0: ~57.60%</li><li>1: ~42.40%</li></ul> |
* Samples:
  | sentence_0                        | sentence_1                                                                                                  | label          |
  |:----------------------------------|:------------------------------------------------------------------------------------------------------------|:---------------|
  | <code>Comparative Analysis</code> | <code>https://cards.scryfall.io/normal/front/d/d/dd83129b-7e8c-4cc5-a7b3-e0ae221d7ad4.jpg?1562939549</code> | <code>1</code> |
  | <code>Breathkeeper Seraph</code>  | <code>https://cards.scryfall.io/normal/front/1/b/1bdd3ecb-8c11-4a4c-a503-bc29f79a9dcb.jpg?1682204691</code> | <code>0</code> |
  | <code>Wei Infantry</code>         | <code>https://cards.scryfall.io/normal/front/7/2/72c6465f-3144-4faf-b248-a9fb941dc002.jpg?1562257016</code> | <code>1</code> |
* Loss: [<code>ContrastiveLoss</code>](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
<details><summary>Click to expand</summary>

- `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`: {}

</details>

### 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}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->