End of training script.

README.md

@@ -0,0 +1,423 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:294252
+- loss:ContrastiveLoss
+base_model: sentence-transformers/clip-ViT-B-32
+widget:
+- source_sentence: Ranger's Guile
+  sentences:
+  - https://cards.scryfall.io/normal/front/0/1/01388e24-d66f-40a8-af41-0f84dd8ed3fe.jpg?1562781768
+  - https://cards.scryfall.io/normal/front/2/0/20995638-e217-49f1-bccc-d1a344694fd8.jpg?1592711262
+  - https://cards.scryfall.io/normal/front/1/3/13680953-cf05-4e38-a3cf-22900c02fab7.jpg?1706240764
+- source_sentence: '{2}, {T}: Choose one that hasn''t been chosen —
+
+    • This artifact deals 2 damage to target creature.
+
+    • Tap target creature.
+
+    • Sacrifice this artifact. You gain 3 life.'
+  sentences:
+  - Haunted Ridge
+  - https://cards.scryfall.io/normal/front/1/e/1ebb7ade-ebbb-49fb-b64f-fa247f9a9af6.jpg?1562544721
+  - Three Bowls of Porridge
+- source_sentence: Soratami Mindsweeper
+  sentences:
+  - https://cards.scryfall.io/normal/front/c/1/c13eacff-0fd1-4e2e-8213-5bf5fff973c8.jpg?1593095724
+  - https://cards.scryfall.io/normal/front/6/7/67f55ef7-8479-4d56-9801-cb4fd5526e73.jpg?1675644776
+  - https://cards.scryfall.io/normal/front/0/e/0ef3b83a-777c-45b6-97a1-25be237df79b.jpg?1561932561
+- source_sentence: 'Flying
+
+    Ward—Sacrifice a creature.
+
+    Whenever a creature dies, target opponent loses 2 life and you gain 2 life.'
+  sentences:
+  - https://cards.scryfall.io/normal/front/e/4/e4c7919a-de62-46df-a937-593647473ef5.jpg?1654567436
+  - https://cards.scryfall.io/normal/front/9/7/9712ecaa-4059-44ba-98b7-07bfe7411b5b.jpg?1562447340
+  - https://cards.scryfall.io/normal/front/0/7/078933b3-6d82-45f2-94e8-addf54cf1704.jpg?1706241798
+- source_sentence: Glimpse of Freedom
+  sentences:
+  - https://cards.scryfall.io/normal/front/c/1/c1e9c025-1cdb-4da8-8d28-14ad5efb512d.jpg?1581479361
+  - https://cards.scryfall.io/normal/front/0/7/0770eb6a-4f01-4677-a401-14c1b30692c9.jpg?1673306796
+  - https://cards.scryfall.io/normal/front/3/3/333039ef-b328-4082-85ae-162caed5612e.jpg?1738358111
+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 = [
+    'Glimpse of Freedom',
+    'https://cards.scryfall.io/normal/front/c/1/c1e9c025-1cdb-4da8-8d28-14ad5efb512d.jpg?1581479361',
+    'https://cards.scryfall.io/normal/front/3/3/333039ef-b328-4082-85ae-162caed5612e.jpg?1738358111',
+]
+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, 0.7515, 0.7515],
+#         [0.7515, 1.0000, 1.0000],
+#         [0.7515, 1.0000, 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: 294,252 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: 25.44 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 54.71 tokens</li><li>max: 69 tokens</li></ul> | <ul><li>0: ~38.90%</li><li>1: ~61.10%</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                          | sentence_1                                                                                                  | label          |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Flying<br>Ascend (If you control ten or more permanents, you get the city's blessing for the rest of the game.)<br>At the beginning of your upkeep, if you have the city's blessing, reveal the top card of your library and put it into your hand. Each opponent loses X life and you gain X life, where X is that card's mana value.</code> | <code>Twilight Prophet</code>                                                                               | <code>1</code> |
+  | <code>Target creature gains deathtouch until end of turn and must be blocked this turn if able.<br>Flashback {G} (You may cast this card from your graveyard for its flashback cost. Then exile it.)</code>                                                                                                                                         | <code>https://cards.scryfall.io/normal/front/f/2/f2c97632-3cf1-4b79-9d18-d8991654dcca.jpg?1562796910</code> | <code>0</code> |
+  | <code>Pay 1 life, Sacrifice another creature: Create a Treasure token. (It's an artifact with "{T}, Sacrifice this token: Add one mana of any color.")</code>                                                                                                                                                                                       | <code>https://cards.scryfall.io/normal/front/7/7/77c0929f-bee6-416d-8571-6540ae4f6e4f.jpg?1562879392</code> | <code>0</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`: 56
+- `per_device_eval_batch_size`: 56
+- `num_train_epochs`: 5
+- `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`: 56
+- `per_device_eval_batch_size`: 56
+- `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`: 5
+- `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 |
+|:------:|:-----:|:-------------:|
+| 0.0951 | 500   | 0.0269        |
+| 0.1903 | 1000  | 0.0253        |
+| 0.2854 | 1500  | 0.0253        |
+| 0.3806 | 2000  | 0.0252        |
+| 0.4757 | 2500  | 0.0252        |
+| 0.5709 | 3000  | 0.0253        |
+| 0.6660 | 3500  | 0.0252        |
+| 0.7612 | 4000  | 0.0251        |
+| 0.8563 | 4500  | 0.0251        |
+| 0.9515 | 5000  | 0.0251        |
+| 1.0466 | 5500  | 0.0251        |
+| 1.1418 | 6000  | 0.0251        |
+| 1.2369 | 6500  | 0.0252        |
+| 1.3321 | 7000  | 0.0251        |
+| 1.4272 | 7500  | 0.0252        |
+| 1.5224 | 8000  | 0.0252        |
+| 1.6175 | 8500  | 0.0251        |
+| 1.7127 | 9000  | 0.0249        |
+| 1.8078 | 9500  | 0.0252        |
+| 1.9029 | 10000 | 0.025         |
+| 1.9981 | 10500 | 0.0252        |
+| 2.0932 | 11000 | 0.0251        |
+| 2.1884 | 11500 | 0.0251        |
+| 2.2835 | 12000 | 0.0252        |
+| 2.3787 | 12500 | 0.0252        |
+| 2.4738 | 13000 | 0.0251        |
+| 2.5690 | 13500 | 0.025         |
+| 2.6641 | 14000 | 0.025         |
+| 2.7593 | 14500 | 0.0251        |
+| 2.8544 | 15000 | 0.0251        |
+| 2.9496 | 15500 | 0.0251        |
+| 3.0447 | 16000 | 0.0251        |
+| 3.1399 | 16500 | 0.0252        |
+| 3.2350 | 17000 | 0.0251        |
+| 3.3302 | 17500 | 0.025         |
+| 3.4253 | 18000 | 0.0252        |
+| 3.5205 | 18500 | 0.0251        |
+| 3.6156 | 19000 | 0.025         |
+| 3.7108 | 19500 | 0.0251        |
+| 3.8059 | 20000 | 0.0252        |
+| 3.9010 | 20500 | 0.025         |
+| 3.9962 | 21000 | 0.025         |
+| 4.0913 | 21500 | 0.0251        |
+| 4.1865 | 22000 | 0.0251        |
+| 4.2816 | 22500 | 0.025         |
+| 4.3768 | 23000 | 0.025         |
+| 4.4719 | 23500 | 0.025         |
+| 4.5671 | 24000 | 0.0252        |
+| 4.6622 | 24500 | 0.025         |
+| 4.7574 | 25000 | 0.0252        |
+| 4.8525 | 25500 | 0.025         |
+| 4.9477 | 26000 | 0.025         |
+
+
+### 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.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/home/phil/.cache/huggingface/hub/models--sentence-transformers--clip-ViT-B-32/snapshots/327ab6726d33c0e22f920c83f2ff9e4bd38ca37f/0_CLIPModel",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "model_type": "clip_text_model",
+    "torch_dtype": "float32"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vision_config": {
+    "dropout": 0.0,
+    "gradient_checkpointing": false,
+    "model_type": "clip_vision_model",
+    "torch_dtype": "float32"
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.49.0",
+    "pytorch": "2.8.0+cu128"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341fc80e886d58cc50059de8b9b063bd1b9a39dc246dd10f13db826617cc9d66
+size 605156676

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.CLIPModel"
+  }
+]

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}