mtg-coloridentity-multilabel-classification

This is a proof-of-concept model trained on datasets/joshuasundance/mtg-coloridentity-multilabel-classification.

It takes card name + text as a single str as input and outputs color identity as an encoding:

colors = ['B', 'G', 'R', 'U', 'W']
b = [1, 0, 0, 0, 0]
bw = [1, 0, 0, 0, 1]
gru = [0, 1, 1, 1, 0]
# and so on

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-mpnet-base-v2
• Classification head: a OneVsRestClassifier instance
• Maximum Sequence Length: 512 tokens

<!-- - **Number of Classes:** Unknown --> <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Classification Report

              precision    recall  f1-score   support

                   0.80      0.77      0.78       594
           B       0.81      0.76      0.78       821
          BG       0.42      0.56      0.48        63
         BGR       0.46      0.55      0.50        22
        BGRU       0.00      0.00      0.00         0
       BGRUW       0.73      0.33      0.46        24
        BGRW       0.00      0.00      0.00         0
         BGU       0.27      0.38      0.32         8
        BGUW       0.12      1.00      0.22         1
         BGW       0.14      0.33      0.19         9
          BR       0.41      0.59      0.48        80
         BRU       0.55      0.50      0.52        24
        BRUW       0.00      0.00      0.00         0
         BRW       0.29      0.36      0.32        14
          BU       0.53      0.56      0.54        91
         BUW       0.29      0.43      0.34        14
          BW       0.36      0.37      0.37        73
           G       0.77      0.76      0.77       791
          GR       0.42      0.46      0.44        85
         GRU       0.14      0.22      0.17         9
        GRUW       0.00      0.00      0.00         0
         GRW       0.27      0.50      0.35        18
          GU       0.48      0.49      0.49        69
         GUW       0.15      0.27      0.20        15
          GW       0.40      0.43      0.41        89
           R       0.81      0.77      0.79       803
          RU       0.43      0.51      0.47        68
         RUW       0.20      0.43      0.27         7
          RW       0.47      0.49      0.48        80
           U       0.83      0.81      0.82       818
          UW       0.37      0.43      0.40        86
           W       0.77      0.72      0.74       777

    accuracy                           0.71      5553
   macro avg       0.40      0.46      0.41      5553
weighted avg       0.73      0.71      0.72      5553

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("joshuasundance/mtg-coloridentity-multilabel-classification")
# Run inference
preds = model("Scattershot Archer

{T}: Scattershot Archer deals 1 damage to each creature with flying.")

<!-- ### Downstream Use *List how someone could finetune this model on their own dataset.* --> <!-- ### 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 Set Metrics

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• body_learning_rate: (2e-05, 2e-05)
• head_learning_rate: 2e-05
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Framework Versions

• Python: 3.11.7
• SetFit: 1.0.3
• Sentence Transformers: 2.3.0
• Transformers: 4.37.2
• PyTorch: 2.1.2+cu118
• Datasets: 2.16.1
• Tokenizers: 0.15.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}

<!-- ## 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.* -->