metadata
base_model: desarrolloasesoreslocales/bert-leg-al-corpus
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: ' A otectos de probar la comisión do la infracción que indobidamento so me imputa, esta parto solicita como medios probatos ¡que se expida y omita por los Órganos correspondientes de la Administración'
- text: >-
procedo al estacionamiento por autorización del agente 12289 (Policia
laca. Aa vuelta en 5 minutos, me encuentro con una multa LL5898790 por
parte del agente 12312
- text: >-
En el momento de la denuncia, mi vehículo contaba con la tarjeta de
persona con movilidad reducida colocada en el cristal delantero, lugar
habitual donde se posición este tipo de tarjetas. Me sorprende que no se
haya tenido en cuenta esta circunstancia.
- text: >-
La presunción de veracidad de las denuncias efectuadas por los agentes de
la autoridad no es absoluta, ya que es necesario que se aporten pruebas
adicionales que respalden la versión de los hechos
- text: >-
La sanción carece de una descripción detallada de los hechos, lo que
impide conocer la conducta real del denunciado y subsumir el hecho
denunciado en el artículo correspondiente.
inference: true
model-index:
- name: SetFit with desarrolloasesoreslocales/bert-leg-al-corpus
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.7875
name: Accuracy
SetFit with desarrolloasesoreslocales/bert-leg-al-corpus
This is a SetFit model that can be used for Text Classification. This SetFit model uses desarrolloasesoreslocales/bert-leg-al-corpus as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: desarrolloasesoreslocales/bert-leg-al-corpus
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 20 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
Label | Examples |
---|---|
2014 |
|
2001 |
|
2026 |
|
2013 |
|
1001 |
|
304 |
|
237 |
|
2038 |
|
49 |
|
357 |
|
2022 |
|
2017 |
|
78 |
|
2037 |
|
2039 |
|
353 |
|
2002 |
|
2010 |
|
994 |
|
2060 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.7875 |
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("desarrolloasesoreslocales/bert-leg-al-setfit-grok")
# Run inference
preds = model("procedo al estacionamiento por autorización del agente 12289 (Policia laca. Aa vuelta en 5 minutos, me encuentro con una multa LL5898790 por parte del agente 12312")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 4 | 44.1625 | 212 |
Label | Training Sample Count |
---|---|
49 | 8 |
78 | 8 |
237 | 8 |
304 | 8 |
353 | 8 |
357 | 8 |
994 | 8 |
1001 | 8 |
2001 | 8 |
2002 | 8 |
2010 | 8 |
2013 | 8 |
2014 | 8 |
2017 | 8 |
2022 | 8 |
2026 | 8 |
2037 | 8 |
2038 | 8 |
2039 | 8 |
2060 | 8 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (5, 5)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 200
- body_learning_rate: (1e-06, 1e-06)
- head_learning_rate: 1e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: True
- use_amp: True
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: 100
- load_best_model_at_end: True
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0002 | 1 | 0.3727 | - |
0.0167 | 100 | 0.1507 | 0.1304 |
0.0333 | 200 | 0.098 | 0.0856 |
0.05 | 300 | 0.0779 | 0.0789 |
0.0667 | 400 | 0.0123 | 0.0652 |
0.0833 | 500 | 0.0087 | 0.0724 |
0.1 | 600 | 0.0248 | 0.0612 |
0.1167 | 700 | 0.0015 | 0.0676 |
0.1333 | 800 | 0.0024 | 0.0652 |
0.15 | 900 | 0.001 | 0.0725 |
0.1667 | 1000 | 0.0009 | 0.0663 |
0.1833 | 1100 | 0.0004 | 0.0677 |
0.2 | 1200 | 0.0152 | 0.0711 |
0.2167 | 1300 | 0.0003 | 0.0767 |
0.2333 | 1400 | 0.0019 | 0.0776 |
0.25 | 1500 | 0.0003 | 0.0741 |
0.2667 | 1600 | 0.0002 | 0.0735 |
0.2833 | 1700 | 0.0003 | 0.0746 |
0.3 | 1800 | 0.0002 | 0.0744 |
0.3167 | 1900 | 0.0002 | 0.0724 |
0.3333 | 2000 | 0.0004 | 0.0707 |
0.35 | 2100 | 0.0001 | 0.0703 |
0.3667 | 2200 | 0.0001 | 0.0756 |
0.3833 | 2300 | 0.0025 | 0.0726 |
0.4 | 2400 | 0.0001 | 0.0743 |
0.4167 | 2500 | 0.0002 | 0.0714 |
0.4333 | 2600 | 0.0002 | 0.0736 |
0.45 | 2700 | 0.0001 | 0.0759 |
0.4667 | 2800 | 0.0001 | 0.0728 |
0.4833 | 2900 | 0.0001 | 0.0723 |
0.5 | 3000 | 0.0003 | 0.0787 |
0.5167 | 3100 | 0.0001 | 0.0742 |
0.5333 | 3200 | 0.0024 | 0.0745 |
0.55 | 3300 | 0.0001 | 0.0768 |
0.5667 | 3400 | 0.0001 | 0.0733 |
0.5833 | 3500 | 0.0002 | 0.0748 |
0.6 | 3600 | 0.0001 | 0.0756 |
0.6167 | 3700 | 0.0001 | 0.0753 |
0.6333 | 3800 | 0.0001 | 0.0723 |
0.65 | 3900 | 0.0001 | 0.0739 |
0.6667 | 4000 | 0.0001 | 0.0725 |
0.6833 | 4100 | 0.0036 | 0.0732 |
0.7 | 4200 | 0.0001 | 0.076 |
0.7167 | 4300 | 0.0001 | 0.0761 |
0.7333 | 4400 | 0.0356 | 0.0737 |
0.75 | 4500 | 0.0001 | 0.0772 |
0.7667 | 4600 | 0.0001 | 0.0775 |
0.7833 | 4700 | 0.0001 | 0.0767 |
0.8 | 4800 | 0.0001 | 0.0742 |
0.8167 | 4900 | 0.0001 | 0.0747 |
0.8333 | 5000 | 0.0078 | 0.0739 |
0.85 | 5100 | 0.0001 | 0.0755 |
0.8667 | 5200 | 0.0 | 0.0792 |
0.8833 | 5300 | 0.0001 | 0.0755 |
0.9 | 5400 | 0.0001 | 0.0754 |
0.9167 | 5500 | 0.0 | 0.0768 |
0.9333 | 5600 | 0.0001 | 0.0774 |
0.95 | 5700 | 0.0001 | 0.0749 |
0.9667 | 5800 | 0.0 | 0.0742 |
0.9833 | 5900 | 0.0035 | 0.0734 |
1.0 | 6000 | 0.0001 | 0.0753 |
0.0006 | 1 | 0.0135 | - |
0.0625 | 100 | 0.0198 | 0.0637 |
0.125 | 200 | 0.001 | 0.0635 |
0.1875 | 300 | 0.0243 | 0.0638 |
0.25 | 400 | 0.0056 | 0.0623 |
0.3125 | 500 | 0.002 | 0.0622 |
0.375 | 600 | 0.0023 | 0.067 |
0.4375 | 700 | 0.0073 | 0.0633 |
0.5 | 800 | 0.0013 | 0.0639 |
0.5625 | 900 | 0.0024 | 0.0655 |
0.625 | 1000 | 0.0017 | 0.0639 |
0.6875 | 1100 | 0.0022 | 0.0663 |
0.75 | 1200 | 0.0074 | 0.0639 |
0.8125 | 1300 | 0.0032 | 0.0655 |
0.875 | 1400 | 0.0011 | 0.0664 |
0.9375 | 1500 | 0.0301 | 0.0644 |
1.0 | 1600 | 0.0054 | 0.0643 |
0.0006 | 1 | 0.0051 | - |
0.0625 | 100 | 0.0042 | 0.0634 |
0.125 | 200 | 0.0011 | 0.0658 |
0.1875 | 300 | 0.0178 | 0.0656 |
0.25 | 400 | 0.0042 | 0.0641 |
0.3125 | 500 | 0.0022 | 0.0648 |
0.375 | 600 | 0.0013 | 0.0685 |
0.4375 | 700 | 0.0031 | 0.0651 |
0.5 | 800 | 0.002 | 0.0659 |
0.5625 | 900 | 0.0026 | 0.0672 |
0.625 | 1000 | 0.0022 | 0.0658 |
0.6875 | 1100 | 0.0017 | 0.0679 |
0.75 | 1200 | 0.0034 | 0.0652 |
0.8125 | 1300 | 0.0021 | 0.0675 |
0.875 | 1400 | 0.0007 | 0.0678 |
0.9375 | 1500 | 0.0189 | 0.0661 |
1.0 | 1600 | 0.0046 | 0.0665 |
0.0006 | 1 | 0.0038 | - |
0.0562 | 100 | 0.0008 | 0.0661 |
0.1125 | 200 | 0.0019 | 0.0684 |
0.1687 | 300 | 0.001 | 0.069 |
0.2250 | 400 | 0.0015 | 0.0651 |
0.2812 | 500 | 0.002 | 0.068 |
0.3375 | 600 | 0.0023 | 0.0704 |
0.3937 | 700 | 0.0009 | 0.068 |
0.4499 | 800 | 0.0011 | 0.0689 |
0.5062 | 900 | 0.0009 | 0.069 |
0.5624 | 1000 | 0.0014 | 0.0692 |
0.6187 | 1100 | 0.0061 | 0.0696 |
0.6749 | 1200 | 0.0014 | 0.0683 |
0.7312 | 1300 | 0.0109 | 0.071 |
0.7874 | 1400 | 0.0016 | 0.0715 |
0.8436 | 1500 | 0.001 | 0.0695 |
0.8999 | 1600 | 0.0012 | 0.0698 |
0.9561 | 1700 | 0.0012 | 0.0713 |
0.0006 | 1 | 0.0029 | - |
0.0562 | 100 | 0.0008 | 0.077 |
0.1125 | 200 | 0.0157 | 0.0892 |
0.1687 | 300 | 0.0016 | 0.0725 |
0.2250 | 400 | 0.0003 | 0.0643 |
0.2812 | 500 | 0.0003 | 0.0689 |
0.3375 | 600 | 0.0002 | 0.0704 |
0.3937 | 700 | 0.0001 | 0.0681 |
0.4499 | 800 | 0.0001 | 0.0679 |
0.5062 | 900 | 0.0003 | 0.0668 |
0.5624 | 1000 | 0.0001 | 0.0699 |
0.6187 | 1100 | 0.0001 | 0.0709 |
0.6749 | 1200 | 0.0001 | 0.0675 |
0.7312 | 1300 | 0.0002 | 0.0724 |
0.7874 | 1400 | 0.0004 | 0.0732 |
0.8436 | 1500 | 0.0001 | 0.0715 |
0.8999 | 1600 | 0.0001 | 0.0698 |
0.9561 | 1700 | 0.0001 | 0.072 |
0.0006 | 1 | 0.0023 | - |
0.0562 | 100 | 0.0003 | 0.0672 |
0.1125 | 200 | 0.0005 | 0.073 |
0.1687 | 300 | 0.0109 | 0.0665 |
0.2250 | 400 | 0.0002 | 0.0661 |
0.2812 | 500 | 0.0004 | 0.0754 |
0.3375 | 600 | 0.0001 | 0.0765 |
0.3937 | 700 | 0.0001 | 0.0735 |
0.4499 | 800 | 0.0002 | 0.0736 |
0.5062 | 900 | 0.0001 | 0.0716 |
0.5624 | 1000 | 0.0001 | 0.0758 |
0.6187 | 1100 | 0.0001 | 0.0762 |
0.6749 | 1200 | 0.0001 | 0.0702 |
0.7312 | 1300 | 0.0001 | 0.0755 |
0.7874 | 1400 | 0.0 | 0.0751 |
0.8436 | 1500 | 0.0001 | 0.0705 |
0.8999 | 1600 | 0.0001 | 0.0734 |
0.9561 | 1700 | 0.0001 | 0.0728 |
0.0006 | 1 | 0.0048 | - |
0.0562 | 100 | 0.0003 | 0.0683 |
0.1125 | 200 | 0.0001 | 0.0839 |
0.1687 | 300 | 0.0001 | 0.0836 |
0.2250 | 400 | 0.0009 | 0.0848 |
0.2812 | 500 | 0.0334 | 0.0874 |
0.3375 | 600 | 0.0002 | 0.0848 |
0.3937 | 700 | 0.0001 | 0.0774 |
0.4499 | 800 | 0.0001 | 0.0712 |
0.5062 | 900 | 0.0001 | 0.0792 |
0.5624 | 1000 | 0.0001 | 0.0778 |
0.6187 | 1100 | 0.0002 | 0.0787 |
0.6749 | 1200 | 0.0001 | 0.0737 |
0.7312 | 1300 | 0.0001 | 0.0788 |
0.7874 | 1400 | 0.0001 | 0.0795 |
0.8436 | 1500 | 0.0001 | 0.0729 |
0.8999 | 1600 | 0.0001 | 0.0745 |
0.9561 | 1700 | 0.0001 | 0.0771 |
0.0006 | 1 | 0.0017 | - |
0.0562 | 100 | 0.0002 | 0.0732 |
0.1125 | 200 | 0.0001 | 0.0793 |
0.1687 | 300 | 0.0001 | 0.0776 |
0.2250 | 400 | 0.0002 | 0.0737 |
0.2812 | 500 | 0.0001 | 0.0791 |
0.3375 | 600 | 0.0001 | 0.0791 |
0.3937 | 700 | 0.0 | 0.0797 |
0.4499 | 800 | 0.0001 | 0.076 |
0.5062 | 900 | 0.0001 | 0.077 |
0.5624 | 1000 | 0.0 | 0.0802 |
0.6187 | 1100 | 0.0 | 0.0815 |
0.6749 | 1200 | 0.0001 | 0.0776 |
0.7312 | 1300 | 0.0 | 0.0823 |
0.7874 | 1400 | 0.0001 | 0.0804 |
0.8436 | 1500 | 0.0 | 0.078 |
0.8999 | 1600 | 0.0 | 0.0788 |
0.9561 | 1700 | 0.0 | 0.079 |
0.0003 | 1 | 0.0017 | - |
0.0281 | 100 | 0.0002 | 0.0735 |
0.0562 | 200 | 0.0001 | 0.0806 |
0.0844 | 300 | 0.0001 | 0.0838 |
0.1125 | 400 | 0.0003 | 0.0765 |
0.1406 | 500 | 0.009 | 0.0841 |
0.1687 | 600 | 0.0009 | 0.092 |
0.1969 | 700 | 0.0003 | 0.0965 |
0.2250 | 800 | 0.0005 | 0.0784 |
0.2531 | 900 | 0.0001 | 0.0917 |
0.2812 | 1000 | 0.0001 | 0.0924 |
0.3093 | 1100 | 0.0001 | 0.0924 |
0.3375 | 1200 | 0.0001 | 0.0888 |
0.3656 | 1300 | 0.0001 | 0.0905 |
0.3937 | 1400 | 0.0001 | 0.0874 |
0.4218 | 1500 | 0.0001 | 0.0912 |
0.4499 | 1600 | 0.0002 | 0.089 |
0.4781 | 1700 | 0.0 | 0.0891 |
0.5062 | 1800 | 0.0001 | 0.0885 |
0.5343 | 1900 | 0.0 | 0.0898 |
0.5624 | 2000 | 0.0001 | 0.0875 |
0.5906 | 2100 | 0.0001 | 0.0906 |
0.6187 | 2200 | 0.0 | 0.0911 |
0.6468 | 2300 | 0.0001 | 0.0934 |
0.6749 | 2400 | 0.0 | 0.0896 |
0.7030 | 2500 | 0.0 | 0.0895 |
0.7312 | 2600 | 0.0371 | 0.092 |
0.7593 | 2700 | 0.0 | 0.0889 |
0.7874 | 2800 | 0.0 | 0.0895 |
0.8155 | 2900 | 0.0057 | 0.091 |
0.8436 | 3000 | 0.0 | 0.0931 |
0.8718 | 3100 | 0.0 | 0.0889 |
0.8999 | 3200 | 0.0 | 0.0909 |
0.9280 | 3300 | 0.0 | 0.0891 |
0.9561 | 3400 | 0.0 | 0.0908 |
0.9843 | 3500 | 0.0 | 0.0885 |
0.0003 | 1 | 0.0018 | - |
0.0281 | 100 | 0.0003 | 0.0758 |
0.0562 | 200 | 0.0025 | 0.0739 |
0.0844 | 300 | 0.0182 | 0.0954 |
0.1125 | 400 | 0.0041 | 0.0794 |
0.1406 | 500 | 0.0009 | 0.082 |
0.1687 | 600 | 0.0005 | 0.0753 |
0.1969 | 700 | 0.0001 | 0.0859 |
0.2250 | 800 | 0.0001 | 0.0851 |
0.2531 | 900 | 0.0001 | 0.0764 |
0.2812 | 1000 | 0.0 | 0.0877 |
0.3093 | 1100 | 0.0 | 0.081 |
0.3375 | 1200 | 0.0001 | 0.0755 |
0.3656 | 1300 | 0.0001 | 0.0818 |
0.3937 | 1400 | 0.0001 | 0.0837 |
0.4218 | 1500 | 0.0001 | 0.0838 |
0.4499 | 1600 | 0.0 | 0.081 |
0.4781 | 1700 | 0.0 | 0.0858 |
0.5062 | 1800 | 0.0001 | 0.0858 |
0.5343 | 1900 | 0.0003 | 0.0844 |
0.5624 | 2000 | 0.0001 | 0.0864 |
0.5906 | 2100 | 0.0 | 0.0842 |
0.6187 | 2200 | 0.0001 | 0.0847 |
0.6468 | 2300 | 0.0 | 0.0864 |
0.6749 | 2400 | 0.0 | 0.0884 |
0.7030 | 2500 | 0.0 | 0.0906 |
0.7312 | 2600 | 0.0359 | 0.0863 |
0.7593 | 2700 | 0.0 | 0.0839 |
0.7874 | 2800 | 0.0001 | 0.0942 |
0.8155 | 2900 | 0.0061 | 0.0944 |
0.8436 | 3000 | 0.0 | 0.0954 |
0.8718 | 3100 | 0.0 | 0.0888 |
0.8999 | 3200 | 0.0 | 0.0915 |
0.9280 | 3300 | 0.0 | 0.093 |
0.9561 | 3400 | 0.0 | 0.0931 |
0.9843 | 3500 | 0.0 | 0.0897 |
0.0003 | 1 | 0.0016 | - |
0.025 | 100 | 0.0023 | 0.0697 |
0.05 | 200 | 0.0022 | 0.0732 |
0.075 | 300 | 0.0007 | 0.0696 |
0.1 | 400 | 0.0004 | 0.0699 |
0.125 | 500 | 0.0026 | 0.07 |
0.15 | 600 | 0.0552 | 0.0709 |
0.175 | 700 | 0.0022 | 0.0691 |
0.2 | 800 | 0.0005 | 0.0672 |
0.225 | 900 | 0.0076 | 0.0677 |
0.25 | 1000 | 0.0006 | 0.0689 |
0.275 | 1100 | 0.0002 | 0.0708 |
0.3 | 1200 | 0.0613 | 0.0659 |
0.325 | 1300 | 0.0008 | 0.0683 |
0.35 | 1400 | 0.063 | 0.0678 |
0.375 | 1500 | 0.0562 | 0.071 |
0.4 | 1600 | 0.0008 | 0.0684 |
0.425 | 1700 | 0.0002 | 0.073 |
0.45 | 1800 | 0.0004 | 0.0719 |
0.475 | 1900 | 0.0003 | 0.0747 |
0.5 | 2000 | 0.0002 | 0.0712 |
0.525 | 2100 | 0.0001 | 0.0742 |
0.55 | 2200 | 0.0001 | 0.0716 |
0.575 | 2300 | 0.0019 | 0.0734 |
0.6 | 2400 | 0.0003 | 0.0748 |
0.625 | 2500 | 0.0543 | 0.0757 |
0.65 | 2600 | 0.0009 | 0.0748 |
0.675 | 2700 | 0.0001 | 0.0709 |
0.7 | 2800 | 0.0002 | 0.0722 |
0.725 | 2900 | 0.0005 | 0.0727 |
0.75 | 3000 | 0.0002 | 0.0755 |
0.775 | 3100 | 0.0002 | 0.0687 |
0.8 | 3200 | 0.0022 | 0.0734 |
0.825 | 3300 | 0.0002 | 0.07 |
0.85 | 3400 | 0.0001 | 0.0737 |
0.875 | 3500 | 0.0001 | 0.0694 |
0.9 | 3600 | 0.0002 | 0.0732 |
0.925 | 3700 | 0.0002 | 0.0701 |
0.95 | 3800 | 0.0002 | 0.0714 |
0.975 | 3900 | 0.0005 | 0.0676 |
1.0 | 4000 | 0.0001 | 0.074 |
1.025 | 4100 | 0.0036 | 0.0727 |
1.05 | 4200 | 0.0001 | 0.0731 |
1.075 | 4300 | 0.0001 | 0.0711 |
1.1 | 4400 | 0.0394 | 0.076 |
1.125 | 4500 | 0.0001 | 0.0746 |
1.15 | 4600 | 0.0001 | 0.0715 |
1.175 | 4700 | 0.0003 | 0.0723 |
1.2 | 4800 | 0.0002 | 0.0743 |
1.225 | 4900 | 0.0003 | 0.0758 |
1.25 | 5000 | 0.0088 | 0.0705 |
1.275 | 5100 | 0.0001 | 0.0748 |
1.3 | 5200 | 0.0001 | 0.0735 |
1.325 | 5300 | 0.0002 | 0.0747 |
1.35 | 5400 | 0.0001 | 0.0706 |
1.375 | 5500 | 0.0001 | 0.0757 |
1.4 | 5600 | 0.0001 | 0.0739 |
1.425 | 5700 | 0.0003 | 0.0752 |
1.45 | 5800 | 0.0001 | 0.0713 |
1.475 | 5900 | 0.0038 | 0.0774 |
1.5 | 6000 | 0.0001 | 0.0748 |
1.525 | 6100 | 0.0001 | 0.0736 |
1.55 | 6200 | 0.0003 | 0.0721 |
1.575 | 6300 | 0.0001 | 0.0764 |
1.6 | 6400 | 0.0001 | 0.0754 |
1.625 | 6500 | 0.0058 | 0.0717 |
1.65 | 6600 | 0.0002 | 0.0724 |
1.675 | 6700 | 0.0001 | 0.0745 |
1.7 | 6800 | 0.003 | 0.0765 |
1.725 | 6900 | 0.0001 | 0.0706 |
1.75 | 7000 | 0.0 | 0.0747 |
1.775 | 7100 | 0.0003 | 0.0745 |
1.8 | 7200 | 0.0042 | 0.0758 |
1.825 | 7300 | 0.0001 | 0.0717 |
1.85 | 7400 | 0.0001 | 0.0771 |
1.875 | 7500 | 0.0002 | 0.0742 |
1.9 | 7600 | 0.0001 | 0.0751 |
1.925 | 7700 | 0.0032 | 0.071 |
1.95 | 7800 | 0.0001 | 0.0768 |
1.975 | 7900 | 0.0001 | 0.0743 |
2.0 | 8000 | 0.0001 | 0.0737 |
2.025 | 8100 | 0.0002 | 0.0722 |
2.05 | 8200 | 0.0001 | 0.0764 |
2.075 | 8300 | 0.0 | 0.0759 |
2.1 | 8400 | 0.0001 | 0.0723 |
2.125 | 8500 | 0.0 | 0.0727 |
2.15 | 8600 | 0.0029 | 0.0759 |
2.175 | 8700 | 0.0 | 0.0786 |
2.2 | 8800 | 0.0036 | 0.0724 |
2.225 | 8900 | 0.0001 | 0.077 |
2.25 | 9000 | 0.0001 | 0.0755 |
2.275 | 9100 | 0.0001 | 0.0764 |
2.3 | 9200 | 0.0 | 0.0717 |
2.325 | 9300 | 0.0001 | 0.0765 |
2.35 | 9400 | 0.0 | 0.074 |
2.375 | 9500 | 0.0024 | 0.0753 |
2.4 | 9600 | 0.0 | 0.0715 |
2.425 | 9700 | 0.0 | 0.0771 |
2.45 | 9800 | 0.0001 | 0.0746 |
2.475 | 9900 | 0.0001 | 0.0734 |
2.5 | 10000 | 0.0001 | 0.0721 |
2.525 | 10100 | 0.0001 | 0.0768 |
2.55 | 10200 | 0.0001 | 0.0774 |
2.575 | 10300 | 0.0 | 0.0736 |
2.6 | 10400 | 0.0029 | 0.0746 |
2.625 | 10500 | 0.0001 | 0.0769 |
2.65 | 10600 | 0.0001 | 0.0787 |
2.675 | 10700 | 0.0001 | 0.0718 |
2.7 | 10800 | 0.0001 | 0.0758 |
2.725 | 10900 | 0.0001 | 0.0749 |
2.75 | 11000 | 0.0 | 0.0763 |
2.775 | 11100 | 0.0001 | 0.0722 |
2.8 | 11200 | 0.0 | 0.0773 |
2.825 | 11300 | 0.0024 | 0.0746 |
2.85 | 11400 | 0.0 | 0.0756 |
2.875 | 11500 | 0.0 | 0.0718 |
2.9 | 11600 | 0.0001 | 0.0773 |
2.925 | 11700 | 0.0001 | 0.0761 |
2.95 | 11800 | 0.0001 | 0.0752 |
2.975 | 11900 | 0.0 | 0.074 |
3.0 | 12000 | 0.0401 | 0.0779 |
3.025 | 12100 | 0.0 | 0.0782 |
3.05 | 12200 | 0.0025 | 0.0738 |
3.075 | 12300 | 0.0001 | 0.0743 |
3.1 | 12400 | 0.0 | 0.076 |
3.125 | 12500 | 0.0001 | 0.078 |
3.15 | 12600 | 0.0048 | 0.0716 |
3.175 | 12700 | 0.0001 | 0.076 |
3.2 | 12800 | 0.0 | 0.0745 |
3.225 | 12900 | 0.0001 | 0.0758 |
3.25 | 13000 | 0.0 | 0.0715 |
3.275 | 13100 | 0.0024 | 0.0764 |
3.3 | 13200 | 0.0001 | 0.0747 |
3.325 | 13300 | 0.0 | 0.0767 |
3.35 | 13400 | 0.0001 | 0.0729 |
3.375 | 13500 | 0.0 | 0.0782 |
3.4 | 13600 | 0.0 | 0.076 |
3.425 | 13700 | 0.0 | 0.075 |
3.45 | 13800 | 0.0001 | 0.0734 |
3.475 | 13900 | 0.0 | 0.077 |
3.5 | 14000 | 0.0026 | 0.0768 |
3.525 | 14100 | 0.0047 | 0.0729 |
3.55 | 14200 | 0.0 | 0.074 |
3.575 | 14300 | 0.0001 | 0.0759 |
3.6 | 14400 | 0.0 | 0.078 |
3.625 | 14500 | 0.0001 | 0.0716 |
3.65 | 14600 | 0.0 | 0.0757 |
3.675 | 14700 | 0.0001 | 0.075 |
3.7 | 14800 | 0.0045 | 0.0769 |
3.725 | 14900 | 0.003 | 0.0728 |
3.75 | 15000 | 0.0 | 0.0779 |
3.775 | 15100 | 0.0 | 0.0751 |
3.8 | 15200 | 0.0001 | 0.0765 |
3.825 | 15300 | 0.0001 | 0.0722 |
3.85 | 15400 | 0.0 | 0.0778 |
3.875 | 15500 | 0.0001 | 0.0753 |
3.9 | 15600 | 0.0001 | 0.0746 |
3.925 | 15700 | 0.0 | 0.0734 |
3.95 | 15800 | 0.0026 | 0.0772 |
3.975 | 15900 | 0.0 | 0.077 |
4.0 | 16000 | 0.0 | 0.0732 |
4.025 | 16100 | 0.0 | 0.0739 |
4.05 | 16200 | 0.0 | 0.076 |
4.075 | 16300 | 0.0001 | 0.0787 |
4.1 | 16400 | 0.0047 | 0.0721 |
4.125 | 16500 | 0.0001 | 0.0765 |
4.15 | 16600 | 0.0 | 0.0754 |
4.175 | 16700 | 0.0031 | 0.0769 |
4.2 | 16800 | 0.0001 | 0.0725 |
4.225 | 16900 | 0.0 | 0.0776 |
4.25 | 17000 | 0.0 | 0.0748 |
4.275 | 17100 | 0.0001 | 0.0763 |
4.3 | 17200 | 0.0 | 0.0722 |
4.325 | 17300 | 0.0 | 0.0779 |
4.35 | 17400 | 0.0 | 0.0756 |
4.375 | 17500 | 0.0 | 0.0746 |
4.4 | 17600 | 0.0026 | 0.0733 |
4.425 | 17700 | 0.0001 | 0.0771 |
4.45 | 17800 | 0.0 | 0.0773 |
4.475 | 17900 | 0.0 | 0.0732 |
4.5 | 18000 | 0.0001 | 0.0742 |
4.525 | 18100 | 0.0 | 0.0763 |
4.55 | 18200 | 0.0001 | 0.0786 |
4.575 | 18300 | 0.0001 | 0.0719 |
4.6 | 18400 | 0.0 | 0.0763 |
4.625 | 18500 | 0.0029 | 0.0751 |
4.65 | 18600 | 0.0 | 0.0766 |
4.675 | 18700 | 0.0 | 0.0723 |
4.7 | 18800 | 0.0 | 0.0774 |
4.725 | 18900 | 0.0001 | 0.0746 |
4.75 | 19000 | 0.0 | 0.076 |
4.775 | 19100 | 0.0 | 0.0719 |
4.8 | 19200 | 0.0001 | 0.0775 |
4.825 | 19300 | 0.0001 | 0.0753 |
4.85 | 19400 | 0.0026 | 0.0747 |
4.875 | 19500 | 0.0 | 0.0734 |
4.9 | 19600 | 0.0421 | 0.0772 |
4.925 | 19700 | 0.0001 | 0.0772 |
4.95 | 19800 | 0.0 | 0.0731 |
4.975 | 19900 | 0.0001 | 0.0741 |
5.0 | 20000 | 0.0 | 0.0761 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.40.2
- PyTorch: 2.3.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.19.1
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}
}