metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: prlv sepa ecole montaigne cotisation scolaire
- text: facture carte du pharmacie pont neuf carte
- text: virement sortant facture soleil energie
- text: leçon de surf hossegor surf club carte
- text: virement initie application mobile vers comptes joints
pipeline_tag: text-classification
inference: true
model-index:
- name: SetFit
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.7007575757575758
name: Accuracy
SetFit
This is a SetFit model that can be used for Text Classification. 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
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 44 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 |
---|---|
Other / kids |
|
Bank services / withdrawal |
|
Housing / rent |
|
Leisure & Entertainment / sports & hobbies |
|
Transportation / car loan & leasing |
|
Healthy & Beauty / veterinary |
|
Transportation / taxi & carpool |
|
Healthy & Beauty / doctor fees |
|
Food & Drinks / eating out |
|
Transportation / other |
|
Healthy & Beauty / beauty & self-care |
|
Bank services / other |
|
Bank services / general fees |
|
Leisure & Entertainment / culture & events |
|
Other / taxes |
|
Housing / services & maintenance |
|
Housing / utilities & bills |
|
Investment / real estate |
|
Recurrent Payments / subscription |
|
Other / other |
|
Shopping / electronics & multimedia |
|
Bank services / transfers |
|
Investment / retirement & savings |
|
Housing / other |
|
Housing / house loan |
|
Recurrent Payments / other |
|
Transportation / fuel |
|
Other / pets |
|
Transportation / maitenance |
|
Food & Drinks / groceries |
|
Recurrent Payments / insurance |
|
Food & Drinks / other |
|
Recurrent Payments / loans |
|
Transportation / public transportation |
|
Investment / securities |
|
Shopping / housing equipment |
|
Healthy & Beauty / other |
|
Healthy & Beauty / pharmacy |
|
Shopping / clothing |
|
Shopping / sporting goods |
|
Leisure & Entertainment / travel |
|
Investment / other |
|
Leisure & Entertainment / other |
|
Shopping / other |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.7008 |
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("HEN10/setfit-particular-transaction-solon-embeddings-labels-large-v4")
# Run inference
preds = model("leçon de surf hossegor surf club carte")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 5.9159 | 12 |
Label | Training Sample Count |
---|---|
Housing / rent | 20 |
Housing / house loan | 20 |
Housing / utilities & bills | 20 |
Housing / services & maintenance | 20 |
Housing / other | 20 |
Food & Drinks / groceries | 20 |
Food & Drinks / eating out | 20 |
Food & Drinks / other | 20 |
Leisure & Entertainment / sports & hobbies | 20 |
Leisure & Entertainment / culture & events | 20 |
Leisure & Entertainment / travel | 20 |
Leisure & Entertainment / other | 20 |
Transportation / car loan & leasing | 20 |
Transportation / fuel | 20 |
Transportation / public transportation | 20 |
Transportation / taxi & carpool | 20 |
Transportation / maitenance | 20 |
Transportation / other | 20 |
Recurrent Payments / loans | 20 |
Recurrent Payments / insurance | 20 |
Recurrent Payments / subscription | 20 |
Recurrent Payments / other | 20 |
Investment / securities | 20 |
Investment / retirement & savings | 20 |
Investment / real estate | 20 |
Investment / other | 20 |
Shopping / clothing | 20 |
Shopping / electronics & multimedia | 20 |
Shopping / sporting goods | 20 |
Shopping / housing equipment | 20 |
Shopping / other | 20 |
Healthy & Beauty / doctor fees | 20 |
Healthy & Beauty / pharmacy | 20 |
Healthy & Beauty / beauty & self-care | 20 |
Healthy & Beauty / veterinary | 20 |
Healthy & Beauty / other | 20 |
Bank services / transfers | 20 |
Bank services / withdrawal | 20 |
Bank services / general fees | 20 |
Bank services / other | 20 |
Other / taxes | 20 |
Other / kids | 20 |
Other / pets | 20 |
Other / other | 20 |
Training Hyperparameters
- batch_size: (26, 26)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: True
- use_amp: False
- warmup_proportion: 0.1
- seed: 6
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0000 | 1 | 0.2084 | - |
0.0012 | 50 | 0.2041 | - |
0.0000 | 1 | 0.1841 | - |
0.0017 | 50 | 0.219 | - |
0.0034 | 100 | 0.2197 | - |
0.0052 | 150 | 0.1724 | - |
0.0069 | 200 | 0.2291 | - |
0.0086 | 250 | 0.1693 | - |
0.0103 | 300 | 0.0832 | - |
0.0120 | 350 | 0.1414 | - |
0.0137 | 400 | 0.0989 | - |
0.0155 | 450 | 0.0962 | - |
0.0172 | 500 | 0.1132 | - |
0.0189 | 550 | 0.1 | - |
0.0206 | 600 | 0.0561 | - |
0.0223 | 650 | 0.0851 | - |
0.0240 | 700 | 0.0762 | - |
0.0258 | 750 | 0.0876 | - |
0.0275 | 800 | 0.0414 | - |
0.0292 | 850 | 0.0368 | - |
0.0309 | 900 | 0.0409 | - |
0.0326 | 950 | 0.0212 | - |
0.0344 | 1000 | 0.0175 | - |
0.0361 | 1050 | 0.05 | - |
0.0378 | 1100 | 0.0848 | - |
0.0395 | 1150 | 0.0549 | - |
0.0412 | 1200 | 0.0395 | - |
0.0429 | 1250 | 0.029 | - |
0.0447 | 1300 | 0.0047 | - |
0.0464 | 1350 | 0.0387 | - |
0.0481 | 1400 | 0.0268 | - |
0.0498 | 1450 | 0.0531 | - |
0.0515 | 1500 | 0.0038 | - |
0.0532 | 1550 | 0.0226 | - |
0.0550 | 1600 | 0.0349 | - |
0.0567 | 1650 | 0.0106 | - |
0.0584 | 1700 | 0.0049 | - |
0.0601 | 1750 | 0.0171 | - |
0.0618 | 1800 | 0.0066 | - |
0.0636 | 1850 | 0.0066 | - |
0.0653 | 1900 | 0.0039 | - |
0.0670 | 1950 | 0.0016 | - |
0.0687 | 2000 | 0.0414 | - |
0.0704 | 2050 | 0.0172 | - |
0.0721 | 2100 | 0.0039 | - |
0.0739 | 2150 | 0.0036 | - |
0.0756 | 2200 | 0.0334 | - |
0.0773 | 2250 | 0.0025 | - |
0.0790 | 2300 | 0.0022 | - |
0.0807 | 2350 | 0.0017 | - |
0.0825 | 2400 | 0.0015 | - |
0.0842 | 2450 | 0.0125 | - |
0.0859 | 2500 | 0.0023 | - |
0.0876 | 2550 | 0.0023 | - |
0.0893 | 2600 | 0.0013 | - |
0.0910 | 2650 | 0.0728 | - |
0.0928 | 2700 | 0.0141 | - |
0.0945 | 2750 | 0.0332 | - |
0.0962 | 2800 | 0.0632 | - |
0.0979 | 2850 | 0.0042 | - |
0.0996 | 2900 | 0.0117 | - |
0.1013 | 2950 | 0.0014 | - |
0.1031 | 3000 | 0.0013 | - |
0.1048 | 3050 | 0.0464 | - |
0.1065 | 3100 | 0.0031 | - |
0.1082 | 3150 | 0.0007 | - |
0.1099 | 3200 | 0.0008 | - |
0.1117 | 3250 | 0.001 | - |
0.1134 | 3300 | 0.001 | - |
0.1151 | 3350 | 0.0016 | - |
0.1168 | 3400 | 0.0006 | - |
0.1185 | 3450 | 0.0005 | - |
0.1202 | 3500 | 0.0006 | - |
0.1220 | 3550 | 0.0008 | - |
0.1237 | 3600 | 0.0368 | - |
0.1254 | 3650 | 0.0026 | - |
0.1271 | 3700 | 0.0372 | - |
0.1288 | 3750 | 0.0006 | - |
0.1305 | 3800 | 0.0005 | - |
0.1323 | 3850 | 0.0276 | - |
0.1340 | 3900 | 0.0007 | - |
0.1357 | 3950 | 0.0013 | - |
0.1374 | 4000 | 0.0008 | - |
0.1391 | 4050 | 0.0018 | - |
0.1409 | 4100 | 0.0292 | - |
0.1426 | 4150 | 0.0102 | - |
0.1443 | 4200 | 0.0093 | - |
0.1460 | 4250 | 0.0022 | - |
0.1477 | 4300 | 0.0032 | - |
0.1494 | 4350 | 0.001 | - |
0.1512 | 4400 | 0.0006 | - |
0.1529 | 4450 | 0.0007 | - |
0.1546 | 4500 | 0.0007 | - |
0.1563 | 4550 | 0.0007 | - |
0.1580 | 4600 | 0.0007 | - |
0.1597 | 4650 | 0.0011 | - |
0.1615 | 4700 | 0.0008 | - |
0.1632 | 4750 | 0.0374 | - |
0.1649 | 4800 | 0.0004 | - |
0.1666 | 4850 | 0.0008 | - |
0.1683 | 4900 | 0.005 | - |
0.1701 | 4950 | 0.0013 | - |
0.1718 | 5000 | 0.0016 | - |
0.1735 | 5050 | 0.0006 | - |
0.1752 | 5100 | 0.0007 | - |
0.1769 | 5150 | 0.0007 | - |
0.1786 | 5200 | 0.0004 | - |
0.1804 | 5250 | 0.0003 | - |
0.1821 | 5300 | 0.0004 | - |
0.1838 | 5350 | 0.0004 | - |
0.1855 | 5400 | 0.0002 | - |
0.1872 | 5450 | 0.036 | - |
0.1890 | 5500 | 0.0003 | - |
0.1907 | 5550 | 0.0003 | - |
0.1924 | 5600 | 0.0003 | - |
0.1941 | 5650 | 0.0006 | - |
0.1958 | 5700 | 0.0005 | - |
0.1975 | 5750 | 0.0057 | - |
0.1993 | 5800 | 0.0008 | - |
0.2010 | 5850 | 0.0002 | - |
0.2027 | 5900 | 0.0013 | - |
0.2044 | 5950 | 0.0004 | - |
0.2061 | 6000 | 0.0002 | - |
0.2078 | 6050 | 0.0002 | - |
0.2096 | 6100 | 0.0015 | - |
0.2113 | 6150 | 0.037 | - |
0.2130 | 6200 | 0.0003 | - |
0.2147 | 6250 | 0.0003 | - |
0.2164 | 6300 | 0.0002 | - |
0.2182 | 6350 | 0.0003 | - |
0.2199 | 6400 | 0.0005 | - |
0.2216 | 6450 | 0.0004 | - |
0.2233 | 6500 | 0.0042 | - |
0.2250 | 6550 | 0.0004 | - |
0.2267 | 6600 | 0.0006 | - |
0.2285 | 6650 | 0.0004 | - |
0.2302 | 6700 | 0.0005 | - |
0.2319 | 6750 | 0.0021 | - |
0.2336 | 6800 | 0.0003 | - |
0.2353 | 6850 | 0.0003 | - |
0.2370 | 6900 | 0.0005 | - |
0.2388 | 6950 | 0.0003 | - |
0.2405 | 7000 | 0.0002 | - |
0.2422 | 7050 | 0.0003 | - |
0.2439 | 7100 | 0.0004 | - |
0.2456 | 7150 | 0.0005 | - |
0.2474 | 7200 | 0.0005 | - |
0.2491 | 7250 | 0.001 | - |
0.2508 | 7300 | 0.0055 | - |
0.2525 | 7350 | 0.0005 | - |
0.2542 | 7400 | 0.0005 | - |
0.2559 | 7450 | 0.0007 | - |
0.2577 | 7500 | 0.0002 | - |
0.2594 | 7550 | 0.0745 | - |
0.2611 | 7600 | 0.0003 | - |
0.2628 | 7650 | 0.0002 | - |
0.2645 | 7700 | 0.0002 | - |
0.2662 | 7750 | 0.0004 | - |
0.2680 | 7800 | 0.0002 | - |
0.2697 | 7850 | 0.0002 | - |
0.2714 | 7900 | 0.0003 | - |
0.2731 | 7950 | 0.0002 | - |
0.2748 | 8000 | 0.0002 | - |
0.2766 | 8050 | 0.0003 | - |
0.2783 | 8100 | 0.0003 | - |
0.2800 | 8150 | 0.0313 | - |
0.2817 | 8200 | 0.0007 | - |
0.2834 | 8250 | 0.0002 | - |
0.2851 | 8300 | 0.0003 | - |
0.2869 | 8350 | 0.0003 | - |
0.2886 | 8400 | 0.0003 | - |
0.2903 | 8450 | 0.0002 | - |
0.2920 | 8500 | 0.0003 | - |
0.2937 | 8550 | 0.0154 | - |
0.2955 | 8600 | 0.0003 | - |
0.2972 | 8650 | 0.0005 | - |
0.2989 | 8700 | 0.0041 | - |
0.3006 | 8750 | 0.0003 | - |
0.3023 | 8800 | 0.0002 | - |
0.3040 | 8850 | 0.0003 | - |
0.3058 | 8900 | 0.0001 | - |
0.3075 | 8950 | 0.0005 | - |
0.3092 | 9000 | 0.0022 | - |
0.3109 | 9050 | 0.0002 | - |
0.3126 | 9100 | 0.0003 | - |
0.3143 | 9150 | 0.0002 | - |
0.3161 | 9200 | 0.0001 | - |
0.3178 | 9250 | 0.0002 | - |
0.3195 | 9300 | 0.0001 | - |
0.3212 | 9350 | 0.0002 | - |
0.3229 | 9400 | 0.0002 | - |
0.3247 | 9450 | 0.0003 | - |
0.3264 | 9500 | 0.0017 | - |
0.3281 | 9550 | 0.003 | - |
0.3298 | 9600 | 0.0039 | - |
0.3315 | 9650 | 0.0028 | - |
0.3332 | 9700 | 0.0037 | - |
0.3350 | 9750 | 0.0005 | - |
0.3367 | 9800 | 0.0352 | - |
0.3384 | 9850 | 0.0006 | - |
0.3401 | 9900 | 0.0006 | - |
0.3418 | 9950 | 0.0004 | - |
0.3435 | 10000 | 0.0002 | - |
0.3453 | 10050 | 0.0012 | - |
0.3470 | 10100 | 0.0002 | - |
0.3487 | 10150 | 0.0003 | - |
0.3504 | 10200 | 0.0002 | - |
0.3521 | 10250 | 0.0002 | - |
0.3539 | 10300 | 0.0004 | - |
0.3556 | 10350 | 0.0003 | - |
0.3573 | 10400 | 0.0003 | - |
0.3590 | 10450 | 0.0002 | - |
0.3607 | 10500 | 0.0004 | - |
0.3624 | 10550 | 0.0004 | - |
0.3642 | 10600 | 0.0371 | - |
0.3659 | 10650 | 0.0005 | - |
0.3676 | 10700 | 0.0236 | - |
0.3693 | 10750 | 0.0002 | - |
0.3710 | 10800 | 0.0002 | - |
0.3727 | 10850 | 0.0003 | - |
0.3745 | 10900 | 0.0004 | - |
0.3762 | 10950 | 0.0002 | - |
0.3779 | 11000 | 0.0002 | - |
0.3796 | 11050 | 0.0002 | - |
0.3813 | 11100 | 0.0001 | - |
0.3831 | 11150 | 0.0001 | - |
0.3848 | 11200 | 0.0002 | - |
0.3865 | 11250 | 0.0002 | - |
0.3882 | 11300 | 0.0001 | - |
0.3899 | 11350 | 0.0001 | - |
0.3916 | 11400 | 0.0351 | - |
0.3934 | 11450 | 0.0003 | - |
0.3951 | 11500 | 0.0001 | - |
0.3968 | 11550 | 0.0326 | - |
0.3985 | 11600 | 0.0001 | - |
0.4002 | 11650 | 0.0006 | - |
0.4020 | 11700 | 0.0002 | - |
0.4037 | 11750 | 0.0004 | - |
0.4054 | 11800 | 0.0002 | - |
0.4071 | 11850 | 0.0002 | - |
0.4088 | 11900 | 0.0001 | - |
0.4105 | 11950 | 0.0002 | - |
0.4123 | 12000 | 0.0002 | - |
0.4140 | 12050 | 0.0003 | - |
0.4157 | 12100 | 0.0003 | - |
0.4174 | 12150 | 0.0001 | - |
0.4191 | 12200 | 0.0001 | - |
0.4208 | 12250 | 0.0003 | - |
0.4226 | 12300 | 0.0001 | - |
0.4243 | 12350 | 0.0002 | - |
0.4260 | 12400 | 0.0003 | - |
0.4277 | 12450 | 0.0002 | - |
0.4294 | 12500 | 0.0002 | - |
0.4312 | 12550 | 0.0002 | - |
0.4329 | 12600 | 0.0002 | - |
0.4346 | 12650 | 0.0007 | - |
0.4363 | 12700 | 0.0002 | - |
0.4380 | 12750 | 0.0003 | - |
0.4397 | 12800 | 0.0001 | - |
0.4415 | 12850 | 0.0001 | - |
0.4432 | 12900 | 0.0002 | - |
0.4449 | 12950 | 0.001 | - |
0.4466 | 13000 | 0.0002 | - |
0.4483 | 13050 | 0.0002 | - |
0.4500 | 13100 | 0.0005 | - |
0.4518 | 13150 | 0.0002 | - |
0.4535 | 13200 | 0.0002 | - |
0.4552 | 13250 | 0.0001 | - |
0.4569 | 13300 | 0.0003 | - |
0.4586 | 13350 | 0.0013 | - |
0.4604 | 13400 | 0.0002 | - |
0.4621 | 13450 | 0.0372 | - |
0.4638 | 13500 | 0.0002 | - |
0.4655 | 13550 | 0.0003 | - |
0.4672 | 13600 | 0.0025 | - |
0.4689 | 13650 | 0.0002 | - |
0.4707 | 13700 | 0.0002 | - |
0.4724 | 13750 | 0.0001 | - |
0.4741 | 13800 | 0.0002 | - |
0.4758 | 13850 | 0.0001 | - |
0.4775 | 13900 | 0.0003 | - |
0.4792 | 13950 | 0.0026 | - |
0.4810 | 14000 | 0.0002 | - |
0.4827 | 14050 | 0.0002 | - |
0.4844 | 14100 | 0.0002 | - |
0.4861 | 14150 | 0.0002 | - |
0.4878 | 14200 | 0.0002 | - |
0.4896 | 14250 | 0.0002 | - |
0.4913 | 14300 | 0.0003 | - |
0.4930 | 14350 | 0.0002 | - |
0.4947 | 14400 | 0.0014 | - |
0.4964 | 14450 | 0.0002 | - |
0.4981 | 14500 | 0.0001 | - |
0.4999 | 14550 | 0.0002 | - |
0.5016 | 14600 | 0.0001 | - |
0.5033 | 14650 | 0.0002 | - |
0.5050 | 14700 | 0.0001 | - |
0.5067 | 14750 | 0.0002 | - |
0.5085 | 14800 | 0.0001 | - |
0.5102 | 14850 | 0.0001 | - |
0.5119 | 14900 | 0.0002 | - |
0.5136 | 14950 | 0.0001 | - |
0.5153 | 15000 | 0.0001 | - |
0.5170 | 15050 | 0.0001 | - |
0.5188 | 15100 | 0.0002 | - |
0.5205 | 15150 | 0.0002 | - |
0.5222 | 15200 | 0.0002 | - |
0.5239 | 15250 | 0.0001 | - |
0.5256 | 15300 | 0.0001 | - |
0.5273 | 15350 | 0.0001 | - |
0.5291 | 15400 | 0.0001 | - |
0.5308 | 15450 | 0.0001 | - |
0.5325 | 15500 | 0.0001 | - |
0.5342 | 15550 | 0.0001 | - |
0.5359 | 15600 | 0.0001 | - |
0.5377 | 15650 | 0.0001 | - |
0.5394 | 15700 | 0.0001 | - |
0.5411 | 15750 | 0.0001 | - |
0.5428 | 15800 | 0.0001 | - |
0.5445 | 15850 | 0.0002 | - |
0.5462 | 15900 | 0.0002 | - |
0.5480 | 15950 | 0.0001 | - |
0.5497 | 16000 | 0.0001 | - |
0.5514 | 16050 | 0.0001 | - |
0.5531 | 16100 | 0.0001 | - |
0.5548 | 16150 | 0.0001 | - |
0.5565 | 16200 | 0.0001 | - |
0.5583 | 16250 | 0.0001 | - |
0.5600 | 16300 | 0.0001 | - |
0.5617 | 16350 | 0.0001 | - |
0.5634 | 16400 | 0.0002 | - |
0.5651 | 16450 | 0.0001 | - |
0.5669 | 16500 | 0.0001 | - |
0.5686 | 16550 | 0.0001 | - |
0.5703 | 16600 | 0.0001 | - |
0.5720 | 16650 | 0.0002 | - |
0.5737 | 16700 | 0.0001 | - |
0.5754 | 16750 | 0.0001 | - |
0.5772 | 16800 | 0.0001 | - |
0.5789 | 16850 | 0.0001 | - |
0.5806 | 16900 | 0.0001 | - |
0.5823 | 16950 | 0.0001 | - |
0.5840 | 17000 | 0.0001 | - |
0.5857 | 17050 | 0.0002 | - |
0.5875 | 17100 | 0.0001 | - |
0.5892 | 17150 | 0.0001 | - |
0.5909 | 17200 | 0.0001 | - |
0.5926 | 17250 | 0.0001 | - |
0.5943 | 17300 | 0.0001 | - |
0.5961 | 17350 | 0.0001 | - |
0.5978 | 17400 | 0.0001 | - |
0.5995 | 17450 | 0.0001 | - |
0.6012 | 17500 | 0.0371 | - |
0.6029 | 17550 | 0.0001 | - |
0.6046 | 17600 | 0.0001 | - |
0.6064 | 17650 | 0.0001 | - |
0.6081 | 17700 | 0.0001 | - |
0.6098 | 17750 | 0.0001 | - |
0.6115 | 17800 | 0.0002 | - |
0.6132 | 17850 | 0.0007 | - |
0.6150 | 17900 | 0.0002 | - |
0.6167 | 17950 | 0.0001 | - |
0.6184 | 18000 | 0.0115 | - |
0.6201 | 18050 | 0.0001 | - |
0.6218 | 18100 | 0.0004 | - |
0.6235 | 18150 | 0.0002 | - |
0.6253 | 18200 | 0.0074 | - |
0.6270 | 18250 | 0.0325 | - |
0.6287 | 18300 | 0.0008 | - |
0.6304 | 18350 | 0.0007 | - |
0.6321 | 18400 | 0.0002 | - |
0.6338 | 18450 | 0.0005 | - |
0.6356 | 18500 | 0.0003 | - |
0.6373 | 18550 | 0.0003 | - |
0.6390 | 18600 | 0.0002 | - |
0.6407 | 18650 | 0.0003 | - |
0.6424 | 18700 | 0.0003 | - |
0.6442 | 18750 | 0.0002 | - |
0.6459 | 18800 | 0.0002 | - |
0.6476 | 18850 | 0.0002 | - |
0.6493 | 18900 | 0.0002 | - |
0.6510 | 18950 | 0.0001 | - |
0.6527 | 19000 | 0.0001 | - |
0.6545 | 19050 | 0.0003 | - |
0.6562 | 19100 | 0.0001 | - |
0.6579 | 19150 | 0.0001 | - |
0.6596 | 19200 | 0.0002 | - |
0.6613 | 19250 | 0.0002 | - |
0.6630 | 19300 | 0.0003 | - |
0.6648 | 19350 | 0.0186 | - |
0.6665 | 19400 | 0.0001 | - |
0.6682 | 19450 | 0.0002 | - |
0.6699 | 19500 | 0.0002 | - |
0.6716 | 19550 | 0.0001 | - |
0.6734 | 19600 | 0.0001 | - |
0.6751 | 19650 | 0.0001 | - |
0.6768 | 19700 | 0.0001 | - |
0.6785 | 19750 | 0.0001 | - |
0.6802 | 19800 | 0.0001 | - |
0.6819 | 19850 | 0.0001 | - |
0.6837 | 19900 | 0.0001 | - |
0.6854 | 19950 | 0.0371 | - |
0.6871 | 20000 | 0.0001 | - |
0.6888 | 20050 | 0.0001 | - |
0.6905 | 20100 | 0.0001 | - |
0.6922 | 20150 | 0.0001 | - |
0.6940 | 20200 | 0.0001 | - |
0.6957 | 20250 | 0.0001 | - |
0.6974 | 20300 | 0.0001 | - |
0.6991 | 20350 | 0.0001 | - |
0.7008 | 20400 | 0.0001 | - |
0.7026 | 20450 | 0.0001 | - |
0.7043 | 20500 | 0.0002 | - |
0.7060 | 20550 | 0.0001 | - |
0.7077 | 20600 | 0.0002 | - |
0.7094 | 20650 | 0.0001 | - |
0.7111 | 20700 | 0.0001 | - |
0.7129 | 20750 | 0.0001 | - |
0.7146 | 20800 | 0.0001 | - |
0.7163 | 20850 | 0.0001 | - |
0.7180 | 20900 | 0.0001 | - |
0.7197 | 20950 | 0.0001 | - |
0.7215 | 21000 | 0.0001 | - |
0.7232 | 21050 | 0.0001 | - |
0.7249 | 21100 | 0.0363 | - |
0.7266 | 21150 | 0.0001 | - |
0.7283 | 21200 | 0.0001 | - |
0.7300 | 21250 | 0.0001 | - |
0.7318 | 21300 | 0.0001 | - |
0.7335 | 21350 | 0.0001 | - |
0.7352 | 21400 | 0.0001 | - |
0.7369 | 21450 | 0.0001 | - |
0.7386 | 21500 | 0.0001 | - |
0.7403 | 21550 | 0.0001 | - |
0.7421 | 21600 | 0.0001 | - |
0.7438 | 21650 | 0.0001 | - |
0.7455 | 21700 | 0.0001 | - |
0.7472 | 21750 | 0.0001 | - |
0.7489 | 21800 | 0.0001 | - |
0.7507 | 21850 | 0.0001 | - |
0.7524 | 21900 | 0.0001 | - |
0.7541 | 21950 | 0.0001 | - |
0.7558 | 22000 | 0.0001 | - |
0.7575 | 22050 | 0.0358 | - |
0.7592 | 22100 | 0.0007 | - |
0.7610 | 22150 | 0.0001 | - |
0.7627 | 22200 | 0.0001 | - |
0.7644 | 22250 | 0.0001 | - |
0.7661 | 22300 | 0.0001 | - |
0.7678 | 22350 | 0.0001 | - |
0.7695 | 22400 | 0.0368 | - |
0.7713 | 22450 | 0.0001 | - |
0.7730 | 22500 | 0.0001 | - |
0.7747 | 22550 | 0.0001 | - |
0.7764 | 22600 | 0.0001 | - |
0.7781 | 22650 | 0.0001 | - |
0.7799 | 22700 | 0.0003 | - |
0.7816 | 22750 | 0.0001 | - |
0.7833 | 22800 | 0.0001 | - |
0.7850 | 22850 | 0.0001 | - |
0.7867 | 22900 | 0.0001 | - |
0.7884 | 22950 | 0.0001 | - |
0.7902 | 23000 | 0.0001 | - |
0.7919 | 23050 | 0.0001 | - |
0.7936 | 23100 | 0.0001 | - |
0.7953 | 23150 | 0.0001 | - |
0.7970 | 23200 | 0.0001 | - |
0.7987 | 23250 | 0.0001 | - |
0.8005 | 23300 | 0.0001 | - |
0.8022 | 23350 | 0.0001 | - |
0.8039 | 23400 | 0.0002 | - |
0.8056 | 23450 | 0.0001 | - |
0.8073 | 23500 | 0.0001 | - |
0.8091 | 23550 | 0.0001 | - |
0.8108 | 23600 | 0.0001 | - |
0.8125 | 23650 | 0.0001 | - |
0.8142 | 23700 | 0.0173 | - |
0.8159 | 23750 | 0.0001 | - |
0.8176 | 23800 | 0.0001 | - |
0.8194 | 23850 | 0.0001 | - |
0.8211 | 23900 | 0.0001 | - |
0.8228 | 23950 | 0.0001 | - |
0.8245 | 24000 | 0.0001 | - |
0.8262 | 24050 | 0.0001 | - |
0.8280 | 24100 | 0.0001 | - |
0.8297 | 24150 | 0.0001 | - |
0.8314 | 24200 | 0.0001 | - |
0.8331 | 24250 | 0.0001 | - |
0.8348 | 24300 | 0.0001 | - |
0.8365 | 24350 | 0.0001 | - |
0.8383 | 24400 | 0.0001 | - |
0.8400 | 24450 | 0.0001 | - |
0.8417 | 24500 | 0.0003 | - |
0.8434 | 24550 | 0.0002 | - |
0.8451 | 24600 | 0.0002 | - |
0.8468 | 24650 | 0.0001 | - |
0.8486 | 24700 | 0.0001 | - |
0.8503 | 24750 | 0.0001 | - |
0.8520 | 24800 | 0.0004 | - |
0.8537 | 24850 | 0.0001 | - |
0.8554 | 24900 | 0.0001 | - |
0.8572 | 24950 | 0.0001 | - |
0.8589 | 25000 | 0.0001 | - |
0.8606 | 25050 | 0.0001 | - |
0.8623 | 25100 | 0.0372 | - |
0.8640 | 25150 | 0.0001 | - |
0.8657 | 25200 | 0.0001 | - |
0.8675 | 25250 | 0.0001 | - |
0.8692 | 25300 | 0.0001 | - |
0.8709 | 25350 | 0.0001 | - |
0.8726 | 25400 | 0.0001 | - |
0.8743 | 25450 | 0.0001 | - |
0.8760 | 25500 | 0.0001 | - |
0.8778 | 25550 | 0.0002 | - |
0.8795 | 25600 | 0.0001 | - |
0.8812 | 25650 | 0.0001 | - |
0.8829 | 25700 | 0.0001 | - |
0.8846 | 25750 | 0.0001 | - |
0.8864 | 25800 | 0.0001 | - |
0.8881 | 25850 | 0.0001 | - |
0.8898 | 25900 | 0.0001 | - |
0.8915 | 25950 | 0.0001 | - |
0.8932 | 26000 | 0.0001 | - |
0.8949 | 26050 | 0.0001 | - |
0.8967 | 26100 | 0.0001 | - |
0.8984 | 26150 | 0.0001 | - |
0.9001 | 26200 | 0.0001 | - |
0.9018 | 26250 | 0.0001 | - |
0.9035 | 26300 | 0.0001 | - |
0.9052 | 26350 | 0.0001 | - |
0.9070 | 26400 | 0.0001 | - |
0.9087 | 26450 | 0.0001 | - |
0.9104 | 26500 | 0.0001 | - |
0.9121 | 26550 | 0.0001 | - |
0.9138 | 26600 | 0.0001 | - |
0.9156 | 26650 | 0.0001 | - |
0.9173 | 26700 | 0.0001 | - |
0.9190 | 26750 | 0.0001 | - |
0.9207 | 26800 | 0.0001 | - |
0.9224 | 26850 | 0.0001 | - |
0.9241 | 26900 | 0.0001 | - |
0.9259 | 26950 | 0.0001 | - |
0.9276 | 27000 | 0.0001 | - |
0.9293 | 27050 | 0.0001 | - |
0.9310 | 27100 | 0.0001 | - |
0.9327 | 27150 | 0.0001 | - |
0.9345 | 27200 | 0.0001 | - |
0.9362 | 27250 | 0.0001 | - |
0.9379 | 27300 | 0.0001 | - |
0.9396 | 27350 | 0.0001 | - |
0.9413 | 27400 | 0.0001 | - |
0.9430 | 27450 | 0.0001 | - |
0.9448 | 27500 | 0.0001 | - |
0.9465 | 27550 | 0.0001 | - |
0.9482 | 27600 | 0.0001 | - |
0.9499 | 27650 | 0.0001 | - |
0.9516 | 27700 | 0.0001 | - |
0.9533 | 27750 | 0.0001 | - |
0.9551 | 27800 | 0.0001 | - |
0.9568 | 27850 | 0.0001 | - |
0.9585 | 27900 | 0.0001 | - |
0.9602 | 27950 | 0.0001 | - |
0.9619 | 28000 | 0.0001 | - |
0.9637 | 28050 | 0.0001 | - |
0.9654 | 28100 | 0.0001 | - |
0.9671 | 28150 | 0.0001 | - |
0.9688 | 28200 | 0.0001 | - |
0.9705 | 28250 | 0.0001 | - |
0.9722 | 28300 | 0.0001 | - |
0.9740 | 28350 | 0.0001 | - |
0.9757 | 28400 | 0.0001 | - |
0.9774 | 28450 | 0.0001 | - |
0.9791 | 28500 | 0.0001 | - |
0.9808 | 28550 | 0.0001 | - |
0.9825 | 28600 | 0.0001 | - |
0.9843 | 28650 | 0.0001 | - |
0.9860 | 28700 | 0.0001 | - |
0.9877 | 28750 | 0.0001 | - |
0.9894 | 28800 | 0.0001 | - |
0.9911 | 28850 | 0.0001 | - |
0.9929 | 28900 | 0.0001 | - |
0.9946 | 28950 | 0.0001 | - |
0.9963 | 29000 | 0.0001 | - |
0.9980 | 29050 | 0.0374 | - |
0.9997 | 29100 | 0.0001 | - |
Framework Versions
- Python: 3.10.13
- SetFit: 1.0.3
- Sentence Transformers: 2.6.1
- Transformers: 4.38.2
- PyTorch: 2.1.2
- Datasets: 2.17.0
- Tokenizers: 0.15.2
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}
}