This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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:
' Original for Buyer/ Duplicate for Temponte/ Teplicate for Assesce OMCL 93103986 76000 1 SUSHIBILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILI'
' Original Box buyer/ Duplicate for Temponte/ Teisplicate Box Assesce MCL 9310301 @099 1 SUSHIBILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILILI'
' GARDANG CHOCO POWE IHADOUS GENERAL TERM & CHOCOLIONSE LIGHTEGAL TERS A CHOCOLIONSE LIGHTICE ICE LIGHTING CHOCOLIZEDAYOSE 3 SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE 3 SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE SUSHIKA LIGHTONE TERS & CHOCOLIZEDAYOSE SUSHIKAIDEE'
' HINDALCO INDUSTRIES LIMITED HIRAKUD WORKS PAYMENT ORDER Pauto HOTOL SHEELA TOWERS SAWABALPUR VucherNQUA Nc. H369 JANCE by Cash/Choque/D./Tangle summer of R&S.84同意 & HZQUAYE Rupes Eight thousand four hundred/Cory one only Rupes of Pavoment Dtalls of Pavoment Amount Sxpemie of fooding &lodging charges Cor Companywa quest Rs. P. Bll Bll B.4411 8,4441 8,443 8,442 (s)B) Sudah Allow P. Allowed 8,443 (S) Stychocolate Allowed Allowed 8,443 (S)B) Shoud Allowed by Allowed by Allowed 8,443 Stella Stakud 8,443 Stakelor Stella Stella Stella 8,443 638 Punidah Ndg. HIGBUG JPGB-21 C.F.F.Code Cssssstine Received Payment Acount Chechected by SQUAE SQUATITE SQUATITE SQUATITE'
' ADITYA BIRLA HINDALCO INDUSTRIES LIMITED HIRAKUR POWER PAYMENT ORDER SHRING WU PEAYAG PADMI SHRING WU PADMI SHRINGHU PEANG AQUATADO PYito -PHOTOPOPICHT STURIO CHOCO AQUAT AQUAT 3 Address Bubwang SAMBOUR AQU AQUAG NO.07462 1314 - Emp No. OTIO JFSC ORBC102746 0.00 by C Chequeque D/Trenzie The sun of 200 2 A.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.P.'
Evaluation
Metrics
Label
Accuracy
all
1.0
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("Gopal2002/setfit_zeon_3456")
# Run inference
preds = model("<s_cord-v2><s_menu><s_nm> RT @kanaka<s_nm> RT @kanaka</s_total>")
Training Details
Training Set Metrics
Training set
Min
Median
Max
Word count
2
193.4045
1530
Label
Training Sample Count
3
38
4
45
5
54
6
41
Training Hyperparameters
batch_size: (32, 32)
num_epochs: (2, 2)
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: False
use_amp: False
warmup_proportion: 0.1
seed: 42
eval_max_steps: -1
load_best_model_at_end: False
Training Results
Epoch
Step
Training Loss
Validation Loss
0.0014
1
0.2908
-
0.0677
50
0.1735
-
0.1353
100
0.0824
-
0.2030
150
0.0505
-
0.2706
200
0.014
-
0.3383
250
0.0066
-
0.4060
300
0.0035
-
0.4736
350
0.0018
-
0.5413
400
0.0022
-
0.6089
450
0.0019
-
0.6766
500
0.0015
-
0.7442
550
0.0014
-
0.8119
600
0.0012
-
0.8796
650
0.0013
-
0.9472
700
0.0014
-
1.0149
750
0.0012
-
1.0825
800
0.001
-
1.1502
850
0.0012
-
1.2179
900
0.001
-
1.2855
950
0.0009
-
1.3532
1000
0.0009
-
1.4208
1050
0.0008
-
1.4885
1100
0.001
-
1.5562
1150
0.0009
-
1.6238
1200
0.001
-
1.6915
1250
0.0009
-
1.7591
1300
0.0009
-
1.8268
1350
0.0008
-
1.8945
1400
0.0007
-
1.9621
1450
0.0008
-
Framework Versions
Python: 3.10.12
SetFit: 1.0.2
Sentence Transformers: 2.2.2
Transformers: 4.35.2
PyTorch: 2.1.0+cu121
Datasets: 2.16.1
Tokenizers: 0.15.0
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}
}
