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

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-mpnet-base-v2 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: sentence-transformers/all-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 384 tokens
Number of Classes: 9 classes

Model Sources

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

Model Labels

Lables

0-press release/advertisement/newspaper publication
1-business updates/strategic announcemet/clarification sought
2-Investor meetings/board meeting
3-earnings call transcript
4-esop/esps
5-violation/litigation/penalty
6-auditors report/result
7-research
8-resignation

Label	Examples
0	'Announcement under Regulation 30 (LODR)-Press Release / Media Release' 'Media Release By The Company' 'Clarification on Market Rumors Regarding Product Recall'
1	'Corporate Insolvency Resolution Process (CIRP)-Updates - Corporate Insolvency Resolution Process (CIRP)' 'Notice Of Record Date For Bonus Issue' "Update To Disclosure Under Regulation 30 Of SEBI (Listing Obligations And Disclosure Requirements) Regulations, 2015 - Resolution Plan Jointly Submitted By Reliance Industries Limited And Assets Care & Reconstruction Enterprise Limited For The Resolution Of Sintex Industries Limited, Approved By Hon'Ble National Company Law Tribunal, Ahmedabad Bench"
2	'Board Meeting - Un-Audited Financial Results For The Quarter Ended June 30, 2023' 'Board Meeting Outcome for Interim Dividend For The Financial Year 2022-23' 'Board Meeting Intimation for Board Meeting - 3Rd February, 2023'
3	'Earnings Call - Intimation' 'Presentation On Earnings Call Update - Consolidated And Standalone Audited Financial Results Of The Bank For The Financial Year Ended March 31, 2023'
4	'An official announcement under SEBI (LODR) has been made declaring the notification of the record date for ESOP Holders and Shareholders post the successful completion of the Amalgamation between XYZ Systems Ltd and our Company.' 'An official announcement under Regulation 30 (LODR) has been released concerning the successful merger of Quantum Software Solutions Limited with the company.' 'Grant Of Stock Options Under The Employee Stock Option Scheme Of The Bank (ESOP Scheme).'
5	'Intimation Regarding Change in Compliance Officer Under Regulation 30 Of SEBI (Listing Obligations and Disclosure Requirements) Regulations' 'Disclosure Under Regulation 30 Of SEBI LODR Regulations (Merger or Demerger)' 'Regulation 30 Of The SEBI (Listing Obligations And Disclosure Requirements) Regulations 2015: Disclosure Of Appointment of Key Managerial Personnel'
6	'Statement Of Unaudited Standalone And Consolidated Financial Results Of The Company For The Quarter And Nine Months Ended 31St December, 2022' 'Unaudited Financial Results' 'Statement Of Audited Standalone And Consolidated Financial Results Of The Company For The Quarter And Year Ended 31St March, 2023'
7	"Energizing Change: Infosys-HFS Research Unveils Companies' Top 3 Priorities in the Energy Transition Era," 'Infosys Rated A Leader In Multicloud Managed Services Providers And Cloud Migration And Managed Service Partners By Independent Research Firm' 'Cloud For Organizational Growth And Transformation Is Three Times More Important Than Cloud For Cost Optimization: Infosys Research'
8	'Resignation Of Smt. Nita M. Ambani From The Board Of The Company - Disclosure Dated August 28' 'Announcement under Regulation 30 (LODR)-Resignation of Head of Customer Relations' 'Announcement under Regulation 30 (LODR)-Resignation of Head of Human Resources'

Evaluation

Metrics

Label	Accuracy
all	0.9558

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("krish2505/setfitmkrt2")
# Run inference
preds = model("Infosys Unveils New AI-Powered Solutions for Enhanced Customer Experience")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	14.7272	50

Label	Training Sample Count
0	142
1	134
2	298
3	66
4	43
5	53
6	202
7	34
8	36

Training Hyperparameters

batch_size: (64, 64)
num_epochs: (2, 2)
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

Epoch	Step	Training Loss	Validation Loss
0.0016	1	0.1754	-
0.0794	50	0.0917	-
0.1587	100	0.0534	-
0.2381	150	0.0521	-
0.3175	200	0.0352	-
0.3968	250	0.0062	-
0.4762	300	0.0159	-
0.5556	350	0.0151	-
0.6349	400	0.0207	-
0.7143	450	0.0129	-
0.7937	500	0.0186	-
0.8730	550	0.0083	-
0.9524	600	0.002	-
1.0317	650	0.0081	-
1.1111	700	0.0263	-
1.1905	750	0.0118	-
1.2698	800	0.0196	-
1.3492	850	0.011	-
1.4286	900	0.0153	-
1.5079	950	0.0015	-
1.5873	1000	0.0156	-
1.6667	1050	0.0215	-
1.7460	1100	0.0022	-
1.8254	1150	0.003	-
1.9048	1200	0.0033	-
1.9841	1250	0.0155	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.2.2
Transformers: 4.36.2
PyTorch: 2.0.0
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}
}

krish2505
/

setfitmkrt2