metadata
base_model: BAAI/bge-small-en-v1.5
datasets: []
language: []
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@5
- cosine_ndcg@10
- cosine_ndcg@100
- cosine_mrr@5
- cosine_mrr@10
- cosine_mrr@100
- cosine_map@100
- dot_accuracy@1
- dot_accuracy@5
- dot_accuracy@10
- dot_precision@1
- dot_precision@5
- dot_precision@10
- dot_recall@1
- dot_recall@5
- dot_recall@10
- dot_ndcg@5
- dot_ndcg@10
- dot_ndcg@100
- dot_mrr@5
- dot_mrr@10
- dot_mrr@100
- dot_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:900
- loss:GISTEmbedLoss
widget:
- source_sentence: How many more Kiosks was SBI planning to establish in the next one year?
sentences:
- >-
'First installment due on (date) : ii). Last Installment due on
(date) : 6. b). Cash Credit : Limit: Drawing Power:
Outstanding: Comments on Irregularity ( if any): Any adverse
comments on the unit by inspecting official in last inspection
report: 7. A. Cost of Project (as accepted by sanctioning
authority)(In Rs. Lakh) B. Means of Finance (as accepted by
sanctioning authority)(In Rs. Lakh) Give component wise details a.
Term loan of Bank: b. Promoter Equity c. Unsecured loan : d. Others
if any Total Total 8. A. Forward Linkages: B. Backward
Linkages with Small/Marginal farmers: 1 No. of members:
2 Details of Primary and Collateral Securities taken by the bank (if
any) 3 a. Primary Securities b. Collateral Securities 4
5 6 (Please enclose details separately) 9
NameoftheConsortium(ifany)associatedwithCreditFacilitywithcompleteaddress,contac
t details and email: 9 a) Address (*with pin-code) : 9 b) Contact
Details : 9 c) Email Address : Request of Branch head for Credit
Guarantee:- In view of the above information, we request Credit
Guarantee Cover against Credit Facility of Rs.....................(in
Rupees ) to FPO(copy of sanction letter along with appraisal/process
note of competent authority is enclosed for your perusal and record ).
Further we confirm that : 1. The KYC norms in respect of the Promoters
have been complied by us. 2. Techno-feasibility and economic viability
aspect of the project has been taken care of by the sanctioning
authority and the branch. 3. On quarterly basis, bank will apprise the
........................(Name of Implementing Agency)about progress of
unit, recovery of bank's dues and present status of account
to........................(Name of Implementing Agency) 4. We undertake
to abide by the Terms & Conditions of the Scheme.'
- >-
'Date: To, (i) The Managing Director Small Farmers' Agri-Business
Consortium (SFAC), NCUI Auditorium, August Kranti Marg, Hauz Khas, New
Delhi 110016. (ii)The Managing Director National Co-operative
Development Corporation (NCDC), 4, Siri Institutional Area, Hauz Khas,
New Delhi 110016. (iii) The Chief General Manager National Bank for
Agriculture and Rural Development (NABARD), Regional Office
--------------------------------------------------------------- (iv) To
any other additional Implementing Agency allowed/designated, as the case
may be. Sub: Application for Equity Grant under scheme of Formation and
Promotion of 10,000 Farmer Producer Organizations (FPOs) Dear
Sir/Madam, We herewith apply for Equity Grant as per the provisions
under the captioned scheme. 1. The details of the FPO are as under-
S. No. Particulars to be furnished Details 1. Name of the FPO 2.
Correspondence address of FPO 3. Contact details of FPO 4.
Registration Number 5. Date of registration/incorporation of FPO
6. Brief account of business of FPO 7. Number of Shareholder
Members 8. Number of Small, Marginal and Landless Shareholder
Members'
- >-
'1.6 Due to greater acceptability of the federations in the villages,
State Bank of India (SBI) approved opening of Kiosks under BC model
through federations to achieve financial inclusion. As on September
2014, 16 kiosks were working through three farmer club federations. SBI
was in the process of establishing 14 more Kiosks at other village
centres in the next one year in the district. The Kiosks were attached
to the nearest branch and worked under the guidance of the concerned
Branch Manager. The Branch Manager supervises and monitors the work of
the Kiosks (BC). 1.7 At present, the Kiosks are mainly involved in
providing banking services like, opening of savings bank accounts,
recurring deposit accounts, acceptance of deposits and payment towards
withdrawal. The kiosks are also dispensing old age pensions, student
scholarships, MNREGA payments and other social sector payments, routed
by the Government. The present monthly income (Rs. 8000 to Rs. 14,000)
of the Kiosk is mainly from banking services. The expenditure involved
was salary to the operator, rent of the premises, interest on the
initial investment etc., which is about Rs. 8000 to Rs. 10,000 (Salary
of the operator-Rs.4000 to Rs. 5000, Premises rent-about Rs. 2000 to Rs.
3000).'
- source_sentence: How are the kiosks attached to the nearest branch?
sentences:
- >-
'In addition, past yield data for requisite number of years will have to
be made available separately for both 7.2.6 While notifying the
crop(s) where a specific conversion factor is being used for reporting
of yield such as in the case of rice/paddy etc, due care should be taken
by the State Nodal Department to use the relevant specific nomenclature
for disclosure of Average Yield, Threshold Yield and Actual Yield while
releasing the Tender Document and submission of Yield data and CCE data
for calculation of admissible claims. Insurance Companies will also be
responsible for prior scrutiny of Tender document. Information/data
provided in Tender document will be treated as final and in case of any
error/ misreporting/disparity, State Govt. and Insurance Company will
be equally liable for payment of additional claims arising on account
of it, if any. 7.2.7 For the current season or subsequent seasons (in
a multi-year contract), the States, if required, can notify additional
IUs or de-notify certain IUs subject to maximum deviation of 10% of
already notified IUs for the crop within a district at the same premium
rate, before the cut-off date for debit of premium. If the deviation is
>10% or in case of addition of new crop, actuarial premium rate may be
worked out either by calculation of weighted average premium rate as
prevalent in contiguous districts or by applying appropriate loading
on the existing premium rate. The rates for such crops will be
determined /verified by TSU and its decision will be binding on both
States and ICs. 7.2.8 States implementing PMFBY at Village/ Village
Panchayat level for major crops shall be entitled for 50% reimbursement
of incremental expenses of CCEs and cost of smart phones/ improved
technology **from GOI.** Only eligible items will be considered for
reimbursement.'
- >-
'i. The credit guarantee cover per FPO will be limited to the project
loan of Rs. 2 crore. In case of project loan up to Rs. 1 crore, credit
guarantee cover will be 85% of bankable project loan with ceiling of Rs.
85 lakh; while in case of project loan above Rs.1 crore and up to Rs. 2
crore, credit guarantee cover will be 75% of bankable project loan with
a maximum ceiling of Rs. 150 lakh. However, for project loan over Rs. 2
crore of bankable projet loan, credit guarantee cover will be limited
maximum upto Rs.2.0 crore only. ii. ELI shall be eligible to seek
Credit Guarantee Cover for a credit facility sanctioned in respect of a
single FPO borrower for a maximum of 2 times over a period of 5 years.
iii. In case of default, claims shall be settled up to 85% or 75 % of
the amount in default subject to maximum cover as specified above.
iv. Other charges such as penal interest, commitment charge, service
charge, or any other levies/ expenses, or any costs whatsoever debited
to the account of FPO by the ELI other than the contracted interest
shall not qualify for Credit Guarantee Cover. v. The Cover shall only
be granted after the ELI enters into an agreement with NABARD or NCDC,
as the case may be, and shall be granted or delivered in accordance with
the Terms and Conditions decided upon by NABARD or NCDC, as the case may
be, from time to time.'
- >-
'1.6 Due to greater acceptability of the federations in the villages,
State Bank of India (SBI) approved opening of Kiosks under BC model
through federations to achieve financial inclusion. As on September
2014, 16 kiosks were working through three farmer club federations. SBI
was in the process of establishing 14 more Kiosks at other village
centres in the next one year in the district. The Kiosks were attached
to the nearest branch and worked under the guidance of the concerned
Branch Manager. The Branch Manager supervises and monitors the work of
the Kiosks (BC). 1.7 At present, the Kiosks are mainly involved in
providing banking services like, opening of savings bank accounts,
recurring deposit accounts, acceptance of deposits and payment towards
withdrawal. The kiosks are also dispensing old age pensions, student
scholarships, MNREGA payments and other social sector payments, routed
by the Government. The present monthly income (Rs. 8000 to Rs. 14,000)
of the Kiosk is mainly from banking services. The expenditure involved
was salary to the operator, rent of the premises, interest on the
initial investment etc., which is about Rs. 8000 to Rs. 10,000 (Salary
of the operator-Rs.4000 to Rs. 5000, Premises rent-about Rs. 2000 to Rs.
3000).'
- source_sentence: What is the principle on which the Scheme operates?
sentences:
- >-
'| Sl. No Section | Page
No.
|\n|-------------------------------------------------------------|---------------------------------------------------------------------------------|\n|
Abbreviations |
I-II
|\n| 1 |
Objective of the
Scheme |\n|
2 | Adoption
of Technology for Scheme Administration
|\n| 3 |
Coverage of
Farmers |\n|
4 | Coverage
of Crops
|\n| 5 |
Coverage of Risks &
Exclusions |\n|
6 |
Preconditions for implementation of the
Scheme |\n|
7 |
Notification
|\n| 8
|
|\n| Engagement of Common Service Centres and Intermediaries for
|
|\n| coverage of non loanee Farmers
|
|\n| 11
|
|\n| 9 |
Electronic Remittance of
Funds |\n|
10 | Census
code Mapping of Entities
|\n| 11 |
Digitization of Land
Records |\n|
12 | Sum
Insured/Coverage
Limit |\n|
13 | Premium
Rates and Premium Subsidy
|\n| 14 |
Budget for Administrative
Expenses |\n|
15 | Technical
Support Unit(TSU)/Central Programme Management Unit(CPMU)
|\n| 16 |
Seasonality
Discipline |\n|
17 | Collection
of Proposals and Premium from Farmers
|\n| 18 |
Assessment of Loss/Short Fall in
Yield |\n|
19 | Dispute
Resolution regarding Yield Data/Crop Loss
|\n| 20 | Use
of Innovative
Technologies |\n|
21 | Assessment
of Claims
|\n| 22 |
Participation of Loss Assessors/Evaluators for Loss Assessment under the
Scheme |\n| 23
| Procedure for Settlement of
Claims |\n|
24 | Important
Conditions/Clauses Applicable for Coverage of Risks
|\n| 25 |
Acreage
Discrepancy
|\n| 26 |
Publicity and
Awareness |\n|
27 | Service
Charges
|\n| 28 | Goods
& Service
Tax(GST) |\n|
29 | Monitoring
and Review of the Scheme
|\n| 30 |
Grievance Redressal
Mechanism |\n|
31 |
Empanelment and Selection of Insurance
Companies |\n|
32 |
Clustering/Clubbing of districts for bidding by the
State |\n|
33 | Assessment
of Performance and De-empanelment of Insurance Companies
|\n| 34 |
Evaluation of Efficiency of Nodal Department of the
State |\n|
35 | Role &
Responsibilities of Various Agencies
|\n| 36 |
National Crop Insurance Portal for administration of Crop Insurance
Program |\n| Annexure -
1 |
78-85
|\n| Annexure - 2 |
86-89
|\n| Annexure - 3 |
90-93
|'
- >-
'16.1 The cut-off date is uniform for both loanee and non-loanee
cultivators. The State-wise cut-off dates for different crops shall be
based on Crop Calendar of major crops published from time to time by the
Directorate of Economics and Statistics, DAC&FW,GOI. The latest copy of
the Crop Calendar (District Wise, Crop Wise) is available on
www.pmfby.gov.in. The SLCCCI, shall besides considering the prevailing
agro-climatic conditions, rainfall distribution/ availability of water
for irrigation, sowing pattern etc. in consultation with the Insurance
Company fix seasonality discipline of the coverage and other activities
in such a way that it does not encourage adverse selection or moral
hazards. If this is violated by SLCCCI, GOI may decide not to provide
premium subsidy. 16.2 The **broad indicative seasonality discipline**
is given in the Table 2 below:'
- >-
'7.2.1 The Scheme shall operate on the principle of \'Area Approach\'
in the selected defined areas called Insurance Unit (IU). State Govt.
/UT will notify crops and defined areas covered during the season in
accordance with decision taken in the meeting of SLCCCI. State/UT Govt.
should notify Village/Village Panchayat or any other equivalent unit as
an insurance unit for major crops defined at District / Taluka or
equivalent level. For **other crops** it may be a unit of size above the
level of Village/village Panchayat. For defining a crop as a major crop
for deciding the Insurance Unit level, the sown area of'
- source_sentence: How can the government prioritize FPOs?
sentences:
- >-
' 2.7 Secured credential/login, preferably linked with Aadhaar
Number and mobile OTP based, for all Stakeholders viz, Central
Government, State Governments, Banks, empanelled Insurance Companies
and their designated field functionaries will be provided on the Portal
to enable them to enter/upload/download the requisite information.
2.8 Insurance Companies shall not distribute/collect/allow any other
proforma/utility/web Portal etc for collecting details of insured
farmers separately. However they may provide all requisite support to
facilitate Bank Branches/PACS for uploading the farmer's details on the
Portal well within the prescribed cut-off dates. 2.9 Only farmers
whose data is uploaded on the National Crop Insurance Portal shall be
eligible for Insurance coverage and the premium subsidy from State
and Central Govt. will be released accordingly. 2.10 All data
pertaining to crop-wise, area-wise historical yield data, weather data,
sown area, coverage and claims data, calamity years and actual yield
shall be made available on the National Crop Insurance Portal for the
purpose of premium rating, claim calculation etc. 2.11
Banks/Financial Institutions/other intermediaries need to compulsorily
transfer the individual farmer's data electronically to the National
Crop Insurance Portal. Accordingly Banks/FIs may endeavour to
undertake CBS integration in a time bound manner for real time transfer
of information/data. 2.12 It is also proposed to develop an
integrated platform/portal for both PMFBY and Interest Subvention
Scheme. The data/information of both the Schemes shall be auto
synchronized to enable real time sharing of information and better
program monitoring. 2.13 Insurance Companies shall compulsorily use
technology/mobile applications for monitoring of crop health/Crop
Cutting Experiments (CCEs) in coordination with concerned States. States
shall also facilitate Insurance Companies with Satellite
Imagery/Usage of Drones by way of prior approval of agency from which
such data can be sourced. This is required for better monitoring and
ground- truthing.'
- >-
' (vi) States/Union Territories may actively consider to make available
appropriate size of land to FPOs for setting up of CFCs and CHCs at
cheaper rate on rent/lease or otherwise; or may make available free of
cost. (vii) Government may prioritize FPOs to undertake procurement
operation on Minimum Support Price (MSP). (viii) States must actively
consider encouraging FPOs for selling their produce through e-National
Agriculture Market (e-NAM) including FPO module of e-NAM or through
other electronic platform from their premises itself without physically
bringing the produce to the APMC market yards. (ix) Department of
Agriculture, Cooperation & Farmers Welfare is authorized to finalize
Operational Guidelines of the scheme (and model Bye Laws if any)
including mid-term changes thereto, and issue the same with the approval
of Hon'ble Minister for Agriculture & Farmers' Welfare. .'
- >-
'1.1 Chhattisgarh is among the few states in India that have recorded
impressive growth in agriculture in recent years. Development of farmers
own institutions catering to their various needs, has kept pace with the
agricultural growth. As on 30 September 2014, the state had 3,679
farmers clubs (FCs). There were eight federations of farmer clubs in the
state, five in Mahasamund, two in Bilaspur and one in Mungeli district.
In Bilaspur and Mungeli districts (the study area), 300 FCs were formed,
of which 201 were active. Majority of the farmer clubs (129 clubs) were
formed by the Regional Rural Bank (Gramin Bank). Other promoting
institutions include Chhattisgarh Agricon Samiti (30), CARMDAKSH (12),
SBI (12), ARDB (8) and IFFDC (5). While all the clubs were active in the
initial three years, many slipped into dormancy through inaction and
non-availability of hand-holding support. These clubs did not have any
vision or roadmap for the future. 1.2 The Chhattisgarh RO and DDM
Bilaspur were keen to make the farmer clubs a sustainable entity and
felt the need to federate the clubs to a higher tier so as to make the
entire farmer clubs programme sustainable and the organization a viable
model. With this in view, the farmer clubs were federated into four
farmer club federations and were registered under 'Chhattisgarh Society
Registrikaran Adhiniyam, 1973' in the year 2012.'
- source_sentence: What is the credit guarantee cover for a project loan up to Rs. 1 crore?
sentences:
- >-
' (ii) Ongoing schemes of Government will be used in convergence to
enhance the cost effectiveness of FPOs in production and raising
productivity and also to meet the cost of infrastructure requirement of
the FPOs. Implementing Agency may converge the fund available with
various on-going Government of India schemes such as Rashtriya Krishi
Vikas Yojna (RKVY), Mission for Integrated Development for Horticulture
(MIDH),National Food Security Mission (NFSM), Pradhan Mantri Kisan
Sampada Yojna (PM-SAMPADA), Deendayal Antyodaya Yojna-National Rural
Livelihood Mission (DAY-NRLM), PM- FME Scheme of MoFPI, TRIFED etc. in
programs, activities and creation of infrastructure like Custom Hiring
Centre/Common Facilitation Centre with machinery/equipment relating to
production and post-production, value addition and farm level
processing, storage and other activities to make FPOs sustainable and
economically viable. (iii) Further, Agricultural Marketing
Infrastructure (AMI) Sub-Scheme of Integrated Scheme for Agriculture
Marketing (ISAM) will also be converged and an FPO willing to develop
post-harvest management and marketing infrastructure can avail
assistance thereunder. (iv) States/ Union Territories can avail
assistance for development of marketing and farm level value addition
infrastructure/facilities for FPOs including setting up of Custom
Hiring Centre (CHC)/Common Facilitation Center (CFC) for marketing and
supply chain etc. under Agri- Market Infrastructure Fund (AMIF)
approved for creation in NABARD for development of marketing and farm
level value addition infrastructure/facilities in Gramin Agriculture
Markets (GrAMs). In this case, operational guidelines of AMIF and
NABARD's procedure and terms and conditions of sanction and repayment of
loan for AMIF shall be applicable. (v) States/Union Territories can
top up and additionally supplement the activities of FPOs from their own
fund for activities and infrastructure not covered under Government of
India Scheme.'
- >-
'7.2.1 The Scheme shall operate on the principle of \'Area Approach\'
in the selected defined areas called Insurance Unit (IU). State Govt.
/UT will notify crops and defined areas covered during the season in
accordance with decision taken in the meeting of SLCCCI. State/UT Govt.
should notify Village/Village Panchayat or any other equivalent unit as
an insurance unit for major crops defined at District / Taluka or
equivalent level. For **other crops** it may be a unit of size above the
level of Village/village Panchayat. For defining a crop as a major crop
for deciding the Insurance Unit level, the sown area of'
- >-
'i. The credit guarantee cover per FPO will be limited to the project
loan of Rs. 2 crore. In case of project loan up to Rs. 1 crore, credit
guarantee cover will be 85% of bankable project loan with ceiling of Rs.
85 lakh; while in case of project loan above Rs.1 crore and up to Rs. 2
crore, credit guarantee cover will be 75% of bankable project loan with
a maximum ceiling of Rs. 150 lakh. However, for project loan over Rs. 2
crore of bankable projet loan, credit guarantee cover will be limited
maximum upto Rs.2.0 crore only. ii. ELI shall be eligible to seek
Credit Guarantee Cover for a credit facility sanctioned in respect of a
single FPO borrower for a maximum of 2 times over a period of 5 years.
iii. In case of default, claims shall be settled up to 85% or 75 % of
the amount in default subject to maximum cover as specified above.
iv. Other charges such as penal interest, commitment charge, service
charge, or any other levies/ expenses, or any costs whatsoever debited
to the account of FPO by the ELI other than the contracted interest
shall not qualify for Credit Guarantee Cover. v. The Cover shall only
be granted after the ELI enters into an agreement with NABARD or NCDC,
as the case may be, and shall be granted or delivered in accordance with
the Terms and Conditions decided upon by NABARD or NCDC, as the case may
be, from time to time.'
model-index:
- name: SentenceTransformer based on BAAI/bge-small-en-v1.5
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: val evaluator
type: val_evaluator
metrics:
- type: cosine_accuracy@1
value: 0.54
name: Cosine Accuracy@1
- type: cosine_accuracy@5
value: 0.89
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.92
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.54
name: Cosine Precision@1
- type: cosine_precision@5
value: 0.17799999999999994
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09199999999999997
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.54
name: Cosine Recall@1
- type: cosine_recall@5
value: 0.89
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.92
name: Cosine Recall@10
- type: cosine_ndcg@5
value: 0.7328328247017718
name: Cosine Ndcg@5
- type: cosine_ndcg@10
value: 0.7420327705006653
name: Cosine Ndcg@10
- type: cosine_ndcg@100
value: 0.7588813763663693
name: Cosine Ndcg@100
- type: cosine_mrr@5
value: 0.6800000000000002
name: Cosine Mrr@5
- type: cosine_mrr@10
value: 0.6835000000000001
name: Cosine Mrr@10
- type: cosine_mrr@100
value: 0.6868224050433418
name: Cosine Mrr@100
- type: cosine_map@100
value: 0.6868224050433418
name: Cosine Map@100
- type: dot_accuracy@1
value: 0.55
name: Dot Accuracy@1
- type: dot_accuracy@5
value: 0.89
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.92
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.55
name: Dot Precision@1
- type: dot_precision@5
value: 0.17799999999999994
name: Dot Precision@5
- type: dot_precision@10
value: 0.09199999999999997
name: Dot Precision@10
- type: dot_recall@1
value: 0.55
name: Dot Recall@1
- type: dot_recall@5
value: 0.89
name: Dot Recall@5
- type: dot_recall@10
value: 0.92
name: Dot Recall@10
- type: dot_ndcg@5
value: 0.7365235271660572
name: Dot Ndcg@5
- type: dot_ndcg@10
value: 0.7457234729649508
name: Dot Ndcg@10
- type: dot_ndcg@100
value: 0.7625720788306548
name: Dot Ndcg@100
- type: dot_mrr@5
value: 0.6850000000000002
name: Dot Mrr@5
- type: dot_mrr@10
value: 0.6885000000000001
name: Dot Mrr@10
- type: dot_mrr@100
value: 0.6918224050433417
name: Dot Mrr@100
- type: dot_map@100
value: 0.6918224050433417
name: Dot Map@100
SentenceTransformer based on BAAI/bge-small-en-v1.5
This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: BAAI/bge-small-en-v1.5
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 384 tokens
- Similarity Function: Cosine Similarity
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("SamagraDataGov/embedding_finetuned")
# Run inference
sentences = [
'What is the credit guarantee cover for a project loan up to Rs. 1 crore?',
"'i. The credit guarantee cover per FPO will be limited to the project loan of Rs. 2 crore. In case of project loan up to Rs. 1 crore, credit guarantee cover will be 85% of bankable project loan with ceiling of Rs. 85 lakh; while in case of project loan above Rs.1 crore and up to Rs. 2 crore, credit guarantee cover will be 75% of bankable project loan with a maximum ceiling of Rs. 150 lakh. However, for project loan over Rs. 2 crore of bankable projet loan, credit guarantee cover will be limited maximum upto Rs.2.0 crore only. ii. ELI shall be eligible to seek Credit Guarantee Cover for a credit facility sanctioned in respect of a single FPO borrower for a maximum of 2 times over a period of 5 years. iii. In case of default, claims shall be settled up to 85% or 75 % of the amount in default subject to maximum cover as specified above. iv. Other charges such as penal interest, commitment charge, service charge, or any other levies/ expenses, or any costs whatsoever debited to the account of FPO by the ELI other than the contracted interest shall not qualify for Credit Guarantee Cover. v. The Cover shall only be granted after the ELI enters into an agreement with NABARD or NCDC, as the case may be, and shall be granted or delivered in accordance with the Terms and Conditions decided upon by NABARD or NCDC, as the case may be, from time to time.'",
"'7.2.1 The Scheme shall operate on the principle of \\'Area Approach\\' in the selected defined areas called Insurance Unit (IU). State Govt. /UT will notify crops and defined areas covered during the season in accordance with decision taken in the meeting of SLCCCI. State/UT Govt. should notify Village/Village Panchayat or any other equivalent unit as an insurance unit for major crops defined at District / Taluka or equivalent level. For **other crops** it may be a unit of size above the level of Village/village Panchayat. For defining a crop as a major crop for deciding the Insurance Unit level, the sown area of'",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Information Retrieval
- Dataset:
val_evaluator
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.54 |
cosine_accuracy@5 | 0.89 |
cosine_accuracy@10 | 0.92 |
cosine_precision@1 | 0.54 |
cosine_precision@5 | 0.178 |
cosine_precision@10 | 0.092 |
cosine_recall@1 | 0.54 |
cosine_recall@5 | 0.89 |
cosine_recall@10 | 0.92 |
cosine_ndcg@5 | 0.7328 |
cosine_ndcg@10 | 0.742 |
cosine_ndcg@100 | 0.7589 |
cosine_mrr@5 | 0.68 |
cosine_mrr@10 | 0.6835 |
cosine_mrr@100 | 0.6868 |
cosine_map@100 | 0.6868 |
dot_accuracy@1 | 0.55 |
dot_accuracy@5 | 0.89 |
dot_accuracy@10 | 0.92 |
dot_precision@1 | 0.55 |
dot_precision@5 | 0.178 |
dot_precision@10 | 0.092 |
dot_recall@1 | 0.55 |
dot_recall@5 | 0.89 |
dot_recall@10 | 0.92 |
dot_ndcg@5 | 0.7365 |
dot_ndcg@10 | 0.7457 |
dot_ndcg@100 | 0.7626 |
dot_mrr@5 | 0.685 |
dot_mrr@10 | 0.6885 |
dot_mrr@100 | 0.6918 |
dot_map@100 | 0.6918 |
Training Details
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 32per_device_eval_batch_size
: 32learning_rate
: 1e-05weight_decay
: 0.01num_train_epochs
: 1.0warmup_ratio
: 0.1load_best_model_at_end
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 32per_device_eval_batch_size
: 32per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 1e-05weight_decay
: 0.01adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 1.0max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Trueignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseeval_use_gather_object
: Falsebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | loss | val_evaluator_dot_map@100 |
---|---|---|---|---|
0.5172 | 15 | 1.8109 | 1.2075 | 0.6918 |
1.0 | 29 | - | 1.2075 | 0.6918 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.14
- Sentence Transformers: 3.0.1
- Transformers: 4.43.4
- PyTorch: 2.4.1+cu121
- Accelerate: 0.33.0
- Datasets: 2.21.0
- Tokenizers: 0.19.1
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
GISTEmbedLoss
@misc{solatorio2024gistembed,
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
author={Aivin V. Solatorio},
year={2024},
eprint={2402.16829},
archivePrefix={arXiv},
primaryClass={cs.LG}
}