Production-ready merged model - LoRA fine-tuned on rich Indian entity resolution dataset (211 records)

94ddeff verified 3 months ago

39.1 kB

tags:
  - sentence-transformers
  - cross-encoder
  - reranker
  - generated_from_trainer
  - dataset_size:126
  - loss:BinaryCrossEntropyLoss
base_model: BAAI/bge-reranker-v2-m3
pipeline_tag: text-ranking
library_name: sentence-transformers
metrics:
  - accuracy
  - accuracy_threshold
  - f1
  - f1_threshold
  - precision
  - recall
  - average_precision
model-index:
  - name: CrossEncoder based on BAAI/bge-reranker-v2-m3
    results:
      - task:
          type: cross-encoder-classification
          name: Cross Encoder Classification
        dataset:
          name: rich entity matching lora
          type: rich-entity-matching-lora
        metrics:
          - type: accuracy
            value: 1
            name: Accuracy
          - type: accuracy_threshold
            value: 0.49942895770072937
            name: Accuracy Threshold
          - type: f1
            value: 1
            name: F1
          - type: f1_threshold
            value: 0.49942895770072937
            name: F1 Threshold
          - type: precision
            value: 1
            name: Precision
          - type: recall
            value: 1
            name: Recall
          - type: average_precision
            value: 1
            name: Average Precision

CrossEncoder based on BAAI/bge-reranker-v2-m3

This is a Cross Encoder model finetuned from BAAI/bge-reranker-v2-m3 using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

Model Type: Cross Encoder
Base model: BAAI/bge-reranker-v2-m3
Maximum Sequence Length: 512 tokens
Number of Output Labels: 1 label

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("pujithapsx/finetuned_bge_reranker_m3_merged_fullrecord_v1")
# Get scores for pairs of texts
pairs = [
    ['Name: Rohan Rao Sharma | First: Rohan | Middle: Rao | Last: Sharma | Gender: M | DOB: 1983-08-04 | Spouse:  | Mother:  | Father:  | Company: ORACLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 551 KORAMANGALA NEAR MALL | City: AHMEDABAD | State: GUJARAT | ZIP: 380071 | Address1: 551 KORAMANGALA NEAR MALL | City1: AHMEDABAD | State1: GUJARAT | ZIP1: 380071 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 8641615633 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: rohan.sharma@gmail.com | Email1:  | Email2:  | Email3:  | Email4: ', 'Name: Rohan Rao Sharma | First: Rohan | Middle: Rao | Last: Sharma | Gender: M | DOB: 1983-08-04 | Spouse:  | Mother:  | Father:  | Company: ORACLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 551 KORAMANGALA NEAR MALL | City: AHMEDABAD | State: GUJARAT | ZIP: 380071 | Address1: 551 KORAMANGALA NEAR MALL | City1: AHMEDABAD | State1: GUJARAT | ZIP1: 380071 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone:  | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: rohan.sharma@yahoo.com | Email1:  | Email2:  | Email3:  | Email4: '],
    ['Name: Priya Prasad Reddy | First: Priya | Middle: Prasad | Last: Reddy | Gender: F | DOB: 1983-07-03 | Spouse:  | Mother:  | Father:  | Company: GLOBAL INFOTECH | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: FLAT 401, LAKE APT, 24 MAIN RD | City: LUCKNOW | State: UTTAR PRADESH | ZIP: 226001 | Address1: FLAT 401, LAKE APT, 24 MAIN RD | City1: LUCKNOW | State1: UTTAR PRADESH | ZIP1: 226001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9149203558 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: priyareddy@gmail.com | Email1: priya.reddy@globalinfotech.com | Email2:  | Email3:  | Email4: ', 'Name: Priya  Reddy | First: Priya | Middle:  | Last: Reddy | Gender: F | DOB: 1983-07-03 | Spouse:  | Mother:  | Father:  | Company: GLOBAL INFOTECH PVT LTD | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD | City: LUCKNOW | State: UTTAR PRADESH | ZIP: 226001 | Address1: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD | City1: LUCKNOW | State1: UTTAR PRADESH | ZIP1: 226001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9208449460 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: priyareddy@gmail.com | Email1: priya.reddy@globalinfotech.com | Email2:  | Email3:  | Email4: '],
    ['Name: Aditya Singh | First: Aditya | Middle:  | Last: Singh | Gender: M | DOB: 1982-02-07 | Spouse:  | Mother:  | Father:  | Company: CAPGEMINI INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 753 SECTOR 12 NEAR PARK | City: COIMBATORE | State: TAMIL NADU | ZIP: 641099 | Address1: 753 SECTOR 12 NEAR PARK | City1: COIMBATORE | State1: TAMIL NADU | ZIP1: 641099 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone:  | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: adityasingh@company.in | Email1:  | Email2:  | Email3:  | Email4: ', 'Name: Kiran Chopra | First: Kiran | Middle:  | Last: Chopra | Gender: M | DOB: 1986-04-13 | Spouse:  | Mother:  | Father:  | Company: GOOGLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 524 MG ROAD NEAR SCHOOL | City: NAGPUR | State: MAHARASHTRA | ZIP: 440013 | Address1: 524 MG ROAD NEAR SCHOOL | City1: NAGPUR | State1: MAHARASHTRA | ZIP1: 440013 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone:  | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: kiranchopra@company.in | Email1:  | Email2:  | Email3:  | Email4: '],
    ['Name: Divya Patel | First: Divya | Middle:  | Last: Patel | Gender: F | DOB: 1985-02-01 | Spouse:  | Mother:  | Father:  | Company: INFOSYS TECHNOLOGIES | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 316 SECTOR 12 NEAR PARK | City: HYDERABAD | State: TELANGANA | ZIP: 500048 | Address1: 316 SECTOR 12 NEAR PARK | City1: HYDERABAD | State1: TELANGANA | ZIP1: 500048 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 8883181644 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: divyapatel@outlook.com | Email1:  | Email2:  | Email3:  | Email4: ', 'Name: Nitin Rao | First: Nitin | Middle:  | Last: Rao | Gender: M | DOB: 1987-12-02 | Spouse:  | Mother:  | Father:  | Company: RELIANCE JIO | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 612 BANJARA HILLS NEAR PARK | City: COIMBATORE | State: TAMIL NADU | ZIP: 641039 | Address1: 612 BANJARA HILLS NEAR PARK | City1: COIMBATORE | State1: TAMIL NADU | ZIP1: 641039 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9358550137 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: nitinrao@gmail.com | Email1:  | Email2:  | Email3:  | Email4: '],
    ['Name: Neha Gupta | First: Neha | Middle:  | Last: Gupta | Gender: F | DOB: 1981-04-13 | Spouse:  | Mother:  | Father:  | Company: HEALTHCARE SYSTEMS | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: HOUSE 57, BLOCK A kanpur | City: KANPUR | State: UTTAR PRADESH | ZIP: 208001 | Address1: HOUSE 57, BLOCK A kanpur | City1: KANPUR | State1: UTTAR PRADESH | ZIP1: 208001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9423646570 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: nehagupta@gmail.com | Email1:  | Email2:  | Email3:  | Email4: ', 'Name: Vikram Gupta | First: Vikram | Middle:  | Last: Gupta | Gender: M | DOB: 1993-06-04 | Spouse:  | Mother:  | Father:  | Company: TECH SOLUTIONS PVT LTD | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: PLOT 510, NEAR TEMPLE delhi | City: DELHI | State: DELHI | ZIP: 110001 | Address1: PLOT 510, NEAR TEMPLE delhi | City1: DELHI | State1: DELHI | ZIP1: 110001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9288650860 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: vikramgupta@yahoo.com | Email1:  | Email2:  | Email3:  | Email4: '],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'Name: Rohan Rao Sharma | First: Rohan | Middle: Rao | Last: Sharma | Gender: M | DOB: 1983-08-04 | Spouse:  | Mother:  | Father:  | Company: ORACLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 551 KORAMANGALA NEAR MALL | City: AHMEDABAD | State: GUJARAT | ZIP: 380071 | Address1: 551 KORAMANGALA NEAR MALL | City1: AHMEDABAD | State1: GUJARAT | ZIP1: 380071 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 8641615633 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: rohan.sharma@gmail.com | Email1:  | Email2:  | Email3:  | Email4: ',
    [
        'Name: Rohan Rao Sharma | First: Rohan | Middle: Rao | Last: Sharma | Gender: M | DOB: 1983-08-04 | Spouse:  | Mother:  | Father:  | Company: ORACLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 551 KORAMANGALA NEAR MALL | City: AHMEDABAD | State: GUJARAT | ZIP: 380071 | Address1: 551 KORAMANGALA NEAR MALL | City1: AHMEDABAD | State1: GUJARAT | ZIP1: 380071 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone:  | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: rohan.sharma@yahoo.com | Email1:  | Email2:  | Email3:  | Email4: ',
        'Name: Priya  Reddy | First: Priya | Middle:  | Last: Reddy | Gender: F | DOB: 1983-07-03 | Spouse:  | Mother:  | Father:  | Company: GLOBAL INFOTECH PVT LTD | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD | City: LUCKNOW | State: UTTAR PRADESH | ZIP: 226001 | Address1: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD | City1: LUCKNOW | State1: UTTAR PRADESH | ZIP1: 226001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9208449460 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: priyareddy@gmail.com | Email1: priya.reddy@globalinfotech.com | Email2:  | Email3:  | Email4: ',
        'Name: Kiran Chopra | First: Kiran | Middle:  | Last: Chopra | Gender: M | DOB: 1986-04-13 | Spouse:  | Mother:  | Father:  | Company: GOOGLE INDIA | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 524 MG ROAD NEAR SCHOOL | City: NAGPUR | State: MAHARASHTRA | ZIP: 440013 | Address1: 524 MG ROAD NEAR SCHOOL | City1: NAGPUR | State1: MAHARASHTRA | ZIP1: 440013 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone:  | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: kiranchopra@company.in | Email1:  | Email2:  | Email3:  | Email4: ',
        'Name: Nitin Rao | First: Nitin | Middle:  | Last: Rao | Gender: M | DOB: 1987-12-02 | Spouse:  | Mother:  | Father:  | Company: RELIANCE JIO | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: 612 BANJARA HILLS NEAR PARK | City: COIMBATORE | State: TAMIL NADU | ZIP: 641039 | Address1: 612 BANJARA HILLS NEAR PARK | City1: COIMBATORE | State1: TAMIL NADU | ZIP1: 641039 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9358550137 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: nitinrao@gmail.com | Email1:  | Email2:  | Email3:  | Email4: ',
        'Name: Vikram Gupta | First: Vikram | Middle:  | Last: Gupta | Gender: M | DOB: 1993-06-04 | Spouse:  | Mother:  | Father:  | Company: TECH SOLUTIONS PVT LTD | ParentCompany:  | TaxID:  | LicenseID:  | PassportID:  | Address: PLOT 510, NEAR TEMPLE delhi | City: DELHI | State: DELHI | ZIP: 110001 | Address1: PLOT 510, NEAR TEMPLE delhi | City1: DELHI | State1: DELHI | ZIP1: 110001 | Address2:  | City2:  | State2:  | ZIP2:  | Address3:  | City3:  | State3:  | ZIP3:  | Address4:  | City4:  | State4:  | ZIP4:  | Phone: 9288650860 | Phone1:  | Phone2:  | Phone3:  | Phone4:  | Email: vikramgupta@yahoo.com | Email1:  | Email2:  | Email3:  | Email4: ',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Classification

Dataset: rich-entity-matching-lora
Evaluated with CrossEncoderClassificationEvaluator

Metric	Value
accuracy	1.0
accuracy_threshold	0.4994
f1	1.0
f1_threshold	0.4994
precision	1.0
recall	1.0
average_precision	1.0

Training Details

Training Dataset

Unnamed Dataset

Size: 126 training samples
Columns: sentence1, sentence2, and label

Approximate statistics based on the first 126 samples:

	sentence1	sentence2	label
type	string	string	int
details	min: 622 characters mean: 660.92 characters max: 715 characters	min: 627 characters mean: 664.96 characters max: 731 characters	0: ~53.97% 1: ~46.03%

Samples:

sentence1	sentence2	label
Name: Arjun Singh \| First: Arjun \| Middle: \| Last: Singh \| Gender: M \| DOB: 1997-12-22 \| Spouse: \| Mother: \| Father: \| Company: RELIANCE JIO \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 910 KORAMANGALA NEAR MALL \| City: PUNE \| State: MAHARASHTRA \| ZIP: 411092 \| Address1: 910 KORAMANGALA NEAR MALL \| City1: PUNE \| State1: MAHARASHTRA \| ZIP1: 411092 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: arjunsingh@workmail.com \| Email1: \| Email2: \| Email3: \| Email4:	Name: Swati Nair \| First: Swati \| Middle: \| Last: Nair \| Gender: F \| DOB: 2003-05-24 \| Spouse: \| Mother: \| Father: \| Company: ZOMATO \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 108 MAIN BAZAR NEAR SCHOOL \| City: CHENNAI \| State: TAMIL NADU \| ZIP: 600078 \| Address1: 108 MAIN BAZAR NEAR SCHOOL \| City1: CHENNAI \| State1: TAMIL NADU \| ZIP1: 600078 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 7185520040 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: swatinair@yahoo.com \| Email1: \| Email2: \| Email3: \| Email4:	`0`
Name: Rahul Iyer \| First: Rahul \| Middle: \| Last: Iyer \| Gender: M \| DOB: 1980-02-25 \| Spouse: \| Mother: \| Father: \| Company: MANUFACTURING CO \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: FLAT 271, PARK APT, 32 MAIN RD \| City: BANGALORE \| State: KARNATAKA \| ZIP: 560001 \| Address1: FLAT 271, PARK APT, 32 MAIN RD \| City1: BANGALORE \| State1: KARNATAKA \| ZIP1: 560001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9162959284 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: rahuliyer@gmail.com \| Email1: rahul.iyer@manufacturingco.com \| Email2: \| Email3: \| Email4:	Name: Rahul Iyer \| First: Rahul \| Middle: \| Last: Iyer \| Gender: M \| DOB: 1980-02-25 \| Spouse: \| Mother: \| Father: \| Company: MANUFACTURING CO PVT LTD \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: FLAT 271, PARK APT, 32 MAIN RD \| City: BANGALORE \| State: KARNATAKA \| ZIP: 560001 \| Address1: FLAT 271, PARK APT, 32 MAIN RD \| City1: BANGALORE \| State1: KARNATAKA \| ZIP1: 560001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9162959284 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: rahuliyer@gmail.com \| Email1: rahul.iyer@manufacturingco.com \| Email2: \| Email3: \| Email4:	`1`
Name: Amit Reddy \| First: Amit \| Middle: \| Last: Reddy \| Gender: M \| DOB: 1994-06-17 \| Spouse: \| Mother: \| Father: \| Company: AUTO PARTS PVT \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: HOUSE 112, SECTOR 12 kanpur \| City: KANPUR \| State: UTTAR PRADESH \| ZIP: 208001 \| Address1: HOUSE 112, SECTOR 12 kanpur \| City1: KANPUR \| State1: UTTAR PRADESH \| ZIP1: 208001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9337887233 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: amitreddy@gmail.com \| Email1: \| Email2: \| Email3: \| Email4:	Name: Pradeep Gupta \| First: Pradeep \| Middle: \| Last: Gupta \| Gender: M \| DOB: 2004-11-01 \| Spouse: \| Mother: \| Father: \| Company: MANUFACTURING CO \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: PLOT 491, NEAR TEMPLE delhi \| City: DELHI \| State: DELHI \| ZIP: 110001 \| Address1: PLOT 491, NEAR TEMPLE delhi \| City1: DELHI \| State1: DELHI \| ZIP1: 110001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9836691577 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: pradeepgupta@yahoo.com \| Email1: \| Email2: \| Email3: \| Email4:	`0`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

Evaluation Dataset

Unnamed Dataset

Size: 32 evaluation samples
Columns: sentence1, sentence2, and label

Approximate statistics based on the first 32 samples:

	sentence1	sentence2	label
type	string	string	int
details	min: 620 characters mean: 661.31 characters max: 708 characters	min: 628 characters mean: 660.66 characters max: 720 characters	0: ~53.12% 1: ~46.88%

Samples:

sentence1	sentence2	label
Name: Rohan Rao Sharma \| First: Rohan \| Middle: Rao \| Last: Sharma \| Gender: M \| DOB: 1983-08-04 \| Spouse: \| Mother: \| Father: \| Company: ORACLE INDIA \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 551 KORAMANGALA NEAR MALL \| City: AHMEDABAD \| State: GUJARAT \| ZIP: 380071 \| Address1: 551 KORAMANGALA NEAR MALL \| City1: AHMEDABAD \| State1: GUJARAT \| ZIP1: 380071 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 8641615633 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: rohan.sharma@gmail.com \| Email1: \| Email2: \| Email3: \| Email4:	Name: Rohan Rao Sharma \| First: Rohan \| Middle: Rao \| Last: Sharma \| Gender: M \| DOB: 1983-08-04 \| Spouse: \| Mother: \| Father: \| Company: ORACLE INDIA \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 551 KORAMANGALA NEAR MALL \| City: AHMEDABAD \| State: GUJARAT \| ZIP: 380071 \| Address1: 551 KORAMANGALA NEAR MALL \| City1: AHMEDABAD \| State1: GUJARAT \| ZIP1: 380071 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: rohan.sharma@yahoo.com \| Email1: \| Email2: \| Email3: \| Email4:	`1`
Name: Priya Prasad Reddy \| First: Priya \| Middle: Prasad \| Last: Reddy \| Gender: F \| DOB: 1983-07-03 \| Spouse: \| Mother: \| Father: \| Company: GLOBAL INFOTECH \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: FLAT 401, LAKE APT, 24 MAIN RD \| City: LUCKNOW \| State: UTTAR PRADESH \| ZIP: 226001 \| Address1: FLAT 401, LAKE APT, 24 MAIN RD \| City1: LUCKNOW \| State1: UTTAR PRADESH \| ZIP1: 226001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9149203558 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: priyareddy@gmail.com \| Email1: priya.reddy@globalinfotech.com \| Email2: \| Email3: \| Email4:	Name: Priya Reddy \| First: Priya \| Middle: \| Last: Reddy \| Gender: F \| DOB: 1983-07-03 \| Spouse: \| Mother: \| Father: \| Company: GLOBAL INFOTECH PVT LTD \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD \| City: LUCKNOW \| State: UTTAR PRADESH \| ZIP: 226001 \| Address1: FLAT 401, LAKE APARTMENT, 24 MAIN ROAD \| City1: LUCKNOW \| State1: UTTAR PRADESH \| ZIP1: 226001 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: 9208449460 \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: priyareddy@gmail.com \| Email1: priya.reddy@globalinfotech.com \| Email2: \| Email3: \| Email4:	`1`
Name: Aditya Singh \| First: Aditya \| Middle: \| Last: Singh \| Gender: M \| DOB: 1982-02-07 \| Spouse: \| Mother: \| Father: \| Company: CAPGEMINI INDIA \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 753 SECTOR 12 NEAR PARK \| City: COIMBATORE \| State: TAMIL NADU \| ZIP: 641099 \| Address1: 753 SECTOR 12 NEAR PARK \| City1: COIMBATORE \| State1: TAMIL NADU \| ZIP1: 641099 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: adityasingh@company.in \| Email1: \| Email2: \| Email3: \| Email4:	Name: Kiran Chopra \| First: Kiran \| Middle: \| Last: Chopra \| Gender: M \| DOB: 1986-04-13 \| Spouse: \| Mother: \| Father: \| Company: GOOGLE INDIA \| ParentCompany: \| TaxID: \| LicenseID: \| PassportID: \| Address: 524 MG ROAD NEAR SCHOOL \| City: NAGPUR \| State: MAHARASHTRA \| ZIP: 440013 \| Address1: 524 MG ROAD NEAR SCHOOL \| City1: NAGPUR \| State1: MAHARASHTRA \| ZIP1: 440013 \| Address2: \| City2: \| State2: \| ZIP2: \| Address3: \| City3: \| State3: \| ZIP3: \| Address4: \| City4: \| State4: \| ZIP4: \| Phone: \| Phone1: \| Phone2: \| Phone3: \| Phone4: \| Email: kiranchopra@company.in \| Email1: \| Email2: \| Email3: \| Email4:	`0`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 3e-05
weight_decay: 0.05
warmup_ratio: 0.2
warmup_steps: 0.2
dataloader_num_workers: 3
load_best_model_at_end: True
dataloader_pin_memory: False
dataloader_persistent_workers: True

All Hyperparameters

Click to expand

do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 4
per_device_eval_batch_size: 8
gradient_accumulation_steps: 4
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 3e-05
weight_decay: 0.05
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: 0.2
warmup_steps: 0.2
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 3
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: False
dataloader_persistent_workers: True
skip_memory_metrics: True
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	rich-entity-matching-lora_average_precision
0.5	4	0.0774	-	-
1.0	8	0.0427	-	-
1.5	12	0.0678	-	-
1.875	15	-	0.0067	1.0
2.0	16	0.0284	-	-
2.5	20	0.0091	-	-
3.0	24	0.0860	-	-

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.2.3
Transformers: 5.0.0
PyTorch: 2.10.0+cpu
Accelerate: 1.12.0
Datasets: 4.8.3
Tokenizers: 0.22.2

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",
}