README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4030
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-distilroberta-v1
widget:
  - source_sentence: What is the contact email for Dr. Amr Ashraf Mohamed Amin?
    sentences:
      - >-
        Topic: Second Level Courses (Mainstream)

        Summary: Outlines the course list for the third and fourth semesters,
        including course codes, titles, credit hours, and prerequisites.

        Chunk: "Second Level Courses (Mainstream) 

        Third Semester
         • HUM113: Report Writing (2 Credit Hours) 
        • CIS250: Object-Oriented Programming (3 Credit Hours) – Prerequisite:
        CIS150 

        (Structured Programming) 

        • BSC221: Discrete Mathematics (3 Credit Hours) 

        • CIS260: Logic Design (3 Credit Hours) – Prerequisite: BSC121 (Physics
        I) 

        • CIS280: Database Management Systems (3 Credit Hours) – Prerequisite:
        CIS150 

        (Structured Programming) 

        • CIS240: Statistical Analysis (3 Credit Hours) – Prerequisite: BSC123
        (Probability & 

        Statistics) 

        • Total Credit Hours: 17 

        Fourth Semester 

        • CIS220: Computer Organization & Architecture (3 Credit Hours) –
        Prerequisite: CIS260 

        (Logic Design) 

        • CIS270: Data Structure (3 Credit Hours) – Prerequisite: CIS250
        (Object-Oriented 

        Programming) 

        • BSC225: Linear Algebra (3 Credit Hours) 

        • CIS230: Operations Research (3 Credit Hours) 

        • CIS243: Artificial Intelligence (3 Credit Hours) – Prerequisite:
        CIS150 (Structured 

        Programming) 

        • Total Credit Hours: 15"
      - >-
        The final exam for the Structured programming course, offered by the
        general department, from 2022, is available at the following link:
        [https://drive.google.com/file/d/1Bpqoa78DcFNC8335i7vucV0nBN-J01v9/view?usp=sharing
      - >-
        Dr. Amr Ashraf Mohamed Amin is part of the Unknown department and can be
        reached at amr.amin.stdsw@cis.asu.edu.eg.
  - source_sentence: What systems have been developed for quickly locating missing children?
    sentences:
      - >-
        The final exam for Digital Signal Processing course, offered by the
        computer science department, from 2024, is available at the following
        link:
        [https://drive.google.com/file/d/1RO0aPoom-TA-qgsopwR9krszD_pQIzfJ/view?usp=sharing
      - >-
        **Lost People Finder**


        ### **Abstract**


        **Missing Persons Statistics**

        Recently, there has been a clear increase in the population. As stated
        in a 2005 report, published by the US Department of Justice, over
        340,500 of children's population go missing, from their parents, for at
        least an hour. Not only was this issue minor in between children, but
        also it has been evident that the elderly and people with special needs
        seem missing whenever their guardians get distracted.


        **Lost People Finder Application**

        Through the Lost People Finder application, we can search for missing
        people quickly and efficiently by entering the missing person's picture
        in the application, and the application searches for him immediately.
      - >-
        The final exam for the English 1course, offered by the general
        department, from 2022, is available at the following link:
        [https://drive.google.com/file/d/1IbqLbHuyZoDyhsL1BERpI2P0iLFZmgt8/view].
  - source_sentence: What are the conditions for the College Council granting a final chance?
    sentences:
      - >-
        Dr. Zeina Rayan is part of the Unknown department and can be reached at
        zeinarayan@cis.asu.edu.eg.
      - >-
        Topic: Academic Warning and Dismissal

        Summary: Students receive academic warnings for low GPAs and may be
        dismissed if the GPA remains low for six semesters or if graduation
        requirements aren't met within double the study years. Students can
        re-study courses to improve their average, with certain conditions and
        grade limits.

        Chunk: "Academic warning - dismissal from study - mechanisms of raising
        the cumulative average

        1. The student is given an academic warning if he obtains a cumulative
        average less than "2" for any semester that he must raise his cumulative
        average to at least 2.00.

        2. A student who is academically probated is dismissed from the study if
        the GPA drops below 2.00 is repeated during six main semesters.

        3. If the student does not meet the graduation requirements within the
        maximum period of study, which is double the years of study according to
        the law, he will be dismissed.

        4. The College Council may consider the possibility of granting the
        student exposed to dismissal as a result of his inability to raise his
        cumulative average to At least one and final chance of two semesters to
        raise his/her GPA to 2.00 and meet graduation requirements if he/she has
        successfully completed at least 80% of the credit hours required for
        graduation.

        5. The student may re-study the courses in which he has previously
        passed in order to improve the cumulative average, and the repetition is
        a study and an exam, and the grade he obtained the last time he studied
        the course is calculated for him. A maximum of (5) courses unless the
        improvement is for the purpose of raising the academic warning or
        achieving the graduation requirements, and in all cases, both grades are
        mentioned in his academic record.

        6. For the student to re-study a course in which he has previously
        obtained a grade of (F), the grade he obtained in the repetition is
        calculated with a maximum of (B), and for calculating the cumulative
        average, the last grade is calculated for him only, provided that both
        grades are mentioned in the student's academic record."
      - >-
        **Abstract**


        **Introduction to Renewable Energy**

        Renewable energy is gaining great importance nowadays. Solar energy is
        one of the most popular renewable energy sources as it is carbon dioxide
        free, has low operating costs, and its exploitation helps improve public
        health.


        **Project Overview**

        This project deals with the introduction of an embedded automatic solar
        energy tracking system that can be monitored remotely. The main
        objective of the system is to exploit the maximum amount of sunlight and
        convert it into electricity so that it can be used easily and
        efficiently. This can be done by rendering and aligning a model that
        drives the solar panels to be perpendicular to and track the sun's rays
        so that more energy is generated.


        **Advantages of the Tracker System**

        The main advantage of this tracker is that the various readings received
        from the sensors can be tracked remotely with a decentralized
        technological system that allows analysis of results, detection of
        faults and making tracking decisions. The advantage of this system is to
        provide access to a permanent and contamination-free power supply
        source. When connected to large battery banks, they can independently
        fill the needs of local areas.
  - source_sentence: How can I contact Dr. Doaa Mahmoud?
    sentences:
      - >-
        Dr. Hanan Hindy is part of the CS department and can be reached at
        hanan.hindy@cis.asu.edu.eg.
      - "The final exam for Database Management System\_course, offered by the general department, from 2019, is available at the following link: [https://drive.google.com/file/d/1OOIPr48WI8Cm3TVzPdel2Dh3SZUQTVxA/view"
      - >-
        Dr. Doaa Mahmoud is part of the Unknown department and can be reached at
        Doaa.Mahmoud@cis.asu.edu.eg.
  - source_sentence: Where can I find Abdel Badi Salem's email address?
    sentences:
      - >-
        # **Abstract**


        ## **Introduction**

        One of the main issues we are aiming to help in society are those of the
        disabled. Disabilities do not have a single type or manner in which it
        attacks the body but comes in a very wide range. At the present time,
        the amount of disabled people is **increasing annually**, so we aim to
        make a standard wheelchair to aid the mobility of disabled people who
        cannot walk; by designing two mechanisms, one uses eye-movement guidance
        and the other uses EEG Signals, which goes through pre-processing stage
        to extract more information from the data. This' done by segmentation
        using a window of size 200 (Sampling frequency), then features
        extraction. That takes us to classification, the highest accuracy we got
        is on subject [E] for motor imaginary dataset on Classical paradigm,
        Multi Level Perceptron classifier (with accuracy of 60.5%), The result
        of this classification's used as a command to move the wheelchair after
        that.
      - >-
        # **Abstract**


        ## **Sports Analytics Overview**

        Sports analytics has been successfully applied in sports like football
        and basketball. However, its application in soccer has been limited.
        Research in soccer analytics with Machine Learning techniques is limited
        and is mostly employed only for predictions. There is a need to find out
        if the application of Machine Learning can bring better and more
        insightful results in soccer analytics. In this thesis, we perform
        descriptive as well as predictive analysis of soccer matches and player
        performances.


        ## **Football Rating Analysis**

        In football, it is popular to rely on ratings by experts to assess a
        player's performance. However, the experts do not unravel the criteria
        they use for their rating. We attempt to identify the most important
        attributes of player's performance which determine the expert ratings.
        In this way we find the latent knowledge which the experts use to assign
        ratings to players. We performed a series of classifications with three
        different pruning strategies and an array of Machine Learning
        algorithms. The best results for predicting ratings using performance
        metrics had mean absolute error of 0.17. We obtained a list of most
        important performance metrics for each of the playing positions which
        approximates the attributes considered by the experts for assigning
        ratings. Then we find the most influential performance metrics of the
        players for determining the match outcome and we examine the extent to
        which the outcome is characterized by the performance attributes of the
        players. We found 34 performance attributes
      - >-
        Dr. Abdel Badi Salem is part of the CS department and can be reached at
        absalem@cis.asu.edu.eg.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-distilroberta-v1
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: ai college validation
          type: ai-college-validation
        metrics:
          - type: cosine_accuracy@1
            value: 0.18810557968593383
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4186435015035082
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5676578683595055
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8463080521216171
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18810557968593383
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13954783383450275
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1135315736719011
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08463080521216171
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18810557968593383
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4186435015035082
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5676578683595055
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8463080521216171
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47259073953229414
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3588172667440963
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3678298256041653
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.18843969261610424
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4173070497828266
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5669896424991647
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8456398262612763
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18843969261610424
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13910234992760886
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11339792849983296
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08456398262612765
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18843969261610424
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4173070497828266
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5669896424991647
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8456398262612763
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47223133269915585
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3585802056650706
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3676667485080777
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.1102813476901702
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3218131295588746
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5451545675581799
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8817297672803056
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1102813476901702
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1072710431862915
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10903091351163598
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08817297672803058
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1102813476901702
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3218131295588746
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5451545675581799
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8817297672803056
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4323392922230707
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2959338835684789
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.30305652186931414
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.18576678917474107
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42064817908453056
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5699966588706983
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.858002004677581
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18576678917474107
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.14021605969484352
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11399933177413965
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08580020046775809
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18576678917474107
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.42064817908453056
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5699966588706983
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.858002004677581
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47488287423350733
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.35840307277828215
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3669503238927413
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.1827597728032075
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42198463080521215
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5750083528232542
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8683595055128633
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1827597728032075
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.14066154360173738
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11500167056465085
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08683595055128634
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1827597728032075
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.42198463080521215
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5750083528232542
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8683595055128633
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4780584736286147
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3594039531393358
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3674823360981191
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.17674574006014032
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42098229201470094
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5720013364517207
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8763782158369529
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17674574006014032
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.140327430671567
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11440026729034415
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08763782158369529
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17674574006014032
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.42098229201470094
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5720013364517207
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8763782158369529
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47784861917490756
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.356773211567732
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3644323168133691
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.17674574006014032
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42098229201470094
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5720013364517207
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8763782158369529
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17674574006014032
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.140327430671567
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11440026729034415
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08763782158369529
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17674574006014032
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.42098229201470094
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5720013364517207
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8763782158369529
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.47784861917490756
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.356773211567732
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3644323168133691
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: ai college modefied validation
          type: ai-college_modefied-validation
        metrics:
          - type: cosine_accuracy@1
            value: 0.1127127474817645
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3218131295588746
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5481069815908302
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8931920805835359
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1127127474817645
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.10727104318629153
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10962139631816603
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08931920805835358
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1127127474817645
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3218131295588746
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5481069815908302
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8931920805835359
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4379716529188091
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2999361137299657
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.30656764876713344
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.10993400486279958
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.32737061479680446
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5489753386592567
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8989232372351511
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.10993400486279958
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.10912353826560146
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10979506773185134
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08989232372351512
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.10993400486279958
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.32737061479680446
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5489753386592567
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8989232372351511
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.43927652334969547
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2998494158575775
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.30624915588054374
            name: Cosine Map@100
          - type: cosine_accuracy@1
            value: 0.10993400486279958
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3268496005557485
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.548627995831886
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8989232372351511
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.10993400486279958
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.10894986685191616
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10972559916637721
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08989232372351512
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.10993400486279958
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3268496005557485
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.548627995831886
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8989232372351511
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.43919844728741414
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.29975865186875866
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3061583918917249
            name: Cosine Map@100

SentenceTransformer based on sentence-transformers/all-distilroberta-v1

This is a sentence-transformers model finetuned from sentence-transformers/all-distilroberta-v1. It maps sentences & paragraphs to a 768-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: sentence-transformers/all-distilroberta-v1
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• 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': False}) with Transformer model: RobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("Bo8dady/finetuned3-College-embeddings")
# Run inference
sentences = [
    "Where can I find Abdel Badi Salem's email address?",
    'Dr. Abdel Badi Salem is part of the CS department and can be reached at absalem@cis.asu.edu.eg.',
    "# **Abstract**\n\n## **Sports Analytics Overview**\nSports analytics has been successfully applied in sports like football and basketball. However, its application in soccer has been limited. Research in soccer analytics with Machine Learning techniques is limited and is mostly employed only for predictions. There is a need to find out if the application of Machine Learning can bring better and more insightful results in soccer analytics. In this thesis, we perform descriptive as well as predictive analysis of soccer matches and player performances.\n\n## **Football Rating Analysis**\nIn football, it is popular to rely on ratings by experts to assess a player's performance. However, the experts do not unravel the criteria they use for their rating. We attempt to identify the most important attributes of player's performance which determine the expert ratings. In this way we find the latent knowledge which the experts use to assign ratings to players. We performed a series of classifications with three different pruning strategies and an array of Machine Learning algorithms. The best results for predicting ratings using performance metrics had mean absolute error of 0.17. We obtained a list of most important performance metrics for each of the playing positions which approximates the attributes considered by the experts for assigning ratings. Then we find the most influential performance metrics of the players for determining the match outcome and we examine the extent to which the outcome is characterized by the performance attributes of the players. We found 34 performance attributes",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Datasets: ai-college-validation, ai-college_modefied-validation, ai-college-validation, ai-college_modefied-validation, ai-college-validation, ai-college_modefied-validation and ai-college-validation
• Evaluated with InformationRetrievalEvaluator

Metric	ai-college-validation	ai-college_modefied-validation
cosine_accuracy@1	0.1767	0.1099
cosine_accuracy@3	0.421	0.3268
cosine_accuracy@5	0.572	0.5486
cosine_accuracy@10	0.8764	0.8989
cosine_precision@1	0.1767	0.1099
cosine_precision@3	0.1403	0.1089
cosine_precision@5	0.1144	0.1097
cosine_precision@10	0.0876	0.0899
cosine_recall@1	0.1767	0.1099
cosine_recall@3	0.421	0.3268
cosine_recall@5	0.572	0.5486
cosine_recall@10	0.8764	0.8989
cosine_ndcg@10	0.4778	0.4392
cosine_mrr@10	0.3568	0.2998
cosine_map@100	0.3644	0.3062

Information Retrieval

• Dataset: ai-college-validation
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1884
cosine_accuracy@3	0.4173
cosine_accuracy@5	0.567
cosine_accuracy@10	0.8456
cosine_precision@1	0.1884
cosine_precision@3	0.1391
cosine_precision@5	0.1134
cosine_precision@10	0.0846
cosine_recall@1	0.1884
cosine_recall@3	0.4173
cosine_recall@5	0.567
cosine_recall@10	0.8456
cosine_ndcg@10	0.4722
cosine_mrr@10	0.3586
cosine_map@100	0.3677

Information Retrieval

• Dataset: ai-college-validation
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1103
cosine_accuracy@3	0.3218
cosine_accuracy@5	0.5452
cosine_accuracy@10	0.8817
cosine_precision@1	0.1103
cosine_precision@3	0.1073
cosine_precision@5	0.109
cosine_precision@10	0.0882
cosine_recall@1	0.1103
cosine_recall@3	0.3218
cosine_recall@5	0.5452
cosine_recall@10	0.8817
cosine_ndcg@10	0.4323
cosine_mrr@10	0.2959
cosine_map@100	0.3031

Information Retrieval

• Dataset: ai-college-validation
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1858
cosine_accuracy@3	0.4206
cosine_accuracy@5	0.57
cosine_accuracy@10	0.858
cosine_precision@1	0.1858
cosine_precision@3	0.1402
cosine_precision@5	0.114
cosine_precision@10	0.0858
cosine_recall@1	0.1858
cosine_recall@3	0.4206
cosine_recall@5	0.57
cosine_recall@10	0.858
cosine_ndcg@10	0.4749
cosine_mrr@10	0.3584
cosine_map@100	0.367

Training Details

Training Dataset

Unnamed Dataset

• Size: 4,030 training samples
• Columns: Question and chunk
• Approximate statistics based on the first 1000 samples:

  	Question	chunk
  type	string	string
  details	min: 8 tokens mean: 15.99 tokens max: 31 tokens	min: 21 tokens mean: 133.41 tokens max: 512 tokens

• Samples:

  Question	chunk
  Could you share the link to the 2018 Distributed Computing final exam?	The final exam for Distributed Computing course, offered by the computer science department, from 2018, is available at the following link: [https://drive.google.com/file/d/1YSzMeYStlFEztP0TloIcBqnfPr60o4ez/view?usp=sharing
  What databases exist for footstep recognition research?	Abstract Documentation Overview This documentation reports an experimental analysis of footsteps as a biometric. The focus here is on information extracted from the time domain of signals collected from an array of piezoelectric sensors. Database Information Results are related to the largest footstep database collected to date, with almost 20,000 valid footstep signals and more than 120 persons, which is well beyond previous related databases. Feature Extraction Three feature approaches have been extracted, the popular ground reaction force (GRF), the spatial average and the upper and lower contours of the pressure signals. Experimental Results Experimental work is based on a verification mode with a holistic approach based on PCA and SVM, achieving results in the range of 5 to 15% equal error rate(EER) depending on the experimental conditions of quantity of data used in the reference models.
  Is there a maximum duration of study specified in the text?	Topic: Duration of Study Summary: A bachelor's degree at the Faculty of Computers and Information requires at least four years of study, contingent on fulfilling degree requirements. Chunk: "Duration of study • The duration of study at the Faculty of Computers and Information to obtain a bachelor's degree is not less than 4 years, provided that the requirements for obtaining the scientific degree are completed."

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 575 evaluation samples
• Columns: Question and chunk
• Approximate statistics based on the first 575 samples:

  	Question	chunk
  type	string	string
  details	min: 9 tokens mean: 15.97 tokens max: 29 tokens	min: 21 tokens mean: 134.83 tokens max: 484 tokens

• Samples:

  Question	chunk
  Are there projects that use machine learning for automatic brain tumor identification?	# Abstract ## Brain and Tumor Description A human brain is center of the nervous system; it is a collection of white mass of cells. A tumor of brain is collection of uncontrolled increasing of these cells abnormally found in different part of the brain namely Glial cells, neurons, lymphatic tissues, blood vessels, pituitary glands and other part of brain which lead to the cancer. ## Detection and Identification Manually it is not so easily possible to detect and identify the tumor. Programming division method by MRI is way to detect and identify the tumor. In order to give precise output a strong segmentation method is needed. Brain tumor identification is really challenging task in early stages of life. But now it became advanced with various machine learning and deep learning algorithms. Now a day's issue of brain tumor automatic identification is of great interest. In Order to detect the brain tumor of a patient we consider the data of patients like MRI images of a pat...
  Are there studies that propose solutions to the challenges of plant pest detection using deep learning?	Abstract Introduction Identification of the plant diseases is the key to preventing the losses in the yield and quantity of the agricultural product. Disease diagnosis based on the detection of early symptoms is a usual threshold taken into account for integrated pest management strategies. through deep learning methodologies, plant diseases can be detected and diagnosed. Study Discussion On this basis, this study discusses possible challenges in practical applications of plant diseases and pests detection based on deep learning. In addition, possible solutions and research ideas are proposed for the challenges, and several suggestions are given. Finally, this study gives the analysis and prospect of the future trend of plant diseases and pests detection based on deep learning. 5
  Is there a link available for the 2025 Calc 1 course exam?	The final exam for the calculus1 course, offered by the general department, from 2025, is available at the following link: [https://drive.google.com/file/d/1g8iiGUo4HCUzNNWBJJrW1QZAsz-RYehw/view?usp=sharing].

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 1e-06
• num_train_epochs: 10
• warmup_ratio: 0.2
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 1e-06
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.2
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• tp_size: 0
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	ai-college-validation_cosine_ndcg@10	ai-college_modefied-validation_cosine_ndcg@10
-1	-1	-	-	0.4208	-
0.3968	100	0.1371	0.0785	0.4483	-
0.7937	200	0.0575	0.0357	0.4600	-
1.1905	300	0.0346	0.0286	0.4640	-
1.5873	400	0.0313	0.0264	0.4698	-
1.9841	500	0.0189	0.0256	0.4716	-
2.3810	600	0.021	0.0249	0.4703	-
2.7778	700	0.0264	0.0247	0.4726	-
-1	-1	-	-	0.4252	-
0.3968	100	0.0132	0.0238	0.4277	-
0.7937	200	0.0192	0.0221	0.4295	-
1.1905	300	0.0169	0.0214	0.4316	-
1.5873	400	0.02	0.0200	0.4315	-
1.9841	500	0.0124	0.0201	0.4315	-
2.3810	600	0.0152	0.0195	0.4311	-
2.7778	700	0.0189	0.0193	0.4309	-
3.1746	800	0.0222	0.0182	0.4307	-
3.5714	900	0.0158	0.0182	0.4312	-
3.9683	1000	0.0144	0.0181	0.4311	-
4.3651	1100	0.0237	0.0176	0.4315	-
4.7619	1200	0.0132	0.0178	0.4323	-
-1	-1	-	-	0.4749	0.4326
0.3968	100	0.0077	0.0175	-	0.4322
0.7937	200	0.0116	0.0171	-	0.4320
1.1905	300	0.0093	0.0169	-	0.4339
1.5873	400	0.0125	0.0160	-	0.4340
1.9841	500	0.0083	0.0161	-	0.4340
2.3810	600	0.0105	0.0156	-	0.4350
2.7778	700	0.0132	0.0155	-	0.4357
3.1746	800	0.0161	0.0145	-	0.4362
3.5714	900	0.0113	0.0144	-	0.4372
3.9683	1000	0.0112	0.0140	-	0.4368
4.3651	1100	0.0185	0.0136	-	0.4366
4.7619	1200	0.0101	0.0139	-	0.4367
5.1587	1300	0.0118	0.0138	-	0.4366
5.5556	1400	0.0145	0.0139	-	0.4366
5.9524	1500	0.0104	0.0139	-	0.4376
6.3492	1600	0.0105	0.0137	-	0.4380
6.7460	1700	0.0125	0.0137	-	0.4380
-1	-1	-	-	0.4781	0.4375
0.3968	100	0.0054	0.0135	-	0.4380
0.7937	200	0.0078	0.0133	-	0.4374
1.1905	300	0.0053	0.0132	-	0.4381
1.5873	400	0.0077	0.0127	-	0.4387
1.9841	500	0.0054	0.0129	-	0.4374
2.3810	600	0.0067	0.0122	-	0.4392
2.7778	700	0.0094	0.0120	-	0.4387
3.1746	800	0.0111	0.0116	-	0.4360
3.5714	900	0.0079	0.0113	-	0.4368
3.9683	1000	0.0081	0.0111	-	0.4369
4.3651	1100	0.0134	0.0109	-	0.4375
4.7619	1200	0.0072	0.0110	-	0.4371
5.1587	1300	0.0091	0.0109	-	0.4378
5.5556	1400	0.0121	0.0111	-	0.4379
5.9524	1500	0.0081	0.0111	-	0.4376
6.3492	1600	0.008	0.0110	-	0.4376
6.7460	1700	0.0103	0.0109	-	0.4389
7.1429	1800	0.013	0.0108	-	0.4397
7.5397	1900	0.0134	0.0109	-	0.4385
7.9365	2000	0.0133	0.0108	-	0.4398
8.3333	2100	0.0109	0.0109	-	0.4389
8.7302	2200	0.0109	0.0107	-	0.4386
9.1270	2300	0.0077	0.0104	-	0.4395
9.5238	2400	0.0107	0.0104	-	0.4387
9.9206	2500	0.0117	0.0104	-	0.4393
-1	-1	-	-	0.4778	0.4392

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.51.1
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.5.0
• Tokenizers: 0.21.0

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}