kasparas12's picture
Push model using huggingface_hub.
1d4388e verified
|
raw
history blame
27 kB
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: ' '
  - text: quantitative algorithmic hustle trading dot com
  - text: cryptoart since early 2020  founder of ENCODE_graphics red_heart EARTH
  - text: >-
      Chief Legal Officer krakenfx Not your lawyer Assumptions opinions
      prevarications and predictions are mine not my employers 
  - text: >-
      Chief of Staff at Remilia Corporation remiliacorp333 Warlord Commander at
      YAYO Corporation YayoCorp THIS IS NOT A PROMISE OF EQUITY OR OWNERSHIP IN
      ANYTHING 
pipeline_tag: text-classification
inference: true
base_model: BAAI/bge-small-en-v1.5
model-index:
  - name: SetFit with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.4891640866873065
            name: Accuracy

SetFit with BAAI/bge-small-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

  1. Fine-tuning a Sentence Transformer with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Sources

Model Labels

Label Examples
NFT_ARTIST
  • 'Onchain music cooprecordsxyz invinmusic cooprecsmusic Los Angeles'
  • 'Artist etc Chicago'
  • 'Where NFTs meet DeFi on SecretNetwork Are you Legendary nfts gamefi defi SCRT LGND Secret Network'
UNDETERMINED
  • '100 readerfunded writer All works free to republish bootleg use or cp All works coauthored by Tim Foley Patreon Australia'
  • 'Pro skater father husband videogame character CEO philanthropist public skatepark advocate Old AF and still skating San Diego world at large'
  • 'Sandy and blue '
DEVELOPER
  • 'BUIDL HODL CELR CelerNetwork BNB bnb48club BTC ETC ATOM No gods no masters only hashes Shadowy Coder trolling by day coding by night Metalhead Cosmos'
  • 'crosspost to Farcaster Bluesky Twitter Lens Threads decentralized social in one feed iOS '
  • 'VP of Engineering at avara space nerd my astrobin profile Opinions strictly my own '
EXECUTIVE
  • 'Epic Games founder and CEO '
  • 'CEO compoundfinance San Francisco USA'
  • 'DeFi FounderUnited_States bornraised Bahai Los Angeles'
INFLUENCER
  • 'That rug really tied the room together weekly news channel on hiatus '
  • 'Conecto con personas de habla hispana con perfil propio dentro de bitcoin y comparto su valor preguntasbtc para respuestas en 24h lunaticoingetalbycom 2515 4D1C 6C36 C024'
  • 'sols 学习新事物 不带偏见的去看币圈 macau'
BUSINESS_DEVELOPER
  • 'Chief of Growth fuel_network Ex0xMantle Ex0xPolygon Tea connoisseur Dog Lover Web3 Degen Views are my own Metaverse'
  • 'Experience Bitcoin like never before '
  • 'Bitcoin Blockchain bitcoinmining Bitpay Founded the Original WomenInBitcoin etc Los Angeles '
TRADER
  • 'your greater fool goblin town'
  • 'Commander in chiefing Periodically 1 ranked trader on ByBit Zaza City'
  • 'Ethereum Maximalist Synthetix Spartan '
ONCHAIN_ANALYST
  • 'technical and onchain analyst crypto stock real estate investor global head of news beincrypto spreading alpha United States'
  • 'Cofounder reflexivityres acq by defitechglobal Using velodata New York NY'
  • 'Cofounder ensuser research y2z_ventures Full time onchain moron ethereum'
RESEARCHER
  • 'Lets skip witty repartee discuss fundamental questions Views are mine not GMUs or Virginias Books Fairfax VA'
  • 'research paradigm '
  • 'Crypto Data Research 0x'
INVESTOR
  • 'peer to peer electronic cash enthusiast light__nh hethey '
  • 'GoldLover '
  • 'I enjoy business innovation lifelong learning to ChangeTheWorld to help others Entrepreneur interim CxO investor adventurer thinker doer NO DMs Global citizen'
SECURITY_AUDITOR
  • 'security researcher nascentsecurity EVM Enthusiast Gas Optimizoor Puzzle Cracker Fan of all things Static Analysis Fuzzing Symbolic Execution '
  • 'think bad do good cofounder openpathsec los angeles'
  • 'Head of GTM CyfrinAudits Ex Lead Dev Rel AlchemyPlatform Created cyfrinupdraft and AlchemyLearn Making web3 mainstream Ethereum'
EDUCATOR
  • 'Professor of Practice at Harvard Teaches Ec 10 some tweets might be educational Also Senior Fellow PIIE Was Chair of President Obamas CEA Cambridge MA'
  • 'Jarrête des carrières Je vulgarise et décortique à vos côtés les nouvelles tokenomics et les influvoleurs crypto de notre époque Bitcoin'
  • ' Bretton Woods NH'
LAWYER
  • 'Author of Digital Money Demystified DickinsonLaw AdvantageEvans AtTechIntersect Crypto IP Law As seen on Coindesk TV Yahoo Finance Bloomberg CNBC Nomad Team '
  • 'UVa Vanderbilt Law Your guide to other worlds Crypto l Metaverse Web3 Not legal or financial advice I am A lawyerjust not YOUR lawyer USA'
  • 'The Crypto Lawyer Юрист Rechtsanwältin محامية Advising Entrepreneurs Investors and Governments on Bitcoin Crypto since 2016 Contributor Forbes UAE Switzerland '
ADVISOR
  • 'Director of Government Relations at BlockchainAssn Author of the Token Taxonomy Act Former WarrenDavidson and Board of Advisors JoinSeedstarter Washington DC'
  • 'Calculated Degen 2x cancer survivor 5x rug pull survivor Paper hands diamond wrist Building WumboLabs Advisoooor arcade_xyz '
  • 'Doggfather Analytics Founderorange_square OrdData '
COMMUNITY_MANAGER
  • 'Contributor to the Optimism Collective OP'
  • 'ecosystem growth indexcoop music NFT enjoyer wavWRLD_ not financial advice typos are my owm '
  • 'Founder KryptoSeoul ericaplanet Ericaverse Organizer buidl_asia eth_seoul_ Seoul Chapter Lead She__Fi Alum Stanford Ewha Where is Erica'
MARKETER
  • 'Positivity Pusher CoFounder PurpleHorizons Future Tech Marketing Strategist Trend Spotter Storyteller Once a DJ Always a DJ Miami FL'
  • 'elissa emm Head of Marketing at spruceid building decentralized identity Seattle WA'
  • 'Marketing Superfluid_HQ Safaryclub solhotgirlclub She__Fi Cohort 9 Words in banklesshq PFP miladymaker 104 NFA Views are my own Brooklyn NY'
ANGEL_INVESTOR
  • 'Developer entrepreneur angel investor crypto enthusiast '
  • 'larp LawliettesLab angel uvocapital '
  • 'cofounder jokerace_io ecodao_ write on web3 angel thecowfund berlin'
VENTURE_CAPITALIST
  • 'visionary at core playful at the surface just launched GetCohosts WalkinEvents prev fabric_vc nothingnyc London UK New York USA'
  • 'Crypto web3 Partner ColliderVC Standing on the shoulders of giants World State'
  • 'startup investor and builder founder w_conviction before GP greylockVC accelerating AI adoption tech podcastchains'
NFT_COLLECTOR
  • 'FINE BITCOIN GOODS Get in THE BANTER Scarce City'
  • 'Cofounder RKOTax omega based spicymargeth '
  • 'Like a shadow following the light Time is actually another dimension Nikennftyeth Niken32lens bcard id 275 Multiverse of Madness'
BLOGGER
  • 'Reporter at Bloomberg business covering crypto blockchain companies Formerly CoinDesk DM open Opinions are my own New York USA'
  • 'viamirror '
  • 'senior writer NFT lead BanklessHQ '
METAVERSE_ENTHUSIAST
  • 'SMOL by Treasure_DAO Smolverse'
  • 'Epic SciFi MMO strategy game from Pixelmatic ExordiumHQ Take command of a fleet of spaceships and fight for humanity NOW Sol System'
  • 'Time to post tweets and save lives Creative Director PlayShadowWar Where dreams come true'
FINANCIAL_ANALYST
  • 'Editor of FTAlphaville Norwegian despite the Harry Potteresque name Author of TRILLIONS Views mine bla bla Oslo Norway'
  • 'markets macro business anchor of 10am ET and ETF IQ on bloombergtv haverfordedu columbiajourn alum ktkaos on InstaThreads Opinions mine Midtown East Manhattan'
  • 'Curious on how behavioral fallacies challenge financial markets and cryptos Always learning new things getting to know new people and having a bit of fun London England'
DATA_SCIENTIST
  • ' '
  • 'Data Wizardry variantfund Chicago IL'
  • 'NLP ML StatArb Math Bowdoincollege Team Doobro_CN Prev first intern Bybit_Official Plucking a feather from every goose but follow no one absolute New York NY'
NODE_OPERATOR
  • 'Founder ClayStack_HQ Building Liquid Staking long before they were called LSDs Running validator nodes at Vibing ClayClanDAO Metaverse'
  • 'Restake ETH Never Worry about EigenLayer Caps EigenLayer'
  • 'HonigdachsPod cohost Making Bitcoin green today netposmon Find me on nostr npub1cear2n95zcyze86s5hry2a0pdgs7euhnc0p7ewcq2284pp845t5szt8rhr '
SHITCOINER
  • 'Eternity belongs to those who live in the present I tweet once per week when Im pooping Results in occasional shitposting '
  • 'Lets hold hands and be enemies enemieswithbenefitseth '
  • '16th Chair of the Central Bank of Retards When I see chaos forming on the timeline I rush in to shitpost adding fuel to the fire Hyperbolic Time Chamber'
MINER
  • ' bitcoin beyonder economic futurist metagame winner rose'
  • 'Steady lads deploying more hashrate Hashrate merchant luxortechnology btc Miami'
  • 'SVP foundryservices I am a miner like my father before me previously greenidge_GREE Bitcoin '
DATA_ANALYST
  • 'Director of Research at proof_xyz Building charts that make NFTs a bit easier to understand '
  • 'Shadowy mediocre Analyst tangent_xyz '
  • 'Lead Analyst CryptoSlate Previously Saidler Bitcoin London'

Evaluation

Metrics

Label Accuracy
all 0.4892

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("kasparas12/crypto_individual_infer_model_setfit")
# Run inference
preds = model(" ")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 2 13.6494 65
Label Training Sample Count
DEVELOPER 702
DATA_SCIENTIST 34
DATA_ANALYST 8
NODE_OPERATOR 18
MINER 22
SECURITY_AUDITOR 129
INVESTOR 212
ANGEL_INVESTOR 84
VENTURE_CAPITALIST 467
TRADER 168
SHITCOINER 34
BUSINESS_DEVELOPER 306
BUSINESS_ANALYST 0
COMMUNITY_MANAGER 122
MARKETER 70
FINANCIAL_ANALYST 32
ADVISOR 79
RESEARCHER 227
ONCHAIN_ANALYST 29
EXECUTIVE 393
INFLUENCER 510
LAWYER 47
BLOGGER 55
NFT_COLLECTOR 174
NFT_ARTIST 312
EDUCATOR 134
METAVERSE_ENTHUSIAST 57
UNDETERMINED 740

Training Hyperparameters

  • batch_size: (64, 64)
  • num_epochs: (1, 1)
  • max_steps: -1
  • sampling_strategy: oversampling
  • num_iterations: 20
  • body_learning_rate: (2e-05, 1e-05)
  • head_learning_rate: 0.01
  • loss: CosineSimilarityLoss
  • distance_metric: cosine_distance
  • margin: 0.25
  • end_to_end: False
  • use_amp: False
  • warmup_proportion: 0.1
  • seed: 42
  • eval_max_steps: -1
  • load_best_model_at_end: False

Training Results

Epoch Step Training Loss Validation Loss
0.0011 1 0.2537 -
0.0562 50 0.2412 -
0.1124 100 0.2242 -
0.1685 150 0.2066 -
0.2247 200 0.1811 -
0.2809 250 0.205 -
0.3371 300 0.1789 -
0.3933 350 0.1831 -
0.4494 400 0.1829 -
0.5056 450 0.1506 -
0.5618 500 0.1474 -
0.6180 550 0.0989 -
0.6742 600 0.1094 -
0.7303 650 0.1316 -
0.7865 700 0.1207 -
0.8427 750 0.1262 -
0.8989 800 0.1229 -
0.9551 850 0.0989 -
0.0003 1 0.2061 -
0.0155 50 0.2073 -
0.0310 100 0.1844 -
0.0465 150 0.1891 -
0.0619 200 0.1975 -
0.0774 250 0.1772 -
0.0929 300 0.2304 -
0.1084 350 0.2085 -
0.1239 400 0.1851 -
0.1394 450 0.1463 -
0.1548 500 0.1216 -
0.1703 550 0.1648 -
0.1858 600 0.1359 -
0.2013 650 0.163 -
0.2168 700 0.1563 -
0.2323 750 0.2 -
0.2478 800 0.1425 -
0.2632 850 0.1614 -
0.2787 900 0.1881 -
0.2942 950 0.133 -
0.3097 1000 0.1348 -
0.3252 1050 0.1256 -
0.3407 1100 0.1065 -
0.3561 1150 0.0932 -
0.3716 1200 0.122 -
0.3871 1250 0.0969 -
0.4026 1300 0.1386 -
0.4181 1350 0.1116 -
0.4336 1400 0.0866 -
0.4491 1450 0.084 -
0.4645 1500 0.1073 -
0.4800 1550 0.1065 -
0.4955 1600 0.1063 -
0.5110 1650 0.1235 -
0.5265 1700 0.0918 -
0.5420 1750 0.078 -
0.5574 1800 0.1358 -
0.5729 1850 0.0664 -
0.5884 1900 0.1123 -
0.6039 1950 0.0996 -
0.6194 2000 0.0471 -
0.6349 2050 0.1068 -
0.6504 2100 0.0933 -
0.6658 2150 0.0836 -
0.6813 2200 0.0858 -
0.6968 2250 0.0421 -
0.7123 2300 0.08 -
0.7278 2350 0.0902 -
0.7433 2400 0.0949 -
0.7587 2450 0.116 -
0.7742 2500 0.0733 -
0.7897 2550 0.101 -
0.8052 2600 0.0709 -
0.8207 2650 0.079 -
0.8362 2700 0.0706 -
0.8517 2750 0.0338 -
0.8671 2800 0.0812 -
0.8826 2850 0.063 -
0.8981 2900 0.075 -
0.9136 2950 0.081 -
0.9291 3000 0.1264 -
0.9446 3050 0.0766 -
0.9600 3100 0.0873 -
0.9755 3150 0.0512 -
0.9910 3200 0.0816 -

Framework Versions

  • Python: 3.9.16
  • SetFit: 1.0.3
  • Sentence Transformers: 2.2.2
  • Transformers: 4.21.3
  • PyTorch: 1.12.1+cu116
  • Datasets: 2.4.0
  • Tokenizers: 0.12.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}