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:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: BAAI/bge-small-en-v1.5
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 27 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
Label | Examples |
---|---|
NFT_ARTIST |
|
UNDETERMINED |
|
DEVELOPER |
|
EXECUTIVE |
|
INFLUENCER |
|
BUSINESS_DEVELOPER |
|
TRADER |
|
ONCHAIN_ANALYST |
|
RESEARCHER |
|
INVESTOR |
|
SECURITY_AUDITOR |
|
EDUCATOR |
|
LAWYER |
|
ADVISOR |
|
COMMUNITY_MANAGER |
|
MARKETER |
|
ANGEL_INVESTOR |
|
VENTURE_CAPITALIST |
|
NFT_COLLECTOR |
|
BLOGGER |
|
METAVERSE_ENTHUSIAST |
|
FINANCIAL_ANALYST |
|
DATA_SCIENTIST |
|
NODE_OPERATOR |
|
SHITCOINER |
|
MINER |
|
DATA_ANALYST |
|
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}
}