metadata

base_model: sentence-transformers/paraphrase-mpnet-base-v2
datasets:
  - zeroshot/twitter-financial-news-sentiment
library_name: setfit
metrics:
  - f1
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      Listen to our latest #RegionalView, where Regional Economist Alex Marre
      discusses economic conditions at a conferen… https://t.co/kPM1I5vMfE
  - text: Peter Thiel Divides Facebook Internally Over Ad Policy (Radio)
  - text: >-
      $SCANX: Mid cap notable movers of interest -- Kohl's (KSS) advances off of
      recent lows https://t.co/ZM3fmCoLx5
  - text: >-
      US wants China trade deal but won't turn blind eye to Hong Kong, Trump
      national security advisor says https://t.co/dvrewpls4T
  - text: Salarius Pharma files for equity offering
inference: true
model-index:
  - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: zeroshot/twitter-financial-news-sentiment
          type: zeroshot/twitter-financial-news-sentiment
          split: test
        metrics:
          - type: f1
            value: 0.6675041876046901
            name: F1

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model trained on the zeroshot/twitter-financial-news-sentiment dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 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: sentence-transformers/paraphrase-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 3 classes
Training Dataset: zeroshot/twitter-financial-news-sentiment

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
Bullish	'Energy Up As Exxon Cuts CapEx Spending -- Energy Roundup #economy #MarketScreener https://t.co/pZc2wlKsXZ https://t.co/TX2jWQyK1m' "Fed's Mester sees U.S. economy performing well, coronavirus a 'big risk' #economy #MarketScreener… https://t.co/fHOfgB9n6R" 'Merck to raise quarterly dividend by 11% to 61 cents a share'
Bearish	'If your household has $250,000, you’re in the top 5%. https://t.co/VslRVqg5zP' "$DTEGY $DTEGF - Hungary's 4iG calls off purchase of T-Systems unit https://t.co/mY43nNN45s" "Here's what has $ZM stock down over 9% https://t.co/V4ikP0o8cl"
Neutral	"How is a bank's GSIB score calculated https://t.co/m7AIabn6U0" '$GOOG $GOOGL - Google rivals want EU to investigate vacation rentals https://t.co/8nXAOxhcqG' 'EU goes into meeting frenzy ahead of February 20 summit on next seven-year budget'

Evaluation

Metrics

Label	F1
all	0.6675

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("setfit_model_id")
# Run inference
preds = model("Salarius Pharma files for equity offering")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	11.1429	20

Label	Training Sample Count
Bearish	11
Bullish	16
Neutral	15

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (5, 5)
max_steps: -1
sampling_strategy: oversampling
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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0137	1	0.4046	-
0.6849	50	0.1465	-
1.0	73	-	0.2203
1.3699	100	0.002	-
2.0	146	-	0.2563
2.0548	150	0.0006	-
2.7397	200	0.0007	-
3.0	219	-	0.2704
3.4247	250	0.0006	-
4.0	292	-	0.2813
4.1096	300	0.0002	-
4.7945	350	0.0004	-
5.0	365	-	0.2856

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.9.19
SetFit: 1.1.0.dev0
Sentence Transformers: 3.0.1
Transformers: 4.39.0
PyTorch: 2.4.0
Datasets: 2.20.0
Tokenizers: 0.15.2

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}
}