metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
Please Find Enclosed The Press Release Titled 'Energy Transition Among The
Top 3 Priorities For 73 Percent Of Companies: Infosys-HFS Research Study'
- text: >-
Financial Results For The Quarter Ended June 30, 2023, And Declaration Of
Interim Dividend
- text: successfully started
- text: >-
Board Meeting Intimation for Notice Of The Board Meeting Dt. August 03,
2023
- text: >-
Board Meeting Intimation for Intimation Regarding Holding Of Meeting Of
The Board Of Directors: - Un-Audited Financial Results For The Quarter
Ended June 30, 2023
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/all-mpnet-base-v2
model-index:
- name: SetFit with sentence-transformers/all-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.8807339449541285
name: Accuracy
SetFit with sentence-transformers/all-mpnet-base-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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/all-mpnet-base-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 384 tokens
- Number of Classes: 9 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 |
|---|---|
| 2 |
|
| 6 |
|
| 5 |
|
| 3 |
|
| 0 |
|
| 1 |
|
| 7 |
|
| 4 |
|
| 8 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.8807 |
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("krish2505/setfitmkrt")
# Run inference
preds = model("successfully started")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 1 | 15.0265 | 70 |
| Label | Training Sample Count |
|---|---|
| 0 | 142 |
| 1 | 130 |
| 2 | 310 |
| 3 | 61 |
| 4 | 42 |
| 5 | 61 |
| 6 | 191 |
| 7 | 6 |
| 8 | 38 |
Training Hyperparameters
- batch_size: (64, 64)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
|---|---|---|---|
| 0.0016 | 1 | 0.1833 | - |
| 0.0814 | 50 | 0.125 | - |
| 0.1629 | 100 | 0.0628 | - |
| 0.2443 | 150 | 0.0361 | - |
| 0.3257 | 200 | 0.0333 | - |
| 0.4072 | 250 | 0.0116 | - |
| 0.4886 | 300 | 0.0253 | - |
| 0.5700 | 350 | 0.0231 | - |
| 0.6515 | 400 | 0.0037 | - |
| 0.7329 | 450 | 0.0144 | - |
| 0.8143 | 500 | 0.0095 | - |
| 0.8958 | 550 | 0.0161 | - |
| 0.9772 | 600 | 0.0104 | - |
| 1.0586 | 650 | 0.0064 | - |
| 1.1401 | 700 | 0.0018 | - |
| 1.2215 | 750 | 0.0107 | - |
| 1.3029 | 800 | 0.0035 | - |
| 1.3844 | 850 | 0.0056 | - |
| 1.4658 | 900 | 0.0142 | - |
| 1.5472 | 950 | 0.014 | - |
| 1.6287 | 1000 | 0.0109 | - |
| 1.7101 | 1050 | 0.0252 | - |
| 1.7915 | 1100 | 0.0093 | - |
| 1.8730 | 1150 | 0.0048 | - |
| 1.9544 | 1200 | 0.0063 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.36.2
- PyTorch: 2.0.0
- Datasets: 2.16.1
- Tokenizers: 0.15.0
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}
}