metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: سیب زمینی خوب بود ولی ساندویچ اصلا جالب نبود کاملا سفت بود
- text: >-
شبیه شوخی بود بیشتر ، نوشتم ساندویچ بدون قارچ و خودشوم تو فاکترش نوشته ،
اما توش یه دنیا قارچ داشت خیلی هم سرد بود + خیلی هم دیر آورد
- text: >-
همه چیز خوب و خوشمزه بود، جز نان سنگک، مثل نان باگت میتوانستی بینش را باز
کنی و مواد بزاری، اون کله پاچه خوشمزه و این نون بسیار بد به هم نمیان
- text: خوبه ولی کیفیت ظروف مناسب نیست
- text: >-
متاسفانه سفارش بنده را اشتباه آورده بودند.و با یک سفارش دیگر که از شرکت به
صورت تلفنی سفارش گذاشته بودند، اشتباه گرفته بودند.
pipeline_tag: text-classification
inference: true
base_model: m3hrdadfi/albert-zwnj-wnli-mean-tokens
model-index:
- name: SetFit with m3hrdadfi/albert-zwnj-wnli-mean-tokens
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.045454545454545456
name: Accuracy
SetFit with m3hrdadfi/albert-zwnj-wnli-mean-tokens
This is a SetFit model that can be used for Text Classification. This SetFit model uses m3hrdadfi/albert-zwnj-wnli-mean-tokens 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: m3hrdadfi/albert-zwnj-wnli-mean-tokens
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 128 tokens
- Number of Classes: 11 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 |
---|---|
7 |
|
4 |
|
3 |
|
5 |
|
0 |
|
8 |
|
6 |
|
2 |
|
9 |
|
1 |
|
10 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.0455 |
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("keivan/albert-zwnj-wnli-mean-tokens")
# Run inference
preds = model("خوبه ولی کیفیت ظروف مناسب نیست")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 21.3377 | 72 |
Label | Training Sample Count |
---|---|
0 | 7 |
1 | 7 |
2 | 7 |
3 | 7 |
4 | 7 |
5 | 7 |
6 | 7 |
7 | 7 |
8 | 7 |
9 | 7 |
10 | 7 |
Training Hyperparameters
- batch_size: (8, 8)
- num_epochs: (2, 2)
- 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 |
---|---|---|---|
0.0015 | 1 | 0.3989 | - |
0.0742 | 50 | 0.2221 | - |
0.1484 | 100 | 0.2617 | - |
0.2226 | 150 | 0.0514 | - |
0.2967 | 200 | 0.0852 | - |
0.3709 | 250 | 0.0754 | - |
0.4451 | 300 | 0.0353 | - |
0.5193 | 350 | 0.0091 | - |
0.5935 | 400 | 0.0116 | - |
0.6677 | 450 | 0.0213 | - |
0.7418 | 500 | 0.0036 | - |
0.8160 | 550 | 0.0039 | - |
0.8902 | 600 | 0.011 | - |
0.9644 | 650 | 0.0014 | - |
1.0 | 674 | - | 0.0344 |
1.0386 | 700 | 0.0014 | - |
1.1128 | 750 | 0.0028 | - |
1.1869 | 800 | 0.0003 | - |
1.2611 | 850 | 0.0003 | - |
1.3353 | 900 | 0.0002 | - |
1.4095 | 950 | 0.0006 | - |
1.4837 | 1000 | 0.0005 | - |
1.5579 | 1050 | 0.0002 | - |
1.6320 | 1100 | 0.0002 | - |
1.7062 | 1150 | 0.0003 | - |
1.7804 | 1200 | 0.0002 | - |
1.8546 | 1250 | 0.0001 | - |
1.9288 | 1300 | 0.0002 | - |
2.0 | 1348 | - | 0.0319 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.15.0
- 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}
}