SOUMYADEEPSAR/Setfit_designed_sample_random_forest_head

SetFit

This is a SetFit model that can be used for Text Classification. A RandomForestClassifier 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 Type: SetFit
• Classification head: a RandomForestClassifier instance
• Maximum Sequence Length: 384 tokens
• Number of Classes: 2 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
1	'Gone are the days when they led the world in recession-busting' 'Who so mean that he will not himself be taxed, who so mindful of wealth that he will not favor increasing the popular taxes, in aid of these defective children?' 'That state has sixty-two counties and sixty cities … In addition there are 932 towns, 507 villages, and, at the last count, 9,600 school districts … Just try to render efficient service … amid the diffused identities and inevitable jealousies of, roughly, 11,000 independent administrative officers or boards!'
0	'Is this a warning of what’s to come?' 'This unique set of circumstances has brought PCL back into focus as the safe haven of choice for global players seeking somewhere to stash their cash.' 'Socialists believe that, if everyone cannot have something, no one shall.'

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("SOUMYADEEPSAR/Setfit_designed_sample_random_forest_head")
# Run inference
preds = model("What could possibly go wrong?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	36.5327	97

Label	Training Sample Count
0	100
1	114

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• 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
0.0003	1	0.3958	-
0.0172	50	0.343	-
0.0345	100	0.2775	-
0.0517	150	0.2861	-
0.0689	200	0.1937	-
0.0861	250	0.0891	-
0.1034	300	0.0089	-
0.1206	350	0.0179	-
0.1378	400	0.0002	-
0.1551	450	0.0004	-
0.1723	500	0.0002	-
0.1895	550	0.0001	-
0.2068	600	0.0001	-
0.2240	650	0.0002	-
0.2412	700	0.0001	-
0.2584	750	0.0001	-
0.2757	800	0.0001	-
0.2929	850	0.0001	-
0.3101	900	0.0001	-
0.3274	950	0.0002	-
0.3446	1000	0.0	-
0.3618	1050	0.0001	-
0.3790	1100	0.0001	-
0.3963	1150	0.0001	-
0.4135	1200	0.0001	-
0.4307	1250	0.0001	-
0.4480	1300	0.0001	-
0.4652	1350	0.0	-
0.4824	1400	0.0	-
0.4997	1450	0.0	-
0.5169	1500	0.0	-
0.5341	1550	0.0001	-
0.5513	1600	0.0	-
0.5686	1650	0.0	-
0.5858	1700	0.0	-
0.6030	1750	0.0	-
0.6203	1800	0.0	-
0.6375	1850	0.0	-
0.6547	1900	0.0	-
0.6720	1950	0.0	-
0.6892	2000	0.0	-
0.7064	2050	0.0	-
0.7236	2100	0.0	-
0.7409	2150	0.0	-
0.7581	2200	0.0	-
0.7753	2250	0.0	-
0.7926	2300	0.0001	-
0.8098	2350	0.0001	-
0.8270	2400	0.0	-
0.8442	2450	0.0001	-
0.8615	2500	0.0	-
0.8787	2550	0.0	-
0.8959	2600	0.0	-
0.9132	2650	0.0	-
0.9304	2700	0.0	-
0.9476	2750	0.0	-
0.9649	2800	0.0	-
0.9821	2850	0.0	-
0.9993	2900	0.0	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.39.0
• PyTorch: 2.3.0+cu121
• 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}
}