metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
datasets:
- hojzas/proj8-lab1
metrics:
- accuracy
widget:
- text: |-
def first_with_given_key(iterable, key=repr):
res = []
keys = set()
for item in iterable:
if key(item) not in keys:
keys.add(key(item))
return res
- text: "def first_with_given_key(iterable, key=repr):\n\tget_key = get_key_l(key)\n\tused_keys = []\n\tfor item in iterable:\n\t\tkey_item = get_key(item)\n\t\t\t\n\t\tif key_item in used_keys:\n\t\t\tcontinue\n\t\t\n\t\ttry:\n\t\t\tused_keys.append(hash(key_item))\n\t\texcept TypeError:\n\t\t\tused_keys.apppend(repr(key_item))\n\t\t\t\n\t\tyield item"
- text: |-
def first_with_given_key(iterable, key=repr):
set_of_keys = set()
key_lambda = _get_lambda(key)
for item in iterable:
key = key_lambda(item)
try:
key_to_set = hash(key)
except TypeError:
key_to_set = repr(key)
if key_to_set in set_of_keys:
continue
set_of_keys.add(key_to_set)
yield item
- text: |-
def first_with_given_key(iterable, key=lambda y: y):
result = list()
func_it = iter(iterable)
while True:
try:
value = next(func_it)
if key(value) not in result:
yield value
result.insert(-1, key(value))
except StopIteration:
break
- text: |-
def first_with_given_key(iterable, key=repr):
used_keys = {}
get_key = return_key(key)
for item in iterable:
item_key = get_key(item)
if item_key in used_keys.keys():
continue
try:
used_keys[hash(item_key)] = repr(item)
except TypeError:
used_keys[repr(item_key)] = repr(item)
yield item
pipeline_tag: text-classification
inference: true
co2_eq_emissions:
emissions: 2.0314927247192536
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
ram_total_size: 251.49161911010742
hours_used: 0.006
hardware_used: 4 x NVIDIA RTX A5000
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: hojzas/proj8-lab1
type: hojzas/proj8-lab1
split: test
metrics:
- type: accuracy
value: 0.9722222222222222
name: Accuracy
SetFit with sentence-transformers/all-mpnet-base-v2
This is a SetFit model trained on the hojzas/proj8-lab1 dataset 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: 2 classes
- Training Dataset: hojzas/proj8-lab1
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 |
|---|---|
| 0 |
|
| 1 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.9722 |
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("hojzas/proj8-lab1")
# Run inference
preds = model("def first_with_given_key(iterable, key=repr):
res = []
keys = set()
for item in iterable:
if key(item) not in keys:
keys.add(key(item))
return res")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 43 | 91.6071 | 125 |
| Label | Training Sample Count |
|---|---|
| 0 | 20 |
| 1 | 8 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- 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 |
|---|---|---|---|
| 0.0143 | 1 | 0.4043 | - |
| 0.7143 | 50 | 0.0022 | - |
Environmental Impact
Carbon emissions were measured using CodeCarbon.
- Carbon Emitted: 0.002 kg of CO2
- Hours Used: 0.006 hours
Training Hardware
- On Cloud: No
- GPU Model: 4 x NVIDIA RTX A5000
- CPU Model: Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
- RAM Size: 251.49 GB
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.36.1
- PyTorch: 2.1.2+cu121
- Datasets: 2.14.7
- Tokenizers: 0.15.1
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}
}