metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
State and federal lawmakers are promising to improve conditions for
hundreds of foreign fishermen working in Hawaii's commercial fleet, and at
least one company has already stopped buying fish from the boats following
an Associated Press investigation that found the men have been confined to
vessels for years without basic labor protections.Whole Foods halted
buying seafood caught by foreign crew until it's clear the men are treated
fairly. On Sunday, the Hawaii Seafood Council said that starting Oct. 1,
the Honolulu Fish Auction will sell fish only from boats that have adopted
a new, standardized contract aimed at assuring no forced labor exists on
board.The AP report found commercial fishing boats in Honolulu were crewed
by men from impoverished Southeast Asia and Pacific Island nations who
catch prized swordfish, ahi tuna and other seafood sold at markets and
upscale restaurants across the country. A legal loophole allows them to
work on the American-owned, American-flagged boats without visas as long
as they don't set foot on shore. The system is facilitated by the U.S.
Coast Guard and Customs and Border Protection. While many men appreciate
the jobs, which pay better than they could get back home, the report
revealed instances of human trafficking, tuberculosis and food shortages.
It also found some fishermen being forced to defecate
- text: "\_Trinidad and Tobago is a destination, transit, and possible source country for adults and children subjected to sex trafficking and forced labor Women and girls from the Dominican Republic, Guyana, Venezuela, and Colombia are subjected to sex trafficking in brothels and clubs, with young women from Venezuela especially vulnerable. Economic migrants from the Caribbean region, especially Guyana, and from Asia are vulnerable to forced labor Victims have been subjected to forced labor in domestic service and the retail sector Immigration officials note an increase in international criminal organizations' involvement in trafficking, and NGOs report young boys are coerced to sell drugs and guns. In a break with common practice, some traffickers have recently allowed victims to keep their passports, removing a common indicator of human trafficking in an attempt to avoid detection. Many other traffickers continue to confiscate victims' passports and travel documents. Economic migrants who lack legal status may be exposed to various forms of exploitation and abuse indicative of trafficking. Trinidad and Tobago experiences a steady flow of vessels transiting its territorial waters, some of which may be engaged in illicit and illegal activities, including forced labor in the fishing industry. Complicity by police and immigration officials in trafficking crimes impeded anti-trafficking efforts. Law enforcement and civil society reported"
- text: >-
icked onto fishing boats. In early 2013, an organization that assists
victims in Cambodia assessed this form of trafficking was rising.
Cambodian and Burmese workers are increasingly unwilling to work in the
Thai fishing industry due to dangerous work conditions and isolation,
which makes them more vulnerable to exploitation; the Government of
Thailand announced plans during the year to import Bangladeshi workers to
ill the labor shortage this has caused. During the year, therewere reports
that some Rohingya asylum seekers from Burma were smuggled into Thailand
en route to Malaysia and ultimately sold into forced labor, allegedly with
the assistance of Thai civilian and military officials.Observers noted
that traffickers (including labor brokers) who bring foreign victims into
Thailand generally work as individuals or in unorganized groups, while
those who exploit Thai victims abroad tend to be more organized. Labor
brokers, largely unregulated, serve as intermediaries between jobseekers
and employers; some facilitate or engage in human trafficking. Brokers are
reportedly of both Thai and foreign origin and work in networks,
collaborating with employers and attimes with corrupt law enforcement
officials. Foreign migrants, members of ethnic minorities, and stateless
persons in Thailand are at the greatest risk of being trafficked, and they
experience the withholding of travel documents
- text: ' in their own villages by debt bondage or born ito slavery, work in construction, textiles, brick-making, mines, fish and prawn processing and hospitality.Russia490,000 - 540,000Migrant workers endure extortion and physical abuse; anecdotal evidence suggests that forced labour camps still operate in Siberia.China2,800,000 - 3,100,000Severe forced labour in brick kilns in the north; forced labour in modern industries including fashion and computer supply chains.Myanmar360,000 - 400,000Slavery includes reports of deceptive recruitment of women for sale as brides in China, forced labour of adults on plantations and in industry and forced labour of children in tea shops, home industries and as beggars.Thailand450,000 - 500,000An explosion in global demand for seafood has led to an increased need for cheap migrant labour, including on fishing boats. High numbers of children are exploited, particulary those from ethnic minorities and hill tribes.SOURCE: THE GLOBAL SLAVERY INDEX 2013'
- text: >-
The number of Cambodians recently found in Indonesia after being
trafficked onto Thai fishing vessels has risen to 230, the Ministry of
Foreign Affairs said in a press statement released yesterday. The ministry
confirmed that, following an investigation by Indonesian authorities along
with Cambodian Embassy personnel, an additional 31 fishermen were rescued
from Ambon Island over the last week, adding to the 199 discovered last
Friday. The men were reportedly trafficked to work on the Thai vessels for
years before Indonesian authorities managed to rescue them.Ministry
spokesman Koy Kuong said Cambodian officials visited the island from May
30 to June 3 to check on the men's conditions, adding that the owner of
the Thai fishing boats have paid the workers their salary and have agreed
to pay for a charter flight from Ambon to Phnom Penh.They have agreed in
principle, and now they are processing the procedure to ensure that these
people to return sometime this month, he said.International Organisation
for Migration project manager Paul Dillon said IOM staff had joined a
small mission from the Ministry of Fisheries and Oceans [Thursday] at the
Indonesian government's request on a fact-finding mission
.â(EURO)°.â(EURO)°. to identify possible
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: sentence-transformers/paraphrase-mpnet-base-v2
model-index:
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 1
name: Accuracy
SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a SetFit model 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: 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 |
|
0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 1.0 |
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("JoshELambert/forced-labor")
# Run inference
preds = model(" in their own villages by debt bondage or born ito slavery, work in construction, textiles, brick-making, mines, fish and prawn processing and hospitality.Russia490,000 - 540,000Migrant workers endure extortion and physical abuse; anecdotal evidence suggests that forced labour camps still operate in Siberia.China2,800,000 - 3,100,000Severe forced labour in brick kilns in the north; forced labour in modern industries including fashion and computer supply chains.Myanmar360,000 - 400,000Slavery includes reports of deceptive recruitment of women for sale as brides in China, forced labour of adults on plantations and in industry and forced labour of children in tea shops, home industries and as beggars.Thailand450,000 - 500,000An explosion in global demand for seafood has led to an increased need for cheap migrant labour, including on fishing boats. High numbers of children are exploited, particulary those from ethnic minorities and hill tribes.SOURCE: THE GLOBAL SLAVERY INDEX 2013")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 50 | 189.8442 | 221 |
Label | Training Sample Count |
---|---|
0 | 8 |
1 | 69 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (4, 4)
- 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
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0033 | 1 | 0.1808 | - |
0.1629 | 50 | 0.1363 | - |
0.3257 | 100 | 0.0103 | - |
0.4886 | 150 | 0.0019 | - |
0.6515 | 200 | 0.0005 | - |
0.8143 | 250 | 0.0001 | - |
0.9772 | 300 | 0.0 | - |
1.0 | 307 | - | 0.0407 |
1.1401 | 350 | 0.0001 | - |
1.3029 | 400 | 0.0 | - |
1.4658 | 450 | 0.0 | - |
1.6287 | 500 | 0.0 | - |
1.7915 | 550 | 0.0 | - |
1.9544 | 600 | 0.0 | - |
2.0 | 614 | - | 0.0272 |
2.1173 | 650 | 0.0 | - |
2.2801 | 700 | 0.0 | - |
2.4430 | 750 | 0.0 | - |
2.6059 | 800 | 0.0 | - |
2.7687 | 850 | 0.0 | - |
2.9316 | 900 | 0.0 | - |
3.0 | 921 | - | 0.0238 |
3.0945 | 950 | 0.0 | - |
3.2573 | 1000 | 0.0 | - |
3.4202 | 1050 | 0.0 | - |
3.5831 | 1100 | 0.0 | - |
3.7459 | 1150 | 0.0 | - |
3.9088 | 1200 | 0.0 | - |
4.0 | 1228 | - | 0.0227 |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.42.2
- PyTorch: 2.5.1+cu121
- Datasets: 3.2.0
- Tokenizers: 0.19.1
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}
}