metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: |
Japan told the General Agreement on
Tariffs and Trade that South Korea's five-year import
diversification plan violated the spirit of the world trade
governing body, a Foreign Ministry spokesman said.
The notification came in Japan's answer to a recent GATT
questionnaire on unfair trade practices, the spokesman said.
In the five-year plan, which starts this year, South Korea
aims to reduce its dependency on Japan as a source of imported
goods and to increase imports from the U.S. And Europe.
Japan's move came after several unsuccessful bilateral
negotiations on the plan, the spokesman said. "The notification
does not represent anything resembling a formal complaint, nor
is it intended to pressure South Korea. It is a routine
procedure followed by all other GATT member states."
Reuter
- text: |
Japan cannot bear a further rise of the
yen, Foreign Minister Tadashi Kuranari said.
"A further stronger yen would be a misfortune for Japan and
the Japanese people would not be able to bear such a burden," he
told reporters.
The minister said he wants to tell U.S. Political leaders
of the sacrifices Japan is making to cut its trade surplus.
Kuranari was widely expected to fly to Washington tomorrow
for talks focussing on trade. But departure remains uncertain
because of the continuing parliamentary boycott by opposition
parties protesting plans for a new sales tax.
If the boycott is lifted tomorrow, Kuranari would probably
have to remain in Japan to attend parliamentary discussions on
the government's 1987/88 budget, Japanese officials said.
Kuranari said both the U.S. And Japan should approach the
trade imbalance in a calm, unemotional manner.
But, he added, "If the issue of rice is to be raised...I
would mention the feelings of the Japanese people."
Japanese politicians have said repeatedly the country
cannot bow to U.S. Pressure to liberalize rice imports because
the issue is too sensitive.
REUTER
- text: |
The European Community Commission
confirmed it granted export licences for 59,000 tonnes of
current series white sugar at a maximum export rebate of 45.678
European Currency Units (ECUs) per 100 kilos.
Out of this, traders in West Germany received 34,750
tonnes, in the U.K. 13,000, in Denmark 7,250 tonnes and in
France 4,000 tonnes.
REUTER
- text: |
Chancellor of the Exchequer Nigel
Lawson's Budget speech was described as sound and well balanced
by analysts, if slightly lacking in excitement.
A cut in bank base lending rates is now widely expected
tomorrow, with most forecasts predicting a half-point fall. A
follow-up half-point cut is anticipated next week.
"Worthy but boring would probably sum it up," Peter Fellner,
U.K. Economist at stockbrokers James Capel and Co, said. "It was
a very, very prudent fiscal budget."
Richard Jeffrey of brokers Hoare Govett said it was a
well-balanced budget within the confines of the government's
philosophy of keeping expenditure levels flat.
Most analysts said the Budget was very sound on the fiscal
side, but offered nothing new on monetary policy.
As was widely expected, Lawson split his "fiscal adjustment"
between trimming the 1987/88 PSBR target to 4.0 billion stg
from 7.1 billion and cutting basic rate income tax from 29 to
27 pct.
The target for the narrow measure of money supply, M0, was
kept unchangd at two to six pct, while the target for the broad
Sterling M3 aggregate was dropped.
Both Jeffrey and Fellner said the budget clears the way for
a half-point fall in U.K. Base rates tomorrow, but the
authorities are unlikely to sanction a larger cut immediately.
Many analysts and currency dealers have forecast a full
one-point cut tomorrow.
"The Bank of England will be loathe to take any action which
it will have to reverse later," Jeffrey said, though he added a
further half-point cut was quite possible in the near future.
The main worry from today's speech is the outlook for
inflation, given the signs of relaxed monetary policy contained
in it, Scrimgeour Vickers economist Richard Holt said.
Holt noted the "rather loose" inflation forecast of 4.0 pct
at end-1987, and said the lower interest rates likely to result
from the tough fiscal stance could cause longer term concern.
"A higher PSBR target could be preferable in the long term,"
he said, although lower mortgage interest rates on the back of
falling base rates would have an offsetting impact on
inflation.
The Budget will inspire a lot of short-term confidence but
it was "not a good budget for inflation," he said
Jeffrey said he would have liked Lawson to say more about
the dangers of excessive liquidity build-up but overall was not
too concerned about a revival of inflation.
Fellner noted that the exchange rate was to remain the
"leading edge" of monetary policy, but said the authorities were
likely to be extremely cautious on this front.
He said they were unlikely to hesitate in holding interest
rates steady or even raising them again if sterling showed any
signs of excessive weakness.
Most analysts agreed Lawson had bolstered the credibility
of the Budget by adopting realistic forecasts.
Raising the forecast for the current account deficit from
1.5 to 2.5 billion stg for 1987 would not unsettle the markets,
which are already discounting that amount, Jeffrey said.
that the 4.0 billion stg PSBR target was given credibility by
the favourable outturn for 1986/87, which is now also forecast
to be 4.0 billion stg.
But analysts said the Budget speech did not give any
clear-cut indication about the timing of the general election,
which has to be held before June, 1988.
Some believe it signals a poll this June, noting that the
benefits, such as income tax cuts and the decision not to raise
duties on alcohol and tobacco, become available immediately.
But others said it kept several options open and it was not
possible to deduce too much from it.
James Capel's Fellner noted that by being fiscally prudent,
Lawson had kept open the possibility of an autumn election in
that there would be no "chickens coming home to roost."
Richard Jeffrey, who favours the likelihood of a June
election, said it was important the Chancellor had not gone for
a Budget aimed overtly at buying an election victory.
Nevertheless, he said, it was likely to result in a boost
to the Conservative Party's pre-election popularity.
REUTER
- text: |
Booker Plc <BOKL.L> said 1987 had
started well and the group had the resources to invest in its
growth business both organically and by acquisition.
It was commenting on figures for 1986 which showed pretax
profits rising to 54.6 mln from 46.5 mln previously. Profits
from the U.S. Accounted for 39 pct of the total. The results
were broadly in line with analysts' forecasts and the company's
shares firmed in morning trading to 421p from 413p at Friday's
close.
The group ended the year with a cash surplus higher at 54
mln stg, compared to 26 mln previously, after capital
expenditure which rose to 54 mln from 43 mln.
In a statement, the company said the U.K. Agribusiness
group reported excellent profits growth while health products
profits rose to 6.5 mln from 5.4 mln.
REUTER
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: false
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: 0.916083916083916
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 OneVsRestClassifier 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 OneVsRestClassifier instance
- Maximum Sequence Length: 512 tokens
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.9161 |
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("ardi555/setfit_mpnet_reuters21578_reducedto15")
# Run inference
preds = model("The European Community Commission
confirmed it granted export licences for 59,000 tonnes of
current series white sugar at a maximum export rebate of 45.678
European Currency Units (ECUs) per 100 kilos.
Out of this, traders in West Germany received 34,750
tonnes, in the U.K. 13,000, in Denmark 7,250 tonnes and in
France 4,000 tonnes.
REUTER
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 20 | 204.4467 | 1075 |
Training Hyperparameters
- batch_size: (8, 8)
- 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
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0013 | 1 | 0.2676 | - |
| 0.0667 | 50 | 0.1617 | - |
| 0.1333 | 100 | 0.0869 | - |
| 0.2 | 150 | 0.0583 | - |
| 0.2667 | 200 | 0.0766 | - |
| 0.3333 | 250 | 0.0578 | - |
| 0.4 | 300 | 0.0483 | - |
| 0.4667 | 350 | 0.0374 | - |
| 0.5333 | 400 | 0.0372 | - |
| 0.6 | 450 | 0.039 | - |
| 0.6667 | 500 | 0.0367 | - |
| 0.7333 | 550 | 0.0378 | - |
| 0.8 | 600 | 0.0299 | - |
| 0.8667 | 650 | 0.0317 | - |
| 0.9333 | 700 | 0.0308 | - |
| 1.0 | 750 | 0.0293 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.2.1
- Transformers: 4.42.2
- PyTorch: 2.5.1+cu121
- Datasets: 3.1.0
- 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}
}