metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: |
Deputy Finance Ministers from the Group
of 10 leading western industrialised countries met here to
discuss the world debt crisis, trade imbalances and currency
stability today following last month's Paris monetary accord,
sources close to the talks said.
The officials met at the offices of the International
Monetary Fund (IMF) to discuss broad aspects of world monetary
policy in preparation for the IMF's interim committee meeting
in Washington in April.
The talks were the first high-level international review of
the monetary situation since the accord last month reached by
the U.S., West Germany, France, Britain, Japan and Canada to
stabilise world currency markets at around present levels
following the 40 pct slide in the dollar since mid-1985.
Other countries represented at today's talks were Italy,
which refused to attend last month's meeting on the grounds
that it was being excluded from the real discussions, the
Netherlands, Belgium and Switzerland.
Many of the officials had met earlier today and yesterday
within the framework of the Organisation for Economic
Cooperation and Development (OECD) to review the slow progress
being made in cutting the record 170 billion dlr U.S. Trade
deficit and persuading West Germany and Japan to open their
economies to more foreign imports.
Reuter
- text: |
Oper shr 69 cts vs 83 cts
Oper net 35.9 mln vs 42.4 mln
Revs 798.9 mln vs 659.2 mln
Avg shrs 52.0 mln vs 50.9 mln
Nine mths
Oper shr 2.38 dlrs vs 2.75 dlrs
Oper net 123.3 mln vs 135.6 mln
Revs 2.31 billion vs 1.86 billion
Avg shrs 51.8 mln vs 49.3 mln
NOTE: Net excludes losses from discontinued operations of
nil vs 16.1 mln dlrs in quarter and 227.5 mln dlrs vs 42.7 mln
dlrs in nine mths.
Quarter net includes gains from sale of aircraft of two mln
dlrs vs 6,200,000 dlrs.
Reuter
- text: |
The National Association of Wheat
Growers, NAWG, board of directors is scheduled to meet
Secretary of State George Schultz and Undersecretary of State
Allen Wallis to discuss the Department's current role in farm
trade policy, the association said.
NAWG President Jim Miller said in a statement that the
organization wanted to convey to Secretary Schultz the
importance that exports hold for U.S. agriculture and the
degree to which farmers are dependent upon favorable State
Department trade policies to remain profitable.
"Foreign policy decisions of the U.S. State Department have
in the past severely hampered our efforts to move our product
to overseas markets," he said.
Miller noted Secretary Schultz is scheduled to meet next
month with representatives of the Soviet Union, and the NAWG
"wanted to be certain the secretary was aware of our concerns
regarding the reopening of wheat trade with the Soviet Union."
The annual spring NAWG board of directors meeting is held
in Washington to allow grower-leaders from around the country
to meet with their state congressional delegations and members
of the executive branch.
The purpose is to discuss the current situation for
producing and marketing wheat and help set the legislative and
regulatory agenda for the coming year, the NAWG statement said.
Reuter
- text: |
The Bank of France is likely to cut its
money market intervention rate by up to a quarter point at the
start of next week. This follows a steady decline in the call
money rate over the past 10 days and signals from the Finance
Ministry that the time is ripe for a fall, dealers said.
The call money rate peaked at just above nine pct ahead of
the meeting of finance ministers from the Group of Five
industrial countries and Canada on February 22, which restored
considerable stability to foreign exchanges after several weeks
of turbulence.
The call money rate dropped to around 8-3/8 pct on February
23, the day after the Paris accord, and then edged steadily
down to eight pct on February 27 and 7-3/4 pct on March 3,
where it has now stabilised.
Dealers said the Bank of France intervened to absorb
liquidity to hold the rate at 7-3/4 pct.
While call money has dropped by well over a percentage
point, the Bank of France's money market intervention rate has
remained unchanged since January 2, when it was raised to eight
pct from 7-1/4 pct in a bid to stop a franc slide.
The seven-day repurchase rate has also been unchanged at
8-3/4 since it was raised by a half-point on January 5.
The Bank of France has begun using the seven-day repurchase
rate to set an upper indicator for money market rates, while
using the intervention rate to set the floor.
Sources close to Finance Minister Edouard Balladur said
that he would be happy to see an interest rate cut, and dealers
said any fall in the intervention rate was most likely to come
when the Bank of France buys first category paper next Monday,
although an earlier cut could not be excluded.
A cut in the seven-day repurchase rate could come as early
as tomorrow morning, banking sources said.
They said recent high interest rates have encouraged an
acceleration in foreign funds returning to France, discouraging
the authorities from making a hasty rate cut. But they also
pointed out that money supply is broadly back on target, giving
scope for a small fall in rates.
M-3 money supply, the government's key aggregate, finished
1986 within the government's three to five pct growth target,
rising 4.6 pct compared with seven pct in 1985.
REUTER
- text: |
The French 1986 current account balance
of payments surplus has been revised slightly upwards to 25.8
billion francs from the 25.4 billion franc figure announced
last month, the Finance Ministry said.
This compares with a 1.5 billion deficit in 1985, and while
it is the first surplus since 1979, is substantially lower than
the 50 billion surplus forecast by the previous socialist
government before they lost office in March last year.
Net long-term capital outflows rose sharply to 70.5 billion
francs last year from 8.8 billion in 1985, largely due to a
major program of foreign debt repayment, the ministry said.
In the fourth quarter alone the unadjusted surplus rose to
14.1 billion francs from 6.6 billion the previous quarter, but
the adjusted surplus fell to 7.4 billion from 9.1 billion.
Fourth quarter medium and long-term foreign debt repayments
exceeded new credits by 11 billion francs.
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: 0.785234899328859
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 | 0.7852 |
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_reuters21578_reducedto15")
# Run inference
preds = model("Oper shr 69 cts vs 83 cts
Oper net 35.9 mln vs 42.4 mln
Revs 798.9 mln vs 659.2 mln
Avg shrs 52.0 mln vs 50.9 mln
Nine mths
Oper shr 2.38 dlrs vs 2.75 dlrs
Oper net 123.3 mln vs 135.6 mln
Revs 2.31 billion vs 1.86 billion
Avg shrs 51.8 mln vs 49.3 mln
NOTE: Net excludes losses from discontinued operations of
nil vs 16.1 mln dlrs in quarter and 227.5 mln dlrs vs 42.7 mln
dlrs in nine mths.
Quarter net includes gains from sale of aircraft of two mln
dlrs vs 6,200,000 dlrs.
Reuter
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 1 | 181.1067 | 788 |
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 | 0.4971 | - |
| 0.0667 | 50 | 0.1826 | - |
| 0.1333 | 100 | 0.1223 | - |
| 0.2 | 150 | 0.0699 | - |
| 0.2667 | 200 | 0.0712 | - |
| 0.3333 | 250 | 0.0646 | - |
| 0.4 | 300 | 0.055 | - |
| 0.4667 | 350 | 0.0611 | - |
| 0.5333 | 400 | 0.053 | - |
| 0.6 | 450 | 0.0555 | - |
| 0.6667 | 500 | 0.0475 | - |
| 0.7333 | 550 | 0.0716 | - |
| 0.8 | 600 | 0.0587 | - |
| 0.8667 | 650 | 0.0571 | - |
| 0.9333 | 700 | 0.0436 | - |
| 1.0 | 750 | 0.0505 | - |
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}
}