metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
Dear Jonathan, I am writing to find out how things are going on the Beta
project. I understand that you are enjoying the role and finding new
applications.I have had some feedback from Terry confirming that you are
doing well but there are some improvement points that I would like to
discuss with you. It has been noted that your contributions are providing
real value and they enjoy working with you, however, some of this value is
spoiled by a conversational tone and being a bit verbose. In business
correspondence it is essential that the facts are clear, concise and
distinguishable from opinion, otherwise the message may be lost
(regardless of how good it is).There are a number of significant reports
required in the coming weeks. Please could you ensure that you confirm
with Terry the exact detail and format required for specific reports and
communication. He should be able to provide templates and guidance to
ensure that his requirements are met. I would also recommend that you
undertake a report-writing course, which should help you to ensure that
you convey your great ideas in the best possible way.I am keen to support
you to ensure the success of the project and your professional
development. When I return in 2 weeks I would like to have a conference
call with you and Terry to better understand how we can help you going
forward. Please could you respond to confirm that you have received this
email. Regards, William
- text: >-
Hi Jonathan, Thank you for your message. I am glad about your excitment on
this assignment that is important to us, and I hear your will to develop
into an engenier team leader role which I think is a topic that can be
discuss.In order to take you to that role, it is important to work on of
your development area that concern the way you report your analysis.You
have a great talent to collect data and get new creative ideas, and it is
crucial to make you able to be more experienced in business writing to
make sure that you adress your conclusions in a sharp and concise way,
avoiding too much commentary.I propose you to write down your current
reports keeping those 2 objectives in mind: avoid too much commentary and
focus on the main data that support your conclusions.I suggest you get
inspired from other reports done internally, that will help you understand
better the formalism the report should have.Then, let is discuss together
the outcome of your report, and I would specially would like to know more
about the many application you identify for Beta Technology that may bring
new business opportunity. Just a tip, quantify your comments, always.See
you soon, and we will have the opportunity to take the time to discuss
your development plan based on your capacity to be more straight to the
point in your reports.I am sure you will make a difference. Good luck,
William
- text: >-
Hey Jonathan! I've been in touch with Terry, I'm so glad to hear how much
you are enjoying the Beta Project, I even hear you are hoping that this
experience will further your ambitions toward a Lead Engineer position!
However, I understand there has been some issues with your reports that
Terry has brought up with you, and I wanted to take a few minutes to
discuss them.1) Opinion vs. FactsYour reports contain a lot of insights
about what the data means, and at times finding the specific hard facts
can be difficult.2) Level of DetailYou include every bit of data that you
can into your reports, which can make it difficult to take away the larger
picture.I want to encourage you to take these things away for the
following reasons:1) your reports are reviewed by everyone in upper
management, including the CEO! The opinions you have are great, but when
evaluating documents the CEO just needs to highest level, most important
items. The nitty-gritty would fall to another department2) as you have a
desire to move up and be a Lead Engineer, these kinds of reports will be
more and more common. Keeping your thoughts organized and well documented
is going to become a very important skill to have.For your next report I
would like you to prepare a cover sheet that goes with the report. This
cover sheet should be a single page highlighting only the key facts of the
report. Your own opinions and analysis can be included, but let those who
are interested read it on their own time, the high level facts are key for
the meeting they will be presented in. I would also encourage you to make
sure the rest of the report has clearly defined headings and topics, so it
is easy to find information related to each item. I
- text: >-
Good Afternoon Jonathan, I hope you are well and the travelling is not too
exhausting. I wanted to touch base with you to see how you are enjoying
working with the Beta project team? I have been advised that you are a
great contributor and are identifying some great improvements, so well
done. I understand you are completing a lot of reports and imagine this is
quite time consuming which added to your traveling must be quite
overwhelming. I have reviewed some of your reports and whilst they provide
all the technical information that is required, they are quite lengthy and
i think it would be beneficial for you to have some training on report
structures. This would mean you could spend less time on the reports by
providing only the main facts needed and perhaps take on more
responsibility. When the reports are reviewed by higher management they
need to be able to clearly and quickly identify any issues. Attending some
training would also be great to add to your career profile for the future.
In the meantime perhaps you could review your reports before submitting to
ensure they are clear and consise with only the technical information
needed,Let me know your thoughts. Many thanks again and well done for all
your hard work. Kind regards William
- text: >-
Jonathan, First I want to thank you for your help with the Beta project.
However, it has been brought to my attention that perhaps ABC-5 didn't do
enough to prepare you for the extra work and I would like to discuss some
issues. The nature of these reports requires them to be technical in
nature. Your insights are very valuable and much appreciated but as the
old line goes "please give me just the facts". Given the critical nature
of the information you are providing I can't stress the importance of
concise yet detail factual reports. I would like to review your reports
as a training exercise to help you better meet the team requirements.
Given that there are some major reports coming up in the immediate future,
I would like you to review some training options and then present a report
for review. Again your insights are appreciated but we need to make sure
we are presenting the end-use with only the information they need to make
a sound business decision. I also understand you would like to grow into a
leadership position so I would like to discuss how successfully
implementing these changes would be beneficial in demonstrating an ability
to grow and take on new challenges.
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2
model-index:
- name: SetFit with sentence-transformers/all-MiniLM-L6-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.6153846153846154
name: Accuracy
SetFit with sentence-transformers/all-MiniLM-L6-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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-MiniLM-L6-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 256 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 |
|---|---|
| 0 |
|
| 1 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.6154 |
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("diegofiggie/empathy_task")
# Run inference
preds = model("Jonathan, First I want to thank you for your help with the Beta project. However, it has been brought to my attention that perhaps ABC-5 didn't do enough to prepare you for the extra work and I would like to discuss some issues. The nature of these reports requires them to be technical in nature. Your insights are very valuable and much appreciated but as the old line goes \"please give me just the facts\". Given the critical nature of the information you are providing I can't stress the importance of concise yet detail factual reports. I would like to review your reports as a training exercise to help you better meet the team requirements. Given that there are some major reports coming up in the immediate future, I would like you to review some training options and then present a report for review. Again your insights are appreciated but we need to make sure we are presenting the end-use with only the information they need to make a sound business decision. I also understand you would like to grow into a leadership position so I would like to discuss how successfully implementing these changes would be beneficial in demonstrating an ability to grow and take on new challenges. ")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 114 | 187.5 | 338 |
| Label | Training Sample Count |
|---|---|
| 0 | 2 |
| 1 | 2 |
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 |
|---|---|---|---|
| 0.1 | 1 | 0.1814 | - |
Framework Versions
- Python: 3.10.9
- SetFit: 1.0.3
- Sentence Transformers: 2.4.0
- Transformers: 4.38.1
- PyTorch: 2.2.1+cpu
- Datasets: 2.17.1
- 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}
}