metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
Hi Jonathan, I just happened to know that you are gathering information
for our Beta project. While your work is really nice insight and
improvement ideas, I feel the need to talk to you about what more can be
done with your reports I have received comments from our team that more
time is needed to spent on extracting information from your reports. Our
team member are looking for technical information and redundant comments
takes them time to extract the fact and sometime confusing. Another thing
is that can help us is to organize the report in a more clear, concise
way. We are showing the reports to our prospect and even the CEO, so we
need it to be well structured, concise and to the point. I am sure if
youspend more time to organize your report, you will be able to address
this problem. I know you are an enthusiastic contributor and you have done
a good work until now, but we need your reports to be improved for our
project team to success. I am afraid if the situationis notgetting better
we will have to look for someone else towork on this project.Please spend
more effort to organize your next report and I really look forward to your
good news
- text: "Hi Jonathan, I hope you are doing well. Unfortunately I won't be able to talk to you personally but as soon as I am back I would like to spend some time with you. I know you are working on Beta project and your involvement is highly appreciated\_, you even identified improvements the team didn't identify, that's great! This Beta project is key for the company, we need to success all together. In that respect, key priorities are to build concise reports and with strong business writing. Terry has been within the company for 5 years and is the best one to be consulted to upskill in these areas. Could you please liaise with him and get more quick wins from him. It will be very impactful in your career. We will discuss once I'm back about this sharing experience. I'm sure you will find a lot of benefits. Regards William"
- text: >-
Hi Jonathan, I am glad to hear that you are enjoying your job, traveling
and learning more about the Beta ray technology. I wanted to share some
feedback with you that I received. I want to help you be able to advance
in your career and I feel that this feedback will be helpful. I am excited
that you are will to share your perspectives on the findings, however if
you could focus on the data portion first, and highlight the main points,
that would be really beneficial to your audience. By being more concise it
will allow the potential customers and then CEO to focus on the facts of
the report, which will allow them to make a decision for themselves. I
understand that this is probably a newer to writing the reports, and I
don't think that anyone has shown you an example of how the reports are
usually written, so I have sent you some examples for you to review. I
think that you are doing a good job learning and with this little tweak in
the report writing you will be able to advance in your career. In order to
help you, if you don't mind, I would like to review the report before you
submit it and then we can work together to ensure it will be a great
report. I understand that you really enjoy providing your perspectives on
the technology and recommendations on how it can be used, so we will find
a spot for that in the report as well, but perhaps in a different section.
Thank you so much for your time today and I look forward to working with
you.
- text: >-
Hi Jonathan. I have been away a long time and unable to have regular
discussions with you. As your manager, I feel responsible for your
performance and would love to you you grow and perform better. I
understand that you are travelling and gaining so much information that it
can be overwhelming. But our role is to present only the most relevant and
useful information in our report to the Senior management and clients. I
have received feedback that they are facing some trouble with the reports
and would like some changes. Let us focus on our project specifications
and only present the required details. Your detailed insights may be
presented at a later stage or as a separate report for evaluation. You may
take up a course or training on the subject and I am also there if you
need any help. If you are looking forward to a career growth next year, we
need this to be a successful assignment.
- text: >-
Hi Jonathan, and I hope your travels are going well. As soon as you get a
chance, I would like to catch up on the reports you are creating for the
Beta projects. Your contributions have been fantastic, but we need to
limit the commentary and make them more concise. I would love to get your
perspective and show you an example as well. Our goal is to continue to
make you better at what you do and to deliver an excellent customer
experience. Looking forward to tackling this together and to your
dedication to being great at what you do. Safe travels and I look forward
to your call.
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: 0.5909090909090909
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 |
|---|---|
| 1 |
|
| 0 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.5909 |
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("sijan1/empathy_model2")
# Run inference
preds = model("Hi Jonathan, and I hope your travels are going well. As soon as you get a chance, I would like to catch up on the reports you are creating for the Beta projects. Your contributions have been fantastic, but we need to limit the commentary and make them more concise. I would love to get your perspective and show you an example as well. Our goal is to continue to make you better at what you do and to deliver an excellent customer experience. Looking forward to tackling this together and to your dedication to being great at what you do. Safe travels and I look forward to your call.")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 129 | 199.5 | 308 |
| Label | Training Sample Count |
|---|---|
| 0 | 4 |
| 1 | 4 |
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 |
|---|---|---|---|
| 0.05 | 1 | 0.238 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.5.0
- Transformers: 4.37.2
- PyTorch: 2.1.0+cu121
- 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}
}