metadata

base_model: BAAI/bge-base-en-v1.5
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      Reasoning:

      The provided answer correctly indicates that the percentage in the
      response status column shows "the total amount of successful completion of
      response actions." This is well-supported by the document, which states,
      "the status of response actions for the different steps in the...
      percentage indicates the total amount of successful completion of response
      actions." Therefore, the answer effectively addresses the specific
      question, maintains relevance, is concise, and uses the correct key/value
      terms from the document.


      Evaluation:
  - text: >-
      Reasoning:

      The document does not explicitly state the purpose of Endpoint controls,
      but it provides instructions on how to enable and configure them. The
      answer given is technically correct because the document does not directly
      address the purpose of Endpoint controls. However, by reviewing the
      instructions provided, one can infer that the purpose involves managing
      device control, firewall control, and disk encryption visibility, all of
      which are related to enhancing endpoint security. 


      While the provided answer states that the information needed isn't
      covered, this can be considered somewhat true, but it does not make any
      inference from the given details.


      Final result: Methodologically, it aligns as'' based on strict criteria.

      Evaluation:
  - text: >-
      Reasoning:

      The provided document clearly outlines the purpose of the <ORGANIZATION>
      XDR On-Site Collector Agent: it is installed to collect logs from
      platforms and securely forward them to <ORGANIZATION> XDR. The answer
      given aligns accurately with the document's description, addressing the
      specific question without deviating into unrelated topics. The response
      isalso concise and to the point.


      Evaluation:
  - text: >-
      Reasoning:

      The document specifies that in the "Email Notifications section," setting
      the "<ORGANIZATION_2> notifications On" will ensure that users with the
      System Admin role receive email notifications about stale or archived
      sensors. The answer provided states that the purpose of the checkbox is to
      enable or disable email notifications for users, which accurately reflects
      the information given in the document. The answer is supported by the
      document, directly addresses the question, and is concise.


      Evaluation:
  - text: >-
      Reasoning:

      The provided document contains specific URLs for images corresponding to
      the queries. The URL for the image associated with the second query is
      given as `..\/..\/_images\/hunting_http://miller.co`. However, the
      provided answer `/..\/..\/_images\/hunting_http://www.flores.net/` does
      not match this information and provides an incorrect URL that is not
      mentioned in the document. Therefore, the answer fails to meet the
      relevant criteria, is not grounded in the context of the document, and
      lacks conciseness by not directly referencing the correct URL.


      Final evaluation: 

      Evaluation:
inference: true
model-index:
  - name: SetFit with BAAI/bge-base-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.6619718309859155
            name: Accuracy

SetFit with BAAI/bge-base-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-base-en-v1.5 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: BAAI/bge-base-en-v1.5
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

Label	Examples
1	'Reasoning:\nThe answer states that a dime holds a monetary value of 10 cents, which is one-tenth of a dollar. This is confirmed by the document, which specifies that a dime is indeed one-tenth of a dollar and worth 10 cents. The answer is directly related to the question, well-supported by the provided document, and is concise and to the point without any unnecessary information.\n\nEvaluation:' 'Reasoning:\nThe document clearly mentions "Set the investigation status" as one of the tasks that can be performed. Therefore, the answer "Yes" is well-supported by the provided document. The answer is concise, directly related to the question, and does not provide unnecessary information. All the criteria such as context grounding, relevance, and conciseness are met.\n\nEvaluation:' 'Reasoning:\nThe answer directly addresses the question by listing the benefits the author has experienced from their regular yoga practice. These benefits include unapologetic "me" time, improved health, self-growth, increased patience, the ability to be still, acceptance of daily changes, the realization that happiness is their responsibility, a deeper appreciation for their body, the understanding that yoga exists off the mat, and the importance of being open. Each of these points is explicitly mentioned in the provided document, making the answer well-supported and contextually accurate. The answer is concise and relevant, sticking closely to the specifics asked for in the question.\n\nFinal Evaluation:'
0	'Reasoning:\nThe answer is strongly grounded in the provided document, addressing the common challenge of losing the last 10 pounds and offering strategies directly related to the information in the text. It mentions reducing salt intake, cutting out processed foods and alcohol, drinking more water, increasing exercise intensity, engaging in interval training, and ensuring adequate sleep. These points are all covered in the document. The answer remains focused on the question without deviating into unrelated topics and is concise, providing practical tips in a clear and straightforward manner.\n\nFinal Evaluation:' 'Reasoning:\nThe correct answer should provide the image URL specifically associated with step 5 in the document. According to the document, the image URL for step 5 is `..\\/..\\/_images\\/bal_http://osborn-mendoza.info/`. The provided answer, `..\\/..\\/_images\\/bal_https://elliott.biz/`, does not match this URL.\n\nFinal evaluation: \nEvaluation:' "Reasoning:\nThe provided answer accurately captures the challenges Amy Bloom faces when starting a significant writing project, as detailed in the document. Notably, it mentions the difficulty of getting started, the need to clear mental space, and to recalibrate her daily life, which are all points grounded in the text. The answer also covers her becoming less involved in everyday life and spending less time on domestic concerns, which aligns well with the provided passage. However, the part about traveling to a remote island with no internet access is not mentioned in the document and appears to be fabricated, which detracts from the answer's context grounding.\n\nFinal Result:"

'Reasoning:\nThe answer states that a dime holds a monetary value of 10 cents, which is one-tenth of a dollar. This is confirmed by the document, which specifies that a dime is indeed one-tenth of a dollar and worth 10 cents. The answer is directly related to the question, well-supported by the provided document, and is concise and to the point without any unnecessary information.\n\nEvaluation:'
'Reasoning:\nThe document clearly mentions "Set the investigation status" as one of the tasks that can be performed. Therefore, the answer "Yes" is well-supported by the provided document. The answer is concise, directly related to the question, and does not provide unnecessary information. All the criteria such as context grounding, relevance, and conciseness are met.\n\nEvaluation:'
'Reasoning:\nThe answer directly addresses the question by listing the benefits the author has experienced from their regular yoga practice. These benefits include unapologetic "me" time, improved health, self-growth, increased patience, the ability to be still, acceptance of daily changes, the realization that happiness is their responsibility, a deeper appreciation for their body, the understanding that yoga exists off the mat, and the importance of being open. Each of these points is explicitly mentioned in the provided document, making the answer well-supported and contextually accurate. The answer is concise and relevant, sticking closely to the specifics asked for in the question.\n\nFinal Evaluation:'

'Reasoning:\nThe answer is strongly grounded in the provided document, addressing the common challenge of losing the last 10 pounds and offering strategies directly related to the information in the text. It mentions reducing salt intake, cutting out processed foods and alcohol, drinking more water, increasing exercise intensity, engaging in interval training, and ensuring adequate sleep. These points are all covered in the document. The answer remains focused on the question without deviating into unrelated topics and is concise, providing practical tips in a clear and straightforward manner.\n\nFinal Evaluation:'
'Reasoning:\nThe correct answer should provide the image URL specifically associated with step 5 in the document. According to the document, the image URL for step 5 is ..\\/..\\/_images\\/bal_http://osborn-mendoza.info/. The provided answer, ..\\/..\\/_images\\/bal_https://elliott.biz/, does not match this URL.\n\nFinal evaluation: \nEvaluation:'
"Reasoning:\nThe provided answer accurately captures the challenges Amy Bloom faces when starting a significant writing project, as detailed in the document. Notably, it mentions the difficulty of getting started, the need to clear mental space, and to recalibrate her daily life, which are all points grounded in the text. The answer also covers her becoming less involved in everyday life and spending less time on domestic concerns, which aligns well with the provided passage. However, the part about traveling to a remote island with no internet access is not mentioned in the document and appears to be fabricated, which detracts from the answer's context grounding.\n\nFinal Result:"

Evaluation

Metrics

Label	Accuracy
all	0.6620

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("Netta1994/setfit_baai_cybereason_gpt-4o_improved-cot-instructions_chat_few_shot_generated_remov")
# Run inference
preds = model("Reasoning:
The provided document clearly outlines the purpose of the <ORGANIZATION> XDR On-Site Collector Agent: it is installed to collect logs from platforms and securely forward them to <ORGANIZATION> XDR. The answer given aligns accurately with the document's description, addressing the specific question without deviating into unrelated topics. The response isalso concise and to the point.

Evaluation:")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	33	75.9366	176

Label	Training Sample Count
0	129
1	139

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
l2_weight: 0.01
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0015	1	0.2012	-
0.0746	50	0.2574	-
0.1493	100	0.252	-
0.2239	150	0.2507	-
0.2985	200	0.2204	-
0.3731	250	0.1529	-
0.4478	300	0.0581	-
0.5224	350	0.0298	-
0.5970	400	0.0209	-
0.6716	450	0.0075	-
0.7463	500	0.0038	-
0.8209	550	0.0032	-
0.8955	600	0.003	-
0.9701	650	0.0027	-

Framework Versions

Python: 3.10.14
SetFit: 1.1.0
Sentence Transformers: 3.1.1
Transformers: 4.44.0
PyTorch: 2.4.0+cu121
Datasets: 3.0.0
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}
}