dim1_setfit_model / README.md

Zlovoblachko

Push model using huggingface_hub.

f318b1f verified 7 months ago

preview code

raw

history blame contribute delete

14.4 kB

metadata

tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      Thesis: In my opinion, watching sports on TV is a good opportunity to get
      relax. There are many reasons why some people like to watch sport games on
      TV. Last argument: None Target sentence: Where is the truth?
  - text: >-
      Thesis: As for me, I suppose that watching sports via TV won't help you
      become a professional at sport. Moreover, sport events are not very
      interesting to be seen through television channels. Last argument:
      Besides, it's much more attractive to visit the play in the real life than
      to watch it at home for many reasons. Target sentence: If you watch the
      sport programme, you can see only those things that the operator wants to
      record.
  - text: >-
      Thesis: Today there are people who belived that watching any sport is a
      useless time spent. I complitely disagree with this opinion. Last
      argument: Watching any sort games or individual competition is wonderfull
      way to spend your free time, by this hobby you can have a lot of profits.
      Target sentence: Watching any sort games or individual competition is
      wonderfull way to spend your free time, by this hobby you can have a lot
      of profits.
  - text: >-
      Thesis: As for me, I suppose that watching sports via TV won't help you
      become a professional at sport. Moreover, sport events are not very
      interesting to be seen through television channels. Last argument:
      Besides, it's much more attractive to visit the play in the real life than
      to watch it at home for many reasons. Target sentence: Besides, it's much
      more attractive to visit the play in the real life than to watch it at
      home for many reasons.
  - text: >-
      Thesis: Some people consider that it is a waste of time, bit I desagree
      with this statment and try to refute it. Last argument: If looks on this
      statement otherwise, it is importnat to say that watching sport events is
      a usual hobby such as cooking, reading books and others. Target sentence:
      People who work in public catering like cooking and it is their hobby
      maybe.
metrics:
  - accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
datasets:
  - Zlovoblachko/DeepSeek_dim1
base_model: BAAI/bge-small-en-v1.5
model-index:
  - name: SetFit with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Zlovoblachko/DeepSeek_dim1
          type: Zlovoblachko/DeepSeek_dim1
          split: test
        metrics:
          - type: accuracy
            value: 0.8740740740740741
            name: Accuracy

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

This is a SetFit model trained on the Zlovoblachko/DeepSeek_dim1 dataset that can be used for Text Classification. This SetFit model uses BAAI/bge-small-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-small-en-v1.5
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 2 classes
Training Dataset: Zlovoblachko/DeepSeek_dim1

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
L	'Thesis: in my opinion it is uself and fun to do pysical exercise and my activity every day. I disagre wits his opinion because these people do not understand that sport should keep fit and mind. Last argument: Secondly the sport is very fun. Target sentence: However some people prefer to watch sports show on tv.' 'Thesis: I personally disadree with this opinion because there are many reasons why watching sports can be useful for people. Last argument: However, I can understend people who agree with first point of view. Target sentence: On the other hand, sometimes it is very difficult to control the time which they lose for that.' "Thesis: None Last argument: People opposing this position may say that sport is not an intellectual activity, so it is not worth spending time at all. Target sentence: They think that watching sport is not developing people's mind, so it has no sense to watch such things."
H	'Thesis: I think, that watching sports really gives a lot of fun. Last argument: The second point is that sports fans are fond of their teams ond sports favoritres. Target sentence: Sports stimulates them to travel (like UFC or Olympic games), to collect merch, to have new datings.' 'Thesis: So, can watching sport be called a waste of time. To my mind, observing a sports game is a fascinating pastime. However, in my opinion they are mistaken. Last argument: Even some hidden talents can be discovered. Target sentence: Although, it is obvious that we should not spend much time in front of the TV, some people believe that watching sports can make a person obese.' 'Thesis: Some people think that spending free time watching sport on TV is just killing precious time. However, my personal opinion is that this activity is useful. Last argument: Also, it can be a good practice if you play some sport Target sentence: because while watching game you can learn some tricks of this game and then apply them in life.'

Label

Examples

'Thesis: in my opinion it is uself and fun to do pysical exercise and my activity every day. I disagre wits his opinion because these people do not understand that sport should keep fit and mind. Last argument: Secondly the sport is very fun. Target sentence: However some people prefer to watch sports show on tv.'
'Thesis: I personally disadree with this opinion because there are many reasons why watching sports can be useful for people. Last argument: However, I can understend people who agree with first point of view. Target sentence: On the other hand, sometimes it is very difficult to control the time which they lose for that.'
"Thesis: None Last argument: People opposing this position may say that sport is not an intellectual activity, so it is not worth spending time at all. Target sentence: They think that watching sport is not developing people's mind, so it has no sense to watch such things."

'Thesis: I think, that watching sports really gives a lot of fun. Last argument: The second point is that sports fans are fond of their teams ond sports favoritres. Target sentence: Sports stimulates them to travel (like UFC or Olympic games), to collect merch, to have new datings.'
'Thesis: So, can watching sport be called a waste of time. To my mind, observing a sports game is a fascinating pastime. However, in my opinion they are mistaken. Last argument: Even some hidden talents can be discovered. Target sentence: Although, it is obvious that we should not spend much time in front of the TV, some people believe that watching sports can make a person obese.'
'Thesis: Some people think that spending free time watching sport on TV is just killing precious time. However, my personal opinion is that this activity is useful. Last argument: Also, it can be a good practice if you play some sport Target sentence: because while watching game you can learn some tricks of this game and then apply them in life.'

Evaluation

Metrics

Label	Accuracy
all	0.8741

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("Zlovoblachko/dim1_setfit_model")
# Run inference
preds = model("Thesis: In my opinion, watching sports on TV is a good opportunity to get relax. There are many reasons why some people like to watch sport games on TV. Last argument: None Target sentence: Where is the truth?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	13	62.7806	140

Label	Training Sample Count
L	540
H	540

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
body_learning_rate: (2e-05, 1e-05)
head_learning_rate: 0.01
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
0.0000	1	0.2674	-
0.0014	50	0.3254	-
0.0027	100	0.3135	0.3191
0.0041	150	0.2963	-
0.0055	200	0.2799	0.2615
0.0068	250	0.2521	-
0.0082	300	0.2554	0.2495
0.0096	350	0.2518	-
0.0110	400	0.2484	0.2488
0.0123	450	0.2498	-
0.0137	500	0.2456	0.2465
0.0151	550	0.2449	-
0.0164	600	0.2433	0.2435
0.0178	650	0.2416	-
0.0192	700	0.2424	0.2410
0.0205	750	0.2381	-
0.0219	800	0.2302	0.2300
0.0233	850	0.227	-
0.0246	900	0.2222	0.2428
0.0260	950	0.2129	-
0.0274	1000	0.2138	0.2144
0.0288	1050	0.2026	-
0.0301	1100	0.1888	0.2009
0.0315	1150	0.1735	-
0.0329	1200	0.1658	0.2017
0.0342	1250	0.1646	-
0.0356	1300	0.1442	0.1889
0.0370	1350	0.1428	-
0.0383	1400	0.1169	0.1804
0.0397	1450	0.1237	-
0.0411	1500	0.0989	0.1838
0.0424	1550	0.106	-
0.0438	1600	0.102	0.1703
0.0452	1650	0.0823	-
0.0466	1700	0.0822	0.1786
0.0479	1750	0.081	-
0.0493	1800	0.0674	0.1685
0.0507	1850	0.0593	-
0.0520	1900	0.0659	0.1732
0.0534	1950	0.0546	-
0.0548	2000	0.0508	0.1889
0.0561	2050	0.0447	-
0.0575	2100	0.0462	0.1637
0.0589	2150	0.0348	-
0.0602	2200	0.0256	0.2151
0.0616	2250	0.0273	-
0.0630	2300	0.0183	0.2285
0.0644	2350	0.0194	-
0.0657	2400	0.0245	0.2068

Framework Versions

Python: 3.11.13
SetFit: 1.1.3
Sentence Transformers: 4.1.0
Transformers: 4.54.0
PyTorch: 2.6.0+cu124
Datasets: 4.0.0
Tokenizers: 0.21.2

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}
}