metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: It doesn't depend on hi-teck evangelism.
  - text: >-
      But in the all region we see gender unequal; in 2000 boys have education
      often then girls on 15 millions.
  - text: >-
      There is opinion, that universities should have equal amount of male and
      female students in every subject in society.
  - text: A building's style may say a lot about its history.
  - text: >-
      Manufactured goods by rail is the same amount as by road, Machinery
      transported by road has minimal percent in second chart.
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: 0.592741935483871
            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: 5 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
Copying expression	'What is needed to improve the situation with widespread using of gadjets is definite action should be encouraged and promoted by means of avoiding them.' 'Inside every of us are our passions.' 'The number of 15-59 year old people will increase for 11% but the number of 0-14 will fall and become 37%.'
Synonyms	'But some persons consider that the institutes should accept the equal amount of girls and boys in every faculty.' 'Nowadays problem of ecology and environment is rather acute and many people are alarmed by it.' 'The amount of people over 65 was rising between 1940 and the end of 1970s.'
Tense semantics	'After that the figure uncreases dramatically from 180 billions in 2009 to approximately 279 billions in 2011.' 'On the contrary, in 2014 the UK book market demonstrate minimum income, only 2,6 and 1,8 billion dollars for print book and eBook, correspondely.' 'It is not clear, what it is depends on, but after the higest point in 42% in Japan the percentage get down to 30%.'
Word form transmission	'A lot of people from music and cinema industry lose money due to somebody sends pirate copies to the internet.' 'The deal was worth $2 billions .' 'According to the projections numbers of people in the age of 15-60 years will show a considerable increase in 2050 by 11 per cent, such as people aged 60 and more years by 2,1 percent.'
Transliteration	'According to the statistic a lot of people with some horible diseases can get cvalificate help only in Japan.' "It doesn't depend on hi-teck evangelism." 'GMO technologies are believed to be dangerous.'

Evaluation

Metrics

Label	Accuracy
all	0.5927

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/L1-classifier")
# Run inference
preds = model("It doesn't depend on hi-teck evangelism.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	20.788	54

Label	Training Sample Count
Synonyms	91
Copying expression	55
Tense semantics	57
Word form transmission	32
Transliteration	15

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (15, 15)
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
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0043	1	0.3438	-
0.0342	50	0.2906	-
0.0685	100	0.2761	-
0.1027	150	0.2696	-
0.1370	200	0.2381	-
0.1712	250	0.2542	-
0.2055	300	0.1781	-
0.2397	350	0.2067	-
0.2740	400	0.222	-
0.3082	450	0.2372	-
0.3425	500	0.193	-
0.3767	550	0.2399	-
0.4110	600	0.1712	-
0.4452	650	0.1697	-
0.4795	700	0.1507	-
0.5137	750	0.0947	-
0.5479	800	0.0722	-
0.5822	850	0.0975	-
0.6164	900	0.035	-
0.6507	950	0.0114	-
0.6849	1000	0.0332	-
0.7192	1050	0.0274	-
0.7534	1100	0.0126	-
0.7877	1150	0.0267	-
0.8219	1200	0.0194	-
0.8562	1250	0.0206	-
0.8904	1300	0.0228	-
0.9247	1350	0.0076	-
0.9589	1400	0.0342	-
0.9932	1450	0.0252	-
1.0274	1500	0.0164	-
1.0616	1550	0.0049	-
1.0959	1600	0.0043	-
1.1301	1650	0.0114	-
1.1644	1700	0.03	-
1.1986	1750	0.0026	-
1.2329	1800	0.0012	-
1.2671	1850	0.0073	-
1.3014	1900	0.0146	-
1.3356	1950	0.001	-
1.3699	2000	0.0088	-
1.4041	2050	0.0031	-
1.4384	2100	0.0125	-
1.4726	2150	0.0357	-
1.5068	2200	0.0186	-
1.5411	2250	0.0178	-
1.5753	2300	0.0071	-
1.6096	2350	0.0186	-
1.6438	2400	0.0077	-
1.6781	2450	0.0183	-
1.7123	2500	0.0007	-
1.7466	2550	0.0007	-
1.7808	2600	0.0052	-
1.8151	2650	0.0077	-
1.8493	2700	0.0421	-
1.8836	2750	0.0272	-
1.9178	2800	0.0144	-
1.9521	2850	0.0038	-
1.9863	2900	0.0043	-
2.0205	2950	0.0187	-
2.0548	3000	0.0075	-
2.0890	3050	0.0151	-
2.1233	3100	0.0114	-
2.1575	3150	0.0022	-
2.1918	3200	0.0007	-
2.2260	3250	0.0196	-
2.2603	3300	0.0266	-
2.2945	3350	0.0139	-
2.3288	3400	0.0169	-
2.3630	3450	0.0124	-
2.3973	3500	0.0018	-
2.4315	3550	0.0242	-
2.4658	3600	0.0402	-
2.5	3650	0.0015	-
2.5342	3700	0.0042	-
2.5685	3750	0.0437	-
2.6027	3800	0.006	-
2.6370	3850	0.0005	-
2.6712	3900	0.0118	-
2.7055	3950	0.0166	-
2.7397	4000	0.025	-
2.7740	4050	0.0167	-
2.8082	4100	0.0285	-
2.8425	4150	0.0048	-
2.8767	4200	0.0149	-
2.9110	4250	0.0078	-
2.9452	4300	0.0097	-
2.9795	4350	0.0068	-
3.0137	4400	0.0235	-
3.0479	4450	0.0004	-
3.0822	4500	0.0355	-
3.1164	4550	0.0237	-
3.1507	4600	0.0004	-
3.1849	4650	0.0003	-
3.2192	4700	0.0038	-
3.2534	4750	0.0002	-
3.2877	4800	0.0105	-
3.3219	4850	0.0055	-
3.3562	4900	0.0282	-
3.3904	4950	0.0105	-
3.4247	5000	0.0362	-
3.4589	5050	0.0004	-
3.4932	5100	0.0229	-
3.5274	5150	0.0092	-
3.5616	5200	0.033	-
3.5959	5250	0.0003	-
3.6301	5300	0.0444	-
3.6644	5350	0.0181	-
3.6986	5400	0.0254	-
3.7329	5450	0.0057	-
3.7671	5500	0.0511	-
3.8014	5550	0.0024	-
3.8356	5600	0.0195	-
3.8699	5650	0.0202	-
3.9041	5700	0.0003	-
3.9384	5750	0.0322	-
3.9726	5800	0.0123	-
4.0068	5850	0.0002	-
4.0411	5900	0.0002	-
4.0753	5950	0.008	-
4.1096	6000	0.0053	-
4.1438	6050	0.0003	-
4.1781	6100	0.0213	-
4.2123	6150	0.0046	-
4.2466	6200	0.0331	-
4.2808	6250	0.0078	-
4.3151	6300	0.0042	-
4.3493	6350	0.0234	-
4.3836	6400	0.0043	-
4.4178	6450	0.0253	-
4.4521	6500	0.0303	-
4.4863	6550	0.004	-
4.5205	6600	0.0166	-
4.5548	6650	0.0269	-
4.5890	6700	0.0079	-
4.6233	6750	0.0001	-
4.6575	6800	0.0002	-
4.6918	6850	0.0002	-
4.7260	6900	0.0199	-
4.7603	6950	0.0282	-
4.7945	7000	0.0016	-
4.8288	7050	0.0068	-
4.8630	7100	0.0054	-
4.8973	7150	0.036	-
4.9315	7200	0.0054	-
4.9658	7250	0.0174	-
5.0	7300	0.0001	-
5.0342	7350	0.0123	-
5.0685	7400	0.0218	-
5.1027	7450	0.0162	-
5.1370	7500	0.0181	-
5.1712	7550	0.0001	-
5.2055	7600	0.0201	-
5.2397	7650	0.0232	-
5.2740	7700	0.0003	-
5.3082	7750	0.0002	-
5.3425	7800	0.0094	-
5.3767	7850	0.0151	-
5.4110	7900	0.0099	-
5.4452	7950	0.01	-
5.4795	8000	0.0378	-
5.5137	8050	0.0199	-
5.5479	8100	0.0201	-
5.5822	8150	0.0242	-
5.6164	8200	0.0015	-
5.6507	8250	0.0002	-
5.6849	8300	0.0047	-
5.7192	8350	0.0002	-
5.7534	8400	0.0001	-
5.7877	8450	0.0215	-
5.8219	8500	0.0159	-
5.8562	8550	0.0001	-
5.8904	8600	0.0194	-
5.9247	8650	0.0058	-
5.9589	8700	0.0001	-
5.9932	8750	0.0164	-
6.0274	8800	0.0272	-
6.0616	8850	0.0001	-
6.0959	8900	0.0031	-
6.1301	8950	0.0154	-
6.1644	9000	0.0403	-
6.1986	9050	0.0035	-
6.2329	9100	0.0001	-
6.2671	9150	0.0061	-
6.3014	9200	0.0118	-
6.3356	9250	0.0031	-
6.3699	9300	0.0001	-
6.4041	9350	0.0098	-
6.4384	9400	0.0001	-
6.4726	9450	0.0343	-
6.5068	9500	0.017	-
6.5411	9550	0.0025	-
6.5753	9600	0.0001	-
6.6096	9650	0.0181	-
6.6438	9700	0.0191	-
6.6781	9750	0.0186	-
6.7123	9800	0.0001	-
6.7466	9850	0.0002	-
6.7808	9900	0.0001	-
6.8151	9950	0.0086	-
6.8493	10000	0.0377	-
6.8836	10050	0.0167	-
6.9178	10100	0.0034	-
6.9521	10150	0.0054	-
6.9863	10200	0.0048	-
7.0205	10250	0.0219	-
7.0548	10300	0.0001	-
7.0890	10350	0.0001	-
7.1233	10400	0.0262	-
7.1575	10450	0.0069	-
7.1918	10500	0.0001	-
7.2260	10550	0.0158	-
7.2603	10600	0.0192	-
7.2945	10650	0.0098	-
7.3288	10700	0.0001	-
7.3630	10750	0.0002	-
7.3973	10800	0.0021	-
7.4315	10850	0.0252	-
7.4658	10900	0.0383	-
7.5	10950	0.0001	-
7.5342	11000	0.0001	-
7.5685	11050	0.0491	-
7.6027	11100	0.0076	-
7.6370	11150	0.0089	-
7.6712	11200	0.0162	-
7.7055	11250	0.0163	-
7.7397	11300	0.0188	-
7.7740	11350	0.0141	-
7.8082	11400	0.0277	-
7.8425	11450	0.0001	-
7.8767	11500	0.0001	-
7.9110	11550	0.0055	-
7.9452	11600	0.0029	-
7.9795	11650	0.0001	-
8.0137	11700	0.0186	-
8.0479	11750	0.0037	-
8.0822	11800	0.0205	-
8.1164	11850	0.0217	-
8.1507	11900	0.0036	-
8.1849	11950	0.0039	-
8.2192	12000	0.0001	-
8.2534	12050	0.0055	-
8.2877	12100	0.0027	-
8.3219	12150	0.0029	-
8.3562	12200	0.0279	-
8.3904	12250	0.0139	-
8.4247	12300	0.04	-
8.4589	12350	0.003	-
8.4932	12400	0.0161	-
8.5274	12450	0.0001	-
8.5616	12500	0.035	-
8.5959	12550	0.0021	-
8.6301	12600	0.0355	-
8.6644	12650	0.0139	-
8.6986	12700	0.0183	-
8.7329	12750	0.0041	-
8.7671	12800	0.0354	-
8.8014	12850	0.0	-
8.8356	12900	0.0197	-
8.8699	12950	0.0189	-
8.9041	13000	0.0063	-
8.9384	13050	0.0309	-
8.9726	13100	0.0029	-
9.0068	13150	0.0027	-
9.0411	13200	0.0018	-
9.0753	13250	0.0104	-
9.1096	13300	0.0057	-
9.1438	13350	0.0051	-
9.1781	13400	0.0172	-
9.2123	13450	0.0001	-
9.2466	13500	0.0347	-
9.2808	13550	0.0024	-
9.3151	13600	0.0147	-
9.3493	13650	0.0218	-
9.3836	13700	0.0028	-
9.4178	13750	0.0205	-
9.4521	13800	0.0215	-
9.4863	13850	0.0001	-
9.5205	13900	0.0157	-
9.5548	13950	0.0227	-
9.5890	14000	0.0001	-
9.6233	14050	0.0048	-
9.6575	14100	0.0106	-
9.6918	14150	0.0077	-
9.7260	14200	0.0225	-
9.7603	14250	0.0173	-
9.7945	14300	0.0028	-
9.8288	14350	0.0022	-
9.8630	14400	0.003	-
9.8973	14450	0.0355	-
9.9315	14500	0.0001	-
9.9658	14550	0.0187	-
10.0	14600	0.0001	-
0.0007	1	0.0055	-
0.0342	50	0.0127	-
0.0685	100	0.0206	-
0.1027	150	0.0195	-
0.1370	200	0.0238	-
0.1712	250	0.0029	-
0.2055	300	0.0204	-
0.2397	350	0.0174	-
0.2740	400	0.0001	-
0.3082	450	0.0023	-
0.3425	500	0.0001	-
0.3767	550	0.0254	-
0.4110	600	0.0029	-
0.4452	650	0.0082	-
0.4795	700	0.0411	-
0.5137	750	0.0159	-
0.5479	800	0.0207	-
0.5822	850	0.0173	-
0.6164	900	0.0001	-
0.6507	950	0.0018	-
0.6849	1000	0.0059	-
0.7192	1050	0.0014	-
0.7534	1100	0.0022	-
0.7877	1150	0.0187	-
0.8219	1200	0.0158	-
0.8562	1250	0.0025	-
0.8904	1300	0.0113	-
0.9247	1350	0.0007	-
0.9589	1400	0.004	-
0.9932	1450	0.0216	-
1.0274	1500	0.0213	-
1.0616	1550	0.0044	-
1.0959	1600	0.0025	-
1.1301	1650	0.0154	-
1.1644	1700	0.038	-
1.1986	1750	0.0001	-
1.2329	1800	0.0004	-
1.2671	1850	0.0065	-
1.3014	1900	0.0087	-
1.3356	1950	0.0001	-
1.3699	2000	0.0039	-
1.4041	2050	0.0005	-
1.4384	2100	0.0087	-
1.4726	2150	0.0369	-
1.5068	2200	0.0157	-
1.5411	2250	0.0094	-
1.5753	2300	0.0042	-
1.6096	2350	0.018	-
1.6438	2400	0.014	-
1.6781	2450	0.0161	-
1.7123	2500	0.0011	-
1.7466	2550	0.0001	-
1.7808	2600	0.004	-
1.8151	2650	0.0048	-
1.8493	2700	0.0403	-
1.8836	2750	0.0254	-
1.9178	2800	0.0124	-
1.9521	2850	0.0028	-
1.9863	2900	0.0026	-
2.0205	2950	0.0171	-
2.0548	3000	0.0049	-
2.0890	3050	0.0092	-
2.1233	3100	0.0134	-
2.1575	3150	0.0021	-
2.1918	3200	0.0001	-
2.2260	3250	0.0153	-
2.2603	3300	0.0253	-
2.2945	3350	0.0095	-
2.3288	3400	0.0144	-
2.3630	3450	0.0064	-
2.3973	3500	0.0013	-
2.4315	3550	0.0216	-
2.4658	3600	0.0387	-
2.5	3650	0.0018	-
2.5342	3700	0.0034	-
2.5685	3750	0.0428	-
2.6027	3800	0.0055	-
2.6370	3850	0.0001	-
2.6712	3900	0.0154	-
2.7055	3950	0.0176	-
2.7397	4000	0.0213	-
2.7740	4050	0.016	-
2.8082	4100	0.0293	-
2.8425	4150	0.0034	-
2.8767	4200	0.0119	-
2.9110	4250	0.0061	-
2.9452	4300	0.0068	-
2.9795	4350	0.006	-
3.0137	4400	0.0211	-
3.0479	4450	0.0001	-
3.0822	4500	0.0303	-
3.1164	4550	0.0225	-
3.1507	4600	0.0001	-
3.1849	4650	0.0002	-
3.2192	4700	0.0031	-
3.2534	4750	0.0001	-
3.2877	4800	0.0103	-
3.3219	4850	0.0055	-
3.3562	4900	0.0297	-
3.3904	4950	0.0121	-
3.4247	5000	0.0348	-
3.4589	5050	0.0003	-
3.4932	5100	0.0212	-
3.5274	5150	0.0077	-
3.5616	5200	0.0339	-
3.5959	5250	0.0001	-
3.6301	5300	0.0444	-
3.6644	5350	0.0167	-
3.6986	5400	0.0245	-
3.7329	5450	0.005	-
3.7671	5500	0.047	-
3.8014	5550	0.0021	-
3.8356	5600	0.019	-
3.8699	5650	0.0187	-
3.9041	5700	0.0001	-
3.9384	5750	0.0328	-
3.9726	5800	0.0097	-
4.0068	5850	0.0001	-
4.0411	5900	0.0001	-
4.0753	5950	0.0078	-
4.1096	6000	0.0057	-
4.1438	6050	0.0002	-
4.1781	6100	0.0218	-
4.2123	6150	0.0038	-
4.2466	6200	0.0337	-
4.2808	6250	0.0065	-
4.3151	6300	0.0033	-
4.3493	6350	0.0228	-
4.3836	6400	0.0033	-
4.4178	6450	0.0244	-
4.4521	6500	0.027	-
4.4863	6550	0.0027	-
4.5205	6600	0.0153	-
4.5548	6650	0.0241	-
4.5890	6700	0.0071	-
4.6233	6750	0.0001	-
4.6575	6800	0.0	-
4.6918	6850	0.0001	-
4.7260	6900	0.0203	-
4.7603	6950	0.0273	-
4.7945	7000	0.0017	-
4.8288	7050	0.0062	-
4.8630	7100	0.0043	-
4.8973	7150	0.0346	-
4.9315	7200	0.005	-
4.9658	7250	0.0182	-
5.0	7300	0.0001	-
5.0342	7350	0.0108	-
5.0685	7400	0.0218	-
5.1027	7450	0.0163	-
5.1370	7500	0.0195	-
5.1712	7550	0.0001	-
5.2055	7600	0.0195	-
5.2397	7650	0.0222	-
5.2740	7700	0.0002	-
5.3082	7750	0.0001	-
5.3425	7800	0.0078	-
5.3767	7850	0.0158	-
5.4110	7900	0.0081	-
5.4452	7950	0.0087	-
5.4795	8000	0.0372	-
5.5137	8050	0.019	-
5.5479	8100	0.0188	-
5.5822	8150	0.0238	-
5.6164	8200	0.0018	-
5.6507	8250	0.0001	-
5.6849	8300	0.0046	-
5.7192	8350	0.0001	-
5.7534	8400	0.0001	-
5.7877	8450	0.0216	-
5.8219	8500	0.0164	-
5.8562	8550	0.0	-
5.8904	8600	0.018	-
5.9247	8650	0.0059	-
5.9589	8700	0.0001	-
5.9932	8750	0.0168	-
6.0274	8800	0.0259	-
6.0616	8850	0.0001	-
6.0959	8900	0.0029	-
6.1301	8950	0.0159	-
6.1644	9000	0.041	-
6.1986	9050	0.0035	-
6.2329	9100	0.0001	-
6.2671	9150	0.005	-
6.3014	9200	0.0101	-
6.3356	9250	0.0027	-
6.3699	9300	0.0	-
6.4041	9350	0.0094	-
6.4384	9400	0.0001	-
6.4726	9450	0.0335	-
6.5068	9500	0.0168	-
6.5411	9550	0.0025	-
6.5753	9600	0.0001	-
6.6096	9650	0.0185	-
6.6438	9700	0.0188	-
6.6781	9750	0.0187	-
6.7123	9800	0.0001	-
6.7466	9850	0.0002	-
6.7808	9900	0.0001	-
6.8151	9950	0.0087	-
6.8493	10000	0.0371	-
6.8836	10050	0.0172	-
6.9178	10100	0.0028	-
6.9521	10150	0.0055	-
6.9863	10200	0.0043	-
7.0205	10250	0.0219	-
7.0548	10300	0.0	-
7.0890	10350	0.0001	-
7.1233	10400	0.026	-
7.1575	10450	0.0067	-
7.1918	10500	0.0001	-
7.2260	10550	0.0162	-
7.2603	10600	0.019	-
7.2945	10650	0.0093	-
7.3288	10700	0.0001	-
7.3630	10750	0.0002	-
7.3973	10800	0.002	-
7.4315	10850	0.0247	-
7.4658	10900	0.0394	-
7.5	10950	0.0001	-
7.5342	11000	0.0001	-
7.5685	11050	0.0503	-
7.6027	11100	0.0066	-
7.6370	11150	0.0087	-
7.6712	11200	0.0165	-
7.7055	11250	0.0164	-
7.7397	11300	0.019	-
7.7740	11350	0.0143	-
7.8082	11400	0.0282	-
7.8425	11450	0.0001	-
7.8767	11500	0.0	-
7.9110	11550	0.0049	-
7.9452	11600	0.0028	-
7.9795	11650	0.0001	-
8.0137	11700	0.0184	-
8.0479	11750	0.0038	-
8.0822	11800	0.0211	-
8.1164	11850	0.0217	-
8.1507	11900	0.0035	-
8.1849	11950	0.0039	-
8.2192	12000	0.0	-
8.2534	12050	0.0055	-
8.2877	12100	0.0027	-
8.3219	12150	0.0031	-
8.3562	12200	0.0271	-
8.3904	12250	0.0138	-
8.4247	12300	0.0413	-
8.4589	12350	0.0029	-
8.4932	12400	0.0161	-
8.5274	12450	0.0	-
8.5616	12500	0.0352	-
8.5959	12550	0.0018	-
8.6301	12600	0.0363	-
8.6644	12650	0.0136	-
8.6986	12700	0.0175	-
8.7329	12750	0.0045	-
8.7671	12800	0.036	-
8.8014	12850	0.0001	-
8.8356	12900	0.0188	-
8.8699	12950	0.0192	-
8.9041	13000	0.0059	-
8.9384	13050	0.0298	-
8.9726	13100	0.0026	-
9.0068	13150	0.0027	-
9.0411	13200	0.0017	-
9.0753	13250	0.0103	-
9.1096	13300	0.0061	-
9.1438	13350	0.0043	-
9.1781	13400	0.0189	-
9.2123	13450	0.0001	-
9.2466	13500	0.0363	-
9.2808	13550	0.0019	-
9.3151	13600	0.0141	-
9.3493	13650	0.0213	-
9.3836	13700	0.0029	-
9.4178	13750	0.0217	-
9.4521	13800	0.0218	-
9.4863	13850	0.0001	-
9.5205	13900	0.014	-
9.5548	13950	0.0213	-
9.5890	14000	0.0	-
9.6233	14050	0.004	-
9.6575	14100	0.0112	-
9.6918	14150	0.0077	-
9.7260	14200	0.0237	-
9.7603	14250	0.0202	-
9.7945	14300	0.003	-
9.8288	14350	0.002	-
9.8630	14400	0.0028	-
9.8973	14450	0.0398	-
9.9315	14500	0.0001	-
9.9658	14550	0.0185	-
10.0	14600	0.0001	-
10.0342	14650	0.0102	-
10.0685	14700	0.0164	-
10.1027	14750	0.0161	-
10.1370	14800	0.0221	-
10.1712	14850	0.0016	-
10.2055	14900	0.0151	-
10.2397	14950	0.0215	-
10.2740	15000	0.0021	-
10.3082	15050	0.0075	-
10.3425	15100	0.0001	-
10.3767	15150	0.0211	-
10.4110	15200	0.0022	-
10.4452	15250	0.0001	-
10.4795	15300	0.0348	-
10.5137	15350	0.0211	-
10.5479	15400	0.0193	-
10.5822	15450	0.0203	-
10.6164	15500	0.0001	-
10.6507	15550	0.0	-
10.6849	15600	0.0028	-
10.7192	15650	0.0025	-
10.7534	15700	0.003	-
10.7877	15750	0.0199	-
10.8219	15800	0.0238	-
10.8562	15850	0.0024	-
10.8904	15900	0.0149	-
10.9247	15950	0.0019	-
10.9589	16000	0.0001	-
10.9932	16050	0.0206	-
11.0274	16100	0.0187	-
11.0616	16150	0.0025	-
11.0959	16200	0.0001	-
11.1301	16250	0.0185	-
11.1644	16300	0.0476	-
11.1986	16350	0.0027	-
11.2329	16400	0.0064	-
11.2671	16450	0.0026	-
11.3014	16500	0.0055	-
11.3356	16550	0.0024	-
11.3699	16600	0.0059	-
11.4041	16650	0.0	-
11.4384	16700	0.0	-
11.4726	16750	0.0333	-
11.5068	16800	0.0231	-
11.5411	16850	0.0084	-
11.5753	16900	0.0001	-
11.6096	16950	0.0173	-
11.6438	17000	0.0207	-
11.6781	17050	0.0162	-
11.7123	17100	0.0071	-
11.7466	17150	0.0049	-
11.7808	17200	0.0025	-
11.8151	17250	0.011	-
11.8493	17300	0.035	-
11.8836	17350	0.0168	-
11.9178	17400	0.0085	-
11.9521	17450	0.0028	-
11.9863	17500	0.0	-
12.0205	17550	0.0239	-
12.0548	17600	0.0026	-
12.0890	17650	0.008	-
12.1233	17700	0.0165	-
12.1575	17750	0.0027	-
12.1918	17800	0.0069	-
12.2260	17850	0.0215	-
12.2603	17900	0.0236	-
12.2945	17950	0.0001	-
12.3288	18000	0.0001	-
12.3630	18050	0.0025	-
12.3973	18100	0.0026	-
12.4315	18150	0.0164	-
12.4658	18200	0.035	-
12.5	18250	0.0032	-
12.5342	18300	0.0	-
12.5685	18350	0.0343	-
12.6027	18400	0.0024	-
12.6370	18450	0.0025	-
12.6712	18500	0.0202	-
12.7055	18550	0.0192	-
12.7397	18600	0.017	-
12.7740	18650	0.02	-
12.8082	18700	0.0321	-
12.8425	18750	0.0001	-
12.8767	18800	0.0023	-
12.9110	18850	0.0028	-
12.9452	18900	0.0	-
12.9795	18950	0.0	-
13.0137	19000	0.0267	-
13.0479	19050	0.0056	-
13.0822	19100	0.0219	-
13.1164	19150	0.0184	-
13.1507	19200	0.0028	-
13.1849	19250	0.0	-
13.2192	19300	0.005	-
13.2534	19350	0.0056	-
13.2877	19400	0.0033	-
13.3219	19450	0.0	-
13.3562	19500	0.034	-
13.3904	19550	0.0173	-
13.4247	19600	0.033	-
13.4589	19650	0.0025	-
13.4932	19700	0.0279	-
13.5274	19750	0.0052	-
13.5616	19800	0.0351	-
13.5959	19850	0.0	-
13.6301	19900	0.035	-
13.6644	19950	0.0069	-
13.6986	20000	0.0227	-
13.7329	20050	0.0	-
13.7671	20100	0.0347	-
13.8014	20150	0.0	-
13.8356	20200	0.0217	-
13.8699	20250	0.02	-
13.9041	20300	0.0	-
13.9384	20350	0.0393	-
13.9726	20400	0.0053	-
14.0068	20450	0.0026	-
14.0411	20500	0.0025	-
14.0753	20550	0.0049	-
14.1096	20600	0.0	-
14.1438	20650	0.0	-
14.1781	20700	0.0184	-
14.2123	20750	0.0029	-
14.2466	20800	0.0313	-
14.2808	20850	0.0	-
14.3151	20900	0.0051	-
14.3493	20950	0.0157	-
14.3836	21000	0.0059	-
14.4178	21050	0.0182	-
14.4521	21100	0.0242	-
14.4863	21150	0.0024	-
14.5205	21200	0.026	-
14.5548	21250	0.0211	-
14.5890	21300	0.0053	-
14.6233	21350	0.0	-
14.6575	21400	0.0	-
14.6918	21450	0.0034	-
14.7260	21500	0.0239	-
14.7603	21550	0.0209	-
14.7945	21600	0.0028	-
14.8288	21650	0.0	-
14.8630	21700	0.0022	-
14.8973	21750	0.0364	-
14.9315	21800	0.0052	-
14.9658	21850	0.0239	-
15.0	21900	0.0	-

Framework Versions

Python: 3.10.12
SetFit: 1.1.0.dev0
Sentence Transformers: 2.6.1
Transformers: 4.38.2
PyTorch: 2.2.1+cu121
Datasets: 2.18.0
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}
}