metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: Dadon Hotel
  - text: Joyi Homeo Hall
  - text: Masum Egg Supplier
  - text: Salam Automobiles
  - text: Shoumik Enterprise
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/paraphrase-mpnet-base-v2
model-index:
  - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.57
            name: Accuracy

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-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/paraphrase-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 19 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
Utility	'Pole No 198' 'Mirpur 12/A Harun Mollah Eidgah Math Water Pump' 'Pole No 44'
Education	'Jamirs Care' 'Institute Of Marine Technology Chandpur' 'Nobo Digonto Coaching Center'
Office	'Media And Multimedia' 'Ataur Rahman Atiq Lawfarm' 'Kemiko Pharmaceutical Limited'
Commercial	'Lakshmipur Police Line Shopping Mall' 'Bolaka Building' 'Vegetables Market'
Industry	'Haque Food Industries Limited' 'Agig Poultry Firm' 'Regular Washing Plant'
Healthcare	'Utsob Homeo Hall' 'Homeo Biochemic Chikitsa Kendro' 'Ananta Homeo Clinic'
Residential	'Hotel City Garden' 'Kasmi Bhaban' 'AR Tower'
Government	'Cyclone Preparedness Program Ministry of Disaster Management and Relief' 'Fire Service And Civil Defense' 'Sherpur Bwdb'
Hotel	'China Inn Limited' 'Hotel Salimar International' 'Hotel Grand Surma'
Religious Place	'Soudagor Tola Hazrat Gorom Dhawan (R.) Jame Masjid' 'Shah Makhdum (R:) Masjid' 'Mahiganj Central Graveyard'
Food	'Takwaya Biryani House' 'Jilapi Ghor' 'Sad Biryani House'
Fuel	'A N Enterprise' 'Sabbir Fuel Station' 'Trade Consortium'
Agricultural	'Vasha Sainik Samir Ahmed Bohumukhi Khamar' 'Tanzila Nursery' 'Insaf Agro'
Construction	'Bohurupa Enterprise' 'M/S Jamiya Steel House' 'Nure Madina Timber And Saw Mill'
Recreation	'Bijoygatha Community Center' 'Shahid Doctor Fazle Rabbi Park' 'Kalabagan Staff Quarter Field'
Shop	'Tawfiq Confectionery & Varieties 2' 'Tammi store' 'Shah Jalal Timber Merchant & Sawmill'
Transportation	'Sagorika Paribahan' 'Bismillah Ahmed Transport Agency' 'Medda Bus Stand'
Bank	'United Commercial Bank Jatrabari (UCB)' 'Union Bank Limited Dewan Bazar Branch' 'Janata Bank Badda'
Landmark	'Dilkhola Moar' 'Gouripur Motlob Road Moar' 'Bot Chattar'

Evaluation

Metrics

Label	Accuracy
all	0.57

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("rafi138/setfit-paraphrase-mpnet-base-v2-business-type")
# Run inference
preds = model("Dadon Hotel")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	3.5132	11

Label	Training Sample Count
ShopCommercialGovernmentHealthcareEducationFoodOfficeReligious PlaceBankTransportationConstructionIndustryResidentialLandmarkRecreationFuelHotelUtilityAgricultural	0

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (4, 4)
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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0001	1	0.2213	-
0.0058	50	0.253	-
0.0117	100	0.2571	-
0.0175	150	0.2189	-
0.0234	200	0.2138	-
0.0292	250	0.173	-
0.0351	300	0.2221	-
0.0409	350	0.1669	-
0.0468	400	0.1214	-
0.0526	450	0.18	-
0.0585	500	0.0983	-
0.0643	550	0.0965	-
0.0702	600	0.0819	-
0.0760	650	0.1476	-
0.0819	700	0.1289	-
0.0877	750	0.0926	-
0.0936	800	0.1395	-
0.0994	850	0.1124	-
0.1053	900	0.1089	-
0.1111	950	0.1349	-
0.1170	1000	0.0884	-
0.1228	1050	0.0559	-
0.1287	1100	0.0433	-
0.1345	1150	0.0556	-
0.1404	1200	0.081	-
0.1462	1250	0.0334	-
0.1520	1300	0.0659	-
0.1579	1350	0.0103	-
0.1637	1400	0.0638	-
0.1696	1450	0.0298	-
0.1754	1500	0.0496	-
0.1813	1550	0.0114	-
0.1871	1600	0.023	-
0.1930	1650	0.0613	-
0.1988	1700	0.0098	-
0.2047	1750	0.0141	-
0.2105	1800	0.0034	-
0.2164	1850	0.0095	-
0.2222	1900	0.005	-
0.2281	1950	0.0034	-
0.2339	2000	0.051	-
0.2398	2050	0.0038	-
0.2456	2100	0.0091	-
0.2515	2150	0.0027	-
0.2573	2200	0.003	-
0.2632	2250	0.0014	-
0.2690	2300	0.0032	-
0.2749	2350	0.0731	-
0.2807	2400	0.0025	-
0.2865	2450	0.0041	-
0.2924	2500	0.0061	-
0.2982	2550	0.0016	-
0.3041	2600	0.0027	-
0.3099	2650	0.002	-
0.3158	2700	0.0013	-
0.3216	2750	0.0155	-
0.3275	2800	0.0079	-
0.3333	2850	0.0026	-
0.3392	2900	0.001	-
0.3450	2950	0.0024	-
0.3509	3000	0.0015	-
0.3567	3050	0.0006	-
0.3626	3100	0.0072	-
0.3684	3150	0.0023	-
0.3743	3200	0.001	-
0.3801	3250	0.0011	-
0.3860	3300	0.0126	-
0.3918	3350	0.0025	-
0.3977	3400	0.0009	-
0.4035	3450	0.006	-
0.4094	3500	0.0011	-
0.4152	3550	0.001	-
0.4211	3600	0.0017	-
0.4269	3650	0.0009	-
0.4327	3700	0.0007	-
0.4386	3750	0.0006	-
0.4444	3800	0.0007	-
0.4503	3850	0.0007	-
0.4561	3900	0.0005	-
0.4620	3950	0.0006	-
0.4678	4000	0.0005	-
0.4737	4050	0.0003	-
0.4795	4100	0.0003	-
0.4854	4150	0.0003	-
0.4912	4200	0.0003	-
0.4971	4250	0.0013	-
0.5029	4300	0.0009	-
0.5088	4350	0.0003	-
0.5146	4400	0.0007	-
0.5205	4450	0.0006	-
0.5263	4500	0.0005	-
0.5322	4550	0.0005	-
0.5380	4600	0.0006	-
0.5439	4650	0.0005	-
0.5497	4700	0.0004	-
0.5556	4750	0.0004	-
0.5614	4800	0.0003	-
0.5673	4850	0.0003	-
0.5731	4900	0.0005	-
0.5789	4950	0.0005	-
0.5848	5000	0.0008	-
0.5906	5050	0.0003	-
0.5965	5100	0.0004	-
0.6023	5150	0.0003	-
0.6082	5200	0.0004	-
0.6140	5250	0.0003	-
0.6199	5300	0.0003	-
0.6257	5350	0.0004	-
0.6316	5400	0.0003	-
0.6374	5450	0.0003	-
0.6433	5500	0.0002	-
0.6491	5550	0.0003	-
0.6550	5600	0.0003	-
0.6608	5650	0.0008	-
0.6667	5700	0.0003	-
0.6725	5750	0.0004	-
0.6784	5800	0.0007	-
0.6842	5850	0.0372	-
0.6901	5900	0.0045	-
0.6959	5950	0.0041	-
0.7018	6000	0.0006	-
0.7076	6050	0.0004	-
0.7135	6100	0.0005	-
0.7193	6150	0.0003	-
0.7251	6200	0.0002	-
0.7310	6250	0.0022	-
0.7368	6300	0.0004	-
0.7427	6350	0.0003	-
0.7485	6400	0.0003	-
0.7544	6450	0.0002	-
0.7602	6500	0.0004	-
0.7661	6550	0.0006	-
0.7719	6600	0.0002	-
0.7778	6650	0.0003	-
0.7836	6700	0.0002	-
0.7895	6750	0.0002	-
0.7953	6800	0.0003	-
0.8012	6850	0.0003	-
0.8070	6900	0.0003	-
0.8129	6950	0.0007	-
0.8187	7000	0.0002	-
0.8246	7050	0.0002	-
0.8304	7100	0.0002	-
0.8363	7150	0.0002	-
0.8421	7200	0.0003	-
0.8480	7250	0.0002	-
0.8538	7300	0.0002	-
0.8596	7350	0.0002	-
0.8655	7400	0.0002	-
0.8713	7450	0.0003	-
0.8772	7500	0.0001	-
0.8830	7550	0.0001	-
0.8889	7600	0.0002	-
0.8947	7650	0.0002	-
0.9006	7700	0.0002	-
0.9064	7750	0.0002	-
0.9123	7800	0.0002	-
0.9181	7850	0.0001	-
0.9240	7900	0.0002	-
0.9298	7950	0.0001	-
0.9357	8000	0.0003	-
0.9415	8050	0.0001	-
0.9474	8100	0.0002	-
0.9532	8150	0.0001	-
0.9591	8200	0.0001	-
0.9649	8250	0.0001	-
0.9708	8300	0.0001	-
0.9766	8350	0.0002	-
0.9825	8400	0.0002	-
0.9883	8450	0.0001	-
0.9942	8500	0.0001	-
1.0	8550	0.0002	0.3616
1.0058	8600	0.0003	-
1.0117	8650	0.0002	-
1.0175	8700	0.0002	-
1.0234	8750	0.0002	-
1.0292	8800	0.0001	-
1.0351	8850	0.0001	-
1.0409	8900	0.0001	-
1.0468	8950	0.0002	-
1.0526	9000	0.0002	-
1.0585	9050	0.0001	-
1.0643	9100	0.0002	-
1.0702	9150	0.0002	-
1.0760	9200	0.0001	-
1.0819	9250	0.0002	-
1.0877	9300	0.0002	-
1.0936	9350	0.0002	-
1.0994	9400	0.0002	-
1.1053	9450	0.0002	-
1.1111	9500	0.0001	-
1.1170	9550	0.0001	-
1.1228	9600	0.0001	-
1.1287	9650	0.0001	-
1.1345	9700	0.0001	-
1.1404	9750	0.0002	-
1.1462	9800	0.0004	-
1.1520	9850	0.0367	-
1.1579	9900	0.0009	-
1.1637	9950	0.038	-
1.1696	10000	0.0005	-
1.1754	10050	0.0005	-
1.1813	10100	0.0004	-
1.1871	10150	0.0002	-
1.1930	10200	0.0002	-
1.1988	10250	0.0002	-
1.2047	10300	0.0002	-
1.2105	10350	0.0002	-
1.2164	10400	0.0002	-
1.2222	10450	0.0001	-
1.2281	10500	0.0003	-
1.2339	10550	0.0002	-
1.2398	10600	0.0002	-
1.2456	10650	0.0003	-
1.2515	10700	0.0002	-
1.2573	10750	0.0001	-
1.2632	10800	0.0002	-
1.2690	10850	0.0002	-
1.2749	10900	0.0002	-
1.2807	10950	0.0002	-
1.2865	11000	0.0002	-
1.2924	11050	0.0001	-
1.2982	11100	0.0002	-
1.3041	11150	0.0002	-
1.3099	11200	0.0002	-
1.3158	11250	0.0001	-
1.3216	11300	0.0001	-
1.3275	11350	0.0001	-
1.3333	11400	0.0001	-
1.3392	11450	0.0002	-
1.3450	11500	0.0002	-
1.3509	11550	0.0001	-
1.3567	11600	0.0002	-
1.3626	11650	0.0002	-
1.3684	11700	0.0001	-
1.3743	11750	0.0001	-
1.3801	11800	0.0001	-
1.3860	11850	0.0002	-
1.3918	11900	0.0001	-
1.3977	11950	0.0001	-
1.4035	12000	0.0001	-
1.4094	12050	0.0001	-
1.4152	12100	0.0001	-
1.4211	12150	0.0001	-
1.4269	12200	0.0002	-
1.4327	12250	0.0002	-
1.4386	12300	0.0001	-
1.4444	12350	0.0002	-
1.4503	12400	0.0002	-
1.4561	12450	0.0001	-
1.4620	12500	0.0001	-
1.4678	12550	0.0001	-
1.4737	12600	0.0002	-
1.4795	12650	0.0002	-
1.4854	12700	0.0001	-
1.4912	12750	0.0002	-
1.4971	12800	0.0001	-
1.5029	12850	0.0001	-
1.5088	12900	0.0001	-
1.5146	12950	0.0001	-
1.5205	13000	0.0001	-
1.5263	13050	0.0001	-
1.5322	13100	0.0001	-
1.5380	13150	0.0002	-
1.5439	13200	0.0001	-
1.5497	13250	0.0002	-
1.5556	13300	0.0002	-
1.5614	13350	0.0002	-
1.5673	13400	0.0001	-
1.5731	13450	0.0001	-
1.5789	13500	0.0002	-
1.5848	13550	0.0002	-
1.5906	13600	0.0001	-
1.5965	13650	0.0001	-
1.6023	13700	0.0002	-
1.6082	13750	0.0001	-
1.6140	13800	0.0001	-
1.6199	13850	0.0001	-
1.6257	13900	0.0001	-
1.6316	13950	0.0001	-
1.6374	14000	0.0001	-
1.6433	14050	0.0001	-
1.6491	14100	0.0002	-
1.6550	14150	0.0001	-
1.6608	14200	0.0001	-
1.6667	14250	0.0001	-
1.6725	14300	0.0001	-
1.6784	14350	0.0001	-
1.6842	14400	0.0001	-
1.6901	14450	0.0002	-
1.6959	14500	0.0001	-
1.7018	14550	0.0002	-
1.7076	14600	0.0077	-
1.7135	14650	0.0326	-
1.7193	14700	0.0001	-
1.7251	14750	0.0002	-
1.7310	14800	0.0001	-
1.7368	14850	0.0001	-
1.7427	14900	0.0002	-
1.7485	14950	0.0001	-
1.7544	15000	0.0001	-
1.7602	15050	0.0001	-
1.7661	15100	0.0001	-
1.7719	15150	0.0001	-
1.7778	15200	0.0001	-
1.7836	15250	0.0001	-
1.7895	15300	0.0002	-
1.7953	15350	0.0002	-
1.8012	15400	0.0001	-
1.8070	15450	0.0001	-
1.8129	15500	0.0002	-
1.8187	15550	0.0002	-
1.8246	15600	0.0002	-
1.8304	15650	0.0001	-
1.8363	15700	0.0001	-
1.8421	15750	0.0001	-
1.8480	15800	0.0001	-
1.8538	15850	0.0001	-
1.8596	15900	0.0001	-
1.8655	15950	0.0001	-
1.8713	16000	0.0001	-
1.8772	16050	0.0001	-
1.8830	16100	0.0001	-
1.8889	16150	0.0001	-
1.8947	16200	0.014	-
1.9006	16250	0.0109	-
1.9064	16300	0.0005	-
1.9123	16350	0.0001	-
1.9181	16400	0.0012	-
1.9240	16450	0.0016	-
1.9298	16500	0.0267	-
1.9357	16550	0.0001	-
1.9415	16600	0.0001	-
1.9474	16650	0.0001	-
1.9532	16700	0.0001	-
1.9591	16750	0.0001	-
1.9649	16800	0.0002	-
1.9708	16850	0.0001	-
1.9766	16900	0.0001	-
1.9825	16950	0.0001	-
1.9883	17000	0.0001	-
1.9942	17050	0.0001	-
2.0	17100	0.0002	0.35
2.0058	17150	0.0001	-
2.0117	17200	0.0001	-
2.0175	17250	0.0001	-
2.0234	17300	0.0002	-
2.0292	17350	0.0001	-
2.0351	17400	0.0001	-
2.0409	17450	0.0001	-
2.0468	17500	0.0001	-
2.0526	17550	0.0001	-
2.0585	17600	0.0002	-
2.0643	17650	0.0001	-
2.0702	17700	0.0001	-
2.0760	17750	0.0001	-
2.0819	17800	0.0001	-
2.0877	17850	0.0001	-
2.0936	17900	0.0001	-
2.0994	17950	0.0001	-
2.1053	18000	0.0001	-
2.1111	18050	0.0001	-
2.1170	18100	0.0001	-
2.1228	18150	0.0001	-
2.1287	18200	0.0001	-
2.1345	18250	0.0001	-
2.1404	18300	0.0001	-
2.1462	18350	0.0001	-
2.1520	18400	0.0001	-
2.1579	18450	0.0001	-
2.1637	18500	0.0002	-
2.1696	18550	0.0001	-
2.1754	18600	0.0001	-
2.1813	18650	0.0001	-
2.1871	18700	0.0001	-
2.1930	18750	0.0001	-
2.1988	18800	0.0001	-
2.2047	18850	0.0001	-
2.2105	18900	0.0002	-
2.2164	18950	0.0001	-
2.2222	19000	0.0001	-
2.2281	19050	0.0001	-
2.2339	19100	0.0001	-
2.2398	19150	0.0004	-
2.2456	19200	0.0001	-
2.2515	19250	0.0001	-
2.2573	19300	0.0001	-
2.2632	19350	0.0001	-
2.2690	19400	0.0001	-
2.2749	19450	0.0001	-
2.2807	19500	0.0001	-
2.2865	19550	0.0001	-
2.2924	19600	0.0001	-
2.2982	19650	0.0001	-
2.3041	19700	0.0001	-
2.3099	19750	0.0001	-
2.3158	19800	0.0001	-
2.3216	19850	0.0001	-
2.3275	19900	0.0001	-
2.3333	19950	0.0001	-
2.3392	20000	0.0001	-
2.3450	20050	0.0001	-
2.3509	20100	0.0001	-
2.3567	20150	0.0001	-
2.3626	20200	0.0001	-
2.3684	20250	0.0001	-
2.3743	20300	0.0001	-
2.3801	20350	0.0001	-
2.3860	20400	0.0001	-
2.3918	20450	0.0001	-
2.3977	20500	0.0001	-
2.4035	20550	0.0002	-
2.4094	20600	0.0002	-
2.4152	20650	0.0001	-
2.4211	20700	0.0001	-
2.4269	20750	0.0001	-
2.4327	20800	0.0002	-
2.4386	20850	0.0001	-
2.4444	20900	0.0003	-
2.4503	20950	0.0001	-
2.4561	21000	0.0001	-
2.4620	21050	0.0001	-
2.4678	21100	0.0005	-
2.4737	21150	0.0001	-
2.4795	21200	0.0001	-
2.4854	21250	0.0001	-
2.4912	21300	0.0001	-
2.4971	21350	0.0003	-
2.5029	21400	0.0001	-
2.5088	21450	0.0001	-
2.5146	21500	0.0001	-
2.5205	21550	0.0001	-
2.5263	21600	0.0001	-
2.5322	21650	0.0001	-
2.5380	21700	0.0001	-
2.5439	21750	0.0001	-
2.5497	21800	0.0001	-
2.5556	21850	0.0001	-
2.5614	21900	0.0001	-
2.5673	21950	0.0001	-
2.5731	22000	0.0001	-
2.5789	22050	0.0001	-
2.5848	22100	0.0001	-
2.5906	22150	0.0001	-
2.5965	22200	0.0001	-
2.6023	22250	0.0	-
2.6082	22300	0.0001	-
2.6140	22350	0.0001	-
2.6199	22400	0.0001	-
2.6257	22450	0.0001	-
2.6316	22500	0.0001	-
2.6374	22550	0.0001	-
2.6433	22600	0.0001	-
2.6491	22650	0.0001	-
2.6550	22700	0.0001	-
2.6608	22750	0.0001	-
2.6667	22800	0.0001	-
2.6725	22850	0.0001	-
2.6784	22900	0.0001	-
2.6842	22950	0.0001	-
2.6901	23000	0.0001	-
2.6959	23050	0.0001	-
2.7018	23100	0.0001	-
2.7076	23150	0.0001	-
2.7135	23200	0.0001	-
2.7193	23250	0.0001	-
2.7251	23300	0.0001	-
2.7310	23350	0.0001	-
2.7368	23400	0.0001	-
2.7427	23450	0.0001	-
2.7485	23500	0.0001	-
2.7544	23550	0.0001	-
2.7602	23600	0.0001	-
2.7661	23650	0.0001	-
2.7719	23700	0.0001	-
2.7778	23750	0.0001	-
2.7836	23800	0.0001	-
2.7895	23850	0.0001	-
2.7953	23900	0.0001	-
2.8012	23950	0.0001	-
2.8070	24000	0.0001	-
2.8129	24050	0.0001	-
2.8187	24100	0.0001	-
2.8246	24150	0.0001	-
2.8304	24200	0.0001	-
2.8363	24250	0.0001	-
2.8421	24300	0.0001	-
2.8480	24350	0.0002	-
2.8538	24400	0.0001	-
2.8596	24450	0.0001	-
2.8655	24500	0.0001	-
2.8713	24550	0.0001	-
2.8772	24600	0.0001	-
2.8830	24650	0.0001	-
2.8889	24700	0.0001	-
2.8947	24750	0.0001	-
2.9006	24800	0.0001	-
2.9064	24850	0.0001	-
2.9123	24900	0.0001	-
2.9181	24950	0.0001	-
2.9240	25000	0.0001	-
2.9298	25050	0.0002	-
2.9357	25100	0.0001	-
2.9415	25150	0.0001	-
2.9474	25200	0.0001	-
2.9532	25250	0.0001	-
2.9591	25300	0.0001	-
2.9649	25350	0.0001	-
2.9708	25400	0.0001	-
2.9766	25450	0.0001	-
2.9825	25500	0.0001	-
2.9883	25550	0.0001	-
2.9942	25600	0.0001	-
3.0	25650	0.0001	0.3812
3.0058	25700	0.0001	-
3.0117	25750	0.0001	-
3.0175	25800	0.0001	-
3.0234	25850	0.0001	-
3.0292	25900	0.0001	-
3.0351	25950	0.0001	-
3.0409	26000	0.0001	-
3.0468	26050	0.0001	-
3.0526	26100	0.0001	-
3.0585	26150	0.0001	-
3.0643	26200	0.0001	-
3.0702	26250	0.0001	-
3.0760	26300	0.0001	-
3.0819	26350	0.0001	-
3.0877	26400	0.0001	-
3.0936	26450	0.0001	-
3.0994	26500	0.0001	-
3.1053	26550	0.0001	-
3.1111	26600	0.0001	-
3.1170	26650	0.0001	-
3.1228	26700	0.0001	-
3.1287	26750	0.0001	-
3.1345	26800	0.0001	-
3.1404	26850	0.0001	-
3.1462	26900	0.0001	-
3.1520	26950	0.0001	-
3.1579	27000	0.0001	-
3.1637	27050	0.0001	-
3.1696	27100	0.0001	-
3.1754	27150	0.0001	-
3.1813	27200	0.0001	-
3.1871	27250	0.0001	-
3.1930	27300	0.0001	-
3.1988	27350	0.0001	-
3.2047	27400	0.0001	-
3.2105	27450	0.0001	-
3.2164	27500	0.0001	-
3.2222	27550	0.0001	-
3.2281	27600	0.0001	-
3.2339	27650	0.0001	-
3.2398	27700	0.0001	-
3.2456	27750	0.0001	-
3.2515	27800	0.0001	-
3.2573	27850	0.0001	-
3.2632	27900	0.0001	-
3.2690	27950	0.0001	-
3.2749	28000	0.0001	-
3.2807	28050	0.0001	-
3.2865	28100	0.0001	-
3.2924	28150	0.0001	-
3.2982	28200	0.0001	-
3.3041	28250	0.0001	-
3.3099	28300	0.0001	-
3.3158	28350	0.0001	-
3.3216	28400	0.0001	-
3.3275	28450	0.0	-
3.3333	28500	0.0001	-
3.3392	28550	0.0001	-
3.3450	28600	0.0001	-
3.3509	28650	0.0001	-
3.3567	28700	0.0001	-
3.3626	28750	0.0001	-
3.3684	28800	0.0001	-
3.3743	28850	0.0001	-
3.3801	28900	0.0001	-
3.3860	28950	0.0001	-
3.3918	29000	0.0001	-
3.3977	29050	0.0001	-
3.4035	29100	0.0001	-
3.4094	29150	0.0001	-
3.4152	29200	0.0001	-
3.4211	29250	0.0001	-
3.4269	29300	0.0001	-
3.4327	29350	0.0001	-
3.4386	29400	0.0001	-
3.4444	29450	0.0001	-
3.4503	29500	0.0001	-
3.4561	29550	0.0001	-
3.4620	29600	0.0001	-
3.4678	29650	0.0001	-
3.4737	29700	0.0001	-
3.4795	29750	0.0001	-
3.4854	29800	0.0001	-
3.4912	29850	0.0001	-
3.4971	29900	0.0001	-
3.5029	29950	0.0001	-
3.5088	30000	0.0001	-
3.5146	30050	0.0001	-
3.5205	30100	0.0001	-
3.5263	30150	0.0001	-
3.5322	30200	0.0001	-
3.5380	30250	0.0001	-
3.5439	30300	0.0001	-
3.5497	30350	0.0001	-
3.5556	30400	0.0001	-
3.5614	30450	0.0001	-
3.5673	30500	0.0001	-
3.5731	30550	0.0001	-
3.5789	30600	0.0001	-
3.5848	30650	0.0001	-
3.5906	30700	0.0001	-
3.5965	30750	0.0001	-
3.6023	30800	0.0001	-
3.6082	30850	0.0001	-
3.6140	30900	0.0001	-
3.6199	30950	0.0001	-
3.6257	31000	0.0001	-
3.6316	31050	0.0001	-
3.6374	31100	0.0001	-
3.6433	31150	0.0001	-
3.6491	31200	0.0001	-
3.6550	31250	0.0001	-
3.6608	31300	0.0001	-
3.6667	31350	0.0001	-
3.6725	31400	0.0001	-
3.6784	31450	0.0001	-
3.6842	31500	0.0001	-
3.6901	31550	0.0001	-
3.6959	31600	0.0001	-
3.7018	31650	0.0	-
3.7076	31700	0.0001	-
3.7135	31750	0.0001	-
3.7193	31800	0.0001	-
3.7251	31850	0.0001	-
3.7310	31900	0.0001	-
3.7368	31950	0.0001	-
3.7427	32000	0.0001	-
3.7485	32050	0.0001	-
3.7544	32100	0.0001	-
3.7602	32150	0.0001	-
3.7661	32200	0.0001	-
3.7719	32250	0.0001	-
3.7778	32300	0.0001	-
3.7836	32350	0.0001	-
3.7895	32400	0.0001	-
3.7953	32450	0.0001	-
3.8012	32500	0.0001	-
3.8070	32550	0.0001	-
3.8129	32600	0.0001	-
3.8187	32650	0.0001	-
3.8246	32700	0.0001	-
3.8304	32750	0.0001	-
3.8363	32800	0.0001	-
3.8421	32850	0.0001	-
3.8480	32900	0.0001	-
3.8538	32950	0.0001	-
3.8596	33000	0.0001	-
3.8655	33050	0.0001	-
3.8713	33100	0.0001	-
3.8772	33150	0.0001	-
3.8830	33200	0.0001	-
3.8889	33250	0.0001	-
3.8947	33300	0.0001	-
3.9006	33350	0.0001	-
3.9064	33400	0.0001	-
3.9123	33450	0.0001	-
3.9181	33500	0.0001	-
3.9240	33550	0.0001	-
3.9298	33600	0.0001	-
3.9357	33650	0.0001	-
3.9415	33700	0.0001	-
3.9474	33750	0.0001	-
3.9532	33800	0.0001	-
3.9591	33850	0.0001	-
3.9649	33900	0.0001	-
3.9708	33950	0.0001	-
3.9766	34000	0.0	-
3.9825	34050	0.0001	-
3.9883	34100	0.0001	-
3.9942	34150	0.0001	-
4.0	34200	0.0001	0.3694

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.2.2
Transformers: 4.36.2
PyTorch: 2.1.2+cu121
Datasets: 2.16.1
Tokenizers: 0.15.0

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}
}