metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      pay rs.20.00 / c 91xx3402 ganeshramkudisodebur 22 - 09 - 2023 .
      ref:3648483126 . query ? click http://m.paytm.me/care : ppbl
  - text: >-
      inform m / s shree salasar balaji tex transfer rs . 10000.00 account .
      xxxxxxxx2869 yes bank account rtgs / neft / imp
  - text: >-
      undelivered!\nyour hdfc bank debit card 9875 / c 8494\nreason ch shift .
      case address change , update seamless card delivery > >
      hdfcbk.io/a/0nzoo052
  - text: >-
      rs 5000.00 debit / c upi 23 - 09 - 2023 14:21:12 vpa 35890012004230@cnrb -
      ( upi ref 363290511260)-federal bank
  - text: >-
      472448 otp set hdfc bank 4 digit login pin . share otp you?call
      18002586161
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/all-mpnet-base-v2
model-index:
  - name: SetFit with sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9715909090909091
            name: Accuracy

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

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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/all-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 384 tokens
Number of Classes: 3 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
2	'840989 otp proceed canara bank mobile banking . valid 15 minute . share otp . - canara bank . kbl8a1ju0mt' 'cheque . 000102 issue riya collection rs . 12,000.00 present / c xxxxx546157 return unpaid insufficient fund . team idfc bank' 'avl bal / c xxxx0959 10 - jul-2022 06:06:24 inr 0.00 . combine avl bal inr 0.00 . use mb app track / c - kotak bank'
0	'/ c . xxxxxxxx7146 debit rs.11933.00 16 - 09 - 23 / c xxxxxxxx4716 credit ( imp ref 325908759095 ) . warm regard , yes bank' 'send rs.290.00 kotak bank ac x4524 bharatpe90727843812@yesbankltd 13-10-23.upi ref 328684167136 . , kotak.com/fraud' 'rs.295 transfer / c ... 4322 : lien_marking_fo . total bal : rs.188.8cr . avlbl amt : rs.609.97(28 - 06 - 2022 16:39:53 ) - bank baroda'
1	'rs 15000credite / c xx4524via neft neofirst technology india private- utr ref hsbcn23276508097 ; avail . bal.:rs 215180.62kotak bank' '/ c : xx6775 credit rs.60.00 14 - 11 - 2023 10:47:49 upi - id 8733076955@omni ( upi ref 331800008439).-canara bank' 'rs.28 credit / c ... 7783 upi/323962847509 kiwicashback_ax . total bal : rs.122751.36cr . avlbl amt : rs.94671.36(27 - 08 - 2023 15:37:01 ) - bank baroda'

Evaluation

Metrics

Label	Accuracy
all	0.9716

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("vipinbansal179/SetFit_sms_Analyzer1")
# Run inference
preds = model("472448 otp set hdfc bank 4 digit login pin . share otp you?call 18002586161")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	23.17	65

Label	Training Sample Count
0	231
1	131
2	338

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (2, 2)
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	0.2945	-
0.0026	50	0.3574	-
0.0052	100	0.2512	-
0.0079	150	0.2319	-
0.0105	200	0.2787	-
0.0131	250	0.2129	-
0.0157	300	0.2189	-
0.0183	350	0.0857	-
0.0210	400	0.0932	-
0.0236	450	0.065	-
0.0262	500	0.0553	-
0.0288	550	0.0674	-
0.0314	600	0.0239	-
0.0341	650	0.0054	-
0.0367	700	0.0025	-
0.0393	750	0.002	-
0.0419	800	0.0007	-
0.0446	850	0.001	-
0.0472	900	0.0008	-
0.0498	950	0.0008	-
0.0524	1000	0.0003	-
0.0550	1050	0.0012	-
0.0577	1100	0.002	-
0.0603	1150	0.0192	-
0.0629	1200	0.0041	-
0.0655	1250	0.0002	-
0.0681	1300	0.0001	-
0.0708	1350	0.0001	-
0.0734	1400	0.0001	-
0.0760	1450	0.0004	-
0.0786	1500	0.0003	-
0.0812	1550	0.0002	-
0.0839	1600	0.0004	-
0.0865	1650	0.0002	-
0.0891	1700	0.0002	-
0.0917	1750	0.0001	-
0.0943	1800	0.0001	-
0.0970	1850	0.0001	-
0.0996	1900	0.0001	-
0.1022	1950	0.0001	-
0.1048	2000	0.0001	-
0.1075	2050	0.0015	-
0.1101	2100	0.0001	-
0.1127	2150	0.0001	-
0.1153	2200	0.0001	-
0.1179	2250	0.0001	-
0.1206	2300	0.0	-
0.1232	2350	0.0001	-
0.1258	2400	0.0	-
0.1284	2450	0.0001	-
0.1310	2500	0.0	-
0.1337	2550	0.0001	-
0.1363	2600	0.0	-
0.1389	2650	0.0001	-
0.1415	2700	0.0	-
0.1441	2750	0.0	-
0.1468	2800	0.0	-
0.1494	2850	0.0	-
0.1520	2900	0.0	-
0.1546	2950	0.0	-
0.1572	3000	0.0	-
0.1599	3050	0.0	-
0.1625	3100	0.0	-
0.1651	3150	0.0	-
0.1677	3200	0.0	-
0.1704	3250	0.0	-
0.1730	3300	0.0	-
0.1756	3350	0.0	-
0.1782	3400	0.0	-
0.1808	3450	0.0	-
0.1835	3500	0.0	-
0.1861	3550	0.0003	-
0.1887	3600	0.0131	-
0.1913	3650	0.0004	-
0.1939	3700	0.0001	-
0.1966	3750	0.0	-
0.1992	3800	0.0001	-
0.2018	3850	0.0002	-
0.2044	3900	0.0	-
0.2070	3950	0.0	-
0.2097	4000	0.0001	-
0.2123	4050	0.0015	-
0.2149	4100	0.0002	-
0.2175	4150	0.0	-
0.2201	4200	0.0	-
0.2228	4250	0.0	-
0.2254	4300	0.0	-
0.2280	4350	0.0	-
0.2306	4400	0.0	-
0.2333	4450	0.0	-
0.2359	4500	0.0	-
0.2385	4550	0.0	-
0.2411	4600	0.0	-
0.2437	4650	0.0	-
0.2464	4700	0.0	-
0.2490	4750	0.0	-
0.2516	4800	0.0	-
0.2542	4850	0.0	-
0.2568	4900	0.0	-
0.2595	4950	0.0	-
0.2621	5000	0.0	-
0.2647	5050	0.0	-
0.2673	5100	0.0	-
0.2699	5150	0.0	-
0.2726	5200	0.0	-
0.2752	5250	0.0	-
0.2778	5300	0.0	-
0.2804	5350	0.0	-
0.2830	5400	0.0	-
0.2857	5450	0.0	-
0.2883	5500	0.0	-
0.2909	5550	0.0	-
0.2935	5600	0.0	-
0.2962	5650	0.0	-
0.2988	5700	0.0	-
0.3014	5750	0.0	-
0.3040	5800	0.0	-
0.3066	5850	0.0	-
0.3093	5900	0.0	-
0.3119	5950	0.0	-
0.3145	6000	0.0	-
0.3171	6050	0.0	-
0.3197	6100	0.0	-
0.3224	6150	0.0	-
0.3250	6200	0.0	-
0.3276	6250	0.0	-
0.3302	6300	0.0	-
0.3328	6350	0.0	-
0.3355	6400	0.0	-
0.3381	6450	0.0	-
0.3407	6500	0.0	-
0.3433	6550	0.0	-
0.3459	6600	0.0	-
0.3486	6650	0.0	-
0.3512	6700	0.0	-
0.3538	6750	0.0	-
0.3564	6800	0.0	-
0.3591	6850	0.0	-
0.3617	6900	0.0	-
0.3643	6950	0.0	-
0.3669	7000	0.0	-
0.3695	7050	0.0	-
0.3722	7100	0.0	-
0.3748	7150	0.0	-
0.3774	7200	0.0	-
0.3800	7250	0.0	-
0.3826	7300	0.0	-
0.3853	7350	0.0	-
0.3879	7400	0.0	-
0.3905	7450	0.0	-
0.3931	7500	0.0	-
0.3957	7550	0.0	-
0.3984	7600	0.0	-
0.4010	7650	0.0	-
0.4036	7700	0.0	-
0.4062	7750	0.0	-
0.4088	7800	0.0	-
0.4115	7850	0.0	-
0.4141	7900	0.0	-
0.4167	7950	0.0	-
0.4193	8000	0.0	-
0.4220	8050	0.0	-
0.4246	8100	0.0	-
0.4272	8150	0.0	-
0.4298	8200	0.0	-
0.4324	8250	0.0	-
0.4351	8300	0.0	-
0.4377	8350	0.0	-
0.4403	8400	0.0	-
0.4429	8450	0.0	-
0.4455	8500	0.0	-
0.4482	8550	0.0	-
0.4508	8600	0.0	-
0.4534	8650	0.0	-
0.4560	8700	0.0	-
0.4586	8750	0.0	-
0.4613	8800	0.0	-
0.4639	8850	0.0	-
0.4665	8900	0.0	-
0.4691	8950	0.0001	-
0.4717	9000	0.0	-
0.4744	9050	0.0	-
0.4770	9100	0.0	-
0.4796	9150	0.0	-
0.4822	9200	0.0	-
0.4849	9250	0.0	-
0.4875	9300	0.0	-
0.4901	9350	0.0	-
0.4927	9400	0.0	-
0.4953	9450	0.0	-
0.4980	9500	0.0	-
0.5006	9550	0.0	-
0.5032	9600	0.0	-
0.5058	9650	0.0	-
0.5084	9700	0.0	-
0.5111	9750	0.0	-
0.5137	9800	0.0	-
0.5163	9850	0.0	-
0.5189	9900	0.0	-
0.5215	9950	0.0	-
0.5242	10000	0.0	-
0.5268	10050	0.0	-
0.5294	10100	0.0	-
0.5320	10150	0.0	-
0.5346	10200	0.0	-
0.5373	10250	0.0	-
0.5399	10300	0.0	-
0.5425	10350	0.0	-
0.5451	10400	0.0	-
0.5478	10450	0.0	-
0.5504	10500	0.0	-
0.5530	10550	0.0	-
0.5556	10600	0.0	-
0.5582	10650	0.0	-
0.5609	10700	0.0	-
0.5635	10750	0.0	-
0.5661	10800	0.0	-
0.5687	10850	0.0	-
0.5713	10900	0.0	-
0.5740	10950	0.0	-
0.5766	11000	0.0	-
0.5792	11050	0.0	-
0.5818	11100	0.0	-
0.5844	11150	0.0	-
0.5871	11200	0.0	-
0.5897	11250	0.0	-
0.5923	11300	0.0	-
0.5949	11350	0.0	-
0.5975	11400	0.0	-
0.6002	11450	0.0	-
0.6028	11500	0.0	-
0.6054	11550	0.0	-
0.6080	11600	0.0	-
0.6107	11650	0.0	-
0.6133	11700	0.0	-
0.6159	11750	0.0	-
0.6185	11800	0.0	-
0.6211	11850	0.0	-
0.6238	11900	0.0	-
0.6264	11950	0.0	-
0.6290	12000	0.0	-
0.6316	12050	0.0	-
0.6342	12100	0.0	-
0.6369	12150	0.0	-
0.6395	12200	0.0	-
0.6421	12250	0.0	-
0.6447	12300	0.0	-
0.6473	12350	0.0	-
0.6500	12400	0.0	-
0.6526	12450	0.0	-
0.6552	12500	0.0	-
0.6578	12550	0.0	-
0.6604	12600	0.0	-
0.6631	12650	0.0	-
0.6657	12700	0.0	-
0.6683	12750	0.0	-
0.6709	12800	0.0	-
0.6736	12850	0.0	-
0.6762	12900	0.0	-
0.6788	12950	0.0	-
0.6814	13000	0.0	-
0.6840	13050	0.0	-
0.6867	13100	0.0	-
0.6893	13150	0.0	-
0.6919	13200	0.0	-
0.6945	13250	0.0	-
0.6971	13300	0.0	-
0.6998	13350	0.0	-
0.7024	13400	0.0	-
0.7050	13450	0.0	-
0.7076	13500	0.0	-
0.7102	13550	0.0	-
0.7129	13600	0.0	-
0.7155	13650	0.0	-
0.7181	13700	0.0	-
0.7207	13750	0.0	-
0.7233	13800	0.0	-
0.7260	13850	0.0	-
0.7286	13900	0.0	-
0.7312	13950	0.0	-
0.7338	14000	0.0	-
0.7365	14050	0.0	-
0.7391	14100	0.0	-
0.7417	14150	0.0	-
0.7443	14200	0.0	-
0.7469	14250	0.0	-
0.7496	14300	0.0	-
0.7522	14350	0.0	-
0.7548	14400	0.0	-
0.7574	14450	0.0	-
0.7600	14500	0.0	-
0.7627	14550	0.0	-
0.7653	14600	0.0	-
0.7679	14650	0.0	-
0.7705	14700	0.0	-
0.7731	14750	0.0	-
0.7758	14800	0.0	-
0.7784	14850	0.0	-
0.7810	14900	0.0	-
0.7836	14950	0.0	-
0.7862	15000	0.0	-
0.7889	15050	0.0	-
0.7915	15100	0.0	-
0.7941	15150	0.0	-
0.7967	15200	0.0	-
0.7994	15250	0.0	-
0.8020	15300	0.0	-
0.8046	15350	0.0	-
0.8072	15400	0.0	-
0.8098	15450	0.0	-
0.8125	15500	0.0	-
0.8151	15550	0.0	-
0.8177	15600	0.0	-
0.8203	15650	0.0	-
0.8229	15700	0.0	-
0.8256	15750	0.0	-
0.8282	15800	0.0	-
0.8308	15850	0.0	-
0.8334	15900	0.0	-
0.8360	15950	0.0	-
0.8387	16000	0.0	-
0.8413	16050	0.0	-
0.8439	16100	0.0	-
0.8465	16150	0.0	-
0.8491	16200	0.0	-
0.8518	16250	0.0	-
0.8544	16300	0.0	-
0.8570	16350	0.0	-
0.8596	16400	0.0	-
0.8622	16450	0.0	-
0.8649	16500	0.0	-
0.8675	16550	0.0	-
0.8701	16600	0.0	-
0.8727	16650	0.0	-
0.8754	16700	0.0	-
0.8780	16750	0.0	-
0.8806	16800	0.0	-
0.8832	16850	0.0	-
0.8858	16900	0.0	-
0.8885	16950	0.0	-
0.8911	17000	0.0	-
0.8937	17050	0.0	-
0.8963	17100	0.0	-
0.8989	17150	0.0	-
0.9016	17200	0.0	-
0.9042	17250	0.0	-
0.9068	17300	0.0	-
0.9094	17350	0.0	-
0.9120	17400	0.0	-
0.9147	17450	0.0	-
0.9173	17500	0.0	-
0.9199	17550	0.0	-
0.9225	17600	0.0	-
0.9251	17650	0.0	-
0.9278	17700	0.0	-
0.9304	17750	0.0	-
0.9330	17800	0.0	-
0.9356	17850	0.0	-
0.9383	17900	0.0	-
0.9409	17950	0.0	-
0.9435	18000	0.0	-
0.9461	18050	0.0	-
0.9487	18100	0.0	-
0.9514	18150	0.0	-
0.9540	18200	0.0	-
0.9566	18250	0.0	-
0.9592	18300	0.0	-
0.9618	18350	0.0	-
0.9645	18400	0.0	-
0.9671	18450	0.0	-
0.9697	18500	0.0	-
0.9723	18550	0.0	-
0.9749	18600	0.0	-
0.9776	18650	0.0	-
0.9802	18700	0.0	-
0.9828	18750	0.0	-
0.9854	18800	0.0	-
0.9880	18850	0.0	-
0.9907	18900	0.0	-
0.9933	18950	0.0	-
0.9959	19000	0.0	-
0.9985	19050	0.0	-
1.0	19078	-	0.0437
1.0012	19100	0.0	-
1.0038	19150	0.0	-
1.0064	19200	0.0	-
1.0090	19250	0.0	-
1.0116	19300	0.0	-
1.0143	19350	0.0	-
1.0169	19400	0.0	-
1.0195	19450	0.3698	-
1.0221	19500	0.1546	-
1.0247	19550	0.0179	-
1.0274	19600	0.0004	-
1.0300	19650	0.0005	-
1.0326	19700	0.0	-
1.0352	19750	0.0002	-
1.0378	19800	0.0	-
1.0405	19850	0.0	-
1.0431	19900	0.0	-
1.0457	19950	0.0002	-
1.0483	20000	0.0011	-
1.0509	20050	0.0	-
1.0536	20100	0.0	-
1.0562	20150	0.0	-
1.0588	20200	0.0003	-
1.0614	20250	0.0	-
1.0641	20300	0.0003	-
1.0667	20350	0.0003	-
1.0693	20400	0.0	-
1.0719	20450	0.0	-
1.0745	20500	0.0	-
1.0772	20550	0.0	-
1.0798	20600	0.0	-
1.0824	20650	0.0	-
1.0850	20700	0.0	-
1.0876	20750	0.0	-
1.0903	20800	0.0	-
1.0929	20850	0.0	-
1.0955	20900	0.0	-
1.0981	20950	0.0	-
1.1007	21000	0.0	-
1.1034	21050	0.0	-
1.1060	21100	0.0	-
1.1086	21150	0.0	-
1.1112	21200	0.0	-
1.1138	21250	0.0	-
1.1165	21300	0.0	-
1.1191	21350	0.0	-
1.1217	21400	0.0	-
1.1243	21450	0.0	-
1.1270	21500	0.0	-
1.1296	21550	0.0	-
1.1322	21600	0.0	-
1.1348	21650	0.0	-
1.1374	21700	0.0	-
1.1401	21750	0.0	-
1.1427	21800	0.0	-
1.1453	21850	0.0	-
1.1479	21900	0.0	-
1.1505	21950	0.0	-
1.1532	22000	0.0	-
1.1558	22050	0.0	-
1.1584	22100	0.0	-
1.1610	22150	0.0	-
1.1636	22200	0.0	-
1.1663	22250	0.0	-
1.1689	22300	0.0	-
1.1715	22350	0.0	-
1.1741	22400	0.0	-
1.1767	22450	0.0	-
1.1794	22500	0.0	-
1.1820	22550	0.0	-
1.1846	22600	0.0	-
1.1872	22650	0.0	-
1.1899	22700	0.0	-
1.1925	22750	0.0	-
1.1951	22800	0.0	-
1.1977	22850	0.0	-
1.2003	22900	0.0	-
1.2030	22950	0.0	-
1.2056	23000	0.0	-
1.2082	23050	0.0	-
1.2108	23100	0.0	-
1.2134	23150	0.0	-
1.2161	23200	0.0	-
1.2187	23250	0.0	-
1.2213	23300	0.0	-
1.2239	23350	0.0	-
1.2265	23400	0.0	-
1.2292	23450	0.0	-
1.2318	23500	0.0	-
1.2344	23550	0.0	-
1.2370	23600	0.0	-
1.2396	23650	0.0	-
1.2423	23700	0.0	-
1.2449	23750	0.0	-
1.2475	23800	0.0	-
1.2501	23850	0.0	-
1.2528	23900	0.0	-
1.2554	23950	0.0	-
1.2580	24000	0.0	-
1.2606	24050	0.0	-
1.2632	24100	0.0	-
1.2659	24150	0.0	-
1.2685	24200	0.0	-
1.2711	24250	0.0	-
1.2737	24300	0.0	-
1.2763	24350	0.0	-
1.2790	24400	0.0	-
1.2816	24450	0.0	-
1.2842	24500	0.0	-
1.2868	24550	0.0	-
1.2894	24600	0.0	-
1.2921	24650	0.0	-
1.2947	24700	0.0	-
1.2973	24750	0.0	-
1.2999	24800	0.0	-
1.3025	24850	0.0	-
1.3052	24900	0.0	-
1.3078	24950	0.0	-
1.3104	25000	0.0	-
1.3130	25050	0.0	-
1.3157	25100	0.0	-
1.3183	25150	0.0	-
1.3209	25200	0.0	-
1.3235	25250	0.0	-
1.3261	25300	0.0	-
1.3288	25350	0.0	-
1.3314	25400	0.0	-
1.3340	25450	0.0	-
1.3366	25500	0.0	-
1.3392	25550	0.0	-
1.3419	25600	0.0	-
1.3445	25650	0.0	-
1.3471	25700	0.0	-
1.3497	25750	0.0	-
1.3523	25800	0.0	-
1.3550	25850	0.0	-
1.3576	25900	0.0	-
1.3602	25950	0.0	-
1.3628	26000	0.0	-
1.3654	26050	0.0	-
1.3681	26100	0.0	-
1.3707	26150	0.0	-
1.3733	26200	0.0	-
1.3759	26250	0.0	-
1.3786	26300	0.0	-
1.3812	26350	0.0	-
1.3838	26400	0.0	-
1.3864	26450	0.0	-
1.3890	26500	0.0	-
1.3917	26550	0.0	-
1.3943	26600	0.0	-
1.3969	26650	0.0	-
1.3995	26700	0.0	-
1.4021	26750	0.0	-
1.4048	26800	0.0	-
1.4074	26850	0.0	-
1.4100	26900	0.0	-
1.4126	26950	0.0	-
1.4152	27000	0.0	-
1.4179	27050	0.0	-
1.4205	27100	0.0	-
1.4231	27150	0.0	-
1.4257	27200	0.0	-
1.4283	27250	0.0	-
1.4310	27300	0.0	-
1.4336	27350	0.0	-
1.4362	27400	0.0	-
1.4388	27450	0.0	-
1.4415	27500	0.0	-
1.4441	27550	0.0	-
1.4467	27600	0.0	-
1.4493	27650	0.0	-
1.4519	27700	0.0	-
1.4546	27750	0.0	-
1.4572	27800	0.0	-
1.4598	27850	0.0	-
1.4624	27900	0.0	-
1.4650	27950	0.0	-
1.4677	28000	0.0	-
1.4703	28050	0.0	-
1.4729	28100	0.0	-
1.4755	28150	0.0	-
1.4781	28200	0.0	-
1.4808	28250	0.0	-
1.4834	28300	0.0	-
1.4860	28350	0.0	-
1.4886	28400	0.0	-
1.4912	28450	0.0	-
1.4939	28500	0.0	-
1.4965	28550	0.0	-
1.4991	28600	0.0	-
1.5017	28650	0.0	-
1.5044	28700	0.0	-
1.5070	28750	0.0	-
1.5096	28800	0.0	-
1.5122	28850	0.0	-
1.5148	28900	0.0	-
1.5175	28950	0.0	-
1.5201	29000	0.0	-
1.5227	29050	0.0	-
1.5253	29100	0.0	-
1.5279	29150	0.0	-
1.5306	29200	0.0	-
1.5332	29250	0.0	-
1.5358	29300	0.0	-
1.5384	29350	0.0	-
1.5410	29400	0.0	-
1.5437	29450	0.0	-
1.5463	29500	0.0	-
1.5489	29550	0.0	-
1.5515	29600	0.0	-
1.5541	29650	0.0	-
1.5568	29700	0.0	-
1.5594	29750	0.0	-
1.5620	29800	0.0	-
1.5646	29850	0.0	-
1.5673	29900	0.0	-
1.5699	29950	0.0	-
1.5725	30000	0.0	-
1.5751	30050	0.0	-
1.5777	30100	0.0	-
1.5804	30150	0.0	-
1.5830	30200	0.0	-
1.5856	30250	0.0	-
1.5882	30300	0.0	-
1.5908	30350	0.0	-
1.5935	30400	0.0	-
1.5961	30450	0.0	-
1.5987	30500	0.0	-
1.6013	30550	0.0	-
1.6039	30600	0.0	-
1.6066	30650	0.0	-
1.6092	30700	0.0	-
1.6118	30750	0.0	-
1.6144	30800	0.0	-
1.6170	30850	0.0	-
1.6197	30900	0.0	-
1.6223	30950	0.0	-
1.6249	31000	0.0	-
1.6275	31050	0.0	-
1.6301	31100	0.0	-
1.6328	31150	0.0	-
1.6354	31200	0.0	-
1.6380	31250	0.0	-
1.6406	31300	0.0	-
1.6433	31350	0.0	-
1.6459	31400	0.0	-
1.6485	31450	0.0	-
1.6511	31500	0.0	-
1.6537	31550	0.0	-
1.6564	31600	0.0	-
1.6590	31650	0.0	-
1.6616	31700	0.0	-
1.6642	31750	0.0	-
1.6668	31800	0.0	-
1.6695	31850	0.0	-
1.6721	31900	0.0	-
1.6747	31950	0.0	-
1.6773	32000	0.0	-
1.6799	32050	0.0	-
1.6826	32100	0.0	-
1.6852	32150	0.0	-
1.6878	32200	0.0	-
1.6904	32250	0.0	-
1.6930	32300	0.0	-
1.6957	32350	0.0	-
1.6983	32400	0.0	-
1.7009	32450	0.0	-
1.7035	32500	0.0	-
1.7062	32550	0.0	-
1.7088	32600	0.0	-
1.7114	32650	0.0	-
1.7140	32700	0.0	-
1.7166	32750	0.0	-
1.7193	32800	0.0	-
1.7219	32850	0.0	-
1.7245	32900	0.0	-
1.7271	32950	0.0	-
1.7297	33000	0.0	-
1.7324	33050	0.0	-
1.7350	33100	0.0	-
1.7376	33150	0.0	-
1.7402	33200	0.0	-
1.7428	33250	0.0	-
1.7455	33300	0.0	-
1.7481	33350	0.0	-
1.7507	33400	0.0	-
1.7533	33450	0.0	-
1.7559	33500	0.0	-
1.7586	33550	0.0	-
1.7612	33600	0.0	-
1.7638	33650	0.0	-
1.7664	33700	0.0	-
1.7691	33750	0.0	-
1.7717	33800	0.0	-
1.7743	33850	0.0	-
1.7769	33900	0.0	-
1.7795	33950	0.0	-
1.7822	34000	0.0	-
1.7848	34050	0.0	-
1.7874	34100	0.0	-
1.7900	34150	0.0	-
1.7926	34200	0.0	-
1.7953	34250	0.0	-
1.7979	34300	0.0	-
1.8005	34350	0.0	-
1.8031	34400	0.0	-
1.8057	34450	0.0	-
1.8084	34500	0.0	-
1.8110	34550	0.0	-
1.8136	34600	0.0	-
1.8162	34650	0.0	-
1.8188	34700	0.0	-
1.8215	34750	0.0	-
1.8241	34800	0.0	-
1.8267	34850	0.0	-
1.8293	34900	0.0	-
1.8320	34950	0.0	-
1.8346	35000	0.0	-
1.8372	35050	0.0	-
1.8398	35100	0.0	-
1.8424	35150	0.0	-
1.8451	35200	0.0	-
1.8477	35250	0.0	-
1.8503	35300	0.0	-
1.8529	35350	0.0	-
1.8555	35400	0.0	-
1.8582	35450	0.0	-
1.8608	35500	0.0	-
1.8634	35550	0.0	-
1.8660	35600	0.0	-
1.8686	35650	0.0	-
1.8713	35700	0.0	-
1.8739	35750	0.0	-
1.8765	35800	0.0	-
1.8791	35850	0.0	-
1.8817	35900	0.0	-
1.8844	35950	0.0	-
1.8870	36000	0.0	-
1.8896	36050	0.0	-
1.8922	36100	0.0	-
1.8949	36150	0.0	-
1.8975	36200	0.0	-
1.9001	36250	0.0	-
1.9027	36300	0.0	-
1.9053	36350	0.0	-
1.9080	36400	0.0	-
1.9106	36450	0.0	-
1.9132	36500	0.0	-
1.9158	36550	0.0	-
1.9184	36600	0.0	-
1.9211	36650	0.0	-
1.9237	36700	0.0	-
1.9263	36750	0.0	-
1.9289	36800	0.0	-
1.9315	36850	0.0	-
1.9342	36900	0.0	-
1.9368	36950	0.0	-
1.9394	37000	0.0	-
1.9420	37050	0.0	-
1.9446	37100	0.0	-
1.9473	37150	0.0	-
1.9499	37200	0.0	-
1.9525	37250	0.0	-
1.9551	37300	0.0	-
1.9578	37350	0.0	-
1.9604	37400	0.0	-
1.9630	37450	0.0	-
1.9656	37500	0.0	-
1.9682	37550	0.0	-
1.9709	37600	0.0	-
1.9735	37650	0.0	-
1.9761	37700	0.0	-
1.9787	37750	0.0	-
1.9813	37800	0.0	-
1.9840	37850	0.0	-
1.9866	37900	0.0	-
1.9892	37950	0.0	-
1.9918	38000	0.0	-
1.9944	38050	0.0	-
1.9971	38100	0.0	-
1.9997	38150	0.0	-
2.0	38156	-	0.0438

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
SetFit: 1.0.1
Sentence Transformers: 2.2.2
Transformers: 4.36.0
PyTorch: 2.0.0
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}
}