README.md

metadata

library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: 인공지능 챗봇 기술 향상에 대한 아이디어가 있는데, 관련된 역시 자세하 정보가 담긴 논문이나 보고서를 찾아줄래요?
  - text: 연구 자료의 서론 부분을 한 줄로 요약해 줄 수 있나요?
  - text: 우리 회사의 HR 정책 개선 방안에 대한 과제를 진행 중이야. 같은 주제의 이전 과제와 어떤 부분에서 왜 중복되었는지 궁금해
  - text: 초전도체의 임계 온도에 관한 연구 자료를 모으고 있어요. 여기에 관련된 유사한 연구나 보고서를 추천받고 싶어요
  - text: >-
      공장에서 발생하는 가스 누출 문제 해결을 위한 시스템을 개발하려고 하는데, 이와 같은 측면에서 진행된 기존 연구나 비슷한 프로젝트가
      있는지 알려주세요
inference: true
model-index:
  - name: SetFit
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9891304347826086
            name: Accuracy

SetFit

This is a SetFit model that can be used for Text Classification. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

• Model Type: SetFit
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 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
오탈자 탐지	'건축 프로젝트 설명 문장에서 오타나 잘못된 맞춤법을 찾아줘.' '경영 보고서 내용에 대한 오탈자를 검토하고 수정해 드릴 수 있을까요?' '경쟁사 분석 항목 내 문장 구성의 오류를 지적해주겠습니까?'
요약	'(특정 논문 제목)의 결론 및 향후 연구 방향에 대해 요점을 정리해 주세요.' '(특정 특허번호)를 기반으로 한 발명의 전체적인 개념을 짧게 설명 부탁드립니다.' '1장의 데이터 수집 기술에 대해 요약해주세요'
유사문서	'5G 통신 모듈 최적화에 관련된 프로젝트를 하고 있는데, 비슷한 내용의 프로젝트나 논문이 있는지 연결해서 말해줄래?' 'AI 기반 헬스케어 솔루션 개발에 관한 문헌 조사를 하고 있습니다. 와 같은 주제를 다룬 문서를 찾아줄 수 있을까요?' 'AI 연산 속도를 최적화하기 위한 반도체 설계 방식을 연구하고 있어. 관련된 유사한 논문이나 보고서를 찾고 싶어'
중복성 검토	'5G 통신망을 기반으로 스마트 시티 구축에 관한 연구를 시작했어. 이와 동일하거나 겹치는 연구 과제나 프로젝트가 있는지 알아봐주고, 이유도 명확하게 밝혀줘' '건물의 내진 설계 강화 방안을 조사하고 있는데 이에 연관된 기존 프로젝트가 무엇이 있는지 그리고 왜 겹치는지 말해줄래?' '고성능 메모리 소자의 내구성을 향상시키는 기술을 개발하고 있어. 이와 비슷한 과제가 이전에 있었는지, 그리고 어떻게 유사하거나 중복되는지 말해줘'
특화 지식정보 제공	'3D 금속 배선 기술(HBM, TSV)의 도입으로 인한 전력 소비 감소 방안에는 어떤 것이 있는가요?' 'AI 워크로드를 처리하기 위한 반도체 아키텍처 설계에서는 어떤 전략들이 사용되나요?' 'LEED 인증의 기준과 획득 과정에 대해 알고 싶습니다.'

Evaluation

Metrics

Label	Accuracy
all	0.9891

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("NTIS/kepri-embedding")
# Run inference
preds = model("연구 자료의 서론 부분을 한 줄로 요약해 줄 수 있나요?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	12.4709	27

Label	Training Sample Count
요약	105
중복성 검토	78
특화 지식정보 제공	106
유사문서	115
오탈자 탐지	95

Training Hyperparameters

• batch_size: (64, 64)
• num_epochs: (10, 10)
• 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
0.0003	1	0.2062	-
0.0161	50	0.2314	-
0.0322	100	0.2008	-
0.0484	150	0.1395	-
0.0645	200	0.11	-
0.0806	250	0.0872	-
0.0967	300	0.0462	-
0.1129	350	0.0188	-
0.1290	400	0.0201	-
0.1451	450	0.025	-
0.1612	500	0.004	-
0.1774	550	0.002	-
0.1935	600	0.0153	-
0.2096	650	0.0011	-
0.2257	700	0.0007	-
0.2419	750	0.0006	-
0.2580	800	0.0006	-
0.2741	850	0.0005	-
0.2902	900	0.0004	-
0.3064	950	0.0005	-
0.3225	1000	0.0002	-
0.3386	1050	0.0002	-
0.3547	1100	0.0003	-
0.3708	1150	0.0002	-
0.3870	1200	0.0002	-
0.4031	1250	0.0002	-
0.4192	1300	0.0001	-
0.4353	1350	0.0002	-
0.4515	1400	0.0001	-
0.4676	1450	0.0001	-
0.4837	1500	0.0001	-
0.4998	1550	0.0001	-
0.5160	1600	0.0001	-
0.5321	1650	0.0001	-
0.5482	1700	0.0001	-
0.5643	1750	0.0001	-
0.5805	1800	0.0001	-
0.5966	1850	0.0001	-
0.6127	1900	0.0001	-
0.6288	1950	0.0001	-
0.6450	2000	0.0001	-
0.6611	2050	0.0001	-
0.6772	2100	0.0001	-
0.6933	2150	0.0001	-
0.7094	2200	0.0001	-
0.7256	2250	0.0001	-
0.7417	2300	0.0001	-
0.7578	2350	0.0001	-
0.7739	2400	0.0001	-
0.7901	2450	0.0001	-
0.8062	2500	0.0001	-
0.8223	2550	0.0001	-
0.8384	2600	0.0	-
0.8546	2650	0.0	-
0.8707	2700	0.0	-
0.8868	2750	0.0001	-
0.9029	2800	0.0	-
0.9191	2850	0.0001	-
0.9352	2900	0.0	-
0.9513	2950	0.0	-
0.9674	3000	0.0	-
0.9836	3050	0.0	-
0.9997	3100	0.0	-
1.0	3101	-	0.0247
1.0158	3150	0.0	-
1.0319	3200	0.0	-
1.0480	3250	0.0	-
1.0642	3300	0.0001	-
1.0803	3350	0.0	-
1.0964	3400	0.0	-
1.1125	3450	0.0	-
1.1287	3500	0.0	-
1.1448	3550	0.0	-
1.1609	3600	0.0	-
1.1770	3650	0.0	-
1.1932	3700	0.0	-
1.2093	3750	0.0	-
1.2254	3800	0.0	-
1.2415	3850	0.0	-
1.2577	3900	0.0	-
1.2738	3950	0.0	-
1.2899	4000	0.0	-
1.3060	4050	0.0	-
1.3222	4100	0.0	-
1.3383	4150	0.0	-
1.3544	4200	0.0	-
1.3705	4250	0.0	-
1.3866	4300	0.0	-
1.4028	4350	0.0	-
1.4189	4400	0.0	-
1.4350	4450	0.0	-
1.4511	4500	0.0	-
1.4673	4550	0.0	-
1.4834	4600	0.0	-
1.4995	4650	0.0	-
1.5156	4700	0.0	-
1.5318	4750	0.0	-
1.5479	4800	0.0	-
1.5640	4850	0.0	-
1.5801	4900	0.0	-
1.5963	4950	0.0	-
1.6124	5000	0.0	-
1.6285	5050	0.0	-
1.6446	5100	0.0	-
1.6608	5150	0.0	-
1.6769	5200	0.0	-
1.6930	5250	0.0	-
1.7091	5300	0.0	-
1.7252	5350	0.0	-
1.7414	5400	0.0	-
1.7575	5450	0.0	-
1.7736	5500	0.0	-
1.7897	5550	0.0	-
1.8059	5600	0.0	-
1.8220	5650	0.0	-
1.8381	5700	0.0	-
1.8542	5750	0.0	-
1.8704	5800	0.0	-
1.8865	5850	0.0	-
1.9026	5900	0.0	-
1.9187	5950	0.0	-
1.9349	6000	0.0	-
1.9510	6050	0.0	-
1.9671	6100	0.0	-
1.9832	6150	0.0	-
1.9994	6200	0.0	-
2.0	6202	-	0.0262
2.0155	6250	0.0	-
2.0316	6300	0.0	-
2.0477	6350	0.0	-
2.0639	6400	0.0	-
2.0800	6450	0.0	-
2.0961	6500	0.0	-
2.1122	6550	0.0	-
2.1283	6600	0.0	-
2.1445	6650	0.0	-
2.1606	6700	0.0	-
2.1767	6750	0.0	-
2.1928	6800	0.0	-
2.2090	6850	0.0	-
2.2251	6900	0.0	-
2.2412	6950	0.0	-
2.2573	7000	0.0	-
2.2735	7050	0.0	-
2.2896	7100	0.0	-
2.3057	7150	0.0	-
2.3218	7200	0.0	-
2.3380	7250	0.0	-
2.3541	7300	0.0	-
2.3702	7350	0.0	-
2.3863	7400	0.0	-
2.4025	7450	0.0	-
2.4186	7500	0.0	-
2.4347	7550	0.0	-
2.4508	7600	0.0	-
2.4669	7650	0.0	-
2.4831	7700	0.0	-
2.4992	7750	0.0	-
2.5153	7800	0.0	-
2.5314	7850	0.0	-
2.5476	7900	0.0	-
2.5637	7950	0.0	-
2.5798	8000	0.0	-
2.5959	8050	0.0	-
2.6121	8100	0.0	-
2.6282	8150	0.0	-
2.6443	8200	0.0	-
2.6604	8250	0.0	-
2.6766	8300	0.0	-
2.6927	8350	0.0	-
2.7088	8400	0.0	-
2.7249	8450	0.0	-
2.7411	8500	0.0	-
2.7572	8550	0.0	-
2.7733	8600	0.0	-
2.7894	8650	0.0	-
2.8055	8700	0.0	-
2.8217	8750	0.0	-
2.8378	8800	0.0	-
2.8539	8850	0.0	-
2.8700	8900	0.0	-
2.8862	8950	0.0	-
2.9023	9000	0.0	-
2.9184	9050	0.0	-
2.9345	9100	0.0	-
2.9507	9150	0.0	-
2.9668	9200	0.0	-
2.9829	9250	0.0	-
2.9990	9300	0.0	-
3.0	9303	-	0.025
3.0152	9350	0.0	-
3.0313	9400	0.0	-
3.0474	9450	0.0	-
3.0635	9500	0.0	-
3.0797	9550	0.0	-
3.0958	9600	0.0	-
3.1119	9650	0.0	-
3.1280	9700	0.0	-
3.1441	9750	0.0	-
3.1603	9800	0.0	-
3.1764	9850	0.0	-
3.1925	9900	0.0	-
3.2086	9950	0.0	-
3.2248	10000	0.0	-
3.2409	10050	0.0	-
3.2570	10100	0.0	-
3.2731	10150	0.0	-
3.2893	10200	0.0	-
3.3054	10250	0.0	-
3.3215	10300	0.0	-
3.3376	10350	0.0	-
3.3538	10400	0.0	-
3.3699	10450	0.0	-
3.3860	10500	0.0	-
3.4021	10550	0.0	-
3.4183	10600	0.0	-
3.4344	10650	0.0	-
3.4505	10700	0.0	-
3.4666	10750	0.0083	-
3.4827	10800	0.0019	-
3.4989	10850	0.0001	-
3.5150	10900	0.0	-
3.5311	10950	0.001	-
3.5472	11000	0.0	-
3.5634	11050	0.0	-
3.5795	11100	0.0	-
3.5956	11150	0.0	-
3.6117	11200	0.0	-
3.6279	11250	0.0	-
3.6440	11300	0.0	-
3.6601	11350	0.0	-
3.6762	11400	0.0	-
3.6924	11450	0.0	-
3.7085	11500	0.0	-
3.7246	11550	0.0	-
3.7407	11600	0.0	-
3.7569	11650	0.0	-
3.7730	11700	0.0	-
3.7891	11750	0.0	-
3.8052	11800	0.0	-
3.8213	11850	0.0	-
3.8375	11900	0.0	-
3.8536	11950	0.0	-
3.8697	12000	0.0	-
3.8858	12050	0.0	-
3.9020	12100	0.0	-
3.9181	12150	0.0	-
3.9342	12200	0.0	-
3.9503	12250	0.0	-
3.9665	12300	0.0	-
3.9826	12350	0.0	-
3.9987	12400	0.0	-
4.0	12404	-	0.0253
4.0148	12450	0.0	-
4.0310	12500	0.0	-
4.0471	12550	0.0	-
4.0632	12600	0.0	-
4.0793	12650	0.0	-
4.0955	12700	0.0	-
4.1116	12750	0.0	-
4.1277	12800	0.0	-
4.1438	12850	0.0	-
4.1599	12900	0.0	-
4.1761	12950	0.0	-
4.1922	13000	0.0	-
4.2083	13050	0.0	-
4.2244	13100	0.0	-
4.2406	13150	0.0	-
4.2567	13200	0.0	-
4.2728	13250	0.0	-
4.2889	13300	0.0	-
4.3051	13350	0.0	-
4.3212	13400	0.0	-
4.3373	13450	0.0	-
4.3534	13500	0.0	-
4.3696	13550	0.0	-
4.3857	13600	0.0	-
4.4018	13650	0.0	-
4.4179	13700	0.0	-
4.4341	13750	0.0	-
4.4502	13800	0.0	-
4.4663	13850	0.0	-
4.4824	13900	0.0	-
4.4985	13950	0.0	-
4.5147	14000	0.0	-
4.5308	14050	0.0	-
4.5469	14100	0.0	-
4.5630	14150	0.0	-
4.5792	14200	0.0	-
4.5953	14250	0.0	-
4.6114	14300	0.0	-
4.6275	14350	0.0	-
4.6437	14400	0.0	-
4.6598	14450	0.0	-
4.6759	14500	0.0	-
4.6920	14550	0.0	-
4.7082	14600	0.0	-
4.7243	14650	0.0	-
4.7404	14700	0.0	-
4.7565	14750	0.0	-
4.7727	14800	0.0	-
4.7888	14850	0.0	-
4.8049	14900	0.0	-
4.8210	14950	0.0	-
4.8371	15000	0.0	-
4.8533	15050	0.0	-
4.8694	15100	0.0	-
4.8855	15150	0.0	-
4.9016	15200	0.0	-
4.9178	15250	0.0	-
4.9339	15300	0.0	-
4.9500	15350	0.0	-
4.9661	15400	0.0	-
4.9823	15450	0.0	-
4.9984	15500	0.0	-
5.0	15505	-	0.0259
5.0145	15550	0.0	-
5.0306	15600	0.0	-
5.0468	15650	0.0	-
5.0629	15700	0.0	-
5.0790	15750	0.0	-
5.0951	15800	0.0	-
5.1113	15850	0.0	-
5.1274	15900	0.0	-
5.1435	15950	0.0	-
5.1596	16000	0.0	-
5.1757	16050	0.0	-
5.1919	16100	0.0	-
5.2080	16150	0.0	-
5.2241	16200	0.0	-
5.2402	16250	0.0	-
5.2564	16300	0.0	-
5.2725	16350	0.0	-
5.2886	16400	0.0	-
5.3047	16450	0.0	-
5.3209	16500	0.0	-
5.3370	16550	0.0	-
5.3531	16600	0.0	-
5.3692	16650	0.0	-
5.3854	16700	0.0	-
5.4015	16750	0.0	-
5.4176	16800	0.0	-
5.4337	16850	0.0	-
5.4499	16900	0.0	-
5.4660	16950	0.0	-
5.4821	17000	0.0	-
5.4982	17050	0.0	-
5.5144	17100	0.0	-
5.5305	17150	0.0	-
5.5466	17200	0.0	-
5.5627	17250	0.0	-
5.5788	17300	0.0	-
5.5950	17350	0.0	-
5.6111	17400	0.0	-
5.6272	17450	0.0	-
5.6433	17500	0.0	-
5.6595	17550	0.0	-
5.6756	17600	0.0	-
5.6917	17650	0.0	-
5.7078	17700	0.0	-
5.7240	17750	0.0	-
5.7401	17800	0.0	-
5.7562	17850	0.0	-
5.7723	17900	0.0	-
5.7885	17950	0.0	-
5.8046	18000	0.0	-
5.8207	18050	0.0	-
5.8368	18100	0.0	-
5.8530	18150	0.0	-
5.8691	18200	0.0	-
5.8852	18250	0.0	-
5.9013	18300	0.0	-
5.9174	18350	0.0	-
5.9336	18400	0.0	-
5.9497	18450	0.0	-
5.9658	18500	0.0	-
5.9819	18550	0.0	-
5.9981	18600	0.0	-
6.0	18606	-	0.0255
6.0142	18650	0.0	-
6.0303	18700	0.0	-
6.0464	18750	0.0	-
6.0626	18800	0.0	-
6.0787	18850	0.0	-
6.0948	18900	0.0	-
6.1109	18950	0.0	-
6.1271	19000	0.0	-
6.1432	19050	0.0	-
6.1593	19100	0.0	-
6.1754	19150	0.0	-
6.1916	19200	0.0	-
6.2077	19250	0.0	-
6.2238	19300	0.0	-
6.2399	19350	0.0	-
6.2560	19400	0.0	-
6.2722	19450	0.0	-
6.2883	19500	0.0	-
6.3044	19550	0.0	-
6.3205	19600	0.0	-
6.3367	19650	0.0	-
6.3528	19700	0.0	-
6.3689	19750	0.0	-
6.3850	19800	0.0	-
6.4012	19850	0.0	-
6.4173	19900	0.0	-
6.4334	19950	0.0	-
6.4495	20000	0.0	-
6.4657	20050	0.0	-
6.4818	20100	0.0	-
6.4979	20150	0.0	-
6.5140	20200	0.0	-
6.5302	20250	0.0	-
6.5463	20300	0.0	-
6.5624	20350	0.0	-
6.5785	20400	0.0	-
6.5946	20450	0.0	-
6.6108	20500	0.0	-
6.6269	20550	0.0	-
6.6430	20600	0.0	-
6.6591	20650	0.0	-
6.6753	20700	0.0	-
6.6914	20750	0.0	-
6.7075	20800	0.0	-
6.7236	20850	0.0	-
6.7398	20900	0.0	-
6.7559	20950	0.0	-
6.7720	21000	0.0	-
6.7881	21050	0.0	-
6.8043	21100	0.0	-
6.8204	21150	0.0	-
6.8365	21200	0.0	-
6.8526	21250	0.0	-
6.8688	21300	0.0	-
6.8849	21350	0.0	-
6.9010	21400	0.0	-
6.9171	21450	0.0	-
6.9332	21500	0.0	-
6.9494	21550	0.0	-
6.9655	21600	0.0	-
6.9816	21650	0.0	-
6.9977	21700	0.0	-
7.0	21707	-	0.0264
7.0139	21750	0.0	-
7.0300	21800	0.0	-
7.0461	21850	0.0	-
7.0622	21900	0.0	-
7.0784	21950	0.0	-
7.0945	22000	0.0	-
7.1106	22050	0.0	-
7.1267	22100	0.0	-
7.1429	22150	0.0	-
7.1590	22200	0.0	-
7.1751	22250	0.0	-
7.1912	22300	0.0	-
7.2074	22350	0.0	-
7.2235	22400	0.0	-
7.2396	22450	0.0	-
7.2557	22500	0.0	-
7.2718	22550	0.0	-
7.2880	22600	0.0	-
7.3041	22650	0.0	-
7.3202	22700	0.0	-
7.3363	22750	0.0	-
7.3525	22800	0.0	-
7.3686	22850	0.0	-
7.3847	22900	0.0	-
7.4008	22950	0.0	-
7.4170	23000	0.0	-
7.4331	23050	0.0	-
7.4492	23100	0.0	-
7.4653	23150	0.0	-
7.4815	23200	0.0	-
7.4976	23250	0.0	-
7.5137	23300	0.0	-
7.5298	23350	0.0	-
7.5460	23400	0.0	-
7.5621	23450	0.0	-
7.5782	23500	0.0	-
7.5943	23550	0.0	-
7.6104	23600	0.0	-
7.6266	23650	0.0	-
7.6427	23700	0.0	-
7.6588	23750	0.0	-
7.6749	23800	0.0	-
7.6911	23850	0.0	-
7.7072	23900	0.0	-
7.7233	23950	0.0	-
7.7394	24000	0.0	-
7.7556	24050	0.0	-
7.7717	24100	0.0	-
7.7878	24150	0.0	-
7.8039	24200	0.0	-
7.8201	24250	0.0	-
7.8362	24300	0.0	-
7.8523	24350	0.0	-
7.8684	24400	0.0	-
7.8846	24450	0.0	-
7.9007	24500	0.0	-
7.9168	24550	0.0	-
7.9329	24600	0.0	-
7.9490	24650	0.0	-
7.9652	24700	0.0	-
7.9813	24750	0.0	-
7.9974	24800	0.0	-
8.0	24808	-	0.0252
8.0135	24850	0.0	-
8.0297	24900	0.0	-
8.0458	24950	0.0	-
8.0619	25000	0.0	-
8.0780	25050	0.0	-
8.0942	25100	0.0	-
8.1103	25150	0.0	-
8.1264	25200	0.0	-
8.1425	25250	0.0	-
8.1587	25300	0.0	-
8.1748	25350	0.0	-
8.1909	25400	0.0	-
8.2070	25450	0.0	-
8.2232	25500	0.0	-
8.2393	25550	0.0	-
8.2554	25600	0.0	-
8.2715	25650	0.0	-
8.2876	25700	0.0	-
8.3038	25750	0.0	-
8.3199	25800	0.0	-
8.3360	25850	0.0	-
8.3521	25900	0.0	-
8.3683	25950	0.0	-
8.3844	26000	0.0	-
8.4005	26050	0.0	-
8.4166	26100	0.0	-
8.4328	26150	0.0	-
8.4489	26200	0.0	-
8.4650	26250	0.0	-
8.4811	26300	0.0	-
8.4973	26350	0.0	-
8.5134	26400	0.0	-
8.5295	26450	0.0	-
8.5456	26500	0.0	-
8.5618	26550	0.0	-
8.5779	26600	0.0	-
8.5940	26650	0.0	-
8.6101	26700	0.0	-
8.6262	26750	0.0	-
8.6424	26800	0.0	-
8.6585	26850	0.0	-
8.6746	26900	0.0	-
8.6907	26950	0.0	-
8.7069	27000	0.0	-
8.7230	27050	0.0	-
8.7391	27100	0.0	-
8.7552	27150	0.0	-
8.7714	27200	0.0	-
8.7875	27250	0.0	-
8.8036	27300	0.0	-
8.8197	27350	0.0	-
8.8359	27400	0.0	-
8.8520	27450	0.0	-
8.8681	27500	0.0	-
8.8842	27550	0.0	-
8.9004	27600	0.0	-
8.9165	27650	0.0	-
8.9326	27700	0.0	-
8.9487	27750	0.0	-
8.9649	27800	0.0	-
8.9810	27850	0.0	-
8.9971	27900	0.0	-
9.0	27909	-	0.0255
9.0132	27950	0.0	-
9.0293	28000	0.0	-
9.0455	28050	0.0	-
9.0616	28100	0.0	-
9.0777	28150	0.0	-
9.0938	28200	0.0	-
9.1100	28250	0.0	-
9.1261	28300	0.0	-
9.1422	28350	0.0	-
9.1583	28400	0.0	-
9.1745	28450	0.0	-
9.1906	28500	0.0	-
9.2067	28550	0.0	-
9.2228	28600	0.0	-
9.2390	28650	0.0	-
9.2551	28700	0.0	-
9.2712	28750	0.0	-
9.2873	28800	0.0	-
9.3035	28850	0.0	-
9.3196	28900	0.0	-
9.3357	28950	0.0	-
9.3518	29000	0.0	-
9.3679	29050	0.0	-
9.3841	29100	0.0	-
9.4002	29150	0.0	-
9.4163	29200	0.0	-
9.4324	29250	0.0	-
9.4486	29300	0.0	-
9.4647	29350	0.0	-
9.4808	29400	0.0	-
9.4969	29450	0.0	-
9.5131	29500	0.0	-
9.5292	29550	0.0	-
9.5453	29600	0.0	-
9.5614	29650	0.0	-
9.5776	29700	0.0	-
9.5937	29750	0.0	-
9.6098	29800	0.0	-
9.6259	29850	0.0	-
9.6421	29900	0.0	-
9.6582	29950	0.0	-
9.6743	30000	0.0	-
9.6904	30050	0.0	-
9.7065	30100	0.0	-
9.7227	30150	0.0	-
9.7388	30200	0.0	-
9.7549	30250	0.0	-
9.7710	30300	0.0	-
9.7872	30350	0.0	-
9.8033	30400	0.0	-
9.8194	30450	0.0	-
9.8355	30500	0.0	-
9.8517	30550	0.0	-
9.8678	30600	0.0	-
9.8839	30650	0.0	-
9.9000	30700	0.0	-
9.9162	30750	0.0	-
9.9323	30800	0.0	-
9.9484	30850	0.0	-
9.9645	30900	0.0	-
9.9807	30950	0.0	-
9.9968	31000	0.0	-
10.0	31010	-	0.0264

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.9.18
• SetFit: 1.0.3
• Sentence Transformers: 2.2.1
• Transformers: 4.32.1
• PyTorch: 1.10.0
• Datasets: 2.20.0
• Tokenizers: 0.13.3

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}
}