Amadeus99/indonesia-election-sentiment-classification-setfit-2

SetFit with indolem/indobertweet-base-uncased

This is a SetFit model that can be used for Text Classification. This SetFit model uses indolem/indobertweet-base-uncased 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:

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
• Sentence Transformer body: indolem/indobertweet-base-uncased
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 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
positif	'prabowo emang vibe leader yang inspiratif, perbuatannya bener-bener kece! #02untukmelanjutkan buktinyata tiadahenti' 'prabowo turut berperan aktif dalam menggalang donasi untuk palestina. #02untukmelanjutkan buktinyata tiadahenti' 'yuli mengaku bahagia bertemu prabowo dan tidak ingin testimoninya menjadi bahan untuk menjelekkan prabowo. #indonesiasentris #indonesiahijau #02melanjutkan #anakmudaindonesiaemas prabowo subianto'
negatif	'gila, nyesel gw 2019 milih prabowo, tau gitu gw golput aja, untungnya dia kalah, kalau prabowo kepilih gw jadi salah satu investor kerusakan negara ini 🥺 [re sgumilang6938]' 'tkd prabowo-gibran bakal laporkan pencopotan spanduk di monumen welcome to batam' 'bagusnya sih asal bukan prabowo, asal bukan dinasti jokowi, asal bukan pdip dan asal bukan surya paloh, tp mau gmn lagi, demokrasi kita terlalu sempurna diciptakan untuk mereka..'
netral	'prabowo, guyonannya khas, politik jadi lebih berwarna' 'prabowo-sby-ahy di aceh, kenang 19 tahun bencana tsunami.. ]mv pdemokrat agusyudhoyono demokrat bersama rakyat' 'prabowo: saya sudah buktikan komitmen pada demokrasi, dulu dituduh kudeta tapi tidak dilakukan #klynews'

Evaluation

Metrics

Label	Accuracy	F1
all	0.7008	0.6938

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("Amadeus99/indonesia-election-sentiment-classification-setfit-2")
# Run inference
preds = model("mahfud md dan ganjar pranowo, pasangan yang mengemban harapan rakyat gan 💫 jar mahfud hebat #coblos3 #3gm #dulujokowisekarangganjar kitamasbowo dangbran")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	25.1867	210

Label	Training Sample Count
negatif	136
netral	72
positif	92

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (7, 7)
• 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	0.2802	-
0.0069	50	0.3051	-
0.0138	100	0.2732	-
0.0207	150	0.2572	-
0.0277	200	0.2471	-
0.0346	250	0.2664	-
0.0415	300	0.2334	-
0.0484	350	0.2553	-
0.0553	400	0.3072	-
0.0622	450	0.2105	-
0.0691	500	0.2945	-
0.0761	550	0.164	-
0.0830	600	0.2292	-
0.0899	650	0.2509	-
0.0968	700	0.2135	-
0.1037	750	0.2488	-
0.1106	800	0.2846	-
0.1175	850	0.136	-
0.1244	900	0.1469	-
0.1314	950	0.2906	-
0.1383	1000	0.1579	-
0.1452	1050	0.1475	-
0.1521	1100	0.0884	-
0.1590	1150	0.0811	-
0.1659	1200	0.2272	-
0.1728	1250	0.1325	-
0.1798	1300	0.1237	-
0.1867	1350	0.1306	-
0.1936	1400	0.0541	-
0.2005	1450	0.0482	-
0.2074	1500	0.016	-
0.2143	1550	0.0388	-
0.2212	1600	0.0168	-
0.2282	1650	0.0042	-
0.2351	1700	0.004	-
0.2420	1750	0.0016	-
0.2489	1800	0.0006	-
0.2558	1850	0.001	-
0.2627	1900	0.0009	-
0.2696	1950	0.0006	-
0.2765	2000	0.0007	-
0.2835	2050	0.0003	-
0.2904	2100	0.0002	-
0.2973	2150	0.0004	-
0.3042	2200	0.0001	-
0.3111	2250	0.0008	-
0.3180	2300	0.0001	-
0.3249	2350	0.0003	-
0.3319	2400	0.0008	-
0.3388	2450	0.0001	-
0.3457	2500	0.0002	-
0.3526	2550	0.0001	-
0.3595	2600	0.0002	-
0.3664	2650	0.0001	-
0.3733	2700	0.0001	-
0.3803	2750	0.0001	-
0.3872	2800	0.0001	-
0.3941	2850	0.0001	-
0.4010	2900	0.0001	-
0.4079	2950	0.0002	-
0.4148	3000	0.0001	-
0.4217	3050	0.0002	-
0.4287	3100	0.0001	-
0.4356	3150	0.0001	-
0.4425	3200	0.0001	-
0.4494	3250	0.0001	-
0.4563	3300	0.0001	-
0.4632	3350	0.0001	-
0.4701	3400	0.0001	-
0.4770	3450	0.0001	-
0.4840	3500	0.0001	-
0.4909	3550	0.0001	-
0.4978	3600	0.0001	-
0.5047	3650	0.0001	-
0.5116	3700	0.0001	-
0.5185	3750	0.0	-
0.5254	3800	0.0001	-
0.5324	3850	0.0	-
0.5393	3900	0.0001	-
0.5462	3950	0.0	-
0.5531	4000	0.0	-
0.5600	4050	0.0	-
0.5669	4100	0.0001	-
0.5738	4150	0.0	-
0.5808	4200	0.0	-
0.5877	4250	0.0001	-
0.5946	4300	0.0001	-
0.6015	4350	0.0292	-
0.6084	4400	0.0002	-
0.6153	4450	0.0003	-
0.6222	4500	0.0512	-
0.6291	4550	0.0001	-
0.6361	4600	0.001	-
0.6430	4650	0.0001	-
0.6499	4700	0.0002	-
0.6568	4750	0.0001	-
0.6637	4800	0.0001	-
0.6706	4850	0.0001	-
0.6775	4900	0.0	-
0.6845	4950	0.0001	-
0.6914	5000	0.0	-
0.6983	5050	0.0	-
0.7052	5100	0.0	-
0.7121	5150	0.0	-
0.7190	5200	0.0	-
0.7259	5250	0.0	-
0.7329	5300	0.0	-
0.7398	5350	0.0	-
0.7467	5400	0.0	-
0.7536	5450	0.0	-
0.7605	5500	0.0	-
0.7674	5550	0.0001	-
0.7743	5600	0.0	-
0.7812	5650	0.0	-
0.7882	5700	0.0	-
0.7951	5750	0.0	-
0.8020	5800	0.0	-
0.8089	5850	0.0	-
0.8158	5900	0.0	-
0.8227	5950	0.0	-
0.8296	6000	0.0	-
0.8366	6050	0.0	-
0.8435	6100	0.0	-
0.8504	6150	0.0	-
0.8573	6200	0.0	-
0.8642	6250	0.0	-
0.8711	6300	0.0	-
0.8780	6350	0.0	-
0.8850	6400	0.0	-
0.8919	6450	0.0	-
0.8988	6500	0.0	-
0.9057	6550	0.0	-
0.9126	6600	0.0	-
0.9195	6650	0.0	-
0.9264	6700	0.0	-
0.9334	6750	0.0	-
0.9403	6800	0.0	-
0.9472	6850	0.0	-
0.9541	6900	0.0	-
0.9610	6950	0.0	-
0.9679	7000	0.0	-
0.9748	7050	0.0	-
0.9817	7100	0.0	-
0.9887	7150	0.0	-
0.9956	7200	0.0	-
1.0	7232	-	0.34
1.0025	7250	0.0	-
1.0094	7300	0.0	-
1.0163	7350	0.0	-
1.0232	7400	0.0	-
1.0301	7450	0.0	-
1.0371	7500	0.0	-
1.0440	7550	0.0	-
1.0509	7600	0.0	-
1.0578	7650	0.0	-
1.0647	7700	0.0	-
1.0716	7750	0.0	-
1.0785	7800	0.0	-
1.0855	7850	0.0	-
1.0924	7900	0.0	-
1.0993	7950	0.0	-
1.1062	8000	0.0	-
1.1131	8050	0.0	-
1.1200	8100	0.0	-
1.1269	8150	0.0	-
1.1338	8200	0.0	-
1.1408	8250	0.0	-
1.1477	8300	0.0	-
1.1546	8350	0.0	-
1.1615	8400	0.0	-
1.1684	8450	0.0	-
1.1753	8500	0.0	-
1.1822	8550	0.0	-
1.1892	8600	0.0	-
1.1961	8650	0.0	-
1.2030	8700	0.0	-
1.2099	8750	0.0	-
1.2168	8800	0.0	-
1.2237	8850	0.0	-
1.2306	8900	0.0	-
1.2376	8950	0.0	-
1.2445	9000	0.0	-
1.2514	9050	0.0	-
1.2583	9100	0.0	-
1.2652	9150	0.0	-
1.2721	9200	0.0	-
1.2790	9250	0.0	-
1.2860	9300	0.0	-
1.2929	9350	0.0	-
1.2998	9400	0.0	-
1.3067	9450	0.0	-
1.3136	9500	0.0	-
1.3205	9550	0.0	-
1.3274	9600	0.0	-
1.3343	9650	0.0	-
1.3413	9700	0.0	-
1.3482	9750	0.0	-
1.3551	9800	0.0	-
1.3620	9850	0.0	-
1.3689	9900	0.0	-
1.3758	9950	0.0	-
1.3827	10000	0.0	-
1.3897	10050	0.0	-
1.3966	10100	0.0	-
1.4035	10150	0.0	-
1.4104	10200	0.0	-
1.4173	10250	0.0	-
1.4242	10300	0.0	-
1.4311	10350	0.0	-
1.4381	10400	0.0	-
1.4450	10450	0.0	-
1.4519	10500	0.0	-
1.4588	10550	0.0	-
1.4657	10600	0.0	-
1.4726	10650	0.0	-
1.4795	10700	0.0	-
1.4864	10750	0.0	-
1.4934	10800	0.0	-
1.5003	10850	0.0	-
1.5072	10900	0.0	-
1.5141	10950	0.0	-
1.5210	11000	0.2258	-
1.5279	11050	0.0281	-
1.5348	11100	0.0133	-
1.5418	11150	0.0016	-
1.5487	11200	0.0003	-
1.5556	11250	0.0003	-
1.5625	11300	0.0003	-
1.5694	11350	0.0001	-
1.5763	11400	0.0001	-
1.5832	11450	0.0001	-
1.5902	11500	0.0	-
1.5971	11550	0.0	-
1.6040	11600	0.0001	-
1.6109	11650	0.0	-
1.6178	11700	0.0001	-
1.6247	11750	0.0	-
1.6316	11800	0.0001	-
1.6386	11850	0.0	-
1.6455	11900	0.0	-
1.6524	11950	0.0001	-
1.6593	12000	0.0	-
1.6662	12050	0.0	-
1.6731	12100	0.0	-
1.6800	12150	0.0	-
1.6869	12200	0.0	-
1.6939	12250	0.0	-
1.7008	12300	0.0	-
1.7077	12350	0.0	-
1.7146	12400	0.0	-
1.7215	12450	0.0	-
1.7284	12500	0.0	-
1.7353	12550	0.0	-
1.7423	12600	0.0	-
1.7492	12650	0.0	-
1.7561	12700	0.0001	-
1.7630	12750	0.0	-
1.7699	12800	0.0	-
1.7768	12850	0.0	-
1.7837	12900	0.0001	-
1.7907	12950	0.0	-
1.7976	13000	0.0	-
1.8045	13050	0.0	-
1.8114	13100	0.0	-
1.8183	13150	0.0	-
1.8252	13200	0.0	-
1.8321	13250	0.0	-
1.8390	13300	0.0	-
1.8460	13350	0.0	-
1.8529	13400	0.0	-
1.8598	13450	0.0	-
1.8667	13500	0.0	-
1.8736	13550	0.0	-
1.8805	13600	0.0	-
1.8874	13650	0.0	-
1.8944	13700	0.0	-
1.9013	13750	0.0	-
1.9082	13800	0.0	-
1.9151	13850	0.0	-
1.9220	13900	0.0	-
1.9289	13950	0.0001	-
1.9358	14000	0.0	-
1.9428	14050	0.0	-
1.9497	14100	0.0	-
1.9566	14150	0.0	-
1.9635	14200	0.0	-
1.9704	14250	0.0	-
1.9773	14300	0.0	-
1.9842	14350	0.0	-
1.9912	14400	0.0	-
1.9981	14450	0.0	-
2.0	14464	-	0.3175
2.0050	14500	0.0	-
2.0119	14550	0.0	-
2.0188	14600	0.0	-
2.0257	14650	0.0	-
2.0326	14700	0.0	-
2.0395	14750	0.0	-
2.0465	14800	0.0	-
2.0534	14850	0.0	-
2.0603	14900	0.0	-
2.0672	14950	0.0	-
2.0741	15000	0.0	-
2.0810	15050	0.0	-
2.0879	15100	0.0	-
2.0949	15150	0.0	-
2.1018	15200	0.0	-
2.1087	15250	0.0	-
2.1156	15300	0.0	-
2.1225	15350	0.0	-
2.1294	15400	0.0	-
2.1363	15450	0.0	-
2.1433	15500	0.0	-
2.1502	15550	0.0	-
2.1571	15600	0.0	-
2.1640	15650	0.0	-
2.1709	15700	0.0	-
2.1778	15750	0.0	-
2.1847	15800	0.0	-
2.1916	15850	0.0	-
2.1986	15900	0.0	-
2.2055	15950	0.0	-
2.2124	16000	0.0	-
2.2193	16050	0.0	-
2.2262	16100	0.0	-
2.2331	16150	0.0	-
2.2400	16200	0.0	-
2.2470	16250	0.0	-
2.2539	16300	0.0	-
2.2608	16350	0.0	-
2.2677	16400	0.0	-
2.2746	16450	0.0	-
2.2815	16500	0.0	-
2.2884	16550	0.0	-
2.2954	16600	0.0	-
2.3023	16650	0.0	-
2.3092	16700	0.0	-
2.3161	16750	0.0	-
2.3230	16800	0.0	-
2.3299	16850	0.0	-
2.3368	16900	0.0	-
2.3438	16950	0.0	-
2.3507	17000	0.0	-
2.3576	17050	0.0	-
2.3645	17100	0.0	-
2.3714	17150	0.0	-
2.3783	17200	0.0	-
2.3852	17250	0.0	-
2.3921	17300	0.0	-
2.3991	17350	0.0	-
2.4060	17400	0.0	-
2.4129	17450	0.0	-
2.4198	17500	0.0	-
2.4267	17550	0.0	-
2.4336	17600	0.0	-
2.4405	17650	0.0	-
2.4475	17700	0.0	-
2.4544	17750	0.0	-
2.4613	17800	0.0	-
2.4682	17850	0.0	-
2.4751	17900	0.0	-
2.4820	17950	0.0	-
2.4889	18000	0.0	-
2.4959	18050	0.0	-
2.5028	18100	0.0	-
2.5097	18150	0.0	-
2.5166	18200	0.0	-
2.5235	18250	0.0	-
2.5304	18300	0.0	-
2.5373	18350	0.0	-
2.5442	18400	0.0	-
2.5512	18450	0.0	-
2.5581	18500	0.0	-
2.5650	18550	0.0	-
2.5719	18600	0.0	-
2.5788	18650	0.0	-
2.5857	18700	0.0	-
2.5926	18750	0.0	-
2.5996	18800	0.0	-
2.6065	18850	0.0	-
2.6134	18900	0.0	-
2.6203	18950	0.0	-
2.6272	19000	0.0	-
2.6341	19050	0.0	-
2.6410	19100	0.0	-
2.6480	19150	0.0	-
2.6549	19200	0.0	-
2.6618	19250	0.0	-
2.6687	19300	0.0	-
2.6756	19350	0.0	-
2.6825	19400	0.0	-
2.6894	19450	0.0	-
2.6963	19500	0.0	-
2.7033	19550	0.0	-
2.7102	19600	0.0	-
2.7171	19650	0.0	-
2.7240	19700	0.0	-
2.7309	19750	0.0	-
2.7378	19800	0.0	-
2.7447	19850	0.0	-
2.7517	19900	0.0	-
2.7586	19950	0.0	-
2.7655	20000	0.0	-
2.7724	20050	0.0	-
2.7793	20100	0.0	-
2.7862	20150	0.0	-
2.7931	20200	0.0	-
2.8001	20250	0.0	-
2.8070	20300	0.0	-
2.8139	20350	0.0	-
2.8208	20400	0.0	-
2.8277	20450	0.0	-
2.8346	20500	0.0	-
2.8415	20550	0.0	-
2.8485	20600	0.0	-
2.8554	20650	0.0	-
2.8623	20700	0.0	-
2.8692	20750	0.0	-
2.8761	20800	0.0	-
2.8830	20850	0.0	-
2.8899	20900	0.0	-
2.8968	20950	0.0	-
2.9038	21000	0.0	-
2.9107	21050	0.0	-
2.9176	21100	0.0	-
2.9245	21150	0.0	-
2.9314	21200	0.0	-
2.9383	21250	0.0	-
2.9452	21300	0.0	-
2.9522	21350	0.0	-
2.9591	21400	0.0	-
2.9660	21450	0.0	-
2.9729	21500	0.0	-
2.9798	21550	0.0	-
2.9867	21600	0.0	-
2.9936	21650	0.0	-
3.0	21696	-	0.3335
3.0006	21700	0.0	-
3.0075	21750	0.0001	-
3.0144	21800	0.0	-
3.0213	21850	0.0	-
3.0282	21900	0.0	-
3.0351	21950	0.0	-
3.0420	22000	0.0	-
3.0489	22050	0.0	-
3.0559	22100	0.0	-
3.0628	22150	0.0	-
3.0697	22200	0.0	-
3.0766	22250	0.0	-
3.0835	22300	0.0	-
3.0904	22350	0.0	-
3.0973	22400	0.0	-
3.1043	22450	0.0	-
3.1112	22500	0.0	-
3.1181	22550	0.0	-
3.125	22600	0.0	-
3.1319	22650	0.0	-
3.1388	22700	0.0	-
3.1457	22750	0.0	-
3.1527	22800	0.0	-
3.1596	22850	0.0	-
3.1665	22900	0.0	-
3.1734	22950	0.0	-
3.1803	23000	0.0	-
3.1872	23050	0.0	-
3.1941	23100	0.0	-
3.2011	23150	0.0	-
3.2080	23200	0.0	-
3.2149	23250	0.0	-
3.2218	23300	0.0	-
3.2287	23350	0.0	-
3.2356	23400	0.0	-
3.2425	23450	0.0	-
3.2494	23500	0.0	-
3.2564	23550	0.0	-
3.2633	23600	0.0	-
3.2702	23650	0.0	-
3.2771	23700	0.0	-
3.2840	23750	0.0	-
3.2909	23800	0.0	-
3.2978	23850	0.0	-
3.3048	23900	0.0	-
3.3117	23950	0.0	-
3.3186	24000	0.0	-
3.3255	24050	0.0	-
3.3324	24100	0.0	-
3.3393	24150	0.0	-
3.3462	24200	0.0	-
3.3532	24250	0.0	-
3.3601	24300	0.0	-
3.3670	24350	0.0	-
3.3739	24400	0.0	-
3.3808	24450	0.0	-
3.3877	24500	0.0	-
3.3946	24550	0.0	-
3.4015	24600	0.0	-
3.4085	24650	0.0	-
3.4154	24700	0.0	-
3.4223	24750	0.0	-
3.4292	24800	0.0	-
3.4361	24850	0.0	-
3.4430	24900	0.0	-
3.4499	24950	0.0	-
3.4569	25000	0.0	-
3.4638	25050	0.0	-
3.4707	25100	0.0	-
3.4776	25150	0.0	-
3.4845	25200	0.0	-
3.4914	25250	0.0	-
3.4983	25300	0.0	-
3.5053	25350	0.0	-
3.5122	25400	0.0	-
3.5191	25450	0.0	-
3.5260	25500	0.0	-
3.5329	25550	0.0	-
3.5398	25600	0.0	-
3.5467	25650	0.0	-
3.5537	25700	0.0	-
3.5606	25750	0.0	-
3.5675	25800	0.0	-
3.5744	25850	0.0	-
3.5813	25900	0.0	-
3.5882	25950	0.0	-
3.5951	26000	0.0	-
3.6020	26050	0.0	-
3.6090	26100	0.0	-
3.6159	26150	0.0	-
3.6228	26200	0.0	-
3.6297	26250	0.0	-
3.6366	26300	0.0	-
3.6435	26350	0.0	-
3.6504	26400	0.0	-
3.6574	26450	0.0	-
3.6643	26500	0.0	-
3.6712	26550	0.0	-
3.6781	26600	0.0	-
3.6850	26650	0.0	-
3.6919	26700	0.0	-
3.6988	26750	0.0	-
3.7058	26800	0.0	-
3.7127	26850	0.0	-
3.7196	26900	0.0	-
3.7265	26950	0.0	-
3.7334	27000	0.0	-
3.7403	27050	0.0	-
3.7472	27100	0.0	-
3.7541	27150	0.0	-
3.7611	27200	0.0	-
3.7680	27250	0.0	-
3.7749	27300	0.0	-
3.7818	27350	0.0	-
3.7887	27400	0.0	-
3.7956	27450	0.0	-
3.8025	27500	0.0	-
3.8095	27550	0.0	-
3.8164	27600	0.0	-
3.8233	27650	0.0	-
3.8302	27700	0.0	-
3.8371	27750	0.0	-
3.8440	27800	0.0	-
3.8509	27850	0.0	-
3.8579	27900	0.0	-
3.8648	27950	0.0	-
3.8717	28000	0.0	-
3.8786	28050	0.0	-
3.8855	28100	0.0	-
3.8924	28150	0.0	-
3.8993	28200	0.0	-
3.9062	28250	0.0	-
3.9132	28300	0.0	-
3.9201	28350	0.0	-
3.9270	28400	0.0	-
3.9339	28450	0.0	-
3.9408	28500	0.0	-
3.9477	28550	0.0	-
3.9546	28600	0.0	-
3.9616	28650	0.0	-
3.9685	28700	0.0	-
3.9754	28750	0.0	-
3.9823	28800	0.0	-
3.9892	28850	0.0	-
3.9961	28900	0.0	-
4.0	28928	-	0.3332
4.0030	28950	0.0	-
4.0100	29000	0.0	-
4.0169	29050	0.0	-
4.0238	29100	0.0	-
4.0307	29150	0.0	-
4.0376	29200	0.0	-
4.0445	29250	0.0	-
4.0514	29300	0.0	-
4.0584	29350	0.0	-
4.0653	29400	0.0	-
4.0722	29450	0.0	-
4.0791	29500	0.0	-
4.0860	29550	0.0	-
4.0929	29600	0.0	-
4.0998	29650	0.0	-
4.1067	29700	0.0	-
4.1137	29750	0.0	-
4.1206	29800	0.0	-
4.1275	29850	0.0	-
4.1344	29900	0.0	-
4.1413	29950	0.0	-
4.1482	30000	0.0	-
4.1551	30050	0.0	-
4.1621	30100	0.0	-
4.1690	30150	0.0	-
4.1759	30200	0.0	-
4.1828	30250	0.0	-
4.1897	30300	0.0	-
4.1966	30350	0.0	-
4.2035	30400	0.0	-
4.2105	30450	0.0	-
4.2174	30500	0.0	-
4.2243	30550	0.0	-
4.2312	30600	0.0	-
4.2381	30650	0.0	-
4.2450	30700	0.0	-
4.2519	30750	0.0	-
4.2588	30800	0.0	-
4.2658	30850	0.0	-
4.2727	30900	0.0	-
4.2796	30950	0.0	-
4.2865	31000	0.0	-
4.2934	31050	0.0	-
4.3003	31100	0.0	-
4.3072	31150	0.0	-
4.3142	31200	0.0	-
4.3211	31250	0.0	-
4.3280	31300	0.0	-
4.3349	31350	0.0	-
4.3418	31400	0.0	-
4.3487	31450	0.0	-
4.3556	31500	0.0	-
4.3626	31550	0.0	-
4.3695	31600	0.0	-
4.3764	31650	0.0	-
4.3833	31700	0.0	-
4.3902	31750	0.0	-
4.3971	31800	0.0	-
4.4040	31850	0.0	-
4.4110	31900	0.0	-
4.4179	31950	0.0	-
4.4248	32000	0.0	-
4.4317	32050	0.0	-
4.4386	32100	0.0	-
4.4455	32150	0.0	-
4.4524	32200	0.0	-
4.4593	32250	0.0	-
4.4663	32300	0.0	-
4.4732	32350	0.0	-
4.4801	32400	0.0	-
4.4870	32450	0.0	-
4.4939	32500	0.0	-
4.5008	32550	0.0	-
4.5077	32600	0.0	-
4.5147	32650	0.0	-
4.5216	32700	0.0	-
4.5285	32750	0.0	-
4.5354	32800	0.0	-
4.5423	32850	0.0	-
4.5492	32900	0.0	-
4.5561	32950	0.0	-
4.5631	33000	0.0	-
4.5700	33050	0.0	-
4.5769	33100	0.0	-
4.5838	33150	0.0	-
4.5907	33200	0.0	-
4.5976	33250	0.0	-
4.6045	33300	0.0	-
4.6114	33350	0.0	-
4.6184	33400	0.0	-
4.6253	33450	0.0	-
4.6322	33500	0.0	-
4.6391	33550	0.0	-
4.6460	33600	0.0	-
4.6529	33650	0.0	-
4.6598	33700	0.0	-
4.6668	33750	0.0	-
4.6737	33800	0.0	-
4.6806	33850	0.0	-
4.6875	33900	0.0	-
4.6944	33950	0.0	-
4.7013	34000	0.0	-
4.7082	34050	0.0	-
4.7152	34100	0.0	-
4.7221	34150	0.0	-
4.7290	34200	0.0	-
4.7359	34250	0.0	-
4.7428	34300	0.0	-
4.7497	34350	0.0	-
4.7566	34400	0.0	-
4.7636	34450	0.0	-
4.7705	34500	0.0	-
4.7774	34550	0.0	-
4.7843	34600	0.0	-
4.7912	34650	0.0	-
4.7981	34700	0.0	-
4.8050	34750	0.0	-
4.8119	34800	0.0	-
4.8189	34850	0.0	-
4.8258	34900	0.0	-
4.8327	34950	0.0	-
4.8396	35000	0.0	-
4.8465	35050	0.0	-
4.8534	35100	0.0	-
4.8603	35150	0.0	-
4.8673	35200	0.0	-
4.8742	35250	0.0	-
4.8811	35300	0.0	-
4.8880	35350	0.0	-
4.8949	35400	0.0	-
4.9018	35450	0.0	-
4.9087	35500	0.0	-
4.9157	35550	0.0	-
4.9226	35600	0.0	-
4.9295	35650	0.0	-
4.9364	35700	0.0	-
4.9433	35750	0.0	-
4.9502	35800	0.0	-
4.9571	35850	0.0	-
4.9640	35900	0.0	-
4.9710	35950	0.0	-
4.9779	36000	0.0	-
4.9848	36050	0.0	-
4.9917	36100	0.0	-
4.9986	36150	0.0	-
5.0	36160	-	0.3376
5.0055	36200	0.0	-
5.0124	36250	0.0	-
5.0194	36300	0.0	-
5.0263	36350	0.0	-
5.0332	36400	0.0	-
5.0401	36450	0.0	-
5.0470	36500	0.0	-
5.0539	36550	0.0	-
5.0608	36600	0.0	-
5.0678	36650	0.0	-
5.0747	36700	0.0	-
5.0816	36750	0.0	-
5.0885	36800	0.0	-
5.0954	36850	0.0	-
5.1023	36900	0.0	-
5.1092	36950	0.0	-
5.1162	37000	0.0	-
5.1231	37050	0.0	-
5.1300	37100	0.0	-
5.1369	37150	0.0	-
5.1438	37200	0.0	-
5.1507	37250	0.0	-
5.1576	37300	0.0	-
5.1645	37350	0.0	-
5.1715	37400	0.0	-
5.1784	37450	0.0	-
5.1853	37500	0.0	-
5.1922	37550	0.0	-
5.1991	37600	0.0	-
5.2060	37650	0.0	-
5.2129	37700	0.0	-
5.2199	37750	0.0	-
5.2268	37800	0.0	-
5.2337	37850	0.0	-
5.2406	37900	0.0	-
5.2475	37950	0.0	-
5.2544	38000	0.0	-
5.2613	38050	0.0	-
5.2683	38100	0.0	-
5.2752	38150	0.0	-
5.2821	38200	0.0	-
5.2890	38250	0.0	-
5.2959	38300	0.0	-
5.3028	38350	0.0	-
5.3097	38400	0.0	-
5.3166	38450	0.0	-
5.3236	38500	0.0	-
5.3305	38550	0.0	-
5.3374	38600	0.0	-
5.3443	38650	0.0	-
5.3512	38700	0.0	-
5.3581	38750	0.0	-
5.3650	38800	0.0	-
5.3720	38850	0.0	-
5.3789	38900	0.0	-
5.3858	38950	0.0	-
5.3927	39000	0.0	-
5.3996	39050	0.0	-
5.4065	39100	0.0	-
5.4134	39150	0.0	-
5.4204	39200	0.0	-
5.4273	39250	0.0	-
5.4342	39300	0.0	-
5.4411	39350	0.0	-
5.4480	39400	0.0	-
5.4549	39450	0.0	-
5.4618	39500	0.0	-
5.4688	39550	0.0	-
5.4757	39600	0.0	-
5.4826	39650	0.0	-
5.4895	39700	0.0	-
5.4964	39750	0.0	-
5.5033	39800	0.0	-
5.5102	39850	0.0	-
5.5171	39900	0.0	-
5.5241	39950	0.0	-
5.5310	40000	0.0	-
5.5379	40050	0.0	-
5.5448	40100	0.0	-
5.5517	40150	0.0	-
5.5586	40200	0.0	-
5.5655	40250	0.0	-
5.5725	40300	0.0	-
5.5794	40350	0.0	-
5.5863	40400	0.0	-
5.5932	40450	0.0	-
5.6001	40500	0.0	-
5.6070	40550	0.0	-
5.6139	40600	0.0	-
5.6209	40650	0.0	-
5.6278	40700	0.0	-
5.6347	40750	0.0	-
5.6416	40800	0.0	-
5.6485	40850	0.0	-
5.6554	40900	0.0	-
5.6623	40950	0.0	-
5.6692	41000	0.0	-
5.6762	41050	0.0	-
5.6831	41100	0.0	-
5.6900	41150	0.0	-
5.6969	41200	0.0	-
5.7038	41250	0.0	-
5.7107	41300	0.0	-
5.7176	41350	0.0	-
5.7246	41400	0.0	-
5.7315	41450	0.0	-
5.7384	41500	0.0	-
5.7453	41550	0.0	-
5.7522	41600	0.0	-
5.7591	41650	0.0	-
5.7660	41700	0.0	-
5.7730	41750	0.0	-
5.7799	41800	0.0	-
5.7868	41850	0.0	-
5.7937	41900	0.0	-
5.8006	41950	0.0	-
5.8075	42000	0.0	-
5.8144	42050	0.0	-
5.8213	42100	0.0	-
5.8283	42150	0.0	-
5.8352	42200	0.0	-
5.8421	42250	0.0	-
5.8490	42300	0.0	-
5.8559	42350	0.0	-
5.8628	42400	0.0	-
5.8697	42450	0.0	-
5.8767	42500	0.0	-
5.8836	42550	0.0	-
5.8905	42600	0.0	-
5.8974	42650	0.0	-
5.9043	42700	0.0	-
5.9112	42750	0.0	-
5.9181	42800	0.0	-
5.9251	42850	0.0	-
5.9320	42900	0.0	-
5.9389	42950	0.0	-
5.9458	43000	0.0	-
5.9527	43050	0.0	-
5.9596	43100	0.0	-
5.9665	43150	0.0	-
5.9735	43200	0.0	-
5.9804	43250	0.0	-
5.9873	43300	0.0	-
5.9942	43350	0.0	-
6.0	43392	-	0.3407
6.0011	43400	0.0	-
6.0080	43450	0.0	-
6.0149	43500	0.0	-
6.0218	43550	0.0	-
6.0288	43600	0.0	-
6.0357	43650	0.0	-
6.0426	43700	0.0	-
6.0495	43750	0.0	-
6.0564	43800	0.0	-
6.0633	43850	0.0	-
6.0702	43900	0.0	-
6.0772	43950	0.0	-
6.0841	44000	0.0	-
6.0910	44050	0.0	-
6.0979	44100	0.0	-
6.1048	44150	0.0	-
6.1117	44200	0.0	-
6.1186	44250	0.0	-
6.1256	44300	0.0	-
6.1325	44350	0.0	-
6.1394	44400	0.0	-
6.1463	44450	0.0	-
6.1532	44500	0.0	-
6.1601	44550	0.0	-
6.1670	44600	0.0	-
6.1739	44650	0.0	-
6.1809	44700	0.0	-
6.1878	44750	0.0	-
6.1947	44800	0.0	-
6.2016	44850	0.0	-
6.2085	44900	0.0	-
6.2154	44950	0.0	-
6.2223	45000	0.0	-
6.2293	45050	0.0	-
6.2362	45100	0.0	-
6.2431	45150	0.0	-
6.25	45200	0.0	-
6.2569	45250	0.0	-
6.2638	45300	0.0	-
6.2707	45350	0.0	-
6.2777	45400	0.0	-
6.2846	45450	0.0	-
6.2915	45500	0.0	-
6.2984	45550	0.0	-
6.3053	45600	0.0	-
6.3122	45650	0.0	-
6.3191	45700	0.0	-
6.3261	45750	0.0	-
6.3330	45800	0.0	-
6.3399	45850	0.0	-
6.3468	45900	0.0	-
6.3537	45950	0.0	-
6.3606	46000	0.0	-
6.3675	46050	0.0	-
6.3744	46100	0.0	-
6.3814	46150	0.0	-
6.3883	46200	0.0	-
6.3952	46250	0.0	-
6.4021	46300	0.0	-
6.4090	46350	0.0	-
6.4159	46400	0.0	-
6.4228	46450	0.0	-
6.4298	46500	0.0	-
6.4367	46550	0.0	-
6.4436	46600	0.0	-
6.4505	46650	0.0	-
6.4574	46700	0.0	-
6.4643	46750	0.0	-
6.4712	46800	0.0	-
6.4782	46850	0.0	-
6.4851	46900	0.0	-
6.4920	46950	0.0	-
6.4989	47000	0.0	-
6.5058	47050	0.0	-
6.5127	47100	0.0	-
6.5196	47150	0.0	-
6.5265	47200	0.0	-
6.5335	47250	0.0	-
6.5404	47300	0.0	-
6.5473	47350	0.0	-
6.5542	47400	0.0	-
6.5611	47450	0.0	-
6.5680	47500	0.0	-
6.5749	47550	0.0	-
6.5819	47600	0.0	-
6.5888	47650	0.0	-
6.5957	47700	0.0	-
6.6026	47750	0.0	-
6.6095	47800	0.0	-
6.6164	47850	0.0	-
6.6233	47900	0.0	-
6.6303	47950	0.0	-
6.6372	48000	0.0	-
6.6441	48050	0.0	-
6.6510	48100	0.0	-
6.6579	48150	0.0	-
6.6648	48200	0.0	-
6.6717	48250	0.0	-
6.6787	48300	0.0	-
6.6856	48350	0.0	-
6.6925	48400	0.0	-
6.6994	48450	0.0	-
6.7063	48500	0.0	-
6.7132	48550	0.0	-
6.7201	48600	0.0	-
6.7270	48650	0.0	-
6.7340	48700	0.0	-
6.7409	48750	0.0	-
6.7478	48800	0.0	-
6.7547	48850	0.0	-
6.7616	48900	0.0	-
6.7685	48950	0.0	-
6.7754	49000	0.0	-
6.7824	49050	0.0	-
6.7893	49100	0.0	-
6.7962	49150	0.0	-
6.8031	49200	0.0	-
6.8100	49250	0.0	-
6.8169	49300	0.0	-
6.8238	49350	0.0	-
6.8308	49400	0.0	-
6.8377	49450	0.0	-
6.8446	49500	0.0	-
6.8515	49550	0.0	-
6.8584	49600	0.0	-
6.8653	49650	0.0	-
6.8722	49700	0.0	-
6.8791	49750	0.0	-
6.8861	49800	0.0	-
6.8930	49850	0.0	-
6.8999	49900	0.0	-
6.9068	49950	0.0	-
6.9137	50000	0.0	-
6.9206	50050	0.0	-
6.9275	50100	0.0	-
6.9345	50150	0.0	-
6.9414	50200	0.0	-
6.9483	50250	0.0	-
6.9552	50300	0.0	-
6.9621	50350	0.0	-
6.9690	50400	0.0	-
6.9759	50450	0.0	-
6.9829	50500	0.0	-
6.9898	50550	0.0	-
6.9967	50600	0.0	-
7.0	50624	-	0.3412

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.13
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2
• Datasets: 2.19.2
• Tokenizers: 0.19.1

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}
}