Amadeus99/indonesia-election-sentiment-classification-setfit-3

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	'mas bro, yang lagi sibuk mikirin pilpres 2024, ini solusinya! pilih ganjar pranowo - mahfud md. dia punya program kece: disabilitas bisa mandiri dan berprestasi, plus ada program 1 desa 1 mobil akses. bikin perubahan!#jnk #ganjarmahfudrebound #ganjarpranowopilihanumat' 'semoga tambah umur makin baik dan sukses selalu mas ganjar mahfud hebat #l3bihbaik #mahfudlebihbaik3 #ganjarmahfud2024 nelayan sejahtera' 'capres terhumble dan selalu mau terjun ke lapangan hanya untuk rakyatnya, no debat kalau pak ganjar emang mendedikasikan hidupnya untuk rakyat'
netral	'minta pak ganjar' 'mas alam penerus pak ganjar pranowo 🥰' 'seruu liat pak ganjar bakar ikan bareng nelayan'
negatif	'dan anda selalu selalu sibuk dgn elektabilitas ganjar mahfud krn partai anda dipastikan hanya jd pemandu sorak di pemilu 2024. paham kau, dungu !!😝😝😂😂' 'ganjar varian wasit epl iki cen ra mutu tenan' '"kami sangat keberatan bila penyuka bokep spt ganjar pranowo disamakan dg sosok khalifah umar bin khattab mahfud hebat #l3bihbaik #mahfudlebihbaik3 #ganjarmahfud2024 buruh naik kelas'

Evaluation

Metrics

Label	Accuracy	F1
all	0.7078	0.6914

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-3")
# Run inference
preds = model("prabowo ada gk sih di.acara kadin ini? pak ganjar ada, muncul jg di yutub... pak prabowo ada gak ?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	29.1233	727

Label	Training Sample Count
negatif	51
netral	55
positif	194

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
0.0002	1	0.2501	-
0.0086	50	0.2921	-
0.0171	100	0.2463	-
0.0257	150	0.2962	-
0.0342	200	0.2217	-
0.0428	250	0.2027	-
0.0513	300	0.2193	-
0.0599	350	0.2862	-
0.0685	400	0.1946	-
0.0770	450	0.2387	-
0.0856	500	0.2247	-
0.0941	550	0.1438	-
0.1027	600	0.1952	-
0.1112	650	0.1609	-
0.1198	700	0.1106	-
0.1284	750	0.0593	-
0.1369	800	0.1993	-
0.1455	850	0.1873	-
0.1540	900	0.074	-
0.1626	950	0.0574	-
0.1711	1000	0.0175	-
0.1797	1050	0.0577	-
0.1883	1100	0.0188	-
0.1968	1150	0.1049	-
0.2054	1200	0.0367	-
0.2139	1250	0.0178	-
0.2225	1300	0.0018	-
0.2310	1350	0.0184	-
0.2396	1400	0.0005	-
0.2482	1450	0.0006	-
0.2567	1500	0.0232	-
0.2653	1550	0.0225	-
0.2738	1600	0.0009	-
0.2824	1650	0.0013	-
0.2909	1700	0.0024	-
0.2995	1750	0.0008	-
0.3081	1800	0.0007	-
0.3166	1850	0.0017	-
0.3252	1900	0.0005	-
0.3337	1950	0.0004	-
0.3423	2000	0.0017	-
0.3508	2050	0.0004	-
0.3594	2100	0.008	-
0.3680	2150	0.0004	-
0.3765	2200	0.0001	-
0.3851	2250	0.0002	-
0.3936	2300	0.0001	-
0.4022	2350	0.0009	-
0.4107	2400	0.0016	-
0.4193	2450	0.0001	-
0.4279	2500	0.0001	-
0.4364	2550	0.0001	-
0.4450	2600	0.0002	-
0.4535	2650	0.0007	-
0.4621	2700	0.0002	-
0.4706	2750	0.0001	-
0.4792	2800	0.0001	-
0.4878	2850	0.0001	-
0.4963	2900	0.0001	-
0.5049	2950	0.0001	-
0.5134	3000	0.0	-
0.5220	3050	0.0	-
0.5305	3100	0.0	-
0.5391	3150	0.0	-
0.5477	3200	0.0002	-
0.5562	3250	0.0002	-
0.5648	3300	0.0	-
0.5733	3350	0.0007	-
0.5819	3400	0.0001	-
0.5905	3450	0.0003	-
0.5990	3500	0.0044	-
0.6076	3550	0.0015	-
0.6161	3600	0.0006	-
0.6247	3650	0.0001	-
0.6332	3700	0.0003	-
0.6418	3750	0.0002	-
0.6504	3800	0.0002	-
0.6589	3850	0.0001	-
0.6675	3900	0.0	-
0.6760	3950	0.0	-
0.6846	4000	0.0001	-
0.6931	4050	0.0	-
0.7017	4100	0.0001	-
0.7103	4150	0.0	-
0.7188	4200	0.0	-
0.7274	4250	0.0	-
0.7359	4300	0.0001	-
0.7445	4350	0.0002	-
0.7530	4400	0.0	-
0.7616	4450	0.0	-
0.7702	4500	0.0001	-
0.7787	4550	0.0	-
0.7873	4600	0.0	-
0.7958	4650	0.0	-
0.8044	4700	0.0	-
0.8129	4750	0.0	-
0.8215	4800	0.0	-
0.8301	4850	0.0	-
0.8386	4900	0.0	-
0.8472	4950	0.0	-
0.8557	5000	0.0	-
0.8643	5050	0.0001	-
0.8728	5100	0.0001	-
0.8814	5150	0.0	-
0.8900	5200	0.0	-
0.8985	5250	0.0	-
0.9071	5300	0.0	-
0.9156	5350	0.0	-
0.9242	5400	0.0001	-
0.9327	5450	0.0001	-
0.9413	5500	0.0	-
0.9499	5550	0.0	-
0.9584	5600	0.0	-
0.9670	5650	0.0001	-
0.9755	5700	0.0	-
0.9841	5750	0.0	-
0.9926	5800	0.0	-
1.0	5843	-	0.2886
1.0012	5850	0.0	-
1.0098	5900	0.0	-
1.0183	5950	0.0	-
1.0269	6000	0.0	-
1.0354	6050	0.0	-
1.0440	6100	0.0	-
1.0525	6150	0.0	-
1.0611	6200	0.0	-
1.0697	6250	0.0	-
1.0782	6300	0.0	-
1.0868	6350	0.0	-
1.0953	6400	0.0	-
1.1039	6450	0.0	-
1.1124	6500	0.0	-
1.1210	6550	0.0	-
1.1296	6600	0.0	-
1.1381	6650	0.0	-
1.1467	6700	0.0	-
1.1552	6750	0.0	-
1.1638	6800	0.0	-
1.1723	6850	0.0	-
1.1809	6900	0.0	-
1.1895	6950	0.0	-
1.1980	7000	0.0	-
1.2066	7050	0.0001	-
1.2151	7100	0.0	-
1.2237	7150	0.0	-
1.2322	7200	0.0	-
1.2408	7250	0.0	-
1.2494	7300	0.0	-
1.2579	7350	0.0	-
1.2665	7400	0.0	-
1.2750	7450	0.0	-
1.2836	7500	0.0	-
1.2921	7550	0.0	-
1.3007	7600	0.0	-
1.3093	7650	0.0	-
1.3178	7700	0.0	-
1.3264	7750	0.0	-
1.3349	7800	0.0	-
1.3435	7850	0.0	-
1.3520	7900	0.0	-
1.3606	7950	0.0	-
1.3692	8000	0.0	-
1.3777	8050	0.0043	-
1.3863	8100	0.0001	-
1.3948	8150	0.0	-
1.4034	8200	0.0	-
1.4119	8250	0.0	-
1.4205	8300	0.0	-
1.4291	8350	0.0	-
1.4376	8400	0.0	-
1.4462	8450	0.0	-
1.4547	8500	0.0	-
1.4633	8550	0.0	-
1.4718	8600	0.0	-
1.4804	8650	0.0684	-
1.4890	8700	0.125	-
1.4975	8750	0.0074	-
1.5061	8800	0.0003	-
1.5146	8850	0.0002	-
1.5232	8900	0.0004	-
1.5317	8950	0.0001	-
1.5403	9000	0.0283	-
1.5489	9050	0.0001	-
1.5574	9100	0.0001	-
1.5660	9150	0.0	-
1.5745	9200	0.0	-
1.5831	9250	0.0	-
1.5916	9300	0.0	-
1.6002	9350	0.0001	-
1.6088	9400	0.0001	-
1.6173	9450	0.0	-
1.6259	9500	0.0	-
1.6344	9550	0.0	-
1.6430	9600	0.0001	-
1.6515	9650	0.0	-
1.6601	9700	0.0	-
1.6687	9750	0.0	-
1.6772	9800	0.0	-
1.6858	9850	0.0	-
1.6943	9900	0.0	-
1.7029	9950	0.0	-
1.7114	10000	0.0	-
1.7200	10050	0.0	-
1.7286	10100	0.0	-
1.7371	10150	0.0	-
1.7457	10200	0.0	-
1.7542	10250	0.0	-
1.7628	10300	0.0	-
1.7714	10350	0.0	-
1.7799	10400	0.0	-
1.7885	10450	0.0	-
1.7970	10500	0.0	-
1.8056	10550	0.0	-
1.8141	10600	0.0	-
1.8227	10650	0.0	-
1.8313	10700	0.0	-
1.8398	10750	0.0	-
1.8484	10800	0.0	-
1.8569	10850	0.0	-
1.8655	10900	0.0	-
1.8740	10950	0.0	-
1.8826	11000	0.0	-
1.8912	11050	0.0	-
1.8997	11100	0.0	-
1.9083	11150	0.0	-
1.9168	11200	0.0	-
1.9254	11250	0.0	-
1.9339	11300	0.0	-
1.9425	11350	0.0	-
1.9511	11400	0.0	-
1.9596	11450	0.0	-
1.9682	11500	0.0	-
1.9767	11550	0.0	-
1.9853	11600	0.0	-
1.9938	11650	0.0	-
2.0	11686	-	0.2892
2.0024	11700	0.0	-
2.0110	11750	0.0	-
2.0195	11800	0.0	-
2.0281	11850	0.0	-
2.0366	11900	0.0	-
2.0452	11950	0.0	-
2.0537	12000	0.0	-
2.0623	12050	0.0	-
2.0709	12100	0.0	-
2.0794	12150	0.0	-
2.0880	12200	0.0	-
2.0965	12250	0.0	-
2.1051	12300	0.0	-
2.1136	12350	0.0	-
2.1222	12400	0.0	-
2.1308	12450	0.0	-
2.1393	12500	0.0	-
2.1479	12550	0.0	-
2.1564	12600	0.0	-
2.1650	12650	0.0	-
2.1735	12700	0.0	-
2.1821	12750	0.0	-
2.1907	12800	0.0	-
2.1992	12850	0.0	-
2.2078	12900	0.0013	-
2.2163	12950	0.0	-
2.2249	13000	0.0002	-
2.2334	13050	0.0002	-
2.2420	13100	0.0001	-
2.2506	13150	0.0	-
2.2591	13200	0.0	-
2.2677	13250	0.0	-
2.2762	13300	0.0007	-
2.2848	13350	0.0001	-
2.2933	13400	0.0	-
2.3019	13450	0.0	-
2.3105	13500	0.0	-
2.3190	13550	0.0	-
2.3276	13600	0.0	-
2.3361	13650	0.0	-
2.3447	13700	0.0	-
2.3532	13750	0.0002	-
2.3618	13800	0.0	-
2.3704	13850	0.0	-
2.3789	13900	0.0	-
2.3875	13950	0.0	-
2.3960	14000	0.0	-
2.4046	14050	0.0	-
2.4131	14100	0.0	-
2.4217	14150	0.0	-
2.4303	14200	0.0	-
2.4388	14250	0.0361	-
2.4474	14300	0.0	-
2.4559	14350	0.0	-
2.4645	14400	0.0	-
2.4730	14450	0.0	-
2.4816	14500	0.0	-
2.4902	14550	0.0	-
2.4987	14600	0.0006	-
2.5073	14650	0.0	-
2.5158	14700	0.0	-
2.5244	14750	0.0	-
2.5329	14800	0.0	-
2.5415	14850	0.0	-
2.5501	14900	0.0	-
2.5586	14950	0.0	-
2.5672	15000	0.0	-
2.5757	15050	0.0	-
2.5843	15100	0.0	-
2.5928	15150	0.0	-
2.6014	15200	0.0	-
2.6100	15250	0.0	-
2.6185	15300	0.0	-
2.6271	15350	0.0	-
2.6356	15400	0.0	-
2.6442	15450	0.0	-
2.6527	15500	0.0	-
2.6613	15550	0.0	-
2.6699	15600	0.0	-
2.6784	15650	0.0	-
2.6870	15700	0.0	-
2.6955	15750	0.0	-
2.7041	15800	0.0	-
2.7126	15850	0.0	-
2.7212	15900	0.0	-
2.7298	15950	0.0	-
2.7383	16000	0.0	-
2.7469	16050	0.0	-
2.7554	16100	0.0	-
2.7640	16150	0.0	-
2.7725	16200	0.0	-
2.7811	16250	0.0	-
2.7897	16300	0.0	-
2.7982	16350	0.0	-
2.8068	16400	0.0	-
2.8153	16450	0.0	-
2.8239	16500	0.0	-
2.8324	16550	0.0	-
2.8410	16600	0.0	-
2.8496	16650	0.0	-
2.8581	16700	0.0	-
2.8667	16750	0.0	-
2.8752	16800	0.0	-
2.8838	16850	0.0	-
2.8923	16900	0.0	-
2.9009	16950	0.0	-
2.9095	17000	0.0	-
2.9180	17050	0.0	-
2.9266	17100	0.0	-
2.9351	17150	0.0	-
2.9437	17200	0.0	-
2.9523	17250	0.0	-
2.9608	17300	0.0	-
2.9694	17350	0.0	-
2.9779	17400	0.0	-
2.9865	17450	0.0	-
2.9950	17500	0.0	-
3.0	17529	-	0.3028
3.0036	17550	0.0	-
3.0122	17600	0.0	-
3.0207	17650	0.0	-
3.0293	17700	0.0	-
3.0378	17750	0.0	-
3.0464	17800	0.0	-
3.0549	17850	0.0	-
3.0635	17900	0.0	-
3.0721	17950	0.0	-
3.0806	18000	0.0	-
3.0892	18050	0.0	-
3.0977	18100	0.0	-
3.1063	18150	0.0	-
3.1148	18200	0.0	-
3.1234	18250	0.0	-
3.1320	18300	0.0	-
3.1405	18350	0.0	-
3.1491	18400	0.0	-
3.1576	18450	0.0	-
3.1662	18500	0.0	-
3.1747	18550	0.0	-
3.1833	18600	0.0	-
3.1919	18650	0.0	-
3.2004	18700	0.0	-
3.2090	18750	0.0	-
3.2175	18800	0.0	-
3.2261	18850	0.0	-
3.2346	18900	0.0	-
3.2432	18950	0.0	-
3.2518	19000	0.0	-
3.2603	19050	0.0	-
3.2689	19100	0.0	-
3.2774	19150	0.0	-
3.2860	19200	0.0	-
3.2945	19250	0.0	-
3.3031	19300	0.0	-
3.3117	19350	0.0	-
3.3202	19400	0.0	-
3.3288	19450	0.0	-
3.3373	19500	0.0	-
3.3459	19550	0.0	-
3.3544	19600	0.0	-
3.3630	19650	0.0	-
3.3716	19700	0.0	-
3.3801	19750	0.0	-
3.3887	19800	0.0	-
3.3972	19850	0.0	-
3.4058	19900	0.0	-
3.4143	19950	0.0	-
3.4229	20000	0.0	-
3.4315	20050	0.0	-
3.4400	20100	0.0	-
3.4486	20150	0.0	-
3.4571	20200	0.0	-
3.4657	20250	0.0	-
3.4742	20300	0.0	-
3.4828	20350	0.0	-
3.4914	20400	0.0	-
3.4999	20450	0.0	-
3.5085	20500	0.0	-
3.5170	20550	0.0	-
3.5256	20600	0.0	-
3.5341	20650	0.0	-
3.5427	20700	0.0	-
3.5513	20750	0.0	-
3.5598	20800	0.0	-
3.5684	20850	0.0	-
3.5769	20900	0.0	-
3.5855	20950	0.0	-
3.5940	21000	0.0	-
3.6026	21050	0.0	-
3.6112	21100	0.0	-
3.6197	21150	0.0	-
3.6283	21200	0.0	-
3.6368	21250	0.0	-
3.6454	21300	0.0	-
3.6539	21350	0.0	-
3.6625	21400	0.0	-
3.6711	21450	0.0	-
3.6796	21500	0.0	-
3.6882	21550	0.0	-
3.6967	21600	0.0	-
3.7053	21650	0.0	-
3.7138	21700	0.0	-
3.7224	21750	0.0	-
3.7310	21800	0.0	-
3.7395	21850	0.0	-
3.7481	21900	0.0	-
3.7566	21950	0.0	-
3.7652	22000	0.0	-
3.7737	22050	0.0	-
3.7823	22100	0.0	-
3.7909	22150	0.0	-
3.7994	22200	0.0	-
3.8080	22250	0.0	-
3.8165	22300	0.0	-
3.8251	22350	0.0	-
3.8336	22400	0.0	-
3.8422	22450	0.0	-
3.8508	22500	0.0	-
3.8593	22550	0.0	-
3.8679	22600	0.0	-
3.8764	22650	0.0	-
3.8850	22700	0.0	-
3.8935	22750	0.0	-
3.9021	22800	0.0	-
3.9107	22850	0.0	-
3.9192	22900	0.0	-
3.9278	22950	0.0	-
3.9363	23000	0.0	-
3.9449	23050	0.0	-
3.9534	23100	0.0	-
3.9620	23150	0.0	-
3.9706	23200	0.0	-
3.9791	23250	0.0	-
3.9877	23300	0.0	-
3.9962	23350	0.0	-
4.0	23372	-	0.3164
4.0048	23400	0.0	-
4.0133	23450	0.0	-
4.0219	23500	0.0	-
4.0305	23550	0.0	-
4.0390	23600	0.0	-
4.0476	23650	0.0	-
4.0561	23700	0.0	-
4.0647	23750	0.0	-
4.0733	23800	0.0	-
4.0818	23850	0.0	-
4.0904	23900	0.0	-
4.0989	23950	0.0	-
4.1075	24000	0.0	-
4.1160	24050	0.0	-
4.1246	24100	0.0	-
4.1332	24150	0.0	-
4.1417	24200	0.0	-
4.1503	24250	0.0	-
4.1588	24300	0.0	-
4.1674	24350	0.0	-
4.1759	24400	0.0	-
4.1845	24450	0.0	-
4.1931	24500	0.0	-
4.2016	24550	0.0	-
4.2102	24600	0.0	-
4.2187	24650	0.0	-
4.2273	24700	0.0	-
4.2358	24750	0.0	-
4.2444	24800	0.0	-
4.2530	24850	0.0	-
4.2615	24900	0.0	-
4.2701	24950	0.0	-
4.2786	25000	0.0	-
4.2872	25050	0.0	-
4.2957	25100	0.0	-
4.3043	25150	0.0	-
4.3129	25200	0.0	-
4.3214	25250	0.0	-
4.3300	25300	0.0	-
4.3385	25350	0.0	-
4.3471	25400	0.0	-
4.3556	25450	0.0	-
4.3642	25500	0.0	-
4.3728	25550	0.0	-
4.3813	25600	0.0	-
4.3899	25650	0.0	-
4.3984	25700	0.0	-
4.4070	25750	0.0	-
4.4155	25800	0.0	-
4.4241	25850	0.0	-
4.4327	25900	0.0	-
4.4412	25950	0.0	-
4.4498	26000	0.0	-
4.4583	26050	0.0	-
4.4669	26100	0.0	-
4.4754	26150	0.0	-
4.4840	26200	0.0	-
4.4926	26250	0.0	-
4.5011	26300	0.0	-
4.5097	26350	0.0	-
4.5182	26400	0.0	-
4.5268	26450	0.0	-
4.5353	26500	0.0	-
4.5439	26550	0.0	-
4.5525	26600	0.0	-
4.5610	26650	0.0	-
4.5696	26700	0.0	-
4.5781	26750	0.0	-
4.5867	26800	0.0	-
4.5952	26850	0.0	-
4.6038	26900	0.0	-
4.6124	26950	0.0	-
4.6209	27000	0.0	-
4.6295	27050	0.0	-
4.6380	27100	0.0	-
4.6466	27150	0.0	-
4.6551	27200	0.0	-
4.6637	27250	0.0	-
4.6723	27300	0.0	-
4.6808	27350	0.0	-
4.6894	27400	0.0	-
4.6979	27450	0.0	-
4.7065	27500	0.0	-
4.7150	27550	0.0	-
4.7236	27600	0.0	-
4.7322	27650	0.0	-
4.7407	27700	0.0	-
4.7493	27750	0.0	-
4.7578	27800	0.0	-
4.7664	27850	0.0	-
4.7749	27900	0.0	-
4.7835	27950	0.0	-
4.7921	28000	0.0	-
4.8006	28050	0.0	-
4.8092	28100	0.0	-
4.8177	28150	0.0	-
4.8263	28200	0.0	-
4.8348	28250	0.0	-
4.8434	28300	0.0	-
4.8520	28350	0.0	-
4.8605	28400	0.0371	-
4.8691	28450	0.0	-
4.8776	28500	0.0	-
4.8862	28550	0.0	-
4.8947	28600	0.0	-
4.9033	28650	0.0	-
4.9119	28700	0.0	-
4.9204	28750	0.0	-
4.9290	28800	0.0	-
4.9375	28850	0.0	-
4.9461	28900	0.0	-
4.9546	28950	0.0	-
4.9632	29000	0.0	-
4.9718	29050	0.0	-
4.9803	29100	0.0	-
4.9889	29150	0.0	-
4.9974	29200	0.0	-
5.0	29215	-	0.3281
5.0060	29250	0.0	-
5.0145	29300	0.0	-
5.0231	29350	0.0	-
5.0317	29400	0.0	-
5.0402	29450	0.0	-
5.0488	29500	0.0	-
5.0573	29550	0.0	-
5.0659	29600	0.0	-
5.0744	29650	0.0	-
5.0830	29700	0.0	-
5.0916	29750	0.0	-
5.1001	29800	0.0	-
5.1087	29850	0.0	-
5.1172	29900	0.0	-
5.1258	29950	0.0	-
5.1343	30000	0.0	-
5.1429	30050	0.0	-
5.1515	30100	0.0	-
5.1600	30150	0.0	-
5.1686	30200	0.0	-
5.1771	30250	0.0	-
5.1857	30300	0.0	-
5.1942	30350	0.0	-
5.2028	30400	0.0	-
5.2114	30450	0.0	-
5.2199	30500	0.0	-
5.2285	30550	0.0	-
5.2370	30600	0.0	-
5.2456	30650	0.0	-
5.2542	30700	0.0	-
5.2627	30750	0.0	-
5.2713	30800	0.0	-
5.2798	30850	0.0	-
5.2884	30900	0.0	-
5.2969	30950	0.0	-
5.3055	31000	0.0	-
5.3141	31050	0.0	-
5.3226	31100	0.0	-
5.3312	31150	0.0	-
5.3397	31200	0.0	-
5.3483	31250	0.0	-
5.3568	31300	0.0	-
5.3654	31350	0.0	-
5.3740	31400	0.0	-
5.3825	31450	0.0	-
5.3911	31500	0.0	-
5.3996	31550	0.0	-
5.4082	31600	0.0	-
5.4167	31650	0.0	-
5.4253	31700	0.0	-
5.4339	31750	0.0	-
5.4424	31800	0.0	-
5.4510	31850	0.0	-
5.4595	31900	0.0	-
5.4681	31950	0.0	-
5.4766	32000	0.0	-
5.4852	32050	0.0	-
5.4938	32100	0.0	-
5.5023	32150	0.0	-
5.5109	32200	0.0	-
5.5194	32250	0.0	-
5.5280	32300	0.0	-
5.5365	32350	0.0	-
5.5451	32400	0.0	-
5.5537	32450	0.0	-
5.5622	32500	0.0	-
5.5708	32550	0.0	-
5.5793	32600	0.0	-
5.5879	32650	0.0	-
5.5964	32700	0.0	-
5.6050	32750	0.0	-
5.6136	32800	0.0	-
5.6221	32850	0.0	-
5.6307	32900	0.0	-
5.6392	32950	0.0	-
5.6478	33000	0.0	-
5.6563	33050	0.0	-
5.6649	33100	0.0	-
5.6735	33150	0.0	-
5.6820	33200	0.0	-
5.6906	33250	0.0	-
5.6991	33300	0.0	-
5.7077	33350	0.0	-
5.7162	33400	0.0	-
5.7248	33450	0.0	-
5.7334	33500	0.0	-
5.7419	33550	0.0	-
5.7505	33600	0.0	-
5.7590	33650	0.0	-
5.7676	33700	0.0	-
5.7761	33750	0.0	-
5.7847	33800	0.0	-
5.7933	33850	0.0	-
5.8018	33900	0.0	-
5.8104	33950	0.0	-
5.8189	34000	0.0	-
5.8275	34050	0.0	-
5.8360	34100	0.0	-
5.8446	34150	0.0	-
5.8532	34200	0.0	-
5.8617	34250	0.0	-
5.8703	34300	0.0	-
5.8788	34350	0.0	-
5.8874	34400	0.0	-
5.8959	34450	0.0	-
5.9045	34500	0.0	-
5.9131	34550	0.0	-
5.9216	34600	0.0	-
5.9302	34650	0.0	-
5.9387	34700	0.0	-
5.9473	34750	0.0	-
5.9558	34800	0.0	-
5.9644	34850	0.0	-
5.9730	34900	0.0	-
5.9815	34950	0.0	-
5.9901	35000	0.0	-
5.9986	35050	0.0	-
6.0	35058	-	0.3336
6.0072	35100	0.0	-
6.0157	35150	0.0	-
6.0243	35200	0.0	-
6.0329	35250	0.0	-
6.0414	35300	0.0	-
6.0500	35350	0.0	-
6.0585	35400	0.0	-
6.0671	35450	0.0	-
6.0756	35500	0.0	-
6.0842	35550	0.0	-
6.0928	35600	0.0	-
6.1013	35650	0.0	-
6.1099	35700	0.0	-
6.1184	35750	0.0	-
6.1270	35800	0.0	-
6.1355	35850	0.0	-
6.1441	35900	0.0	-
6.1527	35950	0.0	-
6.1612	36000	0.0	-
6.1698	36050	0.0	-
6.1783	36100	0.0	-
6.1869	36150	0.0	-
6.1954	36200	0.0	-
6.2040	36250	0.0	-
6.2126	36300	0.0	-
6.2211	36350	0.0	-
6.2297	36400	0.0	-
6.2382	36450	0.0	-
6.2468	36500	0.0	-
6.2553	36550	0.0	-
6.2639	36600	0.0	-
6.2725	36650	0.0	-
6.2810	36700	0.0	-
6.2896	36750	0.0	-
6.2981	36800	0.0	-
6.3067	36850	0.0	-
6.3152	36900	0.0	-
6.3238	36950	0.0	-
6.3324	37000	0.0	-
6.3409	37050	0.0	-
6.3495	37100	0.0	-
6.3580	37150	0.0	-
6.3666	37200	0.0	-
6.3751	37250	0.0	-
6.3837	37300	0.0	-
6.3923	37350	0.0	-
6.4008	37400	0.0	-
6.4094	37450	0.0	-
6.4179	37500	0.0	-
6.4265	37550	0.0	-
6.4351	37600	0.0	-
6.4436	37650	0.0	-
6.4522	37700	0.0	-
6.4607	37750	0.0	-
6.4693	37800	0.0	-
6.4778	37850	0.0	-
6.4864	37900	0.0	-
6.4950	37950	0.0	-
6.5035	38000	0.0	-
6.5121	38050	0.0	-
6.5206	38100	0.0	-
6.5292	38150	0.0	-
6.5377	38200	0.0	-
6.5463	38250	0.0	-
6.5549	38300	0.0	-
6.5634	38350	0.0	-
6.5720	38400	0.0	-
6.5805	38450	0.0	-
6.5891	38500	0.0	-
6.5976	38550	0.0	-
6.6062	38600	0.0	-
6.6148	38650	0.0	-
6.6233	38700	0.0	-
6.6319	38750	0.0	-
6.6404	38800	0.0	-
6.6490	38850	0.0	-
6.6575	38900	0.0	-
6.6661	38950	0.0	-
6.6747	39000	0.0	-
6.6832	39050	0.0	-
6.6918	39100	0.0	-
6.7003	39150	0.0	-
6.7089	39200	0.0	-
6.7174	39250	0.0	-
6.7260	39300	0.0	-
6.7346	39350	0.0	-
6.7431	39400	0.0	-
6.7517	39450	0.0	-
6.7602	39500	0.0	-
6.7688	39550	0.0	-
6.7773	39600	0.0	-
6.7859	39650	0.0	-
6.7945	39700	0.0	-
6.8030	39750	0.0	-
6.8116	39800	0.0	-
6.8201	39850	0.0	-
6.8287	39900	0.0	-
6.8372	39950	0.0	-
6.8458	40000	0.0	-
6.8544	40050	0.0	-
6.8629	40100	0.0	-
6.8715	40150	0.0	-
6.8800	40200	0.0	-
6.8886	40250	0.0	-
6.8971	40300	0.0	-
6.9057	40350	0.0	-
6.9143	40400	0.0	-
6.9228	40450	0.0	-
6.9314	40500	0.0	-
6.9399	40550	0.0	-
6.9485	40600	0.0	-
6.9570	40650	0.0	-
6.9656	40700	0.0	-
6.9742	40750	0.0	-
6.9827	40800	0.0	-
6.9913	40850	0.0	-
6.9998	40900	0.0	-
7.0	40901	-	0.3312

• 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}
}