metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      ketika Leguizamo akhirnya memasang karakter yang menjengkelkan di akhir
      film.
  - text: ini adalah perjalanan yang menawan dan sering kali memberi kesan.
  - text: >-
      hanya sedikit film yang menangkap dengan sempurna harapan dan impian
      anak-anak lelaki di lapangan bisbol serta para lelaki dewasa yang duduk di
      tribun.
  - text: holden caulfield melakukannya dengan lebih baik.
  - text: >-
      tapi jika diambil sebagai one-shot yang penuh gaya dan energik, ratu
      terkutuk ini tidak bisa dikatakan payah.
pipeline_tag: text-classification
inference: true
base_model: firqaaa/indo-sentence-bert-base
model-index:
  - name: SetFit with firqaaa/indo-sentence-bert-base
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.8171334431630972
            name: Accuracy

SetFit with firqaaa/indo-sentence-bert-base

This is a SetFit model that can be used for Text Classification. This SetFit model uses firqaaa/indo-sentence-bert-base 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: firqaaa/indo-sentence-bert-base
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 2 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	'secara implisit mengakui dan merayakan kelicikan dan khayalan diri yang luar biasa dari sebagian besar pebisnis Amerika ini, dan oleh karena itu, dokumen ini mungkin merupakan dokumen Hollywood yang paling jujur \u200b\u200bdan aneh dari semuanya.' 'sebuah potret menarik dari para seniman tanpa kompromi yang mencoba menciptakan sesuatu yang orisinal dengan latar belakang industri musik korporat yang tampaknya hanya peduli pada keuntungan.' 'mengerikan dalam potret obyektif Amerika abad kedua puluh satu yang suram dan hilang.'
negatif	'dengan hari-hari anjing di bulan Agustus yang akan datang, anggaplah film anjing ini setara dengan sinematik dengan kelembapan tinggi.' 'itu kelam dan mudah ditebak, dan tidak banyak yang bisa tertawa.' 'pencapaian film yang paling mustahil?'

Label

Examples

positif

'secara implisit mengakui dan merayakan kelicikan dan khayalan diri yang luar biasa dari sebagian besar pebisnis Amerika ini, dan oleh karena itu, dokumen ini mungkin merupakan dokumen Hollywood yang paling jujur \u200b\u200bdan aneh dari semuanya.'
'sebuah potret menarik dari para seniman tanpa kompromi yang mencoba menciptakan sesuatu yang orisinal dengan latar belakang industri musik korporat yang tampaknya hanya peduli pada keuntungan.'
'mengerikan dalam potret obyektif Amerika abad kedua puluh satu yang suram dan hilang.'

negatif

'dengan hari-hari anjing di bulan Agustus yang akan datang, anggaplah film anjing ini setara dengan sinematik dengan kelembapan tinggi.'
'itu kelam dan mudah ditebak, dan tidak banyak yang bisa tertawa.'
'pencapaian film yang paling mustahil?'

Evaluation

Metrics

Label	Accuracy
all	0.8171

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("firqaaa/indo-setfit-bert-base-p1")
# Run inference
preds = model("holden caulfield melakukannya dengan lebih baik.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	16.073	45

Label	Training Sample Count
negatif	500
positif	500

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (3, 3)
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	0.3943	-
0.0032	50	0.3398	-
0.0064	100	0.2628	-
0.0096	150	0.2842	-
0.0128	200	0.2317	-
0.0160	250	0.2703	-
0.0192	300	0.2272	-
0.0224	350	0.2496	-
0.0255	400	0.2076	-
0.0287	450	0.207	-
0.0319	500	0.232	-
0.0351	550	0.1439	-
0.0383	600	0.1578	-
0.0415	650	0.0821	-
0.0447	700	0.0628	-
0.0479	750	0.0315	-
0.0511	800	0.0089	-
0.0543	850	0.0106	-
0.0575	900	0.0026	-
0.0607	950	0.0025	-
0.0639	1000	0.0028	-
0.0671	1050	0.0093	-
0.0703	1100	0.0008	-
0.0734	1150	0.0008	-
0.0766	1200	0.0003	-
0.0798	1250	0.0006	-
0.0830	1300	0.0005	-
0.0862	1350	0.0005	-
0.0894	1400	0.0002	-
0.0926	1450	0.0003	-
0.0958	1500	0.0003	-
0.0990	1550	0.0003	-
0.1022	1600	0.0002	-
0.1054	1650	0.0002	-
0.1086	1700	0.0001	-
0.1118	1750	0.0002	-
0.1150	1800	0.0001	-
0.1182	1850	0.0001	-
0.1214	1900	0.0001	-
0.1245	1950	0.0001	-
0.1277	2000	0.0001	-
0.1309	2050	0.0001	-
0.1341	2100	0.0001	-
0.1373	2150	0.0001	-
0.1405	2200	0.0001	-
0.1437	2250	0.0001	-
0.1469	2300	0.0001	-
0.1501	2350	0.0001	-
0.1533	2400	0.0001	-
0.1565	2450	0.0002	-
0.1597	2500	0.0001	-
0.1629	2550	0.0001	-
0.1661	2600	0.0134	-
0.1693	2650	0.0001	-
0.1724	2700	0.0001	-
0.1756	2750	0.0016	-
0.1788	2800	0.0001	-
0.1820	2850	0.0001	-
0.1852	2900	0.0002	-
0.1884	2950	0.0001	-
0.1916	3000	0.0066	-
0.1948	3050	0.0001	-
0.1980	3100	0.0001	-
0.2012	3150	0.0005	-
0.2044	3200	0.0001	-
0.2076	3250	0.0001	-
0.2108	3300	0.0001	-
0.2140	3350	0.0001	-
0.2172	3400	0.0001	-
0.2203	3450	0.0	-
0.2235	3500	0.0001	-
0.2267	3550	0.0	-
0.2299	3600	0.0	-
0.2331	3650	0.021	-
0.2363	3700	0.0001	-
0.2395	3750	0.0	-
0.2427	3800	0.0	-
0.2459	3850	0.0	-
0.2491	3900	0.0	-
0.2523	3950	0.0	-
0.2555	4000	0.0	-
0.2587	4050	0.0001	-
0.2619	4100	0.0	-
0.2651	4150	0.0	-
0.2683	4200	0.0016	-
0.2714	4250	0.0	-
0.2746	4300	0.001	-
0.2778	4350	0.0001	-
0.2810	4400	0.0002	-
0.2842	4450	0.0	-
0.2874	4500	0.0001	-
0.2906	4550	0.0001	-
0.2938	4600	0.0002	-
0.2970	4650	0.0	-
0.3002	4700	0.0305	-
0.3034	4750	0.0	-
0.3066	4800	0.0	-
0.3098	4850	0.0	-
0.3130	4900	0.0	-
0.3162	4950	0.0	-
0.3193	5000	0.0	-
0.3225	5050	0.0	-
0.3257	5100	0.0	-
0.3289	5150	0.0	-
0.3321	5200	0.0	-
0.3353	5250	0.0	-
0.3385	5300	0.0	-
0.3417	5350	0.0	-
0.3449	5400	0.0	-
0.3481	5450	0.0	-
0.3513	5500	0.0	-
0.3545	5550	0.0	-
0.3577	5600	0.0	-
0.3609	5650	0.0	-
0.3641	5700	0.0	-
0.3672	5750	0.0	-
0.3704	5800	0.0	-
0.3736	5850	0.0001	-
0.3768	5900	0.0	-
0.3800	5950	0.0	-
0.3832	6000	0.0	-
0.3864	6050	0.0	-
0.3896	6100	0.0	-
0.3928	6150	0.0001	-
0.3960	6200	0.0002	-
0.3992	6250	0.0	-
0.4024	6300	0.0	-
0.4056	6350	0.0	-
0.4088	6400	0.0	-
0.4120	6450	0.0	-
0.4151	6500	0.0	-
0.4183	6550	0.0	-
0.4215	6600	0.0	-
0.4247	6650	0.0	-
0.4279	6700	0.0	-
0.4311	6750	0.0	-
0.4343	6800	0.0	-
0.4375	6850	0.0	-
0.4407	6900	0.0	-
0.4439	6950	0.0	-
0.4471	7000	0.0	-
0.4503	7050	0.0	-
0.4535	7100	0.0	-
0.4567	7150	0.0	-
0.4599	7200	0.0	-
0.4631	7250	0.0	-
0.4662	7300	0.0	-
0.4694	7350	0.0	-
0.4726	7400	0.0	-
0.4758	7450	0.0	-
0.4790	7500	0.0	-
0.4822	7550	0.0	-
0.4854	7600	0.0	-
0.4886	7650	0.0	-
0.4918	7700	0.0	-
0.4950	7750	0.0	-
0.4982	7800	0.0	-
0.5014	7850	0.0	-
0.5046	7900	0.0	-
0.5078	7950	0.0	-
0.5110	8000	0.0	-
0.5141	8050	0.0	-
0.5173	8100	0.0	-
0.5205	8150	0.0	-
0.5237	8200	0.0	-
0.5269	8250	0.0	-
0.5301	8300	0.0	-
0.5333	8350	0.0	-
0.5365	8400	0.0	-
0.5397	8450	0.0	-
0.5429	8500	0.0	-
0.5461	8550	0.0	-
0.5493	8600	0.0	-
0.5525	8650	0.0	-
0.5557	8700	0.0	-
0.5589	8750	0.0	-
0.5620	8800	0.0	-
0.5652	8850	0.0	-
0.5684	8900	0.0	-
0.5716	8950	0.0	-
0.5748	9000	0.0	-
0.5780	9050	0.0	-
0.5812	9100	0.0	-
0.5844	9150	0.0	-
0.5876	9200	0.0	-
0.5908	9250	0.0	-
0.5940	9300	0.0	-
0.5972	9350	0.0	-
0.6004	9400	0.0	-
0.6036	9450	0.0	-
0.6068	9500	0.0	-
0.6100	9550	0.0	-
0.6131	9600	0.0	-
0.6163	9650	0.0	-
0.6195	9700	0.0	-
0.6227	9750	0.0	-
0.6259	9800	0.0	-
0.6291	9850	0.0	-
0.6323	9900	0.0	-
0.6355	9950	0.0	-
0.6387	10000	0.0	-
0.6419	10050	0.0	-
0.6451	10100	0.0	-
0.6483	10150	0.0	-
0.6515	10200	0.0	-
0.6547	10250	0.0	-
0.6579	10300	0.0	-
0.6610	10350	0.0	-
0.6642	10400	0.0	-
0.6674	10450	0.0	-
0.6706	10500	0.0	-
0.6738	10550	0.0	-
0.6770	10600	0.0	-
0.6802	10650	0.0	-
0.6834	10700	0.0	-
0.6866	10750	0.0	-
0.6898	10800	0.0	-
0.6930	10850	0.0	-
0.6962	10900	0.0	-
0.6994	10950	0.0	-
0.7026	11000	0.0	-
0.7058	11050	0.0	-
0.7089	11100	0.0	-
0.7121	11150	0.0	-
0.7153	11200	0.0	-
0.7185	11250	0.0	-
0.7217	11300	0.0	-
0.7249	11350	0.0	-
0.7281	11400	0.0	-
0.7313	11450	0.0	-
0.7345	11500	0.0	-
0.7377	11550	0.0	-
0.7409	11600	0.0	-
0.7441	11650	0.0	-
0.7473	11700	0.0	-
0.7505	11750	0.0	-
0.7537	11800	0.0	-
0.7568	11850	0.0	-
0.7600	11900	0.0	-
0.7632	11950	0.0	-
0.7664	12000	0.0	-
0.7696	12050	0.0	-
0.7728	12100	0.0	-
0.7760	12150	0.0	-
0.7792	12200	0.0	-
0.7824	12250	0.0	-
0.7856	12300	0.0	-
0.7888	12350	0.0	-
0.7920	12400	0.0	-
0.7952	12450	0.0	-
0.7984	12500	0.0	-
0.8016	12550	0.0	-
0.8048	12600	0.0	-
0.8079	12650	0.0	-
0.8111	12700	0.0	-
0.8143	12750	0.0	-
0.8175	12800	0.0	-
0.8207	12850	0.0	-
0.8239	12900	0.0	-
0.8271	12950	0.0	-
0.8303	13000	0.0	-
0.8335	13050	0.0	-
0.8367	13100	0.0	-
0.8399	13150	0.0	-
0.8431	13200	0.0	-
0.8463	13250	0.0	-
0.8495	13300	0.0	-
0.8527	13350	0.0	-
0.8558	13400	0.0	-
0.8590	13450	0.0	-
0.8622	13500	0.0	-
0.8654	13550	0.0	-
0.8686	13600	0.0	-
0.8718	13650	0.0	-
0.8750	13700	0.0	-
0.8782	13750	0.0	-
0.8814	13800	0.0	-
0.8846	13850	0.0	-
0.8878	13900	0.0	-
0.8910	13950	0.0	-
0.8942	14000	0.0	-
0.8974	14050	0.0	-
0.9006	14100	0.0	-
0.9037	14150	0.0	-
0.9069	14200	0.0	-
0.9101	14250	0.0	-
0.9133	14300	0.0	-
0.9165	14350	0.0	-
0.9197	14400	0.0	-
0.9229	14450	0.0	-
0.9261	14500	0.0	-
0.9293	14550	0.0	-
0.9325	14600	0.0	-
0.9357	14650	0.0	-
0.9389	14700	0.0	-
0.9421	14750	0.0	-
0.9453	14800	0.0	-
0.9485	14850	0.0	-
0.9517	14900	0.0	-
0.9548	14950	0.0	-
0.9580	15000	0.0	-
0.9612	15050	0.0	-
0.9644	15100	0.0	-
0.9676	15150	0.0	-
0.9708	15200	0.0	-
0.9740	15250	0.0	-
0.9772	15300	0.0	-
0.9804	15350	0.0	-
0.9836	15400	0.0	-
0.9868	15450	0.0	-
0.9900	15500	0.0	-
0.9932	15550	0.0	-
0.9964	15600	0.0	-
0.9996	15650	0.0	-
1.0	15657	-	0.2641
1.0027	15700	0.0	-
1.0059	15750	0.0	-
1.0091	15800	0.0	-
1.0123	15850	0.0	-
1.0155	15900	0.0	-
1.0187	15950	0.0	-
1.0219	16000	0.0	-
1.0251	16050	0.0	-
1.0283	16100	0.0	-
1.0315	16150	0.0	-
1.0347	16200	0.0	-
1.0379	16250	0.0	-
1.0411	16300	0.0	-
1.0443	16350	0.0	-
1.0475	16400	0.0	-
1.0506	16450	0.0	-
1.0538	16500	0.0	-
1.0570	16550	0.0	-
1.0602	16600	0.0	-
1.0634	16650	0.0	-
1.0666	16700	0.0	-
1.0698	16750	0.0	-
1.0730	16800	0.0	-
1.0762	16850	0.0	-
1.0794	16900	0.0	-
1.0826	16950	0.0	-
1.0858	17000	0.0	-
1.0890	17050	0.0	-
1.0922	17100	0.0	-
1.0954	17150	0.0	-
1.0986	17200	0.0	-
1.1017	17250	0.0	-
1.1049	17300	0.0	-
1.1081	17350	0.0	-
1.1113	17400	0.0	-
1.1145	17450	0.0	-
1.1177	17500	0.0	-
1.1209	17550	0.0	-
1.1241	17600	0.0	-
1.1273	17650	0.0	-
1.1305	17700	0.0	-
1.1337	17750	0.0	-
1.1369	17800	0.0	-
1.1401	17850	0.0	-
1.1433	17900	0.0	-
1.1465	17950	0.0	-
1.1496	18000	0.0	-
1.1528	18050	0.0	-
1.1560	18100	0.0	-
1.1592	18150	0.0	-
1.1624	18200	0.0	-
1.1656	18250	0.0	-
1.1688	18300	0.0	-
1.1720	18350	0.0	-
1.1752	18400	0.0	-
1.1784	18450	0.0	-
1.1816	18500	0.0	-
1.1848	18550	0.0	-
1.1880	18600	0.0	-
1.1912	18650	0.0	-
1.1944	18700	0.0	-
1.1975	18750	0.0	-
1.2007	18800	0.0	-
1.2039	18850	0.0	-
1.2071	18900	0.0	-
1.2103	18950	0.0	-
1.2135	19000	0.0	-
1.2167	19050	0.0	-
1.2199	19100	0.0	-
1.2231	19150	0.0	-
1.2263	19200	0.0	-
1.2295	19250	0.0	-
1.2327	19300	0.0	-
1.2359	19350	0.0	-
1.2391	19400	0.0	-
1.2423	19450	0.0	-
1.2454	19500	0.0	-
1.2486	19550	0.0	-
1.2518	19600	0.0	-
1.2550	19650	0.0	-
1.2582	19700	0.0	-
1.2614	19750	0.0	-
1.2646	19800	0.0	-
1.2678	19850	0.0	-
1.2710	19900	0.0	-
1.2742	19950	0.0	-
1.2774	20000	0.0	-
1.2806	20050	0.0	-
1.2838	20100	0.0	-
1.2870	20150	0.0	-
1.2902	20200	0.0	-
1.2934	20250	0.0	-
1.2965	20300	0.0	-
1.2997	20350	0.0	-
1.3029	20400	0.0	-
1.3061	20450	0.0	-
1.3093	20500	0.0	-
1.3125	20550	0.0	-
1.3157	20600	0.0	-
1.3189	20650	0.0	-
1.3221	20700	0.0	-
1.3253	20750	0.0	-
1.3285	20800	0.0	-
1.3317	20850	0.0	-
1.3349	20900	0.0	-
1.3381	20950	0.0	-
1.3413	21000	0.0	-
1.3444	21050	0.0	-
1.3476	21100	0.0	-
1.3508	21150	0.0	-
1.3540	21200	0.0	-
1.3572	21250	0.0	-
1.3604	21300	0.0	-
1.3636	21350	0.0	-
1.3668	21400	0.0	-
1.3700	21450	0.0	-
1.3732	21500	0.0	-
1.3764	21550	0.0	-
1.3796	21600	0.0	-
1.3828	21650	0.0	-
1.3860	21700	0.0	-
1.3892	21750	0.0	-
1.3923	21800	0.0	-
1.3955	21850	0.0	-
1.3987	21900	0.0	-
1.4019	21950	0.0	-
1.4051	22000	0.0	-
1.4083	22050	0.0	-
1.4115	22100	0.0	-
1.4147	22150	0.0	-
1.4179	22200	0.0	-
1.4211	22250	0.0	-
1.4243	22300	0.0	-
1.4275	22350	0.0	-
1.4307	22400	0.0	-
1.4339	22450	0.0	-
1.4371	22500	0.0	-
1.4403	22550	0.0	-
1.4434	22600	0.0	-
1.4466	22650	0.0	-
1.4498	22700	0.0	-
1.4530	22750	0.0	-
1.4562	22800	0.0	-
1.4594	22850	0.0	-
1.4626	22900	0.0	-
1.4658	22950	0.0	-
1.4690	23000	0.0	-
1.4722	23050	0.0	-
1.4754	23100	0.0	-
1.4786	23150	0.0	-
1.4818	23200	0.0	-
1.4850	23250	0.0	-
1.4882	23300	0.0	-
1.4913	23350	0.0	-
1.4945	23400	0.0	-
1.4977	23450	0.0	-
1.5009	23500	0.0	-
1.5041	23550	0.0	-
1.5073	23600	0.0	-
1.5105	23650	0.0	-
1.5137	23700	0.0	-
1.5169	23750	0.0	-
1.5201	23800	0.0	-
1.5233	23850	0.0	-
1.5265	23900	0.0002	-
1.5297	23950	0.0003	-
1.5329	24000	0.0	-
1.5361	24050	0.0	-
1.5392	24100	0.0	-
1.5424	24150	0.0	-
1.5456	24200	0.0	-
1.5488	24250	0.0	-
1.5520	24300	0.0	-
1.5552	24350	0.0	-
1.5584	24400	0.0	-
1.5616	24450	0.0	-
1.5648	24500	0.0	-
1.5680	24550	0.0	-
1.5712	24600	0.0	-
1.5744	24650	0.0	-
1.5776	24700	0.0	-
1.5808	24750	0.0	-
1.5840	24800	0.0	-
1.5871	24850	0.0	-
1.5903	24900	0.0	-
1.5935	24950	0.0	-
1.5967	25000	0.0	-
1.5999	25050	0.0	-
1.6031	25100	0.0	-
1.6063	25150	0.0	-
1.6095	25200	0.0	-
1.6127	25250	0.0	-
1.6159	25300	0.0	-
1.6191	25350	0.0	-
1.6223	25400	0.0	-
1.6255	25450	0.0	-
1.6287	25500	0.0	-
1.6319	25550	0.0	-
1.6351	25600	0.0	-
1.6382	25650	0.0	-
1.6414	25700	0.0	-
1.6446	25750	0.0	-
1.6478	25800	0.0	-
1.6510	25850	0.0	-
1.6542	25900	0.0	-
1.6574	25950	0.0	-
1.6606	26000	0.0	-
1.6638	26050	0.0	-
1.6670	26100	0.0	-
1.6702	26150	0.0	-
1.6734	26200	0.0	-
1.6766	26250	0.0	-
1.6798	26300	0.0	-
1.6830	26350	0.0	-
1.6861	26400	0.0	-
1.6893	26450	0.0	-
1.6925	26500	0.0	-
1.6957	26550	0.0	-
1.6989	26600	0.0001	-
1.7021	26650	0.0	-
1.7053	26700	0.0	-
1.7085	26750	0.0	-
1.7117	26800	0.0	-
1.7149	26850	0.0	-
1.7181	26900	0.0	-
1.7213	26950	0.0	-
1.7245	27000	0.0	-
1.7277	27050	0.0	-
1.7309	27100	0.0	-
1.7340	27150	0.0	-
1.7372	27200	0.0	-
1.7404	27250	0.0	-
1.7436	27300	0.0	-
1.7468	27350	0.0	-
1.7500	27400	0.0	-
1.7532	27450	0.0	-
1.7564	27500	0.0	-
1.7596	27550	0.0	-
1.7628	27600	0.0	-
1.7660	27650	0.0	-
1.7692	27700	0.0	-
1.7724	27750	0.0	-
1.7756	27800	0.0	-
1.7788	27850	0.0	-
1.7820	27900	0.0	-
1.7851	27950	0.0	-
1.7883	28000	0.0	-
1.7915	28050	0.0	-
1.7947	28100	0.0	-
1.7979	28150	0.0	-
1.8011	28200	0.0	-
1.8043	28250	0.0	-
1.8075	28300	0.0	-
1.8107	28350	0.0	-
1.8139	28400	0.0	-
1.8171	28450	0.0	-
1.8203	28500	0.0	-
1.8235	28550	0.0	-
1.8267	28600	0.0	-
1.8299	28650	0.0	-
1.8330	28700	0.0	-
1.8362	28750	0.0	-
1.8394	28800	0.0	-
1.8426	28850	0.0	-
1.8458	28900	0.0	-
1.8490	28950	0.0	-
1.8522	29000	0.0	-
1.8554	29050	0.0	-
1.8586	29100	0.0	-
1.8618	29150	0.0	-
1.8650	29200	0.0	-
1.8682	29250	0.0	-
1.8714	29300	0.0	-
1.8746	29350	0.0	-
1.8778	29400	0.0	-
1.8809	29450	0.0	-
1.8841	29500	0.0	-
1.8873	29550	0.0	-
1.8905	29600	0.0	-
1.8937	29650	0.0	-
1.8969	29700	0.0	-
1.9001	29750	0.0	-
1.9033	29800	0.0	-
1.9065	29850	0.0	-
1.9097	29900	0.0	-
1.9129	29950	0.0	-
1.9161	30000	0.0	-
1.9193	30050	0.0	-
1.9225	30100	0.0	-
1.9257	30150	0.0	-
1.9288	30200	0.0	-
1.9320	30250	0.0	-
1.9352	30300	0.0	-
1.9384	30350	0.0	-
1.9416	30400	0.0	-
1.9448	30450	0.0	-
1.9480	30500	0.0	-
1.9512	30550	0.0	-
1.9544	30600	0.0	-
1.9576	30650	0.0	-
1.9608	30700	0.0	-
1.9640	30750	0.0	-
1.9672	30800	0.0	-
1.9704	30850	0.0	-
1.9736	30900	0.0	-
1.9768	30950	0.0	-
1.9799	31000	0.0	-
1.9831	31050	0.0	-
1.9863	31100	0.0	-
1.9895	31150	0.0	-
1.9927	31200	0.0	-
1.9959	31250	0.0	-
1.9991	31300	0.0	-
2.0	31314	-	0.2634
2.0023	31350	0.0	-
2.0055	31400	0.0	-
2.0087	31450	0.0	-
2.0119	31500	0.0	-
2.0151	31550	0.0	-
2.0183	31600	0.0	-
2.0215	31650	0.0	-
2.0247	31700	0.0	-
2.0278	31750	0.0	-
2.0310	31800	0.0	-
2.0342	31850	0.0	-
2.0374	31900	0.0	-
2.0406	31950	0.0	-
2.0438	32000	0.0	-
2.0470	32050	0.0	-
2.0502	32100	0.0	-
2.0534	32150	0.0	-
2.0566	32200	0.0	-
2.0598	32250	0.0	-
2.0630	32300	0.0	-
2.0662	32350	0.0	-
2.0694	32400	0.0	-
2.0726	32450	0.0	-
2.0757	32500	0.0	-
2.0789	32550	0.0	-
2.0821	32600	0.0	-
2.0853	32650	0.0	-
2.0885	32700	0.0	-
2.0917	32750	0.0	-
2.0949	32800	0.0	-
2.0981	32850	0.0	-
2.1013	32900	0.0	-
2.1045	32950	0.0	-
2.1077	33000	0.0	-
2.1109	33050	0.0	-
2.1141	33100	0.0	-
2.1173	33150	0.0	-
2.1205	33200	0.0	-
2.1237	33250	0.0	-
2.1268	33300	0.0	-
2.1300	33350	0.0	-
2.1332	33400	0.0	-
2.1364	33450	0.0	-
2.1396	33500	0.0	-
2.1428	33550	0.0	-
2.1460	33600	0.0	-
2.1492	33650	0.0	-
2.1524	33700	0.0	-
2.1556	33750	0.0	-
2.1588	33800	0.0	-
2.1620	33850	0.0	-
2.1652	33900	0.0	-
2.1684	33950	0.0	-
2.1716	34000	0.0	-
2.1747	34050	0.0	-
2.1779	34100	0.0	-
2.1811	34150	0.0	-
2.1843	34200	0.0	-
2.1875	34250	0.0	-
2.1907	34300	0.0	-
2.1939	34350	0.0	-
2.1971	34400	0.0	-
2.2003	34450	0.0	-
2.2035	34500	0.0	-
2.2067	34550	0.0	-
2.2099	34600	0.0	-
2.2131	34650	0.0	-
2.2163	34700	0.0	-
2.2195	34750	0.0	-
2.2226	34800	0.0	-
2.2258	34850	0.0	-
2.2290	34900	0.0	-
2.2322	34950	0.0	-
2.2354	35000	0.0	-
2.2386	35050	0.0	-
2.2418	35100	0.0	-
2.2450	35150	0.0	-
2.2482	35200	0.0	-
2.2514	35250	0.0	-
2.2546	35300	0.0	-
2.2578	35350	0.0	-
2.2610	35400	0.0	-
2.2642	35450	0.0	-
2.2674	35500	0.0	-
2.2705	35550	0.0	-
2.2737	35600	0.0	-
2.2769	35650	0.0	-
2.2801	35700	0.0	-
2.2833	35750	0.0	-
2.2865	35800	0.0	-
2.2897	35850	0.0	-
2.2929	35900	0.0	-
2.2961	35950	0.0	-
2.2993	36000	0.0	-
2.3025	36050	0.0	-
2.3057	36100	0.0	-
2.3089	36150	0.0	-
2.3121	36200	0.0	-
2.3153	36250	0.0	-
2.3185	36300	0.0	-
2.3216	36350	0.0	-
2.3248	36400	0.0	-
2.3280	36450	0.0	-
2.3312	36500	0.0	-
2.3344	36550	0.0	-
2.3376	36600	0.0	-
2.3408	36650	0.0	-
2.3440	36700	0.0	-
2.3472	36750	0.0	-
2.3504	36800	0.0	-
2.3536	36850	0.0	-
2.3568	36900	0.0	-
2.3600	36950	0.0	-
2.3632	37000	0.0	-
2.3664	37050	0.0	-
2.3695	37100	0.0	-
2.3727	37150	0.0	-
2.3759	37200	0.0	-
2.3791	37250	0.0	-
2.3823	37300	0.0	-
2.3855	37350	0.0	-
2.3887	37400	0.0	-
2.3919	37450	0.0	-
2.3951	37500	0.0	-
2.3983	37550	0.0	-
2.4015	37600	0.0	-
2.4047	37650	0.0	-
2.4079	37700	0.0	-
2.4111	37750	0.0	-
2.4143	37800	0.0	-
2.4174	37850	0.0	-
2.4206	37900	0.0	-
2.4238	37950	0.0	-
2.4270	38000	0.0	-
2.4302	38050	0.0	-
2.4334	38100	0.0	-
2.4366	38150	0.0	-
2.4398	38200	0.0	-
2.4430	38250	0.0	-
2.4462	38300	0.0	-
2.4494	38350	0.0	-
2.4526	38400	0.0	-
2.4558	38450	0.0	-
2.4590	38500	0.0	-
2.4622	38550	0.0	-
2.4654	38600	0.0	-
2.4685	38650	0.0	-
2.4717	38700	0.0	-
2.4749	38750	0.0	-
2.4781	38800	0.0	-
2.4813	38850	0.0	-
2.4845	38900	0.0	-
2.4877	38950	0.0	-
2.4909	39000	0.0	-
2.4941	39050	0.0	-
2.4973	39100	0.0	-
2.5005	39150	0.0	-
2.5037	39200	0.0	-
2.5069	39250	0.0	-
2.5101	39300	0.0	-
2.5133	39350	0.0	-
2.5164	39400	0.0	-
2.5196	39450	0.0	-
2.5228	39500	0.0	-
2.5260	39550	0.0	-
2.5292	39600	0.0	-
2.5324	39650	0.0	-
2.5356	39700	0.0	-
2.5388	39750	0.0	-
2.5420	39800	0.0	-
2.5452	39850	0.0	-
2.5484	39900	0.0	-
2.5516	39950	0.0	-
2.5548	40000	0.0	-
2.5580	40050	0.0	-
2.5612	40100	0.0	-
2.5643	40150	0.0	-
2.5675	40200	0.0	-
2.5707	40250	0.0	-
2.5739	40300	0.0	-
2.5771	40350	0.0	-
2.5803	40400	0.0	-
2.5835	40450	0.0	-
2.5867	40500	0.0	-
2.5899	40550	0.0	-
2.5931	40600	0.0	-
2.5963	40650	0.0	-
2.5995	40700	0.0	-
2.6027	40750	0.0	-
2.6059	40800	0.0	-
2.6091	40850	0.0	-
2.6123	40900	0.0	-
2.6154	40950	0.0	-
2.6186	41000	0.0	-
2.6218	41050	0.0	-
2.6250	41100	0.0	-
2.6282	41150	0.0	-
2.6314	41200	0.0	-
2.6346	41250	0.0	-
2.6378	41300	0.0	-
2.6410	41350	0.0	-
2.6442	41400	0.0	-
2.6474	41450	0.0	-
2.6506	41500	0.0	-
2.6538	41550	0.0	-
2.6570	41600	0.0	-
2.6602	41650	0.0	-
2.6633	41700	0.0	-
2.6665	41750	0.0	-
2.6697	41800	0.0	-
2.6729	41850	0.0	-
2.6761	41900	0.0	-
2.6793	41950	0.0	-
2.6825	42000	0.0	-
2.6857	42050	0.0	-
2.6889	42100	0.0	-
2.6921	42150	0.0	-
2.6953	42200	0.0	-
2.6985	42250	0.0	-
2.7017	42300	0.0	-
2.7049	42350	0.0	-
2.7081	42400	0.0	-
2.7112	42450	0.0	-
2.7144	42500	0.0	-
2.7176	42550	0.0	-
2.7208	42600	0.0	-
2.7240	42650	0.0	-
2.7272	42700	0.0	-
2.7304	42750	0.0	-
2.7336	42800	0.0	-
2.7368	42850	0.0	-
2.7400	42900	0.0	-
2.7432	42950	0.0	-
2.7464	43000	0.0	-
2.7496	43050	0.0	-
2.7528	43100	0.0	-
2.7560	43150	0.0	-
2.7591	43200	0.0	-
2.7623	43250	0.0	-
2.7655	43300	0.0	-
2.7687	43350	0.0	-
2.7719	43400	0.0	-
2.7751	43450	0.0	-
2.7783	43500	0.0	-
2.7815	43550	0.0	-
2.7847	43600	0.0	-
2.7879	43650	0.0	-
2.7911	43700	0.0	-
2.7943	43750	0.0	-
2.7975	43800	0.0	-
2.8007	43850	0.0	-
2.8039	43900	0.0	-
2.8071	43950	0.0	-
2.8102	44000	0.0	-
2.8134	44050	0.0	-
2.8166	44100	0.0	-
2.8198	44150	0.0	-
2.8230	44200	0.0	-
2.8262	44250	0.0	-
2.8294	44300	0.0	-
2.8326	44350	0.0	-
2.8358	44400	0.0	-
2.8390	44450	0.0	-
2.8422	44500	0.0	-
2.8454	44550	0.0	-
2.8486	44600	0.0	-
2.8518	44650	0.0	-
2.8550	44700	0.0	-
2.8581	44750	0.0	-
2.8613	44800	0.0	-
2.8645	44850	0.0	-
2.8677	44900	0.0	-
2.8709	44950	0.0	-
2.8741	45000	0.0	-
2.8773	45050	0.0	-
2.8805	45100	0.0	-
2.8837	45150	0.0	-
2.8869	45200	0.0	-
2.8901	45250	0.0	-
2.8933	45300	0.0	-
2.8965	45350	0.0	-
2.8997	45400	0.0	-
2.9029	45450	0.0	-
2.9060	45500	0.0	-
2.9092	45550	0.0	-
2.9124	45600	0.0	-
2.9156	45650	0.0	-
2.9188	45700	0.0	-
2.9220	45750	0.0	-
2.9252	45800	0.0	-
2.9284	45850	0.0	-
2.9316	45900	0.0	-
2.9348	45950	0.0	-
2.9380	46000	0.0	-
2.9412	46050	0.0	-
2.9444	46100	0.0	-
2.9476	46150	0.0	-
2.9508	46200	0.0	-
2.9540	46250	0.0	-
2.9571	46300	0.0	-
2.9603	46350	0.0	-
2.9635	46400	0.0	-
2.9667	46450	0.0	-
2.9699	46500	0.0	-
2.9731	46550	0.0	-
2.9763	46600	0.0	-
2.9795	46650	0.0	-
2.9827	46700	0.0	-
2.9859	46750	0.0	-
2.9891	46800	0.0	-
2.9923	46850	0.0	-
2.9955	46900	0.0	-
2.9987	46950	0.0	-
3.0	46971	-	0.2651

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.13
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}
}