metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
widget:
  - text: >-
      man, product/whatever is my new best friend. i like product but the
      integration of product into office and product is a lot of fun. i just
      spent the day feeding it my training presentation i'm preparing in my day
      job and it was very helpful. almost better than humans.
  - text: >-
      that's great news! product is the perfect platform to share these advanced
      product prompts and help more users get the most out of it!
  - text: >-
      after only one week's trial of the new product with brand enabled, i have
      replaced my default browser product that i was using for more than 7 years
      with new product. i no longer need to spend a lot of time finding answers
      from a bunch of search results and web pages. it's amazing
  - text: >-
      very impressive. brand is finally fighting back. i am just a little
      worried about the scalability of such a high context window size, since
      even in their demos it took quite a while to process everything.
      regardless, i am very interested in seeing what types of capabilities a
      >1m token size window can unleash.
  - text: >-
      product the way it shows the sources is so fucking cool, this new ai is
      amazing
pipeline_tag: text-classification
inference: true
base_model: BAAI/bge-small-en-v1.5
model-index:
  - name: SetFit with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.964
            name: Accuracy
          - type: f1
            value:
              - 0.9130434782608695
              - 0.888888888888889
              - 0.9779951100244498
            name: F1
          - type: precision
            value:
              - 0.9545454545454546
              - 1
              - 0.9615384615384616
            name: Precision
          - type: recall
            value:
              - 0.875
              - 0.8
              - 0.9950248756218906
            name: Recall

SetFit with BAAI/bge-small-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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: BAAI/bge-small-en-v1.5
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
neither	'i asked brand to write it and then let it translate back. so in reality i have no clue what i am sending...' "i saw someone summarize brand the other day; it doesn't give answers, it gives answer-shaped responses." 'thank you comrade i mean colleague. i will have brand summarize.'
peak	'brand!! it helped me finish my resume. i just asked it if it could write my resume based on horribly written descriptions i came up with. and it made it all pretty:)' 'been building products for a bit now and your product (audio pen) is simple, useful and just works (like the early magic when product came out). congratulations and keep the flag flying high. not surprised that india is producing apps like yours. high time:-)' 'just got access to personalization in brand!! totally unexpected. very happy'
pit	'brand recently i came across a very unwell patient in a psychiatric unit who was using product & this was reinforcing his delusional state & detrimentally impacting his mental health. anyone looking into this type of usage of product? what safe guards are being put in place?' 'brand product is def better at extracting numbers from images, product failed (pro version) twice...' "the stuff brand gives is entirely too scripted and impractical, which is what i'm trying to avoid:/"

Evaluation

Metrics

Label	Accuracy	F1	Precision	Recall
all	0.964	[0.9130434782608695, 0.888888888888889, 0.9779951100244498]	[0.9545454545454546, 1.0, 0.9615384615384616]	[0.875, 0.8, 0.9950248756218906]

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("jamiehudson/725_model_v4")
# Run inference
preds = model("product the way it shows the sources is so fucking cool, this new ai is amazing")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	31.6606	98

Label	Training Sample Count
pit	277
peak	265
neither	1105

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (1, 1)
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: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0000	1	0.2683	-
0.0012	50	0.2643	-
0.0023	100	0.2432	-
0.0035	150	0.2623	-
0.0047	200	0.2527	-
0.0058	250	0.2252	-
0.0070	300	0.2362	-
0.0082	350	0.2334	-
0.0093	400	0.2189	-
0.0105	450	0.2144	-
0.0117	500	0.1971	-
0.0129	550	0.1565	-
0.0140	600	0.0816	-
0.0152	650	0.1417	-
0.0164	700	0.1051	-
0.0175	750	0.0686	-
0.0187	800	0.0394	-
0.0199	850	0.0947	-
0.0210	900	0.0468	-
0.0222	950	0.0143	-
0.0234	1000	0.0281	-
0.0245	1050	0.0329	-
0.0257	1100	0.0206	-
0.0269	1150	0.0113	-
0.0280	1200	0.0054	-
0.0292	1250	0.0056	-
0.0304	1300	0.0209	-
0.0315	1350	0.0064	-
0.0327	1400	0.0085	-
0.0339	1450	0.0025	-
0.0350	1500	0.0031	-
0.0362	1550	0.0024	-
0.0374	1600	0.0014	-
0.0386	1650	0.0019	-
0.0397	1700	0.0023	-
0.0409	1750	0.0014	-
0.0421	1800	0.002	-
0.0432	1850	0.001	-
0.0444	1900	0.001	-
0.0456	1950	0.0019	-
0.0467	2000	0.0017	-
0.0479	2050	0.001	-
0.0491	2100	0.0008	-
0.0502	2150	0.0011	-
0.0514	2200	0.0006	-
0.0526	2250	0.0012	-
0.0537	2300	0.0008	-
0.0549	2350	0.0014	-
0.0561	2400	0.0009	-
0.0572	2450	0.0009	-
0.0584	2500	0.001	-
0.0596	2550	0.0007	-
0.0607	2600	0.0007	-
0.0619	2650	0.0006	-
0.0631	2700	0.0004	-
0.0643	2750	0.0007	-
0.0654	2800	0.0005	-
0.0666	2850	0.0007	-
0.0678	2900	0.0007	-
0.0689	2950	0.0006	-
0.0701	3000	0.0005	-
0.0713	3050	0.0007	-
0.0724	3100	0.0008	-
0.0736	3150	0.0005	-
0.0748	3200	0.0005	-
0.0759	3250	0.0005	-
0.0771	3300	0.0006	-
0.0783	3350	0.0006	-
0.0794	3400	0.0006	-
0.0806	3450	0.0004	-
0.0818	3500	0.0005	-
0.0829	3550	0.0005	-
0.0841	3600	0.0005	-
0.0853	3650	0.0005	-
0.0864	3700	0.0006	-
0.0876	3750	0.0039	-
0.0888	3800	0.0004	-
0.0900	3850	0.0003	-
0.0911	3900	0.0004	-
0.0923	3950	0.0007	-
0.0935	4000	0.0003	-
0.0946	4050	0.0004	-
0.0958	4100	0.0003	-
0.0970	4150	0.0003	-
0.0981	4200	0.0004	-
0.0993	4250	0.0003	-
0.1005	4300	0.0004	-
0.1016	4350	0.0003	-
0.1028	4400	0.0004	-
0.1040	4450	0.0003	-
0.1051	4500	0.0004	-
0.1063	4550	0.0003	-
0.1075	4600	0.0003	-
0.1086	4650	0.0003	-
0.1098	4700	0.0003	-
0.1110	4750	0.0016	-
0.1121	4800	0.0003	-
0.1133	4850	0.0002	-
0.1145	4900	0.0003	-
0.1157	4950	0.0002	-
0.1168	5000	0.0003	-
0.1180	5050	0.0003	-
0.1192	5100	0.0003	-
0.1203	5150	0.0002	-
0.1215	5200	0.0003	-
0.1227	5250	0.0002	-
0.1238	5300	0.0178	-
0.1250	5350	0.0014	-
0.1262	5400	0.002	-
0.1273	5450	0.0002	-
0.1285	5500	0.0008	-
0.1297	5550	0.0003	-
0.1308	5600	0.0002	-
0.1320	5650	0.0002	-
0.1332	5700	0.0002	-
0.1343	5750	0.0003	-
0.1355	5800	0.0002	-
0.1367	5850	0.0003	-
0.1378	5900	0.0003	-
0.1390	5950	0.0002	-
0.1402	6000	0.0002	-
0.1414	6050	0.0002	-
0.1425	6100	0.0002	-
0.1437	6150	0.0002	-
0.1449	6200	0.0002	-
0.1460	6250	0.0019	-
0.1472	6300	0.0005	-
0.1484	6350	0.0002	-
0.1495	6400	0.0005	-
0.1507	6450	0.0003	-
0.1519	6500	0.0208	-
0.1530	6550	0.0003	-
0.1542	6600	0.0002	-
0.1554	6650	0.0002	-
0.1565	6700	0.0002	-
0.1577	6750	0.0002	-
0.1589	6800	0.0002	-
0.1600	6850	0.0002	-
0.1612	6900	0.0104	-
0.1624	6950	0.0001	-
0.1635	7000	0.0002	-
0.1647	7050	0.0002	-
0.1659	7100	0.0002	-
0.1671	7150	0.0001	-
0.1682	7200	0.0002	-
0.1694	7250	0.0002	-
0.1706	7300	0.0003	-
0.1717	7350	0.0002	-
0.1729	7400	0.0001	-
0.1741	7450	0.0001	-
0.1752	7500	0.0002	-
0.1764	7550	0.0004	-
0.1776	7600	0.0002	-
0.1787	7650	0.0005	-
0.1799	7700	0.0001	-
0.1811	7750	0.0002	-
0.1822	7800	0.0002	-
0.1834	7850	0.0001	-
0.1846	7900	0.0002	-
0.1857	7950	0.0002	-
0.1869	8000	0.0002	-
0.1881	8050	0.0001	-
0.1892	8100	0.0002	-
0.1904	8150	0.0001	-
0.1916	8200	0.0001	-
0.1928	8250	0.0001	-
0.1939	8300	0.0001	-
0.1951	8350	0.0001	-
0.1963	8400	0.0002	-
0.1974	8450	0.0002	-
0.1986	8500	0.0002	-
0.1998	8550	0.0002	-
0.2009	8600	0.0001	-
0.2021	8650	0.0001	-
0.2033	8700	0.0001	-
0.2044	8750	0.0001	-
0.2056	8800	0.0001	-
0.2068	8850	0.0001	-
0.2079	8900	0.0001	-
0.2091	8950	0.0001	-
0.2103	9000	0.0001	-
0.2114	9050	0.0001	-
0.2126	9100	0.0001	-
0.2138	9150	0.0001	-
0.2149	9200	0.0001	-
0.2161	9250	0.0002	-
0.2173	9300	0.0001	-
0.2185	9350	0.0002	-
0.2196	9400	0.0001	-
0.2208	9450	0.0001	-
0.2220	9500	0.0001	-
0.2231	9550	0.0001	-
0.2243	9600	0.0001	-
0.2255	9650	0.0002	-
0.2266	9700	0.0002	-
0.2278	9750	0.0001	-
0.2290	9800	0.0001	-
0.2301	9850	0.0002	-
0.2313	9900	0.0001	-
0.2325	9950	0.0001	-
0.2336	10000	0.0001	-
0.2348	10050	0.0001	-
0.2360	10100	0.0001	-
0.2371	10150	0.0001	-
0.2383	10200	0.0001	-
0.2395	10250	0.0001	-
0.2406	10300	0.0001	-
0.2418	10350	0.0001	-
0.2430	10400	0.0001	-
0.2442	10450	0.0001	-
0.2453	10500	0.0001	-
0.2465	10550	0.0001	-
0.2477	10600	0.0001	-
0.2488	10650	0.0001	-
0.2500	10700	0.0001	-
0.2512	10750	0.0001	-
0.2523	10800	0.0001	-
0.2535	10850	0.0001	-
0.2547	10900	0.0001	-
0.2558	10950	0.0001	-
0.2570	11000	0.0002	-
0.2582	11050	0.0001	-
0.2593	11100	0.0003	-
0.2605	11150	0.0001	-
0.2617	11200	0.0001	-
0.2628	11250	0.0001	-
0.2640	11300	0.0001	-
0.2652	11350	0.0001	-
0.2663	11400	0.0001	-
0.2675	11450	0.0001	-
0.2687	11500	0.0001	-
0.2699	11550	0.0001	-
0.2710	11600	0.0001	-
0.2722	11650	0.0001	-
0.2734	11700	0.0001	-
0.2745	11750	0.0001	-
0.2757	11800	0.0001	-
0.2769	11850	0.0001	-
0.2780	11900	0.0001	-
0.2792	11950	0.0001	-
0.2804	12000	0.0001	-
0.2815	12050	0.0001	-
0.2827	12100	0.0137	-
0.2839	12150	0.0001	-
0.2850	12200	0.0001	-
0.2862	12250	0.0001	-
0.2874	12300	0.0001	-
0.2885	12350	0.0001	-
0.2897	12400	0.0001	-
0.2909	12450	0.0001	-
0.2920	12500	0.0001	-
0.2932	12550	0.0001	-
0.2944	12600	0.0001	-
0.2956	12650	0.0001	-
0.2967	12700	0.0	-
0.2979	12750	0.0001	-
0.2991	12800	0.0001	-
0.3002	12850	0.0001	-
0.3014	12900	0.0001	-
0.3026	12950	0.0001	-
0.3037	13000	0.0001	-
0.3049	13050	0.0001	-
0.3061	13100	0.0001	-
0.3072	13150	0.0001	-
0.3084	13200	0.0001	-
0.3096	13250	0.0001	-
0.3107	13300	0.0001	-
0.3119	13350	0.0001	-
0.3131	13400	0.0001	-
0.3142	13450	0.0001	-
0.3154	13500	0.0001	-
0.3166	13550	0.0001	-
0.3177	13600	0.0001	-
0.3189	13650	0.0001	-
0.3201	13700	0.0001	-
0.3213	13750	0.0001	-
0.3224	13800	0.0001	-
0.3236	13850	0.0	-
0.3248	13900	0.0001	-
0.3259	13950	0.0001	-
0.3271	14000	0.0001	-
0.3283	14050	0.0002	-
0.3294	14100	0.0001	-
0.3306	14150	0.0001	-
0.3318	14200	0.0001	-
0.3329	14250	0.0001	-
0.3341	14300	0.0001	-
0.3353	14350	0.0001	-
0.3364	14400	0.0001	-
0.3376	14450	0.0001	-
0.3388	14500	0.0001	-
0.3399	14550	0.0001	-
0.3411	14600	0.0001	-
0.3423	14650	0.0001	-
0.3434	14700	0.0001	-
0.3446	14750	0.0001	-
0.3458	14800	0.0001	-
0.3470	14850	0.0001	-
0.3481	14900	0.0001	-
0.3493	14950	0.0	-
0.3505	15000	0.0001	-
0.3516	15050	0.0001	-
0.3528	15100	0.0	-
0.3540	15150	0.0001	-
0.3551	15200	0.0001	-
0.3563	15250	0.0001	-
0.3575	15300	0.0001	-
0.3586	15350	0.0001	-
0.3598	15400	0.0001	-
0.3610	15450	0.0001	-
0.3621	15500	0.0001	-
0.3633	15550	0.0001	-
0.3645	15600	0.0002	-
0.3656	15650	0.0001	-
0.3668	15700	0.0001	-
0.3680	15750	0.0001	-
0.3692	15800	0.0001	-
0.3703	15850	0.0001	-
0.3715	15900	0.0001	-
0.3727	15950	0.0	-
0.3738	16000	0.0	-
0.3750	16050	0.0	-
0.3762	16100	0.0	-
0.3773	16150	0.0001	-
0.3785	16200	0.0001	-
0.3797	16250	0.0001	-
0.3808	16300	0.0001	-
0.3820	16350	0.0001	-
0.3832	16400	0.0001	-
0.3843	16450	0.0	-
0.3855	16500	0.0001	-
0.3867	16550	0.0	-
0.3878	16600	0.0001	-
0.3890	16650	0.0001	-
0.3902	16700	0.0001	-
0.3913	16750	0.0001	-
0.3925	16800	0.0002	-
0.3937	16850	0.0002	-
0.3949	16900	0.0	-
0.3960	16950	0.0	-
0.3972	17000	0.0	-
0.3984	17050	0.0001	-
0.3995	17100	0.0001	-
0.4007	17150	0.0001	-
0.4019	17200	0.0001	-
0.4030	17250	0.0	-
0.4042	17300	0.0	-
0.4054	17350	0.0279	-
0.4065	17400	0.0	-
0.4077	17450	0.0	-
0.4089	17500	0.0	-
0.4100	17550	0.0	-
0.4112	17600	0.0001	-
0.4124	17650	0.0	-
0.4135	17700	0.028	-
0.4147	17750	0.0	-
0.4159	17800	0.0	-
0.4170	17850	0.0	-
0.4182	17900	0.0	-
0.4194	17950	0.0001	-
0.4206	18000	0.0	-
0.4217	18050	0.0	-
0.4229	18100	0.0001	-
0.4241	18150	0.0	-
0.4252	18200	0.0	-
0.4264	18250	0.0	-
0.4276	18300	0.0	-
0.4287	18350	0.0	-
0.4299	18400	0.0	-
0.4311	18450	0.0001	-
0.4322	18500	0.0001	-
0.4334	18550	0.0001	-
0.4346	18600	0.0001	-
0.4357	18650	0.0	-
0.4369	18700	0.0	-
0.4381	18750	0.0001	-
0.4392	18800	0.0001	-
0.4404	18850	0.0	-
0.4416	18900	0.0001	-
0.4427	18950	0.0001	-
0.4439	19000	0.0	-
0.4451	19050	0.0	-
0.4463	19100	0.0001	-
0.4474	19150	0.0	-
0.4486	19200	0.0001	-
0.4498	19250	0.0	-
0.4509	19300	0.0001	-
0.4521	19350	0.0001	-
0.4533	19400	0.0001	-
0.4544	19450	0.0	-
0.4556	19500	0.0001	-
0.4568	19550	0.0001	-
0.4579	19600	0.0001	-
0.4591	19650	0.0001	-
0.4603	19700	0.0001	-
0.4614	19750	0.0001	-
0.4626	19800	0.0	-
0.4638	19850	0.0	-
0.4649	19900	0.0001	-
0.4661	19950	0.0	-
0.4673	20000	0.0	-
0.4684	20050	0.0	-
0.4696	20100	0.0	-
0.4708	20150	0.0	-
0.4720	20200	0.0	-
0.4731	20250	0.0	-
0.4743	20300	0.0001	-
0.4755	20350	0.0001	-
0.4766	20400	0.0001	-
0.4778	20450	0.0	-
0.4790	20500	0.0	-
0.4801	20550	0.0001	-
0.4813	20600	0.0	-
0.4825	20650	0.0005	-
0.4836	20700	0.0001	-
0.4848	20750	0.0001	-
0.4860	20800	0.0	-
0.4871	20850	0.0001	-
0.4883	20900	0.0001	-
0.4895	20950	0.0	-
0.4906	21000	0.0	-
0.4918	21050	0.0	-
0.4930	21100	0.0	-
0.4941	21150	0.0001	-
0.4953	21200	0.0	-
0.4965	21250	0.0001	-
0.4977	21300	0.0	-
0.4988	21350	0.0001	-
0.5000	21400	0.0001	-
0.5012	21450	0.0	-
0.5023	21500	0.0	-
0.5035	21550	0.0	-
0.5047	21600	0.0001	-
0.5058	21650	0.0	-
0.5070	21700	0.0	-
0.5082	21750	0.0	-
0.5093	21800	0.0	-
0.5105	21850	0.0	-
0.5117	21900	0.0001	-
0.5128	21950	0.0	-
0.5140	22000	0.0	-
0.5152	22050	0.0	-
0.5163	22100	0.0	-
0.5175	22150	0.0	-
0.5187	22200	0.0001	-
0.5198	22250	0.0	-
0.5210	22300	0.0001	-
0.5222	22350	0.0	-
0.5234	22400	0.0001	-
0.5245	22450	0.0001	-
0.5257	22500	0.0	-
0.5269	22550	0.0	-
0.5280	22600	0.0	-
0.5292	22650	0.0	-
0.5304	22700	0.0	-
0.5315	22750	0.0	-
0.5327	22800	0.0	-
0.5339	22850	0.0	-
0.5350	22900	0.0001	-
0.5362	22950	0.0	-
0.5374	23000	0.0	-
0.5385	23050	0.0001	-
0.5397	23100	0.0	-
0.5409	23150	0.0	-
0.5420	23200	0.0001	-
0.5432	23250	0.0	-
0.5444	23300	0.0001	-
0.5455	23350	0.0001	-
0.5467	23400	0.0	-
0.5479	23450	0.0	-
0.5491	23500	0.0001	-
0.5502	23550	0.0	-
0.5514	23600	0.0001	-
0.5526	23650	0.0	-
0.5537	23700	0.0	-
0.5549	23750	0.0001	-
0.5561	23800	0.0	-
0.5572	23850	0.0	-
0.5584	23900	0.0	-
0.5596	23950	0.0	-
0.5607	24000	0.0	-
0.5619	24050	0.0	-
0.5631	24100	0.0001	-
0.5642	24150	0.0001	-
0.5654	24200	0.0	-
0.5666	24250	0.0	-
0.5677	24300	0.0001	-
0.5689	24350	0.0	-
0.5701	24400	0.0001	-
0.5712	24450	0.0	-
0.5724	24500	0.0	-
0.5736	24550	0.0	-
0.5748	24600	0.0029	-
0.5759	24650	0.0	-
0.5771	24700	0.0	-
0.5783	24750	0.0	-
0.5794	24800	0.0	-
0.5806	24850	0.0	-
0.5818	24900	0.0	-
0.5829	24950	0.0001	-
0.5841	25000	0.0	-
0.5853	25050	0.0	-
0.5864	25100	0.0001	-
0.5876	25150	0.0	-
0.5888	25200	0.0	-
0.5899	25250	0.0	-
0.5911	25300	0.0001	-
0.5923	25350	0.0	-
0.5934	25400	0.0001	-
0.5946	25450	0.0	-
0.5958	25500	0.0	-
0.5969	25550	0.0	-
0.5981	25600	0.0	-
0.5993	25650	0.0	-
0.6005	25700	0.0	-
0.6016	25750	0.0	-
0.6028	25800	0.0	-
0.6040	25850	0.0	-
0.6051	25900	0.0	-
0.6063	25950	0.0	-
0.6075	26000	0.0	-
0.6086	26050	0.0	-
0.6098	26100	0.0	-
0.6110	26150	0.0	-
0.6121	26200	0.0	-
0.6133	26250	0.0	-
0.6145	26300	0.0	-
0.6156	26350	0.0001	-
0.6168	26400	0.0	-
0.6180	26450	0.0	-
0.6191	26500	0.0	-
0.6203	26550	0.0	-
0.6215	26600	0.0001	-
0.6226	26650	0.0	-
0.6238	26700	0.0	-
0.6250	26750	0.0	-
0.6262	26800	0.0	-
0.6273	26850	0.0	-
0.6285	26900	0.0	-
0.6297	26950	0.0	-
0.6308	27000	0.0	-
0.6320	27050	0.0001	-
0.6332	27100	0.0	-
0.6343	27150	0.0	-
0.6355	27200	0.0	-
0.6367	27250	0.0001	-
0.6378	27300	0.0	-
0.6390	27350	0.0	-
0.6402	27400	0.0	-
0.6413	27450	0.0	-
0.6425	27500	0.0	-
0.6437	27550	0.0	-
0.6448	27600	0.0001	-
0.6460	27650	0.0001	-
0.6472	27700	0.0	-
0.6483	27750	0.0	-
0.6495	27800	0.0	-
0.6507	27850	0.0	-
0.6519	27900	0.0	-
0.6530	27950	0.0	-
0.6542	28000	0.0	-
0.6554	28050	0.0	-
0.6565	28100	0.0	-
0.6577	28150	0.0	-
0.6589	28200	0.0	-
0.6600	28250	0.0	-
0.6612	28300	0.0	-
0.6624	28350	0.0	-
0.6635	28400	0.0	-
0.6647	28450	0.0	-
0.6659	28500	0.0	-
0.6670	28550	0.0	-
0.6682	28600	0.0001	-
0.6694	28650	0.0	-
0.6705	28700	0.0	-
0.6717	28750	0.0	-
0.6729	28800	0.0	-
0.6740	28850	0.0	-
0.6752	28900	0.0	-
0.6764	28950	0.0	-
0.6776	29000	0.0	-
0.6787	29050	0.0	-
0.6799	29100	0.0	-
0.6811	29150	0.0001	-
0.6822	29200	0.0	-
0.6834	29250	0.0	-
0.6846	29300	0.0	-
0.6857	29350	0.0	-
0.6869	29400	0.0	-
0.6881	29450	0.0	-
0.6892	29500	0.0	-
0.6904	29550	0.0	-
0.6916	29600	0.0	-
0.6927	29650	0.0	-
0.6939	29700	0.0	-
0.6951	29750	0.0	-
0.6962	29800	0.0	-
0.6974	29850	0.0	-
0.6986	29900	0.0	-
0.6998	29950	0.0	-
0.7009	30000	0.0	-
0.7021	30050	0.0	-
0.7033	30100	0.0	-
0.7044	30150	0.0	-
0.7056	30200	0.0	-
0.7068	30250	0.0	-
0.7079	30300	0.0	-
0.7091	30350	0.0	-
0.7103	30400	0.0	-
0.7114	30450	0.0	-
0.7126	30500	0.0	-
0.7138	30550	0.0	-
0.7149	30600	0.0	-
0.7161	30650	0.0	-
0.7173	30700	0.0	-
0.7184	30750	0.0	-
0.7196	30800	0.0	-
0.7208	30850	0.0001	-
0.7219	30900	0.0	-
0.7231	30950	0.0	-
0.7243	31000	0.0	-
0.7255	31050	0.0	-
0.7266	31100	0.0	-
0.7278	31150	0.0	-
0.7290	31200	0.0	-
0.7301	31250	0.0	-
0.7313	31300	0.0	-
0.7325	31350	0.0	-
0.7336	31400	0.0	-
0.7348	31450	0.0	-
0.7360	31500	0.0	-
0.7371	31550	0.0	-
0.7383	31600	0.0001	-
0.7395	31650	0.0001	-
0.7406	31700	0.0	-
0.7418	31750	0.0	-
0.7430	31800	0.0	-
0.7441	31850	0.0	-
0.7453	31900	0.0	-
0.7465	31950	0.0	-
0.7476	32000	0.0	-
0.7488	32050	0.0	-
0.7500	32100	0.0	-
0.7512	32150	0.0	-
0.7523	32200	0.0	-
0.7535	32250	0.0	-
0.7547	32300	0.0	-
0.7558	32350	0.0	-
0.7570	32400	0.0	-
0.7582	32450	0.0	-
0.7593	32500	0.0	-
0.7605	32550	0.0	-
0.7617	32600	0.0	-
0.7628	32650	0.0	-
0.7640	32700	0.0	-
0.7652	32750	0.0	-
0.7663	32800	0.0	-
0.7675	32850	0.0	-
0.7687	32900	0.0	-
0.7698	32950	0.0	-
0.7710	33000	0.0	-
0.7722	33050	0.0	-
0.7733	33100	0.0	-
0.7745	33150	0.0	-
0.7757	33200	0.0	-
0.7769	33250	0.0	-
0.7780	33300	0.0	-
0.7792	33350	0.0	-
0.7804	33400	0.0	-
0.7815	33450	0.0	-
0.7827	33500	0.0	-
0.7839	33550	0.0	-
0.7850	33600	0.0	-
0.7862	33650	0.0	-
0.7874	33700	0.0001	-
0.7885	33750	0.0	-
0.7897	33800	0.0	-
0.7909	33850	0.0	-
0.7920	33900	0.0	-
0.7932	33950	0.0	-
0.7944	34000	0.0	-
0.7955	34050	0.0	-
0.7967	34100	0.0	-
0.7979	34150	0.0	-
0.7990	34200	0.0	-
0.8002	34250	0.0	-
0.8014	34300	0.0	-
0.8026	34350	0.0	-
0.8037	34400	0.0	-
0.8049	34450	0.0	-
0.8061	34500	0.0	-
0.8072	34550	0.0	-
0.8084	34600	0.0	-
0.8096	34650	0.0	-
0.8107	34700	0.0	-
0.8119	34750	0.0	-
0.8131	34800	0.0	-
0.8142	34850	0.0	-
0.8154	34900	0.0	-
0.8166	34950	0.0	-
0.8177	35000	0.0	-
0.8189	35050	0.0	-
0.8201	35100	0.0	-
0.8212	35150	0.0	-
0.8224	35200	0.0	-
0.8236	35250	0.0	-
0.8247	35300	0.0	-
0.8259	35350	0.0	-
0.8271	35400	0.0	-
0.8283	35450	0.0	-
0.8294	35500	0.0	-
0.8306	35550	0.0	-
0.8318	35600	0.0	-
0.8329	35650	0.0	-
0.8341	35700	0.0	-
0.8353	35750	0.0	-
0.8364	35800	0.0	-
0.8376	35850	0.0	-
0.8388	35900	0.0	-
0.8399	35950	0.0	-
0.8411	36000	0.0	-
0.8423	36050	0.0	-
0.8434	36100	0.0	-
0.8446	36150	0.0	-
0.8458	36200	0.0	-
0.8469	36250	0.0	-
0.8481	36300	0.0	-
0.8493	36350	0.0	-
0.8504	36400	0.0	-
0.8516	36450	0.0	-
0.8528	36500	0.0	-
0.8540	36550	0.0	-
0.8551	36600	0.0	-
0.8563	36650	0.0	-
0.8575	36700	0.0	-
0.8586	36750	0.0	-
0.8598	36800	0.0	-
0.8610	36850	0.0	-
0.8621	36900	0.0	-
0.8633	36950	0.0	-
0.8645	37000	0.0	-
0.8656	37050	0.0	-
0.8668	37100	0.0	-
0.8680	37150	0.0	-
0.8691	37200	0.0	-
0.8703	37250	0.0	-
0.8715	37300	0.0	-
0.8726	37350	0.0	-
0.8738	37400	0.0	-
0.8750	37450	0.0	-
0.8761	37500	0.0	-
0.8773	37550	0.0	-
0.8785	37600	0.0	-
0.8797	37650	0.0	-
0.8808	37700	0.0	-
0.8820	37750	0.0	-
0.8832	37800	0.0	-
0.8843	37850	0.0	-
0.8855	37900	0.0	-
0.8867	37950	0.0	-
0.8878	38000	0.0	-
0.8890	38050	0.0	-
0.8902	38100	0.0	-
0.8913	38150	0.0	-
0.8925	38200	0.0	-
0.8937	38250	0.0	-
0.8948	38300	0.0	-
0.8960	38350	0.0	-
0.8972	38400	0.0	-
0.8983	38450	0.0	-
0.8995	38500	0.0	-
0.9007	38550	0.0	-
0.9018	38600	0.0	-
0.9030	38650	0.0	-
0.9042	38700	0.0	-
0.9054	38750	0.0	-
0.9065	38800	0.0	-
0.9077	38850	0.0	-
0.9089	38900	0.0	-
0.9100	38950	0.0	-
0.9112	39000	0.0	-
0.9124	39050	0.0	-
0.9135	39100	0.0	-
0.9147	39150	0.0	-
0.9159	39200	0.0	-
0.9170	39250	0.0	-
0.9182	39300	0.0	-
0.9194	39350	0.0	-
0.9205	39400	0.0	-
0.9217	39450	0.0	-
0.9229	39500	0.0	-
0.9240	39550	0.0	-
0.9252	39600	0.0	-
0.9264	39650	0.0	-
0.9275	39700	0.0	-
0.9287	39750	0.0	-
0.9299	39800	0.0	-
0.9311	39850	0.0	-
0.9322	39900	0.0	-
0.9334	39950	0.0	-
0.9346	40000	0.0	-
0.9357	40050	0.0	-
0.9369	40100	0.0	-
0.9381	40150	0.0	-
0.9392	40200	0.0	-
0.9404	40250	0.0	-
0.9416	40300	0.0001	-
0.9427	40350	0.0	-
0.9439	40400	0.0	-
0.9451	40450	0.0	-
0.9462	40500	0.0	-
0.9474	40550	0.0	-
0.9486	40600	0.0	-
0.9497	40650	0.0	-
0.9509	40700	0.0	-
0.9521	40750	0.0	-
0.9532	40800	0.0	-
0.9544	40850	0.0	-
0.9556	40900	0.0	-
0.9568	40950	0.0	-
0.9579	41000	0.0	-
0.9591	41050	0.0	-
0.9603	41100	0.0	-
0.9614	41150	0.0	-
0.9626	41200	0.0	-
0.9638	41250	0.0	-
0.9649	41300	0.0	-
0.9661	41350	0.0	-
0.9673	41400	0.0	-
0.9684	41450	0.0	-
0.9696	41500	0.0	-
0.9708	41550	0.0	-
0.9719	41600	0.0	-
0.9731	41650	0.0	-
0.9743	41700	0.0	-
0.9754	41750	0.0	-
0.9766	41800	0.0	-
0.9778	41850	0.0	-
0.9789	41900	0.0	-
0.9801	41950	0.0	-
0.9813	42000	0.0	-
0.9825	42050	0.0	-
0.9836	42100	0.0	-
0.9848	42150	0.0	-
0.9860	42200	0.0	-
0.9871	42250	0.0	-
0.9883	42300	0.0	-
0.9895	42350	0.0	-
0.9906	42400	0.0	-
0.9918	42450	0.0	-
0.9930	42500	0.0	-
0.9941	42550	0.0	-
0.9953	42600	0.0	-
0.9965	42650	0.0	-
0.9976	42700	0.0	-
0.9988	42750	0.0	-
1.0000	42800	0.0	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.5.1
Transformers: 4.38.1
PyTorch: 2.1.0+cu121
Datasets: 2.18.0
Tokenizers: 0.15.2

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}
}