metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: sentence-transformers/all-roberta-large-v1
metrics:
  - accuracy
widget:
  - text: ' I''m a runner and I have to say you''re wrong'
  - text: ' I walk everywhere on foot and I feel like the greatest loser in my city I have tendonitis in both knees from long distance running (my last favorite hobby which I can''t even do anymore) I''ve wasted my prime years'
  - text: I can't water the garden because my neighbours are watching
  - text: ' That''s kind of the nature of my volunteer work, but you could volunteer with a food bank or boys  and girls club, which would involve more social interaction Just breaking that cycle by going for a short walk around the neighbourhood is a good idea'
  - text: ' Like jumping into a pool, or starting an assignment'
pipeline_tag: text-classification
inference: true
model-index:
  - name: SetFit with sentence-transformers/all-roberta-large-v1
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.4766666666666667
            name: Accuracy

SetFit with sentence-transformers/all-roberta-large-v1

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-roberta-large-v1 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: sentence-transformers/all-roberta-large-v1
Classification head: a LogisticRegression instance
Maximum Sequence Length: 256 tokens
Number of Classes: 4 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
3.0	"It's whenever I look someone in the eye, when I'm on my bike or when I'm walking somewhere, I feel like they look at me and ridicule me in their headsIt's whenever I look someone in the eye, when I'm on my bike or when I'm walking somewhere, I feel like they look at me and ridicule me in their heads" " While I ended up making progress, it wasn't as fast as I had hoped and I still had a lot of trouble doing some things (such as jogging in public)" ' My social anxiety has got a lot worse as there’s been a lot of recent trauma and I can’t even go outside anymore, a social worker cane to visit and agreed that she’d help me get counselling at home, I’m hoping soon I’ll start getting better'
0.0	' holy shit the food runs with people visiting lol' " The problem with doing this is you're just laying there and not focusing on any outside activities and thus you become prey to hell lot of negative thoughts" ' You might feel relaxed not having to deal with people, but trust me humans are social creatures and in the long run you’re going to become miserable from loneliness'
1.0	' I run 8' " Is there anything actually wrong with your legs, or are you just imagining things? Are they really staring at you, or is it in your head? If you can't deal with going out on your own, try going outside with someone you're comfortable with" ' Being outside is an extra plus!! Keep going :) '
2.0	' It summer time and I have plans to hike and do other fun stuff but i cant do them myself ' ' She knows that I barely go outside and tries to get me to go to out but only with muslims cause she believes that other kids are bad for me' ' It depends on if you live in an area where getting around on a bike is a viable option I’ve heard of people delivering Doordash or Postmates on bicycles but it generally is only more viable if you live in an urban area where restaurants and delivery addresses are closer together, in a suburban area that is more car-focused it’s difficult Though if deliveries are slow they will usually make you do other tasks around the restaurant, whereas with apps you can either run multiple apps at once or just fuck around between deliveries if it’s slow '

Evaluation

Metrics

Label	Accuracy
all	0.4767

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("Omar-Nasr/setfitmodel")
# Run inference
preds = model(" I'm a runner and I have to say you're wrong")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	40.3722	1083

Label	Training Sample Count
0.0	90
1.0	90
2.0	90
3.0	90

Training Hyperparameters

batch_size: (8, 8)
num_epochs: (4, 4)
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
0.0001	1	0.2936	-
0.0041	50	0.3404	-
0.0082	100	0.2465	-
0.0123	150	0.287	-
0.0165	200	0.1955	-
0.0206	250	0.2187	-
0.0247	300	0.2239	-
0.0288	350	0.2709	-
0.0329	400	0.2919	-
0.0370	450	0.2689	-
0.0412	500	0.176	-
0.0453	550	0.2699	-
0.0494	600	0.2538	-
0.0535	650	0.2029	-
0.0576	700	0.2566	-
0.0617	750	0.1106	-
0.0658	800	0.1625	-
0.0700	850	0.1276	-
0.0741	900	0.1603	-
0.0782	950	0.0294	-
0.0823	1000	0.011	-
0.0864	1050	0.1924	-
0.0905	1100	0.0149	-
0.0947	1150	0.1249	-
0.0988	1200	0.1251	-
0.1029	1250	0.008	-
0.1070	1300	0.0008	-
0.1111	1350	0.009	-
0.1152	1400	0.0007	-
0.1193	1450	0.0013	-
0.1235	1500	0.0016	-
0.1276	1550	0.0042	-
0.1317	1600	0.0003	-
0.1358	1650	0.0002	-
0.1399	1700	0.0003	-
0.1440	1750	0.0002	-
0.1481	1800	0.0002	-
0.1523	1850	0.0002	-
0.1564	1900	0.0003	-
0.1605	1950	0.0001	-
0.1646	2000	0.0001	-
0.1687	2050	0.0002	-
0.1728	2100	0.0001	-
0.1770	2150	0.0001	-
0.1811	2200	0.0001	-
0.1852	2250	0.0001	-
0.1893	2300	0.0001	-
0.1934	2350	0.0002	-
0.1975	2400	0.0001	-
0.2016	2450	0.0002	-
0.2058	2500	0.0001	-
0.2099	2550	0.0001	-
0.2140	2600	0.0001	-
0.2181	2650	0.0	-
0.2222	2700	0.0001	-
0.2263	2750	0.0001	-
0.2305	2800	0.0001	-
0.2346	2850	0.0	-
0.2387	2900	0.0	-
0.2428	2950	0.0001	-
0.2469	3000	0.0001	-
0.2510	3050	0.0002	-
0.2551	3100	0.0001	-
0.2593	3150	0.0	-
0.2634	3200	0.0	-
0.2675	3250	0.0001	-
0.2716	3300	0.0001	-
0.2757	3350	0.0	-
0.2798	3400	0.0	-
0.2840	3450	0.0	-
0.2881	3500	0.0	-
0.2922	3550	0.0	-
0.2963	3600	0.0	-
0.3004	3650	0.0	-
0.3045	3700	0.0	-
0.3086	3750	0.0001	-
0.3128	3800	0.0	-
0.3169	3850	0.0	-
0.3210	3900	0.0001	-
0.3251	3950	0.0001	-
0.3292	4000	0.0	-
0.3333	4050	0.0001	-
0.3374	4100	0.0	-
0.3416	4150	0.0	-
0.3457	4200	0.482	-
0.3498	4250	0.0384	-
0.3539	4300	0.1998	-
0.3580	4350	0.2232	-
0.3621	4400	0.1794	-
0.3663	4450	0.0911	-
0.3704	4500	0.1016	-
0.3745	4550	0.1266	-
0.3786	4600	0.0004	-
0.3827	4650	0.0005	-
0.3868	4700	0.0001	-
0.3909	4750	0.0002	-
0.3951	4800	0.0005	-
0.3992	4850	0.0001	-
0.4033	4900	0.0003	-
0.4074	4950	0.0002	-
0.4115	5000	0.0001	-
0.4156	5050	0.0001	-
0.4198	5100	0.0001	-
0.4239	5150	0.0	-
0.4280	5200	0.0	-
0.4321	5250	0.0	-
0.4362	5300	0.0001	-
0.4403	5350	0.0	-
0.4444	5400	0.0	-
0.4486	5450	0.0	-
0.4527	5500	0.0	-
0.4568	5550	0.0001	-
0.4609	5600	0.0	-
0.4650	5650	0.0	-
0.4691	5700	0.0	-
0.4733	5750	0.0001	-
0.4774	5800	0.0	-
0.4815	5850	0.0	-
0.4856	5900	0.0	-
0.4897	5950	0.0	-
0.4938	6000	0.0	-
0.4979	6050	0.0001	-
0.5021	6100	0.0	-
0.5062	6150	0.0	-
0.5103	6200	0.0	-
0.5144	6250	0.0	-
0.5185	6300	0.0	-
0.5226	6350	0.0	-
0.5267	6400	0.0	-
0.5309	6450	0.0	-
0.5350	6500	0.0	-
0.5391	6550	0.0	-
0.5432	6600	0.0	-
0.5473	6650	0.0	-
0.5514	6700	0.0	-
0.5556	6750	0.0	-
0.5597	6800	0.0	-
0.5638	6850	0.0	-
0.5679	6900	0.0	-
0.5720	6950	0.0	-
0.5761	7000	0.0	-
0.5802	7050	0.0	-
0.5844	7100	0.0	-
0.5885	7150	0.0	-
0.5926	7200	0.0	-
0.5967	7250	0.0001	-
0.6008	7300	0.0	-
0.6049	7350	0.0	-
0.6091	7400	0.0	-
0.6132	7450	0.0	-
0.6173	7500	0.0	-
0.6214	7550	0.0	-
0.6255	7600	0.0	-
0.6296	7650	0.0	-
0.6337	7700	0.0	-
0.6379	7750	0.0	-
0.6420	7800	0.0	-
0.6461	7850	0.0	-
0.6502	7900	0.001	-
0.6543	7950	0.0061	-
0.6584	8000	0.0966	-
0.6626	8050	0.0911	-
0.6667	8100	0.1791	-
0.6708	8150	0.0001	-
0.6749	8200	0.0354	-
0.6790	8250	0.0061	-
0.6831	8300	0.0	-
0.6872	8350	0.0	-
0.6914	8400	0.0001	-
0.6955	8450	0.0	-
0.6996	8500	0.0	-
0.7037	8550	0.0	-
0.7078	8600	0.0	-
0.7119	8650	0.0	-
0.7160	8700	0.0	-
0.7202	8750	0.0	-
0.7243	8800	0.0	-
0.7284	8850	0.0	-
0.7325	8900	0.0	-
0.7366	8950	0.0	-
0.7407	9000	0.0	-
0.7449	9050	0.0	-
0.7490	9100	0.0001	-
0.7531	9150	0.0	-
0.7572	9200	0.0	-
0.7613	9250	0.0	-
0.7654	9300	0.0	-
0.7695	9350	0.0	-
0.7737	9400	0.0	-
0.7778	9450	0.0	-
0.7819	9500	0.0	-
0.7860	9550	0.0	-
0.7901	9600	0.0	-
0.7942	9650	0.0	-
0.7984	9700	0.0	-
0.8025	9750	0.0	-
0.8066	9800	0.0	-
0.8107	9850	0.0	-
0.8148	9900	0.0	-
0.8189	9950	0.0	-
0.8230	10000	0.0	-
0.8272	10050	0.0	-
0.8313	10100	0.0	-
0.8354	10150	0.0	-
0.8395	10200	0.0	-
0.8436	10250	0.0	-
0.8477	10300	0.0	-
0.8519	10350	0.0	-
0.8560	10400	0.0	-
0.8601	10450	0.0	-
0.8642	10500	0.0	-
0.8683	10550	0.0	-
0.8724	10600	0.0	-
0.8765	10650	0.0	-
0.8807	10700	0.0	-
0.8848	10750	0.0	-
0.8889	10800	0.0	-
0.8930	10850	0.0	-
0.8971	10900	0.0	-
0.9012	10950	0.0	-
0.9053	11000	0.0	-
0.9095	11050	0.0	-
0.9136	11100	0.0	-
0.9177	11150	0.0	-
0.9218	11200	0.0	-
0.9259	11250	0.0	-
0.9300	11300	0.0	-
0.9342	11350	0.0	-
0.9383	11400	0.0	-
0.9424	11450	0.0	-
0.9465	11500	0.0	-
0.9506	11550	0.0	-
0.9547	11600	0.0	-
0.9588	11650	0.0	-
0.9630	11700	0.0	-
0.9671	11750	0.0	-
0.9712	11800	0.0	-
0.9753	11850	0.0	-
0.9794	11900	0.0	-
0.9835	11950	0.0	-
0.9877	12000	0.0	-
0.9918	12050	0.0	-
0.9959	12100	0.0	-
1.0	12150	0.0	-
1.0041	12200	0.0	-
1.0082	12250	0.0	-
1.0123	12300	0.0	-
1.0165	12350	0.0	-
1.0206	12400	0.0	-
1.0247	12450	0.0	-
1.0288	12500	0.0	-
1.0329	12550	0.0	-
1.0370	12600	0.0	-
1.0412	12650	0.0	-
1.0453	12700	0.0	-
1.0494	12750	0.0	-
1.0535	12800	0.0	-
1.0576	12850	0.0001	-
1.0617	12900	0.0	-
1.0658	12950	0.0	-
1.0700	13000	0.0	-
1.0741	13050	0.0	-
1.0782	13100	0.0	-
1.0823	13150	0.0	-
1.0864	13200	0.0	-
1.0905	13250	0.0	-
1.0947	13300	0.0	-
1.0988	13350	0.0	-
1.1029	13400	0.0	-
1.1070	13450	0.0	-
1.1111	13500	0.0	-
1.1152	13550	0.0	-
1.1193	13600	0.0	-
1.1235	13650	0.0	-
1.1276	13700	0.0	-
1.1317	13750	0.0	-
1.1358	13800	0.0	-
1.1399	13850	0.0	-
1.1440	13900	0.0	-
1.1481	13950	0.0	-
1.1523	14000	0.0	-
1.1564	14050	0.0	-
1.1605	14100	0.0	-
1.1646	14150	0.0	-
1.1687	14200	0.0	-
1.1728	14250	0.0	-
1.1770	14300	0.0	-
1.1811	14350	0.0	-
1.1852	14400	0.0	-
1.1893	14450	0.0	-
1.1934	14500	0.0	-
1.1975	14550	0.0	-
1.2016	14600	0.0	-
1.2058	14650	0.0146	-
1.2099	14700	0.4649	-
1.2140	14750	0.0596	-
1.2181	14800	0.0007	-
1.2222	14850	0.0006	-
1.2263	14900	0.0001	-
1.2305	14950	0.0026	-
1.2346	15000	0.0	-
1.2387	15050	0.0	-
1.2428	15100	0.0001	-
1.2469	15150	0.0847	-
1.2510	15200	0.0	-
1.2551	15250	0.0475	-
1.2593	15300	0.0006	-
1.2634	15350	0.0001	-
1.2675	15400	0.0	-
1.2716	15450	0.0	-
1.2757	15500	0.0002	-
1.2798	15550	0.0001	-
1.2840	15600	0.0	-
1.2881	15650	0.0	-
1.2922	15700	0.0	-
1.2963	15750	0.0	-
1.3004	15800	0.0	-
1.3045	15850	0.0004	-
1.3086	15900	0.0	-
1.3128	15950	0.0	-
1.3169	16000	0.0	-
1.3210	16050	0.0	-
1.3251	16100	0.0	-
1.3292	16150	0.0	-
1.3333	16200	0.0	-
1.3374	16250	0.0	-
1.3416	16300	0.0	-
1.3457	16350	0.0	-
1.3498	16400	0.0	-
1.3539	16450	0.0	-
1.3580	16500	0.0	-
1.3621	16550	0.0	-
1.3663	16600	0.0	-
1.3704	16650	0.0001	-
1.3745	16700	0.0	-
1.3786	16750	0.0	-
1.3827	16800	0.0	-
1.3868	16850	0.0001	-
1.3909	16900	0.0	-
1.3951	16950	0.0	-
1.3992	17000	0.0	-
1.4033	17050	0.0	-
1.4074	17100	0.0	-
1.4115	17150	0.0	-
1.4156	17200	0.0	-
1.4198	17250	0.0	-
1.4239	17300	0.0	-
1.4280	17350	0.0	-
1.4321	17400	0.0	-
1.4362	17450	0.0	-
1.4403	17500	0.0	-
1.4444	17550	0.0	-
1.4486	17600	0.0	-
1.4527	17650	0.0	-
1.4568	17700	0.0	-
1.4609	17750	0.0	-
1.4650	17800	0.0	-
1.4691	17850	0.0	-
1.4733	17900	0.0	-
1.4774	17950	0.0002	-
1.4815	18000	0.0	-
1.4856	18050	0.0	-
1.4897	18100	0.0	-
1.4938	18150	0.0	-
1.4979	18200	0.0	-
1.5021	18250	0.0	-
1.5062	18300	0.0	-
1.5103	18350	0.0	-
1.5144	18400	0.0	-
1.5185	18450	0.0	-
1.5226	18500	0.0	-
1.5267	18550	0.0	-
1.5309	18600	0.0	-
1.5350	18650	0.0	-
1.5391	18700	0.0	-
1.5432	18750	0.0	-
1.5473	18800	0.0	-
1.5514	18850	0.0	-
1.5556	18900	0.0	-
1.5597	18950	0.0	-
1.5638	19000	0.0	-
1.5679	19050	0.0	-
1.5720	19100	0.0	-
1.5761	19150	0.0	-
1.5802	19200	0.0	-
1.5844	19250	0.0	-
1.5885	19300	0.0	-
1.5926	19350	0.0	-
1.5967	19400	0.0	-
1.6008	19450	0.0	-
1.6049	19500	0.0	-
1.6091	19550	0.0	-
1.6132	19600	0.0	-
1.6173	19650	0.0022	-
1.6214	19700	0.0981	-
1.6255	19750	0.0	-
1.6296	19800	0.0006	-
1.6337	19850	0.0	-
1.6379	19900	0.0	-
1.6420	19950	0.0	-
1.6461	20000	0.0	-
1.6502	20050	0.0	-
1.6543	20100	0.0	-
1.6584	20150	0.0	-
1.6626	20200	0.0	-
1.6667	20250	0.0173	-
1.6708	20300	0.0001	-
1.6749	20350	0.0	-
1.6790	20400	0.0	-
1.6831	20450	0.0001	-
1.6872	20500	0.0	-
1.6914	20550	0.0	-
1.6955	20600	0.0	-
1.6996	20650	0.0	-
1.7037	20700	0.0	-
1.7078	20750	0.0001	-
1.7119	20800	0.0	-
1.7160	20850	0.0	-
1.7202	20900	0.0	-
1.7243	20950	0.0	-
1.7284	21000	0.0	-
1.7325	21050	0.0	-
1.7366	21100	0.0	-
1.7407	21150	0.0	-
1.7449	21200	0.0	-
1.7490	21250	0.0	-
1.7531	21300	0.0	-
1.7572	21350	0.0	-
1.7613	21400	0.0	-
1.7654	21450	0.0	-
1.7695	21500	0.0	-
1.7737	21550	0.0	-
1.7778	21600	0.0	-
1.7819	21650	0.0	-
1.7860	21700	0.0	-
1.7901	21750	0.0	-
1.7942	21800	0.0	-
1.7984	21850	0.0	-
1.8025	21900	0.0	-
1.8066	21950	0.0	-
1.8107	22000	0.0	-
1.8148	22050	0.0	-
1.8189	22100	0.0	-
1.8230	22150	0.0	-
1.8272	22200	0.0	-
1.8313	22250	0.0	-
1.8354	22300	0.0	-
1.8395	22350	0.0	-
1.8436	22400	0.0	-
1.8477	22450	0.0	-
1.8519	22500	0.0	-
1.8560	22550	0.0	-
1.8601	22600	0.0	-
1.8642	22650	0.0	-
1.8683	22700	0.0	-
1.8724	22750	0.0	-
1.8765	22800	0.0	-
1.8807	22850	0.0	-
1.8848	22900	0.0	-
1.8889	22950	0.0	-
1.8930	23000	0.0	-
1.8971	23050	0.0007	-
1.9012	23100	0.0	-
1.9053	23150	0.0	-
1.9095	23200	0.0	-
1.9136	23250	0.0	-
1.9177	23300	0.0	-
1.9218	23350	0.0	-
1.9259	23400	0.0	-
1.9300	23450	0.0	-
1.9342	23500	0.0	-
1.9383	23550	0.0	-
1.9424	23600	0.0	-
1.9465	23650	0.0	-
1.9506	23700	0.0	-
1.9547	23750	0.0	-
1.9588	23800	0.0	-
1.9630	23850	0.0	-
1.9671	23900	0.0	-
1.9712	23950	0.0	-
1.9753	24000	0.0	-
1.9794	24050	0.0	-
1.9835	24100	0.0	-
1.9877	24150	0.0	-
1.9918	24200	0.0	-
1.9959	24250	0.0	-
2.0	24300	0.0	-
2.0041	24350	0.0001	-
2.0082	24400	0.0	-
2.0123	24450	0.0004	-
2.0165	24500	0.0	-
2.0206	24550	0.0001	-
2.0247	24600	0.0	-
2.0288	24650	0.0	-
2.0329	24700	0.0	-
2.0370	24750	0.0	-
2.0412	24800	0.0	-
2.0453	24850	0.0	-
2.0494	24900	0.0	-
2.0535	24950	0.0	-
2.0576	25000	0.0	-
2.0617	25050	0.0	-
2.0658	25100	0.0	-
2.0700	25150	0.0	-
2.0741	25200	0.0	-
2.0782	25250	0.0	-
2.0823	25300	0.0	-
2.0864	25350	0.0	-
2.0905	25400	0.0	-
2.0947	25450	0.0	-
2.0988	25500	0.0	-
2.1029	25550	0.0	-
2.1070	25600	0.0	-
2.1111	25650	0.0	-
2.1152	25700	0.0	-
2.1193	25750	0.0	-
2.1235	25800	0.0	-
2.1276	25850	0.0	-
2.1317	25900	0.0	-
2.1358	25950	0.0	-
2.1399	26000	0.0	-
2.1440	26050	0.0	-
2.1481	26100	0.0	-
2.1523	26150	0.0	-
2.1564	26200	0.0	-
2.1605	26250	0.0	-
2.1646	26300	0.0	-
2.1687	26350	0.0	-
2.1728	26400	0.0	-
2.1770	26450	0.0	-
2.1811	26500	0.0	-
2.1852	26550	0.0	-
2.1893	26600	0.0	-
2.1934	26650	0.0	-
2.1975	26700	0.0	-
2.2016	26750	0.0	-
2.2058	26800	0.0	-
2.2099	26850	0.0	-
2.2140	26900	0.0	-
2.2181	26950	0.0	-
2.2222	27000	0.0	-
2.2263	27050	0.0	-
2.2305	27100	0.0	-
2.2346	27150	0.0	-
2.2387	27200	0.0	-
2.2428	27250	0.0	-
2.2469	27300	0.0	-
2.2510	27350	0.0	-
2.2551	27400	0.0	-
2.2593	27450	0.0	-
2.2634	27500	0.0	-
2.2675	27550	0.0	-
2.2716	27600	0.0	-
2.2757	27650	0.0	-
2.2798	27700	0.0	-
2.2840	27750	0.0	-
2.2881	27800	0.0	-
2.2922	27850	0.0	-
2.2963	27900	0.0	-
2.3004	27950	0.0	-
2.3045	28000	0.0	-
2.3086	28050	0.0	-
2.3128	28100	0.0	-
2.3169	28150	0.0	-
2.3210	28200	0.0	-
2.3251	28250	0.0	-
2.3292	28300	0.0	-
2.3333	28350	0.0	-
2.3374	28400	0.0	-
2.3416	28450	0.0	-
2.3457	28500	0.0	-
2.3498	28550	0.0	-
2.3539	28600	0.0	-
2.3580	28650	0.0	-
2.3621	28700	0.0	-
2.3663	28750	0.0	-
2.3704	28800	0.0	-
2.3745	28850	0.0	-
2.3786	28900	0.0	-
2.3827	28950	0.0	-
2.3868	29000	0.0	-
2.3909	29050	0.0	-
2.3951	29100	0.0	-
2.3992	29150	0.0	-
2.4033	29200	0.0	-
2.4074	29250	0.0	-
2.4115	29300	0.0	-
2.4156	29350	0.0	-
2.4198	29400	0.0	-
2.4239	29450	0.0	-
2.4280	29500	0.0	-
2.4321	29550	0.0	-
2.4362	29600	0.0	-
2.4403	29650	0.0	-
2.4444	29700	0.0	-
2.4486	29750	0.0	-
2.4527	29800	0.0	-
2.4568	29850	0.0	-
2.4609	29900	0.0	-
2.4650	29950	0.0	-
2.4691	30000	0.0	-
2.4733	30050	0.0	-
2.4774	30100	0.0	-
2.4815	30150	0.0	-
2.4856	30200	0.0	-
2.4897	30250	0.0	-
2.4938	30300	0.0	-
2.4979	30350	0.0	-
2.5021	30400	0.0	-
2.5062	30450	0.0	-
2.5103	30500	0.0	-
2.5144	30550	0.0	-
2.5185	30600	0.0	-
2.5226	30650	0.0	-
2.5267	30700	0.0	-
2.5309	30750	0.0	-
2.5350	30800	0.0	-
2.5391	30850	0.0	-
2.5432	30900	0.0	-
2.5473	30950	0.0	-
2.5514	31000	0.0	-
2.5556	31050	0.0	-
2.5597	31100	0.0	-
2.5638	31150	0.0	-
2.5679	31200	0.0	-
2.5720	31250	0.0	-
2.5761	31300	0.0	-
2.5802	31350	0.0	-
2.5844	31400	0.0	-
2.5885	31450	0.0	-
2.5926	31500	0.0	-
2.5967	31550	0.0	-
2.6008	31600	0.0	-
2.6049	31650	0.0	-
2.6091	31700	0.0	-
2.6132	31750	0.0	-
2.6173	31800	0.0	-
2.6214	31850	0.0	-
2.6255	31900	0.0	-
2.6296	31950	0.0	-
2.6337	32000	0.0	-
2.6379	32050	0.0	-
2.6420	32100	0.0	-
2.6461	32150	0.0	-
2.6502	32200	0.0	-
2.6543	32250	0.0	-
2.6584	32300	0.0	-
2.6626	32350	0.0	-
2.6667	32400	0.0	-
2.6708	32450	0.0	-
2.6749	32500	0.0	-
2.6790	32550	0.0	-
2.6831	32600	0.0	-
2.6872	32650	0.0	-
2.6914	32700	0.0	-
2.6955	32750	0.0	-
2.6996	32800	0.0	-
2.7037	32850	0.0	-
2.7078	32900	0.0	-
2.7119	32950	0.0	-
2.7160	33000	0.0	-
2.7202	33050	0.0	-
2.7243	33100	0.0	-
2.7284	33150	0.0	-
2.7325	33200	0.0	-
2.7366	33250	0.0	-
2.7407	33300	0.0	-
2.7449	33350	0.0	-
2.7490	33400	0.0	-
2.7531	33450	0.0	-
2.7572	33500	0.0	-
2.7613	33550	0.0967	-
2.7654	33600	0.0	-
2.7695	33650	0.0	-
2.7737	33700	0.0	-
2.7778	33750	0.0	-
2.7819	33800	0.0	-
2.7860	33850	0.0	-
2.7901	33900	0.0	-
2.7942	33950	0.0	-
2.7984	34000	0.0	-
2.8025	34050	0.0	-
2.8066	34100	0.0	-
2.8107	34150	0.0	-
2.8148	34200	0.0	-
2.8189	34250	0.0	-
2.8230	34300	0.0	-
2.8272	34350	0.0	-
2.8313	34400	0.0	-
2.8354	34450	0.0	-
2.8395	34500	0.0	-
2.8436	34550	0.0	-
2.8477	34600	0.0	-
2.8519	34650	0.0	-
2.8560	34700	0.0	-
2.8601	34750	0.0	-
2.8642	34800	0.0	-
2.8683	34850	0.0	-
2.8724	34900	0.0	-
2.8765	34950	0.0	-
2.8807	35000	0.0	-
2.8848	35050	0.0	-
2.8889	35100	0.0	-
2.8930	35150	0.0	-
2.8971	35200	0.0	-
2.9012	35250	0.0	-
2.9053	35300	0.0	-
2.9095	35350	0.0	-
2.9136	35400	0.0	-
2.9177	35450	0.0	-
2.9218	35500	0.0	-
2.9259	35550	0.0	-
2.9300	35600	0.0	-
2.9342	35650	0.0	-
2.9383	35700	0.0	-
2.9424	35750	0.0	-
2.9465	35800	0.0	-
2.9506	35850	0.0	-
2.9547	35900	0.0	-
2.9588	35950	0.0012	-
2.9630	36000	0.0	-
2.9671	36050	0.0	-
2.9712	36100	0.0	-
2.9753	36150	0.0	-
2.9794	36200	0.0	-
2.9835	36250	0.0	-
2.9877	36300	0.0	-
2.9918	36350	0.0	-
2.9959	36400	0.0	-
3.0	36450	0.0	-
3.0041	36500	0.0	-
3.0082	36550	0.0	-
3.0123	36600	0.0	-
3.0165	36650	0.0	-
3.0206	36700	0.0	-
3.0247	36750	0.0	-
3.0288	36800	0.0	-
3.0329	36850	0.0	-
3.0370	36900	0.0	-
3.0412	36950	0.0	-
3.0453	37000	0.0	-
3.0494	37050	0.0	-
3.0535	37100	0.0	-
3.0576	37150	0.0	-
3.0617	37200	0.0	-
3.0658	37250	0.0	-
3.0700	37300	0.0	-
3.0741	37350	0.0	-
3.0782	37400	0.0	-
3.0823	37450	0.0	-
3.0864	37500	0.0	-
3.0905	37550	0.0	-
3.0947	37600	0.0	-
3.0988	37650	0.0	-
3.1029	37700	0.0	-
3.1070	37750	0.0	-
3.1111	37800	0.0	-
3.1152	37850	0.0	-
3.1193	37900	0.0	-
3.1235	37950	0.0	-
3.1276	38000	0.0	-
3.1317	38050	0.0	-
3.1358	38100	0.0	-
3.1399	38150	0.0	-
3.1440	38200	0.0	-
3.1481	38250	0.0	-
3.1523	38300	0.0	-
3.1564	38350	0.0	-
3.1605	38400	0.0	-
3.1646	38450	0.0	-
3.1687	38500	0.0	-
3.1728	38550	0.0	-
3.1770	38600	0.0	-
3.1811	38650	0.0	-
3.1852	38700	0.0	-
3.1893	38750	0.0	-
3.1934	38800	0.0	-
3.1975	38850	0.0	-
3.2016	38900	0.0	-
3.2058	38950	0.0	-
3.2099	39000	0.0	-
3.2140	39050	0.0	-
3.2181	39100	0.0	-
3.2222	39150	0.0	-
3.2263	39200	0.0	-
3.2305	39250	0.0	-
3.2346	39300	0.0	-
3.2387	39350	0.0	-
3.2428	39400	0.0	-
3.2469	39450	0.0	-
3.2510	39500	0.0	-
3.2551	39550	0.0	-
3.2593	39600	0.0	-
3.2634	39650	0.0	-
3.2675	39700	0.0	-
3.2716	39750	0.0	-
3.2757	39800	0.0	-
3.2798	39850	0.0	-
3.2840	39900	0.0	-
3.2881	39950	0.0	-
3.2922	40000	0.0	-
3.2963	40050	0.0	-
3.3004	40100	0.0	-
3.3045	40150	0.0	-
3.3086	40200	0.0	-
3.3128	40250	0.0	-
3.3169	40300	0.0	-
3.3210	40350	0.0	-
3.3251	40400	0.0	-
3.3292	40450	0.0	-
3.3333	40500	0.0	-
3.3374	40550	0.0	-
3.3416	40600	0.0	-
3.3457	40650	0.0	-
3.3498	40700	0.0	-
3.3539	40750	0.0	-
3.3580	40800	0.0	-
3.3621	40850	0.0	-
3.3663	40900	0.0002	-
3.3704	40950	0.0	-
3.3745	41000	0.0	-
3.3786	41050	0.0	-
3.3827	41100	0.0	-
3.3868	41150	0.0	-
3.3909	41200	0.0	-
3.3951	41250	0.0	-
3.3992	41300	0.0	-
3.4033	41350	0.0	-
3.4074	41400	0.0	-
3.4115	41450	0.0	-
3.4156	41500	0.0	-
3.4198	41550	0.0	-
3.4239	41600	0.0	-
3.4280	41650	0.0	-
3.4321	41700	0.0	-
3.4362	41750	0.0	-
3.4403	41800	0.0	-
3.4444	41850	0.0	-
3.4486	41900	0.0	-
3.4527	41950	0.0	-
3.4568	42000	0.0	-
3.4609	42050	0.0	-
3.4650	42100	0.0	-
3.4691	42150	0.0	-
3.4733	42200	0.0	-
3.4774	42250	0.0	-
3.4815	42300	0.0	-
3.4856	42350	0.0	-
3.4897	42400	0.0	-
3.4938	42450	0.0	-
3.4979	42500	0.0	-
3.5021	42550	0.0	-
3.5062	42600	0.0	-
3.5103	42650	0.0	-
3.5144	42700	0.0	-
3.5185	42750	0.0	-
3.5226	42800	0.0	-
3.5267	42850	0.0	-
3.5309	42900	0.0	-
3.5350	42950	0.0	-
3.5391	43000	0.0	-
3.5432	43050	0.0	-
3.5473	43100	0.0	-
3.5514	43150	0.0	-
3.5556	43200	0.0	-
3.5597	43250	0.0	-
3.5638	43300	0.0	-
3.5679	43350	0.0	-
3.5720	43400	0.0	-
3.5761	43450	0.0	-
3.5802	43500	0.0	-
3.5844	43550	0.0	-
3.5885	43600	0.0	-
3.5926	43650	0.0	-
3.5967	43700	0.0	-
3.6008	43750	0.0	-
3.6049	43800	0.0	-
3.6091	43850	0.0	-
3.6132	43900	0.0	-
3.6173	43950	0.0	-
3.6214	44000	0.0	-
3.6255	44050	0.0	-
3.6296	44100	0.0	-
3.6337	44150	0.0	-
3.6379	44200	0.0	-
3.6420	44250	0.0	-
3.6461	44300	0.0	-
3.6502	44350	0.0	-
3.6543	44400	0.0	-
3.6584	44450	0.0	-
3.6626	44500	0.0	-
3.6667	44550	0.0	-
3.6708	44600	0.0	-
3.6749	44650	0.0	-
3.6790	44700	0.0	-
3.6831	44750	0.0	-
3.6872	44800	0.0	-
3.6914	44850	0.0	-
3.6955	44900	0.0	-
3.6996	44950	0.0	-
3.7037	45000	0.0	-
3.7078	45050	0.0	-
3.7119	45100	0.0	-
3.7160	45150	0.0	-
3.7202	45200	0.0	-
3.7243	45250	0.0	-
3.7284	45300	0.0	-
3.7325	45350	0.0	-
3.7366	45400	0.0	-
3.7407	45450	0.0	-
3.7449	45500	0.0	-
3.7490	45550	0.0	-
3.7531	45600	0.0	-
3.7572	45650	0.0	-
3.7613	45700	0.0	-
3.7654	45750	0.0	-
3.7695	45800	0.0	-
3.7737	45850	0.0	-
3.7778	45900	0.0	-
3.7819	45950	0.0	-
3.7860	46000	0.0	-
3.7901	46050	0.0	-
3.7942	46100	0.0	-
3.7984	46150	0.0	-
3.8025	46200	0.0	-
3.8066	46250	0.0	-
3.8107	46300	0.0	-
3.8148	46350	0.0	-
3.8189	46400	0.0	-
3.8230	46450	0.0	-
3.8272	46500	0.0	-
3.8313	46550	0.0	-
3.8354	46600	0.0	-
3.8395	46650	0.0	-
3.8436	46700	0.0	-
3.8477	46750	0.0	-
3.8519	46800	0.0	-
3.8560	46850	0.0	-
3.8601	46900	0.0	-
3.8642	46950	0.0	-
3.8683	47000	0.0	-
3.8724	47050	0.0	-
3.8765	47100	0.0	-
3.8807	47150	0.0	-
3.8848	47200	0.0	-
3.8889	47250	0.0	-
3.8930	47300	0.0	-
3.8971	47350	0.0	-
3.9012	47400	0.0	-
3.9053	47450	0.0	-
3.9095	47500	0.0	-
3.9136	47550	0.0	-
3.9177	47600	0.0	-
3.9218	47650	0.0	-
3.9259	47700	0.0	-
3.9300	47750	0.0	-
3.9342	47800	0.0	-
3.9383	47850	0.0	-
3.9424	47900	0.0	-
3.9465	47950	0.0	-
3.9506	48000	0.0	-
3.9547	48050	0.0	-
3.9588	48100	0.0	-
3.9630	48150	0.0	-
3.9671	48200	0.0	-
3.9712	48250	0.0	-
3.9753	48300	0.0	-
3.9794	48350	0.0	-
3.9835	48400	0.0	-
3.9877	48450	0.0	-
3.9918	48500	0.0	-
3.9959	48550	0.0	-
4.0	48600	0.0	-

Framework Versions

Python: 3.10.13
SetFit: 1.0.3
Sentence Transformers: 2.7.0
Transformers: 4.39.3
PyTorch: 2.1.2
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}
}