--- base_model: desarrolloasesoreslocales/bert-leg-al-corpus library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: 'Que no estando conforme en absoluto con los hechos denunciados, se interpone el presente escrito en tiempo y forma en base a las siguientes' - text: "En primer lugar, indicar algo fundamental y es el hecho de que mi vehículo\ \ NO estaba estacionado, \nsino que se encontraba parado, puesto que reunía todos\ \ los requisitos legales\nestablecidos en el anexo l, apartado 81 del RD Legislativo\ \ 6/2015, de 30 de octubre, donde se\nrecoge que la_parada_es la inmovilización\ \ de un vehículo durante un tiempo inferior a dos\nminutos, sin que el conductor\ \ pueda abandonarlo. Es decir, que se estaría sancionando un\nhecho no constitutivo\ \ de infracción administrativa, y, por tanto, vulnerando el principio de tipicidad\ \ \nrecogido en el artículo 27.1 de la Ley 40/2015, de 1 de octubre, de Régimen\ \ Jurídico del\nSector Público, puesto que solo constituyen infracciones administrativas\ \ las vulneraciones del\nordenamiento jurídico previstas como tales infracciones\ \ en una Ley." - text: QUINTA.- Hay que alegar que con el presente expediente se vulnera el PRINCIPIO DE PROPORCIONALIDAD que debe regir a la hora de la imposición de las sanciones. - text: 'Que SE SOLICITA LA APERTURA DEL PERÍODO DE PRUEBA conforme indica el artículo 95 del RD Legislativo 6/2015, de 30 de octubre, así como el artículo 13 del R.D. 320/94 por el que se aprueba el Reglamento del Procedimiento Sancionador en materia de tráfico, circulación de vehículos a motor y seguridad vial, y, en su virtud, se propone la práctica de los siguientes medios de prueba, esenciales para la comprobación de los hechos y mi defensa: * Documento Fotográfico del presunto vehículo infractor para verificar si el mismo circulaba a velocidad superior a la permitida, el cual es exigible que conste de al menos dos fotogramas tomados en diferentes instantes, debiendo figurar en los citados fotogramas, los datos necesarios para relacionar dicha prueba con el cinemómetro que, en principio, los obtuvo; así, como, en caso de tratarse de un radar instalado en un vehículo, deberá constar la velocidad a la que circula el mismo.' - text: 'En relación a la cuantía económica impuesta y en base al principio de proporcionalidad, creo que es excesiva.' inference: true model-index: - name: SetFit with desarrolloasesoreslocales/bert-leg-al-corpus results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.9126984126984127 name: Accuracy --- # SetFit with desarrolloasesoreslocales/bert-leg-al-corpus This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [desarrolloasesoreslocales/bert-leg-al-corpus](https://huggingface.co/desarrolloasesoreslocales/bert-leg-al-corpus) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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](https://www.sbert.net) 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:** [desarrolloasesoreslocales/bert-leg-al-corpus](https://huggingface.co/desarrolloasesoreslocales/bert-leg-al-corpus) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 21 classes ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 2060 | | | 2037 | | | 2027 | | | 2002 | | | 237 | | | 2022 | | | 2026 | | | 2039 | | | 2038 | | | 353 | | | 304 | | | 2001 | | | 2014 | | | 49 | | | 78 | | | 1001 | | | 357 | | | 2017 | | | 2013 | | | 994 | | | 2010 | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.9127 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("desarrolloasesoreslocales/bert-leg-al-setfit") # Run inference preds = model("En relación a la cuantía económica impuesta y en base al principio de proporcionalidad, creo que es excesiva.") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 3 | 30.9507 | 213 | | Label | Training Sample Count | |:------|:----------------------| | 49 | 34 | | 78 | 34 | | 237 | 33 | | 304 | 34 | | 353 | 34 | | 357 | 34 | | 994 | 34 | | 1001 | 34 | | 2001 | 34 | | 2002 | 34 | | 2010 | 34 | | 2013 | 34 | | 2014 | 34 | | 2017 | 34 | | 2022 | 33 | | 2026 | 34 | | 2027 | 33 | | 2037 | 33 | | 2038 | 34 | | 2039 | 34 | | 2060 | 34 | ### Training Hyperparameters - batch_size: (32, 32) - num_epochs: (2, 2) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 60 - body_learning_rate: (1e-06, 1e-06) - head_learning_rate: 0.0002 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: True - use_amp: True - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:----------:|:--------:|:-------------:|:---------------:| | 0.0004 | 1 | 0.3326 | - | | 0.0075 | 20 | 0.352 | 0.3591 | | 0.0150 | 40 | 0.3662 | 0.3591 | | 0.0225 | 60 | 0.3348 | 0.3589 | | 0.0300 | 80 | 0.3773 | 0.3588 | | 0.0376 | 100 | 0.3523 | 0.3585 | | 0.0451 | 120 | 0.36 | 0.3582 | | 0.0526 | 140 | 0.3726 | 0.3579 | | 0.0601 | 160 | 0.3715 | 0.3575 | | 0.0676 | 180 | 0.3519 | 0.357 | | 0.0751 | 200 | 0.3611 | 0.3565 | | 0.0826 | 220 | 0.3635 | 0.356 | | 0.0901 | 240 | 0.3594 | 0.3553 | | 0.0976 | 260 | 0.3383 | 0.3546 | | 0.1051 | 280 | 0.3393 | 0.3539 | | 0.1127 | 300 | 0.3299 | 0.353 | | 0.1202 | 320 | 0.3044 | 0.3522 | | 0.1277 | 340 | 0.3433 | 0.3512 | | 0.1352 | 360 | 0.3564 | 0.3503 | | 0.1427 | 380 | 0.3365 | 0.3493 | | 0.1502 | 400 | 0.3721 | 0.3481 | | 0.1577 | 420 | 0.3636 | 0.3469 | | 0.1652 | 440 | 0.3661 | 0.3457 | | 0.1727 | 460 | 0.351 | 0.3443 | | 0.1802 | 480 | 0.327 | 0.3433 | | 0.1878 | 500 | 0.3447 | 0.3417 | | 0.1953 | 520 | 0.3271 | 0.34 | | 0.2028 | 540 | 0.3364 | 0.3383 | | 0.2103 | 560 | 0.298 | 0.3366 | | 0.2178 | 580 | 0.3392 | - | | 0.0004 | 1 | 0.3057 | - | | 0.0075 | 20 | 0.3281 | 0.3341 | | 0.0150 | 40 | 0.3415 | 0.332 | | 0.0225 | 60 | 0.3017 | 0.3285 | | 0.0300 | 80 | 0.3462 | 0.3232 | | 0.0376 | 100 | 0.3056 | 0.3156 | | 0.0451 | 120 | 0.3111 | 0.3063 | | 0.0526 | 140 | 0.3136 | 0.2955 | | 0.0601 | 160 | 0.3067 | 0.2802 | | 0.0676 | 180 | 0.2645 | 0.2593 | | 0.0751 | 200 | 0.2517 | 0.233 | | 0.0826 | 220 | 0.212 | 0.2077 | | 0.0901 | 240 | 0.1686 | 0.1881 | | 0.0976 | 260 | 0.1783 | 0.1731 | | 0.1051 | 280 | 0.1268 | 0.1592 | | 0.1127 | 300 | 0.137 | 0.1474 | | 0.1202 | 320 | 0.1372 | 0.1376 | | 0.1277 | 340 | 0.146 | 0.1287 | | 0.1352 | 360 | 0.1579 | 0.1226 | | 0.1427 | 380 | 0.1037 | 0.1162 | | 0.1502 | 400 | 0.1391 | 0.1105 | | 0.1577 | 420 | 0.136 | 0.1053 | | 0.1652 | 440 | 0.1212 | 0.1013 | | 0.1727 | 460 | 0.128 | 0.098 | | 0.1802 | 480 | 0.0701 | 0.0944 | | 0.1878 | 500 | 0.1274 | 0.0913 | | 0.1953 | 520 | 0.1235 | 0.0882 | | 0.2028 | 540 | 0.0761 | 0.0857 | | 0.2103 | 560 | 0.0942 | 0.0833 | | 0.2178 | 580 | 0.1046 | 0.0815 | | 0.2253 | 600 | 0.0812 | 0.0795 | | 0.2328 | 620 | 0.0888 | 0.0776 | | 0.2403 | 640 | 0.0867 | 0.076 | | 0.2478 | 660 | 0.0997 | 0.0743 | | 0.2554 | 680 | 0.1344 | 0.0728 | | 0.2629 | 700 | 0.07 | 0.0716 | | 0.2704 | 720 | 0.1014 | 0.0703 | | 0.2779 | 740 | 0.125 | 0.0692 | | 0.2854 | 760 | 0.078 | 0.0674 | | 0.2929 | 780 | 0.062 | 0.0666 | | 0.3004 | 800 | 0.1564 | 0.0659 | | 0.3079 | 820 | 0.0957 | 0.0648 | | 0.3154 | 840 | 0.1069 | 0.0635 | | 0.3229 | 860 | 0.0982 | 0.0622 | | 0.3305 | 880 | 0.0384 | 0.0608 | | 0.3380 | 900 | 0.1394 | 0.0597 | | 0.3455 | 920 | 0.0349 | 0.0591 | | 0.3530 | 940 | 0.087 | 0.0579 | | 0.3605 | 960 | 0.0878 | 0.0571 | | 0.3680 | 980 | 0.0695 | 0.0565 | | 0.3755 | 1000 | 0.0437 | 0.0556 | | 0.3830 | 1020 | 0.0431 | 0.0551 | | 0.3905 | 1040 | 0.0391 | 0.0545 | | 0.3980 | 1060 | 0.0936 | 0.0544 | | 0.4056 | 1080 | 0.066 | 0.054 | | 0.4131 | 1100 | 0.1169 | 0.0534 | | 0.4206 | 1120 | 0.0445 | 0.0525 | | 0.4281 | 1140 | 0.0365 | 0.0519 | | 0.4356 | 1160 | 0.0714 | 0.0517 | | 0.4431 | 1180 | 0.043 | 0.051 | | 0.4506 | 1200 | 0.0754 | 0.0506 | | 0.4581 | 1220 | 0.0592 | 0.0501 | | 0.4656 | 1240 | 0.0775 | 0.0498 | | 0.4732 | 1260 | 0.0601 | 0.0494 | | 0.4807 | 1280 | 0.0903 | 0.0486 | | 0.4882 | 1300 | 0.0518 | 0.0481 | | 0.4957 | 1320 | 0.0462 | 0.0477 | | 0.5032 | 1340 | 0.0413 | 0.0477 | | 0.5107 | 1360 | 0.044 | 0.0473 | | 0.5182 | 1380 | 0.0724 | 0.047 | | 0.5257 | 1400 | 0.0433 | 0.0468 | | 0.5332 | 1420 | 0.0511 | 0.0465 | | 0.5407 | 1440 | 0.065 | 0.0462 | | 0.5483 | 1460 | 0.0611 | 0.0458 | | 0.5558 | 1480 | 0.0419 | 0.0459 | | 0.5633 | 1500 | 0.0595 | 0.0456 | | 0.5708 | 1520 | 0.0718 | 0.0452 | | 0.5783 | 1540 | 0.0577 | 0.0449 | | 0.5858 | 1560 | 0.0515 | 0.0447 | | 0.5933 | 1580 | 0.0388 | 0.0444 | | 0.6008 | 1600 | 0.0764 | 0.0443 | | 0.6083 | 1620 | 0.0876 | 0.0441 | | 0.6158 | 1640 | 0.0361 | 0.0436 | | 0.6234 | 1660 | 0.0549 | 0.0435 | | 0.6309 | 1680 | 0.0207 | 0.0434 | | 0.6384 | 1700 | 0.0366 | 0.0434 | | 0.6459 | 1720 | 0.0342 | 0.0433 | | 0.6534 | 1740 | 0.0313 | 0.043 | | 0.6609 | 1760 | 0.0342 | 0.0432 | | 0.6684 | 1780 | 0.0744 | 0.0429 | | 0.6759 | 1800 | 0.0282 | 0.0428 | | 0.6834 | 1820 | 0.0479 | 0.0429 | | 0.6910 | 1840 | 0.0497 | 0.0426 | | 0.6985 | 1860 | 0.0513 | 0.0426 | | 0.7060 | 1880 | 0.02 | 0.0423 | | 0.7135 | 1900 | 0.0238 | 0.0424 | | 0.7210 | 1920 | 0.0446 | 0.0422 | | 0.7285 | 1940 | 0.0853 | 0.0419 | | 0.7360 | 1960 | 0.0234 | 0.0416 | | 0.7435 | 1980 | 0.0646 | 0.0416 | | 0.7510 | 2000 | 0.0387 | 0.0419 | | 0.7585 | 2020 | 0.0419 | 0.0416 | | 0.7661 | 2040 | 0.0326 | 0.0419 | | 0.7736 | 2060 | 0.0344 | 0.0414 | | 0.7811 | 2080 | 0.0246 | 0.041 | | 0.7886 | 2100 | 0.0383 | 0.0408 | | 0.7961 | 2120 | 0.0315 | 0.0407 | | 0.8036 | 2140 | 0.0408 | 0.0406 | | 0.8111 | 2160 | 0.0293 | 0.0403 | | 0.8186 | 2180 | 0.0242 | 0.0405 | | 0.8261 | 2200 | 0.0317 | 0.0399 | | 0.8336 | 2220 | 0.0416 | 0.0396 | | 0.8412 | 2240 | 0.0503 | 0.0395 | | 0.8487 | 2260 | 0.0468 | 0.0394 | | 0.8562 | 2280 | 0.0231 | 0.0395 | | 0.8637 | 2300 | 0.0363 | 0.0394 | | 0.8712 | 2320 | 0.0423 | 0.0395 | | 0.8787 | 2340 | 0.0321 | 0.0391 | | 0.8862 | 2360 | 0.0226 | 0.0391 | | 0.8937 | 2380 | 0.0567 | 0.039 | | 0.9012 | 2400 | 0.0421 | 0.039 | | 0.9087 | 2420 | 0.0462 | 0.0389 | | 0.9163 | 2440 | 0.0109 | 0.0388 | | 0.9238 | 2460 | 0.0209 | 0.039 | | 0.9313 | 2480 | 0.0133 | 0.0387 | | 0.9388 | 2500 | 0.0309 | 0.0386 | | 0.9463 | 2520 | 0.0179 | 0.0386 | | 0.9538 | 2540 | 0.0288 | 0.0387 | | 0.9613 | 2560 | 0.0434 | 0.0388 | | 0.9688 | 2580 | 0.0307 | 0.0387 | | 0.9763 | 2600 | 0.0396 | 0.039 | | 0.9839 | 2620 | 0.0418 | 0.0385 | | 0.9914 | 2640 | 0.0115 | 0.0385 | | 0.9989 | 2660 | 0.0416 | 0.0386 | | 1.0064 | 2680 | 0.0236 | 0.0385 | | 1.0139 | 2700 | 0.0302 | 0.0385 | | 1.0214 | 2720 | 0.0261 | 0.0385 | | 1.0289 | 2740 | 0.0184 | 0.0388 | | 1.0364 | 2760 | 0.0364 | 0.0385 | | 1.0439 | 2780 | 0.0253 | 0.0385 | | 1.0514 | 2800 | 0.0271 | 0.0385 | | 1.0590 | 2820 | 0.0056 | 0.0385 | | 1.0665 | 2840 | 0.0327 | 0.0384 | | 1.0740 | 2860 | 0.0237 | 0.0381 | | 1.0815 | 2880 | 0.0375 | 0.0383 | | 1.0890 | 2900 | 0.0204 | 0.038 | | 1.0965 | 2920 | 0.0551 | 0.0379 | | 1.1040 | 2940 | 0.0274 | 0.038 | | 1.1115 | 2960 | 0.0136 | 0.038 | | 1.1190 | 2980 | 0.0193 | 0.0381 | | 1.1265 | 3000 | 0.0449 | 0.0376 | | 1.1341 | 3020 | 0.0403 | 0.0376 | | 1.1416 | 3040 | 0.0237 | 0.0372 | | 1.1491 | 3060 | 0.0133 | 0.037 | | 1.1566 | 3080 | 0.0313 | 0.037 | | 1.1641 | 3100 | 0.0205 | 0.0369 | | 1.1716 | 3120 | 0.0274 | 0.0371 | | 1.1791 | 3140 | 0.0178 | 0.0372 | | 1.1866 | 3160 | 0.0258 | 0.0375 | | 1.1941 | 3180 | 0.0466 | 0.0371 | | 1.2017 | 3200 | 0.0258 | 0.037 | | 1.2092 | 3220 | 0.0277 | 0.0371 | | 1.2167 | 3240 | 0.0137 | 0.0371 | | 1.2242 | 3260 | 0.0232 | 0.0372 | | 1.2317 | 3280 | 0.0267 | 0.0371 | | 1.2392 | 3300 | 0.0126 | 0.0375 | | 1.2467 | 3320 | 0.0514 | 0.0372 | | 1.2542 | 3340 | 0.0175 | 0.0373 | | 1.2617 | 3360 | 0.0188 | 0.0374 | | 1.2692 | 3380 | 0.0137 | 0.0372 | | 1.2768 | 3400 | 0.035 | 0.0372 | | 1.2843 | 3420 | 0.0309 | 0.0371 | | 1.2918 | 3440 | 0.0462 | 0.0373 | | 1.2993 | 3460 | 0.0388 | 0.0371 | | 1.3068 | 3480 | 0.0573 | 0.0372 | | 1.3143 | 3500 | 0.02 | 0.0373 | | 1.3218 | 3520 | 0.0376 | 0.0372 | | 1.3293 | 3540 | 0.0165 | 0.0374 | | 1.3368 | 3560 | 0.0118 | 0.0372 | | 1.3443 | 3580 | 0.0167 | 0.0374 | | 1.3519 | 3600 | 0.0137 | 0.0373 | | 1.3594 | 3620 | 0.0044 | 0.0371 | | 1.3669 | 3640 | 0.0085 | 0.037 | | 1.3744 | 3660 | 0.0336 | 0.0368 | | 1.3819 | 3680 | 0.0217 | 0.0369 | | 1.3894 | 3700 | 0.0395 | 0.0369 | | 1.3969 | 3720 | 0.033 | 0.0371 | | 1.4044 | 3740 | 0.0173 | 0.0368 | | 1.4119 | 3760 | 0.0126 | 0.0367 | | 1.4195 | 3780 | 0.012 | 0.0367 | | 1.4270 | 3800 | 0.0364 | 0.0366 | | 1.4345 | 3820 | 0.0238 | 0.0366 | | 1.4420 | 3840 | 0.0199 | 0.0365 | | 1.4495 | 3860 | 0.0152 | 0.0368 | | 1.4570 | 3880 | 0.035 | 0.0366 | | 1.4645 | 3900 | 0.0413 | 0.0365 | | 1.4720 | 3920 | 0.0208 | 0.0366 | | 1.4795 | 3940 | 0.0074 | 0.0366 | | 1.4870 | 3960 | 0.0116 | 0.0366 | | 1.4946 | 3980 | 0.0088 | 0.0365 | | 1.5021 | 4000 | 0.0264 | 0.0367 | | 1.5096 | 4020 | 0.0161 | 0.0363 | | 1.5171 | 4040 | 0.0549 | 0.0362 | | 1.5246 | 4060 | 0.0166 | 0.0362 | | 1.5321 | 4080 | 0.0162 | 0.0361 | | 1.5396 | 4100 | 0.0174 | 0.0363 | | 1.5471 | 4120 | 0.0231 | 0.0362 | | 1.5546 | 4140 | 0.0143 | 0.0364 | | 1.5621 | 4160 | 0.0168 | 0.0361 | | 1.5697 | 4180 | 0.0149 | 0.0361 | | 1.5772 | 4200 | 0.013 | 0.0361 | | 1.5847 | 4220 | 0.0122 | 0.0361 | | 1.5922 | 4240 | 0.0061 | 0.0362 | | 1.5997 | 4260 | 0.0088 | 0.0361 | | 1.6072 | 4280 | 0.0071 | 0.0364 | | 1.6147 | 4300 | 0.0168 | 0.0361 | | 1.6222 | 4320 | 0.0333 | 0.0361 | | 1.6297 | 4340 | 0.0487 | 0.0362 | | 1.6373 | 4360 | 0.0177 | 0.0361 | | 1.6448 | 4380 | 0.0086 | 0.0361 | | 1.6523 | 4400 | 0.0244 | 0.036 | | 1.6598 | 4420 | 0.0294 | 0.0362 | | 1.6673 | 4440 | 0.0134 | 0.0359 | | 1.6748 | 4460 | 0.0081 | 0.0358 | | 1.6823 | 4480 | 0.011 | 0.0357 | | 1.6898 | 4500 | 0.0453 | 0.0357 | | 1.6973 | 4520 | 0.0269 | 0.0358 | | 1.7048 | 4540 | 0.039 | 0.0357 | | 1.7124 | 4560 | 0.0346 | 0.036 | | 1.7199 | 4580 | 0.0164 | 0.0357 | | 1.7274 | 4600 | 0.0081 | 0.0356 | | 1.7349 | 4620 | 0.0343 | 0.0357 | | 1.7424 | 4640 | 0.0071 | 0.0356 | | 1.7499 | 4660 | 0.0349 | 0.0357 | | 1.7574 | 4680 | 0.0128 | 0.0356 | | 1.7649 | 4700 | 0.0128 | 0.0359 | | 1.7724 | 4720 | 0.0375 | 0.0356 | | 1.7799 | 4740 | 0.0257 | 0.0356 | | 1.7875 | 4760 | 0.0514 | 0.0355 | | 1.7950 | 4780 | 0.0077 | 0.0354 | | 1.8025 | 4800 | 0.0281 | 0.0355 | | 1.8100 | 4820 | 0.0236 | 0.0354 | | 1.8175 | 4840 | 0.0097 | 0.0357 | | 1.8250 | 4860 | 0.0195 | 0.0354 | | 1.8325 | 4880 | 0.0057 | 0.0353 | | 1.8400 | 4900 | 0.0213 | 0.0354 | | 1.8475 | 4920 | 0.0059 | 0.0353 | | 1.8551 | 4940 | 0.0237 | 0.0354 | | 1.8626 | 4960 | 0.0189 | 0.0354 | | 1.8701 | 4980 | 0.0352 | 0.0356 | | 1.8776 | 5000 | 0.0069 | 0.0354 | | 1.8851 | 5020 | 0.0067 | 0.0354 | | 1.8926 | 5040 | 0.0151 | 0.0354 | | 1.9001 | 5060 | 0.0107 | 0.0354 | | 1.9076 | 5080 | 0.026 | 0.0355 | | 1.9151 | 5100 | 0.0764 | 0.0354 | | 1.9226 | 5120 | 0.0372 | 0.0357 | | 1.9302 | 5140 | 0.0162 | 0.0354 | | 1.9377 | 5160 | 0.0276 | 0.0353 | | 1.9452 | 5180 | 0.0306 | 0.0354 | | 1.9527 | 5200 | 0.0211 | 0.0353 | | 1.9602 | 5220 | 0.0252 | 0.0354 | | 1.9677 | 5240 | 0.0247 | 0.0354 | | 1.9752 | 5260 | 0.0239 | 0.0356 | | 1.9827 | 5280 | 0.0245 | 0.0354 | | **1.9902** | **5300** | **0.0144** | **0.0353** | | 1.9977 | 5320 | 0.0153 | 0.0353 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 3.0.1 - Transformers: 4.40.2 - PyTorch: 2.3.1+cu121 - Datasets: 2.20.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX ```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} } ```