--- library_name: setfit tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 metrics: - accuracy widget: - text: Não apenas isso. A bola de neve do endividamento - text: ' Bueno, yo lo que espero es que se traten con respeto, que se quieran. ' - text: ' Sí, pues pedirle a María Luisa que le dé seguimiento y que siga atendiendo las demandas de los ciudadanos de Vallarta, si te parece. Ya ella seguramente nos está viendo y está tomando nota para darle continuidad a las demandas de ambientalistas de Vallarta. ' - text: A confiança na economia despertou o apetite pelo risco, criando instrumentos financeiros indispensáveis à captação de novos recursos para a expansão produtiva. - text: " A ver, pon la carta de Elba Esther. Es que luego la borró. Fue en mayo\ \ del 23, 2 de mayo: ‘Ahí le espero con el Ejército —supuestamente esto\ \ es lo que le dijo Calderón a la maestra Elba Esther, ahí la espero con el\ \ Ejército— esa fue la respuesta del entonces presidente de México, Felipe\ \ Calderón, cuando le dije —según la maestra— que las y los maestros de\ \ México nos oponíamos a que Miguel Ã\x81ngel Yunes continuara como titular\ \ del Issste, dadas las malversaciones de fondos financieros que con tanto trabajo\ \ las los trabajadores al servicio del Estado logramos con la reforma a dicha\ \ institución. ‘Cuando me comentó que Yunes estaba haciendo bien su trabajo,\ \ no me dejó más alternativa —dice la maestra— que advertirle que tomaríamos\ \ las instalaciones del Issste y justo esa fue su respuesta: Ahí la espero con\ \ el Ejército. Esto sucedió en el marco de un evento público en una escuela\ \ secundaria técnica de la ahora Ciudad de México. Ante su respuesta, me levanté\ \ y me retiré. ‘Recordemos que la elección y remoción del director del Issste\ \ compete única y exclusivamente al titular del Ejecutivo federal y no a una\ \ servidora.’ Aquí me está contestando a mí, porque yo dije que a ella le\ \ habían entregado por ayudar en el fraude, que no me diría la maestra que no\ \ ayudó en el fraude del 2006, y a cambio yo sostengo que le entregaron el Issste,\ \ la Subsecretaría de Educación Pública y la Lotería Nacional. ‘Por ello,\ \ en relación a las declaraciones hechas por el presidente Andrés Manuel López\ \ Obrador el pasado 29 de abril del presente año, sobre mi persona y la gestión\ \ del señor Miguel Ã\x81ngel Yunes al frente del Issste, le digo categóricamente\ \ que no participé el acto ilícito alguno, como me acusa desde su tribuna’.\ \ Yo no estoy acusando más que de haberse aliado con Calderón y ayudarle en\ \ el fraude electoral. ‘Siempre me he conducido conforme a derecho, de respeto\ \ a las instituciones de este país y, desde luego, a la investidura presidencial.\ \ Por ello, señor presidente, basta de falsas acusaciones a mi persona’. No\ \ es nada personal, maestra, es que estamos viviendo un momento importantísimo\ \ de transformación. Entonces, como el compañero que viene a hacernos preguntas\ \ sobre salud, ayuda a recordar, porque es como si padecieran amnesia, ya se olvidó\ \ cómo era. Y antes esto no lo tocaban, era silencio, como vasallos, obedecer\ \ y callar, siempre y cuando hubiese dinero de por medio, porque lo que no suena\ \ lógico suena metálico. Entonces, hay que ir aclarando todo, seguir purificando\ \ la vida pública del país y por eso son muy buenas estas mañaneras. Pero,\ \ bueno, eso es lo que queríamos decir. ¿Qué se está haciendo? Procurar, ya\ \ es un compromiso, garantizar el derecho a la salud. Y vaya que ha costado, por\ \ estos intereses. Imagínense, no se podían comprar medicinas en el extranjero\ \ porque la ley lo prohibía, lo impedía; tuvimos que reformar la ley. ¿Y quiénes\ \ votaron en contra de que se pudiera comprar la medicina en el extranjero? El\ \ bloque conservador. ¿Qué son entonces? Representantes de minorías, no representantes\ \ del pueblo, esa es nuestra diferencia de fondo. No es nada personal, pero sí\ \ es importante el darle su sitio que le corresponde a lo público. República\ \ es, res publica, cosa pública. Si vivimos en una república, tenemos que pensar\ \ en eso, en lo público. Eso ya se había olvidado. Entonces, vamos a continuar\ \ con lo mismo y va adelante todo el plan de transformación. El viernes vamos\ \ a informar sobre salud y luego vamos a informar en específico sobre el Issste,\ \ porque ya llevamos… ¿Cuánto tiempo llevamos? " pipeline_tag: text-classification inference: true model-index: - name: SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.7727272727272727 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) 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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 128 tokens - **Number of Classes:** 3 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 | |:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 0 | | | 1 | | | 2 | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.7727 | ## 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("alelov/test-model-label1-MiniLMVERSION2") # Run inference preds = model("Não apenas isso. A bola de neve do endividamento") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:---------|:-----| | Word count | 1 | 103.4095 | 2340 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 311 | | 1 | 27 | | 2 | 21 | ### Training Hyperparameters - batch_size: (16, 16) - 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: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:---------:|:-------------:|:---------------:| | 0.0002 | 1 | 0.2894 | - | | 0.0081 | 50 | 0.2562 | - | | 0.0163 | 100 | 0.3346 | - | | 0.0244 | 150 | 0.3106 | - | | 0.0326 | 200 | 0.2452 | - | | 0.0407 | 250 | 0.2848 | - | | 0.0489 | 300 | 0.188 | - | | 0.0570 | 350 | 0.1865 | - | | 0.0651 | 400 | 0.1345 | - | | 0.0733 | 450 | 0.1494 | - | | 0.0814 | 500 | 0.1723 | - | | 0.0896 | 550 | 0.0241 | - | | 0.0977 | 600 | 0.0298 | - | | 0.1058 | 650 | 0.01 | - | | 0.1140 | 700 | 0.0354 | - | | 0.1221 | 750 | 0.004 | - | | 0.1303 | 800 | 0.0016 | - | | 0.1384 | 850 | 0.0022 | - | | 0.1466 | 900 | 0.0032 | - | | 0.1547 | 950 | 0.0029 | - | | 0.1628 | 1000 | 0.0009 | - | | 0.1710 | 1050 | 0.0031 | - | | 0.1791 | 1100 | 0.0525 | - | | 0.1873 | 1150 | 0.0006 | - | | 0.1954 | 1200 | 0.0007 | - | | 0.2035 | 1250 | 0.0007 | - | | 0.2117 | 1300 | 0.0014 | - | | 0.2198 | 1350 | 0.0006 | - | | 0.2280 | 1400 | 0.0071 | - | | 0.2361 | 1450 | 0.0004 | - | | 0.2443 | 1500 | 0.0003 | - | | 0.2524 | 1550 | 0.0004 | - | | 0.2605 | 1600 | 0.0019 | - | | 0.2687 | 1650 | 0.0499 | - | | 0.2768 | 1700 | 0.0004 | - | | 0.2850 | 1750 | 0.0259 | - | | 0.2931 | 1800 | 0.0002 | - | | 0.3013 | 1850 | 0.0001 | - | | 0.3094 | 1900 | 0.0003 | - | | 0.3175 | 1950 | 0.0002 | - | | 0.3257 | 2000 | 0.0003 | - | | 0.3338 | 2050 | 0.0038 | - | | 0.3420 | 2100 | 0.0001 | - | | 0.3501 | 2150 | 0.0002 | - | | 0.3582 | 2200 | 0.0002 | - | | 0.3664 | 2250 | 0.0001 | - | | 0.3745 | 2300 | 0.0001 | - | | 0.3827 | 2350 | 0.0001 | - | | 0.3908 | 2400 | 0.0044 | - | | 0.3990 | 2450 | 0.0436 | - | | 0.4071 | 2500 | 0.0002 | - | | 0.4152 | 2550 | 0.0007 | - | | 0.4234 | 2600 | 0.0001 | - | | 0.4315 | 2650 | 0.0001 | - | | 0.4397 | 2700 | 0.0001 | - | | 0.4478 | 2750 | 0.0023 | - | | 0.4560 | 2800 | 0.0001 | - | | 0.4641 | 2850 | 0.0009 | - | | 0.4722 | 2900 | 0.0001 | - | | 0.4804 | 2950 | 0.0001 | - | | 0.4885 | 3000 | 0.003 | - | | 0.4967 | 3050 | 0.0001 | - | | 0.5048 | 3100 | 0.0004 | - | | 0.5129 | 3150 | 0.0 | - | | 0.5211 | 3200 | 0.0001 | - | | 0.5292 | 3250 | 0.0001 | - | | 0.5374 | 3300 | 0.0 | - | | 0.5455 | 3350 | 0.0 | - | | 0.5537 | 3400 | 0.0001 | - | | 0.5618 | 3450 | 0.0 | - | | 0.5699 | 3500 | 0.0001 | - | | 0.5781 | 3550 | 0.0 | - | | 0.5862 | 3600 | 0.0 | - | | 0.5944 | 3650 | 0.0 | - | | 0.6025 | 3700 | 0.0 | - | | 0.6106 | 3750 | 0.0 | - | | 0.6188 | 3800 | 0.0001 | - | | 0.6269 | 3850 | 0.0 | - | | 0.6351 | 3900 | 0.0 | - | | 0.6432 | 3950 | 0.0004 | - | | 0.6514 | 4000 | 0.0004 | - | | 0.6595 | 4050 | 0.0 | - | | 0.6676 | 4100 | 0.0 | - | | 0.6758 | 4150 | 0.0 | - | | 0.6839 | 4200 | 0.0011 | - | | 0.6921 | 4250 | 0.0006 | - | | 0.7002 | 4300 | 0.0001 | - | | 0.7084 | 4350 | 0.0 | - | | 0.7165 | 4400 | 0.0 | - | | 0.7246 | 4450 | 0.0 | - | | 0.7328 | 4500 | 0.0 | - | | 0.7409 | 4550 | 0.0 | - | | 0.7491 | 4600 | 0.0 | - | | 0.7572 | 4650 | 0.0 | - | | 0.7653 | 4700 | 0.0 | - | | 0.7735 | 4750 | 0.0041 | - | | 0.7816 | 4800 | 0.0004 | - | | 0.7898 | 4850 | 0.0006 | - | | 0.7979 | 4900 | 0.0 | - | | 0.8061 | 4950 | 0.0 | - | | 0.8142 | 5000 | 0.0 | - | | 0.8223 | 5050 | 0.0 | - | | 0.8305 | 5100 | 0.0 | - | | 0.8386 | 5150 | 0.0 | - | | 0.8468 | 5200 | 0.0 | - | | 0.8549 | 5250 | 0.0 | - | | 0.8631 | 5300 | 0.0 | - | | 0.8712 | 5350 | 0.0 | - | | 0.8793 | 5400 | 0.0 | - | | 0.8875 | 5450 | 0.0 | - | | 0.8956 | 5500 | 0.0 | - | | 0.9038 | 5550 | 0.0 | - | | 0.9119 | 5600 | 0.0 | - | | 0.9200 | 5650 | 0.0 | - | | 0.9282 | 5700 | 0.0 | - | | 0.9363 | 5750 | 0.0 | - | | 0.9445 | 5800 | 0.0 | - | | 0.9526 | 5850 | 0.0 | - | | 0.9608 | 5900 | 0.0 | - | | 0.9689 | 5950 | 0.0 | - | | 0.9770 | 6000 | 0.0 | - | | 0.9852 | 6050 | 0.0595 | - | | 0.9933 | 6100 | 0.0001 | - | | 1.0 | 6141 | - | 0.2767 | | 1.0015 | 6150 | 0.0 | - | | 1.0096 | 6200 | 0.0 | - | | 1.0177 | 6250 | 0.0 | - | | 1.0259 | 6300 | 0.0 | - | | 1.0340 | 6350 | 0.0 | - | | 1.0422 | 6400 | 0.0 | - | | 1.0503 | 6450 | 0.0 | - | | 1.0585 | 6500 | 0.0 | - | | 1.0666 | 6550 | 0.0 | - | | 1.0747 | 6600 | 0.0 | - | | 1.0829 | 6650 | 0.0 | - | | 1.0910 | 6700 | 0.0 | - | | 1.0992 | 6750 | 0.0 | - | | 1.1073 | 6800 | 0.0 | - | | 1.1155 | 6850 | 0.0 | - | | 1.1236 | 6900 | 0.0 | - | | 1.1317 | 6950 | 0.0 | - | | 1.1399 | 7000 | 0.0 | - | | 1.1480 | 7050 | 0.0 | - | | 1.1562 | 7100 | 0.0 | - | | 1.1643 | 7150 | 0.0 | - | | 1.1724 | 7200 | 0.0 | - | | 1.1806 | 7250 | 0.0 | - | | 1.1887 | 7300 | 0.0 | - | | 1.1969 | 7350 | 0.0 | - | | 1.2050 | 7400 | 0.0 | - | | 1.2132 | 7450 | 0.0 | - | | 1.2213 | 7500 | 0.0001 | - | | 1.2294 | 7550 | 0.0 | - | | 1.2376 | 7600 | 0.0 | - | | 1.2457 | 7650 | 0.0 | - | | 1.2539 | 7700 | 0.0 | - | | 1.2620 | 7750 | 0.0 | - | | 1.2702 | 7800 | 0.0001 | - | | 1.2783 | 7850 | 0.0 | - | | 1.2864 | 7900 | 0.0 | - | | 1.2946 | 7950 | 0.0002 | - | | 1.3027 | 8000 | 0.0 | - | | 1.3109 | 8050 | 0.0003 | - | | 1.3190 | 8100 | 0.0588 | - | | 1.3271 | 8150 | 0.0 | - | | 1.3353 | 8200 | 0.0002 | - | | 1.3434 | 8250 | 0.0 | - | | 1.3516 | 8300 | 0.0 | - | | 1.3597 | 8350 | 0.0 | - | | 1.3679 | 8400 | 0.0261 | - | | 1.3760 | 8450 | 0.0 | - | | 1.3841 | 8500 | 0.0 | - | | 1.3923 | 8550 | 0.0 | - | | 1.4004 | 8600 | 0.0 | - | | 1.4086 | 8650 | 0.0 | - | | 1.4167 | 8700 | 0.0 | - | | 1.4248 | 8750 | 0.0 | - | | 1.4330 | 8800 | 0.0 | - | | 1.4411 | 8850 | 0.0 | - | | 1.4493 | 8900 | 0.0 | - | | 1.4574 | 8950 | 0.0 | - | | 1.4656 | 9000 | 0.0 | - | | 1.4737 | 9050 | 0.0 | - | | 1.4818 | 9100 | 0.0 | - | | 1.4900 | 9150 | 0.0153 | - | | 1.4981 | 9200 | 0.0 | - | | 1.5063 | 9250 | 0.0 | - | | 1.5144 | 9300 | 0.0 | - | | 1.5226 | 9350 | 0.0 | - | | 1.5307 | 9400 | 0.0 | - | | 1.5388 | 9450 | 0.0003 | - | | 1.5470 | 9500 | 0.0 | - | | 1.5551 | 9550 | 0.0003 | - | | 1.5633 | 9600 | 0.0 | - | | 1.5714 | 9650 | 0.0 | - | | 1.5795 | 9700 | 0.0 | - | | 1.5877 | 9750 | 0.0 | - | | 1.5958 | 9800 | 0.0 | - | | 1.6040 | 9850 | 0.0 | - | | 1.6121 | 9900 | 0.0 | - | | 1.6203 | 9950 | 0.0 | - | | 1.6284 | 10000 | 0.0 | - | | 1.6365 | 10050 | 0.0 | - | | 1.6447 | 10100 | 0.0 | - | | 1.6528 | 10150 | 0.0 | - | | 1.6610 | 10200 | 0.0 | - | | 1.6691 | 10250 | 0.0 | - | | 1.6773 | 10300 | 0.0 | - | | 1.6854 | 10350 | 0.0 | - | | 1.6935 | 10400 | 0.0 | - | | 1.7017 | 10450 | 0.0 | - | | 1.7098 | 10500 | 0.0 | - | | 1.7180 | 10550 | 0.0 | - | | 1.7261 | 10600 | 0.0 | - | | 1.7342 | 10650 | 0.0 | - | | 1.7424 | 10700 | 0.0 | - | | 1.7505 | 10750 | 0.0 | - | | 1.7587 | 10800 | 0.0 | - | | 1.7668 | 10850 | 0.0 | - | | 1.7750 | 10900 | 0.0 | - | | 1.7831 | 10950 | 0.0 | - | | 1.7912 | 11000 | 0.0 | - | | 1.7994 | 11050 | 0.0 | - | | 1.8075 | 11100 | 0.0 | - | | 1.8157 | 11150 | 0.0 | - | | 1.8238 | 11200 | 0.0 | - | | 1.8319 | 11250 | 0.0 | - | | 1.8401 | 11300 | 0.0 | - | | 1.8482 | 11350 | 0.0 | - | | 1.8564 | 11400 | 0.0 | - | | 1.8645 | 11450 | 0.0 | - | | 1.8727 | 11500 | 0.0 | - | | 1.8808 | 11550 | 0.0 | - | | 1.8889 | 11600 | 0.0 | - | | 1.8971 | 11650 | 0.0 | - | | 1.9052 | 11700 | 0.0 | - | | 1.9134 | 11750 | 0.0 | - | | 1.9215 | 11800 | 0.0 | - | | 1.9297 | 11850 | 0.0 | - | | 1.9378 | 11900 | 0.0006 | - | | 1.9459 | 11950 | 0.0 | - | | 1.9541 | 12000 | 0.0 | - | | 1.9622 | 12050 | 0.0 | - | | 1.9704 | 12100 | 0.0 | - | | 1.9785 | 12150 | 0.0 | - | | 1.9866 | 12200 | 0.0 | - | | 1.9948 | 12250 | 0.0 | - | | 2.0 | 12282 | - | 0.2742 | | 2.0029 | 12300 | 0.0 | - | | 2.0111 | 12350 | 0.0 | - | | 2.0192 | 12400 | 0.0 | - | | 2.0274 | 12450 | 0.0 | - | | 2.0355 | 12500 | 0.0 | - | | 2.0436 | 12550 | 0.0 | - | | 2.0518 | 12600 | 0.0 | - | | 2.0599 | 12650 | 0.0 | - | | 2.0681 | 12700 | 0.0 | - | | 2.0762 | 12750 | 0.0 | - | | 2.0844 | 12800 | 0.0 | - | | 2.0925 | 12850 | 0.0 | - | | 2.1006 | 12900 | 0.0 | - | | 2.1088 | 12950 | 0.0 | - | | 2.1169 | 13000 | 0.0 | - | | 2.1251 | 13050 | 0.0 | - | | 2.1332 | 13100 | 0.0 | - | | 2.1413 | 13150 | 0.0 | - | | 2.1495 | 13200 | 0.0 | - | | 2.1576 | 13250 | 0.0 | - | | 2.1658 | 13300 | 0.0 | - | | 2.1739 | 13350 | 0.0 | - | | 2.1821 | 13400 | 0.0 | - | | 2.1902 | 13450 | 0.0 | - | | 2.1983 | 13500 | 0.0 | - | | 2.2065 | 13550 | 0.0 | - | | 2.2146 | 13600 | 0.0 | - | | 2.2228 | 13650 | 0.0 | - | | 2.2309 | 13700 | 0.0 | - | | 2.2390 | 13750 | 0.0 | - | | 2.2472 | 13800 | 0.0 | - | | 2.2553 | 13850 | 0.0 | - | | 2.2635 | 13900 | 0.0 | - | | 2.2716 | 13950 | 0.0 | - | | 2.2798 | 14000 | 0.0 | - | | 2.2879 | 14050 | 0.0013 | - | | 2.2960 | 14100 | 0.0 | - | | 2.3042 | 14150 | 0.0 | - | | 2.3123 | 14200 | 0.0 | - | | 2.3205 | 14250 | 0.0 | - | | 2.3286 | 14300 | 0.0 | - | | 2.3368 | 14350 | 0.0 | - | | 2.3449 | 14400 | 0.0 | - | | 2.3530 | 14450 | 0.0019 | - | | 2.3612 | 14500 | 0.0 | - | | 2.3693 | 14550 | 0.0 | - | | 2.3775 | 14600 | 0.0 | - | | 2.3856 | 14650 | 0.0 | - | | 2.3937 | 14700 | 0.0 | - | | 2.4019 | 14750 | 0.0 | - | | 2.4100 | 14800 | 0.0 | - | | 2.4182 | 14850 | 0.0 | - | | 2.4263 | 14900 | 0.0 | - | | 2.4345 | 14950 | 0.0 | - | | 2.4426 | 15000 | 0.0 | - | | 2.4507 | 15050 | 0.0 | - | | 2.4589 | 15100 | 0.0 | - | | 2.4670 | 15150 | 0.0 | - | | 2.4752 | 15200 | 0.0 | - | | 2.4833 | 15250 | 0.0 | - | | 2.4915 | 15300 | 0.0 | - | | 2.4996 | 15350 | 0.0 | - | | 2.5077 | 15400 | 0.0 | - | | 2.5159 | 15450 | 0.0 | - | | 2.5240 | 15500 | 0.0 | - | | 2.5322 | 15550 | 0.0 | - | | 2.5403 | 15600 | 0.0 | - | | 2.5484 | 15650 | 0.0 | - | | 2.5566 | 15700 | 0.0 | - | | 2.5647 | 15750 | 0.0 | - | | 2.5729 | 15800 | 0.0 | - | | 2.5810 | 15850 | 0.0 | - | | 2.5892 | 15900 | 0.0001 | - | | 2.5973 | 15950 | 0.0 | - | | 2.6054 | 16000 | 0.0 | - | | 2.6136 | 16050 | 0.0 | - | | 2.6217 | 16100 | 0.0 | - | | 2.6299 | 16150 | 0.0 | - | | 2.6380 | 16200 | 0.0 | - | | 2.6461 | 16250 | 0.0 | - | | 2.6543 | 16300 | 0.0 | - | | 2.6624 | 16350 | 0.0 | - | | 2.6706 | 16400 | 0.0 | - | | 2.6787 | 16450 | 0.0 | - | | 2.6869 | 16500 | 0.0 | - | | 2.6950 | 16550 | 0.0 | - | | 2.7031 | 16600 | 0.0 | - | | 2.7113 | 16650 | 0.0002 | - | | 2.7194 | 16700 | 0.0 | - | | 2.7276 | 16750 | 0.0 | - | | 2.7357 | 16800 | 0.0 | - | | 2.7439 | 16850 | 0.0 | - | | 2.7520 | 16900 | 0.0 | - | | 2.7601 | 16950 | 0.0 | - | | 2.7683 | 17000 | 0.0291 | - | | 2.7764 | 17050 | 0.0 | - | | 2.7846 | 17100 | 0.0 | - | | 2.7927 | 17150 | 0.0 | - | | 2.8008 | 17200 | 0.0 | - | | 2.8090 | 17250 | 0.0 | - | | 2.8171 | 17300 | 0.0 | - | | 2.8253 | 17350 | 0.0 | - | | 2.8334 | 17400 | 0.0 | - | | 2.8416 | 17450 | 0.0 | - | | 2.8497 | 17500 | 0.0 | - | | 2.8578 | 17550 | 0.0 | - | | 2.8660 | 17600 | 0.0 | - | | 2.8741 | 17650 | 0.0 | - | | 2.8823 | 17700 | 0.0 | - | | 2.8904 | 17750 | 0.0 | - | | 2.8986 | 17800 | 0.0 | - | | 2.9067 | 17850 | 0.0 | - | | 2.9148 | 17900 | 0.0 | - | | 2.9230 | 17950 | 0.0 | - | | 2.9311 | 18000 | 0.0 | - | | 2.9393 | 18050 | 0.0 | - | | 2.9474 | 18100 | 0.0 | - | | 2.9555 | 18150 | 0.0 | - | | 2.9637 | 18200 | 0.0 | - | | 2.9718 | 18250 | 0.0 | - | | 2.9800 | 18300 | 0.0 | - | | 2.9881 | 18350 | 0.0 | - | | 2.9963 | 18400 | 0.0 | - | | **3.0** | **18423** | **-** | **0.2642** | | 3.0044 | 18450 | 0.0012 | - | | 3.0125 | 18500 | 0.0 | - | | 3.0207 | 18550 | 0.0 | - | | 3.0288 | 18600 | 0.0 | - | | 3.0370 | 18650 | 0.0 | - | | 3.0451 | 18700 | 0.0041 | - | | 3.0532 | 18750 | 0.0 | - | | 3.0614 | 18800 | 0.0 | - | | 3.0695 | 18850 | 0.0 | - | | 3.0777 | 18900 | 0.0 | - | | 3.0858 | 18950 | 0.0 | - | | 3.0940 | 19000 | 0.0 | - | | 3.1021 | 19050 | 0.0 | - | | 3.1102 | 19100 | 0.0 | - | | 3.1184 | 19150 | 0.0 | - | | 3.1265 | 19200 | 0.0 | - | | 3.1347 | 19250 | 0.0 | - | | 3.1428 | 19300 | 0.0 | - | | 3.1510 | 19350 | 0.0 | - | | 3.1591 | 19400 | 0.0 | - | | 3.1672 | 19450 | 0.0 | - | | 3.1754 | 19500 | 0.0014 | - | | 3.1835 | 19550 | 0.0 | - | | 3.1917 | 19600 | 0.0 | - | | 3.1998 | 19650 | 0.0 | - | | 3.2079 | 19700 | 0.0 | - | | 3.2161 | 19750 | 0.0 | - | | 3.2242 | 19800 | 0.0 | - | | 3.2324 | 19850 | 0.0 | - | | 3.2405 | 19900 | 0.0 | - | | 3.2487 | 19950 | 0.0 | - | | 3.2568 | 20000 | 0.0 | - | | 3.2649 | 20050 | 0.0 | - | | 3.2731 | 20100 | 0.0 | - | | 3.2812 | 20150 | 0.0 | - | | 3.2894 | 20200 | 0.0453 | - | | 3.2975 | 20250 | 0.0 | - | | 3.3057 | 20300 | 0.0 | - | | 3.3138 | 20350 | 0.0 | - | | 3.3219 | 20400 | 0.0 | - | | 3.3301 | 20450 | 0.0 | - | | 3.3382 | 20500 | 0.0 | - | | 3.3464 | 20550 | 0.0 | - | | 3.3545 | 20600 | 0.0 | - | | 3.3626 | 20650 | 0.0 | - | | 3.3708 | 20700 | 0.0 | - | | 3.3789 | 20750 | 0.0 | - | | 3.3871 | 20800 | 0.0 | - | | 3.3952 | 20850 | 0.0 | - | | 3.4034 | 20900 | 0.0 | - | | 3.4115 | 20950 | 0.0 | - | | 3.4196 | 21000 | 0.0 | - | | 3.4278 | 21050 | 0.0 | - | | 3.4359 | 21100 | 0.0 | - | | 3.4441 | 21150 | 0.0 | - | | 3.4522 | 21200 | 0.0 | - | | 3.4603 | 21250 | 0.0 | - | | 3.4685 | 21300 | 0.0 | - | | 3.4766 | 21350 | 0.0 | - | | 3.4848 | 21400 | 0.0 | - | | 3.4929 | 21450 | 0.0 | - | | 3.5011 | 21500 | 0.0 | - | | 3.5092 | 21550 | 0.0 | - | | 3.5173 | 21600 | 0.0 | - | | 3.5255 | 21650 | 0.0 | - | | 3.5336 | 21700 | 0.0 | - | | 3.5418 | 21750 | 0.0 | - | | 3.5499 | 21800 | 0.0 | - | | 3.5581 | 21850 | 0.0 | - | | 3.5662 | 21900 | 0.0 | - | | 3.5743 | 21950 | 0.0 | - | | 3.5825 | 22000 | 0.0 | - | | 3.5906 | 22050 | 0.0 | - | | 3.5988 | 22100 | 0.0 | - | | 3.6069 | 22150 | 0.0 | - | | 3.6150 | 22200 | 0.0 | - | | 3.6232 | 22250 | 0.0 | - | | 3.6313 | 22300 | 0.0 | - | | 3.6395 | 22350 | 0.0 | - | | 3.6476 | 22400 | 0.0 | - | | 3.6558 | 22450 | 0.0 | - | | 3.6639 | 22500 | 0.0 | - | | 3.6720 | 22550 | 0.0 | - | | 3.6802 | 22600 | 0.0 | - | | 3.6883 | 22650 | 0.0 | - | | 3.6965 | 22700 | 0.0 | - | | 3.7046 | 22750 | 0.0 | - | | 3.7128 | 22800 | 0.0 | - | | 3.7209 | 22850 | 0.0 | - | | 3.7290 | 22900 | 0.0 | - | | 3.7372 | 22950 | 0.0 | - | | 3.7453 | 23000 | 0.0 | - | | 3.7535 | 23050 | 0.0 | - | | 3.7616 | 23100 | 0.0 | - | | 3.7697 | 23150 | 0.0 | - | | 3.7779 | 23200 | 0.0 | - | | 3.7860 | 23250 | 0.0 | - | | 3.7942 | 23300 | 0.0 | - | | 3.8023 | 23350 | 0.0 | - | | 3.8105 | 23400 | 0.0 | - | | 3.8186 | 23450 | 0.0 | - | | 3.8267 | 23500 | 0.0 | - | | 3.8349 | 23550 | 0.0 | - | | 3.8430 | 23600 | 0.0 | - | | 3.8512 | 23650 | 0.0 | - | | 3.8593 | 23700 | 0.0 | - | | 3.8674 | 23750 | 0.0 | - | | 3.8756 | 23800 | 0.0 | - | | 3.8837 | 23850 | 0.0 | - | | 3.8919 | 23900 | 0.0 | - | | 3.9000 | 23950 | 0.0 | - | | 3.9082 | 24000 | 0.0 | - | | 3.9163 | 24050 | 0.0 | - | | 3.9244 | 24100 | 0.0 | - | | 3.9326 | 24150 | 0.0 | - | | 3.9407 | 24200 | 0.0 | - | | 3.9489 | 24250 | 0.0 | - | | 3.9570 | 24300 | 0.0 | - | | 3.9652 | 24350 | 0.0 | - | | 3.9733 | 24400 | 0.0 | - | | 3.9814 | 24450 | 0.0 | - | | 3.9896 | 24500 | 0.0 | - | | 3.9977 | 24550 | 0.0 | - | | 4.0 | 24564 | - | 0.2671 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 2.7.0 - Transformers: 4.40.2 - PyTorch: 2.2.1+cu121 - Datasets: 2.19.1 - 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} } ```