--- library_name: setfit tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer base_model: sentence-transformers/paraphrase-MiniLM-L6-v2 metrics: - accuracy widget: - text: What fabric has a comfortable feel and is suitable for people with sensitive skin? - text: What is the most recommended fabric for making outerwear that requires a blend of comfort and resilience? - text: What fabric has a fluid drape and is ideal for creating lightweight summer dresses? - text: Which fabric is best for creating versatile clothing items like casual shirts, blouses, and dresses in a periwinkle blue hue? - text: What kind of fabric is suitable for making form-fitting activewear like yoga pants and t-shirts? pipeline_tag: text-classification inference: true model-index: - name: SetFit with sentence-transformers/paraphrase-MiniLM-L6-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.3462566844919786 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-MiniLM-L6-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-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-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-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-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:** 75 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 | |:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 9 | | | 43 | | | 66 | | | 22 | | | 5 | | | 52 | | | 67 | | | 32 | | | 53 | | | 16 | | | 4 | | | 65 | | | 55 | | | 12 | | | 71 | | | 25 | | | 6 | | | 20 | | | 10 | | | 0 | | | 42 | | | 57 | | | 36 | | | 37 | | | 58 | | | 56 | | | 17 | | | 72 | | | 54 | | | 59 | | | 60 | | | 1 | | | 47 | | | 28 | | | 13 | | | 26 | | | 15 | | | 50 | | | 24 | | | 29 | | | 44 | | | 38 | | | 23 | | | 45 | | | 31 | | | 19 | | | 11 | | | 73 | | | 64 | | | 35 | | | 21 | | | 74 | | | 3 | | | 8 | | | 18 | | | 49 | | | 27 | | | 63 | | | 61 | | | 34 | | | 30 | | | 7 | | | 14 | | | 48 | | | 2 | | | 46 | | | 51 | | | 39 | | | 70 | | | 68 | | | 40 | | | 69 | | | 33 | | | 41 | | | 62 | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.3463 | ## 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("Jazielinho/fabric_model") # Run inference preds = model("What fabric has a comfortable feel and is suitable for people with sensitive skin?") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 7 | 15.4858 | 30 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 39 | | 1 | 40 | | 2 | 41 | | 3 | 32 | | 4 | 37 | | 5 | 33 | | 6 | 36 | | 7 | 40 | | 8 | 30 | | 9 | 36 | | 10 | 42 | | 11 | 38 | | 12 | 39 | | 13 | 43 | | 14 | 41 | | 15 | 41 | | 16 | 35 | | 17 | 42 | | 18 | 40 | | 19 | 43 | | 20 | 44 | | 21 | 36 | | 22 | 37 | | 23 | 40 | | 24 | 44 | | 25 | 42 | | 26 | 41 | | 27 | 38 | | 28 | 41 | | 29 | 46 | | 30 | 41 | | 31 | 38 | | 32 | 40 | | 33 | 39 | | 34 | 41 | | 35 | 44 | | 36 | 45 | | 37 | 40 | | 38 | 37 | | 39 | 44 | | 40 | 39 | | 41 | 42 | | 42 | 36 | | 43 | 43 | | 44 | 42 | | 45 | 37 | | 46 | 41 | | 47 | 44 | | 48 | 36 | | 49 | 40 | | 50 | 43 | | 51 | 44 | | 52 | 39 | | 53 | 38 | | 54 | 38 | | 55 | 43 | | 56 | 41 | | 57 | 44 | | 58 | 40 | | 59 | 41 | | 60 | 35 | | 61 | 43 | | 62 | 41 | | 63 | 43 | | 64 | 37 | | 65 | 41 | | 66 | 36 | | 67 | 38 | | 68 | 42 | | 69 | 41 | | 70 | 39 | | 71 | 43 | | 72 | 34 | | 73 | 40 | | 74 | 41 | ### Training Hyperparameters - batch_size: (256, 256) - num_epochs: (20, 20) - max_steps: -1 - sampling_strategy: undersampling - 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 | |:-------:|:-------:|:-------------:|:---------------:| | 0.0000 | 1 | 0.2732 | - | | 0.0015 | 50 | 0.2545 | - | | 0.0029 | 100 | 0.2538 | - | | 0.0044 | 150 | 0.2633 | - | | 0.0058 | 200 | 0.2598 | - | | 0.0073 | 250 | 0.2624 | - | | 0.0087 | 300 | 0.2537 | - | | 0.0102 | 350 | 0.2592 | - | | 0.0116 | 400 | 0.2475 | - | | 0.0131 | 450 | 0.2483 | - | | 0.0145 | 500 | 0.2418 | - | | 0.0160 | 550 | 0.2403 | - | | 0.0174 | 600 | 0.2386 | - | | 0.0189 | 650 | 0.2542 | - | | 0.0203 | 700 | 0.237 | - | | 0.0218 | 750 | 0.2423 | - | | 0.0232 | 800 | 0.2421 | - | | 0.0247 | 850 | 0.2409 | - | | 0.0261 | 900 | 0.2453 | - | | 0.0276 | 950 | 0.2404 | - | | 0.0290 | 1000 | 0.2418 | - | | 0.0305 | 1050 | 0.2454 | - | | 0.0319 | 1100 | 0.2446 | - | | 0.0001 | 1 | 0.2471 | - | | 0.0058 | 50 | 0.2375 | - | | 0.0116 | 100 | 0.2351 | - | | 0.0174 | 150 | 0.2406 | - | | 0.0232 | 200 | 0.2382 | - | | 0.0290 | 250 | 0.2374 | - | | 0.0000 | 1 | 0.2515 | - | | 0.0007 | 50 | 0.2335 | - | | 0.0015 | 100 | 0.229 | - | | 0.0022 | 150 | 0.2387 | - | | 0.0029 | 200 | 0.2209 | - | | 0.0036 | 250 | 0.2367 | - | | 0.0044 | 300 | 0.2521 | - | | 0.0051 | 350 | 0.239 | - | | 0.0058 | 400 | 0.2405 | - | | 0.0065 | 450 | 0.2541 | - | | 0.0073 | 500 | 0.2308 | - | | 0.0080 | 550 | 0.2381 | - | | 0.0087 | 600 | 0.2456 | - | | 0.0094 | 650 | 0.2301 | - | | 0.0102 | 700 | 0.2486 | - | | 0.0109 | 750 | 0.2243 | - | | 0.0116 | 800 | 0.2399 | - | | 0.0123 | 850 | 0.2341 | - | | 0.0131 | 900 | 0.2417 | - | | 0.0138 | 950 | 0.215 | - | | 0.0145 | 1000 | 0.2264 | - | | 0.0152 | 1050 | 0.2161 | - | | 0.0160 | 1100 | 0.2273 | - | | 0.0167 | 1150 | 0.2345 | - | | 0.0174 | 1200 | 0.2302 | - | | 0.0181 | 1250 | 0.2337 | - | | 0.0189 | 1300 | 0.2278 | - | | 0.0196 | 1350 | 0.2345 | - | | 0.0203 | 1400 | 0.2323 | - | | 0.0210 | 1450 | 0.2371 | - | | 0.0218 | 1500 | 0.2217 | - | | 0.0225 | 1550 | 0.2282 | - | | 0.0232 | 1600 | 0.224 | - | | 0.0239 | 1650 | 0.2346 | - | | 0.0247 | 1700 | 0.2087 | - | | 0.0254 | 1750 | 0.2299 | - | | 0.0261 | 1800 | 0.2154 | - | | 0.0268 | 1850 | 0.2108 | - | | 0.0276 | 1900 | 0.216 | - | | 0.0283 | 1950 | 0.2128 | - | | 0.0290 | 2000 | 0.2083 | - | | 0.0297 | 2050 | 0.2053 | - | | 0.0305 | 2100 | 0.2265 | - | | 0.0312 | 2150 | 0.2245 | - | | 0.0319 | 2200 | 0.2036 | - | | 0.0326 | 2250 | 0.2192 | - | | 0.0334 | 2300 | 0.2259 | - | | 0.0341 | 2350 | 0.2038 | - | | 0.0348 | 2400 | 0.2129 | - | | 0.0355 | 2450 | 0.2029 | - | | 0.0363 | 2500 | 0.1883 | - | | 0.0370 | 2550 | 0.187 | - | | 0.0377 | 2600 | 0.2083 | - | | 0.0384 | 2650 | 0.2138 | - | | 0.0392 | 2700 | 0.2057 | - | | 0.0399 | 2750 | 0.2134 | - | | 0.0406 | 2800 | 0.2008 | - | | 0.0413 | 2850 | 0.2018 | - | | 0.0421 | 2900 | 0.2226 | - | | 0.0428 | 2950 | 0.1815 | - | | 0.0435 | 3000 | 0.1943 | - | | 0.0442 | 3050 | 0.1926 | - | | 0.0450 | 3100 | 0.1877 | - | | 0.0457 | 3150 | 0.1764 | - | | 0.0464 | 3200 | 0.2021 | - | | 0.0471 | 3250 | 0.2071 | - | | 0.0479 | 3300 | 0.1832 | - | | 0.0486 | 3350 | 0.1714 | - | | 0.0493 | 3400 | 0.1914 | - | | 0.0500 | 3450 | 0.1749 | - | | 0.0508 | 3500 | 0.1752 | - | | 0.0515 | 3550 | 0.1829 | - | | 0.0522 | 3600 | 0.175 | - | | 0.0529 | 3650 | 0.1752 | - | | 0.0537 | 3700 | 0.1973 | - | | 0.0544 | 3750 | 0.1866 | - | | 0.0551 | 3800 | 0.156 | - | | 0.0558 | 3850 | 0.1923 | - | | 0.0566 | 3900 | 0.1683 | - | | 0.0573 | 3950 | 0.1642 | - | | 0.0580 | 4000 | 0.1705 | - | | 0.0587 | 4050 | 0.174 | - | | 0.0595 | 4100 | 0.1609 | - | | 0.0602 | 4150 | 0.17 | - | | 0.0609 | 4200 | 0.1843 | - | | 0.0616 | 4250 | 0.1855 | - | | 0.0624 | 4300 | 0.1385 | - | | 0.0631 | 4350 | 0.1765 | - | | 0.0638 | 4400 | 0.1873 | - | | 0.0645 | 4450 | 0.1654 | - | | 0.0653 | 4500 | 0.1912 | - | | 0.0660 | 4550 | 0.1533 | - | | 0.0667 | 4600 | 0.1759 | - | | 0.0674 | 4650 | 0.154 | - | | 0.0682 | 4700 | 0.147 | - | | 0.0689 | 4750 | 0.161 | - | | 0.0696 | 4800 | 0.1603 | - | | 0.0703 | 4850 | 0.1529 | - | | 0.0711 | 4900 | 0.1538 | - | | 0.0718 | 4950 | 0.1487 | - | | 0.0725 | 5000 | 0.1593 | - | | 0.0732 | 5050 | 0.1491 | - | | 0.0740 | 5100 | 0.1389 | - | | 0.0747 | 5150 | 0.1132 | - | | 0.0754 | 5200 | 0.1622 | - | | 0.0761 | 5250 | 0.1628 | - | | 0.0769 | 5300 | 0.1598 | - | | 0.0776 | 5350 | 0.1362 | - | | 0.0783 | 5400 | 0.1637 | - | | 0.0790 | 5450 | 0.1352 | - | | 0.0798 | 5500 | 0.1523 | - | | 0.0805 | 5550 | 0.1604 | - | | 0.0812 | 5600 | 0.1534 | - | | 0.0819 | 5650 | 0.1206 | - | | 0.0827 | 5700 | 0.1331 | - | | 0.0834 | 5750 | 0.1449 | - | | 0.0841 | 5800 | 0.1376 | - | | 0.0848 | 5850 | 0.1293 | - | | 0.0856 | 5900 | 0.1258 | - | | 0.0863 | 5950 | 0.1391 | - | | 0.0870 | 6000 | 0.1678 | - | | 0.0877 | 6050 | 0.1439 | - | | 0.0885 | 6100 | 0.1329 | - | | 0.0892 | 6150 | 0.1416 | - | | 0.0899 | 6200 | 0.126 | - | | 0.0906 | 6250 | 0.1072 | - | | 0.0914 | 6300 | 0.1314 | - | | 0.0921 | 6350 | 0.1282 | - | | 0.0928 | 6400 | 0.1418 | - | | 0.0935 | 6450 | 0.1418 | - | | 0.0943 | 6500 | 0.1126 | - | | 0.0950 | 6550 | 0.1118 | - | | 0.0957 | 6600 | 0.1437 | - | | 0.0964 | 6650 | 0.1265 | - | | 0.0972 | 6700 | 0.1203 | - | | 0.0979 | 6750 | 0.1267 | - | | 0.0986 | 6800 | 0.11 | - | | 0.0993 | 6850 | 0.1273 | - | | 0.1001 | 6900 | 0.1253 | - | | 0.1008 | 6950 | 0.1145 | - | | 0.1015 | 7000 | 0.1054 | - | | 0.1022 | 7050 | 0.1311 | - | | 0.1030 | 7100 | 0.1238 | - | | 0.1037 | 7150 | 0.0951 | - | | 0.1044 | 7200 | 0.1187 | - | | 0.1051 | 7250 | 0.1114 | - | | 0.1059 | 7300 | 0.1038 | - | | 0.1066 | 7350 | 0.1048 | - | | 0.1073 | 7400 | 0.0965 | - | | 0.1080 | 7450 | 0.1006 | - | | 0.1088 | 7500 | 0.1273 | - | | 0.1095 | 7550 | 0.12 | - | | 0.1102 | 7600 | 0.1055 | - | | 0.0001 | 1 | 0.1192 | - | | 0.0029 | 50 | 0.1128 | - | | 0.0057 | 100 | 0.0981 | - | | 0.0021 | 1 | 0.1188 | - | | 0.1040 | 50 | 0.1121 | - | | 0.0021 | 1 | 0.1172 | - | | 0.1040 | 50 | 0.1109 | - | | 0.2079 | 100 | 0.0965 | - | | 0.3119 | 150 | 0.1013 | - | | 0.4158 | 200 | 0.1157 | - | | 0.5198 | 250 | 0.1093 | - | | 0.6237 | 300 | 0.1029 | - | | 0.7277 | 350 | 0.0904 | - | | 0.8316 | 400 | 0.1084 | - | | 0.9356 | 450 | 0.1127 | - | | **1.0** | **481** | **-** | **0.1883** | | 1.0395 | 500 | 0.0853 | - | | 1.1435 | 550 | 0.0907 | - | | 1.2474 | 600 | 0.0814 | - | | 1.3514 | 650 | 0.0967 | - | | 1.4553 | 700 | 0.118 | - | | 1.5593 | 750 | 0.0841 | - | | 1.6632 | 800 | 0.0992 | - | | 1.7672 | 850 | 0.0965 | - | | 1.8711 | 900 | 0.092 | - | | 1.9751 | 950 | 0.109 | - | | 2.0 | 962 | - | 0.193 | | 2.0790 | 1000 | 0.0847 | - | | 2.1830 | 1050 | 0.0864 | - | | 2.2869 | 1100 | 0.0843 | - | | 2.3909 | 1150 | 0.0792 | - | | 2.4948 | 1200 | 0.0808 | - | | 2.5988 | 1250 | 0.0913 | - | | 2.7027 | 1300 | 0.0848 | - | | 2.8067 | 1350 | 0.0889 | - | | 2.9106 | 1400 | 0.0673 | - | | 3.0 | 1443 | - | 0.1983 | | 3.0146 | 1450 | 0.0671 | - | | 3.1185 | 1500 | 0.0643 | - | | 3.2225 | 1550 | 0.0649 | - | | 3.3264 | 1600 | 0.0827 | - | | 3.4304 | 1650 | 0.0752 | - | | 3.5343 | 1700 | 0.0785 | - | | 3.6383 | 1750 | 0.0629 | - | | 3.7422 | 1800 | 0.0726 | - | | 3.8462 | 1850 | 0.0672 | - | | 3.9501 | 1900 | 0.0704 | - | | 4.0 | 1924 | - | 0.2015 | | 4.0541 | 1950 | 0.0812 | - | | 4.1580 | 2000 | 0.0709 | - | | 4.2620 | 2050 | 0.0866 | - | | 4.3659 | 2100 | 0.0747 | - | | 4.4699 | 2150 | 0.0554 | - | | 4.5738 | 2200 | 0.0636 | - | | 4.6778 | 2250 | 0.0655 | - | | 4.7817 | 2300 | 0.0562 | - | | 4.8857 | 2350 | 0.0531 | - | | 4.9896 | 2400 | 0.0518 | - | | 5.0 | 2405 | - | 0.2056 | | 5.0936 | 2450 | 0.0808 | - | | 5.1975 | 2500 | 0.0571 | - | | 5.3015 | 2550 | 0.066 | - | | 5.4054 | 2600 | 0.071 | - | | 5.5094 | 2650 | 0.0507 | - | | 5.6133 | 2700 | 0.0603 | - | | 5.7173 | 2750 | 0.0548 | - | | 5.8212 | 2800 | 0.0714 | - | | 5.9252 | 2850 | 0.0532 | - | | 6.0 | 2886 | - | 0.208 | | 6.0291 | 2900 | 0.0581 | - | | 6.1331 | 2950 | 0.0663 | - | | 6.2370 | 3000 | 0.0717 | - | | 6.3410 | 3050 | 0.0549 | - | | 6.4449 | 3100 | 0.0611 | - | | 6.5489 | 3150 | 0.0515 | - | | 6.6528 | 3200 | 0.0546 | - | | 6.7568 | 3250 | 0.0406 | - | | 6.8607 | 3300 | 0.0582 | - | | 6.9647 | 3350 | 0.0565 | - | | 7.0 | 3367 | - | 0.2176 | | 7.0686 | 3400 | 0.0737 | - | | 7.1726 | 3450 | 0.0554 | - | | 7.2765 | 3500 | 0.0462 | - | | 7.3805 | 3550 | 0.051 | - | | 7.4844 | 3600 | 0.0441 | - | | 7.5884 | 3650 | 0.0503 | - | | 7.6923 | 3700 | 0.0531 | - | | 7.7963 | 3750 | 0.0464 | - | | 7.9002 | 3800 | 0.0443 | - | | 8.0 | 3848 | - | 0.2234 | | 8.0042 | 3850 | 0.0376 | - | | 8.1081 | 3900 | 0.0542 | - | | 8.2121 | 3950 | 0.0453 | - | | 8.3160 | 4000 | 0.0448 | - | | 8.4200 | 4050 | 0.0535 | - | | 8.5239 | 4100 | 0.0645 | - | | 8.6279 | 4150 | 0.0451 | - | | 8.7318 | 4200 | 0.0472 | - | | 8.8358 | 4250 | 0.0477 | - | | 8.9397 | 4300 | 0.0327 | - | | 9.0 | 4329 | - | 0.2272 | | 9.0437 | 4350 | 0.0346 | - | | 9.1476 | 4400 | 0.0435 | - | | 9.2516 | 4450 | 0.0479 | - | | 9.3555 | 4500 | 0.0508 | - | | 9.4595 | 4550 | 0.0535 | - | | 9.5634 | 4600 | 0.0631 | - | | 9.6674 | 4650 | 0.0286 | - | | 9.7713 | 4700 | 0.0564 | - | | 9.8753 | 4750 | 0.0349 | - | | 9.9792 | 4800 | 0.0487 | - | | 10.0 | 4810 | - | 0.2288 | | 10.0832 | 4850 | 0.0317 | - | | 10.1871 | 4900 | 0.0546 | - | | 10.2911 | 4950 | 0.0353 | - | | 10.3950 | 5000 | 0.0437 | - | | 10.4990 | 5050 | 0.056 | - | | 10.6029 | 5100 | 0.0353 | - | | 10.7069 | 5150 | 0.0304 | - | | 10.8108 | 5200 | 0.0358 | - | | 10.9148 | 5250 | 0.0481 | - | | 11.0 | 5291 | - | 0.2282 | | 11.0187 | 5300 | 0.0318 | - | | 11.1227 | 5350 | 0.0373 | - | | 11.2266 | 5400 | 0.0305 | - | | 11.3306 | 5450 | 0.0443 | - | | 11.4345 | 5500 | 0.0383 | - | | 11.5385 | 5550 | 0.0425 | - | | 11.6424 | 5600 | 0.039 | - | | 11.7464 | 5650 | 0.0443 | - | | 11.8503 | 5700 | 0.0503 | - | | 11.9543 | 5750 | 0.0553 | - | | 12.0 | 5772 | - | 0.2342 | | 12.0582 | 5800 | 0.0362 | - | | 12.1622 | 5850 | 0.0509 | - | | 12.2661 | 5900 | 0.0337 | - | | 12.3701 | 5950 | 0.0436 | - | | 12.4740 | 6000 | 0.0462 | - | | 12.5780 | 6050 | 0.034 | - | | 12.6819 | 6100 | 0.0334 | - | | 12.7859 | 6150 | 0.0365 | - | | 12.8898 | 6200 | 0.047 | - | | 12.9938 | 6250 | 0.0489 | - | | 13.0 | 6253 | - | 0.2317 | | 13.0977 | 6300 | 0.035 | - | | 13.2017 | 6350 | 0.0412 | - | | 13.3056 | 6400 | 0.0358 | - | | 13.4096 | 6450 | 0.0366 | - | | 13.5135 | 6500 | 0.0473 | - | | 13.6175 | 6550 | 0.0481 | - | | 13.7214 | 6600 | 0.0443 | - | | 13.8254 | 6650 | 0.0454 | - | | 13.9293 | 6700 | 0.0344 | - | | 14.0 | 6734 | - | 0.2304 | | 14.0333 | 6750 | 0.0327 | - | | 14.1372 | 6800 | 0.0386 | - | | 14.2412 | 6850 | 0.0503 | - | | 14.3451 | 6900 | 0.0236 | - | | 14.4491 | 6950 | 0.042 | - | | 14.5530 | 7000 | 0.0405 | - | | 14.6570 | 7050 | 0.0339 | - | | 14.7609 | 7100 | 0.0435 | - | | 14.8649 | 7150 | 0.0314 | - | | 14.9688 | 7200 | 0.0263 | - | | 15.0 | 7215 | - | 0.234 | | 15.0728 | 7250 | 0.0369 | - | | 15.1767 | 7300 | 0.0329 | - | | 15.2807 | 7350 | 0.0366 | - | | 15.3846 | 7400 | 0.0401 | - | | 15.4886 | 7450 | 0.0321 | - | | 15.5925 | 7500 | 0.0571 | - | | 15.6965 | 7550 | 0.0353 | - | | 15.8004 | 7600 | 0.0381 | - | | 15.9044 | 7650 | 0.0347 | - | | 16.0 | 7696 | - | 0.2334 | | 16.0083 | 7700 | 0.0341 | - | | 16.1123 | 7750 | 0.0276 | - | | 16.2162 | 7800 | 0.0555 | - | | 16.3202 | 7850 | 0.0338 | - | | 16.4241 | 7900 | 0.0227 | - | | 16.5281 | 7950 | 0.0256 | - | | 16.6320 | 8000 | 0.0356 | - | | 16.7360 | 8050 | 0.0413 | - | | 16.8399 | 8100 | 0.032 | - | | 16.9439 | 8150 | 0.0329 | - | | 17.0 | 8177 | - | 0.2356 | | 17.0478 | 8200 | 0.0382 | - | | 17.1518 | 8250 | 0.0434 | - | | 17.2557 | 8300 | 0.0411 | - | | 17.3597 | 8350 | 0.0329 | - | | 17.4636 | 8400 | 0.0388 | - | | 17.5676 | 8450 | 0.0384 | - | | 17.6715 | 8500 | 0.0306 | - | | 17.7755 | 8550 | 0.0185 | - | | 17.8794 | 8600 | 0.0357 | - | | 17.9834 | 8650 | 0.0349 | - | | 18.0 | 8658 | - | 0.2368 | | 18.0873 | 8700 | 0.0515 | - | | 18.1913 | 8750 | 0.0326 | - | | 18.2952 | 8800 | 0.0367 | - | | 18.3992 | 8850 | 0.0241 | - | | 18.5031 | 8900 | 0.0313 | - | | 18.6071 | 8950 | 0.0275 | - | | 18.7110 | 9000 | 0.0378 | - | | 18.8150 | 9050 | 0.0401 | - | | 18.9189 | 9100 | 0.0285 | - | | 19.0 | 9139 | - | 0.2347 | | 19.0229 | 9150 | 0.0309 | - | | 19.1268 | 9200 | 0.035 | - | | 19.2308 | 9250 | 0.0415 | - | | 19.3347 | 9300 | 0.0301 | - | | 19.4387 | 9350 | 0.0293 | - | | 19.5426 | 9400 | 0.0323 | - | | 19.6466 | 9450 | 0.0342 | - | | 19.7505 | 9500 | 0.0205 | - | | 19.8545 | 9550 | 0.0331 | - | | 19.9584 | 9600 | 0.0226 | - | | 20.0 | 9620 | - | 0.237 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 2.7.0 - Transformers: 4.40.1 - PyTorch: 2.2.1+cu121 - Datasets: 2.19.0 - 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} } ```