--- base_model: klue/roberta-base library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: '[단품] 뮤트 치크팔레트 (로즈가든/모브가든) 03. 로즈가든 디퍼런트밀리언즈(주)' - text: 나투리아 케라틴 워터팩 250g 옵션없음 나투리아 공식몰 - text: 순수자아 원스텝 워터 클렌징 패드 100매 옵션없음 바라글로벌 - text: Hair Identifier Spray for Face Shaving 2024 Skin Dermaplaning Moisturizing and Care Dermaplaner 2 PC 옵션없음 젠틀스토어 - text: 블랑네이처 5배 매직 티트리 오일 대용량 20ML 옵션없음 에스지헬스케어 inference: true model-index: - name: SetFit with klue/roberta-base results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.6668180270178227 name: Accuracy --- # SetFit with klue/roberta-base This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [klue/roberta-base](https://huggingface.co/klue/roberta-base) 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:** [klue/roberta-base](https://huggingface.co/klue/roberta-base) - **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:** 120 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 | |:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 19 | | | 104 | | | 77 | | | 8 | | | 30 | | | 99 | | | 61 | | | 36 | | | 37 | | | 91 | | | 108 | | | 60 | | | 66 | | | 26 | | | 27 | | | 53 | | | 3 | | | 48 | | | 39 | | | 4 | | | 62 | | | 67 | | | 71 | | | 94 | | | 79 | | | 72 | | | 5 | | | 100 | | | 51 | | | 38 | | | 70 | | | 1 | | | 117 | | | 55 | | | 98 | | | 118 | | | 12 | | | 97 | | | 90 | | | 83 | | | 35 | | | 113 | | | 80 | | | 88 | | | 84 | | | 65 | | | 59 | | | 52 | | | 107 | | | 28 | | | 43 | | | 63 | | | 34 | | | 21 | | | 54 | | | 101 | | | 115 | | | 44 | | | 42 | | | 73 | | | 68 | | | 9 | | | 25 | | | 116 | | | 112 | | | 120 | | | 6 | | | 23 | | | 15 | | | 96 | | | 95 | | | 92 | | | 103 | | | 85 | | | 20 | | | 47 | | | 33 | | | 106 | | | 78 | | | 86 | | | 24 | | | 111 | | | 10 | | | 57 | | | 105 | | | 13 | | | 18 | | | 64 | | | 76 | | | 89 | | | 14 | | | 87 | | | 0 | | | 75 | | | 2 | | | 45 | | | 50 | | | 114 | | | 41 | | | 58 | | | 109 | | | 32 | | | 40 | | | 110 | | | 69 | | | 119 | | | 93 | | | 22 | | | 102 | | | 49 | | | 81 | | | 16 | | | 56 | | | 82 | | | 31 | | | 7 | | | 29 | | | 46 | | | 74 | | | 17 | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.6668 | ## 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("mini1013/master_item_bt_test_flat") # Run inference preds = model("나투리아 케라틴 워터팩 250g 옵션없음 나투리아 공식몰") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:-------|:----| | Word count | 3 | 9.3949 | 26 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 12 | | 1 | 22 | | 2 | 19 | | 3 | 17 | | 4 | 25 | | 5 | 20 | | 6 | 17 | | 7 | 10 | | 8 | 22 | | 9 | 11 | | 10 | 18 | | 12 | 19 | | 13 | 18 | | 14 | 21 | | 15 | 16 | | 16 | 16 | | 17 | 10 | | 18 | 19 | | 19 | 32 | | 20 | 20 | | 21 | 16 | | 22 | 18 | | 23 | 20 | | 24 | 21 | | 25 | 10 | | 26 | 19 | | 27 | 42 | | 28 | 15 | | 29 | 18 | | 30 | 23 | | 31 | 12 | | 32 | 22 | | 33 | 21 | | 34 | 21 | | 35 | 20 | | 36 | 23 | | 37 | 20 | | 38 | 15 | | 39 | 20 | | 40 | 22 | | 41 | 20 | | 42 | 11 | | 43 | 21 | | 44 | 15 | | 45 | 20 | | 46 | 23 | | 47 | 19 | | 48 | 21 | | 49 | 19 | | 50 | 21 | | 51 | 10 | | 52 | 28 | | 53 | 27 | | 54 | 13 | | 55 | 12 | | 56 | 12 | | 57 | 12 | | 58 | 20 | | 59 | 19 | | 60 | 15 | | 61 | 19 | | 62 | 19 | | 63 | 21 | | 64 | 31 | | 65 | 20 | | 66 | 21 | | 67 | 15 | | 68 | 22 | | 69 | 24 | | 70 | 18 | | 71 | 19 | | 72 | 16 | | 73 | 22 | | 74 | 10 | | 75 | 20 | | 76 | 15 | | 77 | 23 | | 78 | 17 | | 79 | 20 | | 80 | 28 | | 81 | 14 | | 82 | 17 | | 83 | 32 | | 84 | 23 | | 85 | 22 | | 86 | 18 | | 87 | 23 | | 88 | 18 | | 89 | 30 | | 90 | 20 | | 91 | 40 | | 92 | 22 | | 93 | 15 | | 94 | 27 | | 95 | 17 | | 96 | 20 | | 97 | 20 | | 98 | 25 | | 99 | 20 | | 100 | 20 | | 101 | 20 | | 102 | 18 | | 103 | 27 | | 104 | 20 | | 105 | 23 | | 106 | 20 | | 107 | 19 | | 108 | 14 | | 109 | 25 | | 110 | 25 | | 111 | 15 | | 112 | 19 | | 113 | 20 | | 114 | 12 | | 115 | 28 | | 116 | 23 | | 117 | 18 | | 118 | 14 | | 119 | 18 | | 120 | 19 | ### Training Hyperparameters - batch_size: (512, 512) - num_epochs: (70, 70) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 120 - 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 - l2_weight: 0.01 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:-----:|:-------------:|:---------------:| | 0.0018 | 1 | 0.3884 | - | | 0.0903 | 50 | 0.3779 | - | | 0.1805 | 100 | 0.3533 | - | | 0.2708 | 150 | 0.3071 | - | | 0.3610 | 200 | 0.2718 | - | | 0.4513 | 250 | 0.2412 | - | | 0.5415 | 300 | 0.2182 | - | | 0.6318 | 350 | 0.1985 | - | | 0.7220 | 400 | 0.1813 | - | | 0.8123 | 450 | 0.164 | - | | 0.9025 | 500 | 0.1489 | - | | 0.9928 | 550 | 0.1352 | - | | 1.0830 | 600 | 0.12 | - | | 1.1733 | 650 | 0.1097 | - | | 1.2635 | 700 | 0.0982 | - | | 1.3538 | 750 | 0.0874 | - | | 1.4440 | 800 | 0.0783 | - | | 1.5343 | 850 | 0.0704 | - | | 1.6245 | 900 | 0.0652 | - | | 1.7148 | 950 | 0.0599 | - | | 1.8051 | 1000 | 0.0562 | - | | 1.8953 | 1050 | 0.0524 | - | | 1.9856 | 1100 | 0.0507 | - | | 2.0758 | 1150 | 0.0455 | - | | 2.1661 | 1200 | 0.0434 | - | | 2.2563 | 1250 | 0.0424 | - | | 2.3466 | 1300 | 0.0403 | - | | 2.4368 | 1350 | 0.038 | - | | 2.5271 | 1400 | 0.0365 | - | | 2.6173 | 1450 | 0.0357 | - | | 2.7076 | 1500 | 0.0338 | - | | 2.7978 | 1550 | 0.0328 | - | | 2.8881 | 1600 | 0.0311 | - | | 2.9783 | 1650 | 0.0304 | - | | 3.0686 | 1700 | 0.028 | - | | 3.1588 | 1750 | 0.0267 | - | | 3.2491 | 1800 | 0.0254 | - | | 3.3394 | 1850 | 0.0253 | - | | 3.4296 | 1900 | 0.024 | - | | 3.5199 | 1950 | 0.0217 | - | | 3.6101 | 2000 | 0.0214 | - | | 3.7004 | 2050 | 0.0207 | - | | 3.7906 | 2100 | 0.0197 | - | | 3.8809 | 2150 | 0.0187 | - | | 3.9711 | 2200 | 0.0179 | - | | 4.0614 | 2250 | 0.0177 | - | | 4.1516 | 2300 | 0.0163 | - | | 4.2419 | 2350 | 0.0157 | - | | 4.3321 | 2400 | 0.0155 | - | | 4.4224 | 2450 | 0.0155 | - | | 4.5126 | 2500 | 0.0139 | - | | 4.6029 | 2550 | 0.0133 | - | | 4.6931 | 2600 | 0.0126 | - | | 4.7834 | 2650 | 0.0127 | - | | 4.8736 | 2700 | 0.012 | - | | 4.9639 | 2750 | 0.0122 | - | | 5.0542 | 2800 | 0.0115 | - | | 5.1444 | 2850 | 0.0109 | - | | 5.2347 | 2900 | 0.0101 | - | | 5.3249 | 2950 | 0.0102 | - | | 5.4152 | 3000 | 0.0093 | - | | 5.5054 | 3050 | 0.0098 | - | | 5.5957 | 3100 | 0.0095 | - | | 5.6859 | 3150 | 0.0089 | - | | 5.7762 | 3200 | 0.0083 | - | | 5.8664 | 3250 | 0.0087 | - | | 5.9567 | 3300 | 0.0083 | - | | 6.0469 | 3350 | 0.0083 | - | | 6.1372 | 3400 | 0.008 | - | | 6.2274 | 3450 | 0.0073 | - | | 6.3177 | 3500 | 0.0075 | - | | 6.4079 | 3550 | 0.0073 | - | | 6.4982 | 3600 | 0.0066 | - | | 6.5884 | 3650 | 0.0062 | - | | 6.6787 | 3700 | 0.0061 | - | | 6.7690 | 3750 | 0.0066 | - | | 6.8592 | 3800 | 0.0062 | - | | 6.9495 | 3850 | 0.0056 | - | | 7.0397 | 3900 | 0.006 | - | | 7.1300 | 3950 | 0.0057 | - | | 7.2202 | 4000 | 0.0054 | - | | 7.3105 | 4050 | 0.0051 | - | | 7.4007 | 4100 | 0.0055 | - | | 7.4910 | 4150 | 0.0047 | - | | 7.5812 | 4200 | 0.0048 | - | | 7.6715 | 4250 | 0.0048 | - | | 7.7617 | 4300 | 0.0049 | - | | 7.8520 | 4350 | 0.0046 | - | | 7.9422 | 4400 | 0.0045 | - | | 8.0325 | 4450 | 0.0046 | - | | 8.1227 | 4500 | 0.0045 | - | | 8.2130 | 4550 | 0.0044 | - | | 8.3032 | 4600 | 0.0048 | - | | 8.3935 | 4650 | 0.0044 | - | | 8.4838 | 4700 | 0.004 | - | | 8.5740 | 4750 | 0.0042 | - | | 8.6643 | 4800 | 0.0043 | - | | 8.7545 | 4850 | 0.0039 | - | | 8.8448 | 4900 | 0.0036 | - | | 8.9350 | 4950 | 0.0037 | - | | 9.0253 | 5000 | 0.0032 | - | | 9.1155 | 5050 | 0.0032 | - | | 9.2058 | 5100 | 0.0035 | - | | 9.2960 | 5150 | 0.0031 | - | | 9.3863 | 5200 | 0.0035 | - | | 9.4765 | 5250 | 0.0033 | - | | 9.5668 | 5300 | 0.0032 | - | | 9.6570 | 5350 | 0.0031 | - | | 9.7473 | 5400 | 0.0032 | - | | 9.8375 | 5450 | 0.0029 | - | | 9.9278 | 5500 | 0.0028 | - | | 10.0181 | 5550 | 0.0029 | - | | 10.1083 | 5600 | 0.0029 | - | | 10.1986 | 5650 | 0.0024 | - | | 10.2888 | 5700 | 0.0027 | - | | 10.3791 | 5750 | 0.0026 | - | | 10.4693 | 5800 | 0.0028 | - | | 10.5596 | 5850 | 0.0026 | - | | 10.6498 | 5900 | 0.0021 | - | | 10.7401 | 5950 | 0.0022 | - | | 10.8303 | 6000 | 0.0024 | - | | 10.9206 | 6050 | 0.0022 | - | | 11.0108 | 6100 | 0.0021 | - | | 11.1011 | 6150 | 0.0022 | - | | 11.1913 | 6200 | 0.0018 | - | | 11.2816 | 6250 | 0.0017 | - | | 11.3718 | 6300 | 0.0016 | - | | 11.4621 | 6350 | 0.0015 | - | | 11.5523 | 6400 | 0.0016 | - | | 11.6426 | 6450 | 0.0013 | - | | 11.7329 | 6500 | 0.0013 | - | | 11.8231 | 6550 | 0.0014 | - | | 11.9134 | 6600 | 0.0012 | - | | 12.0036 | 6650 | 0.0014 | - | | 12.0939 | 6700 | 0.0012 | - | | 12.1841 | 6750 | 0.0011 | - | | 12.2744 | 6800 | 0.0009 | - | | 12.3646 | 6850 | 0.001 | - | | 12.4549 | 6900 | 0.0012 | - | | 12.5451 | 6950 | 0.001 | - | | 12.6354 | 7000 | 0.001 | - | | 12.7256 | 7050 | 0.001 | - | | 12.8159 | 7100 | 0.001 | - | | 12.9061 | 7150 | 0.001 | - | | 12.9964 | 7200 | 0.0009 | - | | 13.0866 | 7250 | 0.0011 | - | | 13.1769 | 7300 | 0.0009 | - | | 13.2671 | 7350 | 0.0009 | - | | 13.3574 | 7400 | 0.0009 | - | | 13.4477 | 7450 | 0.0009 | - | | 13.5379 | 7500 | 0.0008 | - | | 13.6282 | 7550 | 0.0006 | - | | 13.7184 | 7600 | 0.0005 | - | | 13.8087 | 7650 | 0.0006 | - | | 13.8989 | 7700 | 0.0005 | - | | 13.9892 | 7750 | 0.0005 | - | | 14.0794 | 7800 | 0.0005 | - | | 14.1697 | 7850 | 0.0005 | - | | 14.2599 | 7900 | 0.0004 | - | | 14.3502 | 7950 | 0.0004 | - | | 14.4404 | 8000 | 0.0004 | - | | 14.5307 | 8050 | 0.0003 | - | | 14.6209 | 8100 | 0.0004 | - | | 14.7112 | 8150 | 0.0005 | - | | 14.8014 | 8200 | 0.0004 | - | | 14.8917 | 8250 | 0.0004 | - | | 14.9819 | 8300 | 0.0003 | - | | 15.0722 | 8350 | 0.0004 | - | | 15.1625 | 8400 | 0.0003 | - | | 15.2527 | 8450 | 0.0004 | - | | 15.3430 | 8500 | 0.0004 | - | | 15.4332 | 8550 | 0.0003 | - | | 15.5235 | 8600 | 0.0002 | - | | 15.6137 | 8650 | 0.0003 | - | | 15.7040 | 8700 | 0.0003 | - | | 15.7942 | 8750 | 0.0003 | - | | 15.8845 | 8800 | 0.0003 | - | | 15.9747 | 8850 | 0.0003 | - | | 16.0650 | 8900 | 0.0003 | - | | 16.1552 | 8950 | 0.0002 | - | | 16.2455 | 9000 | 0.0004 | - | | 16.3357 | 9050 | 0.0002 | - | | 16.4260 | 9100 | 0.0002 | - | | 16.5162 | 9150 | 0.0003 | - | | 16.6065 | 9200 | 0.0005 | - | | 16.6968 | 9250 | 0.0015 | - | | 16.7870 | 9300 | 0.0006 | - | | 16.8773 | 9350 | 0.0004 | - | | 16.9675 | 9400 | 0.0004 | - | | 17.0578 | 9450 | 0.0004 | - | | 17.1480 | 9500 | 0.0003 | - | | 17.2383 | 9550 | 0.0003 | - | | 17.3285 | 9600 | 0.0003 | - | | 17.4188 | 9650 | 0.0002 | - | | 17.5090 | 9700 | 0.0003 | - | | 17.5993 | 9750 | 0.0002 | - | | 17.6895 | 9800 | 0.0002 | - | | 17.7798 | 9850 | 0.0002 | - | | 17.8700 | 9900 | 0.0002 | - | | 17.9603 | 9950 | 0.0002 | - | | 18.0505 | 10000 | 0.0002 | - | | 18.1408 | 10050 | 0.0001 | - | | 18.2310 | 10100 | 0.0002 | - | | 18.3213 | 10150 | 0.0001 | - | | 18.4116 | 10200 | 0.0001 | - | | 18.5018 | 10250 | 0.0001 | - | | 18.5921 | 10300 | 0.0001 | - | | 18.6823 | 10350 | 0.0001 | - | | 18.7726 | 10400 | 0.0001 | - | | 18.8628 | 10450 | 0.0002 | - | | 18.9531 | 10500 | 0.0001 | - | | 19.0433 | 10550 | 0.0001 | - | | 19.1336 | 10600 | 0.0001 | - | | 19.2238 | 10650 | 0.0001 | - | | 19.3141 | 10700 | 0.0001 | - | | 19.4043 | 10750 | 0.0001 | - | | 19.4946 | 10800 | 0.0001 | - | | 19.5848 | 10850 | 0.0001 | - | | 19.6751 | 10900 | 0.0001 | - | | 19.7653 | 10950 | 0.0001 | - | | 19.8556 | 11000 | 0.0001 | - | | 19.9458 | 11050 | 0.0001 | - | | 20.0361 | 11100 | 0.0001 | - | | 20.1264 | 11150 | 0.0001 | - | | 20.2166 | 11200 | 0.0001 | - | | 20.3069 | 11250 | 0.0001 | - | | 20.3971 | 11300 | 0.0001 | - | | 20.4874 | 11350 | 0.0001 | - | | 20.5776 | 11400 | 0.0001 | - | | 20.6679 | 11450 | 0.0001 | - | | 20.7581 | 11500 | 0.0001 | - | | 20.8484 | 11550 | 0.0001 | - | | 20.9386 | 11600 | 0.0001 | - | | 21.0289 | 11650 | 0.0001 | - | | 21.1191 | 11700 | 0.0001 | - | | 21.2094 | 11750 | 0.0 | - | | 21.2996 | 11800 | 0.0 | - | | 21.3899 | 11850 | 0.0 | - | | 21.4801 | 11900 | 0.0 | - | | 21.5704 | 11950 | 0.0 | - | | 21.6606 | 12000 | 0.0 | - | | 21.7509 | 12050 | 0.0 | - | | 21.8412 | 12100 | 0.0 | - | | 21.9314 | 12150 | 0.0 | - | | 22.0217 | 12200 | 0.0 | - | | 22.1119 | 12250 | 0.0 | - | | 22.2022 | 12300 | 0.0 | - | | 22.2924 | 12350 | 0.0 | - | | 22.3827 | 12400 | 0.0 | - | | 22.4729 | 12450 | 0.0 | - | | 22.5632 | 12500 | 0.0 | - | | 22.6534 | 12550 | 0.0 | - | | 22.7437 | 12600 | 0.0 | - | | 22.8339 | 12650 | 0.0 | - | | 22.9242 | 12700 | 0.0 | - | | 23.0144 | 12750 | 0.0 | - | | 23.1047 | 12800 | 0.0011 | - | | 23.1949 | 12850 | 0.0012 | - | | 23.2852 | 12900 | 0.0004 | - | | 23.3755 | 12950 | 0.0004 | - | | 23.4657 | 13000 | 0.0002 | - | | 23.5560 | 13050 | 0.0002 | - | | 23.6462 | 13100 | 0.0003 | - | | 23.7365 | 13150 | 0.0002 | - | | 23.8267 | 13200 | 0.0001 | - | | 23.9170 | 13250 | 0.0002 | - | | 24.0072 | 13300 | 0.0001 | - | | 24.0975 | 13350 | 0.0001 | - | | 24.1877 | 13400 | 0.0001 | - | | 24.2780 | 13450 | 0.0001 | - | | 24.3682 | 13500 | 0.0001 | - | | 24.4585 | 13550 | 0.0001 | - | | 24.5487 | 13600 | 0.0001 | - | | 24.6390 | 13650 | 0.0001 | - | | 24.7292 | 13700 | 0.0001 | - | | 24.8195 | 13750 | 0.0002 | - | | 24.9097 | 13800 | 0.0001 | - | | 25.0 | 13850 | 0.0001 | - | | 25.0903 | 13900 | 0.0001 | - | | 25.1805 | 13950 | 0.0001 | - | | 25.2708 | 14000 | 0.0001 | - | | 25.3610 | 14050 | 0.0001 | - | | 25.4513 | 14100 | 0.0001 | - | | 25.5415 | 14150 | 0.0001 | - | | 25.6318 | 14200 | 0.0001 | - | | 25.7220 | 14250 | 0.0001 | - | | 25.8123 | 14300 | 0.0001 | - | | 25.9025 | 14350 | 0.0 | - | | 25.9928 | 14400 | 0.0 | - | | 26.0830 | 14450 | 0.0 | - | | 26.1733 | 14500 | 0.0 | - | | 26.2635 | 14550 | 0.0 | - | | 26.3538 | 14600 | 0.0 | - | | 26.4440 | 14650 | 0.0 | - | | 26.5343 | 14700 | 0.0 | - | | 26.6245 | 14750 | 0.0 | - | | 26.7148 | 14800 | 0.0 | - | | 26.8051 | 14850 | 0.0 | - | | 26.8953 | 14900 | 0.0 | - | | 26.9856 | 14950 | 0.0 | - | | 27.0758 | 15000 | 0.0 | - | | 27.1661 | 15050 | 0.0 | - | | 27.2563 | 15100 | 0.0 | - | | 27.3466 | 15150 | 0.0001 | - | | 27.4368 | 15200 | 0.0004 | - | | 27.5271 | 15250 | 0.0006 | - | | 27.6173 | 15300 | 0.0002 | - | | 27.7076 | 15350 | 0.0001 | - | | 27.7978 | 15400 | 0.0002 | - | | 27.8881 | 15450 | 0.0002 | - | | 27.9783 | 15500 | 0.0001 | - | | 28.0686 | 15550 | 0.0001 | - | | 28.1588 | 15600 | 0.0001 | - | | 28.2491 | 15650 | 0.0 | - | | 28.3394 | 15700 | 0.0 | - | | 28.4296 | 15750 | 0.0 | - | | 28.5199 | 15800 | 0.0 | - | | 28.6101 | 15850 | 0.0 | - | | 28.7004 | 15900 | 0.0 | - | | 28.7906 | 15950 | 0.0 | - | | 28.8809 | 16000 | 0.0 | - | | 28.9711 | 16050 | 0.0 | - | | 29.0614 | 16100 | 0.0 | - | | 29.1516 | 16150 | 0.0 | - | | 29.2419 | 16200 | 0.0 | - | | 29.3321 | 16250 | 0.0 | - | | 29.4224 | 16300 | 0.0 | - | | 29.5126 | 16350 | 0.0 | - | | 29.6029 | 16400 | 0.0 | - | | 29.6931 | 16450 | 0.0 | - | | 29.7834 | 16500 | 0.0 | - | | 29.8736 | 16550 | 0.0 | - | | 29.9639 | 16600 | 0.0 | - | | 30.0542 | 16650 | 0.0 | - | | 30.1444 | 16700 | 0.0 | - | | 30.2347 | 16750 | 0.0 | - | | 30.3249 | 16800 | 0.0 | - | | 30.4152 | 16850 | 0.0 | - | | 30.5054 | 16900 | 0.0 | - | | 30.5957 | 16950 | 0.0 | - | | 30.6859 | 17000 | 0.0 | - | | 30.7762 | 17050 | 0.0 | - | | 30.8664 | 17100 | 0.0 | - | | 30.9567 | 17150 | 0.0 | - | | 31.0469 | 17200 | 0.0 | - | | 31.1372 | 17250 | 0.0 | - | | 31.2274 | 17300 | 0.0 | - | | 31.3177 | 17350 | 0.0 | - | | 31.4079 | 17400 | 0.0 | - | | 31.4982 | 17450 | 0.0 | - | | 31.5884 | 17500 | 0.0 | - | | 31.6787 | 17550 | 0.0 | - | | 31.7690 | 17600 | 0.0 | - | | 31.8592 | 17650 | 0.0 | - | | 31.9495 | 17700 | 0.0 | - | | 32.0397 | 17750 | 0.0 | - | | 32.1300 | 17800 | 0.0 | - | | 32.2202 | 17850 | 0.0 | - | | 32.3105 | 17900 | 0.0 | - | | 32.4007 | 17950 | 0.0 | - | | 32.4910 | 18000 | 0.0 | - | | 32.5812 | 18050 | 0.0 | - | | 32.6715 | 18100 | 0.0 | - | | 32.7617 | 18150 | 0.0 | - | | 32.8520 | 18200 | 0.0 | - | | 32.9422 | 18250 | 0.0 | - | | 33.0325 | 18300 | 0.0 | - | | 33.1227 | 18350 | 0.0 | - | | 33.2130 | 18400 | 0.0 | - | | 33.3032 | 18450 | 0.0 | - | | 33.3935 | 18500 | 0.0 | - | | 33.4838 | 18550 | 0.0 | - | | 33.5740 | 18600 | 0.0 | - | | 33.6643 | 18650 | 0.0 | - | | 33.7545 | 18700 | 0.0 | - | | 33.8448 | 18750 | 0.0 | - | | 33.9350 | 18800 | 0.0 | - | | 34.0253 | 18850 | 0.0 | - | | 34.1155 | 18900 | 0.0 | - | | 34.2058 | 18950 | 0.0 | - | | 34.2960 | 19000 | 0.0 | - | | 34.3863 | 19050 | 0.0 | - | | 34.4765 | 19100 | 0.0 | - | | 34.5668 | 19150 | 0.0 | - | | 34.6570 | 19200 | 0.0 | - | | 34.7473 | 19250 | 0.0 | - | | 34.8375 | 19300 | 0.0 | - | | 34.9278 | 19350 | 0.0 | - | | 35.0181 | 19400 | 0.0 | - | | 35.1083 | 19450 | 0.0 | - | | 35.1986 | 19500 | 0.0 | - | | 35.2888 | 19550 | 0.0 | - | | 35.3791 | 19600 | 0.0 | - | | 35.4693 | 19650 | 0.0 | - | | 35.5596 | 19700 | 0.0 | - | | 35.6498 | 19750 | 0.0 | - | | 35.7401 | 19800 | 0.0 | - | | 35.8303 | 19850 | 0.0 | - | | 35.9206 | 19900 | 0.0 | - | | 36.0108 | 19950 | 0.0 | - | | 36.1011 | 20000 | 0.0 | - | | 36.1913 | 20050 | 0.0 | - | | 36.2816 | 20100 | 0.0 | - | | 36.3718 | 20150 | 0.0 | - | | 36.4621 | 20200 | 0.0 | - | | 36.5523 | 20250 | 0.0 | - | | 36.6426 | 20300 | 0.0 | - | | 36.7329 | 20350 | 0.0 | - | | 36.8231 | 20400 | 0.0 | - | | 36.9134 | 20450 | 0.0 | - | | 37.0036 | 20500 | 0.0 | - | | 37.0939 | 20550 | 0.0 | - | | 37.1841 | 20600 | 0.0 | - | | 37.2744 | 20650 | 0.0 | - | | 37.3646 | 20700 | 0.0 | - | | 37.4549 | 20750 | 0.0 | - | | 37.5451 | 20800 | 0.0 | - | | 37.6354 | 20850 | 0.0 | - | | 37.7256 | 20900 | 0.0 | - | | 37.8159 | 20950 | 0.0 | - | | 37.9061 | 21000 | 0.0 | - | | 37.9964 | 21050 | 0.0 | - | | 38.0866 | 21100 | 0.0 | - | | 38.1769 | 21150 | 0.0 | - | | 38.2671 | 21200 | 0.0 | - | | 38.3574 | 21250 | 0.0 | - | | 38.4477 | 21300 | 0.0 | - | | 38.5379 | 21350 | 0.0 | - | | 38.6282 | 21400 | 0.0 | - | | 38.7184 | 21450 | 0.0 | - | | 38.8087 | 21500 | 0.0 | - | | 38.8989 | 21550 | 0.0 | - | | 38.9892 | 21600 | 0.0 | - | | 39.0794 | 21650 | 0.0 | - | | 39.1697 | 21700 | 0.0 | - | | 39.2599 | 21750 | 0.0 | - | | 39.3502 | 21800 | 0.0 | - | | 39.4404 | 21850 | 0.0 | - | | 39.5307 | 21900 | 0.0 | - | | 39.6209 | 21950 | 0.0 | - | | 39.7112 | 22000 | 0.0 | - | | 39.8014 | 22050 | 0.0 | - | | 39.8917 | 22100 | 0.0 | - | | 39.9819 | 22150 | 0.0 | - | | 40.0722 | 22200 | 0.0 | - | | 40.1625 | 22250 | 0.0 | - | | 40.2527 | 22300 | 0.0 | - | | 40.3430 | 22350 | 0.0 | - | | 40.4332 | 22400 | 0.0 | - | | 40.5235 | 22450 | 0.0 | - | | 40.6137 | 22500 | 0.0 | - | | 40.7040 | 22550 | 0.0 | - | | 40.7942 | 22600 | 0.0 | - | | 40.8845 | 22650 | 0.0 | - | | 40.9747 | 22700 | 0.0 | - | | 41.0650 | 22750 | 0.0 | - | | 41.1552 | 22800 | 0.0 | - | | 41.2455 | 22850 | 0.0 | - | | 41.3357 | 22900 | 0.0 | - | | 41.4260 | 22950 | 0.0 | - | | 41.5162 | 23000 | 0.0 | - | | 41.6065 | 23050 | 0.0 | - | | 41.6968 | 23100 | 0.0 | - | | 41.7870 | 23150 | 0.0 | - | | 41.8773 | 23200 | 0.0 | - | | 41.9675 | 23250 | 0.0 | - | | 42.0578 | 23300 | 0.0 | - | | 42.1480 | 23350 | 0.0 | - | | 42.2383 | 23400 | 0.0003 | - | | 42.3285 | 23450 | 0.0005 | - | | 42.4188 | 23500 | 0.0003 | - | | 42.5090 | 23550 | 0.0002 | - | | 42.5993 | 23600 | 0.0 | - | | 42.6895 | 23650 | 0.0 | - | | 42.7798 | 23700 | 0.0 | - | | 42.8700 | 23750 | 0.0 | - | | 42.9603 | 23800 | 0.0 | - | | 43.0505 | 23850 | 0.0 | - | | 43.1408 | 23900 | 0.0 | - | | 43.2310 | 23950 | 0.0 | - | | 43.3213 | 24000 | 0.0 | - | | 43.4116 | 24050 | 0.0 | - | | 43.5018 | 24100 | 0.0 | - | | 43.5921 | 24150 | 0.0 | - | | 43.6823 | 24200 | 0.0 | - | | 43.7726 | 24250 | 0.0 | - | | 43.8628 | 24300 | 0.0 | - | | 43.9531 | 24350 | 0.0 | - | | 44.0433 | 24400 | 0.0 | - | | 44.1336 | 24450 | 0.0 | - | | 44.2238 | 24500 | 0.0 | - | | 44.3141 | 24550 | 0.0 | - | | 44.4043 | 24600 | 0.0 | - | | 44.4946 | 24650 | 0.0 | - | | 44.5848 | 24700 | 0.0 | - | | 44.6751 | 24750 | 0.0 | - | | 44.7653 | 24800 | 0.0 | - | | 44.8556 | 24850 | 0.0 | - | | 44.9458 | 24900 | 0.0 | - | | 45.0361 | 24950 | 0.0 | - | | 45.1264 | 25000 | 0.0 | - | | 45.2166 | 25050 | 0.0 | - | | 45.3069 | 25100 | 0.0 | - | | 45.3971 | 25150 | 0.0 | - | | 45.4874 | 25200 | 0.0 | - | | 45.5776 | 25250 | 0.0 | - | | 45.6679 | 25300 | 0.0 | - | | 45.7581 | 25350 | 0.0 | - | | 45.8484 | 25400 | 0.0 | - | | 45.9386 | 25450 | 0.0 | - | | 46.0289 | 25500 | 0.0 | - | | 46.1191 | 25550 | 0.0 | - | | 46.2094 | 25600 | 0.0 | - | | 46.2996 | 25650 | 0.0 | - | | 46.3899 | 25700 | 0.0 | - | | 46.4801 | 25750 | 0.0 | - | | 46.5704 | 25800 | 0.0 | - | | 46.6606 | 25850 | 0.0 | - | | 46.7509 | 25900 | 0.0 | - | | 46.8412 | 25950 | 0.0 | - | | 46.9314 | 26000 | 0.0 | - | | 47.0217 | 26050 | 0.0 | - | | 47.1119 | 26100 | 0.0 | - | | 47.2022 | 26150 | 0.0 | - | | 47.2924 | 26200 | 0.0 | - | | 47.3827 | 26250 | 0.0 | - | | 47.4729 | 26300 | 0.0 | - | | 47.5632 | 26350 | 0.0 | - | | 47.6534 | 26400 | 0.0 | - | | 47.7437 | 26450 | 0.0 | - | | 47.8339 | 26500 | 0.0 | - | | 47.9242 | 26550 | 0.0 | - | | 48.0144 | 26600 | 0.0 | - | | 48.1047 | 26650 | 0.0 | - | | 48.1949 | 26700 | 0.0 | - | | 48.2852 | 26750 | 0.0 | - | | 48.3755 | 26800 | 0.0 | - | | 48.4657 | 26850 | 0.0 | - | | 48.5560 | 26900 | 0.0 | - | | 48.6462 | 26950 | 0.0 | - | | 48.7365 | 27000 | 0.0 | - | | 48.8267 | 27050 | 0.0 | - | | 48.9170 | 27100 | 0.0 | - | | 49.0072 | 27150 | 0.0 | - | | 49.0975 | 27200 | 0.0 | - | | 49.1877 | 27250 | 0.0 | - | | 49.2780 | 27300 | 0.0 | - | | 49.3682 | 27350 | 0.0 | - | | 49.4585 | 27400 | 0.0 | - | | 49.5487 | 27450 | 0.0 | - | | 49.6390 | 27500 | 0.0 | - | | 49.7292 | 27550 | 0.0 | - | | 49.8195 | 27600 | 0.0 | - | | 49.9097 | 27650 | 0.0 | - | | 50.0 | 27700 | 0.0 | - | | 50.0903 | 27750 | 0.0 | - | | 50.1805 | 27800 | 0.0 | - | | 50.2708 | 27850 | 0.0 | - | | 50.3610 | 27900 | 0.0 | - | | 50.4513 | 27950 | 0.0 | - | | 50.5415 | 28000 | 0.0 | - | | 50.6318 | 28050 | 0.0 | - | | 50.7220 | 28100 | 0.0 | - | | 50.8123 | 28150 | 0.0 | - | | 50.9025 | 28200 | 0.0 | - | | 50.9928 | 28250 | 0.0 | - | | 51.0830 | 28300 | 0.0 | - | | 51.1733 | 28350 | 0.0 | - | | 51.2635 | 28400 | 0.0 | - | | 51.3538 | 28450 | 0.0 | - | | 51.4440 | 28500 | 0.0 | - | | 51.5343 | 28550 | 0.0 | - | | 51.6245 | 28600 | 0.0 | - | | 51.7148 | 28650 | 0.0 | - | | 51.8051 | 28700 | 0.0 | - | | 51.8953 | 28750 | 0.0 | - | | 51.9856 | 28800 | 0.0 | - | | 52.0758 | 28850 | 0.0 | - | | 52.1661 | 28900 | 0.0 | - | | 52.2563 | 28950 | 0.0 | - | | 52.3466 | 29000 | 0.0 | - | | 52.4368 | 29050 | 0.0 | - | | 52.5271 | 29100 | 0.0 | - | | 52.6173 | 29150 | 0.0 | - | | 52.7076 | 29200 | 0.0 | - | | 52.7978 | 29250 | 0.0 | - | | 52.8881 | 29300 | 0.0 | - | | 52.9783 | 29350 | 0.0 | - | | 53.0686 | 29400 | 0.0 | - | | 53.1588 | 29450 | 0.0 | - | | 53.2491 | 29500 | 0.0 | - | | 53.3394 | 29550 | 0.0 | - | | 53.4296 | 29600 | 0.0 | - | | 53.5199 | 29650 | 0.0 | - | | 53.6101 | 29700 | 0.0 | - | | 53.7004 | 29750 | 0.0 | - | | 53.7906 | 29800 | 0.0 | - | | 53.8809 | 29850 | 0.0 | - | | 53.9711 | 29900 | 0.0 | - | | 54.0614 | 29950 | 0.0 | - | | 54.1516 | 30000 | 0.0 | - | | 54.2419 | 30050 | 0.0 | - | | 54.3321 | 30100 | 0.0 | - | | 54.4224 | 30150 | 0.0 | - | | 54.5126 | 30200 | 0.0 | - | | 54.6029 | 30250 | 0.0 | - | | 54.6931 | 30300 | 0.0 | - | | 54.7834 | 30350 | 0.0 | - | | 54.8736 | 30400 | 0.0 | - | | 54.9639 | 30450 | 0.0 | - | | 55.0542 | 30500 | 0.0 | - | | 55.1444 | 30550 | 0.0 | - | | 55.2347 | 30600 | 0.0 | - | | 55.3249 | 30650 | 0.0 | - | | 55.4152 | 30700 | 0.0 | - | | 55.5054 | 30750 | 0.0 | - | | 55.5957 | 30800 | 0.0 | - | | 55.6859 | 30850 | 0.0 | - | | 55.7762 | 30900 | 0.0 | - | | 55.8664 | 30950 | 0.0 | - | | 55.9567 | 31000 | 0.0 | - | | 56.0469 | 31050 | 0.0 | - | | 56.1372 | 31100 | 0.0 | - | | 56.2274 | 31150 | 0.0 | - | | 56.3177 | 31200 | 0.0 | - | | 56.4079 | 31250 | 0.0 | - | | 56.4982 | 31300 | 0.0 | - | | 56.5884 | 31350 | 0.0 | - | | 56.6787 | 31400 | 0.0 | - | | 56.7690 | 31450 | 0.0 | - | | 56.8592 | 31500 | 0.0 | - | | 56.9495 | 31550 | 0.0 | - | | 57.0397 | 31600 | 0.0 | - | | 57.1300 | 31650 | 0.0 | - | | 57.2202 | 31700 | 0.0 | - | | 57.3105 | 31750 | 0.0 | - | | 57.4007 | 31800 | 0.0 | - | | 57.4910 | 31850 | 0.0 | - | | 57.5812 | 31900 | 0.0 | - | | 57.6715 | 31950 | 0.0 | - | | 57.7617 | 32000 | 0.0 | - | | 57.8520 | 32050 | 0.0 | - | | 57.9422 | 32100 | 0.0 | - | | 58.0325 | 32150 | 0.0 | - | | 58.1227 | 32200 | 0.0 | - | | 58.2130 | 32250 | 0.0 | - | | 58.3032 | 32300 | 0.0 | - | | 58.3935 | 32350 | 0.0 | - | | 58.4838 | 32400 | 0.0 | - | | 58.5740 | 32450 | 0.0 | - | | 58.6643 | 32500 | 0.0 | - | | 58.7545 | 32550 | 0.0 | - | | 58.8448 | 32600 | 0.0 | - | | 58.9350 | 32650 | 0.0 | - | | 59.0253 | 32700 | 0.0 | - | | 59.1155 | 32750 | 0.0 | - | | 59.2058 | 32800 | 0.0 | - | | 59.2960 | 32850 | 0.0 | - | | 59.3863 | 32900 | 0.0 | - | | 59.4765 | 32950 | 0.0 | - | | 59.5668 | 33000 | 0.0 | - | | 59.6570 | 33050 | 0.0 | - | | 59.7473 | 33100 | 0.0 | - | | 59.8375 | 33150 | 0.0 | - | | 59.9278 | 33200 | 0.0 | - | | 60.0181 | 33250 | 0.0 | - | | 60.1083 | 33300 | 0.0 | - | | 60.1986 | 33350 | 0.0 | - | | 60.2888 | 33400 | 0.0 | - | | 60.3791 | 33450 | 0.0 | - | | 60.4693 | 33500 | 0.0 | - | | 60.5596 | 33550 | 0.0 | - | | 60.6498 | 33600 | 0.0 | - | | 60.7401 | 33650 | 0.0 | - | | 60.8303 | 33700 | 0.0 | - | | 60.9206 | 33750 | 0.0 | - | | 61.0108 | 33800 | 0.0 | - | | 61.1011 | 33850 | 0.0 | - | | 61.1913 | 33900 | 0.0 | - | | 61.2816 | 33950 | 0.0 | - | | 61.3718 | 34000 | 0.0 | - | | 61.4621 | 34050 | 0.0 | - | | 61.5523 | 34100 | 0.0 | - | | 61.6426 | 34150 | 0.0 | - | | 61.7329 | 34200 | 0.0 | - | | 61.8231 | 34250 | 0.0 | - | | 61.9134 | 34300 | 0.0 | - | | 62.0036 | 34350 | 0.0 | - | | 62.0939 | 34400 | 0.0 | - | | 62.1841 | 34450 | 0.0 | - | | 62.2744 | 34500 | 0.0 | - | | 62.3646 | 34550 | 0.0 | - | | 62.4549 | 34600 | 0.0 | - | | 62.5451 | 34650 | 0.0 | - | | 62.6354 | 34700 | 0.0 | - | | 62.7256 | 34750 | 0.0 | - | | 62.8159 | 34800 | 0.0 | - | | 62.9061 | 34850 | 0.0 | - | | 62.9964 | 34900 | 0.0 | - | | 63.0866 | 34950 | 0.0 | - | | 63.1769 | 35000 | 0.0 | - | | 63.2671 | 35050 | 0.0 | - | | 63.3574 | 35100 | 0.0 | - | | 63.4477 | 35150 | 0.0 | - | | 63.5379 | 35200 | 0.0 | - | | 63.6282 | 35250 | 0.0 | - | | 63.7184 | 35300 | 0.0 | - | | 63.8087 | 35350 | 0.0 | - | | 63.8989 | 35400 | 0.0 | - | | 63.9892 | 35450 | 0.0 | - | | 64.0794 | 35500 | 0.0 | - | | 64.1697 | 35550 | 0.0 | - | | 64.2599 | 35600 | 0.0 | - | | 64.3502 | 35650 | 0.0 | - | | 64.4404 | 35700 | 0.0 | - | | 64.5307 | 35750 | 0.0 | - | | 64.6209 | 35800 | 0.0 | - | | 64.7112 | 35850 | 0.0 | - | | 64.8014 | 35900 | 0.0 | - | | 64.8917 | 35950 | 0.0 | - | | 64.9819 | 36000 | 0.0 | - | | 65.0722 | 36050 | 0.0 | - | | 65.1625 | 36100 | 0.0 | - | | 65.2527 | 36150 | 0.0 | - | | 65.3430 | 36200 | 0.0 | - | | 65.4332 | 36250 | 0.0 | - | | 65.5235 | 36300 | 0.0 | - | | 65.6137 | 36350 | 0.0 | - | | 65.7040 | 36400 | 0.0 | - | | 65.7942 | 36450 | 0.0 | - | | 65.8845 | 36500 | 0.0 | - | | 65.9747 | 36550 | 0.0 | - | | 66.0650 | 36600 | 0.0 | - | | 66.1552 | 36650 | 0.0 | - | | 66.2455 | 36700 | 0.0 | - | | 66.3357 | 36750 | 0.0 | - | | 66.4260 | 36800 | 0.0 | - | | 66.5162 | 36850 | 0.0 | - | | 66.6065 | 36900 | 0.0 | - | | 66.6968 | 36950 | 0.0 | - | | 66.7870 | 37000 | 0.0 | - | | 66.8773 | 37050 | 0.0 | - | | 66.9675 | 37100 | 0.0 | - | | 67.0578 | 37150 | 0.0 | - | | 67.1480 | 37200 | 0.0 | - | | 67.2383 | 37250 | 0.0 | - | | 67.3285 | 37300 | 0.0 | - | | 67.4188 | 37350 | 0.0 | - | | 67.5090 | 37400 | 0.0 | - | | 67.5993 | 37450 | 0.0 | - | | 67.6895 | 37500 | 0.0 | - | | 67.7798 | 37550 | 0.0 | - | | 67.8700 | 37600 | 0.0 | - | | 67.9603 | 37650 | 0.0 | - | | 68.0505 | 37700 | 0.0 | - | | 68.1408 | 37750 | 0.0 | - | | 68.2310 | 37800 | 0.0 | - | | 68.3213 | 37850 | 0.0 | - | | 68.4116 | 37900 | 0.0 | - | | 68.5018 | 37950 | 0.0 | - | | 68.5921 | 38000 | 0.0 | - | | 68.6823 | 38050 | 0.0 | - | | 68.7726 | 38100 | 0.0 | - | | 68.8628 | 38150 | 0.0 | - | | 68.9531 | 38200 | 0.0 | - | | 69.0433 | 38250 | 0.0 | - | | 69.1336 | 38300 | 0.0 | - | | 69.2238 | 38350 | 0.0 | - | | 69.3141 | 38400 | 0.0 | - | | 69.4043 | 38450 | 0.0 | - | | 69.4946 | 38500 | 0.0 | - | | 69.5848 | 38550 | 0.0 | - | | 69.6751 | 38600 | 0.0 | - | | 69.7653 | 38650 | 0.0 | - | | 69.8556 | 38700 | 0.0 | - | | 69.9458 | 38750 | 0.0 | - | ### Framework Versions - Python: 3.10.12 - SetFit: 1.1.0 - Sentence Transformers: 3.3.1 - Transformers: 4.44.2 - PyTorch: 2.2.0a0+81ea7a4 - Datasets: 3.2.0 - 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} } ```