Add SetFit model
Browse files- 1_Pooling/config.json +7 -0
- README.md +384 -0
- config.json +31 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
| 7 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: setfit
|
| 3 |
+
tags:
|
| 4 |
+
- setfit
|
| 5 |
+
- sentence-transformers
|
| 6 |
+
- text-classification
|
| 7 |
+
- generated_from_setfit_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
widget:
|
| 11 |
+
- text: 多要素認証エンジンである「LOCKED」と、セキュリティコンサルティングを通じて、国内企業のゼロトラスト対応を支援しているスタートアップ。
|
| 12 |
+
- text: Hotel rooms on the wheelsをコンセプトにした、自社生産のキャンピングカーレンタルサービスを展開するスタートアップ。
|
| 13 |
+
- text: バイオ新薬事業やバイオシミラー事業などバイオに関わる研究開発を行う企業。2021年7月にジーンテクノサイエンスからキッズウェル・バイオに社名変更をしている。
|
| 14 |
+
- text: 業務用冷凍食品の企画・開発・販売を行い、自社商品の調理方法などを公開する企業。
|
| 15 |
+
- text: がん治療機器「集束超音波(HIFU)治療装置」の開発を行う東北大学発のスタートアップ。「集束超音波」は、超音波を一点に集中させてがん組織に照射し、加熱効果などで切らずに治療する方法。放射線被曝が無いことから繰り返し治療ができ、がんに対する次世代治療として期待されている。2022年12月には、ニッセイ・キャピタル、野村スパークス・インベストメント、大和企業投資、りそなキャピタル、Carbon
|
| 16 |
+
Ventures、QRインベストメント、JA三井リース、ファストトラックイニシアティブ、SBIインベストメント、三菱UFJキャピタル、FFGベンチャービジネスパートナーズ、肥銀キャピタルを引受先とする総額23億5,000万円の資金調達を発表した。今後は、膵癌の国内治験および海外展開を含めた事業拡大に充当し、同社のビジョンである“音響工学(超音波)でがん患者さんに新たな未来をもたらす”を1日でも早く実現することを目指す。
|
| 17 |
+
pipeline_tag: text-classification
|
| 18 |
+
inference: false
|
| 19 |
+
model-index:
|
| 20 |
+
- name: SetFit
|
| 21 |
+
results:
|
| 22 |
+
- task:
|
| 23 |
+
type: text-classification
|
| 24 |
+
name: Text Classification
|
| 25 |
+
dataset:
|
| 26 |
+
name: Unknown
|
| 27 |
+
type: unknown
|
| 28 |
+
split: test
|
| 29 |
+
metrics:
|
| 30 |
+
- type: accuracy
|
| 31 |
+
value: 0.7902097902097902
|
| 32 |
+
name: Accuracy
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
# SetFit
|
| 36 |
+
|
| 37 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A OneVsRestClassifier instance is used for classification.
|
| 38 |
+
|
| 39 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 40 |
+
|
| 41 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 42 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 43 |
+
|
| 44 |
+
## Model Details
|
| 45 |
+
|
| 46 |
+
### Model Description
|
| 47 |
+
- **Model Type:** SetFit
|
| 48 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
| 49 |
+
- **Classification head:** a OneVsRestClassifier instance
|
| 50 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 51 |
+
<!-- - **Number of Classes:** Unknown -->
|
| 52 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 53 |
+
<!-- - **Language:** Unknown -->
|
| 54 |
+
<!-- - **License:** Unknown -->
|
| 55 |
+
|
| 56 |
+
### Model Sources
|
| 57 |
+
|
| 58 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 59 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 60 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 61 |
+
|
| 62 |
+
## Evaluation
|
| 63 |
+
|
| 64 |
+
### Metrics
|
| 65 |
+
| Label | Accuracy |
|
| 66 |
+
|:--------|:---------|
|
| 67 |
+
| **all** | 0.7902 |
|
| 68 |
+
|
| 69 |
+
## Uses
|
| 70 |
+
|
| 71 |
+
### Direct Use for Inference
|
| 72 |
+
|
| 73 |
+
First install the SetFit library:
|
| 74 |
+
|
| 75 |
+
```bash
|
| 76 |
+
pip install setfit
|
| 77 |
+
```
|
| 78 |
+
|
| 79 |
+
Then you can load this model and run inference.
|
| 80 |
+
|
| 81 |
+
```python
|
| 82 |
+
from setfit import SetFitModel
|
| 83 |
+
|
| 84 |
+
# Download from the 🤗 Hub
|
| 85 |
+
model = SetFitModel.from_pretrained("Ekohe/RevenueStreamJP")
|
| 86 |
+
# Run inference
|
| 87 |
+
preds = model("業務用冷凍食品の企画・開発・販売を行い、自社商品の調理方法などを公開する企業。")
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
<!--
|
| 91 |
+
### Downstream Use
|
| 92 |
+
|
| 93 |
+
*List how someone could finetune this model on their own dataset.*
|
| 94 |
+
-->
|
| 95 |
+
|
| 96 |
+
<!--
|
| 97 |
+
### Out-of-Scope Use
|
| 98 |
+
|
| 99 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 100 |
+
-->
|
| 101 |
+
|
| 102 |
+
<!--
|
| 103 |
+
## Bias, Risks and Limitations
|
| 104 |
+
|
| 105 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 106 |
+
-->
|
| 107 |
+
|
| 108 |
+
<!--
|
| 109 |
+
### Recommendations
|
| 110 |
+
|
| 111 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 112 |
+
-->
|
| 113 |
+
|
| 114 |
+
## Training Details
|
| 115 |
+
|
| 116 |
+
### Training Set Metrics
|
| 117 |
+
| Training set | Min | Median | Max |
|
| 118 |
+
|:-------------|:----|:-------|:----|
|
| 119 |
+
| Word count | 1 | 1.8981 | 57 |
|
| 120 |
+
|
| 121 |
+
### Training Hyperparameters
|
| 122 |
+
- batch_size: (8, 8)
|
| 123 |
+
- num_epochs: (35, 35)
|
| 124 |
+
- max_steps: -1
|
| 125 |
+
- sampling_strategy: oversampling
|
| 126 |
+
- num_iterations: 2
|
| 127 |
+
- body_learning_rate: (2e-05, 2e-05)
|
| 128 |
+
- head_learning_rate: 2e-05
|
| 129 |
+
- loss: CosineSimilarityLoss
|
| 130 |
+
- distance_metric: cosine_distance
|
| 131 |
+
- margin: 0.25
|
| 132 |
+
- end_to_end: False
|
| 133 |
+
- use_amp: False
|
| 134 |
+
- warmup_proportion: 0.1
|
| 135 |
+
- seed: 42
|
| 136 |
+
- eval_max_steps: -1
|
| 137 |
+
- load_best_model_at_end: False
|
| 138 |
+
|
| 139 |
+
### Training Results
|
| 140 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 141 |
+
|:-------:|:----:|:-------------:|:---------------:|
|
| 142 |
+
| 0.0035 | 1 | 0.3068 | - |
|
| 143 |
+
| 0.1754 | 50 | 0.2708 | - |
|
| 144 |
+
| 0.3509 | 100 | 0.2253 | - |
|
| 145 |
+
| 0.5263 | 150 | 0.2705 | - |
|
| 146 |
+
| 0.7018 | 200 | 0.1665 | - |
|
| 147 |
+
| 0.8772 | 250 | 0.2609 | - |
|
| 148 |
+
| 1.0526 | 300 | 0.2681 | - |
|
| 149 |
+
| 1.2281 | 350 | 0.2614 | - |
|
| 150 |
+
| 1.4035 | 400 | 0.2151 | - |
|
| 151 |
+
| 1.5789 | 450 | 0.1952 | - |
|
| 152 |
+
| 1.7544 | 500 | 0.2275 | - |
|
| 153 |
+
| 1.9298 | 550 | 0.3111 | - |
|
| 154 |
+
| 2.1053 | 600 | 0.1036 | - |
|
| 155 |
+
| 2.2807 | 650 | 0.1038 | - |
|
| 156 |
+
| 2.4561 | 700 | 0.0081 | - |
|
| 157 |
+
| 2.6316 | 750 | 0.0906 | - |
|
| 158 |
+
| 2.8070 | 800 | 0.0002 | - |
|
| 159 |
+
| 2.9825 | 850 | 0.0928 | - |
|
| 160 |
+
| 3.1579 | 900 | 0.0004 | - |
|
| 161 |
+
| 3.3333 | 950 | 0.0011 | - |
|
| 162 |
+
| 3.5088 | 1000 | 0.0013 | - |
|
| 163 |
+
| 3.6842 | 1050 | 0.0004 | - |
|
| 164 |
+
| 3.8596 | 1100 | 0.0012 | - |
|
| 165 |
+
| 4.0351 | 1150 | 0.0002 | - |
|
| 166 |
+
| 4.2105 | 1200 | 0.0004 | - |
|
| 167 |
+
| 4.3860 | 1250 | 0.0003 | - |
|
| 168 |
+
| 4.5614 | 1300 | 0.0 | - |
|
| 169 |
+
| 4.7368 | 1350 | 0.0001 | - |
|
| 170 |
+
| 4.9123 | 1400 | 0.0002 | - |
|
| 171 |
+
| 5.0877 | 1450 | 0.0 | - |
|
| 172 |
+
| 5.2632 | 1500 | 0.0002 | - |
|
| 173 |
+
| 5.4386 | 1550 | 0.0 | - |
|
| 174 |
+
| 5.6140 | 1600 | 0.0 | - |
|
| 175 |
+
| 5.7895 | 1650 | 0.0 | - |
|
| 176 |
+
| 5.9649 | 1700 | 0.1017 | - |
|
| 177 |
+
| 6.1404 | 1750 | 0.0012 | - |
|
| 178 |
+
| 6.3158 | 1800 | 0.0 | - |
|
| 179 |
+
| 6.4912 | 1850 | 0.0001 | - |
|
| 180 |
+
| 6.6667 | 1900 | 0.0 | - |
|
| 181 |
+
| 6.8421 | 1950 | 0.0003 | - |
|
| 182 |
+
| 7.0175 | 2000 | 0.0 | - |
|
| 183 |
+
| 7.1930 | 2050 | 0.0 | - |
|
| 184 |
+
| 7.3684 | 2100 | 0.0 | - |
|
| 185 |
+
| 7.5439 | 2150 | 0.0 | - |
|
| 186 |
+
| 7.7193 | 2200 | 0.0 | - |
|
| 187 |
+
| 7.8947 | 2250 | 0.0 | - |
|
| 188 |
+
| 8.0702 | 2300 | 0.0 | - |
|
| 189 |
+
| 8.2456 | 2350 | 0.0 | - |
|
| 190 |
+
| 8.4211 | 2400 | 0.0019 | - |
|
| 191 |
+
| 8.5965 | 2450 | 0.0017 | - |
|
| 192 |
+
| 8.7719 | 2500 | 0.0 | - |
|
| 193 |
+
| 8.9474 | 2550 | 0.0034 | - |
|
| 194 |
+
| 9.1228 | 2600 | 0.0 | - |
|
| 195 |
+
| 9.2982 | 2650 | 0.0 | - |
|
| 196 |
+
| 9.4737 | 2700 | 0.0 | - |
|
| 197 |
+
| 9.6491 | 2750 | 0.0 | - |
|
| 198 |
+
| 9.8246 | 2800 | 0.0 | - |
|
| 199 |
+
| 10.0 | 2850 | 0.0 | - |
|
| 200 |
+
| 10.1754 | 2900 | 0.0 | - |
|
| 201 |
+
| 10.3509 | 2950 | 0.0 | - |
|
| 202 |
+
| 10.5263 | 3000 | 0.0 | - |
|
| 203 |
+
| 10.7018 | 3050 | 0.0 | - |
|
| 204 |
+
| 10.8772 | 3100 | 0.0001 | - |
|
| 205 |
+
| 11.0526 | 3150 | 0.0 | - |
|
| 206 |
+
| 11.2281 | 3200 | 0.0 | - |
|
| 207 |
+
| 11.4035 | 3250 | 0.0 | - |
|
| 208 |
+
| 11.5789 | 3300 | 0.0 | - |
|
| 209 |
+
| 11.7544 | 3350 | 0.0 | - |
|
| 210 |
+
| 11.9298 | 3400 | 0.0 | - |
|
| 211 |
+
| 12.1053 | 3450 | 0.0 | - |
|
| 212 |
+
| 12.2807 | 3500 | 0.0 | - |
|
| 213 |
+
| 12.4561 | 3550 | 0.0 | - |
|
| 214 |
+
| 12.6316 | 3600 | 0.0 | - |
|
| 215 |
+
| 12.8070 | 3650 | 0.0 | - |
|
| 216 |
+
| 12.9825 | 3700 | 0.0 | - |
|
| 217 |
+
| 13.1579 | 3750 | 0.0 | - |
|
| 218 |
+
| 13.3333 | 3800 | 0.0 | - |
|
| 219 |
+
| 13.5088 | 3850 | 0.0 | - |
|
| 220 |
+
| 13.6842 | 3900 | 0.0 | - |
|
| 221 |
+
| 13.8596 | 3950 | 0.0 | - |
|
| 222 |
+
| 14.0351 | 4000 | 0.0 | - |
|
| 223 |
+
| 14.2105 | 4050 | 0.0 | - |
|
| 224 |
+
| 14.3860 | 4100 | 0.0 | - |
|
| 225 |
+
| 14.5614 | 4150 | 0.0 | - |
|
| 226 |
+
| 14.7368 | 4200 | 0.0 | - |
|
| 227 |
+
| 14.9123 | 4250 | 0.0 | - |
|
| 228 |
+
| 15.0877 | 4300 | 0.0 | - |
|
| 229 |
+
| 15.2632 | 4350 | 0.0 | - |
|
| 230 |
+
| 15.4386 | 4400 | 0.0 | - |
|
| 231 |
+
| 15.6140 | 4450 | 0.0 | - |
|
| 232 |
+
| 15.7895 | 4500 | 0.0 | - |
|
| 233 |
+
| 15.9649 | 4550 | 0.1016 | - |
|
| 234 |
+
| 16.1404 | 4600 | 0.1214 | - |
|
| 235 |
+
| 16.3158 | 4650 | 0.0 | - |
|
| 236 |
+
| 16.4912 | 4700 | 0.0 | - |
|
| 237 |
+
| 16.6667 | 4750 | 0.0 | - |
|
| 238 |
+
| 16.8421 | 4800 | 0.0 | - |
|
| 239 |
+
| 17.0175 | 4850 | 0.0 | - |
|
| 240 |
+
| 17.1930 | 4900 | 0.0 | - |
|
| 241 |
+
| 17.3684 | 4950 | 0.0 | - |
|
| 242 |
+
| 17.5439 | 5000 | 0.0 | - |
|
| 243 |
+
| 17.7193 | 5050 | 0.0 | - |
|
| 244 |
+
| 17.8947 | 5100 | 0.0 | - |
|
| 245 |
+
| 18.0702 | 5150 | 0.0 | - |
|
| 246 |
+
| 18.2456 | 5200 | 0.0 | - |
|
| 247 |
+
| 18.4211 | 5250 | 0.0 | - |
|
| 248 |
+
| 18.5965 | 5300 | 0.0 | - |
|
| 249 |
+
| 18.7719 | 5350 | 0.0 | - |
|
| 250 |
+
| 18.9474 | 5400 | 0.0 | - |
|
| 251 |
+
| 19.1228 | 5450 | 0.0 | - |
|
| 252 |
+
| 19.2982 | 5500 | 0.0001 | - |
|
| 253 |
+
| 19.4737 | 5550 | 0.0 | - |
|
| 254 |
+
| 19.6491 | 5600 | 0.0001 | - |
|
| 255 |
+
| 19.8246 | 5650 | 0.0174 | - |
|
| 256 |
+
| 20.0 | 5700 | 0.0 | - |
|
| 257 |
+
| 20.1754 | 5750 | 0.0 | - |
|
| 258 |
+
| 20.3509 | 5800 | 0.0 | - |
|
| 259 |
+
| 20.5263 | 5850 | 0.0 | - |
|
| 260 |
+
| 20.7018 | 5900 | 0.0 | - |
|
| 261 |
+
| 20.8772 | 5950 | 0.0 | - |
|
| 262 |
+
| 21.0526 | 6000 | 0.0 | - |
|
| 263 |
+
| 21.2281 | 6050 | 0.0 | - |
|
| 264 |
+
| 21.4035 | 6100 | 0.0 | - |
|
| 265 |
+
| 21.5789 | 6150 | 0.0 | - |
|
| 266 |
+
| 21.7544 | 6200 | 0.0 | - |
|
| 267 |
+
| 21.9298 | 6250 | 0.0 | - |
|
| 268 |
+
| 22.1053 | 6300 | 0.0 | - |
|
| 269 |
+
| 22.2807 | 6350 | 0.0 | - |
|
| 270 |
+
| 22.4561 | 6400 | 0.0 | - |
|
| 271 |
+
| 22.6316 | 6450 | 0.0 | - |
|
| 272 |
+
| 22.8070 | 6500 | 0.0 | - |
|
| 273 |
+
| 22.9825 | 6550 | 0.0 | - |
|
| 274 |
+
| 23.1579 | 6600 | 0.0 | - |
|
| 275 |
+
| 23.3333 | 6650 | 0.0 | - |
|
| 276 |
+
| 23.5088 | 6700 | 0.0 | - |
|
| 277 |
+
| 23.6842 | 6750 | 0.0 | - |
|
| 278 |
+
| 23.8596 | 6800 | 0.0 | - |
|
| 279 |
+
| 24.0351 | 6850 | 0.0 | - |
|
| 280 |
+
| 24.2105 | 6900 | 0.0 | - |
|
| 281 |
+
| 24.3860 | 6950 | 0.0 | - |
|
| 282 |
+
| 24.5614 | 7000 | 0.0 | - |
|
| 283 |
+
| 24.7368 | 7050 | 0.0 | - |
|
| 284 |
+
| 24.9123 | 7100 | 0.0 | - |
|
| 285 |
+
| 25.0877 | 7150 | 0.0 | - |
|
| 286 |
+
| 25.2632 | 7200 | 0.0 | - |
|
| 287 |
+
| 25.4386 | 7250 | 0.0816 | - |
|
| 288 |
+
| 25.6140 | 7300 | 0.0005 | - |
|
| 289 |
+
| 25.7895 | 7350 | 0.0 | - |
|
| 290 |
+
| 25.9649 | 7400 | 0.0001 | - |
|
| 291 |
+
| 26.1404 | 7450 | 0.0001 | - |
|
| 292 |
+
| 26.3158 | 7500 | 0.0 | - |
|
| 293 |
+
| 26.4912 | 7550 | 0.0 | - |
|
| 294 |
+
| 26.6667 | 7600 | 0.0 | - |
|
| 295 |
+
| 26.8421 | 7650 | 0.0 | - |
|
| 296 |
+
| 27.0175 | 7700 | 0.0 | - |
|
| 297 |
+
| 27.1930 | 7750 | 0.0 | - |
|
| 298 |
+
| 27.3684 | 7800 | 0.0 | - |
|
| 299 |
+
| 27.5439 | 7850 | 0.0 | - |
|
| 300 |
+
| 27.7193 | 7900 | 0.0 | - |
|
| 301 |
+
| 27.8947 | 7950 | 0.0 | - |
|
| 302 |
+
| 28.0702 | 8000 | 0.0 | - |
|
| 303 |
+
| 28.2456 | 8050 | 0.0 | - |
|
| 304 |
+
| 28.4211 | 8100 | 0.0 | - |
|
| 305 |
+
| 28.5965 | 8150 | 0.0 | - |
|
| 306 |
+
| 28.7719 | 8200 | 0.0 | - |
|
| 307 |
+
| 28.9474 | 8250 | 0.0 | - |
|
| 308 |
+
| 29.1228 | 8300 | 0.0 | - |
|
| 309 |
+
| 29.2982 | 8350 | 0.0 | - |
|
| 310 |
+
| 29.4737 | 8400 | 0.0 | - |
|
| 311 |
+
| 29.6491 | 8450 | 0.0 | - |
|
| 312 |
+
| 29.8246 | 8500 | 0.0 | - |
|
| 313 |
+
| 30.0 | 8550 | 0.0 | - |
|
| 314 |
+
| 30.1754 | 8600 | 0.0 | - |
|
| 315 |
+
| 30.3509 | 8650 | 0.0 | - |
|
| 316 |
+
| 30.5263 | 8700 | 0.0 | - |
|
| 317 |
+
| 30.7018 | 8750 | 0.0 | - |
|
| 318 |
+
| 30.8772 | 8800 | 0.0 | - |
|
| 319 |
+
| 31.0526 | 8850 | 0.0 | - |
|
| 320 |
+
| 31.2281 | 8900 | 0.0 | - |
|
| 321 |
+
| 31.4035 | 8950 | 0.0 | - |
|
| 322 |
+
| 31.5789 | 9000 | 0.0 | - |
|
| 323 |
+
| 31.7544 | 9050 | 0.0 | - |
|
| 324 |
+
| 31.9298 | 9100 | 0.0 | - |
|
| 325 |
+
| 32.1053 | 9150 | 0.0 | - |
|
| 326 |
+
| 32.2807 | 9200 | 0.0 | - |
|
| 327 |
+
| 32.4561 | 9250 | 0.0 | - |
|
| 328 |
+
| 32.6316 | 9300 | 0.0 | - |
|
| 329 |
+
| 32.8070 | 9350 | 0.0 | - |
|
| 330 |
+
| 32.9825 | 9400 | 0.0 | - |
|
| 331 |
+
| 33.1579 | 9450 | 0.0 | - |
|
| 332 |
+
| 33.3333 | 9500 | 0.0 | - |
|
| 333 |
+
| 33.5088 | 9550 | 0.0 | - |
|
| 334 |
+
| 33.6842 | 9600 | 0.0 | - |
|
| 335 |
+
| 33.8596 | 9650 | 0.0 | - |
|
| 336 |
+
| 34.0351 | 9700 | 0.0 | - |
|
| 337 |
+
| 34.2105 | 9750 | 0.0 | - |
|
| 338 |
+
| 34.3860 | 9800 | 0.0 | - |
|
| 339 |
+
| 34.5614 | 9850 | 0.0 | - |
|
| 340 |
+
| 34.7368 | 9900 | 0.0 | - |
|
| 341 |
+
| 34.9123 | 9950 | 0.0 | - |
|
| 342 |
+
|
| 343 |
+
### Framework Versions
|
| 344 |
+
- Python: 3.10.12
|
| 345 |
+
- SetFit: 1.0.1
|
| 346 |
+
- Sentence Transformers: 2.2.2
|
| 347 |
+
- Transformers: 4.35.2
|
| 348 |
+
- PyTorch: 2.1.0+cu118
|
| 349 |
+
- Datasets: 2.15.0
|
| 350 |
+
- Tokenizers: 0.15.0
|
| 351 |
+
|
| 352 |
+
## Citation
|
| 353 |
+
|
| 354 |
+
### BibTeX
|
| 355 |
+
```bibtex
|
| 356 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 357 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 358 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 359 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 360 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 361 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 362 |
+
publisher = {arXiv},
|
| 363 |
+
year = {2022},
|
| 364 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 365 |
+
}
|
| 366 |
+
```
|
| 367 |
+
|
| 368 |
+
<!--
|
| 369 |
+
## Glossary
|
| 370 |
+
|
| 371 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 372 |
+
-->
|
| 373 |
+
|
| 374 |
+
<!--
|
| 375 |
+
## Model Card Authors
|
| 376 |
+
|
| 377 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 378 |
+
-->
|
| 379 |
+
|
| 380 |
+
<!--
|
| 381 |
+
## Model Card Contact
|
| 382 |
+
|
| 383 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 384 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/bert-base-multilingual-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_fc_size": 768,
|
| 21 |
+
"pooler_num_attention_heads": 12,
|
| 22 |
+
"pooler_num_fc_layers": 3,
|
| 23 |
+
"pooler_size_per_head": 128,
|
| 24 |
+
"pooler_type": "first_token_transform",
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.35.2",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 119547
|
| 31 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "2.2.2",
|
| 4 |
+
"transformers": "4.35.2",
|
| 5 |
+
"pytorch": "2.1.0+cu118"
|
| 6 |
+
}
|
| 7 |
+
}
|
config_setfit.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"normalize_embeddings": false,
|
| 3 |
+
"labels": null
|
| 4 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d870039c769fa154bdf1e2a274e01a52a48effcb94c9b1cc2a90ac254885ca8
|
| 3 |
+
size 711436136
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870dfac192d0419457e5b04571f82de86a74437298fa7e3a9f736b62d7773e34
|
| 3 |
+
size 13956
|
modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|