Add SetFit model
Browse files- 1_Pooling/config.json +7 -0
- README.md +628 -0
- config.json +47 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +11 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -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 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Aku sudah lebih tua dan hidupku sangat berbeda. Aku bisa merasakan betapa
|
12 |
+
takjubnya aku pagi itu
|
13 |
+
- text: Saya merasa cukup href http kata-kata yang tak terucapkan disimpan di dalam
|
14 |
+
- text: Aku melihat ke dalam dompetku dan aku merasakan hawa dingin
|
15 |
+
- text: Aku menurunkan Erik dengan perasaan agak tidak puas dengan malam itu
|
16 |
+
- text: Aku bertanya-tanya apa yang siswa lain di kelasku rasakan ketika aku tidak
|
17 |
+
takut untuk memberikan jawaban di luar sana
|
18 |
+
pipeline_tag: text-classification
|
19 |
+
inference: true
|
20 |
+
base_model: firqaaa/indo-sentence-bert-base
|
21 |
+
model-index:
|
22 |
+
- name: SetFit with firqaaa/indo-sentence-bert-base
|
23 |
+
results:
|
24 |
+
- task:
|
25 |
+
type: text-classification
|
26 |
+
name: Text Classification
|
27 |
+
dataset:
|
28 |
+
name: Unknown
|
29 |
+
type: unknown
|
30 |
+
split: test
|
31 |
+
metrics:
|
32 |
+
- type: accuracy
|
33 |
+
value: 0.718
|
34 |
+
name: Accuracy
|
35 |
+
---
|
36 |
+
|
37 |
+
# SetFit with firqaaa/indo-sentence-bert-base
|
38 |
+
|
39 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-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.
|
40 |
+
|
41 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
42 |
+
|
43 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
44 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
45 |
+
|
46 |
+
## Model Details
|
47 |
+
|
48 |
+
### Model Description
|
49 |
+
- **Model Type:** SetFit
|
50 |
+
- **Sentence Transformer body:** [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base)
|
51 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
52 |
+
- **Maximum Sequence Length:** 512 tokens
|
53 |
+
- **Number of Classes:** 6 classes
|
54 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
55 |
+
<!-- - **Language:** Unknown -->
|
56 |
+
<!-- - **License:** Unknown -->
|
57 |
+
|
58 |
+
### Model Sources
|
59 |
+
|
60 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
61 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
62 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
63 |
+
|
64 |
+
### Model Labels
|
65 |
+
| Label | Examples |
|
66 |
+
|:----------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
67 |
+
| kesedihan | <ul><li>'Saya merasa agak kecewa, saya rasa harus menyerahkan sesuatu yang tidak menarik hanya untuk memenuhi tenggat waktu'</li><li>'Aku merasa seperti aku telah cukup lalai terhadap blogku dan aku hanya mengatakan bahwa kita di sini hidup dan bahagia'</li><li>'Aku tahu dan aku selalu terkoyak karenanya karena aku merasa tidak berdaya dan tidak berguna'</li></ul> |
|
68 |
+
| sukacita | <ul><li>'aku mungkin tidak merasa begitu keren'</li><li>'saya merasa baik-baik saja'</li><li>'saya merasa seperti saya seorang ibu dengan mengorbankan produktivitas'</li></ul> |
|
69 |
+
| cinta | <ul><li>'aku merasa mencintaimu'</li><li>'aku akan merasa sangat nostalgia di usia yang begitu muda'</li><li>'Saya merasa diberkati bahwa saya tinggal di Amerika memiliki keluarga yang luar biasa dan Dorothy Kelsey adalah bagian dari hidup saya'</li></ul> |
|
70 |
+
| amarah | <ul><li>'Aku terlalu memikirkan cara dudukku, suaraku terdengar jika ada makanan di mulutku, dan perasaan bahwa aku harus berjalan ke semua orang agar tidak bersikap kasar'</li><li>'aku merasa memberontak sedikit kesal gila terkurung'</li><li>'Aku merasakan perasaan itu muncul kembali dari perasaan paranoid dan cemburu yang penuh kebencian yang selalu menyiksaku tanpa henti'</li></ul> |
|
71 |
+
| takut | <ul><li>'aku merasa seperti diserang oleh landak titanium'</li><li>'Aku membiarkan diriku memikirkan perilakuku terhadapmu saat kita masih kecil. Aku merasakan campuran aneh antara rasa bersalah dan kekaguman atas ketangguhanmu'</li><li>'saya marah karena majikan saya tidak berinvestasi pada kami sama sekali, gaji pelatihan, kenaikan hari libur bank dan rasanya seperti ketidakadilan sehingga saya merasa tidak berdaya'</li></ul> |
|
72 |
+
| kejutan | <ul><li>'Aku membaca bagian ol feefyefo Aku merasa takjub melihat betapa aku bisa mengoceh dan betapa transparannya aku dalam hidupku'</li><li>'saya menemukan seni di sisi lain saya merasa sangat terkesan dengan karya saya'</li><li>'aku merasa penasaran, bersemangat dan tidak sabar'</li></ul> |
|
73 |
+
|
74 |
+
## Evaluation
|
75 |
+
|
76 |
+
### Metrics
|
77 |
+
| Label | Accuracy |
|
78 |
+
|:--------|:---------|
|
79 |
+
| **all** | 0.718 |
|
80 |
+
|
81 |
+
## Uses
|
82 |
+
|
83 |
+
### Direct Use for Inference
|
84 |
+
|
85 |
+
First install the SetFit library:
|
86 |
+
|
87 |
+
```bash
|
88 |
+
pip install setfit
|
89 |
+
```
|
90 |
+
|
91 |
+
Then you can load this model and run inference.
|
92 |
+
|
93 |
+
```python
|
94 |
+
from setfit import SetFitModel
|
95 |
+
|
96 |
+
# Download from the 🤗 Hub
|
97 |
+
model = SetFitModel.from_pretrained("firqaaa/indo-setfit-bert-base-p3")
|
98 |
+
# Run inference
|
99 |
+
preds = model("Aku melihat ke dalam dompetku dan aku merasakan hawa dingin")
|
100 |
+
```
|
101 |
+
|
102 |
+
<!--
|
103 |
+
### Downstream Use
|
104 |
+
|
105 |
+
*List how someone could finetune this model on their own dataset.*
|
106 |
+
-->
|
107 |
+
|
108 |
+
<!--
|
109 |
+
### Out-of-Scope Use
|
110 |
+
|
111 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
112 |
+
-->
|
113 |
+
|
114 |
+
<!--
|
115 |
+
## Bias, Risks and Limitations
|
116 |
+
|
117 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
118 |
+
-->
|
119 |
+
|
120 |
+
<!--
|
121 |
+
### Recommendations
|
122 |
+
|
123 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
124 |
+
-->
|
125 |
+
|
126 |
+
## Training Details
|
127 |
+
|
128 |
+
### Training Set Metrics
|
129 |
+
| Training set | Min | Median | Max |
|
130 |
+
|:-------------|:----|:--------|:----|
|
131 |
+
| Word count | 2 | 16.7928 | 56 |
|
132 |
+
|
133 |
+
| Label | Training Sample Count |
|
134 |
+
|:----------|:----------------------|
|
135 |
+
| kesedihan | 300 |
|
136 |
+
| sukacita | 300 |
|
137 |
+
| cinta | 300 |
|
138 |
+
| amarah | 300 |
|
139 |
+
| takut | 300 |
|
140 |
+
| kejutan | 300 |
|
141 |
+
|
142 |
+
### Training Hyperparameters
|
143 |
+
- batch_size: (128, 128)
|
144 |
+
- num_epochs: (1, 1)
|
145 |
+
- max_steps: -1
|
146 |
+
- sampling_strategy: oversampling
|
147 |
+
- body_learning_rate: (2e-05, 1e-05)
|
148 |
+
- head_learning_rate: 0.01
|
149 |
+
- loss: CosineSimilarityLoss
|
150 |
+
- distance_metric: cosine_distance
|
151 |
+
- margin: 0.25
|
152 |
+
- end_to_end: False
|
153 |
+
- use_amp: False
|
154 |
+
- warmup_proportion: 0.1
|
155 |
+
- seed: 42
|
156 |
+
- eval_max_steps: -1
|
157 |
+
- load_best_model_at_end: True
|
158 |
+
|
159 |
+
### Training Results
|
160 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
161 |
+
|:-------:|:---------:|:-------------:|:---------------:|
|
162 |
+
| 0.0000 | 1 | 0.2927 | - |
|
163 |
+
| 0.0024 | 50 | 0.2605 | - |
|
164 |
+
| 0.0047 | 100 | 0.2591 | - |
|
165 |
+
| 0.0071 | 150 | 0.2638 | - |
|
166 |
+
| 0.0095 | 200 | 0.245 | - |
|
167 |
+
| 0.0119 | 250 | 0.226 | - |
|
168 |
+
| 0.0142 | 300 | 0.222 | - |
|
169 |
+
| 0.0166 | 350 | 0.1968 | - |
|
170 |
+
| 0.0190 | 400 | 0.1703 | - |
|
171 |
+
| 0.0213 | 450 | 0.1703 | - |
|
172 |
+
| 0.0237 | 500 | 0.1587 | - |
|
173 |
+
| 0.0261 | 550 | 0.1087 | - |
|
174 |
+
| 0.0284 | 600 | 0.1203 | - |
|
175 |
+
| 0.0308 | 650 | 0.0844 | - |
|
176 |
+
| 0.0332 | 700 | 0.0696 | - |
|
177 |
+
| 0.0356 | 750 | 0.0606 | - |
|
178 |
+
| 0.0379 | 800 | 0.0333 | - |
|
179 |
+
| 0.0403 | 850 | 0.0453 | - |
|
180 |
+
| 0.0427 | 900 | 0.033 | - |
|
181 |
+
| 0.0450 | 950 | 0.0142 | - |
|
182 |
+
| 0.0474 | 1000 | 0.004 | - |
|
183 |
+
| 0.0498 | 1050 | 0.0097 | - |
|
184 |
+
| 0.0521 | 1100 | 0.0065 | - |
|
185 |
+
| 0.0545 | 1150 | 0.0081 | - |
|
186 |
+
| 0.0569 | 1200 | 0.0041 | - |
|
187 |
+
| 0.0593 | 1250 | 0.0044 | - |
|
188 |
+
| 0.0616 | 1300 | 0.0013 | - |
|
189 |
+
| 0.0640 | 1350 | 0.0024 | - |
|
190 |
+
| 0.0664 | 1400 | 0.001 | - |
|
191 |
+
| 0.0687 | 1450 | 0.0012 | - |
|
192 |
+
| 0.0711 | 1500 | 0.0013 | - |
|
193 |
+
| 0.0735 | 1550 | 0.0006 | - |
|
194 |
+
| 0.0759 | 1600 | 0.0033 | - |
|
195 |
+
| 0.0782 | 1650 | 0.0006 | - |
|
196 |
+
| 0.0806 | 1700 | 0.0013 | - |
|
197 |
+
| 0.0830 | 1750 | 0.0008 | - |
|
198 |
+
| 0.0853 | 1800 | 0.0006 | - |
|
199 |
+
| 0.0877 | 1850 | 0.0008 | - |
|
200 |
+
| 0.0901 | 1900 | 0.0004 | - |
|
201 |
+
| 0.0924 | 1950 | 0.0005 | - |
|
202 |
+
| 0.0948 | 2000 | 0.0004 | - |
|
203 |
+
| 0.0972 | 2050 | 0.0002 | - |
|
204 |
+
| 0.0996 | 2100 | 0.0002 | - |
|
205 |
+
| 0.1019 | 2150 | 0.0003 | - |
|
206 |
+
| 0.1043 | 2200 | 0.0006 | - |
|
207 |
+
| 0.1067 | 2250 | 0.0005 | - |
|
208 |
+
| 0.1090 | 2300 | 0.0003 | - |
|
209 |
+
| 0.1114 | 2350 | 0.0018 | - |
|
210 |
+
| 0.1138 | 2400 | 0.0003 | - |
|
211 |
+
| 0.1161 | 2450 | 0.0002 | - |
|
212 |
+
| 0.1185 | 2500 | 0.0018 | - |
|
213 |
+
| 0.1209 | 2550 | 0.0003 | - |
|
214 |
+
| 0.1233 | 2600 | 0.0008 | - |
|
215 |
+
| 0.1256 | 2650 | 0.0002 | - |
|
216 |
+
| 0.1280 | 2700 | 0.0007 | - |
|
217 |
+
| 0.1304 | 2750 | 0.006 | - |
|
218 |
+
| 0.1327 | 2800 | 0.0002 | - |
|
219 |
+
| 0.1351 | 2850 | 0.0001 | - |
|
220 |
+
| 0.1375 | 2900 | 0.0001 | - |
|
221 |
+
| 0.1399 | 2950 | 0.0001 | - |
|
222 |
+
| 0.1422 | 3000 | 0.0001 | - |
|
223 |
+
| 0.1446 | 3050 | 0.0001 | - |
|
224 |
+
| 0.1470 | 3100 | 0.0001 | - |
|
225 |
+
| 0.1493 | 3150 | 0.0001 | - |
|
226 |
+
| 0.1517 | 3200 | 0.0002 | - |
|
227 |
+
| 0.1541 | 3250 | 0.0003 | - |
|
228 |
+
| 0.1564 | 3300 | 0.0004 | - |
|
229 |
+
| 0.1588 | 3350 | 0.0001 | - |
|
230 |
+
| 0.1612 | 3400 | 0.0001 | - |
|
231 |
+
| 0.1636 | 3450 | 0.0014 | - |
|
232 |
+
| 0.1659 | 3500 | 0.0005 | - |
|
233 |
+
| 0.1683 | 3550 | 0.0003 | - |
|
234 |
+
| 0.1707 | 3600 | 0.0001 | - |
|
235 |
+
| 0.1730 | 3650 | 0.0001 | - |
|
236 |
+
| 0.1754 | 3700 | 0.0001 | - |
|
237 |
+
| 0.1778 | 3750 | 0.0001 | - |
|
238 |
+
| 0.1801 | 3800 | 0.0001 | - |
|
239 |
+
| 0.1825 | 3850 | 0.0001 | - |
|
240 |
+
| 0.1849 | 3900 | 0.0001 | - |
|
241 |
+
| 0.1873 | 3950 | 0.0001 | - |
|
242 |
+
| 0.1896 | 4000 | 0.0001 | - |
|
243 |
+
| 0.1920 | 4050 | 0.0001 | - |
|
244 |
+
| 0.1944 | 4100 | 0.0003 | - |
|
245 |
+
| 0.1967 | 4150 | 0.0006 | - |
|
246 |
+
| 0.1991 | 4200 | 0.0001 | - |
|
247 |
+
| 0.2015 | 4250 | 0.0 | - |
|
248 |
+
| 0.2038 | 4300 | 0.0 | - |
|
249 |
+
| 0.2062 | 4350 | 0.0001 | - |
|
250 |
+
| 0.2086 | 4400 | 0.0 | - |
|
251 |
+
| 0.2110 | 4450 | 0.0 | - |
|
252 |
+
| 0.2133 | 4500 | 0.0001 | - |
|
253 |
+
| 0.2157 | 4550 | 0.0002 | - |
|
254 |
+
| 0.2181 | 4600 | 0.0003 | - |
|
255 |
+
| 0.2204 | 4650 | 0.0018 | - |
|
256 |
+
| 0.2228 | 4700 | 0.0003 | - |
|
257 |
+
| 0.2252 | 4750 | 0.0145 | - |
|
258 |
+
| 0.2276 | 4800 | 0.0001 | - |
|
259 |
+
| 0.2299 | 4850 | 0.0006 | - |
|
260 |
+
| 0.2323 | 4900 | 0.0001 | - |
|
261 |
+
| 0.2347 | 4950 | 0.0007 | - |
|
262 |
+
| 0.2370 | 5000 | 0.0001 | - |
|
263 |
+
| 0.2394 | 5050 | 0.0 | - |
|
264 |
+
| 0.2418 | 5100 | 0.0 | - |
|
265 |
+
| 0.2441 | 5150 | 0.0001 | - |
|
266 |
+
| 0.2465 | 5200 | 0.0003 | - |
|
267 |
+
| 0.2489 | 5250 | 0.0 | - |
|
268 |
+
| 0.2513 | 5300 | 0.0 | - |
|
269 |
+
| 0.2536 | 5350 | 0.0 | - |
|
270 |
+
| 0.2560 | 5400 | 0.0 | - |
|
271 |
+
| 0.2584 | 5450 | 0.0004 | - |
|
272 |
+
| 0.2607 | 5500 | 0.0 | - |
|
273 |
+
| 0.2631 | 5550 | 0.0 | - |
|
274 |
+
| 0.2655 | 5600 | 0.0 | - |
|
275 |
+
| 0.2678 | 5650 | 0.0 | - |
|
276 |
+
| 0.2702 | 5700 | 0.0 | - |
|
277 |
+
| 0.2726 | 5750 | 0.0002 | - |
|
278 |
+
| 0.2750 | 5800 | 0.0 | - |
|
279 |
+
| 0.2773 | 5850 | 0.0 | - |
|
280 |
+
| 0.2797 | 5900 | 0.0 | - |
|
281 |
+
| 0.2821 | 5950 | 0.0 | - |
|
282 |
+
| 0.2844 | 6000 | 0.0 | - |
|
283 |
+
| 0.2868 | 6050 | 0.0 | - |
|
284 |
+
| 0.2892 | 6100 | 0.0 | - |
|
285 |
+
| 0.2916 | 6150 | 0.0 | - |
|
286 |
+
| 0.2939 | 6200 | 0.0 | - |
|
287 |
+
| 0.2963 | 6250 | 0.0 | - |
|
288 |
+
| 0.2987 | 6300 | 0.0001 | - |
|
289 |
+
| 0.3010 | 6350 | 0.0003 | - |
|
290 |
+
| 0.3034 | 6400 | 0.0048 | - |
|
291 |
+
| 0.3058 | 6450 | 0.0 | - |
|
292 |
+
| 0.3081 | 6500 | 0.0 | - |
|
293 |
+
| 0.3105 | 6550 | 0.0 | - |
|
294 |
+
| 0.3129 | 6600 | 0.0 | - |
|
295 |
+
| 0.3153 | 6650 | 0.0 | - |
|
296 |
+
| 0.3176 | 6700 | 0.0 | - |
|
297 |
+
| 0.3200 | 6750 | 0.0 | - |
|
298 |
+
| 0.3224 | 6800 | 0.0 | - |
|
299 |
+
| 0.3247 | 6850 | 0.0 | - |
|
300 |
+
| 0.3271 | 6900 | 0.0 | - |
|
301 |
+
| 0.3295 | 6950 | 0.0 | - |
|
302 |
+
| 0.3318 | 7000 | 0.0 | - |
|
303 |
+
| 0.3342 | 7050 | 0.0 | - |
|
304 |
+
| 0.3366 | 7100 | 0.0 | - |
|
305 |
+
| 0.3390 | 7150 | 0.0011 | - |
|
306 |
+
| 0.3413 | 7200 | 0.0002 | - |
|
307 |
+
| 0.3437 | 7250 | 0.0 | - |
|
308 |
+
| 0.3461 | 7300 | 0.0 | - |
|
309 |
+
| 0.3484 | 7350 | 0.0001 | - |
|
310 |
+
| 0.3508 | 7400 | 0.0001 | - |
|
311 |
+
| 0.3532 | 7450 | 0.0002 | - |
|
312 |
+
| 0.3556 | 7500 | 0.0 | - |
|
313 |
+
| 0.3579 | 7550 | 0.0 | - |
|
314 |
+
| 0.3603 | 7600 | 0.0 | - |
|
315 |
+
| 0.3627 | 7650 | 0.0 | - |
|
316 |
+
| 0.3650 | 7700 | 0.0 | - |
|
317 |
+
| 0.3674 | 7750 | 0.0 | - |
|
318 |
+
| 0.3698 | 7800 | 0.0001 | - |
|
319 |
+
| 0.3721 | 7850 | 0.0 | - |
|
320 |
+
| 0.3745 | 7900 | 0.0 | - |
|
321 |
+
| 0.3769 | 7950 | 0.0 | - |
|
322 |
+
| 0.3793 | 8000 | 0.0 | - |
|
323 |
+
| 0.3816 | 8050 | 0.0 | - |
|
324 |
+
| 0.3840 | 8100 | 0.0 | - |
|
325 |
+
| 0.3864 | 8150 | 0.0 | - |
|
326 |
+
| 0.3887 | 8200 | 0.0 | - |
|
327 |
+
| 0.3911 | 8250 | 0.0 | - |
|
328 |
+
| 0.3935 | 8300 | 0.0 | - |
|
329 |
+
| 0.3958 | 8350 | 0.0 | - |
|
330 |
+
| 0.3982 | 8400 | 0.0 | - |
|
331 |
+
| 0.4006 | 8450 | 0.0 | - |
|
332 |
+
| 0.4030 | 8500 | 0.0 | - |
|
333 |
+
| 0.4053 | 8550 | 0.0001 | - |
|
334 |
+
| 0.4077 | 8600 | 0.0001 | - |
|
335 |
+
| 0.4101 | 8650 | 0.0008 | - |
|
336 |
+
| 0.4124 | 8700 | 0.0001 | - |
|
337 |
+
| 0.4148 | 8750 | 0.0 | - |
|
338 |
+
| 0.4172 | 8800 | 0.0 | - |
|
339 |
+
| 0.4196 | 8850 | 0.0001 | - |
|
340 |
+
| 0.4219 | 8900 | 0.0 | - |
|
341 |
+
| 0.4243 | 8950 | 0.0 | - |
|
342 |
+
| 0.4267 | 9000 | 0.0 | - |
|
343 |
+
| 0.4290 | 9050 | 0.0 | - |
|
344 |
+
| 0.4314 | 9100 | 0.0 | - |
|
345 |
+
| 0.4338 | 9150 | 0.0 | - |
|
346 |
+
| 0.4361 | 9200 | 0.0 | - |
|
347 |
+
| 0.4385 | 9250 | 0.0 | - |
|
348 |
+
| 0.4409 | 9300 | 0.0 | - |
|
349 |
+
| 0.4433 | 9350 | 0.0 | - |
|
350 |
+
| 0.4456 | 9400 | 0.0 | - |
|
351 |
+
| 0.4480 | 9450 | 0.0 | - |
|
352 |
+
| 0.4504 | 9500 | 0.0 | - |
|
353 |
+
| 0.4527 | 9550 | 0.0 | - |
|
354 |
+
| 0.4551 | 9600 | 0.0 | - |
|
355 |
+
| 0.4575 | 9650 | 0.0 | - |
|
356 |
+
| 0.4598 | 9700 | 0.0 | - |
|
357 |
+
| 0.4622 | 9750 | 0.0001 | - |
|
358 |
+
| 0.4646 | 9800 | 0.0 | - |
|
359 |
+
| 0.4670 | 9850 | 0.0 | - |
|
360 |
+
| 0.4693 | 9900 | 0.0 | - |
|
361 |
+
| 0.4717 | 9950 | 0.0 | - |
|
362 |
+
| 0.4741 | 10000 | 0.0 | - |
|
363 |
+
| 0.4764 | 10050 | 0.0 | - |
|
364 |
+
| 0.4788 | 10100 | 0.0006 | - |
|
365 |
+
| 0.4812 | 10150 | 0.0 | - |
|
366 |
+
| 0.4835 | 10200 | 0.0 | - |
|
367 |
+
| 0.4859 | 10250 | 0.0 | - |
|
368 |
+
| 0.4883 | 10300 | 0.0 | - |
|
369 |
+
| 0.4907 | 10350 | 0.0 | - |
|
370 |
+
| 0.4930 | 10400 | 0.0 | - |
|
371 |
+
| 0.4954 | 10450 | 0.0 | - |
|
372 |
+
| 0.4978 | 10500 | 0.0 | - |
|
373 |
+
| 0.5001 | 10550 | 0.0 | - |
|
374 |
+
| 0.5025 | 10600 | 0.0 | - |
|
375 |
+
| 0.5049 | 10650 | 0.0 | - |
|
376 |
+
| 0.5073 | 10700 | 0.0 | - |
|
377 |
+
| 0.5096 | 10750 | 0.0 | - |
|
378 |
+
| 0.5120 | 10800 | 0.0 | - |
|
379 |
+
| 0.5144 | 10850 | 0.0 | - |
|
380 |
+
| 0.5167 | 10900 | 0.0 | - |
|
381 |
+
| 0.5191 | 10950 | 0.0 | - |
|
382 |
+
| 0.5215 | 11000 | 0.0 | - |
|
383 |
+
| 0.5238 | 11050 | 0.0 | - |
|
384 |
+
| 0.5262 | 11100 | 0.0 | - |
|
385 |
+
| 0.5286 | 11150 | 0.0 | - |
|
386 |
+
| 0.5310 | 11200 | 0.0 | - |
|
387 |
+
| 0.5333 | 11250 | 0.0 | - |
|
388 |
+
| 0.5357 | 11300 | 0.0 | - |
|
389 |
+
| 0.5381 | 11350 | 0.0 | - |
|
390 |
+
| 0.5404 | 11400 | 0.0 | - |
|
391 |
+
| 0.5428 | 11450 | 0.0 | - |
|
392 |
+
| 0.5452 | 11500 | 0.0 | - |
|
393 |
+
| 0.5475 | 11550 | 0.0 | - |
|
394 |
+
| 0.5499 | 11600 | 0.0 | - |
|
395 |
+
| 0.5523 | 11650 | 0.0001 | - |
|
396 |
+
| 0.5547 | 11700 | 0.0 | - |
|
397 |
+
| 0.5570 | 11750 | 0.0043 | - |
|
398 |
+
| 0.5594 | 11800 | 0.0 | - |
|
399 |
+
| 0.5618 | 11850 | 0.0 | - |
|
400 |
+
| 0.5641 | 11900 | 0.0 | - |
|
401 |
+
| 0.5665 | 11950 | 0.0 | - |
|
402 |
+
| 0.5689 | 12000 | 0.0 | - |
|
403 |
+
| 0.5713 | 12050 | 0.0 | - |
|
404 |
+
| 0.5736 | 12100 | 0.0 | - |
|
405 |
+
| 0.5760 | 12150 | 0.0 | - |
|
406 |
+
| 0.5784 | 12200 | 0.0 | - |
|
407 |
+
| 0.5807 | 12250 | 0.0029 | - |
|
408 |
+
| 0.5831 | 12300 | 0.0 | - |
|
409 |
+
| 0.5855 | 12350 | 0.0 | - |
|
410 |
+
| 0.5878 | 12400 | 0.0 | - |
|
411 |
+
| 0.5902 | 12450 | 0.0 | - |
|
412 |
+
| 0.5926 | 12500 | 0.0 | - |
|
413 |
+
| 0.5950 | 12550 | 0.0 | - |
|
414 |
+
| 0.5973 | 12600 | 0.0 | - |
|
415 |
+
| 0.5997 | 12650 | 0.0 | - |
|
416 |
+
| 0.6021 | 12700 | 0.0 | - |
|
417 |
+
| 0.6044 | 12750 | 0.0 | - |
|
418 |
+
| 0.6068 | 12800 | 0.0 | - |
|
419 |
+
| 0.6092 | 12850 | 0.0 | - |
|
420 |
+
| 0.6115 | 12900 | 0.0 | - |
|
421 |
+
| 0.6139 | 12950 | 0.0 | - |
|
422 |
+
| 0.6163 | 13000 | 0.0 | - |
|
423 |
+
| 0.6187 | 13050 | 0.0 | - |
|
424 |
+
| 0.6210 | 13100 | 0.0 | - |
|
425 |
+
| 0.6234 | 13150 | 0.0001 | - |
|
426 |
+
| 0.6258 | 13200 | 0.0 | - |
|
427 |
+
| 0.6281 | 13250 | 0.0 | - |
|
428 |
+
| 0.6305 | 13300 | 0.0 | - |
|
429 |
+
| 0.6329 | 13350 | 0.0 | - |
|
430 |
+
| 0.6353 | 13400 | 0.0001 | - |
|
431 |
+
| 0.6376 | 13450 | 0.0 | - |
|
432 |
+
| 0.6400 | 13500 | 0.0 | - |
|
433 |
+
| 0.6424 | 13550 | 0.0 | - |
|
434 |
+
| 0.6447 | 13600 | 0.0 | - |
|
435 |
+
| 0.6471 | 13650 | 0.0 | - |
|
436 |
+
| 0.6495 | 13700 | 0.0 | - |
|
437 |
+
| 0.6518 | 13750 | 0.0 | - |
|
438 |
+
| 0.6542 | 13800 | 0.0 | - |
|
439 |
+
| 0.6566 | 13850 | 0.0 | - |
|
440 |
+
| 0.6590 | 13900 | 0.0 | - |
|
441 |
+
| 0.6613 | 13950 | 0.0 | - |
|
442 |
+
| 0.6637 | 14000 | 0.0 | - |
|
443 |
+
| 0.6661 | 14050 | 0.0 | - |
|
444 |
+
| 0.6684 | 14100 | 0.0 | - |
|
445 |
+
| 0.6708 | 14150 | 0.0 | - |
|
446 |
+
| 0.6732 | 14200 | 0.0 | - |
|
447 |
+
| 0.6755 | 14250 | 0.0 | - |
|
448 |
+
| 0.6779 | 14300 | 0.0 | - |
|
449 |
+
| 0.6803 | 14350 | 0.0 | - |
|
450 |
+
| 0.6827 | 14400 | 0.0 | - |
|
451 |
+
| 0.6850 | 14450 | 0.0 | - |
|
452 |
+
| 0.6874 | 14500 | 0.0 | - |
|
453 |
+
| 0.6898 | 14550 | 0.0 | - |
|
454 |
+
| 0.6921 | 14600 | 0.0 | - |
|
455 |
+
| 0.6945 | 14650 | 0.0 | - |
|
456 |
+
| 0.6969 | 14700 | 0.0 | - |
|
457 |
+
| 0.6993 | 14750 | 0.0 | - |
|
458 |
+
| 0.7016 | 14800 | 0.0 | - |
|
459 |
+
| 0.7040 | 14850 | 0.0 | - |
|
460 |
+
| 0.7064 | 14900 | 0.0 | - |
|
461 |
+
| 0.7087 | 14950 | 0.0 | - |
|
462 |
+
| 0.7111 | 15000 | 0.0 | - |
|
463 |
+
| 0.7135 | 15050 | 0.0 | - |
|
464 |
+
| 0.7158 | 15100 | 0.0 | - |
|
465 |
+
| 0.7182 | 15150 | 0.0 | - |
|
466 |
+
| 0.7206 | 15200 | 0.0 | - |
|
467 |
+
| 0.7230 | 15250 | 0.0 | - |
|
468 |
+
| 0.7253 | 15300 | 0.0 | - |
|
469 |
+
| 0.7277 | 15350 | 0.0 | - |
|
470 |
+
| 0.7301 | 15400 | 0.0 | - |
|
471 |
+
| 0.7324 | 15450 | 0.0 | - |
|
472 |
+
| 0.7348 | 15500 | 0.0 | - |
|
473 |
+
| 0.7372 | 15550 | 0.0 | - |
|
474 |
+
| 0.7395 | 15600 | 0.0 | - |
|
475 |
+
| 0.7419 | 15650 | 0.0 | - |
|
476 |
+
| 0.7443 | 15700 | 0.0 | - |
|
477 |
+
| 0.7467 | 15750 | 0.0 | - |
|
478 |
+
| 0.7490 | 15800 | 0.0 | - |
|
479 |
+
| 0.7514 | 15850 | 0.0 | - |
|
480 |
+
| 0.7538 | 15900 | 0.0 | - |
|
481 |
+
| 0.7561 | 15950 | 0.0 | - |
|
482 |
+
| 0.7585 | 16000 | 0.0 | - |
|
483 |
+
| 0.7609 | 16050 | 0.0 | - |
|
484 |
+
| 0.7633 | 16100 | 0.0 | - |
|
485 |
+
| 0.7656 | 16150 | 0.0 | - |
|
486 |
+
| 0.7680 | 16200 | 0.0 | - |
|
487 |
+
| 0.7704 | 16250 | 0.0 | - |
|
488 |
+
| 0.7727 | 16300 | 0.0 | - |
|
489 |
+
| 0.7751 | 16350 | 0.0 | - |
|
490 |
+
| 0.7775 | 16400 | 0.0 | - |
|
491 |
+
| 0.7798 | 16450 | 0.0 | - |
|
492 |
+
| 0.7822 | 16500 | 0.0 | - |
|
493 |
+
| 0.7846 | 16550 | 0.0 | - |
|
494 |
+
| 0.7870 | 16600 | 0.0 | - |
|
495 |
+
| 0.7893 | 16650 | 0.0 | - |
|
496 |
+
| 0.7917 | 16700 | 0.0 | - |
|
497 |
+
| 0.7941 | 16750 | 0.0 | - |
|
498 |
+
| 0.7964 | 16800 | 0.0 | - |
|
499 |
+
| 0.7988 | 16850 | 0.0 | - |
|
500 |
+
| 0.8012 | 16900 | 0.0 | - |
|
501 |
+
| 0.8035 | 16950 | 0.0 | - |
|
502 |
+
| 0.8059 | 17000 | 0.0 | - |
|
503 |
+
| 0.8083 | 17050 | 0.0 | - |
|
504 |
+
| 0.8107 | 17100 | 0.0 | - |
|
505 |
+
| 0.8130 | 17150 | 0.0 | - |
|
506 |
+
| 0.8154 | 17200 | 0.0 | - |
|
507 |
+
| 0.8178 | 17250 | 0.0 | - |
|
508 |
+
| 0.8201 | 17300 | 0.0 | - |
|
509 |
+
| 0.8225 | 17350 | 0.0 | - |
|
510 |
+
| 0.8249 | 17400 | 0.0 | - |
|
511 |
+
| 0.8272 | 17450 | 0.0 | - |
|
512 |
+
| 0.8296 | 17500 | 0.0 | - |
|
513 |
+
| 0.8320 | 17550 | 0.0 | - |
|
514 |
+
| 0.8344 | 17600 | 0.0 | - |
|
515 |
+
| 0.8367 | 17650 | 0.0 | - |
|
516 |
+
| 0.8391 | 17700 | 0.0 | - |
|
517 |
+
| 0.8415 | 17750 | 0.0 | - |
|
518 |
+
| 0.8438 | 17800 | 0.0 | - |
|
519 |
+
| 0.8462 | 17850 | 0.0 | - |
|
520 |
+
| 0.8486 | 17900 | 0.0 | - |
|
521 |
+
| 0.8510 | 17950 | 0.0 | - |
|
522 |
+
| 0.8533 | 18000 | 0.0 | - |
|
523 |
+
| 0.8557 | 18050 | 0.0 | - |
|
524 |
+
| 0.8581 | 18100 | 0.0 | - |
|
525 |
+
| 0.8604 | 18150 | 0.0 | - |
|
526 |
+
| 0.8628 | 18200 | 0.0 | - |
|
527 |
+
| 0.8652 | 18250 | 0.0 | - |
|
528 |
+
| 0.8675 | 18300 | 0.0 | - |
|
529 |
+
| 0.8699 | 18350 | 0.0 | - |
|
530 |
+
| 0.8723 | 18400 | 0.0 | - |
|
531 |
+
| 0.8747 | 18450 | 0.0 | - |
|
532 |
+
| 0.8770 | 18500 | 0.0 | - |
|
533 |
+
| 0.8794 | 18550 | 0.0 | - |
|
534 |
+
| 0.8818 | 18600 | 0.0 | - |
|
535 |
+
| 0.8841 | 18650 | 0.0 | - |
|
536 |
+
| 0.8865 | 18700 | 0.0 | - |
|
537 |
+
| 0.8889 | 18750 | 0.0 | - |
|
538 |
+
| 0.8912 | 18800 | 0.0 | - |
|
539 |
+
| 0.8936 | 18850 | 0.0 | - |
|
540 |
+
| 0.8960 | 18900 | 0.0 | - |
|
541 |
+
| 0.8984 | 18950 | 0.0 | - |
|
542 |
+
| 0.9007 | 19000 | 0.0 | - |
|
543 |
+
| 0.9031 | 19050 | 0.0 | - |
|
544 |
+
| 0.9055 | 19100 | 0.0 | - |
|
545 |
+
| 0.9078 | 19150 | 0.0 | - |
|
546 |
+
| 0.9102 | 19200 | 0.0 | - |
|
547 |
+
| 0.9126 | 19250 | 0.0 | - |
|
548 |
+
| 0.9150 | 19300 | 0.0 | - |
|
549 |
+
| 0.9173 | 19350 | 0.0 | - |
|
550 |
+
| 0.9197 | 19400 | 0.0 | - |
|
551 |
+
| 0.9221 | 19450 | 0.0 | - |
|
552 |
+
| 0.9244 | 19500 | 0.0 | - |
|
553 |
+
| 0.9268 | 19550 | 0.0 | - |
|
554 |
+
| 0.9292 | 19600 | 0.0 | - |
|
555 |
+
| 0.9315 | 19650 | 0.0 | - |
|
556 |
+
| 0.9339 | 19700 | 0.0 | - |
|
557 |
+
| 0.9363 | 19750 | 0.0 | - |
|
558 |
+
| 0.9387 | 19800 | 0.0 | - |
|
559 |
+
| 0.9410 | 19850 | 0.0 | - |
|
560 |
+
| 0.9434 | 19900 | 0.0 | - |
|
561 |
+
| 0.9458 | 19950 | 0.0 | - |
|
562 |
+
| 0.9481 | 20000 | 0.0 | - |
|
563 |
+
| 0.9505 | 20050 | 0.0 | - |
|
564 |
+
| 0.9529 | 20100 | 0.0 | - |
|
565 |
+
| 0.9552 | 20150 | 0.0 | - |
|
566 |
+
| 0.9576 | 20200 | 0.0 | - |
|
567 |
+
| 0.9600 | 20250 | 0.0 | - |
|
568 |
+
| 0.9624 | 20300 | 0.0 | - |
|
569 |
+
| 0.9647 | 20350 | 0.0 | - |
|
570 |
+
| 0.9671 | 20400 | 0.0 | - |
|
571 |
+
| 0.9695 | 20450 | 0.0 | - |
|
572 |
+
| 0.9718 | 20500 | 0.0 | - |
|
573 |
+
| 0.9742 | 20550 | 0.0 | - |
|
574 |
+
| 0.9766 | 20600 | 0.0 | - |
|
575 |
+
| 0.9790 | 20650 | 0.0 | - |
|
576 |
+
| 0.9813 | 20700 | 0.0 | - |
|
577 |
+
| 0.9837 | 20750 | 0.0 | - |
|
578 |
+
| 0.9861 | 20800 | 0.0 | - |
|
579 |
+
| 0.9884 | 20850 | 0.0 | - |
|
580 |
+
| 0.9908 | 20900 | 0.0 | - |
|
581 |
+
| 0.9932 | 20950 | 0.0 | - |
|
582 |
+
| 0.9955 | 21000 | 0.0 | - |
|
583 |
+
| 0.9979 | 21050 | 0.0 | - |
|
584 |
+
| **1.0** | **21094** | **-** | **0.2251** |
|
585 |
+
|
586 |
+
* The bold row denotes the saved checkpoint.
|
587 |
+
### Framework Versions
|
588 |
+
- Python: 3.10.13
|
589 |
+
- SetFit: 1.0.3
|
590 |
+
- Sentence Transformers: 2.2.2
|
591 |
+
- Transformers: 4.36.2
|
592 |
+
- PyTorch: 2.1.2+cu121
|
593 |
+
- Datasets: 2.16.1
|
594 |
+
- Tokenizers: 0.15.0
|
595 |
+
|
596 |
+
## Citation
|
597 |
+
|
598 |
+
### BibTeX
|
599 |
+
```bibtex
|
600 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
601 |
+
doi = {10.48550/ARXIV.2209.11055},
|
602 |
+
url = {https://arxiv.org/abs/2209.11055},
|
603 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
604 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
605 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
606 |
+
publisher = {arXiv},
|
607 |
+
year = {2022},
|
608 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
609 |
+
}
|
610 |
+
```
|
611 |
+
|
612 |
+
<!--
|
613 |
+
## Glossary
|
614 |
+
|
615 |
+
*Clearly define terms in order to be accessible across audiences.*
|
616 |
+
-->
|
617 |
+
|
618 |
+
<!--
|
619 |
+
## Model Card Authors
|
620 |
+
|
621 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
622 |
+
-->
|
623 |
+
|
624 |
+
<!--
|
625 |
+
## Model Card Contact
|
626 |
+
|
627 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
628 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints/step_21094/",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertModel"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0,
|
24 |
+
"LABEL_1": 1,
|
25 |
+
"LABEL_2": 2,
|
26 |
+
"LABEL_3": 3,
|
27 |
+
"LABEL_4": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"pooler_fc_size": 768,
|
37 |
+
"pooler_num_attention_heads": 12,
|
38 |
+
"pooler_num_fc_layers": 3,
|
39 |
+
"pooler_size_per_head": 128,
|
40 |
+
"pooler_type": "first_token_transform",
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.36.2",
|
44 |
+
"type_vocab_size": 2,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 50000
|
47 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.20.1",
|
5 |
+
"pytorch": "1.11.0"
|
6 |
+
}
|
7 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": [
|
3 |
+
"kesedihan",
|
4 |
+
"sukacita",
|
5 |
+
"cinta",
|
6 |
+
"amarah",
|
7 |
+
"takut",
|
8 |
+
"kejutan"
|
9 |
+
],
|
10 |
+
"normalize_embeddings": false
|
11 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9746f47e90cf0e3c0fe3ff272208e989c11b1b86906723ad2e2c0eab0fdb3eda
|
3 |
+
size 497787752
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6916804f1dc446c169e25c5ffa25b10f8ff68c40e1ffe28a2f2ca5eaafff4085
|
3 |
+
size 37799
|
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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|