richie-ghost
commited on
Commit
•
bf92c62
1
Parent(s):
c993e88
Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +527 -0
- config.json +27 -0
- config_sentence_transformers.json +9 -0
- config_setfit.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.json +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
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 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,527 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
base_model: FacebookAI/roberta-large
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
widget:
|
12 |
+
- text: Just checking in, how have you been feeling since our last chat?
|
13 |
+
- text: I’m looking forward to learning more from you.
|
14 |
+
- text: Take it easy!
|
15 |
+
- text: It was great seeing you. Let's catch up again soon!
|
16 |
+
- text: Let’s make sure you’re not carrying too much; how are you?
|
17 |
+
pipeline_tag: text-classification
|
18 |
+
inference: true
|
19 |
+
model-index:
|
20 |
+
- name: SetFit with FacebookAI/roberta-large
|
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: 0.96
|
32 |
+
name: Accuracy
|
33 |
+
---
|
34 |
+
|
35 |
+
# SetFit with FacebookAI/roberta-large
|
36 |
+
|
37 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) 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.
|
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 body:** [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large)
|
49 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
50 |
+
- **Maximum Sequence Length:** 512 tokens
|
51 |
+
- **Number of Classes:** 2 classes
|
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 |
+
### Model Labels
|
63 |
+
| Label | Examples |
|
64 |
+
|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
65 |
+
| true | <ul><li>'See you soon!'</li><li>'You look well!'</li><li>'Your journey is quite inspiring, can you share more about it?'</li></ul> |
|
66 |
+
| false | <ul><li>'What are the core components of your business model?'</li><li>'How do you balance your personal and professional life?'</li><li>"There is a situation where a daughter of a narcissistic mother denigrated the father. When the mother complained to the daughter about the father and how poor he was a a husband and person and how badly he treated the wife. The mother's claims were inaccurate and overblown. The mother said I inappropriate things to the daughter such as he flirted with other women, or the mother could have done much better than marrying him. After such episodes, the daughter was dismissive and rude to the father. What are the signs of parental alienation and what are the impacts on a daughter growing up and as an adult?"</li></ul> |
|
67 |
+
|
68 |
+
## Evaluation
|
69 |
+
|
70 |
+
### Metrics
|
71 |
+
| Label | Accuracy |
|
72 |
+
|:--------|:---------|
|
73 |
+
| **all** | 0.96 |
|
74 |
+
|
75 |
+
## Uses
|
76 |
+
|
77 |
+
### Direct Use for Inference
|
78 |
+
|
79 |
+
First install the SetFit library:
|
80 |
+
|
81 |
+
```bash
|
82 |
+
pip install setfit
|
83 |
+
```
|
84 |
+
|
85 |
+
Then you can load this model and run inference.
|
86 |
+
|
87 |
+
```python
|
88 |
+
from setfit import SetFitModel
|
89 |
+
|
90 |
+
# Download from the 🤗 Hub
|
91 |
+
model = SetFitModel.from_pretrained("richie-ghost/setfit-FacebookAI-roberta-large-phatic")
|
92 |
+
# Run inference
|
93 |
+
preds = model("Take it easy!")
|
94 |
+
```
|
95 |
+
|
96 |
+
<!--
|
97 |
+
### Downstream Use
|
98 |
+
|
99 |
+
*List how someone could finetune this model on their own dataset.*
|
100 |
+
-->
|
101 |
+
|
102 |
+
<!--
|
103 |
+
### Out-of-Scope Use
|
104 |
+
|
105 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
106 |
+
-->
|
107 |
+
|
108 |
+
<!--
|
109 |
+
## Bias, Risks and Limitations
|
110 |
+
|
111 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
112 |
+
-->
|
113 |
+
|
114 |
+
<!--
|
115 |
+
### Recommendations
|
116 |
+
|
117 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
118 |
+
-->
|
119 |
+
|
120 |
+
## Training Details
|
121 |
+
|
122 |
+
### Training Set Metrics
|
123 |
+
| Training set | Min | Median | Max |
|
124 |
+
|:-------------|:----|:-------|:----|
|
125 |
+
| Word count | 1 | 9.8722 | 108 |
|
126 |
+
|
127 |
+
| Label | Training Sample Count |
|
128 |
+
|:------|:----------------------|
|
129 |
+
| false | 191 |
|
130 |
+
| true | 169 |
|
131 |
+
|
132 |
+
### Training Hyperparameters
|
133 |
+
- batch_size: (16, 16)
|
134 |
+
- num_epochs: (4, 4)
|
135 |
+
- max_steps: -1
|
136 |
+
- sampling_strategy: oversampling
|
137 |
+
- body_learning_rate: (2e-05, 1e-05)
|
138 |
+
- head_learning_rate: 0.01
|
139 |
+
- loss: CosineSimilarityLoss
|
140 |
+
- distance_metric: cosine_distance
|
141 |
+
- margin: 0.25
|
142 |
+
- end_to_end: False
|
143 |
+
- use_amp: False
|
144 |
+
- warmup_proportion: 0.1
|
145 |
+
- seed: 42
|
146 |
+
- eval_max_steps: -1
|
147 |
+
- load_best_model_at_end: True
|
148 |
+
|
149 |
+
### Training Results
|
150 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
151 |
+
|:-------:|:--------:|:-------------:|:---------------:|
|
152 |
+
| 0.0002 | 1 | 0.4745 | - |
|
153 |
+
| 0.0122 | 50 | 0.441 | - |
|
154 |
+
| 0.0245 | 100 | 0.4422 | - |
|
155 |
+
| 0.0367 | 150 | 0.2339 | - |
|
156 |
+
| 0.0489 | 200 | 0.1182 | - |
|
157 |
+
| 0.0612 | 250 | 0.0806 | - |
|
158 |
+
| 0.0734 | 300 | 0.1183 | - |
|
159 |
+
| 0.0856 | 350 | 0.0551 | - |
|
160 |
+
| 0.0978 | 400 | 0.0146 | - |
|
161 |
+
| 0.1101 | 450 | 0.0115 | - |
|
162 |
+
| 0.1223 | 500 | 0.0042 | - |
|
163 |
+
| 0.1345 | 550 | 0.0053 | - |
|
164 |
+
| 0.1468 | 600 | 0.0021 | - |
|
165 |
+
| 0.1590 | 650 | 0.0596 | - |
|
166 |
+
| 0.1712 | 700 | 0.0029 | - |
|
167 |
+
| 0.1835 | 750 | 0.0009 | - |
|
168 |
+
| 0.1957 | 800 | 0.0002 | - |
|
169 |
+
| 0.2079 | 850 | 0.0005 | - |
|
170 |
+
| 0.2202 | 900 | 0.0013 | - |
|
171 |
+
| 0.2324 | 950 | 0.0008 | - |
|
172 |
+
| 0.2446 | 1000 | 0.0004 | - |
|
173 |
+
| 0.2568 | 1050 | 0.0004 | - |
|
174 |
+
| 0.2691 | 1100 | 0.0004 | - |
|
175 |
+
| 0.2813 | 1150 | 0.0003 | - |
|
176 |
+
| 0.2935 | 1200 | 0.0003 | - |
|
177 |
+
| 0.3058 | 1250 | 0.0012 | - |
|
178 |
+
| 0.3180 | 1300 | 0.0001 | - |
|
179 |
+
| 0.3302 | 1350 | 0.0002 | - |
|
180 |
+
| 0.3425 | 1400 | 0.0003 | - |
|
181 |
+
| 0.3547 | 1450 | 0.0024 | - |
|
182 |
+
| 0.3669 | 1500 | 0.0008 | - |
|
183 |
+
| 0.3792 | 1550 | 0.0015 | - |
|
184 |
+
| 0.3914 | 1600 | 0.0002 | - |
|
185 |
+
| 0.4036 | 1650 | 0.0002 | - |
|
186 |
+
| 0.4159 | 1700 | 0.1842 | - |
|
187 |
+
| 0.4281 | 1750 | 0.0009 | - |
|
188 |
+
| 0.4403 | 1800 | 0.0001 | - |
|
189 |
+
| 0.4525 | 1850 | 0.0013 | - |
|
190 |
+
| 0.4648 | 1900 | 0.0637 | - |
|
191 |
+
| 0.4770 | 1950 | 0.0002 | - |
|
192 |
+
| 0.4892 | 2000 | 0.0007 | - |
|
193 |
+
| 0.5015 | 2050 | 0.0001 | - |
|
194 |
+
| 0.5137 | 2100 | 0.0 | - |
|
195 |
+
| 0.5259 | 2150 | 0.0 | - |
|
196 |
+
| 0.5382 | 2200 | 0.0 | - |
|
197 |
+
| 0.5504 | 2250 | 0.0 | - |
|
198 |
+
| 0.5626 | 2300 | 0.0001 | - |
|
199 |
+
| 0.5749 | 2350 | 0.0 | - |
|
200 |
+
| 0.5871 | 2400 | 0.0 | - |
|
201 |
+
| 0.5993 | 2450 | 0.0 | - |
|
202 |
+
| 0.6115 | 2500 | 0.0 | - |
|
203 |
+
| 0.6238 | 2550 | 0.0 | - |
|
204 |
+
| 0.6360 | 2600 | 0.0 | - |
|
205 |
+
| 0.6482 | 2650 | 0.0 | - |
|
206 |
+
| 0.6605 | 2700 | 0.0001 | - |
|
207 |
+
| 0.6727 | 2750 | 0.0 | - |
|
208 |
+
| 0.6849 | 2800 | 0.0 | - |
|
209 |
+
| 0.6972 | 2850 | 0.0 | - |
|
210 |
+
| 0.7094 | 2900 | 0.0 | - |
|
211 |
+
| 0.7216 | 2950 | 0.0 | - |
|
212 |
+
| 0.7339 | 3000 | 0.0 | - |
|
213 |
+
| 0.7461 | 3050 | 0.0 | - |
|
214 |
+
| 0.7583 | 3100 | 0.0001 | - |
|
215 |
+
| 0.7705 | 3150 | 0.0 | - |
|
216 |
+
| 0.7828 | 3200 | 0.0 | - |
|
217 |
+
| 0.7950 | 3250 | 0.0 | - |
|
218 |
+
| 0.8072 | 3300 | 0.0 | - |
|
219 |
+
| 0.8195 | 3350 | 0.0 | - |
|
220 |
+
| 0.8317 | 3400 | 0.0 | - |
|
221 |
+
| 0.8439 | 3450 | 0.0001 | - |
|
222 |
+
| 0.8562 | 3500 | 0.0 | - |
|
223 |
+
| 0.8684 | 3550 | 0.0 | - |
|
224 |
+
| 0.8806 | 3600 | 0.0 | - |
|
225 |
+
| 0.8929 | 3650 | 0.0 | - |
|
226 |
+
| 0.9051 | 3700 | 0.0 | - |
|
227 |
+
| 0.9173 | 3750 | 0.0 | - |
|
228 |
+
| 0.9295 | 3800 | 0.0 | - |
|
229 |
+
| 0.9418 | 3850 | 0.0 | - |
|
230 |
+
| 0.9540 | 3900 | 0.0 | - |
|
231 |
+
| 0.9662 | 3950 | 0.0 | - |
|
232 |
+
| 0.9785 | 4000 | 0.0 | - |
|
233 |
+
| 0.9907 | 4050 | 0.0 | - |
|
234 |
+
| **1.0** | **4088** | **-** | **0.0815** |
|
235 |
+
| 1.0029 | 4100 | 0.0 | - |
|
236 |
+
| 1.0152 | 4150 | 0.0 | - |
|
237 |
+
| 1.0274 | 4200 | 0.0 | - |
|
238 |
+
| 1.0396 | 4250 | 0.0 | - |
|
239 |
+
| 1.0519 | 4300 | 0.0 | - |
|
240 |
+
| 1.0641 | 4350 | 0.0 | - |
|
241 |
+
| 1.0763 | 4400 | 0.0 | - |
|
242 |
+
| 1.0886 | 4450 | 0.0 | - |
|
243 |
+
| 1.1008 | 4500 | 0.0 | - |
|
244 |
+
| 1.1130 | 4550 | 0.0 | - |
|
245 |
+
| 1.1252 | 4600 | 0.0 | - |
|
246 |
+
| 1.1375 | 4650 | 0.0 | - |
|
247 |
+
| 1.1497 | 4700 | 0.0 | - |
|
248 |
+
| 1.1619 | 4750 | 0.0 | - |
|
249 |
+
| 1.1742 | 4800 | 0.0 | - |
|
250 |
+
| 1.1864 | 4850 | 0.0 | - |
|
251 |
+
| 1.1986 | 4900 | 0.0 | - |
|
252 |
+
| 1.2109 | 4950 | 0.0 | - |
|
253 |
+
| 1.2231 | 5000 | 0.0 | - |
|
254 |
+
| 1.2353 | 5050 | 0.0 | - |
|
255 |
+
| 1.2476 | 5100 | 0.0 | - |
|
256 |
+
| 1.2598 | 5150 | 0.0 | - |
|
257 |
+
| 1.2720 | 5200 | 0.0 | - |
|
258 |
+
| 1.2842 | 5250 | 0.0 | - |
|
259 |
+
| 1.2965 | 5300 | 0.0 | - |
|
260 |
+
| 1.3087 | 5350 | 0.0 | - |
|
261 |
+
| 1.3209 | 5400 | 0.0 | - |
|
262 |
+
| 1.3332 | 5450 | 0.0 | - |
|
263 |
+
| 1.3454 | 5500 | 0.0 | - |
|
264 |
+
| 1.3576 | 5550 | 0.0 | - |
|
265 |
+
| 1.3699 | 5600 | 0.0 | - |
|
266 |
+
| 1.3821 | 5650 | 0.0 | - |
|
267 |
+
| 1.3943 | 5700 | 0.0 | - |
|
268 |
+
| 1.4066 | 5750 | 0.0 | - |
|
269 |
+
| 1.4188 | 5800 | 0.0 | - |
|
270 |
+
| 1.4310 | 5850 | 0.0 | - |
|
271 |
+
| 1.4432 | 5900 | 0.0 | - |
|
272 |
+
| 1.4555 | 5950 | 0.0 | - |
|
273 |
+
| 1.4677 | 6000 | 0.0 | - |
|
274 |
+
| 1.4799 | 6050 | 0.0 | - |
|
275 |
+
| 1.4922 | 6100 | 0.0 | - |
|
276 |
+
| 1.5044 | 6150 | 0.0112 | - |
|
277 |
+
| 1.5166 | 6200 | 0.4712 | - |
|
278 |
+
| 1.5289 | 6250 | 0.3977 | - |
|
279 |
+
| 1.5411 | 6300 | 0.2112 | - |
|
280 |
+
| 1.5533 | 6350 | 0.318 | - |
|
281 |
+
| 1.5656 | 6400 | 0.2523 | - |
|
282 |
+
| 1.5778 | 6450 | 0.2829 | - |
|
283 |
+
| 1.5900 | 6500 | 0.2736 | - |
|
284 |
+
| 1.6023 | 6550 | 0.2493 | - |
|
285 |
+
| 1.6145 | 6600 | 0.3112 | - |
|
286 |
+
| 1.6267 | 6650 | 0.2291 | - |
|
287 |
+
| 1.6389 | 6700 | 0.2855 | - |
|
288 |
+
| 1.6512 | 6750 | 0.2642 | - |
|
289 |
+
| 1.6634 | 6800 | 0.2376 | - |
|
290 |
+
| 1.6756 | 6850 | 0.2983 | - |
|
291 |
+
| 1.6879 | 6900 | 0.2853 | - |
|
292 |
+
| 1.7001 | 6950 | 0.3095 | - |
|
293 |
+
| 1.7123 | 7000 | 0.2497 | - |
|
294 |
+
| 1.7246 | 7050 | 0.2305 | - |
|
295 |
+
| 1.7368 | 7100 | 0.2433 | - |
|
296 |
+
| 1.7490 | 7150 | 0.2505 | - |
|
297 |
+
| 1.7613 | 7200 | 0.2292 | - |
|
298 |
+
| 1.7735 | 7250 | 0.3028 | - |
|
299 |
+
| 1.7857 | 7300 | 0.2394 | - |
|
300 |
+
| 1.7979 | 7350 | 0.2601 | - |
|
301 |
+
| 1.8102 | 7400 | 0.2417 | - |
|
302 |
+
| 1.8224 | 7450 | 0.2086 | - |
|
303 |
+
| 1.8346 | 7500 | 0.2573 | - |
|
304 |
+
| 1.8469 | 7550 | 0.2344 | - |
|
305 |
+
| 1.8591 | 7600 | 0.2381 | - |
|
306 |
+
| 1.8713 | 7650 | 0.2772 | - |
|
307 |
+
| 1.8836 | 7700 | 0.2614 | - |
|
308 |
+
| 1.8958 | 7750 | 0.2659 | - |
|
309 |
+
| 1.9080 | 7800 | 0.2536 | - |
|
310 |
+
| 1.9203 | 7850 | 0.2385 | - |
|
311 |
+
| 1.9325 | 7900 | 0.2695 | - |
|
312 |
+
| 1.9447 | 7950 | 0.2512 | - |
|
313 |
+
| 1.9569 | 8000 | 0.2216 | - |
|
314 |
+
| 1.9692 | 8050 | 0.2291 | - |
|
315 |
+
| 1.9814 | 8100 | 0.2443 | - |
|
316 |
+
| 1.9936 | 8150 | 0.2579 | - |
|
317 |
+
| 2.0 | 8176 | - | 0.5 |
|
318 |
+
| 2.0059 | 8200 | 0.2605 | - |
|
319 |
+
| 2.0181 | 8250 | 0.2528 | - |
|
320 |
+
| 2.0303 | 8300 | 0.2361 | - |
|
321 |
+
| 2.0426 | 8350 | 0.2891 | - |
|
322 |
+
| 2.0548 | 8400 | 0.2692 | - |
|
323 |
+
| 2.0670 | 8450 | 0.25 | - |
|
324 |
+
| 2.0793 | 8500 | 0.2362 | - |
|
325 |
+
| 2.0915 | 8550 | 0.2833 | - |
|
326 |
+
| 2.1037 | 8600 | 0.2698 | - |
|
327 |
+
| 2.1159 | 8650 | 0.2195 | - |
|
328 |
+
| 2.1282 | 8700 | 0.2621 | - |
|
329 |
+
| 2.1404 | 8750 | 0.2564 | - |
|
330 |
+
| 2.1526 | 8800 | 0.2657 | - |
|
331 |
+
| 2.1649 | 8850 | 0.2629 | - |
|
332 |
+
| 2.1771 | 8900 | 0.2503 | - |
|
333 |
+
| 2.1893 | 8950 | 0.2583 | - |
|
334 |
+
| 2.2016 | 9000 | 0.2694 | - |
|
335 |
+
| 2.2138 | 9050 | 0.2824 | - |
|
336 |
+
| 2.2260 | 9100 | 0.2675 | - |
|
337 |
+
| 2.2383 | 9150 | 0.2699 | - |
|
338 |
+
| 2.2505 | 9200 | 0.2515 | - |
|
339 |
+
| 2.2627 | 9250 | 0.2511 | - |
|
340 |
+
| 2.2750 | 9300 | 0.2518 | - |
|
341 |
+
| 2.2872 | 9350 | 0.2555 | - |
|
342 |
+
| 2.2994 | 9400 | 0.2512 | - |
|
343 |
+
| 2.3116 | 9450 | 0.2374 | - |
|
344 |
+
| 2.3239 | 9500 | 0.2546 | - |
|
345 |
+
| 2.3361 | 9550 | 0.2846 | - |
|
346 |
+
| 2.3483 | 9600 | 0.2617 | - |
|
347 |
+
| 2.3606 | 9650 | 0.2474 | - |
|
348 |
+
| 2.3728 | 9700 | 0.2454 | - |
|
349 |
+
| 2.3850 | 9750 | 0.2265 | - |
|
350 |
+
| 2.3973 | 9800 | 0.2272 | - |
|
351 |
+
| 2.4095 | 9850 | 0.2442 | - |
|
352 |
+
| 2.4217 | 9900 | 0.236 | - |
|
353 |
+
| 2.4340 | 9950 | 0.2382 | - |
|
354 |
+
| 2.4462 | 10000 | 0.2645 | - |
|
355 |
+
| 2.4584 | 10050 | 0.2707 | - |
|
356 |
+
| 2.4706 | 10100 | 0.2573 | - |
|
357 |
+
| 2.4829 | 10150 | 0.2435 | - |
|
358 |
+
| 2.4951 | 10200 | 0.2705 | - |
|
359 |
+
| 2.5073 | 10250 | 0.2808 | - |
|
360 |
+
| 2.5196 | 10300 | 0.2581 | - |
|
361 |
+
| 2.5318 | 10350 | 0.2544 | - |
|
362 |
+
| 2.5440 | 10400 | 0.2333 | - |
|
363 |
+
| 2.5563 | 10450 | 0.2544 | - |
|
364 |
+
| 2.5685 | 10500 | 0.2497 | - |
|
365 |
+
| 2.5807 | 10550 | 0.2575 | - |
|
366 |
+
| 2.5930 | 10600 | 0.2382 | - |
|
367 |
+
| 2.6052 | 10650 | 0.2451 | - |
|
368 |
+
| 2.6174 | 10700 | 0.2702 | - |
|
369 |
+
| 2.6296 | 10750 | 0.2569 | - |
|
370 |
+
| 2.6419 | 10800 | 0.249 | - |
|
371 |
+
| 2.6541 | 10850 | 0.2366 | - |
|
372 |
+
| 2.6663 | 10900 | 0.2278 | - |
|
373 |
+
| 2.6786 | 10950 | 0.2568 | - |
|
374 |
+
| 2.6908 | 11000 | 0.2721 | - |
|
375 |
+
| 2.7030 | 11050 | 0.2593 | - |
|
376 |
+
| 2.7153 | 11100 | 0.2439 | - |
|
377 |
+
| 2.7275 | 11150 | 0.2543 | - |
|
378 |
+
| 2.7397 | 11200 | 0.2478 | - |
|
379 |
+
| 2.7520 | 11250 | 0.2325 | - |
|
380 |
+
| 2.7642 | 11300 | 0.2538 | - |
|
381 |
+
| 2.7764 | 11350 | 0.2968 | - |
|
382 |
+
| 2.7886 | 11400 | 0.2505 | - |
|
383 |
+
| 2.8009 | 11450 | 0.2377 | - |
|
384 |
+
| 2.8131 | 11500 | 0.2547 | - |
|
385 |
+
| 2.8253 | 11550 | 0.2529 | - |
|
386 |
+
| 2.8376 | 11600 | 0.2502 | - |
|
387 |
+
| 2.8498 | 11650 | 0.2293 | - |
|
388 |
+
| 2.8620 | 11700 | 0.2676 | - |
|
389 |
+
| 2.8743 | 11750 | 0.2371 | - |
|
390 |
+
| 2.8865 | 11800 | 0.2495 | - |
|
391 |
+
| 2.8987 | 11850 | 0.2937 | - |
|
392 |
+
| 2.9110 | 11900 | 0.2355 | - |
|
393 |
+
| 2.9232 | 11950 | 0.2482 | - |
|
394 |
+
| 2.9354 | 12000 | 0.2336 | - |
|
395 |
+
| 2.9477 | 12050 | 0.2344 | - |
|
396 |
+
| 2.9599 | 12100 | 0.257 | - |
|
397 |
+
| 2.9721 | 12150 | 0.2557 | - |
|
398 |
+
| 2.9843 | 12200 | 0.2854 | - |
|
399 |
+
| 2.9966 | 12250 | 0.2455 | - |
|
400 |
+
| 3.0 | 12264 | - | 0.5 |
|
401 |
+
| 3.0088 | 12300 | 0.2323 | - |
|
402 |
+
| 3.0210 | 12350 | 0.2566 | - |
|
403 |
+
| 3.0333 | 12400 | 0.2319 | - |
|
404 |
+
| 3.0455 | 12450 | 0.2552 | - |
|
405 |
+
| 3.0577 | 12500 | 0.2796 | - |
|
406 |
+
| 3.0700 | 12550 | 0.2823 | - |
|
407 |
+
| 3.0822 | 12600 | 0.2303 | - |
|
408 |
+
| 3.0944 | 12650 | 0.2448 | - |
|
409 |
+
| 3.1067 | 12700 | 0.2502 | - |
|
410 |
+
| 3.1189 | 12750 | 0.2516 | - |
|
411 |
+
| 3.1311 | 12800 | 0.2537 | - |
|
412 |
+
| 3.1433 | 12850 | 0.251 | - |
|
413 |
+
| 3.1556 | 12900 | 0.2639 | - |
|
414 |
+
| 3.1678 | 12950 | 0.2321 | - |
|
415 |
+
| 3.1800 | 13000 | 0.282 | - |
|
416 |
+
| 3.1923 | 13050 | 0.2577 | - |
|
417 |
+
| 3.2045 | 13100 | 0.2448 | - |
|
418 |
+
| 3.2167 | 13150 | 0.2352 | - |
|
419 |
+
| 3.2290 | 13200 | 0.281 | - |
|
420 |
+
| 3.2412 | 13250 | 0.2337 | - |
|
421 |
+
| 3.2534 | 13300 | 0.268 | - |
|
422 |
+
| 3.2657 | 13350 | 0.261 | - |
|
423 |
+
| 3.2779 | 13400 | 0.2378 | - |
|
424 |
+
| 3.2901 | 13450 | 0.2588 | - |
|
425 |
+
| 3.3023 | 13500 | 0.266 | - |
|
426 |
+
| 3.3146 | 13550 | 0.2604 | - |
|
427 |
+
| 3.3268 | 13600 | 0.2202 | - |
|
428 |
+
| 3.3390 | 13650 | 0.2217 | - |
|
429 |
+
| 3.3513 | 13700 | 0.2464 | - |
|
430 |
+
| 3.3635 | 13750 | 0.2684 | - |
|
431 |
+
| 3.3757 | 13800 | 0.2279 | - |
|
432 |
+
| 3.3880 | 13850 | 0.2379 | - |
|
433 |
+
| 3.4002 | 13900 | 0.2741 | - |
|
434 |
+
| 3.4124 | 13950 | 0.2713 | - |
|
435 |
+
| 3.4247 | 14000 | 0.2581 | - |
|
436 |
+
| 3.4369 | 14050 | 0.2638 | - |
|
437 |
+
| 3.4491 | 14100 | 0.2125 | - |
|
438 |
+
| 3.4614 | 14150 | 0.2348 | - |
|
439 |
+
| 3.4736 | 14200 | 0.2253 | - |
|
440 |
+
| 3.4858 | 14250 | 0.2627 | - |
|
441 |
+
| 3.4980 | 14300 | 0.2463 | - |
|
442 |
+
| 3.5103 | 14350 | 0.2533 | - |
|
443 |
+
| 3.5225 | 14400 | 0.2422 | - |
|
444 |
+
| 3.5347 | 14450 | 0.2296 | - |
|
445 |
+
| 3.5470 | 14500 | 0.2532 | - |
|
446 |
+
| 3.5592 | 14550 | 0.2733 | - |
|
447 |
+
| 3.5714 | 14600 | 0.2258 | - |
|
448 |
+
| 3.5837 | 14650 | 0.2253 | - |
|
449 |
+
| 3.5959 | 14700 | 0.2388 | - |
|
450 |
+
| 3.6081 | 14750 | 0.2217 | - |
|
451 |
+
| 3.6204 | 14800 | 0.3033 | - |
|
452 |
+
| 3.6326 | 14850 | 0.2349 | - |
|
453 |
+
| 3.6448 | 14900 | 0.2596 | - |
|
454 |
+
| 3.6570 | 14950 | 0.2415 | - |
|
455 |
+
| 3.6693 | 15000 | 0.2494 | - |
|
456 |
+
| 3.6815 | 15050 | 0.2826 | - |
|
457 |
+
| 3.6937 | 15100 | 0.2633 | - |
|
458 |
+
| 3.7060 | 15150 | 0.2636 | - |
|
459 |
+
| 3.7182 | 15200 | 0.2351 | - |
|
460 |
+
| 3.7304 | 15250 | 0.264 | - |
|
461 |
+
| 3.7427 | 15300 | 0.2652 | - |
|
462 |
+
| 3.7549 | 15350 | 0.2724 | - |
|
463 |
+
| 3.7671 | 15400 | 0.2731 | - |
|
464 |
+
| 3.7794 | 15450 | 0.2825 | - |
|
465 |
+
| 3.7916 | 15500 | 0.2611 | - |
|
466 |
+
| 3.8038 | 15550 | 0.2574 | - |
|
467 |
+
| 3.8160 | 15600 | 0.261 | - |
|
468 |
+
| 3.8283 | 15650 | 0.219 | - |
|
469 |
+
| 3.8405 | 15700 | 0.2323 | - |
|
470 |
+
| 3.8527 | 15750 | 0.2442 | - |
|
471 |
+
| 3.8650 | 15800 | 0.2509 | - |
|
472 |
+
| 3.8772 | 15850 | 0.26 | - |
|
473 |
+
| 3.8894 | 15900 | 0.2475 | - |
|
474 |
+
| 3.9017 | 15950 | 0.2452 | - |
|
475 |
+
| 3.9139 | 16000 | 0.2598 | - |
|
476 |
+
| 3.9261 | 16050 | 0.2377 | - |
|
477 |
+
| 3.9384 | 16100 | 0.2445 | - |
|
478 |
+
| 3.9506 | 16150 | 0.2451 | - |
|
479 |
+
| 3.9628 | 16200 | 0.2714 | - |
|
480 |
+
| 3.9750 | 16250 | 0.2755 | - |
|
481 |
+
| 3.9873 | 16300 | 0.2579 | - |
|
482 |
+
| 3.9995 | 16350 | 0.2338 | - |
|
483 |
+
| 4.0 | 16352 | - | 0.5 |
|
484 |
+
|
485 |
+
* The bold row denotes the saved checkpoint.
|
486 |
+
### Framework Versions
|
487 |
+
- Python: 3.10.12
|
488 |
+
- SetFit: 1.0.3
|
489 |
+
- Sentence Transformers: 2.7.0
|
490 |
+
- Transformers: 4.40.0
|
491 |
+
- PyTorch: 2.2.1+cu121
|
492 |
+
- Datasets: 2.19.0
|
493 |
+
- Tokenizers: 0.19.1
|
494 |
+
|
495 |
+
## Citation
|
496 |
+
|
497 |
+
### BibTeX
|
498 |
+
```bibtex
|
499 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
500 |
+
doi = {10.48550/ARXIV.2209.11055},
|
501 |
+
url = {https://arxiv.org/abs/2209.11055},
|
502 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
503 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
504 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
505 |
+
publisher = {arXiv},
|
506 |
+
year = {2022},
|
507 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
508 |
+
}
|
509 |
+
```
|
510 |
+
|
511 |
+
<!--
|
512 |
+
## Glossary
|
513 |
+
|
514 |
+
*Clearly define terms in order to be accessible across audiences.*
|
515 |
+
-->
|
516 |
+
|
517 |
+
<!--
|
518 |
+
## Model Card Authors
|
519 |
+
|
520 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
521 |
+
-->
|
522 |
+
|
523 |
+
<!--
|
524 |
+
## Model Card Contact
|
525 |
+
|
526 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
527 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints/step_4088",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.0",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.7.0",
|
4 |
+
"transformers": "4.40.0",
|
5 |
+
"pytorch": "2.2.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": [
|
3 |
+
"false",
|
4 |
+
"true"
|
5 |
+
],
|
6 |
+
"normalize_embeddings": false
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cb25fa2b231b9bf4a76bd9bee3890518ae2f90410abcd16c7536c151cbc5f4
|
3 |
+
size 1421483904
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5201b33d7b0ed4ee07dec9dc5ff4d3b06399c8bc693612567205d36efb252c
|
3 |
+
size 9071
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
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 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"sep_token": "</s>",
|
58 |
+
"stride": 0,
|
59 |
+
"tokenizer_class": "RobertaTokenizer",
|
60 |
+
"trim_offsets": true,
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|