Commit
•
5245a0b
1
Parent(s):
9b43c44
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +911 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +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 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,911 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/all-MiniLM-L6-v2
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
metrics:
|
7 |
+
- pearson_cosine
|
8 |
+
- spearman_cosine
|
9 |
+
- pearson_manhattan
|
10 |
+
- spearman_manhattan
|
11 |
+
- pearson_euclidean
|
12 |
+
- spearman_euclidean
|
13 |
+
- pearson_dot
|
14 |
+
- spearman_dot
|
15 |
+
- pearson_max
|
16 |
+
- spearman_max
|
17 |
+
pipeline_tag: sentence-similarity
|
18 |
+
tags:
|
19 |
+
- sentence-transformers
|
20 |
+
- sentence-similarity
|
21 |
+
- feature-extraction
|
22 |
+
- generated_from_trainer
|
23 |
+
- dataset_size:724
|
24 |
+
- loss:CoSENTLoss
|
25 |
+
widget:
|
26 |
+
- source_sentence: Financials
|
27 |
+
sentences:
|
28 |
+
- What is the financial performance of ABC?
|
29 |
+
- What companies operate in the same space as ABC?
|
30 |
+
- What standards are used to evaluate the industry?
|
31 |
+
- source_sentence: Research
|
32 |
+
sentences:
|
33 |
+
- What recent studies have been conducted on ABC?
|
34 |
+
- What are the key factors considered in rating ABC?
|
35 |
+
- How is the rating framework applied to the sector?
|
36 |
+
- source_sentence: Criteria
|
37 |
+
sentences:
|
38 |
+
- What are the projected economic impacts of inflation on the technology industry?
|
39 |
+
- What is the process for assessing the creditworthiness of ABC?
|
40 |
+
- What are the primary ESG challenges faced by ABC?
|
41 |
+
- source_sentence: Financials
|
42 |
+
sentences:
|
43 |
+
- Can you list the strengths and weaknesses of ABC?
|
44 |
+
- What is understood by the term sovereign risk?
|
45 |
+
- Can you provide the financial history of ABC?
|
46 |
+
- source_sentence: Research
|
47 |
+
sentences:
|
48 |
+
- What macroeconomic trends are influencing the credit ratings of the automotive
|
49 |
+
industry?
|
50 |
+
- Who are the main rivals of ABC?
|
51 |
+
- Can you provide the latest research insights on ABC?
|
52 |
+
model-index:
|
53 |
+
- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
|
54 |
+
results:
|
55 |
+
- task:
|
56 |
+
type: semantic-similarity
|
57 |
+
name: Semantic Similarity
|
58 |
+
dataset:
|
59 |
+
name: sts dev
|
60 |
+
type: sts-dev
|
61 |
+
metrics:
|
62 |
+
- type: pearson_cosine
|
63 |
+
value: .nan
|
64 |
+
name: Pearson Cosine
|
65 |
+
- type: spearman_cosine
|
66 |
+
value: .nan
|
67 |
+
name: Spearman Cosine
|
68 |
+
- type: pearson_manhattan
|
69 |
+
value: .nan
|
70 |
+
name: Pearson Manhattan
|
71 |
+
- type: spearman_manhattan
|
72 |
+
value: .nan
|
73 |
+
name: Spearman Manhattan
|
74 |
+
- type: pearson_euclidean
|
75 |
+
value: .nan
|
76 |
+
name: Pearson Euclidean
|
77 |
+
- type: spearman_euclidean
|
78 |
+
value: .nan
|
79 |
+
name: Spearman Euclidean
|
80 |
+
- type: pearson_dot
|
81 |
+
value: .nan
|
82 |
+
name: Pearson Dot
|
83 |
+
- type: spearman_dot
|
84 |
+
value: .nan
|
85 |
+
name: Spearman Dot
|
86 |
+
- type: pearson_max
|
87 |
+
value: .nan
|
88 |
+
name: Pearson Max
|
89 |
+
- type: spearman_max
|
90 |
+
value: .nan
|
91 |
+
name: Spearman Max
|
92 |
+
---
|
93 |
+
|
94 |
+
# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
|
95 |
+
|
96 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
97 |
+
|
98 |
+
## Model Details
|
99 |
+
|
100 |
+
### Model Description
|
101 |
+
- **Model Type:** Sentence Transformer
|
102 |
+
- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a -->
|
103 |
+
- **Maximum Sequence Length:** 512 tokens
|
104 |
+
- **Output Dimensionality:** 384 tokens
|
105 |
+
- **Similarity Function:** Cosine Similarity
|
106 |
+
<!-- - **Training Dataset:** Unknown -->
|
107 |
+
<!-- - **Language:** Unknown -->
|
108 |
+
<!-- - **License:** Unknown -->
|
109 |
+
|
110 |
+
### Model Sources
|
111 |
+
|
112 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
113 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
114 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
115 |
+
|
116 |
+
### Full Model Architecture
|
117 |
+
|
118 |
+
```
|
119 |
+
SentenceTransformer(
|
120 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
121 |
+
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
122 |
+
)
|
123 |
+
```
|
124 |
+
|
125 |
+
## Usage
|
126 |
+
|
127 |
+
### Direct Usage (Sentence Transformers)
|
128 |
+
|
129 |
+
First install the Sentence Transformers library:
|
130 |
+
|
131 |
+
```bash
|
132 |
+
pip install -U sentence-transformers
|
133 |
+
```
|
134 |
+
|
135 |
+
Then you can load this model and run inference.
|
136 |
+
```python
|
137 |
+
from sentence_transformers import SentenceTransformer
|
138 |
+
|
139 |
+
# Download from the 🤗 Hub
|
140 |
+
model = SentenceTransformer("ManishThota/QueryRouter")
|
141 |
+
# Run inference
|
142 |
+
sentences = [
|
143 |
+
'Research',
|
144 |
+
'Can you provide the latest research insights on ABC?',
|
145 |
+
'Who are the main rivals of ABC?',
|
146 |
+
]
|
147 |
+
embeddings = model.encode(sentences)
|
148 |
+
print(embeddings.shape)
|
149 |
+
# [3, 384]
|
150 |
+
|
151 |
+
# Get the similarity scores for the embeddings
|
152 |
+
similarities = model.similarity(embeddings, embeddings)
|
153 |
+
print(similarities.shape)
|
154 |
+
# [3, 3]
|
155 |
+
```
|
156 |
+
|
157 |
+
<!--
|
158 |
+
### Direct Usage (Transformers)
|
159 |
+
|
160 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
161 |
+
|
162 |
+
</details>
|
163 |
+
-->
|
164 |
+
|
165 |
+
<!--
|
166 |
+
### Downstream Usage (Sentence Transformers)
|
167 |
+
|
168 |
+
You can finetune this model on your own dataset.
|
169 |
+
|
170 |
+
<details><summary>Click to expand</summary>
|
171 |
+
|
172 |
+
</details>
|
173 |
+
-->
|
174 |
+
|
175 |
+
<!--
|
176 |
+
### Out-of-Scope Use
|
177 |
+
|
178 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
179 |
+
-->
|
180 |
+
|
181 |
+
## Evaluation
|
182 |
+
|
183 |
+
### Metrics
|
184 |
+
|
185 |
+
#### Semantic Similarity
|
186 |
+
* Dataset: `sts-dev`
|
187 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
188 |
+
|
189 |
+
| Metric | Value |
|
190 |
+
|:--------------------|:--------|
|
191 |
+
| pearson_cosine | nan |
|
192 |
+
| **spearman_cosine** | **nan** |
|
193 |
+
| pearson_manhattan | nan |
|
194 |
+
| spearman_manhattan | nan |
|
195 |
+
| pearson_euclidean | nan |
|
196 |
+
| spearman_euclidean | nan |
|
197 |
+
| pearson_dot | nan |
|
198 |
+
| spearman_dot | nan |
|
199 |
+
| pearson_max | nan |
|
200 |
+
| spearman_max | nan |
|
201 |
+
|
202 |
+
<!--
|
203 |
+
## Bias, Risks and Limitations
|
204 |
+
|
205 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
206 |
+
-->
|
207 |
+
|
208 |
+
<!--
|
209 |
+
### Recommendations
|
210 |
+
|
211 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
212 |
+
-->
|
213 |
+
|
214 |
+
## Training Details
|
215 |
+
|
216 |
+
### Training Dataset
|
217 |
+
|
218 |
+
#### Unnamed Dataset
|
219 |
+
|
220 |
+
|
221 |
+
* Size: 724 training samples
|
222 |
+
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
223 |
+
* Approximate statistics based on the first 1000 samples:
|
224 |
+
| | sentence1 | sentence2 | score |
|
225 |
+
|:--------|:--------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
226 |
+
| type | string | string | float |
|
227 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 3.27 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 14.23 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
|
228 |
+
* Samples:
|
229 |
+
| sentence1 | sentence2 | score |
|
230 |
+
|:--------------------|:-------------------------------------------------|:-----------------|
|
231 |
+
| <code>Rating</code> | <code>What rating does XYZ have?</code> | <code>1.0</code> |
|
232 |
+
| <code>Rating</code> | <code>Can you provide the rating for XYZ?</code> | <code>1.0</code> |
|
233 |
+
| <code>Rating</code> | <code>How is XYZ rated?</code> | <code>1.0</code> |
|
234 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
235 |
+
```json
|
236 |
+
{
|
237 |
+
"scale": 20.0,
|
238 |
+
"similarity_fct": "pairwise_cos_sim"
|
239 |
+
}
|
240 |
+
```
|
241 |
+
|
242 |
+
### Evaluation Dataset
|
243 |
+
|
244 |
+
#### Unnamed Dataset
|
245 |
+
|
246 |
+
|
247 |
+
* Size: 60 evaluation samples
|
248 |
+
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
249 |
+
* Approximate statistics based on the first 1000 samples:
|
250 |
+
| | sentence1 | sentence2 | score |
|
251 |
+
|:--------|:--------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
252 |
+
| type | string | string | float |
|
253 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 3.25 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 12.48 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
|
254 |
+
* Samples:
|
255 |
+
| sentence1 | sentence2 | score |
|
256 |
+
|:--------------------|:-------------------------------------------------|:-----------------|
|
257 |
+
| <code>Rating</code> | <code>What is the current rating of ABC?</code> | <code>1.0</code> |
|
258 |
+
| <code>Rating</code> | <code>Can you tell me the rating for ABC?</code> | <code>1.0</code> |
|
259 |
+
| <code>Rating</code> | <code>What rating has ABC been assigned?</code> | <code>1.0</code> |
|
260 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
261 |
+
```json
|
262 |
+
{
|
263 |
+
"scale": 20.0,
|
264 |
+
"similarity_fct": "pairwise_cos_sim"
|
265 |
+
}
|
266 |
+
```
|
267 |
+
|
268 |
+
### Training Hyperparameters
|
269 |
+
#### Non-Default Hyperparameters
|
270 |
+
|
271 |
+
- `eval_strategy`: steps
|
272 |
+
- `learning_rate`: 2e-05
|
273 |
+
- `num_train_epochs`: 10
|
274 |
+
- `warmup_ratio`: 0.1
|
275 |
+
- `save_only_model`: True
|
276 |
+
- `seed`: 33
|
277 |
+
- `fp16`: True
|
278 |
+
- `load_best_model_at_end`: True
|
279 |
+
|
280 |
+
#### All Hyperparameters
|
281 |
+
<details><summary>Click to expand</summary>
|
282 |
+
|
283 |
+
- `overwrite_output_dir`: False
|
284 |
+
- `do_predict`: False
|
285 |
+
- `eval_strategy`: steps
|
286 |
+
- `prediction_loss_only`: True
|
287 |
+
- `per_device_train_batch_size`: 8
|
288 |
+
- `per_device_eval_batch_size`: 8
|
289 |
+
- `per_gpu_train_batch_size`: None
|
290 |
+
- `per_gpu_eval_batch_size`: None
|
291 |
+
- `gradient_accumulation_steps`: 1
|
292 |
+
- `eval_accumulation_steps`: None
|
293 |
+
- `learning_rate`: 2e-05
|
294 |
+
- `weight_decay`: 0.0
|
295 |
+
- `adam_beta1`: 0.9
|
296 |
+
- `adam_beta2`: 0.999
|
297 |
+
- `adam_epsilon`: 1e-08
|
298 |
+
- `max_grad_norm`: 1.0
|
299 |
+
- `num_train_epochs`: 10
|
300 |
+
- `max_steps`: -1
|
301 |
+
- `lr_scheduler_type`: linear
|
302 |
+
- `lr_scheduler_kwargs`: {}
|
303 |
+
- `warmup_ratio`: 0.1
|
304 |
+
- `warmup_steps`: 0
|
305 |
+
- `log_level`: passive
|
306 |
+
- `log_level_replica`: warning
|
307 |
+
- `log_on_each_node`: True
|
308 |
+
- `logging_nan_inf_filter`: True
|
309 |
+
- `save_safetensors`: True
|
310 |
+
- `save_on_each_node`: False
|
311 |
+
- `save_only_model`: True
|
312 |
+
- `restore_callback_states_from_checkpoint`: False
|
313 |
+
- `no_cuda`: False
|
314 |
+
- `use_cpu`: False
|
315 |
+
- `use_mps_device`: False
|
316 |
+
- `seed`: 33
|
317 |
+
- `data_seed`: None
|
318 |
+
- `jit_mode_eval`: False
|
319 |
+
- `use_ipex`: False
|
320 |
+
- `bf16`: False
|
321 |
+
- `fp16`: True
|
322 |
+
- `fp16_opt_level`: O1
|
323 |
+
- `half_precision_backend`: auto
|
324 |
+
- `bf16_full_eval`: False
|
325 |
+
- `fp16_full_eval`: False
|
326 |
+
- `tf32`: None
|
327 |
+
- `local_rank`: 0
|
328 |
+
- `ddp_backend`: None
|
329 |
+
- `tpu_num_cores`: None
|
330 |
+
- `tpu_metrics_debug`: False
|
331 |
+
- `debug`: []
|
332 |
+
- `dataloader_drop_last`: False
|
333 |
+
- `dataloader_num_workers`: 0
|
334 |
+
- `dataloader_prefetch_factor`: None
|
335 |
+
- `past_index`: -1
|
336 |
+
- `disable_tqdm`: False
|
337 |
+
- `remove_unused_columns`: True
|
338 |
+
- `label_names`: None
|
339 |
+
- `load_best_model_at_end`: True
|
340 |
+
- `ignore_data_skip`: False
|
341 |
+
- `fsdp`: []
|
342 |
+
- `fsdp_min_num_params`: 0
|
343 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
344 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
345 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
346 |
+
- `deepspeed`: None
|
347 |
+
- `label_smoothing_factor`: 0.0
|
348 |
+
- `optim`: adamw_torch
|
349 |
+
- `optim_args`: None
|
350 |
+
- `adafactor`: False
|
351 |
+
- `group_by_length`: False
|
352 |
+
- `length_column_name`: length
|
353 |
+
- `ddp_find_unused_parameters`: None
|
354 |
+
- `ddp_bucket_cap_mb`: None
|
355 |
+
- `ddp_broadcast_buffers`: False
|
356 |
+
- `dataloader_pin_memory`: True
|
357 |
+
- `dataloader_persistent_workers`: False
|
358 |
+
- `skip_memory_metrics`: True
|
359 |
+
- `use_legacy_prediction_loop`: False
|
360 |
+
- `push_to_hub`: False
|
361 |
+
- `resume_from_checkpoint`: None
|
362 |
+
- `hub_model_id`: None
|
363 |
+
- `hub_strategy`: every_save
|
364 |
+
- `hub_private_repo`: False
|
365 |
+
- `hub_always_push`: False
|
366 |
+
- `gradient_checkpointing`: False
|
367 |
+
- `gradient_checkpointing_kwargs`: None
|
368 |
+
- `include_inputs_for_metrics`: False
|
369 |
+
- `eval_do_concat_batches`: True
|
370 |
+
- `fp16_backend`: auto
|
371 |
+
- `push_to_hub_model_id`: None
|
372 |
+
- `push_to_hub_organization`: None
|
373 |
+
- `mp_parameters`:
|
374 |
+
- `auto_find_batch_size`: False
|
375 |
+
- `full_determinism`: False
|
376 |
+
- `torchdynamo`: None
|
377 |
+
- `ray_scope`: last
|
378 |
+
- `ddp_timeout`: 1800
|
379 |
+
- `torch_compile`: False
|
380 |
+
- `torch_compile_backend`: None
|
381 |
+
- `torch_compile_mode`: None
|
382 |
+
- `dispatch_batches`: None
|
383 |
+
- `split_batches`: None
|
384 |
+
- `include_tokens_per_second`: False
|
385 |
+
- `include_num_input_tokens_seen`: False
|
386 |
+
- `neftune_noise_alpha`: None
|
387 |
+
- `optim_target_modules`: None
|
388 |
+
- `batch_eval_metrics`: False
|
389 |
+
- `batch_sampler`: batch_sampler
|
390 |
+
- `multi_dataset_batch_sampler`: proportional
|
391 |
+
|
392 |
+
</details>
|
393 |
+
|
394 |
+
### Training Logs
|
395 |
+
<details><summary>Click to expand</summary>
|
396 |
+
|
397 |
+
| Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine |
|
398 |
+
|:----------:|:-------:|:-------------:|:-------:|:-----------------------:|
|
399 |
+
| 0.0220 | 2 | - | 0.0 | nan |
|
400 |
+
| 0.0440 | 4 | - | 0.0 | nan |
|
401 |
+
| 0.0659 | 6 | - | 0.0 | nan |
|
402 |
+
| 0.0879 | 8 | - | 0.0 | nan |
|
403 |
+
| 0.1099 | 10 | - | 0.0 | nan |
|
404 |
+
| 0.1319 | 12 | - | 0.0 | nan |
|
405 |
+
| 0.1538 | 14 | - | 0.0 | nan |
|
406 |
+
| 0.1758 | 16 | - | 0.0 | nan |
|
407 |
+
| 0.1978 | 18 | - | 0.0 | nan |
|
408 |
+
| 0.2198 | 20 | - | 0.0 | nan |
|
409 |
+
| 0.2418 | 22 | - | 0.0 | nan |
|
410 |
+
| 0.2637 | 24 | - | 0.0 | nan |
|
411 |
+
| 0.2857 | 26 | - | 0.0 | nan |
|
412 |
+
| 0.3077 | 28 | - | 0.0 | nan |
|
413 |
+
| 0.3297 | 30 | - | 0.0 | nan |
|
414 |
+
| 0.3516 | 32 | - | 0.0 | nan |
|
415 |
+
| 0.3736 | 34 | - | 0.0 | nan |
|
416 |
+
| 0.3956 | 36 | - | 0.0 | nan |
|
417 |
+
| 0.4176 | 38 | - | 0.0 | nan |
|
418 |
+
| 0.4396 | 40 | - | 0.0 | nan |
|
419 |
+
| 0.4615 | 42 | - | 0.0 | nan |
|
420 |
+
| 0.4835 | 44 | - | 0.0 | nan |
|
421 |
+
| 0.5055 | 46 | - | 0.0 | nan |
|
422 |
+
| 0.5275 | 48 | - | 0.0 | nan |
|
423 |
+
| 0.5495 | 50 | - | 0.0 | nan |
|
424 |
+
| 0.5714 | 52 | - | 0.0 | nan |
|
425 |
+
| 0.5934 | 54 | - | 0.0 | nan |
|
426 |
+
| 0.6154 | 56 | - | 0.0 | nan |
|
427 |
+
| 0.6374 | 58 | - | 0.0 | nan |
|
428 |
+
| 0.6593 | 60 | - | 0.0 | nan |
|
429 |
+
| 0.6813 | 62 | - | 0.0 | nan |
|
430 |
+
| 0.7033 | 64 | - | 0.0 | nan |
|
431 |
+
| 0.7253 | 66 | - | 0.0 | nan |
|
432 |
+
| 0.7473 | 68 | - | 0.0 | nan |
|
433 |
+
| 0.7692 | 70 | - | 0.0 | nan |
|
434 |
+
| 0.7912 | 72 | - | 0.0 | nan |
|
435 |
+
| 0.8132 | 74 | - | 0.0 | nan |
|
436 |
+
| 0.8352 | 76 | - | 0.0 | nan |
|
437 |
+
| 0.8571 | 78 | - | 0.0 | nan |
|
438 |
+
| 0.8791 | 80 | - | 0.0 | nan |
|
439 |
+
| 0.9011 | 82 | - | 0.0 | nan |
|
440 |
+
| 0.9231 | 84 | - | 0.0 | nan |
|
441 |
+
| 0.9451 | 86 | - | 0.0 | nan |
|
442 |
+
| 0.9670 | 88 | - | 0.0 | nan |
|
443 |
+
| 0.9890 | 90 | - | 0.0 | nan |
|
444 |
+
| 1.0110 | 92 | - | 0.0 | nan |
|
445 |
+
| 1.0330 | 94 | - | 0.0 | nan |
|
446 |
+
| 1.0549 | 96 | - | 0.0 | nan |
|
447 |
+
| 1.0769 | 98 | - | 0.0 | nan |
|
448 |
+
| 1.0989 | 100 | - | 0.0 | nan |
|
449 |
+
| 1.1209 | 102 | - | 0.0 | nan |
|
450 |
+
| 1.1429 | 104 | - | 0.0 | nan |
|
451 |
+
| 1.1648 | 106 | - | 0.0 | nan |
|
452 |
+
| 1.1868 | 108 | - | 0.0 | nan |
|
453 |
+
| 1.2088 | 110 | - | 0.0 | nan |
|
454 |
+
| 1.2308 | 112 | - | 0.0 | nan |
|
455 |
+
| 1.2527 | 114 | - | 0.0 | nan |
|
456 |
+
| 1.2747 | 116 | - | 0.0 | nan |
|
457 |
+
| 1.2967 | 118 | - | 0.0 | nan |
|
458 |
+
| 1.3187 | 120 | - | 0.0 | nan |
|
459 |
+
| 1.3407 | 122 | - | 0.0 | nan |
|
460 |
+
| 1.3626 | 124 | - | 0.0 | nan |
|
461 |
+
| 1.3846 | 126 | - | 0.0 | nan |
|
462 |
+
| 1.4066 | 128 | - | 0.0 | nan |
|
463 |
+
| 1.4286 | 130 | - | 0.0 | nan |
|
464 |
+
| 1.4505 | 132 | - | 0.0 | nan |
|
465 |
+
| 1.4725 | 134 | - | 0.0 | nan |
|
466 |
+
| 1.4945 | 136 | - | 0.0 | nan |
|
467 |
+
| 1.5165 | 138 | - | 0.0 | nan |
|
468 |
+
| 1.5385 | 140 | - | 0.0 | nan |
|
469 |
+
| 1.5604 | 142 | - | 0.0 | nan |
|
470 |
+
| 1.5824 | 144 | - | 0.0 | nan |
|
471 |
+
| 1.6044 | 146 | - | 0.0 | nan |
|
472 |
+
| 1.6264 | 148 | - | 0.0 | nan |
|
473 |
+
| 1.6484 | 150 | - | 0.0 | nan |
|
474 |
+
| 1.6703 | 152 | - | 0.0 | nan |
|
475 |
+
| 1.6923 | 154 | - | 0.0 | nan |
|
476 |
+
| 1.7143 | 156 | - | 0.0 | nan |
|
477 |
+
| 1.7363 | 158 | - | 0.0 | nan |
|
478 |
+
| 1.7582 | 160 | - | 0.0 | nan |
|
479 |
+
| 1.7802 | 162 | - | 0.0 | nan |
|
480 |
+
| 1.8022 | 164 | - | 0.0 | nan |
|
481 |
+
| 1.8242 | 166 | - | 0.0 | nan |
|
482 |
+
| 1.8462 | 168 | - | 0.0 | nan |
|
483 |
+
| 1.8681 | 170 | - | 0.0 | nan |
|
484 |
+
| 1.8901 | 172 | - | 0.0 | nan |
|
485 |
+
| 1.9121 | 174 | - | 0.0 | nan |
|
486 |
+
| 1.9341 | 176 | - | 0.0 | nan |
|
487 |
+
| 1.9560 | 178 | - | 0.0 | nan |
|
488 |
+
| 1.9780 | 180 | - | 0.0 | nan |
|
489 |
+
| 2.0 | 182 | - | 0.0 | nan |
|
490 |
+
| 2.0220 | 184 | - | 0.0 | nan |
|
491 |
+
| 2.0440 | 186 | - | 0.0 | nan |
|
492 |
+
| 2.0659 | 188 | - | 0.0 | nan |
|
493 |
+
| 2.0879 | 190 | - | 0.0 | nan |
|
494 |
+
| 2.1099 | 192 | - | 0.0 | nan |
|
495 |
+
| 2.1319 | 194 | - | 0.0 | nan |
|
496 |
+
| 2.1538 | 196 | - | 0.0 | nan |
|
497 |
+
| 2.1758 | 198 | - | 0.0 | nan |
|
498 |
+
| 2.1978 | 200 | - | 0.0 | nan |
|
499 |
+
| 2.2198 | 202 | - | 0.0 | nan |
|
500 |
+
| 2.2418 | 204 | - | 0.0 | nan |
|
501 |
+
| 2.2637 | 206 | - | 0.0 | nan |
|
502 |
+
| 2.2857 | 208 | - | 0.0 | nan |
|
503 |
+
| 2.3077 | 210 | - | 0.0 | nan |
|
504 |
+
| 2.3297 | 212 | - | 0.0 | nan |
|
505 |
+
| 2.3516 | 214 | - | 0.0 | nan |
|
506 |
+
| 2.3736 | 216 | - | 0.0 | nan |
|
507 |
+
| 2.3956 | 218 | - | 0.0 | nan |
|
508 |
+
| 2.4176 | 220 | - | 0.0 | nan |
|
509 |
+
| 2.4396 | 222 | - | 0.0 | nan |
|
510 |
+
| 2.4615 | 224 | - | 0.0 | nan |
|
511 |
+
| 2.4835 | 226 | - | 0.0 | nan |
|
512 |
+
| 2.5055 | 228 | - | 0.0 | nan |
|
513 |
+
| 2.5275 | 230 | - | 0.0 | nan |
|
514 |
+
| 2.5495 | 232 | - | 0.0 | nan |
|
515 |
+
| 2.5714 | 234 | - | 0.0 | nan |
|
516 |
+
| 2.5934 | 236 | - | 0.0 | nan |
|
517 |
+
| 2.6154 | 238 | - | 0.0 | nan |
|
518 |
+
| 2.6374 | 240 | - | 0.0 | nan |
|
519 |
+
| 2.6593 | 242 | - | 0.0 | nan |
|
520 |
+
| 2.6813 | 244 | - | 0.0 | nan |
|
521 |
+
| 2.7033 | 246 | - | 0.0 | nan |
|
522 |
+
| 2.7253 | 248 | - | 0.0 | nan |
|
523 |
+
| 2.7473 | 250 | - | 0.0 | nan |
|
524 |
+
| 2.7692 | 252 | - | 0.0 | nan |
|
525 |
+
| 2.7912 | 254 | - | 0.0 | nan |
|
526 |
+
| 2.8132 | 256 | - | 0.0 | nan |
|
527 |
+
| 2.8352 | 258 | - | 0.0 | nan |
|
528 |
+
| 2.8571 | 260 | - | 0.0 | nan |
|
529 |
+
| 2.8791 | 262 | - | 0.0 | nan |
|
530 |
+
| 2.9011 | 264 | - | 0.0 | nan |
|
531 |
+
| 2.9231 | 266 | - | 0.0 | nan |
|
532 |
+
| 2.9451 | 268 | - | 0.0 | nan |
|
533 |
+
| 2.9670 | 270 | - | 0.0 | nan |
|
534 |
+
| 2.9890 | 272 | - | 0.0 | nan |
|
535 |
+
| 3.0110 | 274 | - | 0.0 | nan |
|
536 |
+
| 3.0330 | 276 | - | 0.0 | nan |
|
537 |
+
| 3.0549 | 278 | - | 0.0 | nan |
|
538 |
+
| 3.0769 | 280 | - | 0.0 | nan |
|
539 |
+
| 3.0989 | 282 | - | 0.0 | nan |
|
540 |
+
| 3.1209 | 284 | - | 0.0 | nan |
|
541 |
+
| 3.1429 | 286 | - | 0.0 | nan |
|
542 |
+
| 3.1648 | 288 | - | 0.0 | nan |
|
543 |
+
| 3.1868 | 290 | - | 0.0 | nan |
|
544 |
+
| 3.2088 | 292 | - | 0.0 | nan |
|
545 |
+
| 3.2308 | 294 | - | 0.0 | nan |
|
546 |
+
| 3.2527 | 296 | - | 0.0 | nan |
|
547 |
+
| 3.2747 | 298 | - | 0.0 | nan |
|
548 |
+
| 3.2967 | 300 | - | 0.0 | nan |
|
549 |
+
| 3.3187 | 302 | - | 0.0 | nan |
|
550 |
+
| 3.3407 | 304 | - | 0.0 | nan |
|
551 |
+
| 3.3626 | 306 | - | 0.0 | nan |
|
552 |
+
| 3.3846 | 308 | - | 0.0 | nan |
|
553 |
+
| 3.4066 | 310 | - | 0.0 | nan |
|
554 |
+
| 3.4286 | 312 | - | 0.0 | nan |
|
555 |
+
| 3.4505 | 314 | - | 0.0 | nan |
|
556 |
+
| 3.4725 | 316 | - | 0.0 | nan |
|
557 |
+
| 3.4945 | 318 | - | 0.0 | nan |
|
558 |
+
| 3.5165 | 320 | - | 0.0 | nan |
|
559 |
+
| 3.5385 | 322 | - | 0.0 | nan |
|
560 |
+
| 3.5604 | 324 | - | 0.0 | nan |
|
561 |
+
| 3.5824 | 326 | - | 0.0 | nan |
|
562 |
+
| 3.6044 | 328 | - | 0.0 | nan |
|
563 |
+
| 3.6264 | 330 | - | 0.0 | nan |
|
564 |
+
| 3.6484 | 332 | - | 0.0 | nan |
|
565 |
+
| 3.6703 | 334 | - | 0.0 | nan |
|
566 |
+
| 3.6923 | 336 | - | 0.0 | nan |
|
567 |
+
| 3.7143 | 338 | - | 0.0 | nan |
|
568 |
+
| 3.7363 | 340 | - | 0.0 | nan |
|
569 |
+
| 3.7582 | 342 | - | 0.0 | nan |
|
570 |
+
| 3.7802 | 344 | - | 0.0 | nan |
|
571 |
+
| 3.8022 | 346 | - | 0.0 | nan |
|
572 |
+
| 3.8242 | 348 | - | 0.0 | nan |
|
573 |
+
| 3.8462 | 350 | - | 0.0 | nan |
|
574 |
+
| 3.8681 | 352 | - | 0.0 | nan |
|
575 |
+
| 3.8901 | 354 | - | 0.0 | nan |
|
576 |
+
| 3.9121 | 356 | - | 0.0 | nan |
|
577 |
+
| 3.9341 | 358 | - | 0.0 | nan |
|
578 |
+
| 3.9560 | 360 | - | 0.0 | nan |
|
579 |
+
| 3.9780 | 362 | - | 0.0 | nan |
|
580 |
+
| 4.0 | 364 | - | 0.0 | nan |
|
581 |
+
| 4.0220 | 366 | - | 0.0 | nan |
|
582 |
+
| 4.0440 | 368 | - | 0.0 | nan |
|
583 |
+
| 4.0659 | 370 | - | 0.0 | nan |
|
584 |
+
| 4.0879 | 372 | - | 0.0 | nan |
|
585 |
+
| 4.1099 | 374 | - | 0.0 | nan |
|
586 |
+
| 4.1319 | 376 | - | 0.0 | nan |
|
587 |
+
| 4.1538 | 378 | - | 0.0 | nan |
|
588 |
+
| 4.1758 | 380 | - | 0.0 | nan |
|
589 |
+
| 4.1978 | 382 | - | 0.0 | nan |
|
590 |
+
| 4.2198 | 384 | - | 0.0 | nan |
|
591 |
+
| 4.2418 | 386 | - | 0.0 | nan |
|
592 |
+
| 4.2637 | 388 | - | 0.0 | nan |
|
593 |
+
| 4.2857 | 390 | - | 0.0 | nan |
|
594 |
+
| 4.3077 | 392 | - | 0.0 | nan |
|
595 |
+
| 4.3297 | 394 | - | 0.0 | nan |
|
596 |
+
| 4.3516 | 396 | - | 0.0 | nan |
|
597 |
+
| 4.3736 | 398 | - | 0.0 | nan |
|
598 |
+
| 4.3956 | 400 | - | 0.0 | nan |
|
599 |
+
| 4.4176 | 402 | - | 0.0 | nan |
|
600 |
+
| 4.4396 | 404 | - | 0.0 | nan |
|
601 |
+
| 4.4615 | 406 | - | 0.0 | nan |
|
602 |
+
| 4.4835 | 408 | - | 0.0 | nan |
|
603 |
+
| 4.5055 | 410 | - | 0.0 | nan |
|
604 |
+
| 4.5275 | 412 | - | 0.0 | nan |
|
605 |
+
| 4.5495 | 414 | - | 0.0 | nan |
|
606 |
+
| 4.5714 | 416 | - | 0.0 | nan |
|
607 |
+
| 4.5934 | 418 | - | 0.0 | nan |
|
608 |
+
| 4.6154 | 420 | - | 0.0 | nan |
|
609 |
+
| 4.6374 | 422 | - | 0.0 | nan |
|
610 |
+
| 4.6593 | 424 | - | 0.0 | nan |
|
611 |
+
| 4.6813 | 426 | - | 0.0 | nan |
|
612 |
+
| 4.7033 | 428 | - | 0.0 | nan |
|
613 |
+
| 4.7253 | 430 | - | 0.0 | nan |
|
614 |
+
| 4.7473 | 432 | - | 0.0 | nan |
|
615 |
+
| 4.7692 | 434 | - | 0.0 | nan |
|
616 |
+
| 4.7912 | 436 | - | 0.0 | nan |
|
617 |
+
| 4.8132 | 438 | - | 0.0 | nan |
|
618 |
+
| 4.8352 | 440 | - | 0.0 | nan |
|
619 |
+
| 4.8571 | 442 | - | 0.0 | nan |
|
620 |
+
| 4.8791 | 444 | - | 0.0 | nan |
|
621 |
+
| 4.9011 | 446 | - | 0.0 | nan |
|
622 |
+
| 4.9231 | 448 | - | 0.0 | nan |
|
623 |
+
| 4.9451 | 450 | - | 0.0 | nan |
|
624 |
+
| 4.9670 | 452 | - | 0.0 | nan |
|
625 |
+
| 4.9890 | 454 | - | 0.0 | nan |
|
626 |
+
| 5.0110 | 456 | - | 0.0 | nan |
|
627 |
+
| 5.0330 | 458 | - | 0.0 | nan |
|
628 |
+
| 5.0549 | 460 | - | 0.0 | nan |
|
629 |
+
| 5.0769 | 462 | - | 0.0 | nan |
|
630 |
+
| 5.0989 | 464 | - | 0.0 | nan |
|
631 |
+
| 5.1209 | 466 | - | 0.0 | nan |
|
632 |
+
| 5.1429 | 468 | - | 0.0 | nan |
|
633 |
+
| 5.1648 | 470 | - | 0.0 | nan |
|
634 |
+
| 5.1868 | 472 | - | 0.0 | nan |
|
635 |
+
| 5.2088 | 474 | - | 0.0 | nan |
|
636 |
+
| 5.2308 | 476 | - | 0.0 | nan |
|
637 |
+
| 5.2527 | 478 | - | 0.0 | nan |
|
638 |
+
| 5.2747 | 480 | - | 0.0 | nan |
|
639 |
+
| 5.2967 | 482 | - | 0.0 | nan |
|
640 |
+
| 5.3187 | 484 | - | 0.0 | nan |
|
641 |
+
| 5.3407 | 486 | - | 0.0 | nan |
|
642 |
+
| 5.3626 | 488 | - | 0.0 | nan |
|
643 |
+
| 5.3846 | 490 | - | 0.0 | nan |
|
644 |
+
| 5.4066 | 492 | - | 0.0 | nan |
|
645 |
+
| 5.4286 | 494 | - | 0.0 | nan |
|
646 |
+
| 5.4505 | 496 | - | 0.0 | nan |
|
647 |
+
| 5.4725 | 498 | - | 0.0 | nan |
|
648 |
+
| **5.4945** | **500** | **0.0** | **0.0** | **nan** |
|
649 |
+
| 5.5165 | 502 | - | 0.0 | nan |
|
650 |
+
| 5.5385 | 504 | - | 0.0 | nan |
|
651 |
+
| 5.5604 | 506 | - | 0.0 | nan |
|
652 |
+
| 5.5824 | 508 | - | 0.0 | nan |
|
653 |
+
| 5.6044 | 510 | - | 0.0 | nan |
|
654 |
+
| 5.6264 | 512 | - | 0.0 | nan |
|
655 |
+
| 5.6484 | 514 | - | 0.0 | nan |
|
656 |
+
| 5.6703 | 516 | - | 0.0 | nan |
|
657 |
+
| 5.6923 | 518 | - | 0.0 | nan |
|
658 |
+
| 5.7143 | 520 | - | 0.0 | nan |
|
659 |
+
| 5.7363 | 522 | - | 0.0 | nan |
|
660 |
+
| 5.7582 | 524 | - | 0.0 | nan |
|
661 |
+
| 5.7802 | 526 | - | 0.0 | nan |
|
662 |
+
| 5.8022 | 528 | - | 0.0 | nan |
|
663 |
+
| 5.8242 | 530 | - | 0.0 | nan |
|
664 |
+
| 5.8462 | 532 | - | 0.0 | nan |
|
665 |
+
| 5.8681 | 534 | - | 0.0 | nan |
|
666 |
+
| 5.8901 | 536 | - | 0.0 | nan |
|
667 |
+
| 5.9121 | 538 | - | 0.0 | nan |
|
668 |
+
| 5.9341 | 540 | - | 0.0 | nan |
|
669 |
+
| 5.9560 | 542 | - | 0.0 | nan |
|
670 |
+
| 5.9780 | 544 | - | 0.0 | nan |
|
671 |
+
| 6.0 | 546 | - | 0.0 | nan |
|
672 |
+
| 6.0220 | 548 | - | 0.0 | nan |
|
673 |
+
| 6.0440 | 550 | - | 0.0 | nan |
|
674 |
+
| 6.0659 | 552 | - | 0.0 | nan |
|
675 |
+
| 6.0879 | 554 | - | 0.0 | nan |
|
676 |
+
| 6.1099 | 556 | - | 0.0 | nan |
|
677 |
+
| 6.1319 | 558 | - | 0.0 | nan |
|
678 |
+
| 6.1538 | 560 | - | 0.0 | nan |
|
679 |
+
| 6.1758 | 562 | - | 0.0 | nan |
|
680 |
+
| 6.1978 | 564 | - | 0.0 | nan |
|
681 |
+
| 6.2198 | 566 | - | 0.0 | nan |
|
682 |
+
| 6.2418 | 568 | - | 0.0 | nan |
|
683 |
+
| 6.2637 | 570 | - | 0.0 | nan |
|
684 |
+
| 6.2857 | 572 | - | 0.0 | nan |
|
685 |
+
| 6.3077 | 574 | - | 0.0 | nan |
|
686 |
+
| 6.3297 | 576 | - | 0.0 | nan |
|
687 |
+
| 6.3516 | 578 | - | 0.0 | nan |
|
688 |
+
| 6.3736 | 580 | - | 0.0 | nan |
|
689 |
+
| 6.3956 | 582 | - | 0.0 | nan |
|
690 |
+
| 6.4176 | 584 | - | 0.0 | nan |
|
691 |
+
| 6.4396 | 586 | - | 0.0 | nan |
|
692 |
+
| 6.4615 | 588 | - | 0.0 | nan |
|
693 |
+
| 6.4835 | 590 | - | 0.0 | nan |
|
694 |
+
| 6.5055 | 592 | - | 0.0 | nan |
|
695 |
+
| 6.5275 | 594 | - | 0.0 | nan |
|
696 |
+
| 6.5495 | 596 | - | 0.0 | nan |
|
697 |
+
| 6.5714 | 598 | - | 0.0 | nan |
|
698 |
+
| 6.5934 | 600 | - | 0.0 | nan |
|
699 |
+
| 6.6154 | 602 | - | 0.0 | nan |
|
700 |
+
| 6.6374 | 604 | - | 0.0 | nan |
|
701 |
+
| 6.6593 | 606 | - | 0.0 | nan |
|
702 |
+
| 6.6813 | 608 | - | 0.0 | nan |
|
703 |
+
| 6.7033 | 610 | - | 0.0 | nan |
|
704 |
+
| 6.7253 | 612 | - | 0.0 | nan |
|
705 |
+
| 6.7473 | 614 | - | 0.0 | nan |
|
706 |
+
| 6.7692 | 616 | - | 0.0 | nan |
|
707 |
+
| 6.7912 | 618 | - | 0.0 | nan |
|
708 |
+
| 6.8132 | 620 | - | 0.0 | nan |
|
709 |
+
| 6.8352 | 622 | - | 0.0 | nan |
|
710 |
+
| 6.8571 | 624 | - | 0.0 | nan |
|
711 |
+
| 6.8791 | 626 | - | 0.0 | nan |
|
712 |
+
| 6.9011 | 628 | - | 0.0 | nan |
|
713 |
+
| 6.9231 | 630 | - | 0.0 | nan |
|
714 |
+
| 6.9451 | 632 | - | 0.0 | nan |
|
715 |
+
| 6.9670 | 634 | - | 0.0 | nan |
|
716 |
+
| 6.9890 | 636 | - | 0.0 | nan |
|
717 |
+
| 7.0110 | 638 | - | 0.0 | nan |
|
718 |
+
| 7.0330 | 640 | - | 0.0 | nan |
|
719 |
+
| 7.0549 | 642 | - | 0.0 | nan |
|
720 |
+
| 7.0769 | 644 | - | 0.0 | nan |
|
721 |
+
| 7.0989 | 646 | - | 0.0 | nan |
|
722 |
+
| 7.1209 | 648 | - | 0.0 | nan |
|
723 |
+
| 7.1429 | 650 | - | 0.0 | nan |
|
724 |
+
| 7.1648 | 652 | - | 0.0 | nan |
|
725 |
+
| 7.1868 | 654 | - | 0.0 | nan |
|
726 |
+
| 7.2088 | 656 | - | 0.0 | nan |
|
727 |
+
| 7.2308 | 658 | - | 0.0 | nan |
|
728 |
+
| 7.2527 | 660 | - | 0.0 | nan |
|
729 |
+
| 7.2747 | 662 | - | 0.0 | nan |
|
730 |
+
| 7.2967 | 664 | - | 0.0 | nan |
|
731 |
+
| 7.3187 | 666 | - | 0.0 | nan |
|
732 |
+
| 7.3407 | 668 | - | 0.0 | nan |
|
733 |
+
| 7.3626 | 670 | - | 0.0 | nan |
|
734 |
+
| 7.3846 | 672 | - | 0.0 | nan |
|
735 |
+
| 7.4066 | 674 | - | 0.0 | nan |
|
736 |
+
| 7.4286 | 676 | - | 0.0 | nan |
|
737 |
+
| 7.4505 | 678 | - | 0.0 | nan |
|
738 |
+
| 7.4725 | 680 | - | 0.0 | nan |
|
739 |
+
| 7.4945 | 682 | - | 0.0 | nan |
|
740 |
+
| 7.5165 | 684 | - | 0.0 | nan |
|
741 |
+
| 7.5385 | 686 | - | 0.0 | nan |
|
742 |
+
| 7.5604 | 688 | - | 0.0 | nan |
|
743 |
+
| 7.5824 | 690 | - | 0.0 | nan |
|
744 |
+
| 7.6044 | 692 | - | 0.0 | nan |
|
745 |
+
| 7.6264 | 694 | - | 0.0 | nan |
|
746 |
+
| 7.6484 | 696 | - | 0.0 | nan |
|
747 |
+
| 7.6703 | 698 | - | 0.0 | nan |
|
748 |
+
| 7.6923 | 700 | - | 0.0 | nan |
|
749 |
+
| 7.7143 | 702 | - | 0.0 | nan |
|
750 |
+
| 7.7363 | 704 | - | 0.0 | nan |
|
751 |
+
| 7.7582 | 706 | - | 0.0 | nan |
|
752 |
+
| 7.7802 | 708 | - | 0.0 | nan |
|
753 |
+
| 7.8022 | 710 | - | 0.0 | nan |
|
754 |
+
| 7.8242 | 712 | - | 0.0 | nan |
|
755 |
+
| 7.8462 | 714 | - | 0.0 | nan |
|
756 |
+
| 7.8681 | 716 | - | 0.0 | nan |
|
757 |
+
| 7.8901 | 718 | - | 0.0 | nan |
|
758 |
+
| 7.9121 | 720 | - | 0.0 | nan |
|
759 |
+
| 7.9341 | 722 | - | 0.0 | nan |
|
760 |
+
| 7.9560 | 724 | - | 0.0 | nan |
|
761 |
+
| 7.9780 | 726 | - | 0.0 | nan |
|
762 |
+
| 8.0 | 728 | - | 0.0 | nan |
|
763 |
+
| 8.0220 | 730 | - | 0.0 | nan |
|
764 |
+
| 8.0440 | 732 | - | 0.0 | nan |
|
765 |
+
| 8.0659 | 734 | - | 0.0 | nan |
|
766 |
+
| 8.0879 | 736 | - | 0.0 | nan |
|
767 |
+
| 8.1099 | 738 | - | 0.0 | nan |
|
768 |
+
| 8.1319 | 740 | - | 0.0 | nan |
|
769 |
+
| 8.1538 | 742 | - | 0.0 | nan |
|
770 |
+
| 8.1758 | 744 | - | 0.0 | nan |
|
771 |
+
| 8.1978 | 746 | - | 0.0 | nan |
|
772 |
+
| 8.2198 | 748 | - | 0.0 | nan |
|
773 |
+
| 8.2418 | 750 | - | 0.0 | nan |
|
774 |
+
| 8.2637 | 752 | - | 0.0 | nan |
|
775 |
+
| 8.2857 | 754 | - | 0.0 | nan |
|
776 |
+
| 8.3077 | 756 | - | 0.0 | nan |
|
777 |
+
| 8.3297 | 758 | - | 0.0 | nan |
|
778 |
+
| 8.3516 | 760 | - | 0.0 | nan |
|
779 |
+
| 8.3736 | 762 | - | 0.0 | nan |
|
780 |
+
| 8.3956 | 764 | - | 0.0 | nan |
|
781 |
+
| 8.4176 | 766 | - | 0.0 | nan |
|
782 |
+
| 8.4396 | 768 | - | 0.0 | nan |
|
783 |
+
| 8.4615 | 770 | - | 0.0 | nan |
|
784 |
+
| 8.4835 | 772 | - | 0.0 | nan |
|
785 |
+
| 8.5055 | 774 | - | 0.0 | nan |
|
786 |
+
| 8.5275 | 776 | - | 0.0 | nan |
|
787 |
+
| 8.5495 | 778 | - | 0.0 | nan |
|
788 |
+
| 8.5714 | 780 | - | 0.0 | nan |
|
789 |
+
| 8.5934 | 782 | - | 0.0 | nan |
|
790 |
+
| 8.6154 | 784 | - | 0.0 | nan |
|
791 |
+
| 8.6374 | 786 | - | 0.0 | nan |
|
792 |
+
| 8.6593 | 788 | - | 0.0 | nan |
|
793 |
+
| 8.6813 | 790 | - | 0.0 | nan |
|
794 |
+
| 8.7033 | 792 | - | 0.0 | nan |
|
795 |
+
| 8.7253 | 794 | - | 0.0 | nan |
|
796 |
+
| 8.7473 | 796 | - | 0.0 | nan |
|
797 |
+
| 8.7692 | 798 | - | 0.0 | nan |
|
798 |
+
| 8.7912 | 800 | - | 0.0 | nan |
|
799 |
+
| 8.8132 | 802 | - | 0.0 | nan |
|
800 |
+
| 8.8352 | 804 | - | 0.0 | nan |
|
801 |
+
| 8.8571 | 806 | - | 0.0 | nan |
|
802 |
+
| 8.8791 | 808 | - | 0.0 | nan |
|
803 |
+
| 8.9011 | 810 | - | 0.0 | nan |
|
804 |
+
| 8.9231 | 812 | - | 0.0 | nan |
|
805 |
+
| 8.9451 | 814 | - | 0.0 | nan |
|
806 |
+
| 8.9670 | 816 | - | 0.0 | nan |
|
807 |
+
| 8.9890 | 818 | - | 0.0 | nan |
|
808 |
+
| 9.0110 | 820 | - | 0.0 | nan |
|
809 |
+
| 9.0330 | 822 | - | 0.0 | nan |
|
810 |
+
| 9.0549 | 824 | - | 0.0 | nan |
|
811 |
+
| 9.0769 | 826 | - | 0.0 | nan |
|
812 |
+
| 9.0989 | 828 | - | 0.0 | nan |
|
813 |
+
| 9.1209 | 830 | - | 0.0 | nan |
|
814 |
+
| 9.1429 | 832 | - | 0.0 | nan |
|
815 |
+
| 9.1648 | 834 | - | 0.0 | nan |
|
816 |
+
| 9.1868 | 836 | - | 0.0 | nan |
|
817 |
+
| 9.2088 | 838 | - | 0.0 | nan |
|
818 |
+
| 9.2308 | 840 | - | 0.0 | nan |
|
819 |
+
| 9.2527 | 842 | - | 0.0 | nan |
|
820 |
+
| 9.2747 | 844 | - | 0.0 | nan |
|
821 |
+
| 9.2967 | 846 | - | 0.0 | nan |
|
822 |
+
| 9.3187 | 848 | - | 0.0 | nan |
|
823 |
+
| 9.3407 | 850 | - | 0.0 | nan |
|
824 |
+
| 9.3626 | 852 | - | 0.0 | nan |
|
825 |
+
| 9.3846 | 854 | - | 0.0 | nan |
|
826 |
+
| 9.4066 | 856 | - | 0.0 | nan |
|
827 |
+
| 9.4286 | 858 | - | 0.0 | nan |
|
828 |
+
| 9.4505 | 860 | - | 0.0 | nan |
|
829 |
+
| 9.4725 | 862 | - | 0.0 | nan |
|
830 |
+
| 9.4945 | 864 | - | 0.0 | nan |
|
831 |
+
| 9.5165 | 866 | - | 0.0 | nan |
|
832 |
+
| 9.5385 | 868 | - | 0.0 | nan |
|
833 |
+
| 9.5604 | 870 | - | 0.0 | nan |
|
834 |
+
| 9.5824 | 872 | - | 0.0 | nan |
|
835 |
+
| 9.6044 | 874 | - | 0.0 | nan |
|
836 |
+
| 9.6264 | 876 | - | 0.0 | nan |
|
837 |
+
| 9.6484 | 878 | - | 0.0 | nan |
|
838 |
+
| 9.6703 | 880 | - | 0.0 | nan |
|
839 |
+
| 9.6923 | 882 | - | 0.0 | nan |
|
840 |
+
| 9.7143 | 884 | - | 0.0 | nan |
|
841 |
+
| 9.7363 | 886 | - | 0.0 | nan |
|
842 |
+
| 9.7582 | 888 | - | 0.0 | nan |
|
843 |
+
| 9.7802 | 890 | - | 0.0 | nan |
|
844 |
+
| 9.8022 | 892 | - | 0.0 | nan |
|
845 |
+
| 9.8242 | 894 | - | 0.0 | nan |
|
846 |
+
| 9.8462 | 896 | - | 0.0 | nan |
|
847 |
+
| 9.8681 | 898 | - | 0.0 | nan |
|
848 |
+
| 9.8901 | 900 | - | 0.0 | nan |
|
849 |
+
| 9.9121 | 902 | - | 0.0 | nan |
|
850 |
+
| 9.9341 | 904 | - | 0.0 | nan |
|
851 |
+
| 9.9560 | 906 | - | 0.0 | nan |
|
852 |
+
| 9.9780 | 908 | - | 0.0 | nan |
|
853 |
+
| 10.0 | 910 | - | 0.0 | nan |
|
854 |
+
|
855 |
+
* The bold row denotes the saved checkpoint.
|
856 |
+
</details>
|
857 |
+
|
858 |
+
### Framework Versions
|
859 |
+
- Python: 3.10.12
|
860 |
+
- Sentence Transformers: 3.0.1
|
861 |
+
- Transformers: 4.41.2
|
862 |
+
- PyTorch: 2.0.1+cu118
|
863 |
+
- Accelerate: 0.31.0
|
864 |
+
- Datasets: 2.20.0
|
865 |
+
- Tokenizers: 0.19.1
|
866 |
+
|
867 |
+
## Citation
|
868 |
+
|
869 |
+
### BibTeX
|
870 |
+
|
871 |
+
#### Sentence Transformers
|
872 |
+
```bibtex
|
873 |
+
@inproceedings{reimers-2019-sentence-bert,
|
874 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
875 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
876 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
877 |
+
month = "11",
|
878 |
+
year = "2019",
|
879 |
+
publisher = "Association for Computational Linguistics",
|
880 |
+
url = "https://arxiv.org/abs/1908.10084",
|
881 |
+
}
|
882 |
+
```
|
883 |
+
|
884 |
+
#### CoSENTLoss
|
885 |
+
```bibtex
|
886 |
+
@online{kexuefm-8847,
|
887 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
888 |
+
author={Su Jianlin},
|
889 |
+
year={2022},
|
890 |
+
month={Jan},
|
891 |
+
url={https://kexue.fm/archives/8847},
|
892 |
+
}
|
893 |
+
```
|
894 |
+
|
895 |
+
<!--
|
896 |
+
## Glossary
|
897 |
+
|
898 |
+
*Clearly define terms in order to be accessible across audiences.*
|
899 |
+
-->
|
900 |
+
|
901 |
+
<!--
|
902 |
+
## Model Card Authors
|
903 |
+
|
904 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
905 |
+
-->
|
906 |
+
|
907 |
+
<!--
|
908 |
+
## Model Card Contact
|
909 |
+
|
910 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
911 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/workspace/",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.0.1+cu118"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1377e9af0ca0b016a9f2aa584d6fc71ab3ea6804fae21ef9fb1416e2944057ac
|
3 |
+
size 90864192
|
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 |
+
"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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 128,
|
50 |
+
"model_max_length": 512,
|
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
|
|