Upload 11 files
Browse files- final/1_Pooling/config.json +10 -0
- final/README.md +858 -0
- final/config.json +24 -0
- final/config_sentence_transformers.json +10 -0
- final/model.safetensors +3 -0
- final/modules.json +20 -0
- final/sentence_bert_config.json +4 -0
- final/special_tokens_map.json +51 -0
- final/tokenizer.json +0 -0
- final/tokenizer_config.json +72 -0
- final/vocab.txt +0 -0
final/1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
final/README.md
ADDED
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
tags:
|
8 |
+
- sentence-transformers
|
9 |
+
- sentence-similarity
|
10 |
+
- feature-extraction
|
11 |
+
- generated_from_trainer
|
12 |
+
- dataset_size:756057
|
13 |
+
- loss:MultipleNegativesRankingLoss
|
14 |
+
widget:
|
15 |
+
- source_sentence: 府君奈何以盖世之才欲立忠于垂亡之国
|
16 |
+
sentences:
|
17 |
+
- 将远方进贡来的奇兽飞禽以及白山鸡等物纵还山林比起雍畤的祭祀礼数颇有增加
|
18 |
+
- 您为什么以盖绝当世的奇才却打算向这个面临灭亡的国家尽效忠心呢
|
19 |
+
- 大统年间他出任岐州刺史在任不久就因为能力强而闻名
|
20 |
+
- source_sentence: 将率既至授单于印绂诏令上故印绂
|
21 |
+
sentences:
|
22 |
+
- 已经到达的五威将到达后授给单于新印信宣读诏书要求交回汉朝旧印信
|
23 |
+
- 于是拜陶隗为西南面招讨使
|
24 |
+
- 司马错建议秦惠王攻打蜀国张仪说 还不如进攻韩国
|
25 |
+
- source_sentence: 行醮礼皇太子诣醴席乐作
|
26 |
+
sentences:
|
27 |
+
- 闰七月十七日上宣宗废除皇后胡氏尊谥
|
28 |
+
- 等到看见西羌鼠窃狗盗父不父子不子君臣没有分别四夷之人西羌最为低下
|
29 |
+
- 行醮礼皇太子来到酒醴席奏乐
|
30 |
+
- source_sentence: 领军臧盾太府卿沈僧果等并被时遇孝绰尤轻之
|
31 |
+
sentences:
|
32 |
+
- 过了几天太宰官又来要国书并且说 我国自太宰府以东上国使臣没有到过今大朝派使臣来若不见国书何以相信
|
33 |
+
- 所以丹阳葛洪解释说浑天仪注说 天体像鸡蛋地就像是鸡蛋中的蛋黄独处于天体之内天是大的而地是小的
|
34 |
+
- 领军臧盾太府卿沈僧果等都是因赶上时机而得到官职的孝绰尤其轻蔑他们每次在朝中集合会面虽然一起做官但从不与他们说话
|
35 |
+
- source_sentence: 九月辛未太祖曾孙舒国公从式进封安定郡王
|
36 |
+
sentences:
|
37 |
+
- 九月初二太祖曾孙舒国公从式进封安定郡王
|
38 |
+
- 杨难当在汉中大肆烧杀抢劫然后率众离开了汉中向西返回仇池留下赵温据守梁州又派他的魏兴太守薛健屯驻黄金山
|
39 |
+
- 正统元年普定蛮夷阿迟等反叛非法称王四处出击攻打掠夺
|
40 |
+
---
|
41 |
+
|
42 |
+
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
|
43 |
+
|
44 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
45 |
+
|
46 |
+
## Model Details
|
47 |
+
|
48 |
+
### Model Description
|
49 |
+
- **Model Type:** Sentence Transformer
|
50 |
+
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 84f2bcc00d77236f9e89c8a360a00fb1139bf47d -->
|
51 |
+
- **Maximum Sequence Length:** 384 tokens
|
52 |
+
- **Output Dimensionality:** 768 tokens
|
53 |
+
- **Similarity Function:** Cosine Similarity
|
54 |
+
<!-- - **Training Dataset:** Unknown -->
|
55 |
+
<!-- - **Language:** Unknown -->
|
56 |
+
<!-- - **License:** Unknown -->
|
57 |
+
|
58 |
+
### Model Sources
|
59 |
+
|
60 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
61 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
62 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
63 |
+
|
64 |
+
### Full Model Architecture
|
65 |
+
|
66 |
+
```
|
67 |
+
SentenceTransformer(
|
68 |
+
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
|
69 |
+
(1): Pooling({'word_embedding_dimension': 768, '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})
|
70 |
+
(2): Normalize()
|
71 |
+
)
|
72 |
+
```
|
73 |
+
|
74 |
+
## Usage
|
75 |
+
|
76 |
+
### Direct Usage (Sentence Transformers)
|
77 |
+
|
78 |
+
First install the Sentence Transformers library:
|
79 |
+
|
80 |
+
```bash
|
81 |
+
pip install -U sentence-transformers
|
82 |
+
```
|
83 |
+
|
84 |
+
Then you can load this model and run inference.
|
85 |
+
```python
|
86 |
+
from sentence_transformers import SentenceTransformer
|
87 |
+
|
88 |
+
# Download from the 🤗 Hub
|
89 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
90 |
+
# Run inference
|
91 |
+
sentences = [
|
92 |
+
'九月辛未太祖曾孙舒国公从式进封安定郡王',
|
93 |
+
'九月初二太祖曾孙舒国公从式进封安定郡王',
|
94 |
+
'杨难当在汉中大肆烧杀抢劫然后率众离开了汉中向西返回仇池留下赵温据守梁州又派他的魏兴太守薛健屯驻黄金山',
|
95 |
+
]
|
96 |
+
embeddings = model.encode(sentences)
|
97 |
+
print(embeddings.shape)
|
98 |
+
# [3, 768]
|
99 |
+
|
100 |
+
# Get the similarity scores for the embeddings
|
101 |
+
similarities = model.similarity(embeddings, embeddings)
|
102 |
+
print(similarities.shape)
|
103 |
+
# [3, 3]
|
104 |
+
```
|
105 |
+
|
106 |
+
<!--
|
107 |
+
### Direct Usage (Transformers)
|
108 |
+
|
109 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
110 |
+
|
111 |
+
</details>
|
112 |
+
-->
|
113 |
+
|
114 |
+
<!--
|
115 |
+
### Downstream Usage (Sentence Transformers)
|
116 |
+
|
117 |
+
You can finetune this model on your own dataset.
|
118 |
+
|
119 |
+
<details><summary>Click to expand</summary>
|
120 |
+
|
121 |
+
</details>
|
122 |
+
-->
|
123 |
+
|
124 |
+
<!--
|
125 |
+
### Out-of-Scope Use
|
126 |
+
|
127 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
128 |
+
-->
|
129 |
+
|
130 |
+
<!--
|
131 |
+
## Bias, Risks and Limitations
|
132 |
+
|
133 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
134 |
+
-->
|
135 |
+
|
136 |
+
<!--
|
137 |
+
### Recommendations
|
138 |
+
|
139 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
140 |
+
-->
|
141 |
+
|
142 |
+
## Training Details
|
143 |
+
|
144 |
+
### Training Dataset
|
145 |
+
|
146 |
+
#### Unnamed Dataset
|
147 |
+
|
148 |
+
|
149 |
+
* Size: 756,057 training samples
|
150 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
151 |
+
* Approximate statistics based on the first 1000 samples:
|
152 |
+
| | anchor | positive |
|
153 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
154 |
+
| type | string | string |
|
155 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 20.76 tokens</li><li>max: 199 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.27 tokens</li><li>max: 384 tokens</li></ul> |
|
156 |
+
* Samples:
|
157 |
+
| anchor | positive |
|
158 |
+
|:------------------------------------------|:------------------------------------------------------------|
|
159 |
+
| <code>虏怀兼弱之威挟广地之计强兵大众亲自凌殄旍鼓弥年矢石不息</code> | <code>魏人怀有兼并弱小的威严胸藏拓展土地的计谋强人的军队亲自出征侵逼消灭旌旗战鼓连年出动战事不停息</code> |
|
160 |
+
| <code>孟子曰 以善服人者未有能服人者也以善养人然后能服天下</code> | <code>孟子说 用自己的善良使人们服从的人没有能使人服从的用善良影响教导人们才能使天下的人们都信服</code> |
|
161 |
+
| <code>开庆初大元兵渡江理宗议迁都平江庆元后谏不可恐摇动民心乃止</code> | <code>开庆初年大元朝部队渡过长江理宗打算迁都到平江庆元皇后劝谏不可迁都深恐动摇民心理宗才作罢</code> |
|
162 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
163 |
+
```json
|
164 |
+
{
|
165 |
+
"scale": 20.0,
|
166 |
+
"similarity_fct": "cos_sim"
|
167 |
+
}
|
168 |
+
```
|
169 |
+
|
170 |
+
### Evaluation Dataset
|
171 |
+
|
172 |
+
#### Unnamed Dataset
|
173 |
+
|
174 |
+
|
175 |
+
* Size: 84,007 evaluation samples
|
176 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
177 |
+
* Approximate statistics based on the first 1000 samples:
|
178 |
+
| | anchor | positive |
|
179 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
180 |
+
| type | string | string |
|
181 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 20.23 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.42 tokens</li><li>max: 384 tokens</li></ul> |
|
182 |
+
* Samples:
|
183 |
+
| anchor | positive |
|
184 |
+
|:--------------------------------------------------|:------------------------------------------------------------------|
|
185 |
+
| <code>雒阳户五万二千八百三十九</code> | <code>雒阳有五万二千八百三十九户</code> |
|
186 |
+
| <code>拜南青州刺史在任有政绩</code> | <code>任南青州刺史很有政绩</code> |
|
187 |
+
| <code>第六品以下加不得服金钅奠绫锦锦绣七缘绮貂豽裘金叉环铒及以金校饰器物张绛帐</code> | <code>官位在第六品以下的官员再增加不得穿用金钿绫锦锦绣七缘绮貂钠皮衣金叉缳饵以及用金装饰的器物张绛帐等衣服物品</code> |
|
188 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
189 |
+
```json
|
190 |
+
{
|
191 |
+
"scale": 20.0,
|
192 |
+
"similarity_fct": "cos_sim"
|
193 |
+
}
|
194 |
+
```
|
195 |
+
|
196 |
+
### Training Hyperparameters
|
197 |
+
#### Non-Default Hyperparameters
|
198 |
+
|
199 |
+
- `eval_strategy`: steps
|
200 |
+
- `per_device_train_batch_size`: 16
|
201 |
+
- `per_device_eval_batch_size`: 16
|
202 |
+
- `num_train_epochs`: 1
|
203 |
+
- `warmup_ratio`: 0.1
|
204 |
+
- `fp16`: True
|
205 |
+
- `load_best_model_at_end`: True
|
206 |
+
- `batch_sampler`: no_duplicates
|
207 |
+
|
208 |
+
#### All Hyperparameters
|
209 |
+
<details><summary>Click to expand</summary>
|
210 |
+
|
211 |
+
- `overwrite_output_dir`: False
|
212 |
+
- `do_predict`: False
|
213 |
+
- `eval_strategy`: steps
|
214 |
+
- `prediction_loss_only`: True
|
215 |
+
- `per_device_train_batch_size`: 16
|
216 |
+
- `per_device_eval_batch_size`: 16
|
217 |
+
- `per_gpu_train_batch_size`: None
|
218 |
+
- `per_gpu_eval_batch_size`: None
|
219 |
+
- `gradient_accumulation_steps`: 1
|
220 |
+
- `eval_accumulation_steps`: None
|
221 |
+
- `learning_rate`: 5e-05
|
222 |
+
- `weight_decay`: 0.0
|
223 |
+
- `adam_beta1`: 0.9
|
224 |
+
- `adam_beta2`: 0.999
|
225 |
+
- `adam_epsilon`: 1e-08
|
226 |
+
- `max_grad_norm`: 1.0
|
227 |
+
- `num_train_epochs`: 1
|
228 |
+
- `max_steps`: -1
|
229 |
+
- `lr_scheduler_type`: linear
|
230 |
+
- `lr_scheduler_kwargs`: {}
|
231 |
+
- `warmup_ratio`: 0.1
|
232 |
+
- `warmup_steps`: 0
|
233 |
+
- `log_level`: passive
|
234 |
+
- `log_level_replica`: warning
|
235 |
+
- `log_on_each_node`: True
|
236 |
+
- `logging_nan_inf_filter`: True
|
237 |
+
- `save_safetensors`: True
|
238 |
+
- `save_on_each_node`: False
|
239 |
+
- `save_only_model`: False
|
240 |
+
- `restore_callback_states_from_checkpoint`: False
|
241 |
+
- `no_cuda`: False
|
242 |
+
- `use_cpu`: False
|
243 |
+
- `use_mps_device`: False
|
244 |
+
- `seed`: 42
|
245 |
+
- `data_seed`: None
|
246 |
+
- `jit_mode_eval`: False
|
247 |
+
- `use_ipex`: False
|
248 |
+
- `bf16`: False
|
249 |
+
- `fp16`: True
|
250 |
+
- `fp16_opt_level`: O1
|
251 |
+
- `half_precision_backend`: auto
|
252 |
+
- `bf16_full_eval`: False
|
253 |
+
- `fp16_full_eval`: False
|
254 |
+
- `tf32`: None
|
255 |
+
- `local_rank`: 0
|
256 |
+
- `ddp_backend`: None
|
257 |
+
- `tpu_num_cores`: None
|
258 |
+
- `tpu_metrics_debug`: False
|
259 |
+
- `debug`: []
|
260 |
+
- `dataloader_drop_last`: False
|
261 |
+
- `dataloader_num_workers`: 0
|
262 |
+
- `dataloader_prefetch_factor`: None
|
263 |
+
- `past_index`: -1
|
264 |
+
- `disable_tqdm`: False
|
265 |
+
- `remove_unused_columns`: True
|
266 |
+
- `label_names`: None
|
267 |
+
- `load_best_model_at_end`: True
|
268 |
+
- `ignore_data_skip`: False
|
269 |
+
- `fsdp`: []
|
270 |
+
- `fsdp_min_num_params`: 0
|
271 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
272 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
273 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
274 |
+
- `deepspeed`: None
|
275 |
+
- `label_smoothing_factor`: 0.0
|
276 |
+
- `optim`: adamw_torch
|
277 |
+
- `optim_args`: None
|
278 |
+
- `adafactor`: False
|
279 |
+
- `group_by_length`: False
|
280 |
+
- `length_column_name`: length
|
281 |
+
- `ddp_find_unused_parameters`: None
|
282 |
+
- `ddp_bucket_cap_mb`: None
|
283 |
+
- `ddp_broadcast_buffers`: False
|
284 |
+
- `dataloader_pin_memory`: True
|
285 |
+
- `dataloader_persistent_workers`: False
|
286 |
+
- `skip_memory_metrics`: True
|
287 |
+
- `use_legacy_prediction_loop`: False
|
288 |
+
- `push_to_hub`: False
|
289 |
+
- `resume_from_checkpoint`: None
|
290 |
+
- `hub_model_id`: None
|
291 |
+
- `hub_strategy`: every_save
|
292 |
+
- `hub_private_repo`: False
|
293 |
+
- `hub_always_push`: False
|
294 |
+
- `gradient_checkpointing`: False
|
295 |
+
- `gradient_checkpointing_kwargs`: None
|
296 |
+
- `include_inputs_for_metrics`: False
|
297 |
+
- `eval_do_concat_batches`: True
|
298 |
+
- `fp16_backend`: auto
|
299 |
+
- `push_to_hub_model_id`: None
|
300 |
+
- `push_to_hub_organization`: None
|
301 |
+
- `mp_parameters`:
|
302 |
+
- `auto_find_batch_size`: False
|
303 |
+
- `full_determinism`: False
|
304 |
+
- `torchdynamo`: None
|
305 |
+
- `ray_scope`: last
|
306 |
+
- `ddp_timeout`: 1800
|
307 |
+
- `torch_compile`: False
|
308 |
+
- `torch_compile_backend`: None
|
309 |
+
- `torch_compile_mode`: None
|
310 |
+
- `dispatch_batches`: None
|
311 |
+
- `split_batches`: None
|
312 |
+
- `include_tokens_per_second`: False
|
313 |
+
- `include_num_input_tokens_seen`: False
|
314 |
+
- `neftune_noise_alpha`: None
|
315 |
+
- `optim_target_modules`: None
|
316 |
+
- `batch_eval_metrics`: False
|
317 |
+
- `eval_on_start`: False
|
318 |
+
- `batch_sampler`: no_duplicates
|
319 |
+
- `multi_dataset_batch_sampler`: proportional
|
320 |
+
|
321 |
+
</details>
|
322 |
+
|
323 |
+
### Training Logs
|
324 |
+
<details><summary>Click to expand</summary>
|
325 |
+
|
326 |
+
| Epoch | Step | Training Loss | loss |
|
327 |
+
|:----------:|:---------:|:-------------:|:--------:|
|
328 |
+
| 0.0021 | 100 | 0.6475 | - |
|
329 |
+
| 0.0042 | 200 | 0.5193 | - |
|
330 |
+
| 0.0063 | 300 | 0.4132 | - |
|
331 |
+
| 0.0085 | 400 | 0.3981 | - |
|
332 |
+
| 0.0106 | 500 | 0.4032 | - |
|
333 |
+
| 0.0127 | 600 | 0.3627 | - |
|
334 |
+
| 0.0148 | 700 | 0.3821 | - |
|
335 |
+
| 0.0169 | 800 | 0.3767 | - |
|
336 |
+
| 0.0190 | 900 | 0.3731 | - |
|
337 |
+
| 0.0212 | 1000 | 0.3744 | - |
|
338 |
+
| 0.0233 | 1100 | 0.3115 | - |
|
339 |
+
| 0.0254 | 1200 | 0.3998 | - |
|
340 |
+
| 0.0275 | 1300 | 0.3103 | - |
|
341 |
+
| 0.0296 | 1400 | 0.3251 | - |
|
342 |
+
| 0.0317 | 1500 | 0.2833 | - |
|
343 |
+
| 0.0339 | 1600 | 0.3335 | - |
|
344 |
+
| 0.0360 | 1700 | 0.3281 | - |
|
345 |
+
| 0.0381 | 1800 | 0.423 | - |
|
346 |
+
| 0.0402 | 1900 | 0.3687 | - |
|
347 |
+
| 0.0423 | 2000 | 0.3452 | - |
|
348 |
+
| 0.0444 | 2100 | 0.8643 | - |
|
349 |
+
| 0.0466 | 2200 | 0.4279 | - |
|
350 |
+
| 0.0487 | 2300 | 0.4188 | - |
|
351 |
+
| 0.0508 | 2400 | 0.3676 | - |
|
352 |
+
| 0.0529 | 2500 | 0.3279 | - |
|
353 |
+
| 0.0550 | 2600 | 0.3415 | - |
|
354 |
+
| 0.0571 | 2700 | 1.5834 | - |
|
355 |
+
| 0.0593 | 2800 | 2.7778 | - |
|
356 |
+
| 0.0614 | 2900 | 2.7734 | - |
|
357 |
+
| 0.0635 | 3000 | 2.7732 | - |
|
358 |
+
| 0.0656 | 3100 | 2.7751 | - |
|
359 |
+
| 0.0677 | 3200 | 2.7731 | - |
|
360 |
+
| 0.0698 | 3300 | 2.773 | - |
|
361 |
+
| 0.0720 | 3400 | 2.7727 | - |
|
362 |
+
| 0.0741 | 3500 | 2.7534 | - |
|
363 |
+
| 0.0762 | 3600 | 2.2219 | - |
|
364 |
+
| 0.0783 | 3700 | 0.5137 | - |
|
365 |
+
| 0.0804 | 3800 | 0.4143 | - |
|
366 |
+
| 0.0825 | 3900 | 0.4002 | - |
|
367 |
+
| 0.0846 | 4000 | 0.368 | - |
|
368 |
+
| 0.0868 | 4100 | 0.3879 | - |
|
369 |
+
| 0.0889 | 4200 | 0.3519 | - |
|
370 |
+
| 0.0910 | 4300 | 0.364 | - |
|
371 |
+
| 0.0931 | 4400 | 0.3618 | - |
|
372 |
+
| 0.0952 | 4500 | 0.3545 | - |
|
373 |
+
| 0.0973 | 4600 | 0.379 | - |
|
374 |
+
| 0.0995 | 4700 | 0.3837 | - |
|
375 |
+
| 0.1016 | 4800 | 0.3553 | - |
|
376 |
+
| 0.1037 | 4900 | 0.3519 | - |
|
377 |
+
| 0.1058 | 5000 | 0.3416 | 0.3487 |
|
378 |
+
| 0.1079 | 5100 | 0.3763 | - |
|
379 |
+
| 0.1100 | 5200 | 0.3748 | - |
|
380 |
+
| 0.1122 | 5300 | 0.3564 | - |
|
381 |
+
| 0.1143 | 5400 | 0.336 | - |
|
382 |
+
| 0.1164 | 5500 | 0.3601 | - |
|
383 |
+
| 0.1185 | 5600 | 0.3521 | - |
|
384 |
+
| 0.1206 | 5700 | 0.376 | - |
|
385 |
+
| 0.1227 | 5800 | 0.3011 | - |
|
386 |
+
| 0.1249 | 5900 | 0.345 | - |
|
387 |
+
| 0.1270 | 6000 | 0.3211 | - |
|
388 |
+
| 0.1291 | 6100 | 0.3673 | - |
|
389 |
+
| 0.1312 | 6200 | 0.3762 | - |
|
390 |
+
| 0.1333 | 6300 | 0.3562 | - |
|
391 |
+
| 0.1354 | 6400 | 0.2761 | - |
|
392 |
+
| 0.1376 | 6500 | 0.3186 | - |
|
393 |
+
| 0.1397 | 6600 | 0.3582 | - |
|
394 |
+
| 0.1418 | 6700 | 0.3454 | - |
|
395 |
+
| 0.1439 | 6800 | 0.3429 | - |
|
396 |
+
| 0.1460 | 6900 | 0.2932 | - |
|
397 |
+
| 0.1481 | 7000 | 0.3357 | - |
|
398 |
+
| 0.1503 | 7100 | 0.2979 | - |
|
399 |
+
| 0.1524 | 7200 | 0.313 | - |
|
400 |
+
| 0.1545 | 7300 | 0.3364 | - |
|
401 |
+
| 0.1566 | 7400 | 0.3459 | - |
|
402 |
+
| 0.1587 | 7500 | 0.279 | - |
|
403 |
+
| 0.1608 | 7600 | 0.3274 | - |
|
404 |
+
| 0.1629 | 7700 | 0.3367 | - |
|
405 |
+
| 0.1651 | 7800 | 0.2935 | - |
|
406 |
+
| 0.1672 | 7900 | 0.3415 | - |
|
407 |
+
| 0.1693 | 8000 | 0.2838 | - |
|
408 |
+
| 0.1714 | 8100 | 0.2667 | - |
|
409 |
+
| 0.1735 | 8200 | 0.3051 | - |
|
410 |
+
| 0.1756 | 8300 | 0.3197 | - |
|
411 |
+
| 0.1778 | 8400 | 0.3086 | - |
|
412 |
+
| 0.1799 | 8500 | 0.3186 | - |
|
413 |
+
| 0.1820 | 8600 | 0.3063 | - |
|
414 |
+
| 0.1841 | 8700 | 0.2967 | - |
|
415 |
+
| 0.1862 | 8800 | 0.3069 | - |
|
416 |
+
| 0.1883 | 8900 | 0.3391 | - |
|
417 |
+
| 0.1905 | 9000 | 0.335 | - |
|
418 |
+
| 0.1926 | 9100 | 0.3115 | - |
|
419 |
+
| 0.1947 | 9200 | 0.3214 | - |
|
420 |
+
| 0.1968 | 9300 | 0.278 | - |
|
421 |
+
| 0.1989 | 9400 | 0.2833 | - |
|
422 |
+
| 0.2010 | 9500 | 0.303 | - |
|
423 |
+
| 0.2032 | 9600 | 0.3238 | - |
|
424 |
+
| 0.2053 | 9700 | 0.2622 | - |
|
425 |
+
| 0.2074 | 9800 | 0.3295 | - |
|
426 |
+
| 0.2095 | 9900 | 0.2699 | - |
|
427 |
+
| 0.2116 | 10000 | 0.2426 | 0.2962 |
|
428 |
+
| 0.2137 | 10100 | 0.262 | - |
|
429 |
+
| 0.2159 | 10200 | 0.3199 | - |
|
430 |
+
| 0.2180 | 10300 | 0.3677 | - |
|
431 |
+
| 0.2201 | 10400 | 0.2423 | - |
|
432 |
+
| 0.2222 | 10500 | 0.3446 | - |
|
433 |
+
| 0.2243 | 10600 | 0.3002 | - |
|
434 |
+
| 0.2264 | 10700 | 0.2863 | - |
|
435 |
+
| 0.2286 | 10800 | 0.2692 | - |
|
436 |
+
| 0.2307 | 10900 | 0.3157 | - |
|
437 |
+
| 0.2328 | 11000 | 0.3172 | - |
|
438 |
+
| 0.2349 | 11100 | 0.3622 | - |
|
439 |
+
| 0.2370 | 11200 | 0.3019 | - |
|
440 |
+
| 0.2391 | 11300 | 0.2789 | - |
|
441 |
+
| 0.2412 | 11400 | 0.2872 | - |
|
442 |
+
| 0.2434 | 11500 | 0.2823 | - |
|
443 |
+
| 0.2455 | 11600 | 0.3017 | - |
|
444 |
+
| 0.2476 | 11700 | 0.2573 | - |
|
445 |
+
| 0.2497 | 11800 | 0.3104 | - |
|
446 |
+
| 0.2518 | 11900 | 0.2857 | - |
|
447 |
+
| 0.2539 | 12000 | 0.2898 | - |
|
448 |
+
| 0.2561 | 12100 | 0.2389 | - |
|
449 |
+
| 0.2582 | 12200 | 0.3137 | - |
|
450 |
+
| 0.2603 | 12300 | 0.3029 | - |
|
451 |
+
| 0.2624 | 12400 | 0.2894 | - |
|
452 |
+
| 0.2645 | 12500 | 0.2665 | - |
|
453 |
+
| 0.2666 | 12600 | 0.2705 | - |
|
454 |
+
| 0.2688 | 12700 | 0.2673 | - |
|
455 |
+
| 0.2709 | 12800 | 0.248 | - |
|
456 |
+
| 0.2730 | 12900 | 0.2417 | - |
|
457 |
+
| 0.2751 | 13000 | 0.2852 | - |
|
458 |
+
| 0.2772 | 13100 | 0.2619 | - |
|
459 |
+
| 0.2793 | 13200 | 0.3157 | - |
|
460 |
+
| 0.2815 | 13300 | 0.2464 | - |
|
461 |
+
| 0.2836 | 13400 | 0.2837 | - |
|
462 |
+
| 0.2857 | 13500 | 0.3202 | - |
|
463 |
+
| 0.2878 | 13600 | 0.2618 | - |
|
464 |
+
| 0.2899 | 13700 | 0.2823 | - |
|
465 |
+
| 0.2920 | 13800 | 0.2634 | - |
|
466 |
+
| 0.2942 | 13900 | 0.2747 | - |
|
467 |
+
| 0.2963 | 14000 | 0.2835 | - |
|
468 |
+
| 0.2984 | 14100 | 0.2594 | - |
|
469 |
+
| 0.3005 | 14200 | 0.2744 | - |
|
470 |
+
| 0.3026 | 14300 | 0.2722 | - |
|
471 |
+
| 0.3047 | 14400 | 0.2514 | - |
|
472 |
+
| 0.3069 | 14500 | 0.2809 | - |
|
473 |
+
| 0.3090 | 14600 | 0.2949 | - |
|
474 |
+
| 0.3111 | 14700 | 0.2687 | - |
|
475 |
+
| 0.3132 | 14800 | 0.3 | - |
|
476 |
+
| 0.3153 | 14900 | 0.2684 | - |
|
477 |
+
| 0.3174 | 15000 | 0.2894 | 0.2790 |
|
478 |
+
| 0.3195 | 15100 | 0.2676 | - |
|
479 |
+
| 0.3217 | 15200 | 0.2519 | - |
|
480 |
+
| 0.3238 | 15300 | 0.2698 | - |
|
481 |
+
| 0.3259 | 15400 | 0.2898 | - |
|
482 |
+
| 0.3280 | 15500 | 0.2359 | - |
|
483 |
+
| 0.3301 | 15600 | 0.2866 | - |
|
484 |
+
| 0.3322 | 15700 | 0.3098 | - |
|
485 |
+
| 0.3344 | 15800 | 0.2809 | - |
|
486 |
+
| 0.3365 | 15900 | 0.3081 | - |
|
487 |
+
| 0.3386 | 16000 | 0.266 | - |
|
488 |
+
| 0.3407 | 16100 | 0.2523 | - |
|
489 |
+
| 0.3428 | 16200 | 0.3215 | - |
|
490 |
+
| 0.3449 | 16300 | 0.2883 | - |
|
491 |
+
| 0.3471 | 16400 | 0.2897 | - |
|
492 |
+
| 0.3492 | 16500 | 0.3174 | - |
|
493 |
+
| 0.3513 | 16600 | 0.2878 | - |
|
494 |
+
| 0.3534 | 16700 | 0.267 | - |
|
495 |
+
| 0.3555 | 16800 | 0.2452 | - |
|
496 |
+
| 0.3576 | 16900 | 0.2429 | - |
|
497 |
+
| 0.3598 | 17000 | 0.2178 | - |
|
498 |
+
| 0.3619 | 17100 | 0.2798 | - |
|
499 |
+
| 0.3640 | 17200 | 0.2367 | - |
|
500 |
+
| 0.3661 | 17300 | 0.2554 | - |
|
501 |
+
| 0.3682 | 17400 | 0.2883 | - |
|
502 |
+
| 0.3703 | 17500 | 0.2567 | - |
|
503 |
+
| 0.3725 | 17600 | 0.27 | - |
|
504 |
+
| 0.3746 | 17700 | 0.2837 | - |
|
505 |
+
| 0.3767 | 17800 | 0.2783 | - |
|
506 |
+
| 0.3788 | 17900 | 0.2517 | - |
|
507 |
+
| 0.3809 | 18000 | 0.2545 | - |
|
508 |
+
| 0.3830 | 18100 | 0.2632 | - |
|
509 |
+
| 0.3852 | 18200 | 0.2074 | - |
|
510 |
+
| 0.3873 | 18300 | 0.2276 | - |
|
511 |
+
| 0.3894 | 18400 | 0.3022 | - |
|
512 |
+
| 0.3915 | 18500 | 0.2381 | - |
|
513 |
+
| 0.3936 | 18600 | 0.2552 | - |
|
514 |
+
| 0.3957 | 18700 | 0.2579 | - |
|
515 |
+
| 0.3978 | 18800 | 0.2655 | - |
|
516 |
+
| 0.4000 | 18900 | 0.252 | - |
|
517 |
+
| 0.4021 | 19000 | 0.2876 | - |
|
518 |
+
| 0.4042 | 19100 | 0.2037 | - |
|
519 |
+
| 0.4063 | 19200 | 0.251 | - |
|
520 |
+
| 0.4084 | 19300 | 0.2588 | - |
|
521 |
+
| 0.4105 | 19400 | 0.201 | - |
|
522 |
+
| 0.4127 | 19500 | 0.2828 | - |
|
523 |
+
| 0.4148 | 19600 | 0.2637 | - |
|
524 |
+
| 0.4169 | 19700 | 0.3233 | - |
|
525 |
+
| 0.4190 | 19800 | 0.2475 | - |
|
526 |
+
| 0.4211 | 19900 | 0.2618 | - |
|
527 |
+
| 0.4232 | 20000 | 0.3272 | 0.2519 |
|
528 |
+
| 0.4254 | 20100 | 0.3074 | - |
|
529 |
+
| 0.4275 | 20200 | 0.2994 | - |
|
530 |
+
| 0.4296 | 20300 | 0.2624 | - |
|
531 |
+
| 0.4317 | 20400 | 0.2389 | - |
|
532 |
+
| 0.4338 | 20500 | 0.2809 | - |
|
533 |
+
| 0.4359 | 20600 | 0.2659 | - |
|
534 |
+
| 0.4381 | 20700 | 0.2508 | - |
|
535 |
+
| 0.4402 | 20800 | 0.2542 | - |
|
536 |
+
| 0.4423 | 20900 | 0.2525 | - |
|
537 |
+
| 0.4444 | 21000 | 0.257 | - |
|
538 |
+
| 0.4465 | 21100 | 0.2242 | - |
|
539 |
+
| 0.4486 | 21200 | 0.2307 | - |
|
540 |
+
| 0.4508 | 21300 | 0.2721 | - |
|
541 |
+
| 0.4529 | 21400 | 0.2489 | - |
|
542 |
+
| 0.4550 | 21500 | 0.2933 | - |
|
543 |
+
| 0.4571 | 21600 | 0.2448 | - |
|
544 |
+
| 0.4592 | 21700 | 0.2619 | - |
|
545 |
+
| 0.4613 | 21800 | 0.2488 | - |
|
546 |
+
| 0.4635 | 21900 | 0.2411 | - |
|
547 |
+
| 0.4656 | 22000 | 0.2964 | - |
|
548 |
+
| 0.4677 | 22100 | 0.2062 | - |
|
549 |
+
| 0.4698 | 22200 | 0.2665 | - |
|
550 |
+
| 0.4719 | 22300 | 0.263 | - |
|
551 |
+
| 0.4740 | 22400 | 0.2418 | - |
|
552 |
+
| 0.4762 | 22500 | 0.2879 | - |
|
553 |
+
| 0.4783 | 22600 | 0.2406 | - |
|
554 |
+
| 0.4804 | 22700 | 0.2448 | - |
|
555 |
+
| 0.4825 | 22800 | 0.243 | - |
|
556 |
+
| 0.4846 | 22900 | 0.2863 | - |
|
557 |
+
| 0.4867 | 23000 | 0.2833 | - |
|
558 |
+
| 0.4888 | 23100 | 0.2784 | - |
|
559 |
+
| 0.4910 | 23200 | 0.2789 | - |
|
560 |
+
| 0.4931 | 23300 | 0.2495 | - |
|
561 |
+
| 0.4952 | 23400 | 0.2872 | - |
|
562 |
+
| 0.4973 | 23500 | 0.2487 | - |
|
563 |
+
| 0.4994 | 23600 | 0.2669 | - |
|
564 |
+
| 0.5015 | 23700 | 0.2748 | - |
|
565 |
+
| 0.5037 | 23800 | 0.246 | - |
|
566 |
+
| 0.5058 | 23900 | 0.2512 | - |
|
567 |
+
| 0.5079 | 24000 | 0.222 | - |
|
568 |
+
| 0.5100 | 24100 | 0.2662 | - |
|
569 |
+
| 0.5121 | 24200 | 0.2238 | - |
|
570 |
+
| 0.5142 | 24300 | 0.2399 | - |
|
571 |
+
| 0.5164 | 24400 | 0.2595 | - |
|
572 |
+
| 0.5185 | 24500 | 0.3002 | - |
|
573 |
+
| 0.5206 | 24600 | 0.2553 | - |
|
574 |
+
| 0.5227 | 24700 | 0.226 | - |
|
575 |
+
| 0.5248 | 24800 | 0.2823 | - |
|
576 |
+
| 0.5269 | 24900 | 0.2737 | - |
|
577 |
+
| 0.5291 | 25000 | 0.2237 | 0.2492 |
|
578 |
+
| 0.5312 | 25100 | 0.2642 | - |
|
579 |
+
| 0.5333 | 25200 | 0.2486 | - |
|
580 |
+
| 0.5354 | 25300 | 0.2527 | - |
|
581 |
+
| 0.5375 | 25400 | 0.2363 | - |
|
582 |
+
| 0.5396 | 25500 | 0.2443 | - |
|
583 |
+
| 0.5418 | 25600 | 0.2485 | - |
|
584 |
+
| 0.5439 | 25700 | 0.2434 | - |
|
585 |
+
| 0.5460 | 25800 | 0.2631 | - |
|
586 |
+
| 0.5481 | 25900 | 0.284 | - |
|
587 |
+
| 0.5502 | 26000 | 0.217 | - |
|
588 |
+
| 0.5523 | 26100 | 0.2246 | - |
|
589 |
+
| 0.5545 | 26200 | 0.2614 | - |
|
590 |
+
| 0.5566 | 26300 | 0.2722 | - |
|
591 |
+
| 0.5587 | 26400 | 0.2114 | - |
|
592 |
+
| 0.5608 | 26500 | 0.2623 | - |
|
593 |
+
| 0.5629 | 26600 | 0.2475 | - |
|
594 |
+
| 0.5650 | 26700 | 0.2449 | - |
|
595 |
+
| 0.5671 | 26800 | 0.2423 | - |
|
596 |
+
| 0.5693 | 26900 | 0.2435 | - |
|
597 |
+
| 0.5714 | 27000 | 0.2446 | - |
|
598 |
+
| 0.5735 | 27100 | 0.2248 | - |
|
599 |
+
| 0.5756 | 27200 | 0.2159 | - |
|
600 |
+
| 0.5777 | 27300 | 0.2415 | - |
|
601 |
+
| 0.5798 | 27400 | 0.2257 | - |
|
602 |
+
| 0.5820 | 27500 | 0.2775 | - |
|
603 |
+
| 0.5841 | 27600 | 0.2533 | - |
|
604 |
+
| 0.5862 | 27700 | 0.2893 | - |
|
605 |
+
| 0.5883 | 27800 | 0.2095 | - |
|
606 |
+
| 0.5904 | 27900 | 0.2156 | - |
|
607 |
+
| 0.5925 | 28000 | 0.2315 | - |
|
608 |
+
| 0.5947 | 28100 | 0.2865 | - |
|
609 |
+
| 0.5968 | 28200 | 0.262 | - |
|
610 |
+
| 0.5989 | 28300 | 0.2506 | - |
|
611 |
+
| 0.6010 | 28400 | 0.2472 | - |
|
612 |
+
| 0.6031 | 28500 | 0.2395 | - |
|
613 |
+
| 0.6052 | 28600 | 0.2269 | - |
|
614 |
+
| 0.6074 | 28700 | 0.2639 | - |
|
615 |
+
| 0.6095 | 28800 | 0.2674 | - |
|
616 |
+
| 0.6116 | 28900 | 0.2521 | - |
|
617 |
+
| 0.6137 | 29000 | 0.2553 | - |
|
618 |
+
| 0.6158 | 29100 | 0.2526 | - |
|
619 |
+
| 0.6179 | 29200 | 0.231 | - |
|
620 |
+
| 0.6201 | 29300 | 0.2622 | - |
|
621 |
+
| 0.6222 | 29400 | 0.237 | - |
|
622 |
+
| 0.6243 | 29500 | 0.2475 | - |
|
623 |
+
| 0.6264 | 29600 | 0.2435 | - |
|
624 |
+
| 0.6285 | 29700 | 0.2109 | - |
|
625 |
+
| 0.6306 | 29800 | 0.2376 | - |
|
626 |
+
| 0.6328 | 29900 | 0.2202 | - |
|
627 |
+
| 0.6349 | 30000 | 0.2147 | 0.2370 |
|
628 |
+
| 0.6370 | 30100 | 0.2306 | - |
|
629 |
+
| 0.6391 | 30200 | 0.2249 | - |
|
630 |
+
| 0.6412 | 30300 | 0.3027 | - |
|
631 |
+
| 0.6433 | 30400 | 0.2115 | - |
|
632 |
+
| 0.6454 | 30500 | 0.2597 | - |
|
633 |
+
| 0.6476 | 30600 | 0.2483 | - |
|
634 |
+
| 0.6497 | 30700 | 0.2719 | - |
|
635 |
+
| 0.6518 | 30800 | 0.2162 | - |
|
636 |
+
| 0.6539 | 30900 | 0.2947 | - |
|
637 |
+
| 0.6560 | 31000 | 0.2144 | - |
|
638 |
+
| 0.6581 | 31100 | 0.2391 | - |
|
639 |
+
| 0.6603 | 31200 | 0.2572 | - |
|
640 |
+
| 0.6624 | 31300 | 0.1977 | - |
|
641 |
+
| 0.6645 | 31400 | 0.2678 | - |
|
642 |
+
| 0.6666 | 31500 | 0.2353 | - |
|
643 |
+
| 0.6687 | 31600 | 0.1911 | - |
|
644 |
+
| 0.6708 | 31700 | 0.2844 | - |
|
645 |
+
| 0.6730 | 31800 | 0.2689 | - |
|
646 |
+
| 0.6751 | 31900 | 0.2491 | - |
|
647 |
+
| 0.6772 | 32000 | 0.2259 | - |
|
648 |
+
| 0.6793 | 32100 | 0.2248 | - |
|
649 |
+
| 0.6814 | 32200 | 0.2462 | - |
|
650 |
+
| 0.6835 | 32300 | 0.2135 | - |
|
651 |
+
| 0.6857 | 32400 | 0.2085 | - |
|
652 |
+
| 0.6878 | 32500 | 0.227 | - |
|
653 |
+
| 0.6899 | 32600 | 0.2488 | - |
|
654 |
+
| 0.6920 | 32700 | 0.2614 | - |
|
655 |
+
| 0.6941 | 32800 | 0.2274 | - |
|
656 |
+
| 0.6962 | 32900 | 0.2389 | - |
|
657 |
+
| 0.6984 | 33000 | 0.2573 | - |
|
658 |
+
| 0.7005 | 33100 | 0.245 | - |
|
659 |
+
| 0.7026 | 33200 | 0.21 | - |
|
660 |
+
| 0.7047 | 33300 | 0.2196 | - |
|
661 |
+
| 0.7068 | 33400 | 0.2218 | - |
|
662 |
+
| 0.7089 | 33500 | 0.2092 | - |
|
663 |
+
| 0.7111 | 33600 | 0.2526 | - |
|
664 |
+
| 0.7132 | 33700 | 0.2275 | - |
|
665 |
+
| 0.7153 | 33800 | 0.2622 | - |
|
666 |
+
| 0.7174 | 33900 | 0.2469 | - |
|
667 |
+
| 0.7195 | 34000 | 0.2157 | - |
|
668 |
+
| 0.7216 | 34100 | 0.2326 | - |
|
669 |
+
| 0.7237 | 34200 | 0.268 | - |
|
670 |
+
| 0.7259 | 34300 | 0.2628 | - |
|
671 |
+
| 0.7280 | 34400 | 0.2503 | - |
|
672 |
+
| 0.7301 | 34500 | 0.2101 | - |
|
673 |
+
| 0.7322 | 34600 | 0.237 | - |
|
674 |
+
| 0.7343 | 34700 | 0.233 | - |
|
675 |
+
| 0.7364 | 34800 | 0.2077 | - |
|
676 |
+
| 0.7386 | 34900 | 0.259 | - |
|
677 |
+
| 0.7407 | 35000 | 0.2312 | 0.2284 |
|
678 |
+
| 0.7428 | 35100 | 0.287 | - |
|
679 |
+
| 0.7449 | 35200 | 0.2278 | - |
|
680 |
+
| 0.7470 | 35300 | 0.2618 | - |
|
681 |
+
| 0.7491 | 35400 | 0.2298 | - |
|
682 |
+
| 0.7513 | 35500 | 0.195 | - |
|
683 |
+
| 0.7534 | 35600 | 0.2248 | - |
|
684 |
+
| 0.7555 | 35700 | 0.2234 | - |
|
685 |
+
| 0.7576 | 35800 | 0.2218 | - |
|
686 |
+
| 0.7597 | 35900 | 0.2002 | - |
|
687 |
+
| 0.7618 | 36000 | 0.2158 | - |
|
688 |
+
| 0.7640 | 36100 | 0.1919 | - |
|
689 |
+
| 0.7661 | 36200 | 0.2972 | - |
|
690 |
+
| 0.7682 | 36300 | 0.2665 | - |
|
691 |
+
| 0.7703 | 36400 | 0.2114 | - |
|
692 |
+
| 0.7724 | 36500 | 0.1879 | - |
|
693 |
+
| 0.7745 | 36600 | 0.2137 | - |
|
694 |
+
| 0.7767 | 36700 | 0.2847 | - |
|
695 |
+
| 0.7788 | 36800 | 0.2372 | - |
|
696 |
+
| 0.7809 | 36900 | 0.2058 | - |
|
697 |
+
| 0.7830 | 37000 | 0.2205 | - |
|
698 |
+
| 0.7851 | 37100 | 0.2012 | - |
|
699 |
+
| 0.7872 | 37200 | 0.2057 | - |
|
700 |
+
| 0.7894 | 37300 | 0.1932 | - |
|
701 |
+
| 0.7915 | 37400 | 0.2261 | - |
|
702 |
+
| 0.7936 | 37500 | 0.2633 | - |
|
703 |
+
| 0.7957 | 37600 | 0.1558 | - |
|
704 |
+
| 0.7978 | 37700 | 0.2064 | - |
|
705 |
+
| 0.7999 | 37800 | 0.2166 | - |
|
706 |
+
| 0.8020 | 37900 | 0.2249 | - |
|
707 |
+
| 0.8042 | 38000 | 0.2626 | - |
|
708 |
+
| 0.8063 | 38100 | 0.1945 | - |
|
709 |
+
| 0.8084 | 38200 | 0.2611 | - |
|
710 |
+
| 0.8105 | 38300 | 0.199 | - |
|
711 |
+
| 0.8126 | 38400 | 0.2004 | - |
|
712 |
+
| 0.8147 | 38500 | 0.2506 | - |
|
713 |
+
| 0.8169 | 38600 | 0.1722 | - |
|
714 |
+
| 0.8190 | 38700 | 0.1959 | - |
|
715 |
+
| 0.8211 | 38800 | 0.2505 | - |
|
716 |
+
| 0.8232 | 38900 | 0.2343 | - |
|
717 |
+
| 0.8253 | 39000 | 0.2353 | - |
|
718 |
+
| 0.8274 | 39100 | 0.22 | - |
|
719 |
+
| 0.8296 | 39200 | 0.2089 | - |
|
720 |
+
| 0.8317 | 39300 | 0.2416 | - |
|
721 |
+
| 0.8338 | 39400 | 0.1916 | - |
|
722 |
+
| 0.8359 | 39500 | 0.2387 | - |
|
723 |
+
| 0.8380 | 39600 | 0.2475 | - |
|
724 |
+
| 0.8401 | 39700 | 0.2189 | - |
|
725 |
+
| 0.8423 | 39800 | 0.2141 | - |
|
726 |
+
| 0.8444 | 39900 | 0.2008 | - |
|
727 |
+
| 0.8465 | 40000 | 0.2489 | 0.2253 |
|
728 |
+
| 0.8486 | 40100 | 0.2258 | - |
|
729 |
+
| 0.8507 | 40200 | 0.2341 | - |
|
730 |
+
| 0.8528 | 40300 | 0.2377 | - |
|
731 |
+
| 0.8550 | 40400 | 0.194 | - |
|
732 |
+
| 0.8571 | 40500 | 0.2144 | - |
|
733 |
+
| 0.8592 | 40600 | 0.2605 | - |
|
734 |
+
| 0.8613 | 40700 | 0.2517 | - |
|
735 |
+
| 0.8634 | 40800 | 0.2044 | - |
|
736 |
+
| 0.8655 | 40900 | 0.2259 | - |
|
737 |
+
| 0.8677 | 41000 | 0.2141 | - |
|
738 |
+
| 0.8698 | 41100 | 0.1895 | - |
|
739 |
+
| 0.8719 | 41200 | 0.2361 | - |
|
740 |
+
| 0.8740 | 41300 | 0.1978 | - |
|
741 |
+
| 0.8761 | 41400 | 0.2089 | - |
|
742 |
+
| 0.8782 | 41500 | 0.2258 | - |
|
743 |
+
| 0.8803 | 41600 | 0.2368 | - |
|
744 |
+
| 0.8825 | 41700 | 0.2473 | - |
|
745 |
+
| 0.8846 | 41800 | 0.2185 | - |
|
746 |
+
| 0.8867 | 41900 | 0.212 | - |
|
747 |
+
| 0.8888 | 42000 | 0.2469 | - |
|
748 |
+
| 0.8909 | 42100 | 0.1817 | - |
|
749 |
+
| 0.8930 | 42200 | 0.1884 | - |
|
750 |
+
| 0.8952 | 42300 | 0.207 | - |
|
751 |
+
| 0.8973 | 42400 | 0.2422 | - |
|
752 |
+
| 0.8994 | 42500 | 0.2606 | - |
|
753 |
+
| 0.9015 | 42600 | 0.2266 | - |
|
754 |
+
| 0.9036 | 42700 | 0.2103 | - |
|
755 |
+
| 0.9057 | 42800 | 0.2712 | - |
|
756 |
+
| 0.9079 | 42900 | 0.1944 | - |
|
757 |
+
| 0.9100 | 43000 | 0.2003 | - |
|
758 |
+
| 0.9121 | 43100 | 0.1991 | - |
|
759 |
+
| 0.9142 | 43200 | 0.2129 | - |
|
760 |
+
| 0.9163 | 43300 | 0.2465 | - |
|
761 |
+
| 0.9184 | 43400 | 0.1764 | - |
|
762 |
+
| 0.9206 | 43500 | 0.2365 | - |
|
763 |
+
| 0.9227 | 43600 | 0.2054 | - |
|
764 |
+
| 0.9248 | 43700 | 0.2551 | - |
|
765 |
+
| 0.9269 | 43800 | 0.2322 | - |
|
766 |
+
| 0.9290 | 43900 | 0.2213 | - |
|
767 |
+
| 0.9311 | 44000 | 0.1962 | - |
|
768 |
+
| 0.9333 | 44100 | 0.1988 | - |
|
769 |
+
| 0.9354 | 44200 | 0.1982 | - |
|
770 |
+
| 0.9375 | 44300 | 0.2193 | - |
|
771 |
+
| 0.9396 | 44400 | 0.2378 | - |
|
772 |
+
| 0.9417 | 44500 | 0.2244 | - |
|
773 |
+
| 0.9438 | 44600 | 0.2296 | - |
|
774 |
+
| 0.9460 | 44700 | 0.2446 | - |
|
775 |
+
| 0.9481 | 44800 | 0.2206 | - |
|
776 |
+
| 0.9502 | 44900 | 0.1815 | - |
|
777 |
+
| **0.9523** | **45000** | **0.2385** | **0.22** |
|
778 |
+
| 0.9544 | 45100 | 0.2106 | - |
|
779 |
+
| 0.9565 | 45200 | 0.1929 | - |
|
780 |
+
| 0.9586 | 45300 | 0.181 | - |
|
781 |
+
| 0.9608 | 45400 | 0.1908 | - |
|
782 |
+
| 0.9629 | 45500 | 0.1926 | - |
|
783 |
+
| 0.9650 | 45600 | 0.1922 | - |
|
784 |
+
| 0.9671 | 45700 | 0.2003 | - |
|
785 |
+
| 0.9692 | 45800 | 0.2377 | - |
|
786 |
+
| 0.9713 | 45900 | 0.2069 | - |
|
787 |
+
| 0.9735 | 46000 | 0.2024 | - |
|
788 |
+
| 0.9756 | 46100 | 0.1795 | - |
|
789 |
+
| 0.9777 | 46200 | 0.2372 | - |
|
790 |
+
| 0.9798 | 46300 | 0.2135 | - |
|
791 |
+
| 0.9819 | 46400 | 0.2396 | - |
|
792 |
+
| 0.9840 | 46500 | 0.2295 | - |
|
793 |
+
| 0.9862 | 46600 | 0.2235 | - |
|
794 |
+
| 0.9883 | 46700 | 0.2427 | - |
|
795 |
+
| 0.9904 | 46800 | 0.2145 | - |
|
796 |
+
| 0.9925 | 46900 | 0.2231 | - |
|
797 |
+
| 0.9946 | 47000 | 0.2401 | - |
|
798 |
+
| 0.9967 | 47100 | 0.1764 | - |
|
799 |
+
| 0.9989 | 47200 | 0.1943 | - |
|
800 |
+
|
801 |
+
* The bold row denotes the saved checkpoint.
|
802 |
+
</details>
|
803 |
+
|
804 |
+
### Framework Versions
|
805 |
+
- Python: 3.12.4
|
806 |
+
- Sentence Transformers: 3.1.0.dev0
|
807 |
+
- Transformers: 4.42.4
|
808 |
+
- PyTorch: 2.3.1+cpu
|
809 |
+
- Accelerate: 0.32.1
|
810 |
+
- Datasets: 2.20.0
|
811 |
+
- Tokenizers: 0.19.1
|
812 |
+
|
813 |
+
## Citation
|
814 |
+
|
815 |
+
### BibTeX
|
816 |
+
|
817 |
+
#### Sentence Transformers
|
818 |
+
```bibtex
|
819 |
+
@inproceedings{reimers-2019-sentence-bert,
|
820 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
821 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
822 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
823 |
+
month = "11",
|
824 |
+
year = "2019",
|
825 |
+
publisher = "Association for Computational Linguistics",
|
826 |
+
url = "https://arxiv.org/abs/1908.10084",
|
827 |
+
}
|
828 |
+
```
|
829 |
+
|
830 |
+
#### MultipleNegativesRankingLoss
|
831 |
+
```bibtex
|
832 |
+
@misc{henderson2017efficient,
|
833 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
834 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
835 |
+
year={2017},
|
836 |
+
eprint={1705.00652},
|
837 |
+
archivePrefix={arXiv},
|
838 |
+
primaryClass={cs.CL}
|
839 |
+
}
|
840 |
+
```
|
841 |
+
|
842 |
+
<!--
|
843 |
+
## Glossary
|
844 |
+
|
845 |
+
*Clearly define terms in order to be accessible across audiences.*
|
846 |
+
-->
|
847 |
+
|
848 |
+
<!--
|
849 |
+
## Model Card Authors
|
850 |
+
|
851 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
852 |
+
-->
|
853 |
+
|
854 |
+
<!--
|
855 |
+
## Model Card Contact
|
856 |
+
|
857 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
858 |
+
-->
|
final/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
+
"vocab_size": 30527
|
24 |
+
}
|
final/config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.1.0.dev0",
|
4 |
+
"transformers": "4.42.4",
|
5 |
+
"pytorch": "2.3.1+cpu"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
final/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e981daa41a8b51b959a05b4c15a733ddb286d5b68010884eb5d3c7b8b9987a4
|
3 |
+
size 437967672
|
final/modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
final/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 384,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
final/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
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": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
final/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
final/tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[UNK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"30526": {
|
44 |
+
"content": "<mask>",
|
45 |
+
"lstrip": true,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"bos_token": "<s>",
|
53 |
+
"clean_up_tokenization_spaces": true,
|
54 |
+
"cls_token": "<s>",
|
55 |
+
"do_lower_case": true,
|
56 |
+
"eos_token": "</s>",
|
57 |
+
"mask_token": "<mask>",
|
58 |
+
"max_length": 128,
|
59 |
+
"model_max_length": 384,
|
60 |
+
"pad_to_multiple_of": null,
|
61 |
+
"pad_token": "<pad>",
|
62 |
+
"pad_token_type_id": 0,
|
63 |
+
"padding_side": "right",
|
64 |
+
"sep_token": "</s>",
|
65 |
+
"stride": 0,
|
66 |
+
"strip_accents": null,
|
67 |
+
"tokenize_chinese_chars": true,
|
68 |
+
"tokenizer_class": "MPNetTokenizer",
|
69 |
+
"truncation_side": "right",
|
70 |
+
"truncation_strategy": "longest_first",
|
71 |
+
"unk_token": "[UNK]"
|
72 |
+
}
|
final/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|