philipp-zettl
commited on
Commit
•
6a2981e
1
Parent(s):
2467532
Add new SentenceTransformer model.
Browse files- .gitattributes +2 -0
- 1_Pooling/config.json +10 -0
- README.md +962 -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 +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +64 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
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 +1,962 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: []
|
3 |
+
library_name: sentence-transformers
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
- feature-extraction
|
8 |
+
- generated_from_trainer
|
9 |
+
- dataset_size:1793370
|
10 |
+
- loss:CoSENTLoss
|
11 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
12 |
+
datasets: []
|
13 |
+
metrics:
|
14 |
+
- pearson_cosine
|
15 |
+
- spearman_cosine
|
16 |
+
- pearson_manhattan
|
17 |
+
- spearman_manhattan
|
18 |
+
- pearson_euclidean
|
19 |
+
- spearman_euclidean
|
20 |
+
- pearson_dot
|
21 |
+
- spearman_dot
|
22 |
+
- pearson_max
|
23 |
+
- spearman_max
|
24 |
+
widget:
|
25 |
+
- source_sentence: ek wil bietjie moderne rock hoor
|
26 |
+
sentences:
|
27 |
+
- request datetime
|
28 |
+
- turn wemo on
|
29 |
+
- query cooking
|
30 |
+
- source_sentence: skakel af die alarm vir woensdag ses v. m.
|
31 |
+
sentences:
|
32 |
+
- set alarm
|
33 |
+
- turn hue light up
|
34 |
+
- request weather
|
35 |
+
- source_sentence: speel my top-gegradeerde pop liedjies asseblief
|
36 |
+
sentences:
|
37 |
+
- greeting
|
38 |
+
- request fact
|
39 |
+
- request datetime
|
40 |
+
- source_sentence: is dit warm buite
|
41 |
+
sentences:
|
42 |
+
- request weather
|
43 |
+
- play music
|
44 |
+
- request transport
|
45 |
+
- source_sentence: maak 'n speellys van al die eminem liedjies en speel dit met skommel
|
46 |
+
sentences:
|
47 |
+
- search recipe
|
48 |
+
- recommend movie
|
49 |
+
- play music
|
50 |
+
pipeline_tag: sentence-similarity
|
51 |
+
model-index:
|
52 |
+
- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
53 |
+
results:
|
54 |
+
- task:
|
55 |
+
type: semantic-similarity
|
56 |
+
name: Semantic Similarity
|
57 |
+
dataset:
|
58 |
+
name: MiniLM dev
|
59 |
+
type: MiniLM-dev
|
60 |
+
metrics:
|
61 |
+
- type: pearson_cosine
|
62 |
+
value: 0.807743120621169
|
63 |
+
name: Pearson Cosine
|
64 |
+
- type: spearman_cosine
|
65 |
+
value: 0.8111451989044506
|
66 |
+
name: Spearman Cosine
|
67 |
+
- type: pearson_manhattan
|
68 |
+
value: 0.8090992313100879
|
69 |
+
name: Pearson Manhattan
|
70 |
+
- type: spearman_manhattan
|
71 |
+
value: 0.8112673840020295
|
72 |
+
name: Spearman Manhattan
|
73 |
+
- type: pearson_euclidean
|
74 |
+
value: 0.8107892143621067
|
75 |
+
name: Pearson Euclidean
|
76 |
+
- type: spearman_euclidean
|
77 |
+
value: 0.8137277702128023
|
78 |
+
name: Spearman Euclidean
|
79 |
+
- type: pearson_dot
|
80 |
+
value: 0.7013144883870261
|
81 |
+
name: Pearson Dot
|
82 |
+
- type: spearman_dot
|
83 |
+
value: 0.7113684320495312
|
84 |
+
name: Spearman Dot
|
85 |
+
- type: pearson_max
|
86 |
+
value: 0.8107892143621067
|
87 |
+
name: Pearson Max
|
88 |
+
- type: spearman_max
|
89 |
+
value: 0.8137277702128023
|
90 |
+
name: Spearman Max
|
91 |
+
---
|
92 |
+
|
93 |
+
# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
94 |
+
|
95 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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.
|
96 |
+
|
97 |
+
## Model Details
|
98 |
+
|
99 |
+
### Model Description
|
100 |
+
- **Model Type:** Sentence Transformer
|
101 |
+
- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
|
102 |
+
- **Maximum Sequence Length:** 128 tokens
|
103 |
+
- **Output Dimensionality:** 384 tokens
|
104 |
+
- **Similarity Function:** Cosine Similarity
|
105 |
+
<!-- - **Training Dataset:** Unknown -->
|
106 |
+
<!-- - **Language:** Unknown -->
|
107 |
+
<!-- - **License:** Unknown -->
|
108 |
+
|
109 |
+
### Model Sources
|
110 |
+
|
111 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
112 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
113 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
114 |
+
|
115 |
+
### Full Model Architecture
|
116 |
+
|
117 |
+
```
|
118 |
+
SentenceTransformer(
|
119 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
120 |
+
(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})
|
121 |
+
)
|
122 |
+
```
|
123 |
+
|
124 |
+
## Usage
|
125 |
+
|
126 |
+
### Direct Usage (Sentence Transformers)
|
127 |
+
|
128 |
+
First install the Sentence Transformers library:
|
129 |
+
|
130 |
+
```bash
|
131 |
+
pip install -U sentence-transformers
|
132 |
+
```
|
133 |
+
|
134 |
+
Then you can load this model and run inference.
|
135 |
+
```python
|
136 |
+
from sentence_transformers import SentenceTransformer
|
137 |
+
|
138 |
+
# Download from the 🤗 Hub
|
139 |
+
model = SentenceTransformer("philipp-zettl/MiniLM-amazon_massive_intent-similarity")
|
140 |
+
# Run inference
|
141 |
+
sentences = [
|
142 |
+
"maak 'n speellys van al die eminem liedjies en speel dit met skommel",
|
143 |
+
'play music',
|
144 |
+
'recommend movie',
|
145 |
+
]
|
146 |
+
embeddings = model.encode(sentences)
|
147 |
+
print(embeddings.shape)
|
148 |
+
# [3, 384]
|
149 |
+
|
150 |
+
# Get the similarity scores for the embeddings
|
151 |
+
similarities = model.similarity(embeddings, embeddings)
|
152 |
+
print(similarities.shape)
|
153 |
+
# [3, 3]
|
154 |
+
```
|
155 |
+
|
156 |
+
<!--
|
157 |
+
### Direct Usage (Transformers)
|
158 |
+
|
159 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
160 |
+
|
161 |
+
</details>
|
162 |
+
-->
|
163 |
+
|
164 |
+
<!--
|
165 |
+
### Downstream Usage (Sentence Transformers)
|
166 |
+
|
167 |
+
You can finetune this model on your own dataset.
|
168 |
+
|
169 |
+
<details><summary>Click to expand</summary>
|
170 |
+
|
171 |
+
</details>
|
172 |
+
-->
|
173 |
+
|
174 |
+
<!--
|
175 |
+
### Out-of-Scope Use
|
176 |
+
|
177 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
178 |
+
-->
|
179 |
+
|
180 |
+
## Evaluation
|
181 |
+
|
182 |
+
### Metrics
|
183 |
+
|
184 |
+
#### Semantic Similarity
|
185 |
+
* Dataset: `MiniLM-dev`
|
186 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
187 |
+
|
188 |
+
| Metric | Value |
|
189 |
+
|:--------------------|:-----------|
|
190 |
+
| pearson_cosine | 0.8077 |
|
191 |
+
| **spearman_cosine** | **0.8111** |
|
192 |
+
| pearson_manhattan | 0.8091 |
|
193 |
+
| spearman_manhattan | 0.8113 |
|
194 |
+
| pearson_euclidean | 0.8108 |
|
195 |
+
| spearman_euclidean | 0.8137 |
|
196 |
+
| pearson_dot | 0.7013 |
|
197 |
+
| spearman_dot | 0.7114 |
|
198 |
+
| pearson_max | 0.8108 |
|
199 |
+
| spearman_max | 0.8137 |
|
200 |
+
|
201 |
+
<!--
|
202 |
+
## Bias, Risks and Limitations
|
203 |
+
|
204 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
205 |
+
-->
|
206 |
+
|
207 |
+
<!--
|
208 |
+
### Recommendations
|
209 |
+
|
210 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
211 |
+
-->
|
212 |
+
|
213 |
+
## Training Details
|
214 |
+
|
215 |
+
### Training Hyperparameters
|
216 |
+
#### Non-Default Hyperparameters
|
217 |
+
|
218 |
+
- `eval_strategy`: steps
|
219 |
+
- `per_device_train_batch_size`: 32
|
220 |
+
- `per_device_eval_batch_size`: 32
|
221 |
+
- `learning_rate`: 2e-05
|
222 |
+
- `num_train_epochs`: 1
|
223 |
+
- `warmup_ratio`: 0.1
|
224 |
+
- `fp16`: True
|
225 |
+
- `batch_sampler`: no_duplicates
|
226 |
+
|
227 |
+
#### All Hyperparameters
|
228 |
+
<details><summary>Click to expand</summary>
|
229 |
+
|
230 |
+
- `overwrite_output_dir`: False
|
231 |
+
- `do_predict`: False
|
232 |
+
- `eval_strategy`: steps
|
233 |
+
- `prediction_loss_only`: True
|
234 |
+
- `per_device_train_batch_size`: 32
|
235 |
+
- `per_device_eval_batch_size`: 32
|
236 |
+
- `per_gpu_train_batch_size`: None
|
237 |
+
- `per_gpu_eval_batch_size`: None
|
238 |
+
- `gradient_accumulation_steps`: 1
|
239 |
+
- `eval_accumulation_steps`: None
|
240 |
+
- `learning_rate`: 2e-05
|
241 |
+
- `weight_decay`: 0.0
|
242 |
+
- `adam_beta1`: 0.9
|
243 |
+
- `adam_beta2`: 0.999
|
244 |
+
- `adam_epsilon`: 1e-08
|
245 |
+
- `max_grad_norm`: 1.0
|
246 |
+
- `num_train_epochs`: 1
|
247 |
+
- `max_steps`: -1
|
248 |
+
- `lr_scheduler_type`: linear
|
249 |
+
- `lr_scheduler_kwargs`: {}
|
250 |
+
- `warmup_ratio`: 0.1
|
251 |
+
- `warmup_steps`: 0
|
252 |
+
- `log_level`: passive
|
253 |
+
- `log_level_replica`: warning
|
254 |
+
- `log_on_each_node`: True
|
255 |
+
- `logging_nan_inf_filter`: True
|
256 |
+
- `save_safetensors`: True
|
257 |
+
- `save_on_each_node`: False
|
258 |
+
- `save_only_model`: False
|
259 |
+
- `restore_callback_states_from_checkpoint`: False
|
260 |
+
- `no_cuda`: False
|
261 |
+
- `use_cpu`: False
|
262 |
+
- `use_mps_device`: False
|
263 |
+
- `seed`: 42
|
264 |
+
- `data_seed`: None
|
265 |
+
- `jit_mode_eval`: False
|
266 |
+
- `use_ipex`: False
|
267 |
+
- `bf16`: False
|
268 |
+
- `fp16`: True
|
269 |
+
- `fp16_opt_level`: O1
|
270 |
+
- `half_precision_backend`: auto
|
271 |
+
- `bf16_full_eval`: False
|
272 |
+
- `fp16_full_eval`: False
|
273 |
+
- `tf32`: None
|
274 |
+
- `local_rank`: 0
|
275 |
+
- `ddp_backend`: None
|
276 |
+
- `tpu_num_cores`: None
|
277 |
+
- `tpu_metrics_debug`: False
|
278 |
+
- `debug`: []
|
279 |
+
- `dataloader_drop_last`: False
|
280 |
+
- `dataloader_num_workers`: 0
|
281 |
+
- `dataloader_prefetch_factor`: None
|
282 |
+
- `past_index`: -1
|
283 |
+
- `disable_tqdm`: False
|
284 |
+
- `remove_unused_columns`: True
|
285 |
+
- `label_names`: None
|
286 |
+
- `load_best_model_at_end`: False
|
287 |
+
- `ignore_data_skip`: False
|
288 |
+
- `fsdp`: []
|
289 |
+
- `fsdp_min_num_params`: 0
|
290 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
291 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
292 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
293 |
+
- `deepspeed`: None
|
294 |
+
- `label_smoothing_factor`: 0.0
|
295 |
+
- `optim`: adamw_torch
|
296 |
+
- `optim_args`: None
|
297 |
+
- `adafactor`: False
|
298 |
+
- `group_by_length`: False
|
299 |
+
- `length_column_name`: length
|
300 |
+
- `ddp_find_unused_parameters`: None
|
301 |
+
- `ddp_bucket_cap_mb`: None
|
302 |
+
- `ddp_broadcast_buffers`: False
|
303 |
+
- `dataloader_pin_memory`: True
|
304 |
+
- `dataloader_persistent_workers`: False
|
305 |
+
- `skip_memory_metrics`: True
|
306 |
+
- `use_legacy_prediction_loop`: False
|
307 |
+
- `push_to_hub`: False
|
308 |
+
- `resume_from_checkpoint`: None
|
309 |
+
- `hub_model_id`: None
|
310 |
+
- `hub_strategy`: every_save
|
311 |
+
- `hub_private_repo`: False
|
312 |
+
- `hub_always_push`: False
|
313 |
+
- `gradient_checkpointing`: False
|
314 |
+
- `gradient_checkpointing_kwargs`: None
|
315 |
+
- `include_inputs_for_metrics`: False
|
316 |
+
- `eval_do_concat_batches`: True
|
317 |
+
- `fp16_backend`: auto
|
318 |
+
- `push_to_hub_model_id`: None
|
319 |
+
- `push_to_hub_organization`: None
|
320 |
+
- `mp_parameters`:
|
321 |
+
- `auto_find_batch_size`: False
|
322 |
+
- `full_determinism`: False
|
323 |
+
- `torchdynamo`: None
|
324 |
+
- `ray_scope`: last
|
325 |
+
- `ddp_timeout`: 1800
|
326 |
+
- `torch_compile`: False
|
327 |
+
- `torch_compile_backend`: None
|
328 |
+
- `torch_compile_mode`: None
|
329 |
+
- `dispatch_batches`: None
|
330 |
+
- `split_batches`: None
|
331 |
+
- `include_tokens_per_second`: False
|
332 |
+
- `include_num_input_tokens_seen`: False
|
333 |
+
- `neftune_noise_alpha`: None
|
334 |
+
- `optim_target_modules`: None
|
335 |
+
- `batch_eval_metrics`: False
|
336 |
+
- `batch_sampler`: no_duplicates
|
337 |
+
- `multi_dataset_batch_sampler`: proportional
|
338 |
+
|
339 |
+
</details>
|
340 |
+
|
341 |
+
### Training Logs
|
342 |
+
<details><summary>Click to expand</summary>
|
343 |
+
|
344 |
+
| Epoch | Step | Training Loss | loss | MiniLM-dev_spearman_cosine |
|
345 |
+
|:------:|:-----:|:-------------:|:------:|:--------------------------:|
|
346 |
+
| 0.0018 | 100 | 10.7509 | - | - |
|
347 |
+
| 0.0036 | 200 | 9.8726 | - | - |
|
348 |
+
| 0.0054 | 300 | 8.9837 | - | - |
|
349 |
+
| 0.0071 | 400 | 7.3162 | - | - |
|
350 |
+
| 0.0089 | 500 | 8.2842 | - | - |
|
351 |
+
| 0.0107 | 600 | 6.2254 | - | - |
|
352 |
+
| 0.0125 | 700 | 6.1004 | - | - |
|
353 |
+
| 0.0143 | 800 | 5.8583 | - | - |
|
354 |
+
| 0.0161 | 900 | 6.3118 | - | - |
|
355 |
+
| 0.0178 | 1000 | 5.7908 | 2.6141 | 0.4045 |
|
356 |
+
| 0.0196 | 1100 | 5.6907 | - | - |
|
357 |
+
| 0.0214 | 1200 | 5.6743 | - | - |
|
358 |
+
| 0.0232 | 1300 | 5.5022 | - | - |
|
359 |
+
| 0.0250 | 1400 | 5.0283 | - | - |
|
360 |
+
| 0.0268 | 1500 | 5.2936 | - | - |
|
361 |
+
| 0.0285 | 1600 | 5.2928 | - | - |
|
362 |
+
| 0.0303 | 1700 | 5.5088 | - | - |
|
363 |
+
| 0.0321 | 1800 | 5.3125 | - | - |
|
364 |
+
| 0.0339 | 1900 | 5.7931 | - | - |
|
365 |
+
| 0.0357 | 2000 | 5.5979 | 2.3256 | 0.5075 |
|
366 |
+
| 0.0375 | 2100 | 5.3222 | - | - |
|
367 |
+
| 0.0393 | 2200 | 5.268 | - | - |
|
368 |
+
| 0.0410 | 2300 | 5.264 | - | - |
|
369 |
+
| 0.0428 | 2400 | 4.9437 | - | - |
|
370 |
+
| 0.0446 | 2500 | 4.9219 | - | - |
|
371 |
+
| 0.0464 | 2600 | 4.8656 | - | - |
|
372 |
+
| 0.0482 | 2700 | 5.2733 | - | - |
|
373 |
+
| 0.0500 | 2800 | 5.0311 | - | - |
|
374 |
+
| 0.0517 | 2900 | 5.302 | - | - |
|
375 |
+
| 0.0535 | 3000 | 5.3347 | 2.1545 | 0.6496 |
|
376 |
+
| 0.0553 | 3100 | 5.1241 | - | - |
|
377 |
+
| 0.0571 | 3200 | 5.0232 | - | - |
|
378 |
+
| 0.0589 | 3300 | 4.9932 | - | - |
|
379 |
+
| 0.0607 | 3400 | 4.9651 | - | - |
|
380 |
+
| 0.0625 | 3500 | 4.5226 | - | - |
|
381 |
+
| 0.0642 | 3600 | 4.6666 | - | - |
|
382 |
+
| 0.0660 | 3700 | 4.8979 | - | - |
|
383 |
+
| 0.0678 | 3800 | 4.9139 | - | - |
|
384 |
+
| 0.0696 | 3900 | 4.9241 | - | - |
|
385 |
+
| 0.0714 | 4000 | 5.2878 | 2.1118 | 0.6948 |
|
386 |
+
| 0.0732 | 4100 | 5.0776 | - | - |
|
387 |
+
| 0.0749 | 4200 | 4.934 | - | - |
|
388 |
+
| 0.0767 | 4300 | 4.9012 | - | - |
|
389 |
+
| 0.0785 | 4400 | 4.8835 | - | - |
|
390 |
+
| 0.0803 | 4500 | 4.5886 | - | - |
|
391 |
+
| 0.0821 | 4600 | 4.7829 | - | - |
|
392 |
+
| 0.0839 | 4700 | 4.8057 | - | - |
|
393 |
+
| 0.0856 | 4800 | 4.8761 | - | - |
|
394 |
+
| 0.0874 | 4900 | 4.6787 | - | - |
|
395 |
+
| 0.0892 | 5000 | 5.313 | 2.1114 | 0.6770 |
|
396 |
+
| 0.0910 | 5100 | 5.3036 | - | - |
|
397 |
+
| 0.0928 | 5200 | 5.0731 | - | - |
|
398 |
+
| 0.0946 | 5300 | 5.0052 | - | - |
|
399 |
+
| 0.0964 | 5400 | 4.9494 | - | - |
|
400 |
+
| 0.0981 | 5500 | 4.836 | - | - |
|
401 |
+
| 0.0999 | 5600 | 4.6319 | - | - |
|
402 |
+
| 0.1017 | 5700 | 4.667 | - | - |
|
403 |
+
| 0.1035 | 5800 | 4.9578 | - | - |
|
404 |
+
| 0.1053 | 5900 | 4.9473 | - | - |
|
405 |
+
| 0.1071 | 6000 | 4.9897 | 3.0813 | 0.4424 |
|
406 |
+
| 0.1088 | 6100 | 5.1704 | - | - |
|
407 |
+
| 0.1106 | 6200 | 4.8472 | - | - |
|
408 |
+
| 0.1124 | 6300 | 4.8296 | - | - |
|
409 |
+
| 0.1142 | 6400 | 4.8287 | - | - |
|
410 |
+
| 0.1160 | 6500 | 4.6539 | - | - |
|
411 |
+
| 0.1178 | 6600 | 4.2599 | - | - |
|
412 |
+
| 0.1196 | 6700 | 4.5506 | - | - |
|
413 |
+
| 0.1213 | 6800 | 4.6585 | - | - |
|
414 |
+
| 0.1231 | 6900 | 4.7248 | - | - |
|
415 |
+
| 0.1249 | 7000 | 4.6389 | 3.1390 | 0.5199 |
|
416 |
+
| 0.1267 | 7100 | 4.8133 | - | - |
|
417 |
+
| 0.1285 | 7200 | 4.8838 | - | - |
|
418 |
+
| 0.1303 | 7300 | 4.7375 | - | - |
|
419 |
+
| 0.1320 | 7400 | 4.6357 | - | - |
|
420 |
+
| 0.1338 | 7500 | 4.7807 | - | - |
|
421 |
+
| 0.1356 | 7600 | 4.409 | - | - |
|
422 |
+
| 0.1374 | 7700 | 4.5612 | - | - |
|
423 |
+
| 0.1392 | 7800 | 4.3731 | - | - |
|
424 |
+
| 0.1410 | 7900 | 4.622 | - | - |
|
425 |
+
| 0.1427 | 8000 | 4.5574 | 2.6558 | 0.5814 |
|
426 |
+
| 0.1445 | 8100 | 4.6542 | - | - |
|
427 |
+
| 0.1463 | 8200 | 4.7831 | - | - |
|
428 |
+
| 0.1481 | 8300 | 4.6775 | - | - |
|
429 |
+
| 0.1499 | 8400 | 4.61 | - | - |
|
430 |
+
| 0.1517 | 8500 | 4.6416 | - | - |
|
431 |
+
| 0.1535 | 8600 | 4.3096 | - | - |
|
432 |
+
| 0.1552 | 8700 | 4.2629 | - | - |
|
433 |
+
| 0.1570 | 8800 | 4.5151 | - | - |
|
434 |
+
| 0.1588 | 8900 | 4.5301 | - | - |
|
435 |
+
| 0.1606 | 9000 | 4.5731 | 2.8939 | 0.5675 |
|
436 |
+
| 0.1624 | 9100 | 4.4347 | - | - |
|
437 |
+
| 0.1642 | 9200 | 4.648 | - | - |
|
438 |
+
| 0.1659 | 9300 | 4.6076 | - | - |
|
439 |
+
| 0.1677 | 9400 | 4.4229 | - | - |
|
440 |
+
| 0.1695 | 9500 | 4.4785 | - | - |
|
441 |
+
| 0.1713 | 9600 | 4.4252 | - | - |
|
442 |
+
| 0.1731 | 9700 | 4.0223 | - | - |
|
443 |
+
| 0.1749 | 9800 | 4.1593 | - | - |
|
444 |
+
| 0.1767 | 9900 | 4.2946 | - | - |
|
445 |
+
| 0.1784 | 10000 | 4.4888 | 2.7814 | 0.5852 |
|
446 |
+
| 0.1802 | 10100 | 4.3605 | - | - |
|
447 |
+
| 0.1820 | 10200 | 4.5952 | - | - |
|
448 |
+
| 0.1838 | 10300 | 4.709 | - | - |
|
449 |
+
| 0.1856 | 10400 | 4.5743 | - | - |
|
450 |
+
| 0.1874 | 10500 | 4.5539 | - | - |
|
451 |
+
| 0.1891 | 10600 | 4.4427 | - | - |
|
452 |
+
| 0.1909 | 10700 | 4.1095 | - | - |
|
453 |
+
| 0.1927 | 10800 | 4.4079 | - | - |
|
454 |
+
| 0.1945 | 10900 | 4.1667 | - | - |
|
455 |
+
| 0.1963 | 11000 | 4.2273 | 3.3803 | 0.5663 |
|
456 |
+
| 0.1981 | 11100 | 4.3333 | - | - |
|
457 |
+
| 0.1998 | 11200 | 4.5174 | - | - |
|
458 |
+
| 0.2016 | 11300 | 4.4961 | - | - |
|
459 |
+
| 0.2034 | 11400 | 4.5746 | - | - |
|
460 |
+
| 0.2052 | 11500 | 4.731 | - | - |
|
461 |
+
| 0.2070 | 11600 | 4.4485 | - | - |
|
462 |
+
| 0.2088 | 11700 | 4.4099 | - | - |
|
463 |
+
| 0.2106 | 11800 | 3.8921 | - | - |
|
464 |
+
| 0.2123 | 11900 | 4.2423 | - | - |
|
465 |
+
| 0.2141 | 12000 | 4.2641 | 3.0230 | 0.6300 |
|
466 |
+
| 0.2159 | 12100 | 4.2052 | - | - |
|
467 |
+
| 0.2177 | 12200 | 4.2757 | - | - |
|
468 |
+
| 0.2195 | 12300 | 4.8586 | - | - |
|
469 |
+
| 0.2213 | 12400 | 4.5872 | - | - |
|
470 |
+
| 0.2230 | 12500 | 4.4273 | - | - |
|
471 |
+
| 0.2248 | 12600 | 4.5728 | - | - |
|
472 |
+
| 0.2266 | 12700 | 4.4607 | - | - |
|
473 |
+
| 0.2284 | 12800 | 4.1361 | - | - |
|
474 |
+
| 0.2302 | 12900 | 4.4781 | - | - |
|
475 |
+
| 0.2320 | 13000 | 4.145 | 2.7088 | 0.6617 |
|
476 |
+
| 0.2337 | 13100 | 4.3366 | - | - |
|
477 |
+
| 0.2355 | 13200 | 4.2699 | - | - |
|
478 |
+
| 0.2373 | 13300 | 4.3397 | - | - |
|
479 |
+
| 0.2391 | 13400 | 4.6033 | - | - |
|
480 |
+
| 0.2409 | 13500 | 4.2292 | - | - |
|
481 |
+
| 0.2427 | 13600 | 4.3399 | - | - |
|
482 |
+
| 0.2445 | 13700 | 4.5222 | - | - |
|
483 |
+
| 0.2462 | 13800 | 4.2185 | - | - |
|
484 |
+
| 0.2480 | 13900 | 3.9426 | - | - |
|
485 |
+
| 0.2498 | 14000 | 4.2146 | 2.6014 | 0.6724 |
|
486 |
+
| 0.2516 | 14100 | 4.2534 | - | - |
|
487 |
+
| 0.2534 | 14200 | 4.1765 | - | - |
|
488 |
+
| 0.2552 | 14300 | 4.117 | - | - |
|
489 |
+
| 0.2569 | 14400 | 5.0908 | - | - |
|
490 |
+
| 0.2587 | 14500 | 4.488 | - | - |
|
491 |
+
| 0.2605 | 14600 | 4.4429 | - | - |
|
492 |
+
| 0.2623 | 14700 | 4.3688 | - | - |
|
493 |
+
| 0.2641 | 14800 | 4.4857 | - | - |
|
494 |
+
| 0.2659 | 14900 | 4.1763 | - | - |
|
495 |
+
| 0.2677 | 15000 | 4.4425 | 2.6388 | 0.6842 |
|
496 |
+
| 0.2694 | 15100 | 4.4277 | - | - |
|
497 |
+
| 0.2712 | 15200 | 4.3841 | - | - |
|
498 |
+
| 0.2730 | 15300 | 4.4 | - | - |
|
499 |
+
| 0.2748 | 15400 | 4.55 | - | - |
|
500 |
+
| 0.2766 | 15500 | 4.4769 | - | - |
|
501 |
+
| 0.2784 | 15600 | 4.3918 | - | - |
|
502 |
+
| 0.2801 | 15700 | 4.554 | - | - |
|
503 |
+
| 0.2819 | 15800 | 4.406 | - | - |
|
504 |
+
| 0.2837 | 15900 | 4.0593 | - | - |
|
505 |
+
| 0.2855 | 16000 | 4.3586 | 2.5251 | 0.7238 |
|
506 |
+
| 0.2873 | 16100 | 4.2308 | - | - |
|
507 |
+
| 0.2891 | 16200 | 4.469 | - | - |
|
508 |
+
| 0.2908 | 16300 | 4.2312 | - | - |
|
509 |
+
| 0.2926 | 16400 | 4.2695 | - | - |
|
510 |
+
| 0.2944 | 16500 | 4.5821 | - | - |
|
511 |
+
| 0.2962 | 16600 | 4.5623 | - | - |
|
512 |
+
| 0.2980 | 16700 | 4.1865 | - | - |
|
513 |
+
| 0.2998 | 16800 | 4.4228 | - | - |
|
514 |
+
| 0.3016 | 16900 | 4.0553 | - | - |
|
515 |
+
| 0.3033 | 17000 | 3.7183 | 2.6050 | 0.7319 |
|
516 |
+
| 0.3051 | 17100 | 4.1849 | - | - |
|
517 |
+
| 0.3069 | 17200 | 4.2975 | - | - |
|
518 |
+
| 0.3087 | 17300 | 4.4272 | - | - |
|
519 |
+
| 0.3105 | 17400 | 4.0634 | - | - |
|
520 |
+
| 0.3123 | 17500 | 4.8608 | - | - |
|
521 |
+
| 0.3140 | 17600 | 4.4146 | - | - |
|
522 |
+
| 0.3158 | 17700 | 4.2655 | - | - |
|
523 |
+
| 0.3176 | 17800 | 4.3814 | - | - |
|
524 |
+
| 0.3194 | 17900 | 4.3972 | - | - |
|
525 |
+
| 0.3212 | 18000 | 3.8868 | 2.4737 | 0.7500 |
|
526 |
+
| 0.3230 | 18100 | 4.434 | - | - |
|
527 |
+
| 0.3248 | 18200 | 4.2213 | - | - |
|
528 |
+
| 0.3265 | 18300 | 4.4632 | - | - |
|
529 |
+
| 0.3283 | 18400 | 4.4001 | - | - |
|
530 |
+
| 0.3301 | 18500 | 4.8262 | - | - |
|
531 |
+
| 0.3319 | 18600 | 4.5022 | - | - |
|
532 |
+
| 0.3337 | 18700 | 4.4148 | - | - |
|
533 |
+
| 0.3355 | 18800 | 4.2182 | - | - |
|
534 |
+
| 0.3372 | 18900 | 4.2127 | - | - |
|
535 |
+
| 0.3390 | 19000 | 4.051 | 2.4633 | 0.7575 |
|
536 |
+
| 0.3408 | 19100 | 3.655 | - | - |
|
537 |
+
| 0.3426 | 19200 | 4.2441 | - | - |
|
538 |
+
| 0.3444 | 19300 | 4.3494 | - | - |
|
539 |
+
| 0.3462 | 19400 | 4.1824 | - | - |
|
540 |
+
| 0.3479 | 19500 | 4.3528 | - | - |
|
541 |
+
| 0.3497 | 19600 | 5.6073 | - | - |
|
542 |
+
| 0.3515 | 19700 | 4.8231 | - | - |
|
543 |
+
| 0.3533 | 19800 | 4.5816 | - | - |
|
544 |
+
| 0.3551 | 19900 | 4.5812 | - | - |
|
545 |
+
| 0.3569 | 20000 | 4.637 | 2.1229 | 0.7945 |
|
546 |
+
| 0.3587 | 20100 | 4.2619 | - | - |
|
547 |
+
| 0.3604 | 20200 | 4.5645 | - | - |
|
548 |
+
| 0.3622 | 20300 | 4.7248 | - | - |
|
549 |
+
| 0.3640 | 20400 | 4.5665 | - | - |
|
550 |
+
| 0.3658 | 20500 | 4.5628 | - | - |
|
551 |
+
| 0.3676 | 20600 | 4.8494 | - | - |
|
552 |
+
| 0.3694 | 20700 | 4.4338 | - | - |
|
553 |
+
| 0.3711 | 20800 | 4.3256 | - | - |
|
554 |
+
| 0.3729 | 20900 | 4.4388 | - | - |
|
555 |
+
| 0.3747 | 21000 | 4.158 | 2.3475 | 0.7732 |
|
556 |
+
| 0.3765 | 21100 | 3.962 | - | - |
|
557 |
+
| 0.3783 | 21200 | 3.931 | - | - |
|
558 |
+
| 0.3801 | 21300 | 4.0345 | - | - |
|
559 |
+
| 0.3818 | 21400 | 4.319 | - | - |
|
560 |
+
| 0.3836 | 21500 | 4.1329 | - | - |
|
561 |
+
| 0.3854 | 21600 | 4.245 | - | - |
|
562 |
+
| 0.3872 | 21700 | 4.518 | - | - |
|
563 |
+
| 0.3890 | 21800 | 4.4653 | - | - |
|
564 |
+
| 0.3908 | 21900 | 4.2777 | - | - |
|
565 |
+
| 0.3926 | 22000 | 4.3358 | 2.1933 | 0.7845 |
|
566 |
+
| 0.3943 | 22100 | 4.2291 | - | - |
|
567 |
+
| 0.3961 | 22200 | 3.8067 | - | - |
|
568 |
+
| 0.3979 | 22300 | 4.2039 | - | - |
|
569 |
+
| 0.3997 | 22400 | 4.0104 | - | - |
|
570 |
+
| 0.4015 | 22500 | 4.2346 | - | - |
|
571 |
+
| 0.4033 | 22600 | 4.0056 | - | - |
|
572 |
+
| 0.4050 | 22700 | 5.6038 | - | - |
|
573 |
+
| 0.4068 | 22800 | 5.1185 | - | - |
|
574 |
+
| 0.4086 | 22900 | 4.924 | - | - |
|
575 |
+
| 0.4104 | 23000 | 4.7841 | 1.9839 | 0.7956 |
|
576 |
+
| 0.4122 | 23100 | 4.7953 | - | - |
|
577 |
+
| 0.4140 | 23200 | 4.4229 | - | - |
|
578 |
+
| 0.4158 | 23300 | 4.6432 | - | - |
|
579 |
+
| 0.4175 | 23400 | 4.5284 | - | - |
|
580 |
+
| 0.4193 | 23500 | 4.7215 | - | - |
|
581 |
+
| 0.4211 | 23600 | 4.7432 | - | - |
|
582 |
+
| 0.4229 | 23700 | 5.0136 | - | - |
|
583 |
+
| 0.4247 | 23800 | 4.7958 | - | - |
|
584 |
+
| 0.4265 | 23900 | 4.6827 | - | - |
|
585 |
+
| 0.4282 | 24000 | 4.6665 | 1.9663 | 0.7870 |
|
586 |
+
| 0.4300 | 24100 | 4.5074 | - | - |
|
587 |
+
| 0.4318 | 24200 | 4.4189 | - | - |
|
588 |
+
| 0.4336 | 24300 | 4.4586 | - | - |
|
589 |
+
| 0.4354 | 24400 | 4.6421 | - | - |
|
590 |
+
| 0.4372 | 24500 | 4.4281 | - | - |
|
591 |
+
| 0.4389 | 24600 | 4.5153 | - | - |
|
592 |
+
| 0.4407 | 24700 | 4.9942 | - | - |
|
593 |
+
| 0.4425 | 24800 | 5.11 | - | - |
|
594 |
+
| 0.4443 | 24900 | 4.7071 | - | - |
|
595 |
+
| 0.4461 | 25000 | 4.6257 | 1.9461 | 0.7935 |
|
596 |
+
| 0.4479 | 25100 | 4.6576 | - | - |
|
597 |
+
| 0.4497 | 25200 | 4.6103 | - | - |
|
598 |
+
| 0.4514 | 25300 | 4.2066 | - | - |
|
599 |
+
| 0.4532 | 25400 | 4.6869 | - | - |
|
600 |
+
| 0.4550 | 25500 | 4.7575 | - | - |
|
601 |
+
| 0.4568 | 25600 | 4.6081 | - | - |
|
602 |
+
| 0.4586 | 25700 | 4.8144 | - | - |
|
603 |
+
| 0.4604 | 25800 | 5.2007 | - | - |
|
604 |
+
| 0.4621 | 25900 | 4.8367 | - | - |
|
605 |
+
| 0.4639 | 26000 | 4.5258 | 1.9131 | 0.7993 |
|
606 |
+
| 0.4657 | 26100 | 4.4784 | - | - |
|
607 |
+
| 0.4675 | 26200 | 4.5568 | - | - |
|
608 |
+
| 0.4693 | 26300 | 4.2591 | - | - |
|
609 |
+
| 0.4711 | 26400 | 4.4521 | - | - |
|
610 |
+
| 0.4729 | 26500 | 4.4041 | - | - |
|
611 |
+
| 0.4746 | 26600 | 4.4926 | - | - |
|
612 |
+
| 0.4764 | 26700 | 4.1686 | - | - |
|
613 |
+
| 0.4782 | 26800 | 4.6294 | - | - |
|
614 |
+
| 0.4800 | 26900 | 4.6889 | - | - |
|
615 |
+
| 0.4818 | 27000 | 4.5765 | 1.9539 | 0.7961 |
|
616 |
+
| 0.4836 | 27100 | 4.3427 | - | - |
|
617 |
+
| 0.4853 | 27200 | 4.5275 | - | - |
|
618 |
+
| 0.4871 | 27300 | 4.4186 | - | - |
|
619 |
+
| 0.4889 | 27400 | 4.0163 | - | - |
|
620 |
+
| 0.4907 | 27500 | 4.3204 | - | - |
|
621 |
+
| 0.4925 | 27600 | 4.179 | - | - |
|
622 |
+
| 0.4943 | 27700 | 4.3838 | - | - |
|
623 |
+
| 0.4960 | 27800 | 4.2631 | - | - |
|
624 |
+
| 0.4978 | 27900 | 4.7177 | - | - |
|
625 |
+
| 0.4996 | 28000 | 4.5161 | 2.0116 | 0.7935 |
|
626 |
+
| 0.5014 | 28100 | 4.2861 | - | - |
|
627 |
+
| 0.5032 | 28200 | 4.4123 | - | - |
|
628 |
+
| 0.5050 | 28300 | 4.293 | - | - |
|
629 |
+
| 0.5068 | 28400 | 4.2346 | - | - |
|
630 |
+
| 0.5085 | 28500 | 4.3355 | - | - |
|
631 |
+
| 0.5103 | 28600 | 4.4616 | - | - |
|
632 |
+
| 0.5121 | 28700 | 4.2409 | - | - |
|
633 |
+
| 0.5139 | 28800 | 4.2398 | - | - |
|
634 |
+
| 0.5157 | 28900 | 4.7412 | - | - |
|
635 |
+
| 0.5175 | 29000 | 4.5044 | 2.1008 | 0.7859 |
|
636 |
+
| 0.5192 | 29100 | 4.4556 | - | - |
|
637 |
+
| 0.5210 | 29200 | 4.2938 | - | - |
|
638 |
+
| 0.5228 | 29300 | 4.4962 | - | - |
|
639 |
+
| 0.5246 | 29400 | 4.477 | - | - |
|
640 |
+
| 0.5264 | 29500 | 4.2602 | - | - |
|
641 |
+
| 0.5282 | 29600 | 4.4231 | - | - |
|
642 |
+
| 0.5300 | 29700 | 4.2165 | - | - |
|
643 |
+
| 0.5317 | 29800 | 4.3729 | - | - |
|
644 |
+
| 0.5335 | 29900 | 4.2414 | - | - |
|
645 |
+
| 0.5353 | 30000 | 4.9937 | 2.0884 | 0.7702 |
|
646 |
+
| 0.5371 | 30100 | 4.5737 | - | - |
|
647 |
+
| 0.5389 | 30200 | 4.4517 | - | - |
|
648 |
+
| 0.5407 | 30300 | 4.4178 | - | - |
|
649 |
+
| 0.5424 | 30400 | 4.3514 | - | - |
|
650 |
+
| 0.5442 | 30500 | 3.9723 | - | - |
|
651 |
+
| 0.5460 | 30600 | 4.3707 | - | - |
|
652 |
+
| 0.5478 | 30700 | 4.2235 | - | - |
|
653 |
+
| 0.5496 | 30800 | 4.4278 | - | - |
|
654 |
+
| 0.5514 | 30900 | 4.2914 | - | - |
|
655 |
+
| 0.5531 | 31000 | 4.5636 | 2.3277 | 0.7454 |
|
656 |
+
| 0.5549 | 31100 | 4.4889 | - | - |
|
657 |
+
| 0.5567 | 31200 | 4.3211 | - | - |
|
658 |
+
| 0.5585 | 31300 | 4.404 | - | - |
|
659 |
+
| 0.5603 | 31400 | 4.2117 | - | - |
|
660 |
+
| 0.5621 | 31500 | 4.1126 | - | - |
|
661 |
+
| 0.5639 | 31600 | 4.1737 | - | - |
|
662 |
+
| 0.5656 | 31700 | 4.203 | - | - |
|
663 |
+
| 0.5674 | 31800 | 4.1093 | - | - |
|
664 |
+
| 0.5692 | 31900 | 4.0702 | - | - |
|
665 |
+
| 0.5710 | 32000 | 4.4189 | 2.6265 | 0.7375 |
|
666 |
+
| 0.5728 | 32100 | 4.9817 | - | - |
|
667 |
+
| 0.5746 | 32200 | 4.4736 | - | - |
|
668 |
+
| 0.5763 | 32300 | 4.348 | - | - |
|
669 |
+
| 0.5781 | 32400 | 4.5404 | - | - |
|
670 |
+
| 0.5799 | 32500 | 4.2987 | - | - |
|
671 |
+
| 0.5817 | 32600 | 4.0725 | - | - |
|
672 |
+
| 0.5835 | 32700 | 4.5469 | - | - |
|
673 |
+
| 0.5853 | 32800 | 4.4367 | - | - |
|
674 |
+
| 0.5870 | 32900 | 4.3369 | - | - |
|
675 |
+
| 0.5888 | 33000 | 4.2292 | 2.5687 | 0.7213 |
|
676 |
+
| 0.5906 | 33100 | 4.7929 | - | - |
|
677 |
+
| 0.5924 | 33200 | 4.4123 | - | - |
|
678 |
+
| 0.5942 | 33300 | 4.1699 | - | - |
|
679 |
+
| 0.5960 | 33400 | 4.4021 | - | - |
|
680 |
+
| 0.5978 | 33500 | 4.5257 | - | - |
|
681 |
+
| 0.5995 | 33600 | 3.7222 | - | - |
|
682 |
+
| 0.6013 | 33700 | 4.0746 | - | - |
|
683 |
+
| 0.6031 | 33800 | 4.1399 | - | - |
|
684 |
+
| 0.6049 | 33900 | 3.9957 | - | - |
|
685 |
+
| 0.6067 | 34000 | 4.093 | 2.4645 | 0.7524 |
|
686 |
+
| 0.6085 | 34100 | 4.2929 | - | - |
|
687 |
+
| 0.6102 | 34200 | 4.4765 | - | - |
|
688 |
+
| 0.6120 | 34300 | 4.3871 | - | - |
|
689 |
+
| 0.6138 | 34400 | 4.385 | - | - |
|
690 |
+
| 0.6156 | 34500 | 4.1455 | - | - |
|
691 |
+
| 0.6174 | 34600 | 3.7689 | - | - |
|
692 |
+
| 0.6192 | 34700 | 3.6574 | - | - |
|
693 |
+
| 0.6210 | 34800 | 4.2426 | - | - |
|
694 |
+
| 0.6227 | 34900 | 4.293 | - | - |
|
695 |
+
| 0.6245 | 35000 | 4.1368 | 2.4370 | 0.7765 |
|
696 |
+
| 0.6263 | 35100 | 3.6174 | - | - |
|
697 |
+
| 0.6281 | 35200 | 4.7763 | - | - |
|
698 |
+
| 0.6299 | 35300 | 4.3121 | - | - |
|
699 |
+
| 0.6317 | 35400 | 4.1886 | - | - |
|
700 |
+
| 0.6334 | 35500 | 4.3538 | - | - |
|
701 |
+
| 0.6352 | 35600 | 4.0285 | - | - |
|
702 |
+
| 0.6370 | 35700 | 3.4691 | - | - |
|
703 |
+
| 0.6388 | 35800 | 4.2732 | - | - |
|
704 |
+
| 0.6406 | 35900 | 4.2052 | - | - |
|
705 |
+
| 0.6424 | 36000 | 4.0452 | 2.4680 | 0.7732 |
|
706 |
+
| 0.6441 | 36100 | 3.9032 | - | - |
|
707 |
+
| 0.6459 | 36200 | 4.2608 | - | - |
|
708 |
+
| 0.6477 | 36300 | 4.262 | - | - |
|
709 |
+
| 0.6495 | 36400 | 4.1138 | - | - |
|
710 |
+
| 0.6513 | 36500 | 4.248 | - | - |
|
711 |
+
| 0.6531 | 36600 | 4.1163 | - | - |
|
712 |
+
| 0.6549 | 36700 | 3.6375 | - | - |
|
713 |
+
| 0.6566 | 36800 | 4.0768 | - | - |
|
714 |
+
| 0.6584 | 36900 | 4.0268 | - | - |
|
715 |
+
| 0.6602 | 37000 | 4.0129 | 2.6361 | 0.7702 |
|
716 |
+
| 0.6620 | 37100 | 3.7976 | - | - |
|
717 |
+
| 0.6638 | 37200 | 4.2518 | - | - |
|
718 |
+
| 0.6656 | 37300 | 4.5011 | - | - |
|
719 |
+
| 0.6673 | 37400 | 4.4488 | - | - |
|
720 |
+
| 0.6691 | 37500 | 3.9798 | - | - |
|
721 |
+
| 0.6709 | 37600 | 4.027 | - | - |
|
722 |
+
| 0.6727 | 37700 | 4.0342 | - | - |
|
723 |
+
| 0.6745 | 37800 | 3.8229 | - | - |
|
724 |
+
| 0.6763 | 37900 | 4.0573 | - | - |
|
725 |
+
| 0.6781 | 38000 | 4.1739 | 2.4511 | 0.7935 |
|
726 |
+
| 0.6798 | 38100 | 4.57 | - | - |
|
727 |
+
| 0.6816 | 38200 | 3.9108 | - | - |
|
728 |
+
| 0.6834 | 38300 | 4.3569 | - | - |
|
729 |
+
| 0.6852 | 38400 | 4.3775 | - | - |
|
730 |
+
| 0.6870 | 38500 | 4.2887 | - | - |
|
731 |
+
| 0.6888 | 38600 | 4.144 | - | - |
|
732 |
+
| 0.6905 | 38700 | 4.5112 | - | - |
|
733 |
+
| 0.6923 | 38800 | 3.5093 | - | - |
|
734 |
+
| 0.6941 | 38900 | 3.9626 | - | - |
|
735 |
+
| 0.6959 | 39000 | 4.024 | 2.4241 | 0.7868 |
|
736 |
+
| 0.6977 | 39100 | 4.0671 | - | - |
|
737 |
+
| 0.6995 | 39200 | 3.9545 | - | - |
|
738 |
+
| 0.7012 | 39300 | 4.0036 | - | - |
|
739 |
+
| 0.7030 | 39400 | 4.3796 | - | - |
|
740 |
+
| 0.7048 | 39500 | 4.2912 | - | - |
|
741 |
+
| 0.7066 | 39600 | 4.1181 | - | - |
|
742 |
+
| 0.7084 | 39700 | 4.1437 | - | - |
|
743 |
+
| 0.7102 | 39800 | 3.8734 | - | - |
|
744 |
+
| 0.7120 | 39900 | 3.7678 | - | - |
|
745 |
+
| 0.7137 | 40000 | 4.2327 | 2.3937 | 0.7956 |
|
746 |
+
| 0.7155 | 40100 | 3.8276 | - | - |
|
747 |
+
| 0.7173 | 40200 | 4.2885 | - | - |
|
748 |
+
| 0.7191 | 40300 | 4.019 | - | - |
|
749 |
+
| 0.7209 | 40400 | 4.6898 | - | - |
|
750 |
+
| 0.7227 | 40500 | 4.2398 | - | - |
|
751 |
+
| 0.7244 | 40600 | 4.317 | - | - |
|
752 |
+
| 0.7262 | 40700 | 4.2543 | - | - |
|
753 |
+
| 0.7280 | 40800 | 4.1048 | - | - |
|
754 |
+
| 0.7298 | 40900 | 3.4243 | - | - |
|
755 |
+
| 0.7316 | 41000 | 4.0587 | 2.2848 | 0.8035 |
|
756 |
+
| 0.7334 | 41100 | 4.2112 | - | - |
|
757 |
+
| 0.7351 | 41200 | 4.0331 | - | - |
|
758 |
+
| 0.7369 | 41300 | 4.2361 | - | - |
|
759 |
+
| 0.7387 | 41400 | 4.3818 | - | - |
|
760 |
+
| 0.7405 | 41500 | 4.1311 | - | - |
|
761 |
+
| 0.7423 | 41600 | 4.0607 | - | - |
|
762 |
+
| 0.7441 | 41700 | 4.1277 | - | - |
|
763 |
+
| 0.7459 | 41800 | 3.8844 | - | - |
|
764 |
+
| 0.7476 | 41900 | 3.6138 | - | - |
|
765 |
+
| 0.7494 | 42000 | 3.7973 | 2.4197 | 0.8045 |
|
766 |
+
| 0.7512 | 42100 | 4.0854 | - | - |
|
767 |
+
| 0.7530 | 42200 | 4.0926 | - | - |
|
768 |
+
| 0.7548 | 42300 | 3.9821 | - | - |
|
769 |
+
| 0.7566 | 42400 | 4.5564 | - | - |
|
770 |
+
| 0.7583 | 42500 | 6.1707 | - | - |
|
771 |
+
| 0.7601 | 42600 | 5.4598 | - | - |
|
772 |
+
| 0.7619 | 42700 | 5.2202 | - | - |
|
773 |
+
| 0.7637 | 42800 | 5.1402 | - | - |
|
774 |
+
| 0.7655 | 42900 | 4.8446 | - | - |
|
775 |
+
| 0.7673 | 43000 | 4.5341 | 1.9710 | 0.8181 |
|
776 |
+
| 0.7691 | 43100 | 5.0068 | - | - |
|
777 |
+
| 0.7708 | 43200 | 5.0099 | - | - |
|
778 |
+
| 0.7726 | 43300 | 4.7986 | - | - |
|
779 |
+
| 0.7744 | 43400 | 5.0468 | - | - |
|
780 |
+
| 0.7762 | 43500 | 5.135 | - | - |
|
781 |
+
| 0.7780 | 43600 | 4.8018 | - | - |
|
782 |
+
| 0.7798 | 43700 | 4.6291 | - | - |
|
783 |
+
| 0.7815 | 43800 | 4.6119 | - | - |
|
784 |
+
| 0.7833 | 43900 | 4.5318 | - | - |
|
785 |
+
| 0.7851 | 44000 | 3.9703 | 1.9790 | 0.8211 |
|
786 |
+
| 0.7869 | 44100 | 4.461 | - | - |
|
787 |
+
| 0.7887 | 44200 | 4.5536 | - | - |
|
788 |
+
| 0.7905 | 44300 | 4.411 | - | - |
|
789 |
+
| 0.7922 | 44400 | 4.5796 | - | - |
|
790 |
+
| 0.7940 | 44500 | 4.7385 | - | - |
|
791 |
+
| 0.7958 | 44600 | 4.6635 | - | - |
|
792 |
+
| 0.7976 | 44700 | 4.4808 | - | - |
|
793 |
+
| 0.7994 | 44800 | 4.5565 | - | - |
|
794 |
+
| 0.8012 | 44900 | 4.4707 | - | - |
|
795 |
+
| 0.8030 | 45000 | 3.9981 | 1.9823 | 0.8197 |
|
796 |
+
| 0.8047 | 45100 | 4.119 | - | - |
|
797 |
+
| 0.8065 | 45200 | 4.4209 | - | - |
|
798 |
+
| 0.8083 | 45300 | 4.3268 | - | - |
|
799 |
+
| 0.8101 | 45400 | 4.2979 | - | - |
|
800 |
+
| 0.8119 | 45500 | 4.413 | - | - |
|
801 |
+
| 0.8137 | 45600 | 4.3317 | - | - |
|
802 |
+
| 0.8154 | 45700 | 4.3683 | - | - |
|
803 |
+
| 0.8172 | 45800 | 4.0769 | - | - |
|
804 |
+
| 0.8190 | 45900 | 4.304 | - | - |
|
805 |
+
| 0.8208 | 46000 | 4.0985 | 2.0490 | 0.8183 |
|
806 |
+
| 0.8226 | 46100 | 3.8719 | - | - |
|
807 |
+
| 0.8244 | 46200 | 4.1843 | - | - |
|
808 |
+
| 0.8262 | 46300 | 4.2131 | - | - |
|
809 |
+
| 0.8279 | 46400 | 4.3327 | - | - |
|
810 |
+
| 0.8297 | 46500 | 3.8533 | - | - |
|
811 |
+
| 0.8315 | 46600 | 5.2854 | - | - |
|
812 |
+
| 0.8333 | 46700 | 5.2465 | - | - |
|
813 |
+
| 0.8351 | 46800 | 5.0221 | - | - |
|
814 |
+
| 0.8369 | 46900 | 4.9466 | - | - |
|
815 |
+
| 0.8386 | 47000 | 5.0361 | 1.8252 | 0.8360 |
|
816 |
+
| 0.8404 | 47100 | 4.3676 | - | - |
|
817 |
+
| 0.8422 | 47200 | 4.619 | - | - |
|
818 |
+
| 0.8440 | 47300 | 4.6412 | - | - |
|
819 |
+
| 0.8458 | 47400 | 4.7874 | - | - |
|
820 |
+
| 0.8476 | 47500 | 4.663 | - | - |
|
821 |
+
| 0.8493 | 47600 | 4.7068 | - | - |
|
822 |
+
| 0.8511 | 47700 | 4.5889 | - | - |
|
823 |
+
| 0.8529 | 47800 | 4.3468 | - | - |
|
824 |
+
| 0.8547 | 47900 | 4.4393 | - | - |
|
825 |
+
| 0.8565 | 48000 | 4.5488 | 1.9117 | 0.8176 |
|
826 |
+
| 0.8583 | 48100 | 4.0933 | - | - |
|
827 |
+
| 0.8601 | 48200 | 3.7754 | - | - |
|
828 |
+
| 0.8618 | 48300 | 4.1346 | - | - |
|
829 |
+
| 0.8636 | 48400 | 4.402 | - | - |
|
830 |
+
| 0.8654 | 48500 | 4.0163 | - | - |
|
831 |
+
| 0.8672 | 48600 | 4.3405 | - | - |
|
832 |
+
| 0.8690 | 48700 | 4.7694 | - | - |
|
833 |
+
| 0.8708 | 48800 | 4.4457 | - | - |
|
834 |
+
| 0.8725 | 48900 | 4.3679 | - | - |
|
835 |
+
| 0.8743 | 49000 | 4.3283 | 1.9392 | 0.8251 |
|
836 |
+
| 0.8761 | 49100 | 4.6855 | - | - |
|
837 |
+
| 0.8779 | 49200 | 3.881 | - | - |
|
838 |
+
| 0.8797 | 49300 | 4.1392 | - | - |
|
839 |
+
| 0.8815 | 49400 | 4.4343 | - | - |
|
840 |
+
| 0.8833 | 49500 | 4.4822 | - | - |
|
841 |
+
| 0.8850 | 49600 | 4.3977 | - | - |
|
842 |
+
| 0.8868 | 49700 | 4.5944 | - | - |
|
843 |
+
| 0.8886 | 49800 | 4.4176 | - | - |
|
844 |
+
| 0.8904 | 49900 | 4.5269 | - | - |
|
845 |
+
| 0.8922 | 50000 | 4.4267 | 1.8965 | 0.8206 |
|
846 |
+
| 0.8940 | 50100 | 4.5109 | - | - |
|
847 |
+
| 0.8957 | 50200 | 4.1775 | - | - |
|
848 |
+
| 0.8975 | 50300 | 4.3453 | - | - |
|
849 |
+
| 0.8993 | 50400 | 4.5443 | - | - |
|
850 |
+
| 0.9011 | 50500 | 4.226 | - | - |
|
851 |
+
| 0.9029 | 50600 | 4.3296 | - | - |
|
852 |
+
| 0.9047 | 50700 | 4.1968 | - | - |
|
853 |
+
| 0.9064 | 50800 | 4.2206 | - | - |
|
854 |
+
| 0.9082 | 50900 | 4.2299 | - | - |
|
855 |
+
| 0.9100 | 51000 | 4.0471 | 2.0479 | 0.8146 |
|
856 |
+
| 0.9118 | 51100 | 4.0832 | - | - |
|
857 |
+
| 0.9136 | 51200 | 3.7516 | - | - |
|
858 |
+
| 0.9154 | 51300 | 4.0545 | - | - |
|
859 |
+
| 0.9172 | 51400 | 4.1281 | - | - |
|
860 |
+
| 0.9189 | 51500 | 4.2336 | - | - |
|
861 |
+
| 0.9207 | 51600 | 4.2511 | - | - |
|
862 |
+
| 0.9225 | 51700 | 4.2588 | - | - |
|
863 |
+
| 0.9243 | 51800 | 4.0719 | - | - |
|
864 |
+
| 0.9261 | 51900 | 4.1847 | - | - |
|
865 |
+
| 0.9279 | 52000 | 4.1445 | 2.1419 | 0.8128 |
|
866 |
+
| 0.9296 | 52100 | 3.9735 | - | - |
|
867 |
+
| 0.9314 | 52200 | 3.8635 | - | - |
|
868 |
+
| 0.9332 | 52300 | 4.1738 | - | - |
|
869 |
+
| 0.9350 | 52400 | 4.07 | - | - |
|
870 |
+
| 0.9368 | 52500 | 4.1008 | - | - |
|
871 |
+
| 0.9386 | 52600 | 3.9628 | - | - |
|
872 |
+
| 0.9403 | 52700 | 4.2895 | - | - |
|
873 |
+
| 0.9421 | 52800 | 4.3393 | - | - |
|
874 |
+
| 0.9439 | 52900 | 2.8535 | - | - |
|
875 |
+
| 0.9457 | 53000 | 2.5506 | 2.1743 | 0.8116 |
|
876 |
+
| 0.9475 | 53100 | 2.1566 | - | - |
|
877 |
+
| 0.9493 | 53200 | 2.0386 | - | - |
|
878 |
+
| 0.9511 | 53300 | 1.8535 | - | - |
|
879 |
+
| 0.9528 | 53400 | 1.8561 | - | - |
|
880 |
+
| 0.9546 | 53500 | 1.3213 | - | - |
|
881 |
+
| 0.9564 | 53600 | 1.0904 | - | - |
|
882 |
+
| 0.9582 | 53700 | 1.2266 | - | - |
|
883 |
+
| 0.9600 | 53800 | 0.9386 | - | - |
|
884 |
+
| 0.9618 | 53900 | 0.8379 | - | - |
|
885 |
+
| 0.9635 | 54000 | 0.9314 | 2.3331 | 0.8071 |
|
886 |
+
| 0.9653 | 54100 | 1.1145 | - | - |
|
887 |
+
| 0.9671 | 54200 | 1.4435 | - | - |
|
888 |
+
| 0.9689 | 54300 | 1.3226 | - | - |
|
889 |
+
| 0.9707 | 54400 | 0.6677 | - | - |
|
890 |
+
| 0.9725 | 54500 | 0.7357 | - | - |
|
891 |
+
| 0.9743 | 54600 | 0.6854 | - | - |
|
892 |
+
| 0.9760 | 54700 | 0.8408 | - | - |
|
893 |
+
| 0.9778 | 54800 | 0.6291 | - | - |
|
894 |
+
| 0.9796 | 54900 | 0.8203 | - | - |
|
895 |
+
| 0.9814 | 55000 | 1.6263 | 2.4720 | 0.8104 |
|
896 |
+
| 0.9832 | 55100 | 0.95 | - | - |
|
897 |
+
| 0.9850 | 55200 | 0.6462 | - | - |
|
898 |
+
| 0.9867 | 55300 | 1.2467 | - | - |
|
899 |
+
| 0.9885 | 55400 | 1.4926 | - | - |
|
900 |
+
| 0.9903 | 55500 | 1.9608 | - | - |
|
901 |
+
| 0.9921 | 55600 | 1.6415 | - | - |
|
902 |
+
| 0.9939 | 55700 | 1.3258 | - | - |
|
903 |
+
| 0.9957 | 55800 | 1.2157 | - | - |
|
904 |
+
| 0.9974 | 55900 | 1.2391 | - | - |
|
905 |
+
| 0.9992 | 56000 | 1.3474 | 2.5008 | 0.8111 |
|
906 |
+
|
907 |
+
</details>
|
908 |
+
|
909 |
+
### Framework Versions
|
910 |
+
- Python: 3.10.14
|
911 |
+
- Sentence Transformers: 3.0.1
|
912 |
+
- Transformers: 4.41.2
|
913 |
+
- PyTorch: 2.3.1+cu121
|
914 |
+
- Accelerate: 0.33.0
|
915 |
+
- Datasets: 2.21.0
|
916 |
+
- Tokenizers: 0.19.1
|
917 |
+
|
918 |
+
## Citation
|
919 |
+
|
920 |
+
### BibTeX
|
921 |
+
|
922 |
+
#### Sentence Transformers
|
923 |
+
```bibtex
|
924 |
+
@inproceedings{reimers-2019-sentence-bert,
|
925 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
926 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
927 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
928 |
+
month = "11",
|
929 |
+
year = "2019",
|
930 |
+
publisher = "Association for Computational Linguistics",
|
931 |
+
url = "https://arxiv.org/abs/1908.10084",
|
932 |
+
}
|
933 |
+
```
|
934 |
+
|
935 |
+
#### CoSENTLoss
|
936 |
+
```bibtex
|
937 |
+
@online{kexuefm-8847,
|
938 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
939 |
+
author={Su Jianlin},
|
940 |
+
year={2022},
|
941 |
+
month={Jan},
|
942 |
+
url={https://kexue.fm/archives/8847},
|
943 |
+
}
|
944 |
+
```
|
945 |
+
|
946 |
+
<!--
|
947 |
+
## Glossary
|
948 |
+
|
949 |
+
*Clearly define terms in order to be accessible across audiences.*
|
950 |
+
-->
|
951 |
+
|
952 |
+
<!--
|
953 |
+
## Model Card Authors
|
954 |
+
|
955 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
956 |
+
-->
|
957 |
+
|
958 |
+
<!--
|
959 |
+
## Model Card Contact
|
960 |
+
|
961 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
962 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./models/paraphrase-multilingual-MiniLM-L12-v2-amazon_massive_intent-similarity/checkpoint-56000",
|
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": 12,
|
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": 250037
|
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": "2.3.1+cu121"
|
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 sha256:097bc28db6ad367ffbdb8f158902833d723e1f224b443d47d46da33426d2cd44
|
3 |
+
size 470637416
|
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": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": 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 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
|
3 |
+
size 17082987
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"max_length": 128,
|
51 |
+
"model_max_length": 128,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "</s>",
|
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 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|