Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- README.md +482 -0
- config.json +31 -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 +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:2560698
|
8 |
+
- loss:ModifiedMatryoshkaLoss
|
9 |
+
base_model: google-bert/bert-base-multilingual-cased
|
10 |
+
widget:
|
11 |
+
- source_sentence: We got off the exit, we found a Shoney's restaurant.
|
12 |
+
sentences:
|
13 |
+
- Nos alejamos de la salida, comenzamos a buscar un -- encontramos un restaurante
|
14 |
+
Shoney's.
|
15 |
+
- Reduzcan sus emisiones de dióxido de carbono con todo el rango de opciones que
|
16 |
+
tienen y luego compren o adquieran compensaciones para el resto que no han reducido
|
17 |
+
completamente.
|
18 |
+
- En el momento que nos invitaron a ir allí teníamos sede en San Francisco. Así
|
19 |
+
que fuimos de un lado a otro durante el resto de 2009, pasando la mitad del tiempo
|
20 |
+
en el condado de Bertie.
|
21 |
+
- source_sentence: And in the audio world that's when the microphone gets too close
|
22 |
+
to its sound source, and then it gets in this self-destructive loop that creates
|
23 |
+
a very unpleasant sound.
|
24 |
+
sentences:
|
25 |
+
- Y, en el mundo del audio, es cuando el micrófono se acerca demasiado a su fuente
|
26 |
+
de sonido, y entra en este bucle autodestructivo que crea un sonido muy desagradable.
|
27 |
+
- Tiene que ayudarles a alcanzar un compromiso equitativo, y a asegurar que una
|
28 |
+
amplia coalición de partidarios locales regionales e internacionales les ayuden
|
29 |
+
a implementar el acuerdo.
|
30 |
+
- Y es un renegado y visionario absoluto, y esa es la razón por la que ahora vivo
|
31 |
+
y trabajo allí.
|
32 |
+
- source_sentence: Figure out some of the other options that are much better.
|
33 |
+
sentences:
|
34 |
+
- Así que no sólo estamos reclutando a las multinacionales, les estamos dando las
|
35 |
+
herramientas para entregar este bien público, el respeto por los Derechos Humanos,
|
36 |
+
y lo estamos verificando.
|
37 |
+
- Piensen en otras de las opciones que son mucho mejores.
|
38 |
+
- Termina la propiedad comunal de las tierras de reserva.
|
39 |
+
- source_sentence: He is 16 years old, loves hunting and fishing and being outside
|
40 |
+
and doing anything with his hands, and so for him, Studio H means that he can
|
41 |
+
stay interested in his education through that hands-on engagement.
|
42 |
+
sentences:
|
43 |
+
- Tiene 16 años, le encanta cazar, pescar y estar al aire libre y hacer tareas manuales.
|
44 |
+
Para él Studio H representa el nexo educativo mediante esa motivación práctica.
|
45 |
+
- Carbón capturado y secuestrado -- eso es lo que CCS significa -- es probable que
|
46 |
+
se convierta en la aplicación determinante que nos posibilitará continuar utilizando
|
47 |
+
combustibles fósiles en un modo que sea seguro.
|
48 |
+
- El condado de Bertie no es la excepción.
|
49 |
+
- source_sentence: There are thousands of these blue dots all over the county.
|
50 |
+
sentences:
|
51 |
+
- Me gusta crisis climática en vez de colapso climático, pero de nuevo, aquellos
|
52 |
+
de ustedes que son buenos en diseño de marcas, necesito su ayuda en esto.
|
53 |
+
- Si miran con cuidado, se ve que su cráneo ha sido sustituido por una cúpula transparente
|
54 |
+
de plexiglás así que el funcionamiento de su cerebro se puede observar y controlar
|
55 |
+
con luz.
|
56 |
+
- Hay miles de estos puntos azules en todo el condado.
|
57 |
+
pipeline_tag: sentence-similarity
|
58 |
+
library_name: sentence-transformers
|
59 |
+
metrics:
|
60 |
+
- negative_mse
|
61 |
+
model-index:
|
62 |
+
- name: SentenceTransformer based on google-bert/bert-base-multilingual-cased
|
63 |
+
results:
|
64 |
+
- task:
|
65 |
+
type: knowledge-distillation
|
66 |
+
name: Knowledge Distillation
|
67 |
+
dataset:
|
68 |
+
name: MSE val en es
|
69 |
+
type: MSE-val-en-es
|
70 |
+
metrics:
|
71 |
+
- type: negative_mse
|
72 |
+
value: -31.070706248283386
|
73 |
+
name: Negative Mse
|
74 |
+
- task:
|
75 |
+
type: knowledge-distillation
|
76 |
+
name: Knowledge Distillation
|
77 |
+
dataset:
|
78 |
+
name: MSE val en pt
|
79 |
+
type: MSE-val-en-pt
|
80 |
+
metrics:
|
81 |
+
- type: negative_mse
|
82 |
+
value: -31.284737586975098
|
83 |
+
name: Negative Mse
|
84 |
+
- task:
|
85 |
+
type: knowledge-distillation
|
86 |
+
name: Knowledge Distillation
|
87 |
+
dataset:
|
88 |
+
name: MSE val en pt br
|
89 |
+
type: MSE-val-en-pt-br
|
90 |
+
metrics:
|
91 |
+
- type: negative_mse
|
92 |
+
value: -29.748335480690002
|
93 |
+
name: Negative Mse
|
94 |
+
---
|
95 |
+
|
96 |
+
# SentenceTransformer based on google-bert/bert-base-multilingual-cased
|
97 |
+
|
98 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased). 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.
|
99 |
+
|
100 |
+
## Model Details
|
101 |
+
|
102 |
+
### Model Description
|
103 |
+
- **Model Type:** Sentence Transformer
|
104 |
+
- **Base model:** [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) <!-- at revision 3f076fdb1ab68d5b2880cb87a0886f315b8146f8 -->
|
105 |
+
- **Maximum Sequence Length:** 128 tokens
|
106 |
+
- **Output Dimensionality:** 768 dimensions
|
107 |
+
- **Similarity Function:** Cosine Similarity
|
108 |
+
<!-- - **Training Dataset:** Unknown -->
|
109 |
+
<!-- - **Language:** Unknown -->
|
110 |
+
<!-- - **License:** Unknown -->
|
111 |
+
|
112 |
+
### Model Sources
|
113 |
+
|
114 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
115 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
116 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
117 |
+
|
118 |
+
### Full Model Architecture
|
119 |
+
|
120 |
+
```
|
121 |
+
SentenceTransformer(
|
122 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
123 |
+
(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})
|
124 |
+
)
|
125 |
+
```
|
126 |
+
|
127 |
+
## Usage
|
128 |
+
|
129 |
+
### Direct Usage (Sentence Transformers)
|
130 |
+
|
131 |
+
First install the Sentence Transformers library:
|
132 |
+
|
133 |
+
```bash
|
134 |
+
pip install -U sentence-transformers
|
135 |
+
```
|
136 |
+
|
137 |
+
Then you can load this model and run inference.
|
138 |
+
```python
|
139 |
+
from sentence_transformers import SentenceTransformer
|
140 |
+
|
141 |
+
# Download from the 🤗 Hub
|
142 |
+
model = SentenceTransformer("luanafelbarros/bert-en-es-pt-matryoshka_v1")
|
143 |
+
# Run inference
|
144 |
+
sentences = [
|
145 |
+
'There are thousands of these blue dots all over the county.',
|
146 |
+
'Hay miles de estos puntos azules en todo el condado.',
|
147 |
+
'Me gusta crisis climática en vez de colapso climático, pero de nuevo, aquellos de ustedes que son buenos en diseño de marcas, necesito su ayuda en esto.',
|
148 |
+
]
|
149 |
+
embeddings = model.encode(sentences)
|
150 |
+
print(embeddings.shape)
|
151 |
+
# [3, 768]
|
152 |
+
|
153 |
+
# Get the similarity scores for the embeddings
|
154 |
+
similarities = model.similarity(embeddings, embeddings)
|
155 |
+
print(similarities.shape)
|
156 |
+
# [3, 3]
|
157 |
+
```
|
158 |
+
|
159 |
+
<!--
|
160 |
+
### Direct Usage (Transformers)
|
161 |
+
|
162 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
163 |
+
|
164 |
+
</details>
|
165 |
+
-->
|
166 |
+
|
167 |
+
<!--
|
168 |
+
### Downstream Usage (Sentence Transformers)
|
169 |
+
|
170 |
+
You can finetune this model on your own dataset.
|
171 |
+
|
172 |
+
<details><summary>Click to expand</summary>
|
173 |
+
|
174 |
+
</details>
|
175 |
+
-->
|
176 |
+
|
177 |
+
<!--
|
178 |
+
### Out-of-Scope Use
|
179 |
+
|
180 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
181 |
+
-->
|
182 |
+
|
183 |
+
## Evaluation
|
184 |
+
|
185 |
+
### Metrics
|
186 |
+
|
187 |
+
#### Knowledge Distillation
|
188 |
+
|
189 |
+
* Datasets: `MSE-val-en-es`, `MSE-val-en-pt` and `MSE-val-en-pt-br`
|
190 |
+
* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
|
191 |
+
|
192 |
+
| Metric | MSE-val-en-es | MSE-val-en-pt | MSE-val-en-pt-br |
|
193 |
+
|:-----------------|:--------------|:--------------|:-----------------|
|
194 |
+
| **negative_mse** | **-31.0707** | **-31.2847** | **-29.7483** |
|
195 |
+
|
196 |
+
<!--
|
197 |
+
## Bias, Risks and Limitations
|
198 |
+
|
199 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
200 |
+
-->
|
201 |
+
|
202 |
+
<!--
|
203 |
+
### Recommendations
|
204 |
+
|
205 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
206 |
+
-->
|
207 |
+
|
208 |
+
## Training Details
|
209 |
+
|
210 |
+
### Training Dataset
|
211 |
+
|
212 |
+
#### Unnamed Dataset
|
213 |
+
|
214 |
+
|
215 |
+
* Size: 2,560,698 training samples
|
216 |
+
* Columns: <code>english</code>, <code>non_english</code>, and <code>label</code>
|
217 |
+
* Approximate statistics based on the first 1000 samples:
|
218 |
+
| | english | non_english | label |
|
219 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-------------------------------------|
|
220 |
+
| type | string | string | list |
|
221 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 25.46 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.67 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
|
222 |
+
* Samples:
|
223 |
+
| english | non_english | label |
|
224 |
+
|:-------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------|
|
225 |
+
| <code>And then there are certain conceptual things that can also benefit from hand calculating, but I think they're relatively small in number.</code> | <code>Y luego hay ciertas aspectos conceptuales que pueden beneficiarse del cálculo a mano pero creo que son relativamente pocos.</code> | <code>[-0.015244179405272007, 0.04601434990763664, -0.052873335778713226, 0.03535117208957672, -0.039562877267599106, ...]</code> |
|
226 |
+
| <code>One thing I often ask about is ancient Greek and how this relates.</code> | <code>Algo que pregunto a menudo es sobre el griego antiguo y cómo se relaciona.</code> | <code>[0.0012022971641272306, -0.009590390138328075, -0.032977133989334106, 0.017047710716724396, -0.0028919472824782133, ...]</code> |
|
227 |
+
| <code>See, the thing we're doing right now is we're forcing people to learn mathematics.</code> | <code>Vean, lo que estamos haciendo ahora es forzar a la gente a aprender matemáticas.</code> | <code>[-0.01942082867026329, 0.1043599545955658, 0.009455358609557152, -0.02814248949289322, -0.017036128789186478, ...]</code> |
|
228 |
+
* Loss: <code>__main__.ModifiedMatryoshkaLoss</code> with these parameters:
|
229 |
+
```json
|
230 |
+
{
|
231 |
+
"loss": "MSELoss",
|
232 |
+
"matryoshka_dims": [
|
233 |
+
768,
|
234 |
+
512,
|
235 |
+
256,
|
236 |
+
128,
|
237 |
+
64
|
238 |
+
],
|
239 |
+
"matryoshka_weights": [
|
240 |
+
1,
|
241 |
+
1,
|
242 |
+
1,
|
243 |
+
1,
|
244 |
+
1
|
245 |
+
],
|
246 |
+
"n_dims_per_step": -1
|
247 |
+
}
|
248 |
+
```
|
249 |
+
|
250 |
+
### Evaluation Dataset
|
251 |
+
|
252 |
+
#### Unnamed Dataset
|
253 |
+
|
254 |
+
|
255 |
+
* Size: 6,974 evaluation samples
|
256 |
+
* Columns: <code>english</code>, <code>non_english</code>, and <code>label</code>
|
257 |
+
* Approximate statistics based on the first 1000 samples:
|
258 |
+
| | english | non_english | label |
|
259 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-------------------------------------|
|
260 |
+
| type | string | string | list |
|
261 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 25.68 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 27.31 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
|
262 |
+
* Samples:
|
263 |
+
| english | non_english | label |
|
264 |
+
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------|
|
265 |
+
| <code>Thank you so much, Chris.</code> | <code>Muchas gracias Chris.</code> | <code>[-0.0616779625415802, -0.04450426995754242, -0.03250579163432121, -0.06641441583633423, 0.003981655463576317, ...]</code> |
|
266 |
+
| <code>And it's truly a great honor to have the opportunity to come to this stage twice; I'm extremely grateful.</code> | <code>Y es en verdad un gran honor tener la oportunidad de venir a este escenario por segunda vez. Estoy extremadamente agradecido.</code> | <code>[0.011398598551750183, -0.02500401996076107, -0.009884790517389774, 0.009336900897324085, 0.003082842566072941, ...]</code> |
|
267 |
+
| <code>I have been blown away by this conference, and I want to thank all of you for the many nice comments about what I had to say the other night.</code> | <code>He quedado conmovido por esta conferencia, y deseo agradecer a todos ustedes sus amables comentarios acerca de lo que tenía que decir la otra noche.</code> | <code>[-0.03842132166028023, 0.03635749593377113, -0.02491452544927597, -0.0032229204662144184, 0.0003549510147422552, ...]</code> |
|
268 |
+
* Loss: <code>__main__.ModifiedMatryoshkaLoss</code> with these parameters:
|
269 |
+
```json
|
270 |
+
{
|
271 |
+
"loss": "MSELoss",
|
272 |
+
"matryoshka_dims": [
|
273 |
+
768,
|
274 |
+
512,
|
275 |
+
256,
|
276 |
+
128,
|
277 |
+
64
|
278 |
+
],
|
279 |
+
"matryoshka_weights": [
|
280 |
+
1,
|
281 |
+
1,
|
282 |
+
1,
|
283 |
+
1,
|
284 |
+
1
|
285 |
+
],
|
286 |
+
"n_dims_per_step": -1
|
287 |
+
}
|
288 |
+
```
|
289 |
+
|
290 |
+
### Training Hyperparameters
|
291 |
+
#### Non-Default Hyperparameters
|
292 |
+
|
293 |
+
- `eval_strategy`: steps
|
294 |
+
- `per_device_train_batch_size`: 200
|
295 |
+
- `per_device_eval_batch_size`: 200
|
296 |
+
- `learning_rate`: 2e-05
|
297 |
+
- `num_train_epochs`: 1
|
298 |
+
- `warmup_ratio`: 0.1
|
299 |
+
- `fp16`: True
|
300 |
+
- `label_names`: ['label']
|
301 |
+
|
302 |
+
#### All Hyperparameters
|
303 |
+
<details><summary>Click to expand</summary>
|
304 |
+
|
305 |
+
- `overwrite_output_dir`: False
|
306 |
+
- `do_predict`: False
|
307 |
+
- `eval_strategy`: steps
|
308 |
+
- `prediction_loss_only`: True
|
309 |
+
- `per_device_train_batch_size`: 200
|
310 |
+
- `per_device_eval_batch_size`: 200
|
311 |
+
- `per_gpu_train_batch_size`: None
|
312 |
+
- `per_gpu_eval_batch_size`: None
|
313 |
+
- `gradient_accumulation_steps`: 1
|
314 |
+
- `eval_accumulation_steps`: None
|
315 |
+
- `torch_empty_cache_steps`: None
|
316 |
+
- `learning_rate`: 2e-05
|
317 |
+
- `weight_decay`: 0.0
|
318 |
+
- `adam_beta1`: 0.9
|
319 |
+
- `adam_beta2`: 0.999
|
320 |
+
- `adam_epsilon`: 1e-08
|
321 |
+
- `max_grad_norm`: 1.0
|
322 |
+
- `num_train_epochs`: 1
|
323 |
+
- `max_steps`: -1
|
324 |
+
- `lr_scheduler_type`: linear
|
325 |
+
- `lr_scheduler_kwargs`: {}
|
326 |
+
- `warmup_ratio`: 0.1
|
327 |
+
- `warmup_steps`: 0
|
328 |
+
- `log_level`: passive
|
329 |
+
- `log_level_replica`: warning
|
330 |
+
- `log_on_each_node`: True
|
331 |
+
- `logging_nan_inf_filter`: True
|
332 |
+
- `save_safetensors`: True
|
333 |
+
- `save_on_each_node`: False
|
334 |
+
- `save_only_model`: False
|
335 |
+
- `restore_callback_states_from_checkpoint`: False
|
336 |
+
- `no_cuda`: False
|
337 |
+
- `use_cpu`: False
|
338 |
+
- `use_mps_device`: False
|
339 |
+
- `seed`: 42
|
340 |
+
- `data_seed`: None
|
341 |
+
- `jit_mode_eval`: False
|
342 |
+
- `use_ipex`: False
|
343 |
+
- `bf16`: False
|
344 |
+
- `fp16`: True
|
345 |
+
- `fp16_opt_level`: O1
|
346 |
+
- `half_precision_backend`: auto
|
347 |
+
- `bf16_full_eval`: False
|
348 |
+
- `fp16_full_eval`: False
|
349 |
+
- `tf32`: None
|
350 |
+
- `local_rank`: 0
|
351 |
+
- `ddp_backend`: None
|
352 |
+
- `tpu_num_cores`: None
|
353 |
+
- `tpu_metrics_debug`: False
|
354 |
+
- `debug`: []
|
355 |
+
- `dataloader_drop_last`: False
|
356 |
+
- `dataloader_num_workers`: 0
|
357 |
+
- `dataloader_prefetch_factor`: None
|
358 |
+
- `past_index`: -1
|
359 |
+
- `disable_tqdm`: False
|
360 |
+
- `remove_unused_columns`: True
|
361 |
+
- `label_names`: ['label']
|
362 |
+
- `load_best_model_at_end`: False
|
363 |
+
- `ignore_data_skip`: False
|
364 |
+
- `fsdp`: []
|
365 |
+
- `fsdp_min_num_params`: 0
|
366 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
367 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
368 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
369 |
+
- `deepspeed`: None
|
370 |
+
- `label_smoothing_factor`: 0.0
|
371 |
+
- `optim`: adamw_torch
|
372 |
+
- `optim_args`: None
|
373 |
+
- `adafactor`: False
|
374 |
+
- `group_by_length`: False
|
375 |
+
- `length_column_name`: length
|
376 |
+
- `ddp_find_unused_parameters`: None
|
377 |
+
- `ddp_bucket_cap_mb`: None
|
378 |
+
- `ddp_broadcast_buffers`: False
|
379 |
+
- `dataloader_pin_memory`: True
|
380 |
+
- `dataloader_persistent_workers`: False
|
381 |
+
- `skip_memory_metrics`: True
|
382 |
+
- `use_legacy_prediction_loop`: False
|
383 |
+
- `push_to_hub`: False
|
384 |
+
- `resume_from_checkpoint`: None
|
385 |
+
- `hub_model_id`: None
|
386 |
+
- `hub_strategy`: every_save
|
387 |
+
- `hub_private_repo`: False
|
388 |
+
- `hub_always_push`: False
|
389 |
+
- `gradient_checkpointing`: False
|
390 |
+
- `gradient_checkpointing_kwargs`: None
|
391 |
+
- `include_inputs_for_metrics`: False
|
392 |
+
- `include_for_metrics`: []
|
393 |
+
- `eval_do_concat_batches`: True
|
394 |
+
- `fp16_backend`: auto
|
395 |
+
- `push_to_hub_model_id`: None
|
396 |
+
- `push_to_hub_organization`: None
|
397 |
+
- `mp_parameters`:
|
398 |
+
- `auto_find_batch_size`: False
|
399 |
+
- `full_determinism`: False
|
400 |
+
- `torchdynamo`: None
|
401 |
+
- `ray_scope`: last
|
402 |
+
- `ddp_timeout`: 1800
|
403 |
+
- `torch_compile`: False
|
404 |
+
- `torch_compile_backend`: None
|
405 |
+
- `torch_compile_mode`: None
|
406 |
+
- `dispatch_batches`: None
|
407 |
+
- `split_batches`: None
|
408 |
+
- `include_tokens_per_second`: False
|
409 |
+
- `include_num_input_tokens_seen`: False
|
410 |
+
- `neftune_noise_alpha`: None
|
411 |
+
- `optim_target_modules`: None
|
412 |
+
- `batch_eval_metrics`: False
|
413 |
+
- `eval_on_start`: False
|
414 |
+
- `use_liger_kernel`: False
|
415 |
+
- `eval_use_gather_object`: False
|
416 |
+
- `average_tokens_across_devices`: False
|
417 |
+
- `prompts`: None
|
418 |
+
- `batch_sampler`: batch_sampler
|
419 |
+
- `multi_dataset_batch_sampler`: proportional
|
420 |
+
|
421 |
+
</details>
|
422 |
+
|
423 |
+
### Training Logs
|
424 |
+
| Epoch | Step | Training Loss | Validation Loss | MSE-val-en-es_negative_mse | MSE-val-en-pt_negative_mse | MSE-val-en-pt-br_negative_mse |
|
425 |
+
|:------:|:-----:|:-------------:|:---------------:|:--------------------------:|:--------------------------:|:-----------------------------:|
|
426 |
+
| 0.0781 | 1000 | 0.0252 | 0.0231 | -24.4152 | -24.3443 | -25.3002 |
|
427 |
+
| 0.1562 | 2000 | 0.0222 | 0.0212 | -25.3038 | -25.3995 | -24.8563 |
|
428 |
+
| 0.2343 | 3000 | 0.021 | 0.0204 | -27.0894 | -27.2195 | -26.2906 |
|
429 |
+
| 0.3124 | 4000 | 0.0204 | 0.0198 | -28.7895 | -28.9815 | -28.0121 |
|
430 |
+
| 0.3905 | 5000 | 0.02 | 0.0194 | -29.1917 | -29.3694 | -28.0828 |
|
431 |
+
| 0.4686 | 6000 | 0.0196 | 0.0191 | -30.0902 | -30.2569 | -28.9723 |
|
432 |
+
| 0.5467 | 7000 | 0.0194 | 0.0189 | -30.3385 | -30.5334 | -29.1280 |
|
433 |
+
| 0.6248 | 8000 | 0.0192 | 0.0188 | -30.6629 | -30.8491 | -29.4291 |
|
434 |
+
| 0.7029 | 9000 | 0.0191 | 0.0186 | -30.6934 | -30.8920 | -29.4820 |
|
435 |
+
| 0.7810 | 10000 | 0.019 | 0.0185 | -31.0134 | -31.2205 | -29.6545 |
|
436 |
+
| 0.8591 | 11000 | 0.0189 | 0.0185 | -31.0993 | -31.2950 | -29.8062 |
|
437 |
+
| 0.9372 | 12000 | 0.0188 | 0.0184 | -31.0707 | -31.2847 | -29.7483 |
|
438 |
+
|
439 |
+
|
440 |
+
### Framework Versions
|
441 |
+
- Python: 3.10.12
|
442 |
+
- Sentence Transformers: 3.3.1
|
443 |
+
- Transformers: 4.46.3
|
444 |
+
- PyTorch: 2.5.1+cu121
|
445 |
+
- Accelerate: 1.1.1
|
446 |
+
- Datasets: 3.1.0
|
447 |
+
- Tokenizers: 0.20.3
|
448 |
+
|
449 |
+
## Citation
|
450 |
+
|
451 |
+
### BibTeX
|
452 |
+
|
453 |
+
#### Sentence Transformers
|
454 |
+
```bibtex
|
455 |
+
@inproceedings{reimers-2019-sentence-bert,
|
456 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
457 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
458 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
459 |
+
month = "11",
|
460 |
+
year = "2019",
|
461 |
+
publisher = "Association for Computational Linguistics",
|
462 |
+
url = "https://arxiv.org/abs/1908.10084",
|
463 |
+
}
|
464 |
+
```
|
465 |
+
|
466 |
+
<!--
|
467 |
+
## Glossary
|
468 |
+
|
469 |
+
*Clearly define terms in order to be accessible across audiences.*
|
470 |
+
-->
|
471 |
+
|
472 |
+
<!--
|
473 |
+
## Model Card Authors
|
474 |
+
|
475 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
476 |
+
-->
|
477 |
+
|
478 |
+
<!--
|
479 |
+
## Model Card Contact
|
480 |
+
|
481 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
482 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
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-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 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.46.3",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 119547
|
31 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.46.3",
|
5 |
+
"pytorch": "2.5.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3c3e5a1477bfcb62c0a33a522b96a612b37034f413d06396b2dc35d0ba98a12
|
3 |
+
size 711436136
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|