rufimelo/Legal-BERTimbau-sts-base-ma
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: rufimelo/Legal-BERTimbau-sts-base-ma
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-03 22:33:31 +08:00
commit 7d81e20073
16 changed files with 60213 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
.gitattributes vendored Normal file
View File

@@ -0,0 +1,32 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
model.safetensors filter=lfs diff=lfs merge=lfs -text

7
1_Pooling/config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"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
}

186
README.md Normal file
View File

@@ -0,0 +1,186 @@
---
language:
- pt
thumbnail: "Portugues BERT for the Legal Domain"
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- transformers
datasets:
- assin
- assin2
- stsb_multi_mt
- rufimelo/PortugueseLegalSentences-v0
widget:
- source_sentence: "O advogado apresentou as provas ao juíz."
sentences:
- "O juíz leu as provas."
- "O juíz leu o recurso."
- "O juíz atirou uma pedra."
example_title: "Example 1"
model-index:
- name: BERTimbau
results:
- task:
name: STS
type: STS
metrics:
- name: Pearson Correlation - assin Dataset
type: Pearson Correlation
value: 0.74874
- name: Pearson Correlation - assin2 Dataset
type: Pearson Correlation
value: 0.79532
- name: Pearson Correlation - stsb_multi_mt pt Dataset
type: Pearson Correlation
value: 0.82254
---
# rufimelo/Legal-BERTimbau-sts-base-ma
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
rufimelo/rufimelo/Legal-BERTimbau-sts-base-ma is based on Legal-BERTimbau-base which derives from [BERTimbau](https://huggingface.co/neuralmind/bert-large-portuguese-cased) alrge.
It is adapted to the Portuguese legal domain and trained for STS on portuguese datasets.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["Isto é um exemplo", "Isto é um outro exemplo"]
model = SentenceTransformer('rufimelo/Legal-BERTimbau-sts-base-ma')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('rufimelo/Legal-BERTimbau-sts-base-ma')
model = AutoModel.from_pretrained('rufimelo/Legal-BERTimbau-sts-base-ma')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results STS
| Model| Assin | Assin2|stsb_multi_mt pt| avg|
| ---------------------------------------- | ---------- | ---------- |---------- |---------- |
| Legal-BERTimbau-sts-base| 0.71457| 0.73545 | 0.72383|0.72462|
| Legal-BERTimbau-sts-base-ma| 0.74874 | 0.79532|0.82254 |0.78886|
| Legal-BERTimbau-sts-base-ma-v2| 0.75481 | 0.80262|0.82178|0.79307|
| Legal-BERTimbau-base-TSDAE-sts|0.78814 |0.81380 |0.75777|0.78657|
| Legal-BERTimbau-sts-large| 0.76629| 0.82357 | 0.79120|0.79369|
| Legal-BERTimbau-sts-large-v2| 0.76299 | 0.81121|0.81726 |0.79715|
| Legal-BERTimbau-sts-large-ma| 0.76195| 0.81622 | 0.82608|0.80142|
| Legal-BERTimbau-sts-large-ma-v2| 0.7836| 0.8462| 0.8261| 0.81863|
| Legal-BERTimbau-sts-large-ma-v3| 0.7749| **0.8470**| 0.8364| **0.81943**|
| Legal-BERTimbau-large-v2-sts| 0.71665| 0.80106| 0.73724| 0.75165|
| Legal-BERTimbau-large-TSDAE-sts| 0.72376| 0.79261| 0.73635| 0.75090|
| Legal-BERTimbau-large-TSDAE-sts-v2| 0.81326| 0.83130| 0.786314| 0.81029|
| Legal-BERTimbau-large-TSDAE-sts-v3|0.80703 |0.82270 |0.77638 |0.80204 |
| ---------------------------------------- | ---------- |---------- |---------- |---------- |
| BERTimbau base Fine-tuned for STS|**0.78455** | 0.80626|0.82841|0.80640|
| BERTimbau large Fine-tuned for STS|0.78193 | 0.81758|0.83784|0.81245|
| ---------------------------------------- | ---------- |---------- |---------- |---------- |
| paraphrase-multilingual-mpnet-base-v2| 0.71457| 0.79831 |0.83999 |0.78429|
| paraphrase-multilingual-mpnet-base-v2 Fine-tuned with assin(s)| 0.77641|0.79831 |**0.84575**|0.80682|
## Training
rufimelo/Legal-BERTimbau-sts-base-ma is based on Legal-BERTimbau-base which derives from [BERTimbau](https://huggingface.co/neuralmind/bert-base-portuguese-cased) base.
Firstly, due to the lack of portuguese datasets, it was trained using multilingual knowledge distillation.
For the Multilingual Knowledge Distillation process, the teacher model was 'sentence-transformers/paraphrase-xlm-r-multilingual-v1', the supposed supported language as English and the language to learn was portuguese.
It was trained for Semantic Textual Similarity, being submitted to a fine tuning stage with the [assin](https://huggingface.co/datasets/assin), [assin2](https://huggingface.co/datasets/assin2) and [stsb_multi_mt pt](https://huggingface.co/datasets/stsb_multi_mt) datasets.
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(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})
)
```
## Citing & Authors
## Citing & Authors
If you use this work, please cite:
```bibtex
@inproceedings{souza2020bertimbau,
author = {F{\'a}bio Souza and
Rodrigo Nogueira and
Roberto Lotufo},
title = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
year = {2020}
}
@inproceedings{fonseca2016assin,
title={ASSIN: Avaliacao de similaridade semantica e inferencia textual},
author={Fonseca, E and Santos, L and Criscuolo, Marcelo and Aluisio, S},
booktitle={Computational Processing of the Portuguese Language-12th International Conference, Tomar, Portugal},
pages={13--15},
year={2016}
}
@inproceedings{real2020assin,
title={The assin 2 shared task: a quick overview},
author={Real, Livy and Fonseca, Erick and Oliveira, Hugo Goncalo},
booktitle={International Conference on Computational Processing of the Portuguese Language},
pages={406--412},
year={2020},
organization={Springer}
}
@InProceedings{huggingface:dataset:stsb_multi_mt,
title = {Machine translated multilingual STS benchmark dataset.},
author={Philip May},
year={2021},
url={https://github.com/PhilipMay/stsb-multi-mt}
}
```

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_name_or_path": "rufimelo/Legal-BERTimbau-base",
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 29794
}

7
config_sentence_transformers.json Normal file
View File

@@ -0,0 +1,7 @@
{
"__version__": {
"sentence_transformers": "2.2.0",
"transformers": "4.20.1",
"pytorch": "1.10.1+cu111"
}
}

51
eval/mse_evaluation_TED2020-en-pt-dev.tsv.gz_results.csv Normal file
View File

@@ -0,0 +1,51 @@
epoch,steps,MSE
0,1000,5.367035418748856
0,2000,5.193383619189262
0,3000,5.061572417616844
0,4000,4.889959841966629
0,5000,4.609957709908485
0,6000,4.376227408647537
0,7000,4.126685485243797
0,8000,3.894694149494171
0,9000,3.71534526348114
0,-1,3.620472177863121
1,1000,3.3613737672567368
1,2000,3.2121531665325165
1,3000,3.0989496037364006
1,4000,2.999489940702915
1,5000,2.927454374730587
1,6000,2.853638492524624
1,7000,2.805120311677456
1,8000,2.740798704326153
1,9000,2.7038952335715294
1,-1,2.6784922927618027
2,1000,2.6389440521597862
2,2000,2.608192525804043
2,3000,2.5770554319024086
2,4000,2.548805996775627
2,5000,2.518361434340477
2,6000,2.505100704729557
2,7000,2.474398724734783
2,8000,2.456068992614746
2,9000,2.4350930005311966
2,-1,2.429385669529438
3,1000,2.4136649444699287
3,2000,2.3951873183250427
3,3000,2.381756342947483
3,4000,2.368186227977276
3,5000,2.3565009236335754
3,6000,2.345930226147175
3,7000,2.3331772536039352
3,8000,2.3244358599185944
3,9000,2.315283380448818
3,-1,2.3112069815397263
4,1000,2.3025305941700935
4,2000,2.2977473214268684
4,3000,2.2921686992049217
4,4000,2.2856738418340683
4,5000,2.2822346538305283
4,6000,2.2782722488045692
4,7000,2.2773338481783867
4,8000,2.2727908566594124
4,9000,2.2715413942933083
4,-1,2.2708337754011154
1 epoch steps MSE
2 0 1000 5.367035418748856
3 0 2000 5.193383619189262
4 0 3000 5.061572417616844
5 0 4000 4.889959841966629
6 0 5000 4.609957709908485
7 0 6000 4.376227408647537
8 0 7000 4.126685485243797
9 0 8000 3.894694149494171
10 0 9000 3.71534526348114
11 0 -1 3.620472177863121
12 1 1000 3.3613737672567368
13 1 2000 3.2121531665325165
14 1 3000 3.0989496037364006
15 1 4000 2.999489940702915
16 1 5000 2.927454374730587
17 1 6000 2.853638492524624
18 1 7000 2.805120311677456
19 1 8000 2.740798704326153
20 1 9000 2.7038952335715294
21 1 -1 2.6784922927618027
22 2 1000 2.6389440521597862
23 2 2000 2.608192525804043
24 2 3000 2.5770554319024086
25 2 4000 2.548805996775627
26 2 5000 2.518361434340477
27 2 6000 2.505100704729557
28 2 7000 2.474398724734783
29 2 8000 2.456068992614746
30 2 9000 2.4350930005311966
31 2 -1 2.429385669529438
32 3 1000 2.4136649444699287
33 3 2000 2.3951873183250427
34 3 3000 2.381756342947483
35 3 4000 2.368186227977276
36 3 5000 2.3565009236335754
37 3 6000 2.345930226147175
38 3 7000 2.3331772536039352
39 3 8000 2.3244358599185944
40 3 9000 2.315283380448818
41 3 -1 2.3112069815397263
42 4 1000 2.3025305941700935
43 4 2000 2.2977473214268684
44 4 3000 2.2921686992049217
45 4 4000 2.2856738418340683
46 4 5000 2.2822346538305283
47 4 6000 2.2782722488045692
48 4 7000 2.2773338481783867
49 4 8000 2.2727908566594124
50 4 9000 2.2715413942933083
51 4 -1 2.2708337754011154

51
eval/similarity_evaluation_STS.en-en.txt_results.csv Normal file
View File

@@ -0,0 +1,51 @@
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
0,1000,0.5140056805201973,0.5890807953828568,0.559515868293356,0.5922912753774262,0.5451349325359995,0.5819437046190675,0.22539237809823698,0.22321946160517406
0,2000,0.44619621291626504,0.5540864865627407,0.5162284484313594,0.5612347248265113,0.5150404333011369,0.5623890676693863,-0.03925888866920268,-0.0475617696609267
0,3000,0.43431388438460883,0.5435586338219284,0.5104576500180034,0.5460433731280702,0.5106740455350732,0.5445945825270726,0.0800124192733146,0.043582496564209525
0,4000,0.4815789858416121,0.5789254229000352,0.5474475569981547,0.5914225391719992,0.5464185006481518,0.589996427967515,0.16963048197098604,0.1883327838193587
0,5000,0.5294007839824181,0.5791329970376151,0.567137936153863,0.586330438059923,0.5649011349039395,0.5854009671994264,0.26817398324585057,0.2920114527819132
0,6000,0.5463603874314922,0.5734973592023205,0.5686220459321023,0.5703722152420895,0.5685273926188351,0.5723764588593888,0.29675469571899443,0.2705229167837791
0,7000,0.5469980476553145,0.5754608567852059,0.5701478329200861,0.5696883737777289,0.5730245680102316,0.573734916270884,0.2881408596960359,0.2756284717751429
0,8000,0.5838914267430435,0.6075437461274882,0.5854000552991829,0.5852629688375908,0.5866926240554013,0.5858368728883442,0.31497607283965356,0.31274042119512513
0,9000,0.6082456344854708,0.6231621623941724,0.6021977865748874,0.5993860825205976,0.601416194932199,0.5996405530374085,0.3162368894399329,0.32753507565285805
0,-1,0.6340241303458328,0.6488629157989745,0.6272089670611783,0.6212413328284562,0.6261247664573459,0.6231917609286052,0.3614941847538112,0.37414354186712145
1,1000,0.6489685011407933,0.667540359819105,0.6420782114622586,0.6385622414198467,0.6414950991944978,0.6386564185748599,0.41926990072233455,0.44001873201431163
1,2000,0.6501563072131639,0.6724291151556631,0.6478906595409323,0.6482440373517454,0.6471718858768877,0.6482186671793746,0.46287014167446283,0.485352539265214
1,3000,0.6604112169020907,0.6875120670267013,0.6634056718084428,0.6645136213759489,0.6626030154646603,0.6639950704285503,0.48555192969433814,0.5041191632851935
1,4000,0.6623806223921189,0.6924842364148425,0.6646110249594901,0.6652581974953791,0.6644709604750156,0.6659943168906857,0.528495364233784,0.5462351870070561
1,5000,0.6850816606891217,0.7075345145790395,0.6806572905222198,0.678914269368831,0.6797787684901784,0.6797999190225054,0.5479364502980393,0.5600915294836176
1,6000,0.6851700329054995,0.7078185836302832,0.6874242074031183,0.6846771424625312,0.686830327548116,0.6857607563400085,0.5694312299436508,0.5769857579033162
1,7000,0.6890474363339373,0.7154811444793906,0.6931583436684235,0.6908082674521603,0.6927393578265696,0.6917877098642965,0.579360228173903,0.5864995725423955
1,8000,0.7008481781396507,0.730200457213113,0.70873346507043,0.7077839879406864,0.7089441297196204,0.7086238944047829,0.5928760319501843,0.5999522986403294
1,9000,0.706014592098889,0.7314924140212724,0.7128013776176435,0.714079250257624,0.7132612508970737,0.7159108998234912,0.6054494128829728,0.6106827283635577
1,-1,0.7200253926417177,0.7398388163347404,0.7188000262780588,0.7147411811185732,0.7187261585057005,0.7175292093035124,0.6156732874019484,0.6163637249918793
2,1000,0.7178886037426083,0.73718993970129,0.7188454644618073,0.7163179757710785,0.7194434859869421,0.7170467916319146,0.6393994461966461,0.6420075877071223
2,2000,0.7299703637244253,0.7495332973528245,0.7277494458275431,0.727454712648792,0.727480829295701,0.7270045842874844,0.6458760444542806,0.6473533905429072
2,3000,0.734261157337224,0.753223504243134,0.7330394673578884,0.7315831316073258,0.7331244904533004,0.7331099547081914,0.6513263507254936,0.654268300100176
2,4000,0.7343011501722011,0.7521441187277185,0.7332802694216066,0.7300190220410061,0.7333951460801283,0.7306352097123775,0.6484172411241667,0.6530839743263172
2,5000,0.742889074497301,0.7578270373387953,0.7368161790211505,0.7330780497944523,0.7366270428032792,0.7334839725523863,0.662337265771508,0.668018933525192
2,6000,0.7431224743771536,0.758464751217027,0.7395656885060564,0.7367328922020631,0.7391788408718201,0.736238173840831,0.6692784158683307,0.6753332310990264
2,7000,0.7456805796696031,0.7601338010417898,0.7391593091221383,0.7367286638400012,0.7389669412990082,0.7370692391842527,0.6704350477276445,0.675819492736135
2,8000,0.7484436749852499,0.7616302568151206,0.7449520469152102,0.7437711930522265,0.7445979805880989,0.7435405551215821,0.6783951732730306,0.6837830360847332
2,9000,0.7515812487144248,0.7653300736192071,0.7479981515666386,0.7463912399443463,0.7477166755497039,0.7468763483918016,0.6711506749052628,0.6750929832546052
2,-1,0.7542529351113809,0.7673316264606489,0.7496156203554739,0.7468824987366188,0.749008069829383,0.7469482305468524,0.6818984216075609,0.686199737201335
3,1000,0.7611521834139107,0.7740116697252114,0.7536009182598888,0.7521679513138851,0.7531755451605359,0.7523513084687473,0.6892740827791818,0.6931277162413401
3,2000,0.7586248161621655,0.7701569411110422,0.755909895602228,0.7544185931204229,0.7548875499498792,0.7537097658802425,0.6879328540486022,0.6938988157227944
3,3000,0.7596638492114828,0.7707911954203143,0.7538348247790335,0.7529963258814494,0.7525016100495691,0.7513153597636032,0.6932043864798306,0.6983043845946526
3,4000,0.7613138031064591,0.7727527710204444,0.7571464667789152,0.7562071902725698,0.75597648205047,0.7563336567378731,0.6938998652971966,0.6962067326154422
3,5000,0.7650309606568694,0.7768146893756425,0.7594812570831899,0.7602564235415824,0.7590889841536251,0.7594991623359669,0.6978314025203474,0.7022659754500203
3,6000,0.7664952424832512,0.7790511085097905,0.7618506923044225,0.7615095562980834,0.7604737238388333,0.7618524380216414,0.7028292027901824,0.7054530072549742
3,7000,0.7663263064442136,0.777784906270553,0.7605793391945297,0.76110747750566,0.7593518137572904,0.7596444642322727,0.7090311202732736,0.710636594746206
3,8000,0.7736767057917926,0.7843703879835514,0.7661449138740201,0.7653715884467232,0.765197369764307,0.7645774251722043,0.7118985320428509,0.7171817148213416
3,9000,0.7702620952806344,0.7798033725602421,0.7627031514117696,0.7628783924164577,0.7618706673707889,0.7619888987972725,0.7116935091812764,0.7166508631843085
3,-1,0.7741045322811847,0.7846164017762386,0.766426143295265,0.7672316833573697,0.7656662248256637,0.7657060134461573,0.7175361585482368,0.7232432640352262
4,1000,0.7735083894838758,0.783234880571679,0.7675561452748201,0.768252640597022,0.7668961139319035,0.7669191689613465,0.7132638654641691,0.7171378936145191
4,2000,0.7725586129136159,0.7815166279883786,0.7650998024971205,0.76562106180837,0.764474806234657,0.763171302588376,0.7167715021505252,0.7228265781738621
4,3000,0.7748299500771854,0.7856911745330413,0.7683797677065075,0.7697556311117211,0.7675892533909863,0.7666677736169443,0.7149058735588968,0.7214984880899017
4,4000,0.7733142656422624,0.7829665717790294,0.7697179531436572,0.7706212921447395,0.7687669037730513,0.7688492240442888,0.7129858054389775,0.7196264768861717
4,5000,0.7727933114079547,0.7833551966921651,0.7680052284404755,0.7678947674079721,0.7670476312702246,0.7664794193069181,0.7161797854781118,0.7222991861057886
4,6000,0.7779233136930357,0.7875170581506424,0.7720112160776631,0.7722818852453789,0.7712775067154483,0.7710914091267029,0.7184599484089325,0.7252632679111196
4,7000,0.7762983351044147,0.7866387120314384,0.770285872163689,0.7706720324894812,0.76963801099933,0.7707823542996394,0.7172870884685507,0.723367808517774
4,8000,0.7759104338027587,0.7852256703096908,0.7699957777935053,0.7699055457666398,0.7692556775653562,0.7698498082667341,0.718403828898744,0.7242734467921043
4,9000,0.7761319595948091,0.7863454174629692,0.7707770511912085,0.770702399817016,0.7699469552447272,0.7706581942136426,0.7189941981604312,0.7253793556695439
4,-1,0.7758264479442808,0.7863123593595768,0.7705611226987729,0.7702111410247436,0.7697432047898018,0.7699178464562743,0.7189547164729727,0.7252978636007161
1 epoch steps cosine_pearson cosine_spearman euclidean_pearson euclidean_spearman manhattan_pearson manhattan_spearman dot_pearson dot_spearman
2 0 1000 0.5140056805201973 0.5890807953828568 0.559515868293356 0.5922912753774262 0.5451349325359995 0.5819437046190675 0.22539237809823698 0.22321946160517406
3 0 2000 0.44619621291626504 0.5540864865627407 0.5162284484313594 0.5612347248265113 0.5150404333011369 0.5623890676693863 -0.03925888866920268 -0.0475617696609267
4 0 3000 0.43431388438460883 0.5435586338219284 0.5104576500180034 0.5460433731280702 0.5106740455350732 0.5445945825270726 0.0800124192733146 0.043582496564209525
5 0 4000 0.4815789858416121 0.5789254229000352 0.5474475569981547 0.5914225391719992 0.5464185006481518 0.589996427967515 0.16963048197098604 0.1883327838193587
6 0 5000 0.5294007839824181 0.5791329970376151 0.567137936153863 0.586330438059923 0.5649011349039395 0.5854009671994264 0.26817398324585057 0.2920114527819132
7 0 6000 0.5463603874314922 0.5734973592023205 0.5686220459321023 0.5703722152420895 0.5685273926188351 0.5723764588593888 0.29675469571899443 0.2705229167837791
8 0 7000 0.5469980476553145 0.5754608567852059 0.5701478329200861 0.5696883737777289 0.5730245680102316 0.573734916270884 0.2881408596960359 0.2756284717751429
9 0 8000 0.5838914267430435 0.6075437461274882 0.5854000552991829 0.5852629688375908 0.5866926240554013 0.5858368728883442 0.31497607283965356 0.31274042119512513
10 0 9000 0.6082456344854708 0.6231621623941724 0.6021977865748874 0.5993860825205976 0.601416194932199 0.5996405530374085 0.3162368894399329 0.32753507565285805
11 0 -1 0.6340241303458328 0.6488629157989745 0.6272089670611783 0.6212413328284562 0.6261247664573459 0.6231917609286052 0.3614941847538112 0.37414354186712145
12 1 1000 0.6489685011407933 0.667540359819105 0.6420782114622586 0.6385622414198467 0.6414950991944978 0.6386564185748599 0.41926990072233455 0.44001873201431163
13 1 2000 0.6501563072131639 0.6724291151556631 0.6478906595409323 0.6482440373517454 0.6471718858768877 0.6482186671793746 0.46287014167446283 0.485352539265214
14 1 3000 0.6604112169020907 0.6875120670267013 0.6634056718084428 0.6645136213759489 0.6626030154646603 0.6639950704285503 0.48555192969433814 0.5041191632851935
15 1 4000 0.6623806223921189 0.6924842364148425 0.6646110249594901 0.6652581974953791 0.6644709604750156 0.6659943168906857 0.528495364233784 0.5462351870070561
16 1 5000 0.6850816606891217 0.7075345145790395 0.6806572905222198 0.678914269368831 0.6797787684901784 0.6797999190225054 0.5479364502980393 0.5600915294836176
17 1 6000 0.6851700329054995 0.7078185836302832 0.6874242074031183 0.6846771424625312 0.686830327548116 0.6857607563400085 0.5694312299436508 0.5769857579033162
18 1 7000 0.6890474363339373 0.7154811444793906 0.6931583436684235 0.6908082674521603 0.6927393578265696 0.6917877098642965 0.579360228173903 0.5864995725423955
19 1 8000 0.7008481781396507 0.730200457213113 0.70873346507043 0.7077839879406864 0.7089441297196204 0.7086238944047829 0.5928760319501843 0.5999522986403294
20 1 9000 0.706014592098889 0.7314924140212724 0.7128013776176435 0.714079250257624 0.7132612508970737 0.7159108998234912 0.6054494128829728 0.6106827283635577
21 1 -1 0.7200253926417177 0.7398388163347404 0.7188000262780588 0.7147411811185732 0.7187261585057005 0.7175292093035124 0.6156732874019484 0.6163637249918793
22 2 1000 0.7178886037426083 0.73718993970129 0.7188454644618073 0.7163179757710785 0.7194434859869421 0.7170467916319146 0.6393994461966461 0.6420075877071223
23 2 2000 0.7299703637244253 0.7495332973528245 0.7277494458275431 0.727454712648792 0.727480829295701 0.7270045842874844 0.6458760444542806 0.6473533905429072
24 2 3000 0.734261157337224 0.753223504243134 0.7330394673578884 0.7315831316073258 0.7331244904533004 0.7331099547081914 0.6513263507254936 0.654268300100176
25 2 4000 0.7343011501722011 0.7521441187277185 0.7332802694216066 0.7300190220410061 0.7333951460801283 0.7306352097123775 0.6484172411241667 0.6530839743263172
26 2 5000 0.742889074497301 0.7578270373387953 0.7368161790211505 0.7330780497944523 0.7366270428032792 0.7334839725523863 0.662337265771508 0.668018933525192
27 2 6000 0.7431224743771536 0.758464751217027 0.7395656885060564 0.7367328922020631 0.7391788408718201 0.736238173840831 0.6692784158683307 0.6753332310990264
28 2 7000 0.7456805796696031 0.7601338010417898 0.7391593091221383 0.7367286638400012 0.7389669412990082 0.7370692391842527 0.6704350477276445 0.675819492736135
29 2 8000 0.7484436749852499 0.7616302568151206 0.7449520469152102 0.7437711930522265 0.7445979805880989 0.7435405551215821 0.6783951732730306 0.6837830360847332
30 2 9000 0.7515812487144248 0.7653300736192071 0.7479981515666386 0.7463912399443463 0.7477166755497039 0.7468763483918016 0.6711506749052628 0.6750929832546052
31 2 -1 0.7542529351113809 0.7673316264606489 0.7496156203554739 0.7468824987366188 0.749008069829383 0.7469482305468524 0.6818984216075609 0.686199737201335
32 3 1000 0.7611521834139107 0.7740116697252114 0.7536009182598888 0.7521679513138851 0.7531755451605359 0.7523513084687473 0.6892740827791818 0.6931277162413401
33 3 2000 0.7586248161621655 0.7701569411110422 0.755909895602228 0.7544185931204229 0.7548875499498792 0.7537097658802425 0.6879328540486022 0.6938988157227944
34 3 3000 0.7596638492114828 0.7707911954203143 0.7538348247790335 0.7529963258814494 0.7525016100495691 0.7513153597636032 0.6932043864798306 0.6983043845946526
35 3 4000 0.7613138031064591 0.7727527710204444 0.7571464667789152 0.7562071902725698 0.75597648205047 0.7563336567378731 0.6938998652971966 0.6962067326154422
36 3 5000 0.7650309606568694 0.7768146893756425 0.7594812570831899 0.7602564235415824 0.7590889841536251 0.7594991623359669 0.6978314025203474 0.7022659754500203
37 3 6000 0.7664952424832512 0.7790511085097905 0.7618506923044225 0.7615095562980834 0.7604737238388333 0.7618524380216414 0.7028292027901824 0.7054530072549742
38 3 7000 0.7663263064442136 0.777784906270553 0.7605793391945297 0.76110747750566 0.7593518137572904 0.7596444642322727 0.7090311202732736 0.710636594746206
39 3 8000 0.7736767057917926 0.7843703879835514 0.7661449138740201 0.7653715884467232 0.765197369764307 0.7645774251722043 0.7118985320428509 0.7171817148213416
40 3 9000 0.7702620952806344 0.7798033725602421 0.7627031514117696 0.7628783924164577 0.7618706673707889 0.7619888987972725 0.7116935091812764 0.7166508631843085
41 3 -1 0.7741045322811847 0.7846164017762386 0.766426143295265 0.7672316833573697 0.7656662248256637 0.7657060134461573 0.7175361585482368 0.7232432640352262
42 4 1000 0.7735083894838758 0.783234880571679 0.7675561452748201 0.768252640597022 0.7668961139319035 0.7669191689613465 0.7132638654641691 0.7171378936145191
43 4 2000 0.7725586129136159 0.7815166279883786 0.7650998024971205 0.76562106180837 0.764474806234657 0.763171302588376 0.7167715021505252 0.7228265781738621
44 4 3000 0.7748299500771854 0.7856911745330413 0.7683797677065075 0.7697556311117211 0.7675892533909863 0.7666677736169443 0.7149058735588968 0.7214984880899017
45 4 4000 0.7733142656422624 0.7829665717790294 0.7697179531436572 0.7706212921447395 0.7687669037730513 0.7688492240442888 0.7129858054389775 0.7196264768861717
46 4 5000 0.7727933114079547 0.7833551966921651 0.7680052284404755 0.7678947674079721 0.7670476312702246 0.7664794193069181 0.7161797854781118 0.7222991861057886
47 4 6000 0.7779233136930357 0.7875170581506424 0.7720112160776631 0.7722818852453789 0.7712775067154483 0.7710914091267029 0.7184599484089325 0.7252632679111196
48 4 7000 0.7762983351044147 0.7866387120314384 0.770285872163689 0.7706720324894812 0.76963801099933 0.7707823542996394 0.7172870884685507 0.723367808517774
49 4 8000 0.7759104338027587 0.7852256703096908 0.7699957777935053 0.7699055457666398 0.7692556775653562 0.7698498082667341 0.718403828898744 0.7242734467921043
50 4 9000 0.7761319595948091 0.7863454174629692 0.7707770511912085 0.770702399817016 0.7699469552447272 0.7706581942136426 0.7189941981604312 0.7253793556695439
51 4 -1 0.7758264479442808 0.7863123593595768 0.7705611226987729 0.7702111410247436 0.7697432047898018 0.7699178464562743 0.7189547164729727 0.7252978636007161

51
eval/translation_evaluation_TED2020-en-pt-dev.tsv.gz_results.csv Normal file
View File

@@ -0,0 +1,51 @@
epoch,steps,src2trg,trg2src
0,1000,0.045,0.185
0,2000,0.055,0.108
0,3000,0.093,0.139
0,4000,0.21,0.248
0,5000,0.426,0.438
0,6000,0.584,0.613
0,7000,0.718,0.719
0,8000,0.808,0.814
0,9000,0.856,0.879
0,-1,0.887,0.895
1,1000,0.92,0.923
1,2000,0.93,0.929
1,3000,0.939,0.936
1,4000,0.946,0.947
1,5000,0.954,0.951
1,6000,0.957,0.958
1,7000,0.959,0.957
1,8000,0.964,0.959
1,9000,0.966,0.962
1,-1,0.966,0.964
2,1000,0.966,0.965
2,2000,0.969,0.966
2,3000,0.969,0.968
2,4000,0.971,0.97
2,5000,0.972,0.971
2,6000,0.972,0.972
2,7000,0.973,0.972
2,8000,0.973,0.97
2,9000,0.973,0.97
2,-1,0.972,0.971
3,1000,0.973,0.973
3,2000,0.975,0.971
3,3000,0.975,0.971
3,4000,0.973,0.971
3,5000,0.973,0.973
3,6000,0.974,0.974
3,7000,0.974,0.973
3,8000,0.974,0.976
3,9000,0.973,0.974
3,-1,0.973,0.975
4,1000,0.975,0.976
4,2000,0.974,0.975
4,3000,0.975,0.974
4,4000,0.974,0.975
4,5000,0.974,0.975
4,6000,0.974,0.976
4,7000,0.974,0.976
4,8000,0.974,0.976
4,9000,0.974,0.976
4,-1,0.974,0.976
1 epoch steps src2trg trg2src
2 0 1000 0.045 0.185
3 0 2000 0.055 0.108
4 0 3000 0.093 0.139
5 0 4000 0.21 0.248
6 0 5000 0.426 0.438
7 0 6000 0.584 0.613
8 0 7000 0.718 0.719
9 0 8000 0.808 0.814
10 0 9000 0.856 0.879
11 0 -1 0.887 0.895
12 1 1000 0.92 0.923
13 1 2000 0.93 0.929
14 1 3000 0.939 0.936
15 1 4000 0.946 0.947
16 1 5000 0.954 0.951
17 1 6000 0.957 0.958
18 1 7000 0.959 0.957
19 1 8000 0.964 0.959
20 1 9000 0.966 0.962
21 1 -1 0.966 0.964
22 2 1000 0.966 0.965
23 2 2000 0.969 0.966
24 2 3000 0.969 0.968
25 2 4000 0.971 0.97
26 2 5000 0.972 0.971
27 2 6000 0.972 0.972
28 2 7000 0.973 0.972
29 2 8000 0.973 0.97
30 2 9000 0.973 0.97
31 2 -1 0.972 0.971
32 3 1000 0.973 0.973
33 3 2000 0.975 0.971
34 3 3000 0.975 0.971
35 3 4000 0.973 0.971
36 3 5000 0.973 0.973
37 3 6000 0.974 0.974
38 3 7000 0.974 0.973
39 3 8000 0.974 0.976
40 3 9000 0.973 0.974
41 3 -1 0.973 0.975
42 4 1000 0.975 0.976
43 4 2000 0.974 0.975
44 4 3000 0.975 0.974
45 4 4000 0.974 0.975
46 4 5000 0.974 0.975
47 4 6000 0.974 0.976
48 4 7000 0.974 0.976
49 4 8000 0.974 0.976
50 4 9000 0.974 0.976
51 4 -1 0.974 0.976

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:001894c52cc891ae67d49c4b86fcbd406b9c30768db03df1f2b8e85b0f6c8e82
size 435719088

14
modules.json Normal file
View File

@@ -0,0 +1,14 @@
[
{
"idx": 0,
"name": "0",
"path": "",
"type": "sentence_transformers.models.Transformer"
},
{
"idx": 1,
"name": "1",
"path": "1_Pooling",
"type": "sentence_transformers.models.Pooling"
}
]

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa463de066e07c9105cf2565f31f553fcf919054cb93aa46fef22ae2542d3ca3
size 435761969

4
sentence_bert_config.json Normal file
View File

@@ -0,0 +1,4 @@
{
"max_seq_length": 128,
"do_lower_case": false
}

7
special_tokens_map.json Normal file
View File

@@ -0,0 +1,7 @@
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]"
}

29956
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

15
tokenizer_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"name_or_path": "rufimelo/Legal-BERTimbau-base",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ruimelo/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

29794
vocab.txt Normal file
View File

File diff suppressed because it is too large Load Diff