Rui Melo commited on
Commit
86e902e
1 Parent(s): 05884cf

initial commit

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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
+ }
README.md CHANGED
@@ -1,3 +1,125 @@
1
  ---
2
- license: mit
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
  ---
9
+
10
+ # {MODEL_NAME}
11
+
12
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
13
+
14
+ <!--- Describe your model here -->
15
+
16
+ ## Usage (Sentence-Transformers)
17
+
18
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
19
+
20
+ ```
21
+ pip install -U sentence-transformers
22
+ ```
23
+
24
+ Then you can use the model like this:
25
+
26
+ ```python
27
+ from sentence_transformers import SentenceTransformer
28
+ sentences = ["This is an example sentence", "Each sentence is converted"]
29
+
30
+ model = SentenceTransformer('{MODEL_NAME}')
31
+ embeddings = model.encode(sentences)
32
+ print(embeddings)
33
+ ```
34
+
35
+
36
+
37
+ ## Usage (HuggingFace Transformers)
38
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
39
+
40
+ ```python
41
+ from transformers import AutoTokenizer, AutoModel
42
+ import torch
43
+
44
+
45
+ #Mean Pooling - Take attention mask into account for correct averaging
46
+ def mean_pooling(model_output, attention_mask):
47
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
48
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
49
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
50
+
51
+
52
+ # Sentences we want sentence embeddings for
53
+ sentences = ['This is an example sentence', 'Each sentence is converted']
54
+
55
+ # Load model from HuggingFace Hub
56
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
57
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
58
+
59
+ # Tokenize sentences
60
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
61
+
62
+ # Compute token embeddings
63
+ with torch.no_grad():
64
+ model_output = model(**encoded_input)
65
+
66
+ # Perform pooling. In this case, mean pooling.
67
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
68
+
69
+ print("Sentence embeddings:")
70
+ print(sentence_embeddings)
71
+ ```
72
+
73
+
74
+
75
+ ## Evaluation Results
76
+
77
+ <!--- Describe how your model was evaluated -->
78
+
79
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
80
+
81
+
82
+ ## Training
83
+ The model was trained with the parameters:
84
+
85
+ **DataLoader**:
86
+
87
+ `torch.utils.data.dataloader.DataLoader` of length 3450 with parameters:
88
+ ```
89
+ {'batch_size': 5, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
90
+ ```
91
+
92
+ **Loss**:
93
+
94
+ `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
95
+
96
+ Parameters of the fit()-Method:
97
+ ```
98
+ {
99
+ "epochs": 8,
100
+ "evaluation_steps": 0,
101
+ "evaluator": "NoneType",
102
+ "max_grad_norm": 1,
103
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
104
+ "optimizer_params": {
105
+ "lr": 1e-05
106
+ },
107
+ "scheduler": "WarmupLinear",
108
+ "steps_per_epoch": null,
109
+ "warmup_steps": 2760,
110
+ "weight_decay": 0.01
111
+ }
112
+ ```
113
+
114
+
115
+ ## Full Model Architecture
116
+ ```
117
+ SentenceTransformer(
118
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
119
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
120
+ )
121
+ ```
122
+
123
+ ## Citing & Authors
124
+
125
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ruimelo/.cache/torch/sentence_transformers/rufimelo_Legal-BERTimbau-large",
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": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "output_past": true,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.20.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 29794
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.0",
4
+ "transformers": "4.20.1",
5
+ "pytorch": "1.10.1+cu111"
6
+ }
7
+ }
eval/mse_evaluation_TED2020-en-pt-dev.tsv.gz_results.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,MSE
2
+ 0,1000,64.99935984611511
3
+ 0,2000,62.76329755783081
4
+ 0,3000,61.53953671455383
5
+ 0,4000,58.37080478668213
6
+ 0,5000,54.03456091880798
7
+ 0,6000,49.51984882354736
8
+ 0,7000,45.98751664161682
9
+ 0,8000,43.67443919181824
10
+ 0,9000,41.6261225938797
11
+ 0,10000,39.84037637710571
12
+ 0,11000,38.216570019721985
13
+ 0,12000,36.40350699424744
14
+ 0,13000,35.88871657848358
15
+ 0,14000,34.63050723075867
16
+ 0,15000,33.85293185710907
17
+ 0,16000,32.859036326408386
18
+ 0,17000,32.202520966529846
19
+ 0,18000,31.7839115858078
20
+ 0,19000,31.272220611572266
21
+ 0,-1,31.08965754508972
22
+ 1,1000,30.368927121162415
23
+ 1,2000,29.852202534675598
24
+ 1,3000,29.51239049434662
25
+ 1,4000,28.987878561019897
26
+ 1,5000,28.705519437789917
27
+ 1,6000,28.418806195259094
28
+ 1,7000,28.066352009773254
29
+ 1,8000,27.935269474983215
30
+ 1,9000,27.698129415512085
31
+ 1,10000,27.39318311214447
32
+ 1,11000,27.302807569503784
33
+ 1,12000,27.083414793014526
34
+ 1,13000,26.880216598510742
35
+ 1,14000,26.773616671562195
36
+ 1,15000,26.427313685417175
37
+ 1,16000,26.260003447532654
38
+ 1,17000,26.178589463233948
39
+ 1,18000,25.91191828250885
40
+ 1,19000,25.875642895698547
41
+ 1,-1,25.815001130104065
42
+ 2,1000,25.804230570793152
43
+ 2,2000,25.660431385040283
44
+ 2,3000,25.59364140033722
45
+ 2,4000,25.508084893226624
46
+ 2,5000,25.35875141620636
47
+ 2,6000,25.22062659263611
48
+ 2,7000,25.159135460853577
49
+ 2,8000,24.956446886062622
50
+ 2,9000,24.871687591075897
51
+ 2,10000,24.808356165885925
52
+ 2,11000,24.743928015232086
53
+ 2,12000,24.755747616291046
54
+ 2,13000,24.648834764957428
55
+ 2,14000,24.519598484039307
56
+ 2,15000,24.472644925117493
57
+ 2,16000,24.416744709014893
58
+ 2,17000,24.312198162078857
59
+ 2,18000,24.279186129570007
60
+ 2,19000,24.304020404815674
61
+ 2,-1,24.219979345798492
62
+ 3,1000,24.235571920871735
63
+ 3,2000,24.162116646766663
64
+ 3,3000,24.112235009670258
65
+ 3,4000,24.13550764322281
66
+ 3,5000,23.988333344459534
67
+ 3,6000,23.9453986287117
68
+ 3,7000,23.897892236709595
69
+ 3,8000,23.885785043239594
70
+ 3,9000,23.80005270242691
71
+ 3,10000,23.821403086185455
72
+ 3,11000,23.703201115131378
73
+ 3,12000,23.73550683259964
74
+ 3,13000,23.70356023311615
75
+ 3,14000,23.703579604625702
76
+ 3,15000,23.54370504617691
77
+ 3,16000,23.583070933818817
78
+ 3,17000,23.5649511218071
79
+ 3,18000,23.503218591213226
80
+ 3,19000,23.50882589817047
81
+ 3,-1,23.483632504940033
82
+ 4,1000,23.52752536535263
83
+ 4,2000,23.5111266374588
84
+ 4,3000,23.47365766763687
85
+ 4,4000,23.44345450401306
86
+ 4,5000,23.41287136077881
87
+ 4,6000,23.393918573856354
88
+ 4,7000,23.358194530010223
89
+ 4,8000,23.27660471200943
90
+ 4,9000,23.287396132946014
91
+ 4,10000,23.24793189764023
92
+ 4,11000,23.219414055347443
93
+ 4,12000,23.18641096353531
94
+ 4,13000,23.21683168411255
95
+ 4,14000,23.219676315784454
96
+ 4,15000,23.17209541797638
97
+ 4,16000,23.18331152200699
98
+ 4,17000,23.168405890464783
99
+ 4,18000,23.155540227890015
100
+ 4,19000,23.15620929002762
101
+ 4,-1,23.156486451625824
eval/similarity_evaluation_STS.en-en.txt_results.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,1000,0.5723700099934447,0.6260013153204044,0.6195235703657329,0.6297253491072086,0.623386715642248,0.63454375987492,0.29285565299478483,0.28133522297238617
3
+ 0,2000,0.4512876780549574,0.5400560124485428,0.49146715534776886,0.5226021026504807,0.4914708377988649,0.5228362001500847,0.30445694976477344,0.3096706303382489
4
+ 0,3000,0.3802343487280994,0.4653197130059967,0.4084330748566771,0.4395613001185336,0.40816055604870155,0.4399395463247903,0.1676846205882516,0.18399448434393847
5
+ 0,4000,0.3978039458517782,0.5025108481155003,0.4419006161895136,0.49194263373682506,0.4432464649712142,0.490979720376385,0.17227463298539153,0.17467017720453848
6
+ 0,5000,0.4316552494171327,0.4975921098479585,0.4714941808113478,0.4929797356316226,0.4728046756859312,0.49078982848015446,0.24429162957671882,0.23046764297222386
7
+ 0,6000,0.4999437792048075,0.5397815533110761,0.5240676456440825,0.5307520783263499,0.5249635225341014,0.5342693067686761,0.31569971823340937,0.2638494082605849
8
+ 0,7000,0.5452157436454734,0.5809431203966221,0.5746706704449455,0.58033385186317,0.5765961075045893,0.5863788720253584,0.3147757836763207,0.2836554405546684
9
+ 0,8000,0.5671517411498572,0.5984965889014124,0.5991440894672145,0.6033999513069114,0.5985861660435446,0.6030747518247028,0.335790787409962,0.314279160589074
10
+ 0,9000,0.5560365767816866,0.586965076765746,0.5957021258750492,0.5881367174534194,0.5924504677222248,0.5855923966818611,0.4192009120599224,0.40509861172855277
11
+ 0,10000,0.6047227126882299,0.6193985357626077,0.6234072194670075,0.6135645493069589,0.6208593111812291,0.6112239587074698,0.4639327300298368,0.4571966450887027
12
+ 0,11000,0.6373482072614782,0.6480084022659371,0.6546131612230232,0.6367920953021513,0.6518351497261183,0.6315443135868902,0.5033544934271019,0.49712160846944403
13
+ 0,12000,0.617175609764256,0.6402420543480397,0.6481232987315185,0.6354459385802905,0.6448122480887685,0.6307905119502343,0.49096069208354903,0.4832348986653477
14
+ 0,13000,0.6210712633927629,0.6335977599627272,0.6441780213298841,0.6275189129040442,0.6405739970471596,0.6225713448951719,0.5146042627283327,0.5067930256944637
15
+ 0,14000,0.6652021810105723,0.676724362217363,0.678464713763157,0.6677502403359913,0.675370730319645,0.6635526299982641,0.5688267546183803,0.5632843272368374
16
+ 0,15000,0.6649492777778055,0.6798352835052042,0.6782949075006383,0.6625001522414238,0.6752047595933511,0.6603002507796277,0.5790825928101233,0.5770614840238777
17
+ 0,16000,0.6683991964754876,0.6864046205630574,0.6854231042074739,0.6746736066173836,0.6835876038393638,0.6733251435162164,0.5770708790346064,0.5716322671365097
18
+ 0,17000,0.682820577387972,0.7008521649351706,0.6995544342996738,0.6940879388259228,0.6983710847291914,0.6908470915038187,0.6010464416133104,0.5930212444279156
19
+ 0,18000,0.7070929942857228,0.7215150171415979,0.7176262019017724,0.7113919339690663,0.7179730124765973,0.7101445671608314,0.6320649258253889,0.6181300271440638
20
+ 0,19000,0.7050391175053488,0.7206724199016438,0.7247908870900343,0.7160208372370984,0.7244148234142286,0.7145535956016492,0.6308264562474821,0.6210472125701637
21
+ 0,-1,0.7066058283468926,0.724563666188165,0.7204132794734848,0.7160934881852513,0.71846158918219,0.7122007043125257,0.6259331425340063,0.6187062375741236
22
+ 1,1000,0.7132986061129764,0.726211574202619,0.7258113530128887,0.71887421283572,0.7231383983286782,0.7139873794819173,0.656182357244423,0.6445872729613793
23
+ 1,2000,0.7131336690624694,0.7316861498830137,0.7249876401595006,0.7172781983556611,0.7231842920513099,0.7118543630200082,0.656948474986115,0.6549056295818564
24
+ 1,3000,0.7351731268773352,0.7513803227807346,0.7456202286756073,0.7394847871112012,0.7431935226540799,0.7352441243597538,0.6848470792930701,0.6791952632476661
25
+ 1,4000,0.7409540531152012,0.7559192772558154,0.7515861951858731,0.7477581540799652,0.7498831829685604,0.7451761624464017,0.6888887287485415,0.6827109541037881
26
+ 1,5000,0.7423462131964345,0.7597728526803315,0.7596788532614885,0.7577313225975778,0.7581803609058917,0.7556094536356499,0.6874434021572445,0.6816961472089531
27
+ 1,6000,0.7448860894107862,0.762480157589545,0.7624488319664005,0.7579046854421122,0.7616941918865863,0.7548606491541578,0.698493449868909,0.6940541119294285
28
+ 1,7000,0.756288382227085,0.7702353580074613,0.7692492714653116,0.768393329734715,0.769134046387722,0.7670675460300611,0.7044289895135046,0.6945403735665369
29
+ 1,8000,0.7509610605398019,0.7645612805170593,0.7656382542536059,0.7620726972454066,0.7655873909439901,0.7604274800068103,0.7052852170473671,0.6994398920065249
30
+ 1,9000,0.7549754200191944,0.7688661374925361,0.7704863418942726,0.7655841597394669,0.7689510617584605,0.7615626030221315,0.7078213980680204,0.7003090126085031
31
+ 1,10000,0.758289734451616,0.7692259326643412,0.7743581188569517,0.7717356577463027,0.7733933831964022,0.7694062146467948,0.704163476500717,0.6971131396828746
32
+ 1,11000,0.7579547424866138,0.7723160965384244,0.773377623460383,0.768028537407746,0.7726574222102773,0.7657317680150793,0.7104537221886451,0.7022306109673215
33
+ 1,12000,0.770058291103023,0.782459937124714,0.7853622943787061,0.7843776915180217,0.7837698647091592,0.7801866159216628,0.721095422079322,0.7126062426739087
34
+ 1,13000,0.7644721641774666,0.7775865576501989,0.7838551232112407,0.7801781591975392,0.7830974658302025,0.7786424949759989,0.7127526801508547,0.7053496045827353
35
+ 1,14000,0.7679987802064016,0.7826452162623316,0.7874616921448943,0.7804656878177425,0.7863127387704726,0.7770626251510852,0.7166174607084033,0.7103229271605297
36
+ 1,15000,0.7727157667300284,0.7852260547062418,0.7889549350370786,0.7831906749683055,0.7879892656737133,0.7805994578175162,0.724889303193062,0.7207496836084096
37
+ 1,16000,0.7743474026501818,0.7856438937572593,0.7937764374669009,0.7870811524617246,0.793489524482856,0.7848447333275765,0.7305403407186635,0.7244913996365632
38
+ 1,17000,0.7758105761472955,0.7876927273744831,0.7920243720581309,0.7846410031555073,0.7909037555127167,0.7824660874695312,0.7340630955793304,0.7277337845448716
39
+ 1,18000,0.7805672267937347,0.7903416040079336,0.7956509142951407,0.7878199626328887,0.7940983982265936,0.7839329447084292,0.7396446569801722,0.7327324772950369
40
+ 1,19000,0.7827674781299959,0.7939626195190498,0.7964658960592859,0.7883016115113841,0.7947022842687362,0.784202406690732,0.7410594055353605,0.7326636703123947
41
+ 1,-1,0.7772735076515949,0.784883172982684,0.79327818952267,0.7850696053099547,0.7916007599369315,0.7817403467811035,0.7320980978482686,0.7226908861913329
42
+ 2,1000,0.778858890703781,0.7885587728040527,0.7932225977160065,0.7871945494442913,0.7921395481260183,0.7837222953984407,0.7402789907239563,0.7332122041907772
43
+ 2,2000,0.7806970403485964,0.7875055262541102,0.7938655299457252,0.7888816659069547,0.7931104382400748,0.7856619603951597,0.7380607299576202,0.7299940362651862
44
+ 2,3000,0.7844723587461059,0.7927556143486777,0.801595505205874,0.792330856159741,0.8015368676066014,0.7919003320225383,0.7450982266230133,0.7400033380586
45
+ 2,4000,0.7810887024044944,0.7898730246121745,0.798589904562383,0.78957434849199,0.798002899438714,0.7886894676314179,0.7397248629642452,0.7330788185875544
46
+ 2,5000,0.7785344148872018,0.7879037610810228,0.79768252393598,0.7895385996127402,0.7967042091215882,0.7866010411694333,0.7299531152896094,0.7216176510207346
47
+ 2,6000,0.7850117412257008,0.788997369268828,0.8033463183518811,0.7924619353836572,0.8019224350438007,0.7890273521998118,0.7451311515894946,0.735818028410507
48
+ 2,7000,0.7844172500819625,0.7881374741840758,0.8022177144050754,0.7915593722817358,0.8013574870941333,0.7883166029768761,0.7423639615333613,0.7324149657438498
49
+ 2,8000,0.7835405983291004,0.7922186123668276,0.8017872251369841,0.7907002459900855,0.8010396577789481,0.7878126590984184,0.7434053779568189,0.73443381643009
50
+ 2,9000,0.7870314015631342,0.7939587755535391,0.8018478350988324,0.7938207771917034,0.8007634779963503,0.791508631936994,0.7462455162792039,0.7376754325452963
51
+ 2,10000,0.7844891099685182,0.7940225853810173,0.8040027595623842,0.7964792637389306,0.8029042207169612,0.7931307853825258,0.7412977176134552,0.733139168846073
52
+ 2,11000,0.7842489070251935,0.792314327108045,0.8043892594292972,0.7945661221042358,0.8031395008708325,0.7920110382292476,0.7429536883071132,0.7358341730656522
53
+ 2,12000,0.7888144491616509,0.7968183014969779,0.8054341207960984,0.7942882033978094,0.8045893452196629,0.7919941247810003,0.7527132566070543,0.7456039958077469
54
+ 2,13000,0.7845425998672597,0.7915447652127948,0.8049378002589647,0.7942951225357288,0.8037612121417645,0.7921867074530883,0.7492903443825661,0.7424227299510592
55
+ 2,14000,0.7866408150449017,0.7953771988270019,0.8065055903413098,0.7948409656382537,0.8051111949165691,0.7930923457274186,0.7475077711029047,0.7415197824525865
56
+ 2,15000,0.784542021150478,0.7936797036574594,0.8042432484857206,0.7944127478803574,0.8026098203826021,0.7919887432292853,0.7456154058093194,0.7410392867637442
57
+ 2,16000,0.7884033931455445,0.7938480693468297,0.808806349619064,0.7985046491665391,0.8084314571797466,0.796943614772628,0.7456709933183066,0.7368758877190625
58
+ 2,17000,0.7863073385139975,0.7944707917595695,0.8086166754992482,0.7994106718374203,0.807516636440688,0.7969132474450933,0.7455314887355947,0.7397219597832139
59
+ 2,18000,0.7928203631762801,0.7970270288242111,0.8130282271230438,0.8004766034735484,0.8116198864958533,0.7969516871002005,0.7535002087413512,0.7439084226209598
60
+ 2,19000,0.7900017640040945,0.7943474004666748,0.810962045863006,0.7967725583074001,0.8097831325227183,0.7954267859820904,0.7463689920921452,0.7389055015087328
61
+ 2,-1,0.7942714375725454,0.7998565718366661,0.8155145317660067,0.8039984446744876,0.814185489227875,0.8006749520939025,0.7493211246777689,0.7408505480571669
62
+ 3,1000,0.7957942522534867,0.8026273021768069,0.815868045386862,0.8031796800207003,0.8151033479464161,0.8019907414882286,0.7603177532198132,0.7554437787221371
63
+ 3,2000,0.7960892918868433,0.8004508489046265,0.8164214572523217,0.8047480179490818,0.8161169676115229,0.8022844204532491,0.7582032637356728,0.7521095230381218
64
+ 3,3000,0.7924318241331291,0.7987679608040249,0.8112284903774285,0.8011650576965219,0.8106747824957385,0.7997158826989731,0.7550680066316094,0.7497316459731787
65
+ 3,4000,0.7912600904218274,0.7969705225312033,0.8102622012723937,0.7999922638191953,0.809659742710389,0.7981290937361399,0.7565326323807433,0.7509751688159028
66
+ 3,5000,0.7949985815697862,0.8010270593346862,0.815022572087091,0.8017493404541541,0.8137466147092767,0.8002394308015358,0.7584108524218812,0.752703415709531
67
+ 3,6000,0.7945479210940957,0.8026461376078096,0.8146074664012538,0.804489319070209,0.8133845431710623,0.8027176353663092,0.7585877696959269,0.7536901616561378
68
+ 3,7000,0.7971403464424573,0.8013430332996689,0.8172283397293227,0.8045554352769937,0.8162730970978793,0.8041964088982907,0.7623707000748308,0.7570697761331796
69
+ 3,8000,0.7982056723218348,0.8029025301073758,0.817927486522594,0.8071551091519067,0.8171254902329853,0.8061856610500983,0.7604100740312604,0.754487015706514
70
+ 3,9000,0.7973387043913959,0.8029940164865315,0.8177260433884168,0.8061699007915042,0.8173231273244351,0.805690942688866,0.7587219140768711,0.7530436066572315
71
+ 3,10000,0.7940008023721767,0.7997916088195346,0.8144970221475533,0.8023351607979908,0.8134668227171457,0.8012473185584517,0.7585779028528035,0.7513334264015036
72
+ 3,11000,0.7989213063390486,0.8043036555360403,0.8171616559196833,0.8036563317440317,0.815981418313407,0.8016893745921866,0.7649642804194935,0.7621338162970275
73
+ 3,12000,0.7970872159608983,0.8051062755346827,0.8168647400177472,0.8047741569145548,0.8159634340872441,0.8035187177787473,0.7623320649552251,0.7595637409565472
74
+ 3,13000,0.7947564793213664,0.7991569701137117,0.8150976227429091,0.8022498247636524,0.8143528729971656,0.8003520589910005,0.757230691778058,0.7522125413138097
75
+ 3,14000,0.7970708474188177,0.8010124522657455,0.816823488082002,0.8036655572612575,0.8158982229645625,0.8016659264025711,0.7619566033442233,0.7565554535478427
76
+ 3,15000,0.7960822607785477,0.801858509074659,0.8169743853616835,0.8036236580371905,0.8158311488835054,0.8018808040746214,0.7601564715277158,0.7569037168231157
77
+ 3,16000,0.7954766826976625,0.801395311230615,0.8156300760676541,0.8026976467456534,0.8148836187827058,0.80048429140457,0.7595892411835121,0.7561249294106399
78
+ 3,17000,0.7947527697149959,0.8021779426086015,0.8151961053613337,0.8038988859677596,0.8139813689886876,0.8001810025257725,0.7571399278623248,0.753129327088121
79
+ 3,18000,0.7987425878311516,0.8056828703612935,0.8191644528114327,0.8073611457032821,0.8187303318402535,0.8058939040678331,0.7612294334237008,0.7566746164786757
80
+ 3,19000,0.7975697253913575,0.8041964088982907,0.8182580501693996,0.8059069735505696,0.8178060364633866,0.8045658139838728,0.7608254362845596,0.7573999727705522
81
+ 3,-1,0.7959764235510056,0.8028952265729055,0.8169792616699579,0.8048963950177963,0.8161173664588516,0.8028179628661396,0.7590453857909853,0.7547645500163894
82
+ 4,1000,0.7956425959755347,0.801296136920438,0.8167124416048023,0.8030952669762371,0.8159931765240885,0.8025773306251675,0.7585649267984061,0.7538512238110379
83
+ 4,2000,0.7989237174451557,0.8051112726898466,0.8187514695401161,0.8064424379462155,0.8177734075739885,0.8040476474330251,0.7650100058136148,0.7604693792308774
84
+ 4,3000,0.7998834638184185,0.8062417829465549,0.8194907488673198,0.8070751546692833,0.8185819356231895,0.8043607006653397,0.7639628253108766,0.761055583971265
85
+ 4,4000,0.7984836005233165,0.8032507933826489,0.8171746693160173,0.8046050224320822,0.8165561412577794,0.8023747536427513,0.7643150405139535,0.7602175994899238
86
+ 4,5000,0.7995354490928371,0.8034041676065273,0.8199726612835596,0.8076252261338699,0.8192375505964392,0.8058200999300269,0.7633148121654315,0.7583786463895864
87
+ 4,6000,0.7960459644235468,0.8022448276084885,0.8173264223821854,0.8049602048452745,0.8167789546751139,0.8040764771743557,0.7610138078794764,0.7561660598416049
88
+ 4,7000,0.800098632679958,0.8041368274328743,0.8198099509317249,0.8078812342368852,0.8196582072933943,0.8055233457925979,0.7639444101449687,0.7596736783701544
89
+ 4,8000,0.7981021158168051,0.8028391046764486,0.8180514723802143,0.8054433913099744,0.8176590130781365,0.8028775443315561,0.7620544492646885,0.7574976094945249
90
+ 4,9000,0.7989537883307358,0.8051600910518331,0.8189218085897586,0.8070090384624985,0.8184013500956752,0.805534108896028,0.7643918191348974,0.7604351679378317
91
+ 4,10000,0.7999973351405895,0.8059123551022848,0.8193760771590554,0.8079819461332666,0.8189278788233341,0.8061256951881307,0.7656582746518006,0.7612716148329687
92
+ 4,11000,0.799889946163539,0.8047380236387538,0.8178365617681728,0.806024214498647,0.8177741620392476,0.8046230890699828,0.7653121040981288,0.7601068932832147
93
+ 4,12000,0.8001172306509283,0.805502972775391,0.8195871207638407,0.8080027035470246,0.8192164877309068,0.806574285963234,0.7661370609472041,0.7623267833656666
94
+ 4,13000,0.7996292372556252,0.8039711525193612,0.8192082522106113,0.8064893343254467,0.8190506060356165,0.806887184755808,0.7644005571824162,0.7595464431117489
95
+ 4,14000,0.7992873868512631,0.8044812467426364,0.8190753557719389,0.8054495416547917,0.8189279760431806,0.8053261503618969,0.7648320242715321,0.7594007568188919
96
+ 4,15000,0.7993981939436787,0.8051577846725265,0.8192634541801723,0.8074337966514351,0.8188848169301974,0.804915230448799,0.7637513895063649,0.7599289176800674
97
+ 4,16000,0.7997737409162505,0.8057355326887905,0.8193679739963344,0.8081729912191503,0.8190871019614439,0.8062921388947457,0.7651670741501253,0.7611978106951625
98
+ 4,17000,0.7996526902910406,0.805508354327106,0.8196589619274325,0.8075691042374132,0.8192860472238176,0.806372093377369,0.7650842321697999,0.7613638700052263
99
+ 4,18000,0.7997494125416625,0.8046576847595793,0.8194349112489244,0.8073626832894865,0.8190191240097638,0.8060999406192086,0.7650255761381362,0.7610817229367381
100
+ 4,19000,0.7996270096063823,0.8042429208809706,0.8194125359494282,0.8068806500144399,0.8190501816952906,0.8052312044137817,0.765165121837548,0.7613861650051886
101
+ 4,-1,0.7996674572034206,0.8042356173465003,0.8194270405521464,0.8068214529455745,0.8190648652706823,0.8053276879481012,0.7652135800545512,0.7615645250048869
eval/translation_evaluation_TED2020-en-pt-dev.tsv.gz_results.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,src2trg,trg2src
2
+ 0,1000,0.051,0.066
3
+ 0,2000,0.058,0.063
4
+ 0,3000,0.082,0.12
5
+ 0,4000,0.193,0.214
6
+ 0,5000,0.384,0.439
7
+ 0,6000,0.59,0.589
8
+ 0,7000,0.69,0.699
9
+ 0,8000,0.762,0.776
10
+ 0,9000,0.804,0.811
11
+ 0,10000,0.849,0.851
12
+ 0,11000,0.872,0.867
13
+ 0,12000,0.89,0.896
14
+ 0,13000,0.902,0.896
15
+ 0,14000,0.915,0.905
16
+ 0,15000,0.91,0.908
17
+ 0,16000,0.923,0.92
18
+ 0,17000,0.917,0.923
19
+ 0,18000,0.925,0.924
20
+ 0,19000,0.93,0.932
21
+ 0,-1,0.932,0.931
22
+ 1,1000,0.938,0.93
23
+ 1,2000,0.942,0.936
24
+ 1,3000,0.943,0.933
25
+ 1,4000,0.942,0.941
26
+ 1,5000,0.944,0.943
27
+ 1,6000,0.947,0.941
28
+ 1,7000,0.944,0.946
29
+ 1,8000,0.946,0.947
30
+ 1,9000,0.95,0.946
31
+ 1,10000,0.95,0.951
32
+ 1,11000,0.951,0.95
33
+ 1,12000,0.954,0.952
34
+ 1,13000,0.956,0.952
35
+ 1,14000,0.957,0.951
36
+ 1,15000,0.953,0.952
37
+ 1,16000,0.952,0.952
38
+ 1,17000,0.957,0.954
39
+ 1,18000,0.955,0.951
40
+ 1,19000,0.956,0.953
41
+ 1,-1,0.956,0.953
42
+ 2,1000,0.956,0.954
43
+ 2,2000,0.959,0.954
44
+ 2,3000,0.956,0.954
45
+ 2,4000,0.958,0.956
46
+ 2,5000,0.955,0.959
47
+ 2,6000,0.959,0.956
48
+ 2,7000,0.96,0.956
49
+ 2,8000,0.962,0.956
50
+ 2,9000,0.958,0.956
51
+ 2,10000,0.962,0.955
52
+ 2,11000,0.962,0.954
53
+ 2,12000,0.961,0.952
54
+ 2,13000,0.96,0.955
55
+ 2,14000,0.959,0.954
56
+ 2,15000,0.961,0.955
57
+ 2,16000,0.96,0.956
58
+ 2,17000,0.961,0.957
59
+ 2,18000,0.96,0.958
60
+ 2,19000,0.961,0.956
61
+ 2,-1,0.962,0.959
62
+ 3,1000,0.963,0.958
63
+ 3,2000,0.96,0.956
64
+ 3,3000,0.961,0.959
65
+ 3,4000,0.961,0.956
66
+ 3,5000,0.962,0.959
67
+ 3,6000,0.963,0.96
68
+ 3,7000,0.964,0.962
69
+ 3,8000,0.961,0.958
70
+ 3,9000,0.959,0.959
71
+ 3,10000,0.959,0.959
72
+ 3,11000,0.963,0.96
73
+ 3,12000,0.962,0.957
74
+ 3,13000,0.962,0.958
75
+ 3,14000,0.962,0.957
76
+ 3,15000,0.963,0.958
77
+ 3,16000,0.959,0.96
78
+ 3,17000,0.96,0.962
79
+ 3,18000,0.961,0.959
80
+ 3,19000,0.962,0.959
81
+ 3,-1,0.96,0.96
82
+ 4,1000,0.964,0.959
83
+ 4,2000,0.963,0.957
84
+ 4,3000,0.965,0.96
85
+ 4,4000,0.96,0.958
86
+ 4,5000,0.961,0.96
87
+ 4,6000,0.959,0.959
88
+ 4,7000,0.964,0.96
89
+ 4,8000,0.964,0.961
90
+ 4,9000,0.962,0.96
91
+ 4,10000,0.961,0.962
92
+ 4,11000,0.962,0.962
93
+ 4,12000,0.963,0.961
94
+ 4,13000,0.964,0.962
95
+ 4,14000,0.961,0.961
96
+ 4,15000,0.962,0.96
97
+ 4,16000,0.964,0.961
98
+ 4,17000,0.964,0.961
99
+ 4,18000,0.963,0.961
100
+ 4,19000,0.964,0.961
101
+ 4,-1,0.964,0.961
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc7525e21543ce0bf541ca496bfed3cfefac92d7f01586aead5ea5de0150852
3
+ size 1337719025
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "/home/ruimelo/.cache/torch/sentence_transformers/rufimelo_Legal-BERTimbau-large",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "/home/ruimelo/.cache/huggingface/transformers/d5b721c156180bbbcc4a1017e8c72a18f8f96cdc178acec5ddcd45905712b4cf.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff