mmazuecos commited on
Commit
9066f0f
1 Parent(s): 7b773e9

Pushing model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
2_Dense/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
2_Dense/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8b726320c19db73fe1b10f1e8fd9476783234dc72483d7aa971bc328069ff4
3
+ size 1575975
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ ---
8
+
9
+ # {MODEL_NAME}
10
+
11
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
12
+
13
+ <!--- Describe your model here -->
14
+
15
+ ## Usage (Sentence-Transformers)
16
+
17
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
18
+
19
+ ```
20
+ pip install -U sentence-transformers
21
+ ```
22
+
23
+ Then you can use the model like this:
24
+
25
+ ```python
26
+ from sentence_transformers import SentenceTransformer
27
+ sentences = ["This is an example sentence", "Each sentence is converted"]
28
+
29
+ model = SentenceTransformer('{MODEL_NAME}')
30
+ embeddings = model.encode(sentences)
31
+ print(embeddings)
32
+ ```
33
+
34
+
35
+
36
+ ## Evaluation Results
37
+
38
+ <!--- Describe how your model was evaluated -->
39
+
40
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
41
+
42
+
43
+ ## Training
44
+ The model was trained with the parameters:
45
+
46
+ **DataLoader**:
47
+
48
+ `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1127 with parameters:
49
+ ```
50
+ {'batch_size': 64}
51
+ ```
52
+
53
+ **Loss**:
54
+
55
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
56
+ ```
57
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
58
+ ```
59
+
60
+ Parameters of the fit()-Method:
61
+ ```
62
+ {
63
+ "epochs": 20,
64
+ "evaluation_steps": 0,
65
+ "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
66
+ "max_grad_norm": 1,
67
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
68
+ "optimizer_params": {
69
+ "lr": 2e-05
70
+ },
71
+ "scheduler": "WarmupLinear",
72
+ "steps_per_epoch": null,
73
+ "warmup_steps": 1127,
74
+ "weight_decay": 0.01
75
+ }
76
+ ```
77
+
78
+
79
+ ## Full Model Architecture
80
+ ```
81
+ SentenceTransformer(
82
+ (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: RobertaModel
83
+ (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})
84
+ (2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
85
+ )
86
+ ```
87
+
88
+ ## Citing & Authors
89
+
90
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.17.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.0",
4
+ "transformers": "4.17.0",
5
+ "pytorch": "1.10.2"
6
+ }
7
+ }
eval/similarity_evaluation_sts-test_results.csv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,-1,0.6581493026240269,0.5802356493272345,0.6634103225436967,0.5887142267642859,0.6633780369919056,0.5889272703378547,0.571143299245293,0.4732063731208094
3
+ 1,-1,0.6708623071971952,0.5985927642452136,0.675257124555732,0.6046557636211276,0.6767056382416057,0.6064614282847686,0.5864286716770518,0.495613872629927
4
+ 2,-1,0.6702651671065515,0.5922353474286076,0.6672984469521261,0.594962259717964,0.6673488770673561,0.5945960133985778,0.6020281121442566,0.5095236479097289
5
+ 3,-1,0.6605032101558846,0.5890776181094547,0.6641603284425521,0.5993232115293229,0.6645610706259933,0.5984927833321959,0.5913711078698719,0.5082729703485656
6
+ 4,-1,0.6530779759890578,0.5781118041787935,0.6547349577996249,0.5874599982401654,0.6543895215674207,0.5869029941907284,0.581310838565905,0.497299912453472
7
+ 5,-1,0.6543208566097818,0.58194344945178,0.6491366001755403,0.5864144953186581,0.6498888685831916,0.5868199442690898,0.5910026676646215,0.5151166986440603
8
+ 6,-1,0.6472013765440673,0.5732578792820385,0.6433653543280587,0.5798672298185186,0.6435570196620376,0.5787832344585572,0.5864683897395871,0.5061222515124659
9
+ 7,-1,0.6400980616286338,0.5667287521006833,0.63656772778559,0.5743034106112495,0.6370456545413393,0.5730667948633957,0.5747946450752401,0.4979748652884891
10
+ 8,-1,0.6452381886531463,0.5729618568060901,0.6424560387096414,0.5811990823928792,0.6429919873656215,0.5808723511892786,0.58104040571895,0.5054740303265891
11
+ 9,-1,0.6384071016780053,0.5625492118848722,0.635541246663347,0.572271947315098,0.6356269918508849,0.5711684216588732,0.5787246865749316,0.5019918424201281
12
+ 10,-1,0.6419031233362158,0.569618113843397,0.6353794935936075,0.5752729939447357,0.6357950326588047,0.5748007016676012,0.5828757686864627,0.5121824811372735
13
+ 11,-1,0.6423540880042571,0.568767118468823,0.6349101892245405,0.5744865976882757,0.6356595326561394,0.5750529478722156,0.5862014516783208,0.5123514217509163
14
+ 12,-1,0.6402987765788005,0.563953589326667,0.6355130494886717,0.5722567776013456,0.6357087618283007,0.572723715026341,0.581950349472401,0.5068270750478774
15
+ 13,-1,0.6349740259317077,0.5605840947806097,0.6310765115255937,0.5677235330673125,0.6313588325370229,0.5675908264796831,0.5761493116509655,0.5012367514530972
16
+ 14,-1,0.6358190709395628,0.5624146872042087,0.6327586555267605,0.5708724133867766,0.6331569512601531,0.5702529265931481,0.5781642308453095,0.504501876095922
17
+ 15,-1,0.6311127603260229,0.5584118997205461,0.6288133015450812,0.5664748582492568,0.628861427115307,0.5660526913652236,0.5729793164702304,0.5013857356549215
18
+ 16,-1,0.6333152268675507,0.5610230364136519,0.6305527453515162,0.5691509491567724,0.6304938356795253,0.567996417468633,0.5755055543932878,0.5033426713405311
19
+ 17,-1,0.6353869036678222,0.5630840974232757,0.6323343041403464,0.5707859119291437,0.6322656960665566,0.5696195382630574,0.5764210881100128,0.5045764889295747
20
+ 18,-1,0.6352029170986021,0.5627512048617189,0.6315279989234651,0.5694638031971371,0.6315471951413272,0.5690261399107593,0.5761747454613159,0.5035466102450782
21
+ 19,-1,0.6355421845320552,0.5627031532309846,0.631491538163409,0.569449769791531,0.631682972028249,0.5686912699000612,0.5771564421958566,0.5049254207535826
loss_digest.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Dense",
18
+ "type": "sentence_transformers.models.Dense"
19
+ }
20
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94bf68a63b5b838390ca25847d46db5693bd6ba6aa72f218f6fda267787eed75
3
+ size 498664817
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 514,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-roberta-base-spanish", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff