eduardofv commited on
Commit
632aa4d
1 Parent(s): 2c062fc

Carga inicial

Browse files
0_Transformer/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "transformers_version": "4.6.1",
22
+ "vocab_size": 30522
23
+ }
0_Transformer/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4247d2f9cba7380e84be9a69bb9bff9608d505966ec86f078a1ff4d0285ebaaf
3
+ size 265490176
0_Transformer/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "max_seq_length": null,
3
+ "do_lower_case": false
4
+ }
0_Transformer/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
0_Transformer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
0_Transformer/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased"}
0_Transformer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
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
+ }
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ {
2
+ "__version__": "1.2.0"
3
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "0_Transformer",
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
+ ]
similarity_evaluation_sts-dev_results.csv ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,-1,0.7674348102247248,0.7667286405457256,0.7502040339902296,0.7576824147761646,0.7492861452801035,0.7561106972845474,0.7285506159415656,0.7343265392689423
3
+ 1,-1,0.7782789678703184,0.7761241007579364,0.763784529139891,0.7691237269220588,0.7626542374963032,0.7680705009011701,0.7410908722043604,0.7446238826558748
4
+ 2,-1,0.7766684878569015,0.7754911419362798,0.7610854551118094,0.764845075190592,0.7603155185939217,0.7640645508417966,0.7416572024271656,0.7459471184421463
5
+ 3,-1,0.7784200404666838,0.7767716670405521,0.7601348642559405,0.7632601234978199,0.7594430674974024,0.7626042533614712,0.7442829550102651,0.7497069964750338
similarity_evaluation_stsb-multi-mt-test_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ -1,-1,0.7450619922414319,0.7363506275013219,0.7336101237784383,0.7320799242026941,0.7332076483340091,0.7317512428692636,0.7022330212363639,0.6964875585742952