Harish Tayyar Madabushi
commited on
Commit
•
8060fb9
1
Parent(s):
dba7c01
Added model
Browse files- 0_Transformer/config.json +24 -0
- 0_Transformer/pytorch_model.bin +3 -0
- 0_Transformer/sentence_bert_config.json +4 -0
- 0_Transformer/special_tokens_map.json +1 -0
- 0_Transformer/tokenizer_config.json +1 -0
- 0_Transformer/vocab.txt +0 -0
- 1_Pooling/config.json +7 -0
- config.json +3 -0
- modules.json +14 -0
- similarity_evaluation_sts-dev_results.csv +9 -0
- similarity_evaluation_sts-test_results.csv +2 -0
0_Transformer/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output-no-git/NEW/BERT/TransformerModels/pt-e5-select/0_Transformer",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.6.0.dev0",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 28996
|
24 |
+
}
|
0_Transformer/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9aeee813b00dccb234bad8c0dae1d10e187d335907b03e891d9771de962ee96
|
3 |
+
size 433327607
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "truncation": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/rds/homes/t/tayyarmh/.cache/huggingface/transformers/226a307193a9f4344264cdc76a12988448a25345ba172f2c7421f3b6810fddad.3dab63143af66769bbb35e3811f75f7e16b2320e12b7935e216bd6159ce6d9a6", "name_or_path": "output-no-git/NEW/BERT/TransformerModels/pt-e5-select/0_Transformer", "max_length": 510}
|
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__": "1.1.0"
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
|
2 |
+
0,1000,0.841338433501473,0.8442765704671797,0.7979352460297595,0.8080708594311425,0.7972471807820661,0.8079435700259968,0.7201830842932453,0.7367536803845508
|
3 |
+
0,-1,0.8439733762043259,0.8456181051984315,0.8032082466966844,0.8121280490601864,0.8026775785293708,0.8117951634313535,0.744185003484758,0.7636690861567739
|
4 |
+
1,1000,0.8494493743997568,0.8519148131368952,0.8158977701844998,0.8223465080602662,0.815076499729319,0.8217836909463818,0.7683369625916134,0.7814347225504635
|
5 |
+
1,-1,0.8535626438197125,0.8546797769163053,0.818641196627495,0.8247880809174286,0.8176190771518785,0.8237493606080887,0.7686359973444298,0.778342165651755
|
6 |
+
2,1000,0.8588287089818568,0.8603250032220291,0.8241081808926235,0.8297488576203019,0.8236483926242709,0.829195303553255,0.7718417659850942,0.7828361118055842
|
7 |
+
2,-1,0.8581720775316972,0.8602791765530422,0.8201601203753465,0.826257357730798,0.819627596309942,0.8255151081089033,0.7792675692880614,0.7898714814169437
|
8 |
+
3,1000,0.860797939829317,0.8631979828352097,0.8250126464928228,0.8308747783241359,0.8246311614630802,0.8303460206911423,0.7805892938133608,0.7896109427935752
|
9 |
+
3,-1,0.8614342944799335,0.8637776504945157,0.8257840913283957,0.8312569270129091,0.8253334816909105,0.830856772973664,0.7816233659953968,0.7899002821485122
|
similarity_evaluation_sts-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,-1,0.82576274577719,0.8245460198182728,0.8023232670775502,0.7965767205321669,0.8017378179760507,0.7961737630655558,0.7353935640927387,0.7335397223109451
|