Ubuntu
commited on
Commit
•
3453e2b
1
Parent(s):
bafc847
added model
Browse files- 0_Transformer/config.json +30 -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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output-no-git/mBERT/bert-base-multilingual-cased-original/0_Transformer",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"transformers_version": "4.6.0.dev0",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 119547
|
30 |
+
}
|
0_Transformer/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a337127ff4f494df027dadc4214130ba366a547d93ef9d67264e25eaa7cfeb
|
3 |
+
size 711500343
|
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, "max_length": 510, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/ubuntu/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24", "name_or_path": "output-no-git/mBERT/bert-base-multilingual-cased-original/0_Transformer"}
|
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 |
+
0,1000,0.7606960480822791,0.7527262963114983,0.7533229800645973,0.7538859415041085,0.751848721060783,0.752776844320859,0.45344440772246764,0.4413684819860246
|
3 |
+
0,-1,0.8476425459650283,0.812270980165622,0.8221967175541937,0.807827759542219,0.8215100976240384,0.8073680141748321,0.642911767157194,0.558356544165204
|
4 |
+
1,1000,0.876830529540382,0.837191683486827,0.851656089280112,0.830579123948632,0.8507285671689212,0.8305971030379506,0.7182435380601571,0.6444620877467745
|
5 |
+
1,-1,0.905629936091339,0.8758520932528994,0.8825429556926093,0.874075080796819,0.8808337895080377,0.8725120808589879,0.740660740330966,0.6542357599099502
|
6 |
+
2,1000,0.9239698619544061,0.8974956284049873,0.895680454782259,0.8908695963570652,0.8945885073751177,0.8895238032667916,0.8073052081494065,0.7590658241561002
|
7 |
+
2,-1,0.9394337960061873,0.9058439091717433,0.9101851188380967,0.9006750047046694,0.9096959395785905,0.8999331509621397,0.7825370630588722,0.7165539025795263
|
8 |
+
3,1000,0.9502836915410755,0.9176517753726461,0.9242902694647394,0.9126817847969604,0.9235430414802268,0.9121173530438861,0.8005551242314324,0.7330227151864028
|
9 |
+
3,-1,0.9523887149029426,0.9188026815037671,0.9242290515033774,0.9131621245538982,0.9233831320446814,0.9121472150457058,0.8184599719084373,0.7552718878925767
|
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,-1,0.7947514506615774,0.7756833152568035,0.7748096289735229,0.7638625356667715,0.774792060372983,0.7639692899295706,0.6644632351950672,0.6142583091052344
|