Ubuntu
commited on
Commit
•
791be75
1
Parent(s):
c08ea49
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/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 sha256:02847b693aec1baa139a9f6537930977d373d54a73d190ba9d3b8ab02bd3c04b
|
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, "truncation": true, "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/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 |
+
0,1000,0.808610000124635,0.7904169909268025,0.7890748657727445,0.7827219316759051,0.7898510099762094,0.7827764646010639,0.6406215624322416,0.5431673510705365
|
3 |
+
0,-1,0.8512032205933435,0.8211559202805497,0.8317654749230341,0.8213705699386389,0.8328187903862371,0.8214601202317404,0.6088322745794972,0.5204132029628957
|
4 |
+
1,1000,0.8791474792799332,0.8529615651735871,0.8423194149490582,0.8450567413047867,0.8416755361780882,0.843708137597615,0.746333815137871,0.6537737514186941
|
5 |
+
1,-1,0.9158377840565254,0.893616257615058,0.8843129030811623,0.8849861076310558,0.8837617668234907,0.8846747637255984,0.7962866266082649,0.7093805785844141
|
6 |
+
2,1000,0.9292193070536092,0.8976436865188125,0.8982986010714099,0.8904431725204103,0.8978941195905453,0.890331324007088,0.7991976578489706,0.7036143694272589
|
7 |
+
2,-1,0.9412279500546888,0.910824838477643,0.9068153928743897,0.90418140776196,0.9062915707984183,0.9037573080910265,0.8276745544442946,0.7394839211096906
|
8 |
+
3,1000,0.9523328170288394,0.9218630610551374,0.9155644608321573,0.9147043321310978,0.9151663096790067,0.9142782745050488,0.8249897649533443,0.7279404449679865
|
9 |
+
3,-1,0.9539001602998229,0.9250445503551714,0.9167811577938763,0.9173821411237776,0.9163428239787551,0.9166624185921395,0.8299690144676938,0.7329663215190114
|
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,-1,0.8082766442121261,0.7856061517977896,0.7817580409331031,0.7724776788122987,0.781205276050626,0.7718881871833072,0.7002401487316227,0.6078591746482085
|