Ubuntu
commited on
Commit
•
4521c69
1
Parent(s):
bf1e4be
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/pt-e5-all/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:b3939578e3df40e2f0c4e1a6ecb22962c7cf7b2e70265cb1b94d5932ec529b4b
|
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/pt-e5-all/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 |
+
0,1000,0.8310434175950746,0.8084352804092589,0.8164561513133928,0.805353961581712,0.8158425599257554,0.8054873625754602,0.7216794286755167,0.6404686488156007
|
3 |
+
0,-1,0.8683390942435285,0.8459892279111034,0.8485398348729415,0.8413321576789707,0.8480279504117403,0.8410338124674865,0.6632068263519741,0.5573149106980765
|
4 |
+
1,1000,0.8959618658889451,0.871257392555793,0.859527562888271,0.8648164810781868,0.8579009704489259,0.8641430212170358,0.7636375653694925,0.6788671936868453
|
5 |
+
1,-1,0.9199621369555948,0.898663634480422,0.8897617436790175,0.8923169611196459,0.8891804239262432,0.8917963366883072,0.7770863241973909,0.6825237281008382
|
6 |
+
2,1000,0.9325759360438963,0.9127091033199908,0.9021153444181113,0.9059407843043414,0.901856762172847,0.9051953158659304,0.7981131199622317,0.705905102791291
|
7 |
+
2,-1,0.9435178149235999,0.9220240815907487,0.9099587025741255,0.9145791379027683,0.9092165202028255,0.9138673952278411,0.8202117138077736,0.7351810409357941
|
8 |
+
3,1000,0.9513516166903263,0.9279106768524762,0.92002963745839,0.9227598156361299,0.9195583380558486,0.9222505622491294,0.8179699356783608,0.7280930618136591
|
9 |
+
3,-1,0.9528704139197507,0.9301966875593483,0.9197361016453713,0.9235889651718986,0.9192645702544217,0.9234046295551208,0.8240511891781511,0.7344756083831954
|
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,-1,0.8063132872105296,0.7831758196309248,0.7809573510441334,0.7709440782562949,0.7796703258107609,0.7701085380085085,0.6811931544669564,0.5887852040317765
|