Harish Tayyar Madabushi
commited on
Commit
•
83cf889
1
Parent(s):
62304c4
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/bert-base-cased-tokenised/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 sha256:1ee60b248a71d83d4cf31b1a846a097cc76c71e36a99a53260d2275383f84266
|
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/bert-base-cased-tokenised/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 |
+
0,1000,0.8335144822310411,0.835180328293515,0.8032677060240342,0.8093158805815838,0.8029312809040198,0.8092959716557867,0.7614861857232819,0.7738051162654095
|
3 |
+
0,-1,0.850140063657488,0.8531779146725595,0.816466319852687,0.8213777582822627,0.8157881598723679,0.820856454382156,0.790490947431872,0.7950029653761593
|
4 |
+
1,1000,0.8531095646162251,0.8541523431488004,0.8299450801975106,0.8319622371075649,0.8299030285401695,0.8318409701200706,0.8103714686857855,0.8121012867540373
|
5 |
+
1,-1,0.8506581058224175,0.8538724052334412,0.8261256209618806,0.8316570838723357,0.8257377032755663,0.8310337862897207,0.7876499984223349,0.7913521123293493
|
6 |
+
2,1000,0.8626660670190143,0.8643934488403119,0.8343747661985403,0.8385836829523486,0.834153333905632,0.8383077948618445,0.8134887113730604,0.8176311265335471
|
7 |
+
2,-1,0.863600251972787,0.865715161736523,0.8384737546970248,0.8427478637583358,0.8382592923077236,0.8423398456835265,0.8196239326910786,0.8226354666029246
|
8 |
+
3,1000,0.8637415431681831,0.8659113558217477,0.8352789465654492,0.8399184027334765,0.835103264545804,0.8394728429613278,0.818978196713896,0.8228119346959237
|
9 |
+
3,-1,0.8642539374647745,0.8662342047984236,0.8363111193865003,0.8409964835476875,0.8360746942711231,0.8403775087791109,0.818295913510811,0.8218163717330649
|
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,-1,0.843292477235119,0.842250842613354,0.827930845874399,0.8275300842558161,0.8275406655454793,0.8271789001957125,0.7810013142413237,0.7764617994006479
|