shibing624
commited on
Commit
•
7d5f95e
1
Parent(s):
7cbccd7
Upload 7 files
Browse files- config.json +40 -0
- eval_results.txt +2 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_progress_scores.csv +6 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "shibing624/text2vec-bge-large-chinese",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 16,
|
26 |
+
"num_hidden_layers": 24,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pooler_fc_size": 768,
|
30 |
+
"pooler_num_attention_heads": 12,
|
31 |
+
"pooler_num_fc_layers": 3,
|
32 |
+
"pooler_size_per_head": 128,
|
33 |
+
"pooler_type": "first_token_transform",
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.31.0",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 21128
|
40 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
eval_pearson = 0.5551856961372815
|
2 |
+
eval_spearman = 0.5470897314949114
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_progress_scores.csv
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
global_step,train_loss,eval_spearman,eval_pearson
|
2 |
+
6217,1.187222957611084,0.5114652838626846,0.4941802088748416
|
3 |
+
12434,0.5630741119384766,0.529277507678798,0.5185274121904764
|
4 |
+
18651,0.4950772523880005,0.4936530600465713,0.4916064648614785
|
5 |
+
24868,0.06126270815730095,0.5470897314949114,0.5551856961372815
|
6 |
+
31085,0.09893279522657394,0.5114652838626846,0.5117443179915746
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|