twang2218 commited on
Commit
d45b15a
·
verified ·
1 Parent(s): 5564e9c

Signed-off-by: Tao Wang <[email protected]>

1_Pooling/config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_mean_tokens": true
4
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "shibing624/text2vec-base-chinese",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.29.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 21128
32
+ }
eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ eval_pearson = 0.9521139554586924
2
+ eval_spearman = 0.8516852932062846
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a611477f2c8b4eed1b807299eca643ad9db52bd0c0b1ade32881502303bc9518
3
+ size 409141805
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
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": 1000000000000000019884624838656,
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ global_step,train_loss,eval_spearman,eval_pearson
2
+ 2144,0.0,0.8479460350153861,0.948485133470978
3
+ 4288,0.0,0.8498950964077886,0.9465204947615107
4
+ 6432,0.0,0.849468294643029,0.9468169311979125
5
+ 8576,0.0,0.848567268695203,0.9472771180148725
6
+ 10720,0.0,0.8516852932062846,0.9521139554586924
7
+ 12864,0.0,0.8481712915023426,0.9352248634550469
8
+ 15008,0.0,0.8498927252868733,0.9520898128741913
9
+ 17152,0.0,0.8507155042444935,0.9543544491683162
10
+ 19296,0.0,0.8487877829403289,0.947800578361301
11
+ 21440,0.0,0.850419114130077,0.9521228966704754
12
+ 23584,0.0,0.849432727829299,0.947384125053125
13
+ 25728,0.0,0.8491339665939672,0.9484934936142233
14
+ 27872,0.0,0.851184986185729,0.9468601578695205
15
+ 30016,0.0,0.8471896474433954,0.9482947463945062
16
+ 32160,0.0,0.8505518969013355,0.9505983453497635
17
+ 34304,0.0,0.8507107620026627,0.9545982143319675
18
+ 36448,0.0,0.8508577720063408,0.9546999080180405
19
+ 38592,0.0,0.8500824149600997,0.951359698794045
20
+ 40736,0.0,0.8496390158551345,0.9508174759023411
vocab.txt ADDED
The diff for this file is too large to render. See raw diff