Hugging Face's logo

certainstar
/
Trained-Chinese-classification

Text Classification
Transformers
Safetensors
Chinese
bert
Model card Files
xet
Community
certainstar commited on
Commit
bb15f46
·
verified ·
1 Parent(s): 2e6b16b

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +32 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer_config.json +57 -0
  8. trainer_state.json +133 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../bert/bert-base-chinese",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
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
+ "problem_type": "single_label_classification",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.40.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 21128
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bffec9ef3080e8d0bddee5c22a30296b406a706fd621043bf41a17aca3d26995
3
+ size 409100240
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8aeca89fccb7eb1a76cd735bcb387a4ae2e513f996c338ae60434d4580dc6c2
3
+ size 818313466
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67a78e67d0df4c8046de21110faacf95755fca36de076a0c8c610a079370afc
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b817162e973d9340d0128c9a9798824c40c72955b9e1e793b96bb5cd8acc76e7
3
+ size 1064
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_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3858,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.38880248833592534,
13
+ "grad_norm": 0.6042742133140564,
14
+ "learning_rate": 1.740798341109383e-05,
15
+ "loss": 0.2151,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.38880248833592534,
20
+ "eval_accuracy": 0.9762738234150136,
21
+ "eval_loss": 0.10295161604881287,
22
+ "eval_runtime": 26.8587,
23
+ "eval_samples_per_second": 95.723,
24
+ "eval_steps_per_second": 11.989,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 0.7776049766718507,
29
+ "grad_norm": 0.04766521230340004,
30
+ "learning_rate": 1.4815966822187664e-05,
31
+ "loss": 0.1167,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.7776049766718507,
36
+ "eval_accuracy": 0.9875534811357448,
37
+ "eval_loss": 0.05390123650431633,
38
+ "eval_runtime": 26.735,
39
+ "eval_samples_per_second": 96.166,
40
+ "eval_steps_per_second": 12.044,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 1.166407465007776,
45
+ "grad_norm": 0.008871573023498058,
46
+ "learning_rate": 1.2223950233281495e-05,
47
+ "loss": 0.0687,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 1.166407465007776,
52
+ "eval_accuracy": 0.9793854531310774,
53
+ "eval_loss": 0.12513048946857452,
54
+ "eval_runtime": 27.1074,
55
+ "eval_samples_per_second": 94.845,
56
+ "eval_steps_per_second": 11.879,
57
+ "step": 1500
58
+ },
59
+ {
60
+ "epoch": 1.5552099533437014,
61
+ "grad_norm": 0.0014064661227166653,
62
+ "learning_rate": 9.631933644375326e-06,
63
+ "loss": 0.0279,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 1.5552099533437014,
68
+ "eval_accuracy": 0.9778296382730455,
69
+ "eval_loss": 0.148821160197258,
70
+ "eval_runtime": 26.879,
71
+ "eval_samples_per_second": 95.651,
72
+ "eval_steps_per_second": 11.98,
73
+ "step": 2000
74
+ },
75
+ {
76
+ "epoch": 1.9440124416796267,
77
+ "grad_norm": 0.002627410925924778,
78
+ "learning_rate": 7.039917055469155e-06,
79
+ "loss": 0.0293,
80
+ "step": 2500
81
+ },
82
+ {
83
+ "epoch": 1.9440124416796267,
84
+ "eval_accuracy": 0.9914430182808246,
85
+ "eval_loss": 0.04895803704857826,
86
+ "eval_runtime": 26.8775,
87
+ "eval_samples_per_second": 95.656,
88
+ "eval_steps_per_second": 11.98,
89
+ "step": 2500
90
+ },
91
+ {
92
+ "epoch": 2.332814930015552,
93
+ "grad_norm": 0.0008352847071364522,
94
+ "learning_rate": 4.447900466562986e-06,
95
+ "loss": 0.0119,
96
+ "step": 3000
97
+ },
98
+ {
99
+ "epoch": 2.332814930015552,
100
+ "eval_accuracy": 0.9766627771295215,
101
+ "eval_loss": 0.15932457149028778,
102
+ "eval_runtime": 27.4463,
103
+ "eval_samples_per_second": 93.674,
104
+ "eval_steps_per_second": 11.732,
105
+ "step": 3000
106
+ },
107
+ {
108
+ "epoch": 2.721617418351477,
109
+ "grad_norm": 0.006800688803195953,
110
+ "learning_rate": 1.8558838776568172e-06,
111
+ "loss": 0.0045,
112
+ "step": 3500
113
+ },
114
+ {
115
+ "epoch": 2.721617418351477,
116
+ "eval_accuracy": 0.9797744068455854,
117
+ "eval_loss": 0.14682677388191223,
118
+ "eval_runtime": 27.6918,
119
+ "eval_samples_per_second": 92.843,
120
+ "eval_steps_per_second": 11.628,
121
+ "step": 3500
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 3858,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 3,
128
+ "save_steps": 500,
129
+ "total_flos": 5863351757603040.0,
130
+ "train_batch_size": 8,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3717b04d45a79d28ef26b65f930331ef5726e873ced31526c15d7d560fc5c42
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff