conan1024hao commited on
Commit
02c8738
1 Parent(s): bd3e92e

model first version

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/groups/gcc50435/ou/cjkbert/cjkbert-base/epoch-15/",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
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": 2,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.19.2",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 15015
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a786f22e81efbea199a6eb27871240bd6b954d769c7a47bbda370acb461598d1
3
+ size 390429291
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"tokenizer_class": "PreTrainedTokenizerFast"}
train_results.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ epoch = 20.0
2
+ train_loss = 0.4021474394976566
3
+ train_runtime = 51134.1112
4
+ train_samples_per_second = 11365.472
5
+ train_steps_per_second = 44.396
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.999995595043544,
5
+ "global_step": 2270160,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.666798815942489e-05,
13
+ "loss": 2.7208,
14
+ "step": 113508
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 4.3335917585838296e-05,
19
+ "loss": 2.1526,
20
+ "step": 227016
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 4.000384701225171e-05,
25
+ "loss": 2.0051,
26
+ "step": 340524
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 3.667171770565364e-05,
31
+ "loss": 1.9189,
32
+ "step": 454032
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 3.3339647132067057e-05,
37
+ "loss": 1.8591,
38
+ "step": 567540
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 3.000757655848046e-05,
43
+ "loss": 1.8134,
44
+ "step": 681048
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 2.6675505984893874e-05,
49
+ "loss": 1.7768,
50
+ "step": 794556
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 2.3343376678295804e-05,
55
+ "loss": 1.7453,
56
+ "step": 908064
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 2.001136483772069e-05,
61
+ "loss": 1.7178,
62
+ "step": 1021572
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 1.6679294264134097e-05,
67
+ "loss": 1.6944,
68
+ "step": 1135080
69
+ },
70
+ {
71
+ "epoch": 11.0,
72
+ "learning_rate": 1.334719432404177e-05,
73
+ "loss": 1.6729,
74
+ "step": 1248588
75
+ },
76
+ {
77
+ "epoch": 12.0,
78
+ "learning_rate": 1.0015123750455182e-05,
79
+ "loss": 1.6535,
80
+ "step": 1362096
81
+ },
82
+ {
83
+ "epoch": 13.0,
84
+ "learning_rate": 6.683023810362853e-06,
85
+ "loss": 1.6363,
86
+ "step": 1475604
87
+ },
88
+ {
89
+ "epoch": 14.0,
90
+ "learning_rate": 3.350953236776263e-06,
91
+ "loss": 1.6216,
92
+ "step": 1589112
93
+ },
94
+ {
95
+ "epoch": 15.0,
96
+ "learning_rate": 1.8882663189672388e-08,
97
+ "loss": 1.6102,
98
+ "step": 1702620
99
+ },
100
+ {
101
+ "epoch": 16.0,
102
+ "learning_rate": 1.0015065017443704e-05,
103
+ "loss": 1.6294,
104
+ "step": 1816128
105
+ },
106
+ {
107
+ "epoch": 17.0,
108
+ "learning_rate": 7.515968037495155e-06,
109
+ "loss": 1.6191,
110
+ "step": 1929636
111
+ },
112
+ {
113
+ "epoch": 18.0,
114
+ "learning_rate": 5.016915107305212e-06,
115
+ "loss": 1.6079,
116
+ "step": 2043144
117
+ },
118
+ {
119
+ "epoch": 19.0,
120
+ "learning_rate": 2.517884201994573e-06,
121
+ "loss": 1.5972,
122
+ "step": 2156652
123
+ },
124
+ {
125
+ "epoch": 20.0,
126
+ "learning_rate": 1.8831271804630513e-08,
127
+ "loss": 1.5893,
128
+ "step": 2270160
129
+ },
130
+ {
131
+ "epoch": 20.0,
132
+ "step": 2270160,
133
+ "total_flos": 3.805740641757115e+19,
134
+ "train_loss": 0.4021474394976566,
135
+ "train_runtime": 51134.1112,
136
+ "train_samples_per_second": 11365.472,
137
+ "train_steps_per_second": 44.396
138
+ }
139
+ ],
140
+ "max_steps": 2270160,
141
+ "num_train_epochs": 20,
142
+ "total_flos": 3.805740641757115e+19,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01bce61e4e4d2babd6021cf619298cb8992c8b6863fd1035638a1a05d354c73c
3
+ size 3247