Hugging Face's logo

soikit
/
chinese-bert-wwm-chinese_bert_wwm3

Text Generation
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
soikit commited on
Commit
187d2eb
·
1 Parent(s): bf86a58

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -34,8 +34,8 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 16
38
- - eval_batch_size: 16
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
@@ -45,36 +45,36 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | No log | 1.0 | 287 | 0.0094 |
49
- | 0.6238 | 2.0 | 574 | 0.0008 |
50
- | 0.6238 | 3.0 | 861 | 0.0003 |
51
- | 0.0074 | 4.0 | 1148 | 0.0002 |
52
- | 0.0074 | 5.0 | 1435 | 0.0002 |
53
- | 0.003 | 6.0 | 1722 | 0.0001 |
54
- | 0.0019 | 7.0 | 2009 | 0.0001 |
55
- | 0.0019 | 8.0 | 2296 | 0.0001 |
56
- | 0.0014 | 9.0 | 2583 | 0.0001 |
57
- | 0.0014 | 10.0 | 2870 | 0.0000 |
58
- | 0.0012 | 11.0 | 3157 | 0.0000 |
59
- | 0.0012 | 12.0 | 3444 | 0.0000 |
60
- | 0.0011 | 13.0 | 3731 | 0.0000 |
61
- | 0.0008 | 14.0 | 4018 | 0.0000 |
62
- | 0.0008 | 15.0 | 4305 | 0.0000 |
63
- | 0.0006 | 16.0 | 4592 | 0.0000 |
64
- | 0.0006 | 17.0 | 4879 | 0.0000 |
65
- | 0.0006 | 18.0 | 5166 | 0.0000 |
66
- | 0.0006 | 19.0 | 5453 | 0.0000 |
67
- | 0.0005 | 20.0 | 5740 | 0.0000 |
68
- | 0.0003 | 21.0 | 6027 | 0.0000 |
69
- | 0.0003 | 22.0 | 6314 | 0.0000 |
70
- | 0.0003 | 23.0 | 6601 | 0.0000 |
71
- | 0.0003 | 24.0 | 6888 | 0.0000 |
72
- | 0.0003 | 25.0 | 7175 | 0.0000 |
73
- | 0.0003 | 26.0 | 7462 | 0.0000 |
74
- | 0.0002 | 27.0 | 7749 | 0.0000 |
75
- | 0.0002 | 28.0 | 8036 | 0.0000 |
76
- | 0.0002 | 29.0 | 8323 | 0.0000 |
77
- | 0.0002 | 30.0 | 8610 | 0.0000 |
78
 
79
 
80
  ### Framework versions
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 64
38
+ - eval_batch_size: 64
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 72 | 0.4251 |
49
+ | No log | 2.0 | 144 | 0.0282 |
50
+ | No log | 3.0 | 216 | 0.0048 |
51
+ | No log | 4.0 | 288 | 0.0018 |
52
+ | No log | 5.0 | 360 | 0.0011 |
53
+ | No log | 6.0 | 432 | 0.0006 |
54
+ | 0.483 | 7.0 | 504 | 0.0004 |
55
+ | 0.483 | 8.0 | 576 | 0.0004 |
56
+ | 0.483 | 9.0 | 648 | 0.0002 |
57
+ | 0.483 | 10.0 | 720 | 0.0002 |
58
+ | 0.483 | 11.0 | 792 | 0.0002 |
59
+ | 0.483 | 12.0 | 864 | 0.0001 |
60
+ | 0.483 | 13.0 | 936 | 0.0001 |
61
+ | 0.0031 | 14.0 | 1008 | 0.0001 |
62
+ | 0.0031 | 15.0 | 1080 | 0.0001 |
63
+ | 0.0031 | 16.0 | 1152 | 0.0001 |
64
+ | 0.0031 | 17.0 | 1224 | 0.0001 |
65
+ | 0.0031 | 18.0 | 1296 | 0.0001 |
66
+ | 0.0031 | 19.0 | 1368 | 0.0001 |
67
+ | 0.0031 | 20.0 | 1440 | 0.0001 |
68
+ | 0.0015 | 21.0 | 1512 | 0.0001 |
69
+ | 0.0015 | 22.0 | 1584 | 0.0001 |
70
+ | 0.0015 | 23.0 | 1656 | 0.0001 |
71
+ | 0.0015 | 24.0 | 1728 | 0.0001 |
72
+ | 0.0015 | 25.0 | 1800 | 0.0000 |
73
+ | 0.0015 | 26.0 | 1872 | 0.0001 |
74
+ | 0.0015 | 27.0 | 1944 | 0.0000 |
75
+ | 0.001 | 28.0 | 2016 | 0.0000 |
76
+ | 0.001 | 29.0 | 2088 | 0.0000 |
77
+ | 0.001 | 30.0 | 2160 | 0.0000 |
78
 
79
 
80
  ### Framework versions