Hugging Face's logo

wsqstar
/
bert-finetuned-weibo-luobokuaipao

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
wsqstar commited on
Commit
c7e0e93
•
1 Parent(s): 0127b6e

End of training

Browse files
Files changed (1) hide show
  1. README.md +44 -24
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.3065
20
- - Accuracy: 0.5833
21
 
22
  ## Model description
23
 
@@ -36,38 +36,58 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 5e-05
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 20
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 1.0 | 270 | 0.9893 | 0.5852 |
52
- | 1.0044 | 2.0 | 540 | 1.0391 | 0.5907 |
53
- | 1.0044 | 3.0 | 810 | 1.2162 | 0.6130 |
54
- | 0.5461 | 4.0 | 1080 | 1.3702 | 0.5667 |
55
- | 0.5461 | 5.0 | 1350 | 1.8272 | 0.5704 |
56
- | 0.349 | 6.0 | 1620 | 2.1860 | 0.5741 |
57
- | 0.349 | 7.0 | 1890 | 2.1618 | 0.5685 |
58
- | 0.2502 | 8.0 | 2160 | 2.5620 | 0.5593 |
59
- | 0.2502 | 9.0 | 2430 | 2.6044 | 0.5667 |
60
- | 0.1651 | 10.0 | 2700 | 3.0138 | 0.5778 |
61
- | 0.1651 | 11.0 | 2970 | 3.1734 | 0.5481 |
62
- | 0.1153 | 12.0 | 3240 | 3.0025 | 0.5759 |
63
- | 0.0893 | 13.0 | 3510 | 3.1646 | 0.5889 |
64
- | 0.0893 | 14.0 | 3780 | 3.0978 | 0.5833 |
65
- | 0.0659 | 15.0 | 4050 | 3.1681 | 0.5741 |
66
- | 0.0659 | 16.0 | 4320 | 3.1982 | 0.5778 |
67
- | 0.0433 | 17.0 | 4590 | 3.2583 | 0.5778 |
68
- | 0.0433 | 18.0 | 4860 | 3.2408 | 0.5778 |
69
- | 0.0396 | 19.0 | 5130 | 3.2881 | 0.5852 |
70
- | 0.0396 | 20.0 | 5400 | 3.3065 | 0.5833 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 3.2017
20
+ - Accuracy: 0.5815
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 40
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 243 | 1.0137 | 0.5852 |
52
+ | No log | 2.0 | 486 | 0.9878 | 0.5815 |
53
+ | 1.0413 | 3.0 | 729 | 1.0463 | 0.6056 |
54
+ | 1.0413 | 4.0 | 972 | 1.1697 | 0.6130 |
55
+ | 0.5875 | 5.0 | 1215 | 1.3835 | 0.5852 |
56
+ | 0.5875 | 6.0 | 1458 | 1.5941 | 0.5722 |
57
+ | 0.3069 | 7.0 | 1701 | 1.9360 | 0.5796 |
58
+ | 0.3069 | 8.0 | 1944 | 2.0863 | 0.6093 |
59
+ | 0.1782 | 9.0 | 2187 | 2.2601 | 0.5833 |
60
+ | 0.1782 | 10.0 | 2430 | 2.4810 | 0.5926 |
61
+ | 0.12 | 11.0 | 2673 | 2.5233 | 0.6 |
62
+ | 0.12 | 12.0 | 2916 | 2.5486 | 0.5833 |
63
+ | 0.089 | 13.0 | 3159 | 2.6555 | 0.5704 |
64
+ | 0.089 | 14.0 | 3402 | 2.6093 | 0.6019 |
65
+ | 0.0718 | 15.0 | 3645 | 2.6888 | 0.5907 |
66
+ | 0.0718 | 16.0 | 3888 | 2.9839 | 0.5722 |
67
+ | 0.061 | 17.0 | 4131 | 2.8104 | 0.5778 |
68
+ | 0.061 | 18.0 | 4374 | 2.9843 | 0.5685 |
69
+ | 0.062 | 19.0 | 4617 | 3.1577 | 0.5648 |
70
+ | 0.062 | 20.0 | 4860 | 3.1641 | 0.5722 |
71
+ | 0.0553 | 21.0 | 5103 | 3.1004 | 0.5611 |
72
+ | 0.0553 | 22.0 | 5346 | 3.0974 | 0.5778 |
73
+ | 0.0417 | 23.0 | 5589 | 3.0206 | 0.5759 |
74
+ | 0.0417 | 24.0 | 5832 | 3.0191 | 0.5667 |
75
+ | 0.0374 | 25.0 | 6075 | 3.0920 | 0.5722 |
76
+ | 0.0374 | 26.0 | 6318 | 2.9696 | 0.5852 |
77
+ | 0.0335 | 27.0 | 6561 | 3.0100 | 0.5889 |
78
+ | 0.0335 | 28.0 | 6804 | 3.1014 | 0.5667 |
79
+ | 0.0313 | 29.0 | 7047 | 3.2620 | 0.5574 |
80
+ | 0.0313 | 30.0 | 7290 | 3.0502 | 0.5889 |
81
+ | 0.032 | 31.0 | 7533 | 3.0984 | 0.5833 |
82
+ | 0.032 | 32.0 | 7776 | 3.1546 | 0.5704 |
83
+ | 0.0329 | 33.0 | 8019 | 3.0977 | 0.5741 |
84
+ | 0.0329 | 34.0 | 8262 | 3.0975 | 0.5796 |
85
+ | 0.0276 | 35.0 | 8505 | 3.1124 | 0.5870 |
86
+ | 0.0276 | 36.0 | 8748 | 3.1204 | 0.5926 |
87
+ | 0.0276 | 37.0 | 8991 | 3.1556 | 0.5833 |
88
+ | 0.026 | 38.0 | 9234 | 3.1909 | 0.5815 |
89
+ | 0.026 | 39.0 | 9477 | 3.1959 | 0.5815 |
90
+ | 0.0245 | 40.0 | 9720 | 3.2017 | 0.5815 |
91
 
92
 
93
  ### Framework versions