ZON8955 commited on
Commit
ebea324
·
verified ·
1 Parent(s): 952402d

End of training

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -16,7 +16,7 @@ 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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0183
20
 
21
  ## Model description
22
 
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | No log | 1.0 | 5 | 0.9613 |
54
- | 6.4632 | 2.0 | 10 | 0.6466 |
55
- | 6.4632 | 3.0 | 15 | 0.2690 |
56
- | 2.5919 | 4.0 | 20 | 0.1573 |
57
- | 2.5919 | 5.0 | 25 | 0.0958 |
58
- | 0.9207 | 6.0 | 30 | 0.0558 |
59
- | 0.9207 | 7.0 | 35 | 0.0323 |
60
- | 0.3551 | 8.0 | 40 | 0.0234 |
61
- | 0.3551 | 9.0 | 45 | 0.0197 |
62
- | 0.2133 | 10.0 | 50 | 0.0183 |
63
 
64
 
65
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0010
20
 
21
  ## Model description
22
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | No log | 1.0 | 5 | 0.0127 |
54
+ | 0.1471 | 2.0 | 10 | 0.0063 |
55
+ | 0.1471 | 3.0 | 15 | 0.0036 |
56
+ | 0.0399 | 4.0 | 20 | 0.0023 |
57
+ | 0.0399 | 5.0 | 25 | 0.0017 |
58
+ | 0.0163 | 6.0 | 30 | 0.0014 |
59
+ | 0.0163 | 7.0 | 35 | 0.0012 |
60
+ | 0.0112 | 8.0 | 40 | 0.0011 |
61
+ | 0.0112 | 9.0 | 45 | 0.0010 |
62
+ | 0.0096 | 10.0 | 50 | 0.0010 |
63
 
64
 
65
  ### Framework versions