Hugging Face's logo

sharkMeow
/
bert-base-chinese-finetuned-QA-b8

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
sharkMeow commited on
Commit
ad0812b
路
1 Parent(s): 0ee9be7

Model save

Browse files
Files changed (2) hide show
  1. README.md +14 -28
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [ckiplab/bert-base-chinese](https://huggingface.co/ckiplab/bert-base-chinese) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.3405
19
 
20
  ## Model description
21
 
@@ -48,33 +48,19 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 1.9325 | 0.14 | 500 | 1.2076 |
52
- | 1.1199 | 0.29 | 1000 | 1.0315 |
53
- | 1.0118 | 0.43 | 1500 | 0.9836 |
54
- | 0.9398 | 0.58 | 2000 | 0.9762 |
55
- | 0.9526 | 0.72 | 2500 | 0.9374 |
56
- | 0.9142 | 0.87 | 3000 | 0.8783 |
57
- | 0.8265 | 1.01 | 3500 | 0.9919 |
58
- | 0.6091 | 1.16 | 4000 | 0.9613 |
59
- | 0.6303 | 1.3 | 4500 | 0.9769 |
60
- | 0.6161 | 1.45 | 5000 | 0.9882 |
61
- | 0.6109 | 1.59 | 5500 | 0.9160 |
62
- | 0.5887 | 1.73 | 6000 | 0.9105 |
63
- | 0.5811 | 1.88 | 6500 | 0.9812 |
64
- | 0.5638 | 2.02 | 7000 | 1.0669 |
65
- | 0.4174 | 2.17 | 7500 | 1.2101 |
66
- | 0.3958 | 2.31 | 8000 | 1.2186 |
67
- | 0.4032 | 2.46 | 8500 | 1.1691 |
68
- | 0.4183 | 2.6 | 9000 | 1.0890 |
69
- | 0.4247 | 2.75 | 9500 | 1.0721 |
70
- | 0.3917 | 2.89 | 10000 | 1.1714 |
71
- | 0.3738 | 3.04 | 10500 | 1.1794 |
72
- | 0.29 | 3.18 | 11000 | 1.2494 |
73
- | 0.326 | 3.32 | 11500 | 1.2822 |
74
- | 0.3076 | 3.47 | 12000 | 1.3214 |
75
- | 0.3071 | 3.61 | 12500 | 1.2968 |
76
- | 0.2797 | 3.76 | 13000 | 1.3410 |
77
- | 0.3192 | 3.9 | 13500 | 1.3405 |
78
 
79
 
80
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [ckiplab/bert-base-chinese](https://huggingface.co/ckiplab/bert-base-chinese) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.2136
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 1.3406 | 0.29 | 1000 | 0.8157 |
52
+ | 0.7651 | 0.58 | 2000 | 0.7385 |
53
+ | 0.7172 | 0.87 | 3000 | 0.6328 |
54
+ | 0.5028 | 1.16 | 4000 | 0.6747 |
55
+ | 0.405 | 1.45 | 5000 | 0.6796 |
56
+ | 0.4005 | 1.73 | 6000 | 0.6860 |
57
+ | 0.3522 | 2.02 | 7000 | 0.8813 |
58
+ | 0.2048 | 2.31 | 8000 | 0.9346 |
59
+ | 0.1929 | 2.6 | 9000 | 1.0987 |
60
+ | 0.2032 | 2.89 | 10000 | 1.0005 |
61
+ | 0.142 | 3.18 | 11000 | 1.1372 |
62
+ | 0.0938 | 3.47 | 12000 | 1.2476 |
63
+ | 0.0953 | 3.76 | 13000 | 1.2136 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16cfa8d465f1f6d0018128480561cc9ac8553f3aa857e2e7936b41a9c5c0d037
3
  size 406782121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf91d9a910dca340f067cb101f5d8045aed80a47088c1a270c4d21b635da740e
3
  size 406782121