Hugging Face's logo

hung200504
/
bert-30

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
hung200504 commited on
Commit
1288f19
•
1 Parent(s): 0e574cc

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +26 -26
  2. pytorch_model.bin +1 -1
  3. training_args.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 [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 11.5113
19
 
20
  ## Model description
21
 
@@ -35,39 +35,39 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 3e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 16
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 2
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 11.3133 | 0.09 | 5 | 12.3059 |
50
- | 11.4119 | 0.18 | 10 | 12.2326 |
51
- | 10.9781 | 0.27 | 15 | 12.1623 |
52
- | 11.087 | 0.36 | 20 | 12.0961 |
53
- | 11.0516 | 0.45 | 25 | 12.0332 |
54
- | 11.0596 | 0.55 | 30 | 11.9737 |
55
- | 10.3306 | 0.64 | 35 | 11.9182 |
56
- | 10.9488 | 0.73 | 40 | 11.8666 |
57
- | 10.4959 | 0.82 | 45 | 11.8184 |
58
- | 10.3818 | 0.91 | 50 | 11.7738 |
59
- | 10.143 | 1.0 | 55 | 11.7325 |
60
- | 10.3456 | 1.09 | 60 | 11.6951 |
61
- | 10.4584 | 1.18 | 65 | 11.6612 |
62
- | 10.6774 | 1.27 | 70 | 11.6308 |
63
- | 10.2145 | 1.36 | 75 | 11.6035 |
64
- | 10.6536 | 1.45 | 80 | 11.5801 |
65
- | 10.3892 | 1.55 | 85 | 11.5599 |
66
- | 10.3469 | 1.64 | 90 | 11.5429 |
67
- | 10.1863 | 1.73 | 95 | 11.5295 |
68
- | 10.4296 | 1.82 | 100 | 11.5200 |
69
- | 9.989 | 1.91 | 105 | 11.5140 |
70
- | 10.3568 | 2.0 | 110 | 11.5113 |
71
 
72
 
73
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 11.4865
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 3e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 4
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 11.2225 | 0.18 | 5 | 12.3054 |
50
+ | 10.9594 | 0.36 | 10 | 12.2315 |
51
+ | 11.0948 | 0.54 | 15 | 12.1603 |
52
+ | 10.8444 | 0.71 | 20 | 12.0935 |
53
+ | 10.7294 | 0.89 | 25 | 12.0294 |
54
+ | 10.5432 | 1.07 | 30 | 11.9697 |
55
+ | 10.71 | 1.25 | 35 | 11.9133 |
56
+ | 10.5919 | 1.43 | 40 | 11.8601 |
57
+ | 10.5393 | 1.61 | 45 | 11.8109 |
58
+ | 10.562 | 1.79 | 50 | 11.7650 |
59
+ | 10.6558 | 1.96 | 55 | 11.7222 |
60
+ | 10.4995 | 2.14 | 60 | 11.6835 |
61
+ | 10.3046 | 2.32 | 65 | 11.6488 |
62
+ | 10.2809 | 2.5 | 70 | 11.6169 |
63
+ | 10.6538 | 2.68 | 75 | 11.5887 |
64
+ | 10.2451 | 2.86 | 80 | 11.5635 |
65
+ | 10.2671 | 3.04 | 85 | 11.5420 |
66
+ | 10.7256 | 3.21 | 90 | 11.5243 |
67
+ | 10.2996 | 3.39 | 95 | 11.5094 |
68
+ | 10.1658 | 3.57 | 100 | 11.4983 |
69
+ | 10.4609 | 3.75 | 105 | 11.4906 |
70
+ | 10.3872 | 3.93 | 110 | 11.4865 |
71
 
72
 
73
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a3f28d3f2b6ca5629aa227d4dffd994565ea966a9fcef3df5d3b6bf11a18f83
3
  size 430953062
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5392786d4ab13d0d258c0bd1e8d622c0f4b62349b487b6ededc3a1974207e832
3
  size 430953062
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b9f337a4a726d5951947835e63488208843b179304f5e9272a7b17f0c26e5a
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d84166177fe7daa5e17177c997939be534de74eb4056835bd16b8344b9ec43a
3
  size 4472