Hugging Face's logo

hung200504
/
bert-30

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
1
hung200504 commited on
Commit
cd8fb92
路
1 Parent(s): 465a203

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +14 -24
  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: 11.5401
19
 
20
  ## Model description
21
 
@@ -35,8 +35,8 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 3e-05
38
- - train_batch_size: 8
39
- - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
@@ -46,27 +46,17 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 10.8471 | 0.05 | 5 | 12.3076 |
50
- | 10.8298 | 0.09 | 10 | 12.2362 |
51
- | 11.0622 | 0.14 | 15 | 12.1684 |
52
- | 11.6335 | 0.18 | 20 | 12.1040 |
53
- | 11.4197 | 0.23 | 25 | 12.0427 |
54
- | 10.5672 | 0.28 | 30 | 11.9853 |
55
- | 10.7596 | 0.32 | 35 | 11.9313 |
56
- | 10.8418 | 0.37 | 40 | 11.8806 |
57
- | 11.0164 | 0.41 | 45 | 11.8333 |
58
- | 10.3409 | 0.46 | 50 | 11.7898 |
59
- | 11.2085 | 0.5 | 55 | 11.7495 |
60
- | 10.3929 | 0.55 | 60 | 11.7126 |
61
- | 9.9285 | 0.6 | 65 | 11.6798 |
62
- | 9.834 | 0.64 | 70 | 11.6507 |
63
- | 10.5704 | 0.69 | 75 | 11.6249 |
64
- | 10.8002 | 0.73 | 80 | 11.6020 |
65
- | 10.5069 | 0.78 | 85 | 11.5831 |
66
- | 10.0382 | 0.83 | 90 | 11.5671 |
67
- | 10.133 | 0.87 | 95 | 11.5551 |
68
- | 10.212 | 0.92 | 100 | 11.5459 |
69
- | 9.9872 | 0.96 | 105 | 11.5401 |
70
 
71
 
72
  ### 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: 11.9330
19
 
20
  ## Model description
21
 
 
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
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 11.3134 | 0.09 | 5 | 12.3068 |
50
+ | 11.4146 | 0.18 | 10 | 12.2378 |
51
+ | 10.9861 | 0.27 | 15 | 12.1756 |
52
+ | 11.1036 | 0.36 | 20 | 12.1205 |
53
+ | 11.079 | 0.45 | 25 | 12.0721 |
54
+ | 11.1039 | 0.55 | 30 | 12.0310 |
55
+ | 10.3894 | 0.64 | 35 | 11.9972 |
56
+ | 11.034 | 0.73 | 40 | 11.9707 |
57
+ | 10.6017 | 0.82 | 45 | 11.9511 |
58
+ | 10.5161 | 0.91 | 50 | 11.9387 |
59
+ | 10.3011 | 1.0 | 55 | 11.9330 |
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326d4cdb5de4637fbae007d0d1899abd9eb583793523af5eddf088a75d4ea38d
3
  size 430952617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055f8a0c756bf95bf820c9730481af9927b9da408eb4a4cf860c79e749fbf47d
3
  size 430952617
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2128a4322e8259c022654ae253176db67177454c5a8ef6a80a08cf72aed76b22
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1671a4052174948ce92ca710490887e84a8ec17ce2a57053549b6fd9c3aca365
3
  size 4027