Hugging Face's logo

hung200504
/
bert-31

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
1
hung200504 commited on
Commit
50ee40e
路
1 Parent(s): ec51588

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +15 -47
  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 [hung200504/bert-21](https://huggingface.co/hung200504/bert-21) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 11.6562
19
 
20
  ## Model description
21
 
@@ -34,9 +34,9 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 3e-07
38
- - train_batch_size: 4
39
- - eval_batch_size: 4
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
@@ -46,49 +46,17 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 9.9408 | 0.02 | 5 | 11.9244 |
50
- | 10.9745 | 0.05 | 10 | 11.9123 |
51
- | 11.7105 | 0.07 | 15 | 11.8995 |
52
- | 10.574 | 0.09 | 20 | 11.8876 |
53
- | 11.2567 | 0.11 | 25 | 11.8761 |
54
- | 10.1985 | 0.14 | 30 | 11.8651 |
55
- | 11.1306 | 0.16 | 35 | 11.8543 |
56
- | 11.0848 | 0.18 | 40 | 11.8435 |
57
- | 10.9051 | 0.21 | 45 | 11.8331 |
58
- | 11.2139 | 0.23 | 50 | 11.8228 |
59
- | 9.4434 | 0.25 | 55 | 11.8132 |
60
- | 10.6242 | 0.28 | 60 | 11.8038 |
61
- | 10.2756 | 0.3 | 65 | 11.7948 |
62
- | 11.1823 | 0.32 | 70 | 11.7861 |
63
- | 11.3154 | 0.34 | 75 | 11.7776 |
64
- | 10.4026 | 0.37 | 80 | 11.7694 |
65
- | 11.4274 | 0.39 | 85 | 11.7615 |
66
- | 10.1923 | 0.41 | 90 | 11.7535 |
67
- | 10.8907 | 0.44 | 95 | 11.7463 |
68
- | 10.5215 | 0.46 | 100 | 11.7395 |
69
- | 11.2088 | 0.48 | 105 | 11.7323 |
70
- | 10.3167 | 0.5 | 110 | 11.7258 |
71
- | 10.6535 | 0.53 | 115 | 11.7197 |
72
- | 10.8819 | 0.55 | 120 | 11.7137 |
73
- | 10.0389 | 0.57 | 125 | 11.7080 |
74
- | 10.0161 | 0.6 | 130 | 11.7025 |
75
- | 10.4476 | 0.62 | 135 | 11.6975 |
76
- | 10.3089 | 0.64 | 140 | 11.6930 |
77
- | 10.6388 | 0.67 | 145 | 11.6885 |
78
- | 11.1704 | 0.69 | 150 | 11.6842 |
79
- | 10.6095 | 0.71 | 155 | 11.6804 |
80
- | 10.8112 | 0.73 | 160 | 11.6766 |
81
- | 10.0912 | 0.76 | 165 | 11.6734 |
82
- | 10.8292 | 0.78 | 170 | 11.6704 |
83
- | 10.3543 | 0.8 | 175 | 11.6676 |
84
- | 9.7421 | 0.83 | 180 | 11.6649 |
85
- | 11.3465 | 0.85 | 185 | 11.6626 |
86
- | 9.4446 | 0.87 | 190 | 11.6609 |
87
- | 10.4486 | 0.89 | 195 | 11.6593 |
88
- | 10.2593 | 0.92 | 200 | 11.6579 |
89
- | 10.379 | 0.94 | 205 | 11.6571 |
90
- | 9.7728 | 0.96 | 210 | 11.6567 |
91
- | 9.7654 | 0.99 | 215 | 11.6562 |
92
 
93
 
94
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [hung200504/bert-21](https://huggingface.co/hung200504/bert-21) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 9.6564
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 3e-06
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
+ | 10.8389 | 0.09 | 5 | 11.6872 |
50
+ | 10.6506 | 0.18 | 10 | 11.3129 |
51
+ | 9.9367 | 0.27 | 15 | 10.9748 |
52
+ | 9.7504 | 0.36 | 20 | 10.6767 |
53
+ | 9.4789 | 0.45 | 25 | 10.4164 |
54
+ | 9.3145 | 0.55 | 30 | 10.1941 |
55
+ | 8.4653 | 0.64 | 35 | 10.0120 |
56
+ | 8.9579 | 0.73 | 40 | 9.8679 |
57
+ | 8.3746 | 0.82 | 45 | 9.7613 |
58
+ | 8.3205 | 0.91 | 50 | 9.6904 |
59
+ | 8.0754 | 1.0 | 55 | 9.6564 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:ebbb68b88b8ab428f75c82ef3ec0e86a2f1773f1c6c91c79be4efe5b1083273f
3
  size 430953062
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392790dbbdd452af0a3c3f0ad733d9535783cac96e6cfd3056939b7e6f596d60
3
  size 430953062
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00da6c47f2c88e65093029c1d97ed5c3d3676aa2f00f2c2e6e6cfa916f4058e7
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87cdfed3eed151819fb28ba4e7d5b7ebad76c579d36146f3cc2aa4151720fa6
3
  size 4472