Hugging Face's logo

ceviriyap
/
bert_4

Transformers
TensorFlow
bert
pretraining
generated_from_keras_callback
Model card Files
xet
Community
hanci05 commited on
Commit
9326dc8
·
1 Parent(s): 214d478

Upload TFBertForPreTraining

Browse files
Files changed (2) hide show
  1. README.md +42 -42
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 3.7745
17
  - Epoch: 39
18
 
19
  ## Model description
@@ -33,53 +33,53 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - optimizer: {'name': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
37
  - training_precision: float32
38
 
39
  ### Training results
40
 
41
  | Train Loss | Epoch |
42
  |:----------:|:-----:|
43
- | 9.8117 | 0 |
44
- | 8.2576 | 1 |
45
- | 7.4407 | 2 |
46
- | 6.6293 | 3 |
47
- | 6.5469 | 4 |
48
- | 6.2164 | 5 |
49
- | 6.0521 | 6 |
50
- | 5.9713 | 7 |
51
- | 5.9086 | 8 |
52
- | 5.8189 | 9 |
53
- | 5.6795 | 10 |
54
- | 5.5906 | 11 |
55
- | 5.5204 | 12 |
56
- | 5.5486 | 13 |
57
- | 5.4477 | 14 |
58
- | 5.2403 | 15 |
59
- | 5.0455 | 16 |
60
- | 5.3176 | 17 |
61
- | 5.0164 | 18 |
62
- | 4.9527 | 19 |
63
- | 4.8094 | 20 |
64
- | 4.5558 | 21 |
65
- | 4.5773 | 22 |
66
- | 4.4212 | 23 |
67
- | 4.6842 | 24 |
68
- | 4.3020 | 25 |
69
- | 4.3645 | 26 |
70
- | 4.3142 | 27 |
71
- | 4.1144 | 28 |
72
- | 4.2619 | 29 |
73
- | 4.1658 | 30 |
74
- | 3.9685 | 31 |
75
- | 4.0776 | 32 |
76
- | 4.0119 | 33 |
77
- | 4.0048 | 34 |
78
- | 3.9660 | 35 |
79
- | 3.8173 | 36 |
80
- | 3.8051 | 37 |
81
- | 3.6915 | 38 |
82
- | 3.7745 | 39 |
83
 
84
 
85
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: nan
17
  - Epoch: 39
18
 
19
  ## Model description
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - optimizer: {'name': 'Adam', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
37
  - training_precision: float32
38
 
39
  ### Training results
40
 
41
  | Train Loss | Epoch |
42
  |:----------:|:-----:|
43
+ | 10.2428 | 0 |
44
+ | nan | 1 |
45
+ | nan | 2 |
46
+ | nan | 3 |
47
+ | nan | 4 |
48
+ | nan | 5 |
49
+ | nan | 6 |
50
+ | nan | 7 |
51
+ | nan | 8 |
52
+ | nan | 9 |
53
+ | nan | 10 |
54
+ | nan | 11 |
55
+ | nan | 12 |
56
+ | nan | 13 |
57
+ | nan | 14 |
58
+ | nan | 15 |
59
+ | nan | 16 |
60
+ | nan | 17 |
61
+ | nan | 18 |
62
+ | nan | 19 |
63
+ | nan | 20 |
64
+ | nan | 21 |
65
+ | nan | 22 |
66
+ | nan | 23 |
67
+ | nan | 24 |
68
+ | nan | 25 |
69
+ | nan | 26 |
70
+ | nan | 27 |
71
+ | nan | 28 |
72
+ | nan | 29 |
73
+ | nan | 30 |
74
+ | nan | 31 |
75
+ | nan | 32 |
76
+ | nan | 33 |
77
+ | nan | 34 |
78
+ | nan | 35 |
79
+ | nan | 36 |
80
+ | nan | 37 |
81
+ | nan | 38 |
82
+ | nan | 39 |
83
 
84
 
85
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61aa1799dc56bdd9d3031d86bd230933519f21396ce76ec51f46e637d6fcd677
3
  size 526681688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e63c377320d94e13c5266931288e63a364c08c1ed10c336a2bc8742496f80db
3
  size 526681688