amrisaurus commited on
Commit
dd8e017
1 Parent(s): 6e0825b

Upload TFBertForPreTraining

Browse files
Files changed (2) hide show
  1. README.md +92 -92
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -41,98 +41,98 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 8.8949 | 9.5572 | 0 |
45
- | 7.0519 | 9.6533 | 1 |
46
- | 6.6105 | 10.5350 | 2 |
47
- | 6.1179 | 10.5029 | 3 |
48
- | 6.2132 | 10.4847 | 4 |
49
- | 5.9871 | 11.0885 | 5 |
50
- | 6.1688 | 10.8718 | 6 |
51
- | 5.9314 | 11.3327 | 7 |
52
- | 5.7351 | 10.9617 | 8 |
53
- | 5.8560 | 11.1321 | 9 |
54
- | 5.8481 | 11.6140 | 10 |
55
- | 5.7559 | 12.0339 | 11 |
56
- | 5.7173 | 11.4748 | 12 |
57
- | 5.7983 | 11.6411 | 13 |
58
- | 5.7962 | 11.7358 | 14 |
59
- | 5.6231 | 11.9414 | 15 |
60
- | 5.7017 | 11.9826 | 16 |
61
- | 5.7410 | 12.3874 | 17 |
62
- | 5.6265 | 11.7751 | 18 |
63
- | 5.6306 | 12.2193 | 19 |
64
- | 5.7388 | 12.3857 | 20 |
65
- | 5.6609 | 12.2233 | 21 |
66
- | 5.6789 | 12.2402 | 22 |
67
- | 5.7445 | 12.2426 | 23 |
68
- | 5.5452 | 12.4404 | 24 |
69
- | 5.4805 | 12.3489 | 25 |
70
- | 5.7127 | 12.7864 | 26 |
71
- | 5.6447 | 12.3328 | 27 |
72
- | 5.6164 | 12.4801 | 28 |
73
- | 5.8520 | 12.3771 | 29 |
74
- | 5.6463 | 12.5703 | 30 |
75
- | 5.5623 | 12.6834 | 31 |
76
- | 5.8278 | 12.6487 | 32 |
77
- | 5.5685 | 13.1277 | 33 |
78
- | 5.6011 | 12.5943 | 34 |
79
- | 5.6875 | 12.3462 | 35 |
80
- | 5.6110 | 12.5878 | 36 |
81
- | 5.5835 | 12.4549 | 37 |
82
- | 5.5815 | 12.8878 | 38 |
83
- | 5.6311 | 12.9602 | 39 |
84
- | 5.4738 | 13.0979 | 40 |
85
- | 5.5735 | 12.9235 | 41 |
86
- | 5.6244 | 13.1418 | 42 |
87
- | 5.5516 | 12.6599 | 43 |
88
- | 5.6252 | 13.0641 | 44 |
89
- | 5.4607 | 13.0718 | 45 |
90
- | 5.5763 | 13.2025 | 46 |
91
- | 5.5362 | 13.4460 | 47 |
92
- | 5.4854 | 13.4286 | 48 |
93
- | 5.6867 | 13.1493 | 49 |
94
- | 5.7481 | 13.1630 | 50 |
95
- | 5.5379 | 13.2930 | 51 |
96
- | 5.6109 | 13.3768 | 52 |
97
- | 5.5973 | 13.4531 | 53 |
98
- | 5.6822 | 13.5087 | 54 |
99
- | 5.6060 | 12.7496 | 55 |
100
- | 5.7165 | 13.2133 | 56 |
101
- | 5.5243 | 13.6238 | 57 |
102
- | 5.5200 | 13.4976 | 58 |
103
- | 5.5642 | 13.8498 | 59 |
104
- | 5.6705 | 13.1397 | 60 |
105
- | 5.5390 | 13.3590 | 61 |
106
- | 5.4978 | 13.5817 | 62 |
107
- | 5.5061 | 13.4669 | 63 |
108
- | 5.5881 | 13.6493 | 64 |
109
- | 5.5648 | 13.2408 | 65 |
110
- | 5.6299 | 13.5216 | 66 |
111
- | 5.6599 | 13.0719 | 67 |
112
- | 5.7965 | 13.6826 | 68 |
113
- | 5.7421 | 13.6060 | 69 |
114
- | 5.5650 | 13.3846 | 70 |
115
- | 5.4875 | 13.6878 | 71 |
116
- | 5.7371 | 13.5511 | 72 |
117
- | 5.5966 | 13.2887 | 73 |
118
- | 5.5894 | 14.0936 | 74 |
119
- | 5.7004 | 13.7622 | 75 |
120
- | 5.6737 | 13.4648 | 76 |
121
- | 5.6136 | 13.7371 | 77 |
122
- | 5.6187 | 13.7884 | 78 |
123
- | 5.6274 | 13.4675 | 79 |
124
- | 5.6162 | 13.6366 | 80 |
125
- | 5.5840 | 13.8244 | 81 |
126
- | 5.6641 | 14.1976 | 82 |
127
- | 5.4985 | 14.3078 | 83 |
128
- | 5.6718 | 13.9896 | 84 |
129
- | 5.6091 | 13.8538 | 85 |
130
- | 5.6904 | 13.6769 | 86 |
131
- | 5.4727 | 14.0480 | 87 |
132
- | 5.6546 | 14.1696 | 88 |
133
- | 5.5732 | 13.7503 | 89 |
134
- | 5.5981 | 13.8329 | 90 |
135
- | 5.6295 | 14.3874 | 91 |
136
  | nan | nan | 92 |
137
  | nan | nan | 93 |
138
  | nan | nan | 94 |
 
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 8.9076 | 9.5544 | 0 |
45
+ | 7.0572 | 9.6310 | 1 |
46
+ | 6.5781 | 10.4973 | 2 |
47
+ | 6.1054 | 10.4749 | 3 |
48
+ | 6.1980 | 10.4411 | 4 |
49
+ | 6.0896 | 11.1385 | 5 |
50
+ | 6.1630 | 10.8668 | 6 |
51
+ | 5.9313 | 11.2520 | 7 |
52
+ | 5.7459 | 10.9396 | 8 |
53
+ | 5.8505 | 11.1343 | 9 |
54
+ | 5.8592 | 11.6048 | 10 |
55
+ | 5.7595 | 12.0371 | 11 |
56
+ | 5.7283 | 11.4402 | 12 |
57
+ | 5.7948 | 11.6117 | 13 |
58
+ | 5.7973 | 11.7393 | 14 |
59
+ | 5.6228 | 11.9450 | 15 |
60
+ | 5.6996 | 11.9938 | 16 |
61
+ | 5.7468 | 12.3826 | 17 |
62
+ | 5.6336 | 11.7692 | 18 |
63
+ | 5.6287 | 12.1970 | 19 |
64
+ | 5.7435 | 12.3895 | 20 |
65
+ | 5.6587 | 12.2124 | 21 |
66
+ | 5.6767 | 12.1633 | 22 |
67
+ | 5.7494 | 12.1844 | 23 |
68
+ | 5.5532 | 12.4163 | 24 |
69
+ | 5.4826 | 12.3235 | 25 |
70
+ | 5.7103 | 12.7326 | 26 |
71
+ | 5.6399 | 12.3326 | 27 |
72
+ | 5.6171 | 12.4726 | 28 |
73
+ | 5.8517 | 12.3647 | 29 |
74
+ | 5.6446 | 12.4943 | 30 |
75
+ | 5.5662 | 12.6303 | 31 |
76
+ | 5.8222 | 12.5869 | 32 |
77
+ | 5.5710 | 13.0406 | 33 |
78
+ | 5.6011 | 12.5007 | 34 |
79
+ | 5.6860 | 12.2958 | 35 |
80
+ | 5.6071 | 12.5690 | 36 |
81
+ | 5.5824 | 12.4472 | 37 |
82
+ | 5.5800 | 12.8570 | 38 |
83
+ | 5.6298 | 12.9604 | 39 |
84
+ | 5.4751 | 13.0937 | 40 |
85
+ | 5.5724 | 12.8909 | 41 |
86
+ | 5.6251 | 13.1132 | 42 |
87
+ | 5.5483 | 12.7036 | 43 |
88
+ | 5.6252 | 13.1233 | 44 |
89
+ | 5.4592 | 13.1353 | 45 |
90
+ | 5.5780 | 13.2373 | 46 |
91
+ | 5.5350 | 13.4289 | 47 |
92
+ | 5.4859 | 13.3994 | 48 |
93
+ | 5.6908 | 13.1062 | 49 |
94
+ | 5.7516 | 13.1705 | 50 |
95
+ | 5.5373 | 13.3196 | 51 |
96
+ | 5.6078 | 13.3352 | 52 |
97
+ | 5.5998 | 13.3831 | 53 |
98
+ | 5.6833 | 13.4430 | 54 |
99
+ | 5.6047 | 12.7287 | 55 |
100
+ | 5.7165 | 13.1647 | 56 |
101
+ | 5.5246 | 13.5831 | 57 |
102
+ | 5.5244 | 13.4733 | 58 |
103
+ | 5.5659 | 13.8621 | 59 |
104
+ | 5.6702 | 13.0873 | 60 |
105
+ | 5.5403 | 13.2744 | 61 |
106
+ | 5.4980 | 13.5826 | 62 |
107
+ | 5.5052 | 13.4584 | 63 |
108
+ | 5.5921 | 13.6191 | 64 |
109
+ | 5.5647 | 13.2221 | 65 |
110
+ | 5.6330 | 13.4804 | 66 |
111
+ | 5.6607 | 13.0722 | 67 |
112
+ | 5.7957 | 13.6183 | 68 |
113
+ | 5.7403 | 13.5204 | 69 |
114
+ | 5.5702 | 13.4229 | 70 |
115
+ | 5.4891 | 13.6547 | 71 |
116
+ | 5.7374 | 13.5464 | 72 |
117
+ | 5.6032 | 13.3607 | 73 |
118
+ | 5.5891 | 14.0467 | 74 |
119
+ | 5.7014 | 13.7621 | 75 |
120
+ | 5.6749 | 13.4568 | 76 |
121
+ | 5.6180 | 13.7552 | 77 |
122
+ | 5.6203 | 13.7563 | 78 |
123
+ | 5.6290 | 13.4801 | 79 |
124
+ | 5.6179 | 13.6345 | 80 |
125
+ | 5.5856 | 13.8037 | 81 |
126
+ | 5.6667 | 14.1205 | 82 |
127
+ | 5.5012 | 14.2115 | 83 |
128
+ | 5.6736 | 13.9032 | 84 |
129
+ | 5.6132 | 13.7493 | 85 |
130
+ | 5.6931 | 13.5402 | 86 |
131
+ | 5.4744 | 13.9974 | 87 |
132
+ | 5.6554 | 14.0855 | 88 |
133
+ | 5.5775 | 13.7100 | 89 |
134
+ | 5.6002 | 13.7944 | 90 |
135
+ | 5.6341 | 14.4328 | 91 |
136
  | nan | nan | 92 |
137
  | nan | nan | 93 |
138
  | nan | nan | 94 |
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:100954f4c36e511f6721bd24aa7f1fb7b1aadc31d1f3d2c24fe1ce44ba3087df
3
  size 536063536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f102ce019cb6e8265e796ccdf060a86759de7453b0144f1c4f279f0f4e901268
3
  size 536063536