Hugging Face's logo

amanneo
/
mail-generator-mini-v2

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Model card Files
xet
 Community
amanneo commited on
Commit
04fc875
·
1 Parent(s): 35a420a

End of training

Browse files
Files changed (2) hide show
  1. README.md +104 -5
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 2.5928
17
- - Train Accuracy: 0.0171
18
- - Validation Loss: 5.5430
19
- - Validation Accuracy: 0.0048
20
- - Epoch: 0
21
 
22
  ## Model description
23
 
@@ -44,6 +44,105 @@ The following hyperparameters were used during training:
44
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
45
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
46
  | 2.5928 | 0.0171 | 5.5430 | 0.0048 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 0.5212
17
+ - Train Accuracy: 0.0027
18
+ - Validation Loss: 5.5781
19
+ - Validation Accuracy: 0.0
20
+ - Epoch: 99
21
 
22
  ## Model description
23
 
 
44
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
45
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
46
  | 2.5928 | 0.0171 | 5.5430 | 0.0048 | 0 |
47
+ | 2.6003 | 0.0207 | 5.5430 | 0.0048 | 1 |
48
+ | 2.5954 | 0.0171 | 5.5508 | 0.0048 | 2 |
49
+ | 2.5775 | 0.0190 | 5.5508 | 0.0024 | 3 |
50
+ | 2.5758 | 0.0231 | 5.5508 | 0.0024 | 4 |
51
+ | 2.5742 | 0.0207 | 5.5586 | 0.0048 | 5 |
52
+ | 2.5547 | 0.0209 | 5.5586 | 0.0048 | 6 |
53
+ | 2.5566 | 0.0188 | 5.5586 | 0.0048 | 7 |
54
+ | 2.5391 | 0.0193 | 5.5586 | 0.0048 | 8 |
55
+ | 2.5378 | 0.0215 | 5.5508 | 0.0048 | 9 |
56
+ | 2.5238 | 0.0188 | 5.5469 | 0.0048 | 10 |
57
+ | 2.5150 | 0.0160 | 5.5508 | 0.0048 | 11 |
58
+ | 2.4967 | 0.0174 | 5.5508 | 0.0071 | 12 |
59
+ | 2.4691 | 0.0193 | 5.5430 | 0.0071 | 13 |
60
+ | 2.4626 | 0.0163 | 5.5430 | 0.0071 | 14 |
61
+ | 2.4417 | 0.0231 | 5.5352 | 0.0048 | 15 |
62
+ | 2.4323 | 0.0215 | 5.5352 | 0.0048 | 16 |
63
+ | 2.4193 | 0.0226 | 5.5469 | 0.0048 | 17 |
64
+ | 2.4170 | 0.0185 | 5.5469 | 0.0048 | 18 |
65
+ | 2.3743 | 0.0193 | 5.5312 | 0.0048 | 19 |
66
+ | 2.3730 | 0.0207 | 5.5312 | 0.0048 | 20 |
67
+ | 2.3535 | 0.0198 | 5.5312 | 0.0048 | 21 |
68
+ | 2.3372 | 0.0182 | 5.5312 | 0.0071 | 22 |
69
+ | 2.3324 | 0.0177 | 5.5312 | 0.0048 | 23 |
70
+ | 2.3011 | 0.0204 | 5.5195 | 0.0048 | 24 |
71
+ | 2.2650 | 0.0212 | 5.5117 | 0.0048 | 25 |
72
+ | 2.2568 | 0.0198 | 5.5078 | 0.0048 | 26 |
73
+ | 2.2331 | 0.0196 | 5.5156 | 0.0048 | 27 |
74
+ | 2.2021 | 0.0193 | 5.5078 | 0.0048 | 28 |
75
+ | 2.1807 | 0.0204 | 5.5039 | 0.0048 | 29 |
76
+ | 2.1691 | 0.0190 | 5.5 | 0.0 | 30 |
77
+ | 2.1463 | 0.0174 | 5.4766 | 0.0 | 31 |
78
+ | 2.1097 | 0.0196 | 5.4844 | 0.0 | 32 |
79
+ | 2.1014 | 0.0179 | 5.4844 | 0.0024 | 33 |
80
+ | 2.0833 | 0.0177 | 5.4844 | 0.0024 | 34 |
81
+ | 2.0423 | 0.0201 | 5.4844 | 0.0 | 35 |
82
+ | 2.0163 | 0.0198 | 5.4844 | 0.0 | 36 |
83
+ | 1.9909 | 0.0168 | 5.4883 | 0.0 | 37 |
84
+ | 1.9774 | 0.0207 | 5.4805 | 0.0 | 38 |
85
+ | 1.9414 | 0.0207 | 5.4844 | 0.0 | 39 |
86
+ | 1.9206 | 0.0215 | 5.4766 | 0.0 | 40 |
87
+ | 1.8849 | 0.0182 | 5.4805 | 0.0 | 41 |
88
+ | 1.8732 | 0.0193 | 5.4648 | 0.0 | 42 |
89
+ | 1.8460 | 0.0160 | 5.4609 | 0.0 | 43 |
90
+ | 1.8171 | 0.0168 | 5.4648 | 0.0 | 44 |
91
+ | 1.7791 | 0.0201 | 5.4531 | 0.0 | 45 |
92
+ | 1.7583 | 0.0158 | 5.4570 | 0.0 | 46 |
93
+ | 1.7360 | 0.0171 | 5.4570 | 0.0 | 47 |
94
+ | 1.7061 | 0.0120 | 5.4297 | 0.0 | 48 |
95
+ | 1.6802 | 0.0155 | 5.4258 | 0.0 | 49 |
96
+ | 1.6551 | 0.0182 | 5.4141 | 0.0 | 50 |
97
+ | 1.6289 | 0.0130 | 5.4219 | 0.0 | 51 |
98
+ | 1.5981 | 0.0130 | 5.3945 | 0.0 | 52 |
99
+ | 1.5656 | 0.0128 | 5.4297 | 0.0 | 53 |
100
+ | 1.5535 | 0.0168 | 5.4219 | 0.0 | 54 |
101
+ | 1.5184 | 0.0141 | 5.4102 | 0.0 | 55 |
102
+ | 1.4943 | 0.0149 | 5.4023 | 0.0 | 56 |
103
+ | 1.4616 | 0.0122 | 5.4062 | 0.0 | 57 |
104
+ | 1.4344 | 0.0111 | 5.4062 | 0.0 | 58 |
105
+ | 1.3965 | 0.0111 | 5.4141 | 0.0 | 59 |
106
+ | 1.3643 | 0.0122 | 5.4375 | 0.0 | 60 |
107
+ | 1.3309 | 0.0087 | 5.4453 | 0.0 | 61 |
108
+ | 1.3215 | 0.0090 | 5.4648 | 0.0 | 62 |
109
+ | 1.3058 | 0.0084 | 5.4727 | 0.0 | 63 |
110
+ | 1.2700 | 0.0109 | 5.4453 | 0.0 | 64 |
111
+ | 1.2396 | 0.0079 | 5.4609 | 0.0 | 65 |
112
+ | 1.2189 | 0.0092 | 5.4375 | 0.0 | 66 |
113
+ | 1.1855 | 0.0079 | 5.4375 | 0.0 | 67 |
114
+ | 1.1592 | 0.0073 | 5.4375 | 0.0 | 68 |
115
+ | 1.1219 | 0.0071 | 5.4648 | 0.0 | 69 |
116
+ | 1.1071 | 0.0065 | 5.4570 | 0.0 | 70 |
117
+ | 1.0848 | 0.0060 | 5.4375 | 0.0 | 71 |
118
+ | 1.0581 | 0.0076 | 5.4453 | 0.0 | 72 |
119
+ | 1.0316 | 0.0090 | 5.4570 | 0.0 | 73 |
120
+ | 1.0068 | 0.0063 | 5.4219 | 0.0 | 74 |
121
+ | 0.9832 | 0.0060 | 5.4570 | 0.0 | 75 |
122
+ | 0.9534 | 0.0046 | 5.4570 | 0.0 | 76 |
123
+ | 0.9378 | 0.0057 | 5.4648 | 0.0 | 77 |
124
+ | 0.9170 | 0.0033 | 5.4844 | 0.0 | 78 |
125
+ | 0.8941 | 0.0041 | 5.4883 | 0.0 | 79 |
126
+ | 0.8666 | 0.0030 | 5.4922 | 0.0 | 80 |
127
+ | 0.8419 | 0.0054 | 5.4375 | 0.0 | 81 |
128
+ | 0.8200 | 0.0035 | 5.4492 | 0.0 | 82 |
129
+ | 0.8020 | 0.0022 | 5.4648 | 0.0 | 83 |
130
+ | 0.7785 | 0.0057 | 5.4883 | 0.0 | 84 |
131
+ | 0.7607 | 0.0052 | 5.4648 | 0.0 | 85 |
132
+ | 0.7454 | 0.0041 | 5.5078 | 0.0 | 86 |
133
+ | 0.7208 | 0.0024 | 5.5078 | 0.0 | 87 |
134
+ | 0.7040 | 0.0027 | 5.5078 | 0.0 | 88 |
135
+ | 0.6799 | 0.0041 | 5.5156 | 0.0 | 89 |
136
+ | 0.6594 | 0.0030 | 5.5312 | 0.0 | 90 |
137
+ | 0.6397 | 0.0030 | 5.5312 | 0.0 | 91 |
138
+ | 0.6217 | 0.0030 | 5.5195 | 0.0 | 92 |
139
+ | 0.6112 | 0.0033 | 5.5195 | 0.0 | 93 |
140
+ | 0.5937 | 0.0046 | 5.5625 | 0.0 | 94 |
141
+ | 0.5745 | 0.0035 | 5.5625 | 0.0 | 95 |
142
+ | 0.5616 | 0.0027 | 5.5586 | 0.0 | 96 |
143
+ | 0.5468 | 0.0043 | 5.5742 | 0.0 | 97 |
144
+ | 0.5354 | 0.0027 | 5.5781 | 0.0 | 98 |
145
+ | 0.5212 | 0.0027 | 5.5781 | 0.0 | 99 |
146
 
147
 
148
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2615973d922e453e083596c559b8a617c20342e8f26faaf2ef4874af4ea874c5
3
  size 497935464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d038975b4445b7d039b07a89dd03b9a47b0e07090291e8a410e9562873aeda
3
  size 497935464