Hugging Face's logo

pradeep4321
/
model2

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Model card Files
xet
Community
pradeep4321 commited on
Commit
0e0c5dd
·
1 Parent(s): ff5a3c5

Upload model

Browse files
Files changed (2) hide show
  1. README.md +103 -53
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 3.5158
18
- - Validation Loss: 6.4256
19
- - Epoch: 49
20
 
21
  ## Model description
22
 
@@ -42,56 +42,106 @@ The following hyperparameters were used during training:
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 7.2465 | 7.5143 | 0 |
46
- | 7.1890 | 7.4800 | 1 |
47
- | 7.1104 | 7.4496 | 2 |
48
- | 7.0491 | 7.4218 | 3 |
49
- | 7.0064 | 7.3964 | 4 |
50
- | 6.9428 | 7.3732 | 5 |
51
- | 6.9061 | 7.3505 | 6 |
52
- | 6.8538 | 7.3301 | 7 |
53
- | 6.7857 | 7.3108 | 8 |
54
- | 6.7253 | 7.2893 | 9 |
55
- | 6.6743 | 7.2693 | 10 |
56
- | 6.5944 | 7.2491 | 11 |
57
- | 6.5499 | 7.2288 | 12 |
58
- | 6.4767 | 7.2084 | 13 |
59
- | 6.4145 | 7.1887 | 14 |
60
- | 6.3713 | 7.1664 | 15 |
61
- | 6.2863 | 7.1450 | 16 |
62
- | 6.2017 | 7.1229 | 17 |
63
- | 6.1524 | 7.1017 | 18 |
64
- | 6.0841 | 7.0788 | 19 |
65
- | 5.9643 | 7.0540 | 20 |
66
- | 5.9225 | 7.0365 | 21 |
67
- | 5.8569 | 7.0151 | 22 |
68
- | 5.7639 | 6.9941 | 23 |
69
- | 5.6801 | 6.9732 | 24 |
70
- | 5.5930 | 6.9537 | 25 |
71
- | 5.5279 | 6.9410 | 26 |
72
- | 5.4268 | 6.9139 | 27 |
73
- | 5.3621 | 6.8950 | 28 |
74
- | 5.2726 | 6.8795 | 29 |
75
- | 5.1767 | 6.8652 | 30 |
76
- | 5.0694 | 6.8448 | 31 |
77
- | 4.9900 | 6.8524 | 32 |
78
- | 4.8658 | 6.8038 | 33 |
79
- | 4.7845 | 6.8157 | 34 |
80
- | 4.7204 | 6.7753 | 35 |
81
- | 4.6609 | 6.7670 | 36 |
82
- | 4.5092 | 6.7305 | 37 |
83
- | 4.4266 | 6.7136 | 38 |
84
- | 4.3334 | 6.6761 | 39 |
85
- | 4.1928 | 6.6554 | 40 |
86
- | 4.1157 | 6.6311 | 41 |
87
- | 4.0755 | 6.6162 | 42 |
88
- | 4.0072 | 6.5830 | 43 |
89
- | 3.8881 | 6.5423 | 44 |
90
- | 3.7678 | 6.5271 | 45 |
91
- | 3.6915 | 6.4925 | 46 |
92
- | 3.6772 | 6.4618 | 47 |
93
- | 3.5962 | 6.4445 | 48 |
94
- | 3.5158 | 6.4256 | 49 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
 
96
 
97
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.7652
18
+ - Validation Loss: 5.5941
19
+ - Epoch: 99
20
 
21
  ## Model description
22
 
 
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 3.4440 | 6.3917 | 0 |
46
+ | 3.4011 | 6.3744 | 1 |
47
+ | 3.3080 | 6.3398 | 2 |
48
+ | 3.1988 | 6.3392 | 3 |
49
+ | 3.1543 | 6.2950 | 4 |
50
+ | 3.1246 | 6.2795 | 5 |
51
+ | 3.0182 | 6.2569 | 6 |
52
+ | 2.9706 | 6.2238 | 7 |
53
+ | 2.9353 | 6.2055 | 8 |
54
+ | 2.8828 | 6.1995 | 9 |
55
+ | 2.8187 | 6.1703 | 10 |
56
+ | 2.8116 | 6.1570 | 11 |
57
+ | 2.7118 | 6.1329 | 12 |
58
+ | 2.6847 | 6.1232 | 13 |
59
+ | 2.5602 | 6.1206 | 14 |
60
+ | 2.5477 | 6.0860 | 15 |
61
+ | 2.5032 | 6.0694 | 16 |
62
+ | 2.4366 | 6.0671 | 17 |
63
+ | 2.4570 | 6.0441 | 18 |
64
+ | 2.3515 | 6.0281 | 19 |
65
+ | 2.3095 | 6.0236 | 20 |
66
+ | 2.2707 | 6.0046 | 21 |
67
+ | 2.2307 | 6.0047 | 22 |
68
+ | 2.2420 | 5.9822 | 23 |
69
+ | 2.1877 | 5.9821 | 24 |
70
+ | 2.1529 | 5.9695 | 25 |
71
+ | 2.1017 | 5.9491 | 26 |
72
+ | 2.0531 | 5.9321 | 27 |
73
+ | 2.0368 | 5.9264 | 28 |
74
+ | 1.9904 | 5.8998 | 29 |
75
+ | 1.9361 | 5.8969 | 30 |
76
+ | 1.8996 | 5.8903 | 31 |
77
+ | 1.8659 | 5.8584 | 32 |
78
+ | 1.8632 | 5.8600 | 33 |
79
+ | 1.8212 | 5.8541 | 34 |
80
+ | 1.7985 | 5.8355 | 35 |
81
+ | 1.7606 | 5.8375 | 36 |
82
+ | 1.7477 | 5.8386 | 37 |
83
+ | 1.7227 | 5.8048 | 38 |
84
+ | 1.6932 | 5.7964 | 39 |
85
+ | 1.6661 | 5.8007 | 40 |
86
+ | 1.6619 | 5.7988 | 41 |
87
+ | 1.5900 | 5.7883 | 42 |
88
+ | 1.5415 | 5.7777 | 43 |
89
+ | 1.5588 | 5.7713 | 44 |
90
+ | 1.5399 | 5.7631 | 45 |
91
+ | 1.5140 | 5.7631 | 46 |
92
+ | 1.4937 | 5.7553 | 47 |
93
+ | 1.5147 | 5.7406 | 48 |
94
+ | 1.4266 | 5.7349 | 49 |
95
+ | 1.4252 | 5.7405 | 50 |
96
+ | 1.3933 | 5.7348 | 51 |
97
+ | 1.4023 | 5.7215 | 52 |
98
+ | 1.3401 | 5.7227 | 53 |
99
+ | 1.3143 | 5.7167 | 54 |
100
+ | 1.3144 | 5.7003 | 55 |
101
+ | 1.2713 | 5.7020 | 56 |
102
+ | 1.2799 | 5.7082 | 57 |
103
+ | 1.2838 | 5.6978 | 58 |
104
+ | 1.2470 | 5.6985 | 59 |
105
+ | 1.2221 | 5.7085 | 60 |
106
+ | 1.2011 | 5.6839 | 61 |
107
+ | 1.1714 | 5.6601 | 62 |
108
+ | 1.2091 | 5.6667 | 63 |
109
+ | 1.1699 | 5.6733 | 64 |
110
+ | 1.1445 | 5.6703 | 65 |
111
+ | 1.1000 | 5.6558 | 66 |
112
+ | 1.1695 | 5.6495 | 67 |
113
+ | 1.0887 | 5.6600 | 68 |
114
+ | 1.0687 | 5.6746 | 69 |
115
+ | 1.0707 | 5.6642 | 70 |
116
+ | 1.0540 | 5.6388 | 71 |
117
+ | 1.0631 | 5.6357 | 72 |
118
+ | 1.0715 | 5.6466 | 73 |
119
+ | 1.0207 | 5.6451 | 74 |
120
+ | 1.0022 | 5.6403 | 75 |
121
+ | 1.0054 | 5.6351 | 76 |
122
+ | 0.9940 | 5.6329 | 77 |
123
+ | 0.9626 | 5.6395 | 78 |
124
+ | 0.9546 | 5.6376 | 79 |
125
+ | 0.9911 | 5.6295 | 80 |
126
+ | 0.9299 | 5.6289 | 81 |
127
+ | 0.9670 | 5.6176 | 82 |
128
+ | 0.9488 | 5.6055 | 83 |
129
+ | 0.9189 | 5.6171 | 84 |
130
+ | 0.9037 | 5.6366 | 85 |
131
+ | 0.8709 | 5.6191 | 86 |
132
+ | 0.8831 | 5.6023 | 87 |
133
+ | 0.8548 | 5.6089 | 88 |
134
+ | 0.8604 | 5.6212 | 89 |
135
+ | 0.8613 | 5.6210 | 90 |
136
+ | 0.8719 | 5.6093 | 91 |
137
+ | 0.8374 | 5.6026 | 92 |
138
+ | 0.8557 | 5.5959 | 93 |
139
+ | 0.8125 | 5.5987 | 94 |
140
+ | 0.7930 | 5.6022 | 95 |
141
+ | 0.7937 | 5.6002 | 96 |
142
+ | 0.8035 | 5.5926 | 97 |
143
+ | 0.7795 | 5.5938 | 98 |
144
+ | 0.7652 | 5.5941 | 99 |
145
 
146
 
147
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d8278d8ee76028d8f565047ab81a0118c7c37838be4fbf5f08c94d519b6276
3
  size 351244368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972e095d63574cd92abe582465c0eb354bccce299f9c2c59813e838309f6bda9
3
  size 351244368