Hugging Face's logo

madatnlp
/
ke-t5-scratch

Text2Text Generation
Transformers
TensorFlow
t5
generated_from_keras_callback
Inference Endpoints
text-generation-inference
Model card Files Community
madatnlp commited on
Commit
30d2e11
•
1 Parent(s): e3e8d2b

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +4 -82
  2. tf_model.h5 +1 -1
  3. tokenizer.json +0 -0
README.md CHANGED
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [madatnlp/ke-t5-math-py](https://huggingface.co/madatnlp/ke-t5-math-py) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 0.7822
17
- - Validation Loss: 0.7830
18
- - Epoch: 78
19
 
20
  ## Model description
21
 
@@ -41,85 +41,7 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 8.1521 | 4.7300 | 0 |
45
- | 4.5192 | 3.2568 | 1 |
46
- | 3.4913 | 2.7407 | 2 |
47
- | 2.9793 | 2.3012 | 3 |
48
- | 2.6884 | 2.2078 | 4 |
49
- | 2.4174 | 1.9750 | 5 |
50
- | 2.2986 | 1.8614 | 6 |
51
- | 2.1074 | 1.5899 | 7 |
52
- | 2.0098 | 1.6175 | 8 |
53
- | 1.9521 | 1.6886 | 9 |
54
- | 1.8728 | 1.4932 | 10 |
55
- | 1.7885 | 1.4924 | 11 |
56
- | 1.6926 | 1.5297 | 12 |
57
- | 1.6965 | 1.3357 | 13 |
58
- | 1.6310 | 1.4610 | 14 |
59
- | 1.6144 | 1.3840 | 15 |
60
- | 1.5745 | 1.3763 | 16 |
61
- | 1.5375 | 1.2571 | 17 |
62
- | 1.5061 | 1.2785 | 18 |
63
- | 1.4627 | 1.2533 | 19 |
64
- | 1.4811 | 1.2842 | 20 |
65
- | 1.4139 | 1.1947 | 21 |
66
- | 1.3810 | 1.1776 | 22 |
67
- | 1.3875 | 1.1778 | 23 |
68
- | 1.3648 | 1.1158 | 24 |
69
- | 1.3542 | 1.0514 | 25 |
70
- | 1.3055 | 1.1236 | 26 |
71
- | 1.3064 | 1.0815 | 27 |
72
- | 1.2706 | 1.0877 | 28 |
73
- | 1.2624 | 1.0519 | 29 |
74
- | 1.2626 | 1.0742 | 30 |
75
- | 1.2480 | 1.0478 | 31 |
76
- | 1.2137 | 1.0730 | 32 |
77
- | 1.2224 | 1.0391 | 33 |
78
- | 1.1865 | 0.9326 | 34 |
79
- | 1.1898 | 0.9682 | 35 |
80
- | 1.1624 | 1.0019 | 36 |
81
- | 1.1561 | 1.0398 | 37 |
82
- | 1.1376 | 0.9905 | 38 |
83
- | 1.1346 | 0.9957 | 39 |
84
- | 1.1269 | 1.0249 | 40 |
85
- | 1.1009 | 0.9031 | 41 |
86
- | 1.0933 | 0.9404 | 42 |
87
- | 1.0637 | 0.9948 | 43 |
88
- | 1.0598 | 0.9522 | 44 |
89
- | 1.0699 | 0.8862 | 45 |
90
- | 1.0712 | 0.8994 | 46 |
91
- | 1.0542 | 0.9584 | 47 |
92
- | 1.0199 | 0.9133 | 48 |
93
- | 1.0248 | 0.9043 | 49 |
94
- | 1.0052 | 0.8633 | 50 |
95
- | 0.9896 | 0.9102 | 51 |
96
- | 1.0057 | 0.8636 | 52 |
97
- | 0.9817 | 0.8472 | 53 |
98
- | 0.9668 | 0.8686 | 54 |
99
- | 0.9541 | 0.8884 | 55 |
100
- | 0.9731 | 0.8862 | 56 |
101
- | 0.9364 | 0.8166 | 57 |
102
- | 0.9429 | 0.8448 | 58 |
103
- | 0.9285 | 0.8711 | 59 |
104
- | 0.9222 | 0.8232 | 60 |
105
- | 0.9163 | 0.8039 | 61 |
106
- | 0.8940 | 0.8100 | 62 |
107
- | 0.8967 | 0.8318 | 63 |
108
- | 0.8892 | 0.7802 | 64 |
109
- | 0.8869 | 0.7814 | 65 |
110
- | 0.8683 | 0.7917 | 66 |
111
- | 0.8623 | 0.8259 | 67 |
112
- | 0.8480 | 0.7539 | 68 |
113
- | 0.8441 | 0.8287 | 69 |
114
- | 0.8312 | 0.7945 | 70 |
115
- | 0.8215 | 0.8013 | 71 |
116
- | 0.8289 | 0.7837 | 72 |
117
- | 0.8181 | 0.7744 | 73 |
118
- | 0.8062 | 0.7707 | 74 |
119
- | 0.8025 | 0.7796 | 75 |
120
- | 0.7848 | 0.7748 | 76 |
121
- | 0.7860 | 0.7861 | 77 |
122
- | 0.7822 | 0.7830 | 78 |
123
 
124
 
125
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [madatnlp/ke-t5-math-py](https://huggingface.co/madatnlp/ke-t5-math-py) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 4.2751
17
+ - Validation Loss: 2.1074
18
+ - Epoch: 0
19
 
20
  ## Model description
21
 
 
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 4.2751 | 2.1074 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
 
46
 
47
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8bb7df150dcf3a0b1db2be7c9ccbf65a02e5c4961179dc5a2aa826d9c0b02be
3
  size 831509840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402117b1fe2824d706fc9ec5d07405b0b702793247f5459a03dfdd8f55bbd52d
3
  size 831509840
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff