Training in progress epoch 0
Browse files- README.md +4 -82
- tf_model.h5 +1 -1
- 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:
|
17 |
-
- Validation Loss:
|
18 |
-
- Epoch:
|
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 |
-
|
|
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:
|
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
|
|