Model save
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ should 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 |
-
- Loss: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,28 +44,36 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| No log | 1.0 |
|
48 |
-
| No log | 2.0 |
|
49 |
-
| No log | 3.0 |
|
50 |
-
| No log | 4.0 |
|
51 |
-
| No log | 5.0 |
|
52 |
-
| No log | 6.0 |
|
53 |
-
| No log | 7.0 |
|
54 |
-
| No log | 8.0 |
|
55 |
-
| No log | 9.0 |
|
56 |
-
| No log | 10.0 |
|
57 |
-
| No log | 11.0 |
|
58 |
-
| No log | 12.0 |
|
59 |
-
| No log | 13.0 |
|
60 |
-
| No log | 14.0 |
|
61 |
-
| No log | 15.0 |
|
62 |
-
| No log | 16.0 |
|
63 |
-
| No log | 17.0 |
|
64 |
-
| No log | 18.0 |
|
65 |
-
| No log | 19.0 |
|
66 |
-
| No log | 20.0 |
|
67 |
-
| No log | 21.0 |
|
68 |
-
| No log | 22.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### 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 |
+
- Loss: 0.2981
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 6 | 1.2395 |
|
48 |
+
| No log | 2.0 | 12 | 1.0996 |
|
49 |
+
| No log | 3.0 | 18 | 0.9962 |
|
50 |
+
| No log | 4.0 | 24 | 0.8884 |
|
51 |
+
| No log | 5.0 | 30 | 0.8230 |
|
52 |
+
| No log | 6.0 | 36 | 0.7659 |
|
53 |
+
| No log | 7.0 | 42 | 0.7012 |
|
54 |
+
| No log | 8.0 | 48 | 0.6511 |
|
55 |
+
| No log | 9.0 | 54 | 0.6197 |
|
56 |
+
| No log | 10.0 | 60 | 0.5812 |
|
57 |
+
| No log | 11.0 | 66 | 0.5467 |
|
58 |
+
| No log | 12.0 | 72 | 0.5068 |
|
59 |
+
| No log | 13.0 | 78 | 0.4874 |
|
60 |
+
| No log | 14.0 | 84 | 0.4649 |
|
61 |
+
| No log | 15.0 | 90 | 0.4498 |
|
62 |
+
| No log | 16.0 | 96 | 0.4297 |
|
63 |
+
| No log | 17.0 | 102 | 0.4009 |
|
64 |
+
| No log | 18.0 | 108 | 0.3867 |
|
65 |
+
| No log | 19.0 | 114 | 0.3814 |
|
66 |
+
| No log | 20.0 | 120 | 0.3634 |
|
67 |
+
| No log | 21.0 | 126 | 0.3476 |
|
68 |
+
| No log | 22.0 | 132 | 0.3386 |
|
69 |
+
| No log | 23.0 | 138 | 0.3316 |
|
70 |
+
| No log | 24.0 | 144 | 0.3207 |
|
71 |
+
| No log | 25.0 | 150 | 0.3140 |
|
72 |
+
| No log | 26.0 | 156 | 0.3073 |
|
73 |
+
| No log | 27.0 | 162 | 0.3028 |
|
74 |
+
| No log | 28.0 | 168 | 0.3011 |
|
75 |
+
| No log | 29.0 | 174 | 0.2986 |
|
76 |
+
| No log | 30.0 | 180 | 0.2981 |
|
77 |
|
78 |
|
79 |
### Framework versions
|