princetyagi
commited on
Commit
•
e737c8d
1
Parent(s):
d3a6f20
update model card README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the germanquad dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
| 1.
|
53 |
-
|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the germanquad dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.5837
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| No log | 1.0 | 360 | 1.7190 |
|
51 |
+
| 2.7136 | 2.0 | 720 | 1.6624 |
|
52 |
+
| 1.3704 | 3.0 | 1080 | 1.6460 |
|
53 |
+
| 1.3704 | 4.0 | 1440 | 1.9336 |
|
54 |
+
| 0.7467 | 5.0 | 1800 | 2.0047 |
|
55 |
+
| 0.4077 | 6.0 | 2160 | 2.1701 |
|
56 |
+
| 0.2468 | 7.0 | 2520 | 2.3223 |
|
57 |
+
| 0.2468 | 8.0 | 2880 | 2.4638 |
|
58 |
+
| 0.1475 | 9.0 | 3240 | 2.5493 |
|
59 |
+
| 0.1023 | 10.0 | 3600 | 2.5837 |
|
60 |
|
61 |
|
62 |
### Framework versions
|