felixshier
commited on
Commit
•
f6c412c
1
Parent(s):
4732857
Upload TFBertForSequenceClassification
Browse files- README.md +10 -8
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 0.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train Precision: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,10 +44,12 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Precision | Epoch |
|
46 |
|:----------:|:---------------:|:---------------:|:-----:|
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.4789
|
19 |
+
- Validation Loss: 0.7231
|
20 |
+
- Train Precision: 0.6429
|
21 |
+
- Epoch: 5
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Precision | Epoch |
|
46 |
|:----------:|:---------------:|:---------------:|:-----:|
|
47 |
+
| 0.7100 | 0.7421 | 0.0 | 0 |
|
48 |
+
| 0.6764 | 0.6861 | 0.625 | 1 |
|
49 |
+
| 0.6311 | 0.6838 | 0.5862 | 2 |
|
50 |
+
| 0.5909 | 0.7072 | 0.6286 | 3 |
|
51 |
+
| 0.5413 | 0.7504 | 0.6667 | 4 |
|
52 |
+
| 0.4789 | 0.7231 | 0.6429 | 5 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 438223128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e08176875ede3826e9111574898a538b90c50abbb3dbba5a2c172b35ee2d960d
|
3 |
size 438223128
|