Upload TFBertForSequenceClassification
Browse files- README.md +7 -7
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss: 0.
|
| 18 |
-
- Train Accuracy: 0.
|
| 19 |
-
- Validation Loss: 0.
|
| 20 |
-
- Validation Accuracy: 0.
|
| 21 |
- Epoch: 2
|
| 22 |
|
| 23 |
## Model description
|
|
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
| 46 |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
| 47 |
-
| 0.
|
| 48 |
-
| 0.
|
| 49 |
-
| 0.
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.2546
|
| 18 |
+
- Train Accuracy: 0.9045
|
| 19 |
+
- Validation Loss: 0.4144
|
| 20 |
+
- Validation Accuracy: 0.8437
|
| 21 |
- Epoch: 2
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 44 |
|
| 45 |
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
| 46 |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
| 47 |
+
| 0.3534 | 0.8812 | 0.4083 | 0.8414 | 0 |
|
| 48 |
+
| 0.3215 | 0.8842 | 0.3936 | 0.8483 | 1 |
|
| 49 |
+
| 0.2546 | 0.9045 | 0.4144 | 0.8437 | 2 |
|
| 50 |
|
| 51 |
|
| 52 |
### 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 sha256:612bd5d0ca7c2b077e1a33cc8e4f81351cc572e041bab9163e3f1eb51adbb392
|
| 3 |
size 438223128
|