vedantjumle
commited on
Commit
•
5520fcc
1
Parent(s):
c4b998f
Training in progress epoch 4
Browse files- README.md +6 -4
- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-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 Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -47,6 +47,8 @@ The following hyperparameters were used during training:
|
|
47 |
| 2.3373 | 1.2016 | 0.7546 | 0 |
|
48 |
| 0.8827 | 0.7496 | 0.8309 | 1 |
|
49 |
| 0.5245 | 0.6397 | 0.8462 | 2 |
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.3125
|
19 |
+
- Validation Loss: 0.5946
|
20 |
+
- Train Accuracy: 0.8549
|
21 |
+
- Epoch: 4
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
47 |
| 2.3373 | 1.2016 | 0.7546 | 0 |
|
48 |
| 0.8827 | 0.7496 | 0.8309 | 1 |
|
49 |
| 0.5245 | 0.6397 | 0.8462 | 2 |
|
50 |
+
| 0.3795 | 0.6053 | 0.8518 | 3 |
|
51 |
+
| 0.3125 | 0.5946 | 0.8549 | 4 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268133320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d2c9232dd57ee042fc2c4613f041e2171286988daa439a263cdb14ef6bbb85a
|
3 |
size 268133320
|