Training in progress epoch 6
Browse files- README.md +7 -6
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,13 +15,13 @@ 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 |
-
- Train End Logits Accuracy: 0.
|
20 |
-
- Train Start Logits Accuracy: 0.
|
21 |
-
- Validation Loss: 0.
|
22 |
- Validation End Logits Accuracy: 0.8938
|
23 |
-
- Validation Start Logits Accuracy: 0.
|
24 |
-
- Epoch:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -53,6 +53,7 @@ The following hyperparameters were used during training:
|
|
53 |
| 0.2854 | 0.9039 | 0.9096 | 0.4773 | 0.8813 | 0.8810 | 3 |
|
54 |
| 0.2145 | 0.9269 | 0.9287 | 0.4887 | 0.8732 | 0.8820 | 4 |
|
55 |
| 0.1669 | 0.9436 | 0.9462 | 0.4637 | 0.8938 | 0.8925 | 5 |
|
|
|
56 |
|
57 |
|
58 |
### 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: 0.1300
|
19 |
+
- Train End Logits Accuracy: 0.9522
|
20 |
+
- Train Start Logits Accuracy: 0.9563
|
21 |
+
- Validation Loss: 0.5295
|
22 |
- Validation End Logits Accuracy: 0.8938
|
23 |
+
- Validation Start Logits Accuracy: 0.8960
|
24 |
+
- Epoch: 6
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
53 |
| 0.2854 | 0.9039 | 0.9096 | 0.4773 | 0.8813 | 0.8810 | 3 |
|
54 |
| 0.2145 | 0.9269 | 0.9287 | 0.4887 | 0.8732 | 0.8820 | 4 |
|
55 |
| 0.1669 | 0.9436 | 0.9462 | 0.4637 | 0.8938 | 0.8925 | 5 |
|
56 |
+
| 0.1300 | 0.9522 | 0.9563 | 0.5295 | 0.8938 | 0.8960 | 6 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265583592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c67394b9820693b33b4448f46949f452b51323af6ae9a9058ce88196ee3480
|
3 |
size 265583592
|