Commit
·
5da4c09
1
Parent(s):
00058dd
Upload TFEsmForSequenceClassification
Browse files- README.md +6 -6
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [facebook/esm2_t12_35M_UR50D](https://huggingface.co/facebook/esm2_t12_35M_UR50D) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Train Loss: 0.
|
17 |
- Train Accuracy: 0.9647
|
18 |
-
- Validation Loss: 0.
|
19 |
-
- Validation Accuracy: 0.
|
20 |
- Epoch: 2
|
21 |
|
22 |
## Model description
|
@@ -43,9 +43,9 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
45 |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
46 |
-
| 0.
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
|
50 |
|
51 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [facebook/esm2_t12_35M_UR50D](https://huggingface.co/facebook/esm2_t12_35M_UR50D) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.0987
|
17 |
- Train Accuracy: 0.9647
|
18 |
+
- Validation Loss: 0.1547
|
19 |
+
- Validation Accuracy: 0.9504
|
20 |
- Epoch: 2
|
21 |
|
22 |
## Model description
|
|
|
43 |
|
44 |
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
45 |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
46 |
+
| 0.2361 | 0.9250 | 0.1592 | 0.9504 | 0 |
|
47 |
+
| 0.1393 | 0.9534 | 0.1941 | 0.9417 | 1 |
|
48 |
+
| 0.0987 | 0.9647 | 0.1547 | 0.9504 | 2 |
|
49 |
|
50 |
|
51 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134306840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:325f8b18d5d52634ccf14398e981f4a0b2e4d23b47d8d742a8b051b23dca95f3
|
3 |
size 134306840
|