Commit
•
d23dfbd
1
Parent(s):
c5ae0eb
Training in progress epoch 0
Browse files- README.md +4 -4
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -12,10 +12,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# robingeibel/roBERTa-base-finetuned-big_patent
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 1.
|
18 |
-
- Validation Loss: 1.
|
19 |
- Epoch: 0
|
20 |
|
21 |
## Model description
|
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
| 1.
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
12 |
|
13 |
# robingeibel/roBERTa-base-finetuned-big_patent
|
14 |
|
15 |
+
This model is a fine-tuned version of [robingeibel/roBERTa-base-finetuned-big_patent](https://huggingface.co/robingeibel/roBERTa-base-finetuned-big_patent) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 1.1827
|
18 |
+
- Validation Loss: 1.0542
|
19 |
- Epoch: 0
|
20 |
|
21 |
## Model description
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 1.1827 | 1.0542 | 0 |
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "robingeibel/roBERTa-base-finetuned-big_patent",
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 655071244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ac752c84945c00b53d6a59eb614b165bafa8c7fb8230a0952d14a9c92ddf1a6
|
3 |
size 655071244
|