Commit
·
272e624
1
Parent(s):
4f1522a
Upload TFFlaubertForSequenceClassification
Browse files- README.md +3 -13
- config.json +1 -1
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
-
base_model: flaubert/flaubert_base_cased
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,12 +11,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# complexity_80_model
|
15 |
|
16 |
-
This model
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
|
19 |
-
- Validation Loss: 0.1550
|
20 |
-
- Train Accuracy: 0.9328
|
21 |
-
- Epoch: 2
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,16 +32,11 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer:
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
-
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
-
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
| 0.1899 | 0.1728 | 0.9235 | 0 |
|
48 |
-
| 0.1619 | 0.1627 | 0.9315 | 1 |
|
49 |
-
| 0.1458 | 0.1550 | 0.9328 | 2 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
model-index:
|
|
|
11 |
|
12 |
# complexity_80_model
|
13 |
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- optimizer: None
|
36 |
- training_precision: float32
|
37 |
|
38 |
### Training results
|
39 |
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
|
42 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"amp": 1,
|
4 |
"architectures": [
|
5 |
"FlaubertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "complexity_80_model",
|
3 |
"amp": 1,
|
4 |
"architectures": [
|
5 |
"FlaubertForSequenceClassification"
|