borough-oblast
commited on
Commit
•
6f8c091
1
Parent(s):
8a30a56
Training in progress epoch 0
Browse files- README.md +5 -7
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-2
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-v4
|
15 |
|
16 |
-
This model
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss: 2.
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
@@ -36,14 +34,14 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
model-index:
|
|
|
11 |
|
12 |
# borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-v4
|
13 |
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 1.9530
|
17 |
+
- Validation Loss: 2.7814
|
18 |
- Epoch: 0
|
19 |
|
20 |
## Model description
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 123673, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
38 |
- training_precision: float32
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
+
| 1.9530 | 2.7814 | 0 |
|
45 |
|
46 |
|
47 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForMaskedLM"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "borough-oblast/distilbert-base-multilingual-cased-finetuned-en-de-v4",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForMaskedLM"
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 910749348
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3d07fec51e1b1442d0457fe9598a72e4d84cfdba001c5a2d44c828073b9854
|
3 |
size 910749348
|