BeardedJohn
commited on
Commit
•
5098599
1
Parent(s):
34efa05
Upload TFBertForTokenClassification
Browse files- README.md +7 -7
- 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 |
# bert-finetuned-ner-per-v2
|
14 |
|
15 |
-
This model is a fine-tuned version of [bert-
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
- Validation Loss: 0.
|
19 |
- Epoch: 2
|
20 |
|
21 |
## Model description
|
@@ -35,16 +35,16 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
39 |
- training_precision: mixed_float16
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
| 0.
|
46 |
-
| 0.
|
47 |
-
| 0.
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
12 |
|
13 |
# bert-finetuned-ner-per-v2
|
14 |
|
15 |
+
This model is a fine-tuned version of [BeardedJohn/bert-finetuned-ner-per-v2](https://huggingface.co/BeardedJohn/bert-finetuned-ner-per-v2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.0005
|
18 |
+
- Validation Loss: 0.0002
|
19 |
- Epoch: 2
|
20 |
|
21 |
## Model description
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 939, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
39 |
- training_precision: mixed_float16
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 0.0202 | 0.0006 | 0 |
|
46 |
+
| 0.0010 | 0.0002 | 1 |
|
47 |
+
| 0.0005 | 0.0002 | 2 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bert-
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "BeardedJohn/bert-finetuned-ner-per-v2",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 431179820
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e90cb5b64104dbec414055417424157a7222885d48cdc0c61b327c2b7a3da44
|
3 |
size 431179820
|