felixshier
commited on
Commit
•
1100b5f
1
Parent(s):
307cf02
Upload TFBertForSequenceClassification
Browse files- README.md +9 -9
- config.json +4 -4
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 0.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train F1: 0.
|
21 |
- Epoch: 4
|
22 |
|
23 |
## Model description
|
@@ -37,18 +37,18 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train F1 | Epoch |
|
46 |
|:----------:|:---------------:|:--------:|:-----:|
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.1439
|
19 |
+
- Validation Loss: 0.6405
|
20 |
+
- Train F1: 0.7929
|
21 |
- Epoch: 4
|
22 |
|
23 |
## Model description
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train F1 | Epoch |
|
46 |
|:----------:|:---------------:|:--------:|:-----:|
|
47 |
+
| 0.5683 | 0.4794 | 0.7730 | 0 |
|
48 |
+
| 0.3997 | 0.4386 | 0.8343 | 1 |
|
49 |
+
| 0.2829 | 0.4851 | 0.8106 | 2 |
|
50 |
+
| 0.2183 | 0.5251 | 0.7931 | 3 |
|
51 |
+
| 0.1439 | 0.6405 | 0.7929 | 4 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
config.json
CHANGED
@@ -10,14 +10,14 @@
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
-
"1": "
|
15 |
},
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 3072,
|
18 |
"label2id": {
|
19 |
-
"
|
20 |
-
"
|
21 |
},
|
22 |
"layer_norm_eps": 1e-12,
|
23 |
"max_position_embeddings": 512,
|
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
+
"0": "Other",
|
14 |
+
"1": "Africa"
|
15 |
},
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 3072,
|
18 |
"label2id": {
|
19 |
+
"Africa": 1,
|
20 |
+
"Other": 0
|
21 |
},
|
22 |
"layer_norm_eps": 1e-12,
|
23 |
"max_position_embeddings": 512,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 438223128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56fd8bd71225404e839129c6cc387da8ee97fbc7cc48bd78a06f3a0c0a245423
|
3 |
size 438223128
|