vedantjumle
commited on
Commit
•
39c9366
1
Parent(s):
071d652
Training in progress epoch 0
Browse files- README.md +6 -10
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,18 +37,14 @@ 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 Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
| 2.
|
48 |
-
| 0.4091 | 0.1858 | 0.9809 | 1 |
|
49 |
-
| 0.1379 | 0.1273 | 0.9804 | 2 |
|
50 |
-
| 0.0741 | 0.1160 | 0.9791 | 3 |
|
51 |
-
| 0.0491 | 0.1118 | 0.9769 | 4 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.6008
|
19 |
+
- Validation Loss: 0.5869
|
20 |
+
- Train Accuracy: 0.9613
|
21 |
+
- Epoch: 0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
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': 12640, '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 Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 2.6008 | 0.5869 | 0.9613 | 0 |
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout":
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
|
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": 0.2,
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1341734528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb9540b38b56d4a723fc6c8bdffb4a3a3402824ae23ecb894532c06015e0eedb
|
3 |
size 1341734528
|