Training in progress epoch 0
Browse files
README.md
CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
- Validation Loss: 0.
|
19 |
-
- Train
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,23 +36,19 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- 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':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
-
| Train Loss | Validation Loss | Train
|
45 |
-
|
46 |
-
| 0.
|
47 |
-
| 0.2531 | 0.3534 | 0.6921 | 1 |
|
48 |
-
| 0.1756 | 0.3472 | 0.7141 | 2 |
|
49 |
-
| 0.1030 | 0.4079 | 0.6920 | 3 |
|
50 |
-
| 0.0644 | 0.4228 | 0.6855 | 4 |
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.35.2
|
56 |
- TensorFlow 2.15.0
|
57 |
-
- Datasets 2.
|
58 |
- Tokenizers 0.15.0
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.4618
|
18 |
+
- Validation Loss: 0.3742
|
19 |
+
- Train F1: 0.7700
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- 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': 627, '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}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
+
| Train Loss | Validation Loss | Train F1 | Epoch |
|
45 |
+
|:----------:|:---------------:|:--------:|:-----:|
|
46 |
+
| 0.4618 | 0.3742 | 0.7700 | 0 |
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.35.2
|
52 |
- TensorFlow 2.15.0
|
53 |
+
- Datasets 2.16.1
|
54 |
- Tokenizers 0.15.0
|
logs/train/events.out.tfevents.1704312409.9e5a43f02215.207.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b4b61c9673f5df2779047547325abadaf579340ff4e392fe10b4a3c0a3a2ef
|
3 |
+
size 3530117
|
logs/validation/events.out.tfevents.1704312513.9e5a43f02215.207.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e9d38cba2eafea2376c65c3ba005cf26c0feec01cb937d299ccb1c3d47d2f9e
|
3 |
+
size 232
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 451979544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626ed792349c4769121eaaee7433bb27aa4d7ad4b096bed7d13c554cdd3bae93
|
3 |
size 451979544
|