Training in progress epoch 0
Browse files
README.md
CHANGED
@@ -14,11 +14,9 @@ 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 |
-
-
|
19 |
-
-
|
20 |
-
- Validation Accuracy: 0.8720
|
21 |
-
- Epoch: 2
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,21 +35,19 @@ 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':
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
-
| Train Loss |
|
46 |
-
|
47 |
-
| 0.
|
48 |
-
| 0.2975 | 0.8837 | 0.3372 | 0.8668 | 1 |
|
49 |
-
| 0.2119 | 0.9163 | 0.3329 | 0.8720 | 2 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
-
- Transformers 4.
|
55 |
- TensorFlow 2.15.0
|
56 |
-
- Datasets 2.
|
57 |
-
- Tokenizers 0.15.
|
|
|
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: 0.5400
|
18 |
+
- Validation Loss: 0.3599
|
19 |
+
- Epoch: 0
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- 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': 5e-05, 'decay_steps': 3922, '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}
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 0.5400 | 0.3599 | 0 |
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.38.2
|
51 |
- TensorFlow 2.15.0
|
52 |
+
- Datasets 2.18.0
|
53 |
+
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -26,7 +26,7 @@
|
|
26 |
"output_past": true,
|
27 |
"pad_token_id": 0,
|
28 |
"position_embedding_type": "absolute",
|
29 |
-
"transformers_version": "4.
|
30 |
"type_vocab_size": 2,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 35000
|
|
|
26 |
"output_past": true,
|
27 |
"pad_token_id": 0,
|
28 |
"position_embedding_type": "absolute",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
"type_vocab_size": 2,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 35000
|
logs/train/events.out.tfevents.1713376673.635f15221149.1216.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe8812570a4498f4ea8419767523e3a1afa41b2cbcd05fcb0b9e68aefcb83f3
|
3 |
+
size 3541055
|
logs/validation/events.out.tfevents.1713376802.635f15221149.1216.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:765f7bb435af9a24968381c6337bfed9d8a02386dde672a6896509e2bd005670
|
3 |
+
size 231
|
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 sha256:604e9a448499de45326700a83f1f8a420a058bb743884f5db536e514f346a603
|
3 |
size 451979544
|
tokenizer.json
CHANGED
@@ -1,14 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
5 |
-
"strategy": "BatchLongest",
|
6 |
-
"direction": "Right",
|
7 |
-
"pad_to_multiple_of": null,
|
8 |
-
"pad_id": 0,
|
9 |
-
"pad_type_id": 0,
|
10 |
-
"pad_token": "[PAD]"
|
11 |
-
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|