czigopis commited on
Commit
befd11f
1 Parent(s): 5a75701

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: 0.2119
18
- - Train Accuracy: 0.9163
19
- - Validation Loss: 0.3329
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': 2e-05, 'decay_steps': 10035, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
- |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
- | 0.4348 | 0.8062 | 0.3133 | 0.8772 | 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 4.35.2
55
  - TensorFlow 2.15.0
56
- - Datasets 2.16.1
57
- - 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: 0.5400
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": "4.35.2",
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 sha256:35972633d9238f7f9fa0b6ec2fc8e99aa743caa682e8988ca73c43cebb880ec4
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,