gustavokpc commited on
Commit
376fcaa
·
1 Parent(s): 7f49634

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +13 -16
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,17 +15,17 @@ 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: 0.6850
19
- - Train Accuracy: 0.5792
20
- - Train F1 M: 0.0241
21
- - Train Precision M: 0.0340
22
- - Train Recall M: 0.0206
23
- - Validation Loss: 0.6760
24
- - Validation Accuracy: 0.5937
25
- - Validation F1 M: 0.0
26
- - Validation Precision M: 0.0
27
- - Validation Recall M: 0.0
28
- - Epoch: 3
29
 
30
  ## Model description
31
 
@@ -44,17 +44,14 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 36384, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
48
  - training_precision: float32
49
 
50
  ### Training results
51
 
52
  | Train Loss | Train Accuracy | Train F1 M | Train Precision M | Train Recall M | Validation Loss | Validation Accuracy | Validation F1 M | Validation Precision M | Validation Recall M | Epoch |
53
  |:----------:|:--------------:|:----------:|:-----------------:|:--------------:|:---------------:|:-------------------:|:---------------:|:----------------------:|:-------------------:|:-----:|
54
- | 0.6893 | 0.5716 | 0.0775 | 0.0982 | 0.0749 | 0.6911 | 0.5937 | 0.0 | 0.0 | 0.0 | 0 |
55
- | 0.6859 | 0.5751 | 0.0365 | 0.0488 | 0.0328 | 0.6818 | 0.5937 | 0.0 | 0.0 | 0.0 | 1 |
56
- | 0.6827 | 0.5795 | 0.0201 | 0.0302 | 0.0165 | 0.6756 | 0.5937 | 0.0 | 0.0 | 0.0 | 2 |
57
- | 0.6850 | 0.5792 | 0.0241 | 0.0340 | 0.0206 | 0.6760 | 0.5937 | 0.0 | 0.0 | 0.0 | 3 |
58
 
59
 
60
  ### 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: 0.4176
19
+ - Train Accuracy: 0.8080
20
+ - Train F1 M: 0.4543
21
+ - Train Precision M: 0.3667
22
+ - Train Recall M: 0.6857
23
+ - Validation Loss: 0.2600
24
+ - Validation Accuracy: 0.8991
25
+ - Validation F1 M: 0.5567
26
+ - Validation Precision M: 0.4108
27
+ - Validation Recall M: 0.9084
28
+ - Epoch: 0
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2274, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
48
  - training_precision: float32
49
 
50
  ### Training results
51
 
52
  | Train Loss | Train Accuracy | Train F1 M | Train Precision M | Train Recall M | Validation Loss | Validation Accuracy | Validation F1 M | Validation Precision M | Validation Recall M | Epoch |
53
  |:----------:|:--------------:|:----------:|:-----------------:|:--------------:|:---------------:|:-------------------:|:---------------:|:----------------------:|:-------------------:|:-----:|
54
+ | 0.4176 | 0.8080 | 0.4543 | 0.3667 | 0.6857 | 0.2600 | 0.8991 | 0.5567 | 0.4108 | 0.9084 | 0 |
 
 
 
55
 
56
 
57
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab9e57e13d12ebff96202bdd3418e19435a4f3388c34e2eb501968d168b1aa8b
3
  size 1341127728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e7d9ef00411d313f67ee0aaf0424b80c4e371268464fa4afd7a07773eb4319
3
  size 1341127728