antonioFlavio commited on
Commit
0045d30
1 Parent(s): 706aaf7

Upload TFBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +8 -25
  2. config.json +1 -1
  3. tf_model.h5 +3 -0
README.md CHANGED
@@ -1,24 +1,19 @@
1
  ---
2
- license: mit
3
- base_model: neuralmind/bert-base-portuguese-cased
4
  tags:
5
- - generated_from_trainer
6
- metrics:
7
- - accuracy
8
  model-index:
9
  - name: google-play-sentiment-analysis
10
  results: []
11
  ---
12
 
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
 
16
  # google-play-sentiment-analysis
17
 
18
- This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4174
21
- - Accuracy: 0.5309
22
 
23
  ## Model description
24
 
@@ -37,28 +32,16 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 2.5e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 8
43
- - seed: 42
44
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
- - lr_scheduler_type: linear
46
- - num_epochs: 5
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 1.1052 | 1.0 | 5313 | 1.0804 | 0.5383 |
53
- | 1.0051 | 2.0 | 10626 | 1.0840 | 0.5425 |
54
- | 0.8599 | 3.0 | 15939 | 1.1426 | 0.5398 |
55
- | 0.7222 | 4.0 | 21252 | 1.2653 | 0.5331 |
56
- | 0.615 | 5.0 | 26565 | 1.4174 | 0.5309 |
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.36.1
62
- - Pytorch 2.0.1+cu118
63
  - Datasets 2.15.0
64
  - Tokenizers 0.15.0
 
1
  ---
 
 
2
  tags:
3
+ - generated_from_keras_callback
 
 
4
  model-index:
5
  - name: google-play-sentiment-analysis
6
  results: []
7
  ---
8
 
9
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
+ probably proofread and complete it, then remove this comment. -->
11
 
12
  # google-play-sentiment-analysis
13
 
14
+ This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+
 
17
 
18
  ## Model description
19
 
 
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
+ - optimizer: None
36
+ - training_precision: float32
 
 
 
 
 
37
 
38
  ### Training results
39
 
 
 
 
 
 
 
 
40
 
41
 
42
  ### Framework versions
43
 
44
  - Transformers 4.36.1
45
+ - TensorFlow 2.13.0
46
  - Datasets 2.15.0
47
  - Tokenizers 0.15.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "google-play-sentiment-analysis",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd14b39d9021547921fa231a20e30fb8b5e60628806614f1ca0dab2f5c4f8a0
3
+ size 435995940