ukzash1 commited on
Commit
5d74857
1 Parent(s): 81ebdd8

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +47 -88
  2. config.json +33 -25
README.md CHANGED
@@ -1,88 +1,47 @@
1
- ---
2
- license: apache-2.0
3
- base_model: bert-base-cased
4
- tags:
5
- - generated_from_keras_callback
6
- model-index:
7
- - name: ukzash1/bert_fineTuned
8
- results:
9
- - task:
10
- type: sequence-classification
11
- dataset:
12
- name: glue
13
- type: cola
14
- metrics:
15
- - name: Validation Accuracy
16
- type: Accuracy
17
- value: 0.8207
18
- source:
19
- name: Hugging Face Model Hub
20
- url: https://huggingface.co/ukzash1/bert_fineTuned
21
- widget:
22
- - text: I liked this movie
23
- output:
24
- - label: Acceptable
25
- score: 0.8
26
- - label: Not Acceptable
27
- score: 0.2
28
- - text: This not is bad
29
- output:
30
- - label: Acceptable
31
- score: 0.2
32
- - label: Not Acceptable
33
- score: 0.8
34
- library_name: transformers
35
- language:
36
- - en
37
- metrics:
38
- - accuracy
39
- pipeline_tag: text-classification
40
- ---
41
-
42
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
43
- probably proofread and complete it, then remove this comment. -->
44
-
45
- # ukzash1/bert_fineTuned
46
-
47
- This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
48
- It achieves the following results on the evaluation set:
49
- - Train Loss: 0.3426
50
- - Train Accuracy: 0.8555
51
- - Validation Loss: 0.4083
52
- - Validation Accuracy: 0.8198
53
- - Epoch: 1
54
-
55
- ## Model description
56
-
57
- More information needed
58
-
59
- ## Intended uses & limitations
60
-
61
- More information needed
62
-
63
- ## Training and evaluation data
64
-
65
- More information needed
66
-
67
- ## Training procedure
68
-
69
- ### Training hyperparameters
70
-
71
- The following hyperparameters were used during training:
72
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
73
- - training_precision: float32
74
-
75
- ### Training results
76
-
77
- | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
78
- |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
79
- | 0.5409 | 0.7317 | 0.5398 | 0.7756 | 0 |
80
- | 0.3426 | 0.8555 | 0.4083 | 0.8198 | 1 |
81
-
82
-
83
- ### Framework versions
84
-
85
- - Transformers 4.38.2
86
- - TensorFlow 2.13.0
87
- - Datasets 2.20.0
88
- - Tokenizers 0.15.2
 
1
+ ---
2
+ tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: bert_fineTuned
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
+ # bert_fineTuned
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
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
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 4.38.2
45
+ - TensorFlow 2.13.0
46
+ - Datasets 2.16.0
47
+ - Tokenizers 0.15.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,25 +1,33 @@
1
- {
2
- "_name_or_path": "bert-base-cased",
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "transformers_version": "4.38.2",
22
- "type_vocab_size": 2,
23
- "use_cache": true,
24
- "vocab_size": 28996
25
- }
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "path/to/save/updated-model",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Acceptable",
14
+ "1": "Not Acceptable"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Acceptable": 0,
20
+ "Not Acceptable": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
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": 28996
33
+ }