dipesh commited on
Commit
f658530
·
1 Parent(s): e95ec9f
Files changed (3) hide show
  1. README.md +13 -3
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - generated_from_keras_callback
4
  model-index:
@@ -11,9 +12,13 @@ probably proofread and complete it, then remove this comment. -->
11
 
12
  # Intent-Classification-Bert-Base-Cased
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
 
@@ -32,11 +37,16 @@ More information needed
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
 
1
  ---
2
+ license: apache-2.0
3
  tags:
4
  - generated_from_keras_callback
5
  model-index:
 
12
 
13
  # Intent-Classification-Bert-Base-Cased
14
 
15
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.6110
18
+ - Train Sparse Categorical Accuracy: 0.9836
19
+ - Validation Loss: 0.4073
20
+ - Validation Sparse Categorical Accuracy: 0.9583
21
+ - Epoch: 2
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
+ | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
+ |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
+ | 2.5420 | 0.3224 | 1.9997 | 0.6806 | 0 |
48
+ | 1.4238 | 0.8684 | 0.9106 | 0.9444 | 1 |
49
+ | 0.6110 | 0.9836 | 0.4073 | 0.9583 | 2 |
50
 
51
 
52
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/drive/MyDrive/JarvisAI-Intent-Classification/models/bert-base-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4511f45997975c799cf063143f63a1f0e6ec78195acdc69205f2993f9ef95f98
3
  size 433587612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a77ce0152d8d03255371add6c7932e72559963b8f8c0034fce5395e9ba2a64
3
  size 433587612