Hugging Face's logo

helling100
/
Regression_bert_1

Text Classification
Transformers
TensorFlow
distilbert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
helling100 commited on
Commit
387208f
·
1 Parent(s): 40ea54f

Upload TFBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +32 -22
  2. config.json +2 -20
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -14,17 +14,17 @@ probably proofread and complete it, then remove this comment. -->
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: 0.5177
18
- - Train Mae: 0.3287
19
- - Train Mse: 0.1635
20
- - Train R2-score: -3.2462
21
- - Train Accuracy: 0.5354
22
- - Validation Loss: 0.1634
23
- - Validation Mae: 0.3519
24
- - Validation Mse: 0.1614
25
- - Validation R2-score: -0.4800
26
- - Validation Accuracy: 0.4459
27
- - Epoch: 9
28
 
29
  ## Model description
30
 
@@ -43,23 +43,33 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - 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': 0.0002, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
47
  - training_precision: float32
48
 
49
  ### Training results
50
 
51
  | Train Loss | Train Mae | Train Mse | Train R2-score | Train Accuracy | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Validation Accuracy | Epoch |
52
  |:----------:|:---------:|:---------:|:--------------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-------------------:|:-----:|
53
- | 0.5954 | 0.3730 | 0.2146 | -3.4803 | 0.4931 | 0.2190 | 0.4056 | 0.2174 | -0.8845 | 0.3622 | 0 |
54
- | 0.8021 | 0.3763 | 0.2082 | -2.7115 | 0.4777 | 0.1827 | 0.3730 | 0.1810 | -0.5508 | 0.3838 | 1 |
55
- | 0.6147 | 0.3404 | 0.1752 | -2.1219 | 0.5223 | 0.2622 | 0.4567 | 0.2613 | -0.9969 | 0.2811 | 2 |
56
- | 0.6303 | 0.3447 | 0.1768 | -2.9520 | 0.5154 | 0.2331 | 0.4248 | 0.2321 | -0.7839 | 0.2811 | 3 |
57
- | 0.3887 | 0.3369 | 0.1734 | -2.7189 | 0.5262 | 0.2114 | 0.4056 | 0.2101 | -0.6812 | 0.2865 | 4 |
58
- | 0.3735 | 0.3176 | 0.1515 | -5.1147 | 0.5292 | 0.1646 | 0.3546 | 0.1630 | -0.3295 | 0.2703 | 5 |
59
- | 0.4549 | 0.3358 | 0.1716 | -1.5835 | 0.5323 | 0.1803 | 0.3670 | 0.1786 | -0.5113 | 0.3108 | 6 |
60
- | 0.5800 | 0.3221 | 0.1587 | -2.4273 | 0.5385 | 0.2369 | 0.4334 | 0.2358 | -0.8347 | 0.2919 | 7 |
61
- | 0.4042 | 0.3339 | 0.1714 | -3.7265 | 0.5300 | 0.1818 | 0.3766 | 0.1804 | -0.4590 | 0.2703 | 8 |
62
- | 0.5177 | 0.3287 | 0.1635 | -3.2462 | 0.5354 | 0.1634 | 0.3519 | 0.1614 | -0.4800 | 0.4459 | 9 |
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
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: 0.2489
18
+ - Train Mae: 0.3355
19
+ - Train Mse: 0.1670
20
+ - Train R2-score: 0.5318
21
+ - Train Accuracy: 0.5
22
+ - Validation Loss: 0.2163
23
+ - Validation Mae: 0.4087
24
+ - Validation Mse: 0.2153
25
+ - Validation R2-score: 0.8371
26
+ - Validation Accuracy: 0.2703
27
+ - Epoch: 19
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - 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': 1e-06, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
47
  - training_precision: float32
48
 
49
  ### Training results
50
 
51
  | Train Loss | Train Mae | Train Mse | Train R2-score | Train Accuracy | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Validation Accuracy | Epoch |
52
  |:----------:|:---------:|:---------:|:--------------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-------------------:|:-----:|
53
+ | 0.2907 | 0.3158 | 0.1575 | 0.6537 | 0.5692 | 0.2087 | 0.3991 | 0.2076 | 0.8421 | 0.2703 | 0 |
54
+ | 0.5109 | 0.3124 | 0.1437 | 0.7067 | 0.5538 | 0.2134 | 0.4051 | 0.2124 | 0.8390 | 0.2703 | 1 |
55
+ | 0.3757 | 0.3131 | 0.1489 | 0.7306 | 0.5538 | 0.2138 | 0.4055 | 0.2127 | 0.8388 | 0.2703 | 2 |
56
+ | 0.5703 | 0.3369 | 0.1733 | 0.6746 | 0.5385 | 0.2097 | 0.4004 | 0.2086 | 0.8414 | 0.2703 | 3 |
57
+ | 0.3149 | 0.3314 | 0.1616 | 0.6958 | 0.5154 | 0.2090 | 0.3995 | 0.2079 | 0.8419 | 0.2703 | 4 |
58
+ | 0.3633 | 0.3331 | 0.1653 | 0.6961 | 0.5154 | 0.2083 | 0.3986 | 0.2072 | 0.8423 | 0.2703 | 5 |
59
+ | 0.2274 | 0.3384 | 0.1795 | 0.6844 | 0.5231 | 0.2075 | 0.3975 | 0.2064 | 0.8429 | 0.2703 | 6 |
60
+ | 0.2552 | 0.3141 | 0.1496 | 0.4397 | 0.5615 | 0.2061 | 0.3957 | 0.2050 | 0.8438 | 0.2703 | 7 |
61
+ | 0.2650 | 0.3459 | 0.1772 | 0.6305 | 0.4615 | 0.2043 | 0.3934 | 0.2032 | 0.8449 | 0.2703 | 8 |
62
+ | 0.3674 | 0.3251 | 0.1647 | 0.6980 | 0.4923 | 0.2086 | 0.3990 | 0.2075 | 0.8421 | 0.2703 | 9 |
63
+ | 0.4815 | 0.3122 | 0.1546 | 0.6067 | 0.5538 | 0.2078 | 0.3979 | 0.2067 | 0.8427 | 0.2703 | 10 |
64
+ | 0.4321 | 0.3446 | 0.1783 | 0.6082 | 0.5308 | 0.2068 | 0.3966 | 0.2056 | 0.8433 | 0.2703 | 11 |
65
+ | 0.3884 | 0.3257 | 0.1637 | 0.6823 | 0.5077 | 0.2038 | 0.3928 | 0.2027 | 0.8452 | 0.2703 | 12 |
66
+ | 0.2694 | 0.3353 | 0.1719 | 0.6679 | 0.5385 | 0.2026 | 0.3912 | 0.2014 | 0.8460 | 0.2703 | 13 |
67
+ | 0.3124 | 0.3223 | 0.1605 | 0.6018 | 0.5231 | 0.2067 | 0.3965 | 0.2055 | 0.8434 | 0.2703 | 14 |
68
+ | 0.3527 | 0.3281 | 0.1645 | 0.5474 | 0.5462 | 0.2088 | 0.3992 | 0.2077 | 0.8420 | 0.2703 | 15 |
69
+ | 0.3506 | 0.3452 | 0.1775 | 0.6449 | 0.5077 | 0.2120 | 0.4032 | 0.2109 | 0.8399 | 0.2703 | 16 |
70
+ | 0.5240 | 0.3363 | 0.1683 | 0.6028 | 0.5077 | 0.2194 | 0.4124 | 0.2183 | 0.8351 | 0.2703 | 17 |
71
+ | 0.2749 | 0.3272 | 0.1678 | 0.6595 | 0.5308 | 0.2191 | 0.4121 | 0.2181 | 0.8352 | 0.2703 | 18 |
72
+ | 0.2489 | 0.3355 | 0.1670 | 0.5318 | 0.5 | 0.2163 | 0.4087 | 0.2153 | 0.8371 | 0.2703 | 19 |
73
 
74
 
75
  ### Framework versions
config.json CHANGED
@@ -10,30 +10,12 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "LABEL_0",
14
- "1": "LABEL_1",
15
- "2": "LABEL_2",
16
- "3": "LABEL_3",
17
- "4": "LABEL_4",
18
- "5": "LABEL_5",
19
- "6": "LABEL_6",
20
- "7": "LABEL_7",
21
- "8": "LABEL_8",
22
- "9": "LABEL_9"
23
  },
24
  "initializer_range": 0.02,
25
  "intermediate_size": 3072,
26
  "label2id": {
27
- "LABEL_0": 0,
28
- "LABEL_1": 1,
29
- "LABEL_2": 2,
30
- "LABEL_3": 3,
31
- "LABEL_4": 4,
32
- "LABEL_5": 5,
33
- "LABEL_6": 6,
34
- "LABEL_7": 7,
35
- "LABEL_8": 8,
36
- "LABEL_9": 9
37
  },
38
  "layer_norm_eps": 1e-12,
39
  "max_position_embeddings": 512,
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
+ "0": "LABEL_0"
 
 
 
 
 
 
 
 
 
14
  },
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
  "label2id": {
18
+ "LABEL_0": 0
 
 
 
 
 
 
 
 
 
19
  },
20
  "layer_norm_eps": 1e-12,
21
  "max_position_embeddings": 512,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e22a4ec42198041fd75037b5d17133f4323ecdc6e32db4ea73cb46e0a0da8de7
3
- size 433559864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52dee4962f46730eb59668a2116ca2319fc2d92e489f7a2e093bc0e13c2fcd32
3
+ size 433532180