Svetlana0303 commited on
Commit
5c5ba82
·
1 Parent(s): a070cb4

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +73 -0
  2. config.json +30 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: Regression_bert_aug_CustomLoss_3
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Regression_bert_aug_CustomLoss_3
14
+
15
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.1282
18
+ - Train Mae: 0.3851
19
+ - Train Mse: 0.1862
20
+ - Train R2-score: 0.7249
21
+ - Validation Loss: 0.1246
22
+ - Validation Mae: 0.3798
23
+ - Validation Mse: 0.1857
24
+ - Validation R2-score: 0.8337
25
+ - Epoch: 14
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - 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-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
45
+ - training_precision: float32
46
+
47
+ ### Training results
48
+
49
+ | Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
50
+ |:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
51
+ | 0.1451 | 0.4188 | 0.2732 | 0.8063 | 0.0642 | 0.3529 | 0.1994 | 0.8824 | 0 |
52
+ | 0.0567 | 0.3078 | 0.1428 | 0.7511 | 0.0452 | 0.3038 | 0.1257 | 0.8820 | 1 |
53
+ | 0.0380 | 0.2662 | 0.1007 | 0.8889 | 0.0661 | 0.2984 | 0.1442 | 0.8883 | 2 |
54
+ | 0.0363 | 0.2542 | 0.0980 | 0.8034 | 0.0318 | 0.2567 | 0.0978 | 0.9117 | 3 |
55
+ | 0.0279 | 0.2257 | 0.0714 | 0.9002 | 0.0327 | 0.2305 | 0.0793 | 0.8920 | 4 |
56
+ | 0.0241 | 0.2046 | 0.0593 | 0.8695 | 0.0306 | 0.2353 | 0.0813 | 0.9330 | 5 |
57
+ | 0.0230 | 0.1960 | 0.0540 | 0.8762 | 0.0284 | 0.2160 | 0.0710 | 0.9197 | 6 |
58
+ | 0.0223 | 0.1914 | 0.0510 | 0.9366 | 0.0285 | 0.2251 | 0.0791 | 0.9282 | 7 |
59
+ | 0.0223 | 0.1923 | 0.0516 | 0.9498 | 0.0306 | 0.2042 | 0.0748 | 0.9309 | 8 |
60
+ | 0.0231 | 0.1827 | 0.0493 | 0.8516 | 0.0302 | 0.2009 | 0.0682 | 0.9198 | 9 |
61
+ | 0.0335 | 0.1794 | 0.0576 | 0.9259 | 0.0765 | 0.3684 | 0.2192 | 0.8243 | 10 |
62
+ | 0.1380 | 0.3960 | 0.2567 | 0.8748 | 0.1037 | 0.4172 | 0.2244 | 0.6992 | 11 |
63
+ | 0.1078 | 0.4071 | 0.2170 | 0.8256 | 0.1219 | 0.4020 | 0.2234 | 0.7304 | 12 |
64
+ | 0.1217 | 0.3807 | 0.2060 | 0.8084 | 0.1434 | 0.3934 | 0.2113 | 0.8317 | 13 |
65
+ | 0.1282 | 0.3851 | 0.1862 | 0.7249 | 0.1246 | 0.3798 | 0.1857 | 0.8337 | 14 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.28.1
71
+ - TensorFlow 2.12.0
72
+ - Datasets 2.12.0
73
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "transformers_version": "4.28.1",
29
+ "vocab_size": 30522
30
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f4c43412aaac94f1bcd41b5f1069829ff2acc45dee9cafdff8984673be675e
3
+ size 267952072