helling100 commited on
Commit
5e02a78
·
1 Parent(s): e179248

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +68 -0
  2. config.json +24 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: Regression_albert_5
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_albert_5
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: 0.1814
18
+ - Train Mae: 0.2938
19
+ - Train Mse: 0.1429
20
+ - Train Accuracy: 0.6500
21
+ - Validation Loss: 0.1964
22
+ - Validation Mae: 0.3819
23
+ - Validation Mse: 0.1952
24
+ - Validation Accuracy: 0.5811
25
+ - Epoch: 9
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': 2e-06, '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 Accuracy | Validation Loss | Validation Mae | Validation Mse | Validation Accuracy | Epoch |
50
+ |:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
51
+ | 1.1449 | 0.5862 | 0.4388 | 0.5115 | 0.3923 | 0.5808 | 0.3920 | 0.3243 | 0 |
52
+ | 0.3044 | 0.3674 | 0.2078 | 0.5654 | 0.2169 | 0.4102 | 0.2158 | 0.3243 | 1 |
53
+ | 0.1775 | 0.2928 | 0.1414 | 0.6923 | 0.1833 | 0.3691 | 0.1819 | 0.6351 | 2 |
54
+ | 0.1832 | 0.2879 | 0.1347 | 0.7269 | 0.1846 | 0.3672 | 0.1833 | 0.6486 | 3 |
55
+ | 0.1642 | 0.2894 | 0.1411 | 0.7038 | 0.1930 | 0.3802 | 0.1917 | 0.3919 | 4 |
56
+ | 0.1657 | 0.2888 | 0.1386 | 0.6615 | 0.1856 | 0.3711 | 0.1843 | 0.6081 | 5 |
57
+ | 0.1787 | 0.2922 | 0.1425 | 0.6731 | 0.1960 | 0.3854 | 0.1947 | 0.4865 | 6 |
58
+ | 0.1896 | 0.2842 | 0.1335 | 0.7231 | 0.1788 | 0.3646 | 0.1774 | 0.6351 | 7 |
59
+ | 0.1712 | 0.2949 | 0.1465 | 0.6308 | 0.1876 | 0.3728 | 0.1863 | 0.5811 | 8 |
60
+ | 0.1814 | 0.2938 | 0.1429 | 0.6500 | 0.1964 | 0.3819 | 0.1952 | 0.5811 | 9 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.27.2
66
+ - TensorFlow 2.11.0
67
+ - Datasets 2.10.1
68
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "regression",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "transformers_version": "4.27.2",
23
+ "vocab_size": 30522
24
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6b2d9c094263fae89f3c8b904c17241e097a2ccb2dffa69197276e0229d973
3
+ size 267951808