felixshier commited on
Commit
9b25b76
1 Parent(s): 6e0e1d4

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +64 -0
  2. config.json +31 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: oc-01-distilbert-finetuned
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # oc-01-distilbert-finetuned
15
+
16
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0061
19
+ - Validation Loss: 0.4666
20
+ - Train Recall: 0.9070
21
+ - Epoch: 9
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6140, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
+ - training_precision: float32
42
+
43
+ ### Training results
44
+
45
+ | Train Loss | Validation Loss | Train Recall | Epoch |
46
+ |:----------:|:---------------:|:------------:|:-----:|
47
+ | 0.3386 | 0.2557 | 0.8915 | 0 |
48
+ | 0.1989 | 0.2661 | 0.9283 | 1 |
49
+ | 0.1097 | 0.2809 | 0.9244 | 2 |
50
+ | 0.0716 | 0.3101 | 0.9244 | 3 |
51
+ | 0.0310 | 0.4023 | 0.8721 | 4 |
52
+ | 0.0288 | 0.4877 | 0.9535 | 5 |
53
+ | 0.0155 | 0.3834 | 0.9109 | 6 |
54
+ | 0.0105 | 0.4263 | 0.9012 | 7 |
55
+ | 0.0095 | 0.4746 | 0.9070 | 8 |
56
+ | 0.0061 | 0.4666 | 0.9070 | 9 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.31.0
62
+ - TensorFlow 2.13.0
63
+ - Datasets 2.14.4
64
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "0",
13
+ "1": "1"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "0": 0,
18
+ "1": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "transformers_version": "4.31.0",
30
+ "vocab_size": 30522
31
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf94de4104e119f8390c969af5abd34c6e7ff9c115ab1fe3461798036a825b4
3
+ size 267955144