felixshier commited on
Commit
4732857
1 Parent(s): 70e673b

Upload TFBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +58 -0
  2. config.json +33 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: csc-01-bert-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
+ # csc-01-bert-finetuned
15
+
16
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.6165
19
+ - Validation Loss: 0.6875
20
+ - Train Precision: 0.4918
21
+ - Epoch: 3
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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 70, '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 Precision | Epoch |
46
+ |:----------:|:---------------:|:---------------:|:-----:|
47
+ | 0.7154 | 0.6899 | 0.4861 | 0 |
48
+ | 0.6647 | 0.6831 | 0.5088 | 1 |
49
+ | 0.6534 | 0.6986 | 0.4795 | 2 |
50
+ | 0.6165 | 0.6875 | 0.4918 | 3 |
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.31.0
56
+ - TensorFlow 2.13.0
57
+ - Datasets 2.14.4
58
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "neg",
14
+ "1": "pos"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "neg": 0,
20
+ "pos": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "transformers_version": "4.31.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6979707ff7391b2747d39c250a06c3eb49e14f753c34777048f9d61a3119be
3
+ size 438223128