leetdavid commited on
Commit
79e0f51
1 Parent(s): bb6ef27
Files changed (3) hide show
  1. README.md +57 -0
  2. config.json +43 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: celera_relevance
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
+ # celera_relevance
14
+
15
+ This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.3072
18
+ - Train Sparse Categorical Accuracy: 0.8813
19
+ - Validation Loss: 0.4371
20
+ - Validation Sparse Categorical Accuracy: 0.8295
21
+ - Epoch: 2
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', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
41
+ - training_precision: float32
42
+
43
+ ### Training results
44
+
45
+ | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
+ |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
+ | 0.4060 | 0.8274 | 0.3665 | 0.8440 | 0 |
48
+ | 0.3388 | 0.8594 | 0.3639 | 0.8585 | 1 |
49
+ | 0.3072 | 0.8813 | 0.4371 | 0.8295 | 2 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.16.0
55
+ - TensorFlow 2.7.0
56
+ - Datasets 1.18.1
57
+ - Tokenizers 0.11.0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-roberta-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "pooler_fc_size": 768,
34
+ "pooler_num_attention_heads": 12,
35
+ "pooler_num_fc_layers": 3,
36
+ "pooler_size_per_head": 128,
37
+ "pooler_type": "first_token_transform",
38
+ "position_embedding_type": "absolute",
39
+ "transformers_version": "4.16.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53ac5a060f6638f8bb0238ec4118725b02b36e5bf7860eb602d75e9258d3661
3
+ size 409367900