Hugging Face's logo

leetdavid
/
market_positivity_model

Text Classification
Transformers
TensorFlow
bert
generated_from_keras_callback
Model card Files
xet
Community
1
leetdavid commited on
Commit
8182c4f
·
1 Parent(s): 9ec28fe

add model

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
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: 0.4546
18
- - Train Sparse Categorical Accuracy: 0.8132
19
- - Validation Loss: 0.5708
20
- - Validation Sparse Categorical Accuracy: 0.7705
21
  - Epoch: 2
22
 
23
  ## Model description
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
- | 0.6264 | 0.7340 | 0.6649 | 0.7134 | 0 |
48
- | 0.5270 | 0.7727 | 0.5472 | 0.7394 | 1 |
49
- | 0.4546 | 0.8132 | 0.5708 | 0.7705 | 2 |
50
 
51
 
52
  ### Framework versions
@@ -54,4 +54,4 @@ The following hyperparameters were used during training:
54
  - Transformers 4.16.2
55
  - TensorFlow 2.8.0
56
  - Datasets 1.18.3
57
- - Tokenizers 0.10.3
 
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: 0.5776
18
+ - Train Sparse Categorical Accuracy: 0.7278
19
+ - Validation Loss: 0.6460
20
+ - Validation Sparse Categorical Accuracy: 0.6859
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
+ | 0.7207 | 0.6394 | 0.6930 | 0.6811 | 0 |
48
+ | 0.6253 | 0.7033 | 0.6549 | 0.6872 | 1 |
49
+ | 0.5776 | 0.7278 | 0.6460 | 0.6859 | 2 |
50
 
51
 
52
  ### Framework versions
 
54
  - Transformers 4.16.2
55
  - TensorFlow 2.8.0
56
  - Datasets 1.18.3
57
+ - Tokenizers 0.11.0
config.json CHANGED
@@ -29,7 +29,7 @@
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,
 
29
  "num_attention_heads": 12,
30
  "num_hidden_layers": 12,
31
  "output_past": true,
32
+ "pad_token_id": 0,
33
  "pooler_fc_size": 768,
34
  "pooler_num_attention_heads": 12,
35
  "pooler_num_fc_layers": 3,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:909e1d480b6e2a00081d0a785f14538f1a8a40ec474d289205eb42b1e48d2d84
3
  size 409367900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a2c50cef3d8d2bdee5c94fdcc3334ce30bfc1b922c71811acb6d252a707fd8
3
  size 409367900