Hugging Face's logo

afbudiman
/
distilled-optimized-indobert-classification

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
afbudiman commited on
Commit
d72b74e
·
1 Parent(s): 2e72b5a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -15
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -20,10 +19,10 @@ model-index:
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.8944444444444445
24
  - name: F1
25
  type: f1
26
- value: 0.89395273315396
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the indonlu dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.7098
37
- - Accuracy: 0.8944
38
- - F1: 0.8940
39
 
40
  ## Model description
41
 
@@ -66,15 +65,15 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
69
- | 1.5386 | 1.0 | 688 | 1.0026 | 0.8325 | 0.8332 |
70
- | 0.8165 | 2.0 | 1376 | 0.7364 | 0.8786 | 0.8782 |
71
- | 0.4755 | 3.0 | 2064 | 0.8695 | 0.8794 | 0.8767 |
72
- | 0.3011 | 4.0 | 2752 | 0.8100 | 0.8921 | 0.8899 |
73
- | 0.1963 | 5.0 | 3440 | 0.8074 | 0.8960 | 0.8954 |
74
- | 0.1312 | 6.0 | 4128 | 0.8235 | 0.8897 | 0.8906 |
75
- | 0.0974 | 7.0 | 4816 | 0.7395 | 0.9063 | 0.9067 |
76
- | 0.0716 | 8.0 | 5504 | 0.7185 | 0.8960 | 0.8953 |
77
- | 0.0512 | 9.0 | 6192 | 0.7098 | 0.8944 | 0.8940 |
78
 
79
 
80
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9
23
  - name: F1
24
  type: f1
25
+ value: 0.8994069293432798
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the indonlu dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7397
36
+ - Accuracy: 0.9
37
+ - F1: 0.8994
38
 
39
  ## Model description
40
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
68
+ | 0.128 | 1.0 | 688 | 0.8535 | 0.8913 | 0.8917 |
69
+ | 0.1475 | 2.0 | 1376 | 0.9171 | 0.8913 | 0.8913 |
70
+ | 0.0997 | 3.0 | 2064 | 0.7799 | 0.8960 | 0.8951 |
71
+ | 0.0791 | 4.0 | 2752 | 0.7179 | 0.9032 | 0.9023 |
72
+ | 0.0577 | 5.0 | 3440 | 0.6908 | 0.9063 | 0.9055 |
73
+ | 0.0406 | 6.0 | 4128 | 0.7613 | 0.8992 | 0.8986 |
74
+ | 0.0275 | 7.0 | 4816 | 0.7502 | 0.8992 | 0.8989 |
75
+ | 0.023 | 8.0 | 5504 | 0.7408 | 0.8976 | 0.8969 |
76
+ | 0.0169 | 9.0 | 6192 | 0.7397 | 0.9 | 0.8994 |
77
 
78
 
79
  ### Framework versions