Hugging Face's logo

sekarmulyani
/
indobertweet-ulasan-beauty-products

Text Classification
Transformers
PyTorch
Indonesian
bert
rating classification
e-commerce
Inference Endpoints
Model card Files Community
9
sekarmulyani commited on
Commit
0e5db68
•
1 Parent(s): 79c9d6a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -35,16 +35,16 @@ The final output of this model, although holding substantial potential to enhanc
35
  ## Training Data (WIP)
36
  <small><em>This model is from Epoch 6 Checkpoint</em></small>
37
 
38
- | Epoch | Training Loss | Validation Loss | F1 | Roc Auc | Accuracy |
39
- |-------|---------------|-----------------|----------|----------|----------|
40
- | 1 | 0.371500 | 0.368949 | 0.412707 | 0.630868 | 0.304636 |
41
- | 2 | 0.349400 | 0.368781 | 0.457155 | 0.653646 | 0.366337 |
42
- | 3 | 0.322000 | 0.379917 | 0.488654 | 0.673030 | 0.422530 |
43
- | 4 | 0.286300 | 0.412161 | 0.495117 | 0.679087 | 0.448102 |
44
- | 5 | 0.248400 | 0.451065 | 0.488383 | 0.676833 | 0.455970 |
45
- | 6 | <strong>0.213400</strong> | <strong>0.496999</strong> | <strong>0.494043</strong> | <strong>0.680316</strong> | <strong>0.462986</strong> |
46
- | 7 | 0.179300 | 0.540976 | 0.489517 | 0.677931 | 0.461609 |
47
- | 8 | 0.156000 | 0.599047 | 0.486695 | 0.677005 | 0.464297 |
48
 
49
  <small>Note: The lower accuracy might be attributed to the presence of reviewer bias in the testing dataset.</small>
50
 
 
35
  ## Training Data (WIP)
36
  <small><em>This model is from Epoch 6 Checkpoint</em></small>
37
 
38
+ | **Epoch** | **Training Loss** | **Validation Loss** | **F1** | **Roc Auc** | **Validation Acc** | **Test Acc** |
39
+ |----------|-------------------|---------------------|-----------|------------|-------------------|--------------|
40
+ | 1 | 0.374800 | 0.374789 | 0.438253 | 0.643794 | 0.344436 | 51.56% |
41
+ **| 2 | 0.346300 | 0.367311 | 0.469088 | 0.660424 | 0.384696 | 52.22% |**
42
+ | 3 | 0.311500 | 0.386395 | 0.480959 | 0.669563 | 0.423579 | 51.25% |
43
+ | 4 | 0.261800 | 0.431841 | 0.496517 | 0.680931 | 0.458986 | 51.27% |
44
+ | 5 | 0.222300 | 0.478353 | 0.495308 | 0.681398 | 0.468297 | 50.43% |
45
+ | 6 | 0.198800 | 0.536330 | 0.496174 | 0.682431 | 0.473149 | 50.69% |
46
+ | 7 | 0.166200 | 0.608345 | 0.492919 | 0.680791 | 0.472166 | 49.78% |
47
+ | 8 | 0.142400 | 0.651709 | 0.496586 | 0.683545 | 0.480428 | 50.07% |
48
 
49
  <small>Note: The lower accuracy might be attributed to the presence of reviewer bias in the testing dataset.</small>
50