Hugging Face's logo

nepp1d0
/
prot_bert_classification_finetuned

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files
xet
Metrics Community
2
nepp1d0 commited on
Commit
04de607
·
1 Parent(s): 7e3157c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [nepp1d0/prot_bert-finetuned-smiles-bindingDB](https://huggingface.co/nepp1d0/prot_bert-finetuned-smiles-bindingDB) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5773
22
- - Accuracy: 0.7275
23
- - F1: 0.7336
24
- - Precision: 0.6979
25
- - Recall: 0.7732
26
 
27
  ## Model description
28
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
- | 0.6271 | 1.0 | 3350 | 0.6222 | 0.6416 | 0.6482 | 0.6189 | 0.6805 |
61
- | 0.5376 | 2.0 | 6700 | 0.5915 | 0.6846 | 0.6920 | 0.6575 | 0.7303 |
62
- | 0.5523 | 3.0 | 10050 | 0.5881 | 0.7047 | 0.7109 | 0.6771 | 0.7483 |
63
- | 0.511 | 4.0 | 13400 | 0.5989 | 0.7128 | 0.7158 | 0.6884 | 0.7455 |
64
- | 0.5487 | 5.0 | 16750 | 0.5890 | 0.7134 | 0.7236 | 0.6800 | 0.7732 |
65
- | 0.5288 | 6.0 | 20100 | 0.5773 | 0.7275 | 0.7336 | 0.6979 | 0.7732 |
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [nepp1d0/prot_bert-finetuned-smiles-bindingDB](https://huggingface.co/nepp1d0/prot_bert-finetuned-smiles-bindingDB) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6797
22
+ - Accuracy: 0.53
23
+ - F1: 0.2540
24
+ - Precision: 0.6154
25
+ - Recall: 0.16
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 0.6902 | 1.0 | 25 | 0.6897 | 0.53 | 0.1455 | 0.8 | 0.08 |
61
+ | 0.6717 | 2.0 | 50 | 0.6867 | 0.54 | 0.1786 | 0.8333 | 0.1 |
62
+ | 0.6803 | 3.0 | 75 | 0.6846 | 0.55 | 0.2373 | 0.7778 | 0.14 |
63
+ | 0.6911 | 4.0 | 100 | 0.6792 | 0.52 | 0.2258 | 0.5833 | 0.14 |
64
+ | 0.6447 | 5.0 | 125 | 0.6799 | 0.53 | 0.2540 | 0.6154 | 0.16 |
65
+ | 0.6287 | 6.0 | 150 | 0.6797 | 0.53 | 0.2540 | 0.6154 | 0.16 |
66
 
67
 
68
  ### Framework versions