avuhong commited on
Commit
9fb74dc
1 Parent(s): 868132d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -21,8 +21,14 @@ To load tokenizer from ESM, you need to install transformers with this version a
21
  !git clone -b add_esm-proper --single-branch https://github.com/liujas000/transformers.git
22
  !pip -q install ./transformers
23
 
24
- This model is a fine-tuned version of [facebook/esm-1b](https://huggingface.co/facebook/esm-1b) on an unknown dataset.
25
- It achieves the following results on the evaluation set:
 
 
 
 
 
 
26
  - Loss: 0.2250
27
  - Accuracy: 0.9620
28
  - F1: 0.9632
 
21
  !git clone -b add_esm-proper --single-branch https://github.com/liujas000/transformers.git
22
  !pip -q install ./transformers
23
 
24
+ This model is a fine-tuned version of [facebook/esm-1b](https://huggingface.co/facebook/esm-1b) on AAV2 dataset with ~230k sequences (Bryant et al 2020).
25
+
26
+ The WT sequence (aa561-588): D E E E I R T T N P V A T E Q Y G S V S T N L Q R G N R
27
+ Maximum length: 50
28
+
29
+ It achieves the following results on the evaluation set.
30
+ Note:this is result of the last epoch, I think the pushed model is loaded with best checkpoint - best val_loss, I'm not so sure though :/
31
+
32
  - Loss: 0.2250
33
  - Accuracy: 0.9620
34
  - F1: 0.9632