apcl
/

aakashba commited on
Commit
3c62230
·
1 Parent(s): 4c68a42

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -16,6 +16,8 @@ Jam-so is a GPT2-like model for research in fine-grained Java analysis. It is in
16
 
17
  - We train the model on [training set](https://huggingface.co/datasets/apcl/so13m/blob/main/train.bin) for 1 epoch, roughly 300,000 training iterations.
18
 
 
 
19
  | Hyperparameter | Description | Value |
20
  | ----------- | ----------- |------------|
21
  |e | embedding dimensions | 1024 |
@@ -28,7 +30,7 @@ Jam-so is a GPT2-like model for research in fine-grained Java analysis. It is in
28
  |r | learning rate | 3e-5 |
29
  |y | weight decay | 1e-1 |
30
 
31
- We train our models using a single NVidia A5000 GPUs. Our [GitHub repo](https://github.com/apcl-research/jam/blob/main) contains the code for re-training using the [raw data](https://huggingface.co/datasets/apcl/so13m/blob/main/so13m.pkl).
32
 
33
  ---
34
  ## Jam Projects
 
16
 
17
  - We train the model on [training set](https://huggingface.co/datasets/apcl/so13m/blob/main/train.bin) for 1 epoch, roughly 300,000 training iterations.
18
 
19
+ - Our [GitHub repo](https://github.com/apcl-research/jam/blob/main) contains the code for re-training using the [raw data](https://huggingface.co/datasets/apcl/so13m/blob/main/so13m.pkl).
20
+
21
  | Hyperparameter | Description | Value |
22
  | ----------- | ----------- |------------|
23
  |e | embedding dimensions | 1024 |
 
30
  |r | learning rate | 3e-5 |
31
  |y | weight decay | 1e-1 |
32
 
33
+ We train our models using a single NVidia A5000 GPUs.
34
 
35
  ---
36
  ## Jam Projects