sileod commited on
Commit
d558a5c
1 Parent(s): 6afdd36

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -373,7 +373,7 @@ https://ibm.github.io/model-recycling/
373
 
374
  ### Software and training details
375
 
376
- The model was trained on 600 tasks for 200k steps with a batch size of 384 and a peak learning rate of 2e-5. Training took 12 days on Nvidia A30 24GB gpu.
377
  This is the shared model with the MNLI classifier on top. Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched.
378
 
379
 
 
373
 
374
  ### Software and training details
375
 
376
+ The model was trained on 600 tasks for 200k steps with a batch size of 384 and a peak learning rate of 2e-5. Training took 15 days on Nvidia A30 24GB gpu.
377
  This is the shared model with the MNLI classifier on top. Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched.
378
 
379