projects
/
beaver.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
e29aed4
)
Update
author
François Fleuret
<francois@fleuret.org>
Fri, 7 Apr 2023 17:12:20 +0000
(19:12 +0200)
committer
François Fleuret
<francois@fleuret.org>
Fri, 7 Apr 2023 17:12:20 +0000
(19:12 +0200)
README.txt
patch
|
blob
|
history
diff --git
a/README.txt
b/README.txt
index
f25211f
..
1bd713a
100644
(file)
--- a/
README.txt
+++ b/
README.txt
@@
-1,8
+1,17
@@
-To train the shortest-path solving GPT, and train the one-shot MLP
-read-out:
+To train the shortest-path solving GPT
- ./beaver.py
--oneshot
+ ./beaver.py
Same, lighter settings (~95% test success instead of ~99%):
Same, lighter settings (~95% test success instead of ~99%):
- ./beaver.py --nb_train_samples=25000 --nb_test_samples=10000 --oneshot
+ ./beaver.py --nb_train_samples=25000 --nb_test_samples=10000
+
+To train with a non-causal attention on the prompt + random
+auto-regression order:
+
+ ./beaver.py --nb_epochs=50 --learning_rate_schedule='25: 2e-4' --random_regression_order --noncausal_prompt
+
+to get the one-shot prediction from an existing checkpoint (trained
+with --random_regression_order and --noncausal_prompt):
+
+ ./beaver --oneshot