Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Sign in / Register
Toggle navigation
B
Basedformer
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Packages
Packages
List
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issues
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
novelai-storage
Basedformer
Commits
aa35ad92
Commit
aa35ad92
authored
Jul 14, 2022
by
Wes Brown
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Small fixes.
parent
8b26deda
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
hypertrain.py
hypertrain.py
+3
-3
No files found.
hypertrain.py
View file @
aa35ad92
...
...
@@ -214,7 +214,7 @@ parser.add_argument('--optimizer', type=str, help='the optimizer to use',
parser
.
add_argument
(
'--lr'
,
type
=
float
,
help
=
'learning rate'
,
default
=
2e-4
)
parser
.
add_argument
(
'--end_lr'
,
type
=
float
,
help
=
'end learning rate'
,
default
=
2e-4
)
parser
.
add_argument
(
'--warmup'
,
type
=
int
,
help
=
'warmup steps'
)
parser
.
add_argument
(
'--warmup'
,
type
=
int
,
help
=
'warmup steps'
,
default
=
10
)
parser
.
add_argument
(
'--bs'
,
type
=
int
,
help
=
'batch size'
,
default
=
4
)
parser
.
add_argument
(
'--gas'
,
type
=
int
,
help
=
'gas'
,
default
=
1
)
parser
.
add_argument
(
'--seed'
,
type
=
int
,
help
=
"Random seed value"
,
...
...
@@ -247,7 +247,7 @@ if args.output == '':
# we need 250 batch size to train the small GPT.
train_config
=
{
"data_path"
:
args
.
dataset
,
"save_path"
:
args
.
model
,
"save_path"
:
args
.
output
,
"lm_path"
:
args
.
model
,
"optimizer"
:
args
.
optimizer
,
"masked_softmax_fusion"
:
args
.
masked
,
...
...
@@ -259,7 +259,7 @@ train_config = {
"bs"
:
args
.
bs
,
"gas"
:
args
.
gas
,
"seed"
:
args
.
seed
,
"save_every"
:
args
.
save_steps
0
,
"save_every"
:
args
.
save_steps
,
"amp"
:
args
.
amp
,
"loss_scale"
:
args
.
loss_scale
,
"eval_every"
:
args
.
eval_every
,
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment