Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
Llama Recipes
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
mirrored_repos
MachineLearning
meta-llama
Llama Recipes
Commits
f1d90d0f
Commit
f1d90d0f
authored
10 months ago
by
Kai Wu
Browse files
Options
Downloads
Patches
Plain Diff
fix wandb config update
parent
98c0284a
No related branches found
Branches containing commit
No related tags found
Tags containing commit
No related merge requests found
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
docs/multi_gpu.md
+1
-1
1 addition, 1 deletion
docs/multi_gpu.md
docs/single_gpu.md
+1
-1
1 addition, 1 deletion
docs/single_gpu.md
src/llama_recipes/finetuning.py
+3
-2
3 additions, 2 deletions
src/llama_recipes/finetuning.py
with
5 additions
and
4 deletions
docs/multi_gpu.md
+
1
−
1
View file @
f1d90d0f
...
...
@@ -34,7 +34,7 @@ The args used in the command above are:
*
`--use_peft`
boolean flag to enable PEFT methods in the script
*
`--peft_method`
to specify the PEFT method, here we use
`lora`
other options are
`llama_adapter`
,
`prefix`
.
*
`--peft_method`
to specify the PEFT method, here we use
`lora`
other options are
`llama_adapter`
.
We use
`torchrun`
here to spawn multiple processes for FSDP.
...
...
This diff is collapsed.
Click to expand it.
docs/single_gpu.md
+
1
−
1
View file @
f1d90d0f
...
...
@@ -27,7 +27,7 @@ The args used in the command above are:
*
`--use_peft`
boolean flag to enable PEFT methods in the script
*
`--peft_method`
to specify the PEFT method, here we use
`lora`
other options are
`llama_adapter`
,
`prefix`
.
*
`--peft_method`
to specify the PEFT method, here we use
`lora`
other options are
`llama_adapter`
.
*
`--quantization`
boolean flag to enable int8 quantization
...
...
This diff is collapsed.
Click to expand it.
src/llama_recipes/finetuning.py
+
3
−
2
View file @
f1d90d0f
...
...
@@ -154,12 +154,13 @@ def main(**kwargs):
# Load the pre-trained peft model checkpoint and setup its configuration
if
train_config
.
from_peft_checkpoint
:
model
=
PeftModel
.
from_pretrained
(
model
,
train_config
.
from_peft_checkpoint
,
is_trainable
=
True
)
peft_config
=
model
.
peft_config
()
# Generate the peft config and start fine-tuning from original model
else
:
peft_config
=
generate_peft_config
(
train_config
,
kwargs
)
model
=
get_peft_model
(
model
,
peft_config
)
if
wandb_run
:
wandb_run
.
config
.
update
(
peft_config
)
if
wandb_run
:
wandb_run
.
config
.
update
(
peft_config
)
model
.
print_trainable_parameters
()
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment