Skip to content

Fix the get_info/grad path in README.md #23

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix the get_info/grad path in README.md #23

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ MODEL_PATH=../out/llama2-7b-p0.05-lora-seed3/checkpoint-${CKPT}
OUTPUT_PATH=../grads/llama2-7b-p0.05-lora-seed3/${TRAINING_DATA_NAME}-ckpt${CKPT}-${GRADIENT_TYPE}
DIMS="8192"

./less/scripts/get_info/get_train_lora_grads.sh "$TRAINING_DATA_FILE" "$MODEL_PATH" "$OUTPUT_PATH" "$DIMS" "$GRADIENT_TYPE"
./less/scripts/get_info/grad/get_train_lora_grads.sh "$TRAINING_DATA_FILE" "$MODEL_PATH" "$OUTPUT_PATH" "$DIMS" "$GRADIENT_TYPE"
```
Ideally, you would aim to create a datastore that encompasses a gradient of all the checkpoints and training data from which you wish to choose.

Expand All @@ -82,7 +82,7 @@ OUTPUT_PATH=../grads/llama2-7b-p0.05-lora-seed3/${TASK}-ckpt${CKPT}-sgd # for va
DATA_DIR=../data
DIMS="4096 8192" # We use 8192 as our default projection dimension

./less/scripts/get_info/get_eval_lora_grads.sh "$TASK" "$DATA_DIR" "$MODEL_PATH" $OUTPUT_PATH "$DIMS"
./less/scripts/get_info/grad/get_eval_lora_grads.sh "$TASK" "$DATA_DIR" "$MODEL_PATH" $OUTPUT_PATH "$DIMS"
```
You should gain the gradients of the validation data for all the checkpoints you used for building the gradient datastore in the previous step. After obtaining the gradients for the validation data, we can then select data for the task. The following script will calculate the influence score for each training data point, and select the top-k data points with the highest influence score.

Expand Down