Model Card for Model ID
#!/bin/bash
#SBATCH --job-name="fintune"
#SBATCH --partition=ghx4
#SBATCH --nodes=1
#SBATCH --gpus-per-node=4
#SBATCH --tasks=1
#SBATCH --tasks-per-node=1
#SBATCH --cpus-per-task=20
#SBATCH --mem=512g
#SBATCH --time=23:59:00
#SBATCH --output="run.log"
#SBATCH --error="run.err"
set -e
export WANDB_API_KEY='1b2611814911cad498235f1ccb1a2e182638bd62'
# set up exp1 or exp3!!!!!
# launch this script after bilevel weighting and preparing data
# this script is for exp1 and exp3
# 1. finetune on bilevel and baseline
CUDA_VISIBLE=0,1,2,3
hf_ds=pxyyy/rlhflow_mixture_clean_empty_round_with_dart-math_scalebiosampled-600k
hf_val_ds=pxyyy/rlhflow_scalbio_test
model_and_tok=meta-llama/Meta-Llama-3-8B
conv_template=llama3
hf_ds_str=$(echo ${hf_ds}|sed 's/\//-/g')
tmp_data_dir=./tmp_data/${hf_ds_str}/
val_data_dir=./tmp_data/${hf_ds_str}_val/
mkdir -p ${tmp_data_dir}
mkdir -p ${val_data_dir}
python3 hf2lmflow.py --ds_name ${hf_ds} --save ${tmp_data_dir}/data.json
python3 hf2lmflow.py --ds_name ${hf_val_ds} --save ${val_data_dir}/data.json
model_str=$(echo ${model_and_tok}|sed 's/\//-/g')
lisa_activated_layers=2
lisa_interval_steps=20
gradient_accumulation_steps=2
per_device_train_batch_size=8
epoch=1
project_dir=/u/xpan2/projects/scalebio/finetune/
for lr in 2e-5
do
# Finetune
exp_id=scalebio-scalebio-${model_str}-${hf_ds_str}-${epoch}-$lr-lisa_${lisa_activated_layers}_${lisa_interval_steps}
# project_dir=$(cd "$(dirname $0)"; pwd)
log_dir=${project_dir}/log/${exp_id}
output_dir=${project_dir}/output_models/${exp_id}
echo $exp_id
mkdir -p ${output_dir} ${log_dir}
export TRANSFORMERS_VERBOSITY=info
deepspeed --master_port=7964 --include=localhost:${CUDA_VISIBLE} finetune.py \
--model_name_or_path ${model_and_tok} \
--trust_remote_code 1 \
--dataset_path ${tmp_data_dir}/ \
--eval_dataset_path ${val_data_dir}/ \
--output_dir ${output_dir} --overwrite_output_dir \
--conversation_template ${conv_template} \
--num_train_epochs $epoch \
--learning_rate $lr \
--disable_group_texts 1 \
--block_size 1024 \
--per_device_train_batch_size ${per_device_train_batch_size} \
--per_device_eval_batch_size 1 \
--bf16 \
--deepspeed configs/ds_config_zero2_no_offload.json \
--torch_dtype bfloat16 \
--run_name ${exp_id} \
--optim adamw_torch_fused \
--logging_steps 1 \
--do_train \
--do_eval \
--ddp_timeout 72000 \
--save_total_limit 1 \
--load_best_model_at_end False \
--eval_steps 10 \
--save_only_model \
--evaluation_strategy "steps" \
--dataloader_num_workers 1 \
--lr_scheduler_type cosine \
--warmup_ratio 0.03 \
--gradient_checkpointing True \
--use_flash_attention 1 \
--gradient_accumulation_steps ${gradient_accumulation_steps} \
--lisa_activated_layers ${lisa_activated_layers} \
--lisa_interval_steps ${lisa_interval_steps} \
| tee ${log_dir}/train.log \
2> ${log_dir}/train.err
done
no lisa
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]