# 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](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **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]