Inquiry regarding the feasibility of fine-tuning LLaMA2-7B with a single A100 about openrlhf HOT 4 CLOSED

[2023-12-01 05:53:04,949] [INFO] [comm.py:662:init_distributed] Distributed backend already initialized
[2023-12-01 05:53:15,433] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
[2023-12-01 05:53:15,436] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer
[2023-12-01 05:53:15,436] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer
[2023-12-01 05:53:15,453] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = DeepSpeedCPUAdam
[2023-12-01 05:53:15,453] [INFO] [utils.py:56:is_zero_supported_optimizer] Checking ZeRO support for optimizer=DeepSpeedCPUAdam type=<class 'deepspeed.ops.adam.cpu_adam.DeepSpeedCPUAdam'>
[2023-12-01 05:53:15,453] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.bfloat16 ZeRO stage 2 optimizer
[2023-12-01 05:53:15,453] [INFO] [stage_1_and_2.py:146:__init__] Reduce bucket size 500,000,000
[2023-12-01 05:53:15,453] [INFO] [stage_1_and_2.py:147:__init__] Allgather bucket size 500,000,000
[2023-12-01 05:53:15,453] [INFO] [stage_1_and_2.py:148:__init__] CPU Offload: True
[2023-12-01 05:53:15,453] [INFO] [stage_1_and_2.py:149:__init__] Round robin gradient partitioning: False
[2023-12-01 05:53:49,783] [INFO] [utils.py:802:see_memory_usage] Before initializing optimizer states
[2023-12-01 05:53:49,784] [INFO] [utils.py:803:see_memory_usage] MA 12.86 GB         Max_MA 12.86 GB         CA 12.86 GB         Max_CA 13 GB
[2023-12-01 05:53:49,784] [INFO] [utils.py:810:see_memory_usage] CPU Virtual Memory:  used = 52.58 GB, percent = 41.9%
[2023-12-01 05:54:12,066] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 2440
[2023-12-01 05:54:12,099] [ERROR] [launch.py:321:sigkill_handler] ['/usr/bin/python', '-u', '../train_sft.py', '--local_rank=0', '--max_len', '200', '--dataset', 'OpenOrca', '--dataset_probs', '1.0', '--train_batch_size', '50', '--micro_train_batch_size', '1', '--max_samples', '500', '--pretrain', 'Llama-2-7b-hf', '--save_path', './ckpt/7b_llama', '--save_steps', '-1', '--logging_steps', '1', '--eval_steps', '-1', '--ckpt_path', './ckpt/7b_llama/checkpoints_sft', '--zero_stage', '2', '--max_epochs', '1', '--bf16', '--flash_attn', '--learning_rate', '5e-6', '--adam_offload', '--gradient_checkpointing'] exits with return code = -9

set -x

read -r -d '' training_commands <<EOF
../train_sft.py \
    --max_len 200 \
    --dataset OpenOrca \
    --dataset_probs 1.0 \
    --train_batch_size 50 \
    --micro_train_batch_size 1 \
    --max_samples 500 \
    --pretrain Llama-2-7b-hf \
    --save_path ./ckpt/7b_llama \
    --save_steps -1 \
    --logging_steps 1 \
    --eval_steps -1 \
    --ckpt_path ./ckpt/7b_llama/checkpoints_sft \
    --zero_stage 2 \
    --max_epochs 1 \
    --bf16 \
    --flash_attn \
    --learning_rate 5e-6 \
    --adam_offload \
    --gradient_checkpointing
EOF
    # --wandb [WANDB_TOKENS]

if [[ ${1} != "slurm" ]]; then
    export PATH=$HOME/.local/bin/:$PATH
    CUDA_VISIBLE_DIVICES=0 deepspeed $training_commands
fi