#!/bin/bash

MODEL_PATH="/model/BitCPM-CANN-1B-unquantized"
DATA_PATH="/dataset/c4-pro/data/000_1_7.parquet"
OUTPUT_DIR="./output"
DS_CONFIG="./ds_config_z2.json"

NUM_GPUS=8
BATCH_SIZE_PER_GPU=8
GRAD_ACCUM_STEPS=8
MAX_SEQ_LENGTH=1024

export ASCEND_RT_VISIBLE_DEVICES=8,9,10,11,12,13,14,15
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
export DS_SKIP_CUDA_CHECK=1
torchrun --nproc_per_node=$NUM_GPUS train.py \
    --model_name_or_path $MODEL_PATH \
    --data_path $DATA_PATH \
    --max_seq_length $MAX_SEQ_LENGTH \
    --output_dir $OUTPUT_DIR \
    --per_device_train_batch_size $BATCH_SIZE_PER_GPU \
    --gradient_accumulation_steps $GRAD_ACCUM_STEPS \
    --max_steps 100 \
    --learning_rate 4e-5 \
    --lr_scheduler_type cosine \
    --warmup_ratio 0.1 \
    --weight_decay 1e-2 \
    --logging_steps 2 \
    --save_steps 500 \
    --save_total_limit 3 \
    --bf16 \
    --deepspeed $DS_CONFIG \
    --gradient_checkpointing \
    --seed 42 \
    --dataloader_num_workers 4 \
    --report_to tensorboard \
    --logging_dir /data/tensorboard/pretrain \
    --gradient_checkpointing_kwargs '{"use_reentrant": false}'