CPM-9G-8B/train.sh

#!/bin/bash

deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset TACO \
    --template jiuge \
    --finetuning_type full \
    --output_dir TACO \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048

deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset Tested-143k-Python-Alpaca \
    --template jiuge \
    --finetuning_type full \
    --output_dir Tested-143k-Python-Alpaca \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048
    
deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset UltraInteract_sft \
    --template jiuge \
    --finetuning_type full \
    --output_dir UltraInteract_sft \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048
    
    
deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset  code_instructions_120k_alpaca \
    --template jiuge \
    --finetuning_type full \
    --output_dir code_instructions_120k_alpaca \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048
    
    
deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset  CodeExercise-Python-27k \
    --template jiuge \
    --finetuning_type full \
    --output_dir CodeExercise-Python-27k \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048
    

deepspeed --include localhost:0,1,2,3,4,5,6,7 --master_port 21666 src/train.py \
    --stage sft \
    --model_name_or_path /mnt/diskhd/Backup/DownloadModel/2b_sft_model/ \
    --do_train \
    --dataset CodeNet4Repair \
    --template jiuge \
    --finetuning_type full \
    --output_dir CodeNet4Repair \
    --per_device_train_batch_size 14 \
    --gradient_accumulation_steps 6 \
    --lr_scheduler_type cosine \
    --logging_step 1 \
    --save_steps 300 \
    --lr_scheduler_type cosine_with_restarts \
    --warmup_ratio 0.001 \
    --optim adamw_torch \
    --learning_rate 2e-5 \
    --num_train_epochs 2.0 \
    --plot_loss \
    --bf16 \
    --gradient_checkpointing \
    --report_to tensorboard \
    --deepspeed deepspeed_configs/zero2.json \
    --cutoff_len 2048