torchrun --nproc_per_node=4 --master_port=28636 train.py \
    --model_name_or_path "/nas/models/llama_hf/7B/" \
    --data_path ./alpaca_data.json \
    --bf16 True \
    --output_dir ./outputs/ \
    --num_train_epochs 3 \
    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 8 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2000 \
    --save_total_limit 1 \
    --learning_rate 2e-5 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --fsdp "full_shard auto_wrap" \
    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
    --tf32 True

{'loss': 1.0645, 'learning_rate': 1.893588419088962e-05, 'epoch': 0.52}                                                                         
{'loss': 1.157, 'learning_rate': 1.892391168466452e-05, 'epoch': 0.52}                                                                          
{'loss': 1.1938, 'learning_rate': 1.891187603111447e-05, 'epoch': 0.53}                                                                         
{'loss': 0.0, 'learning_rate': 1.8899777315406073e-05, 'epoch': 0.53}                                                                           
{'loss': 0.0, 'learning_rate': 1.8887615623152188e-05, 'epoch': 0.53}                                                                           
{'loss': 0.0, 'learning_rate': 1.88753910404113e-05, 'epoch': 0.53}