wehub-resource-sync
33 lines
954 B
Bash
33 lines
954 B
Bash
# 8 * 65GiB
|
|
PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
|
|
NPROC_PER_NODE=8 \
|
|
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
|
|
megatron sft \
|
|
--model Qwen/Qwen2.5-14B \
|
|
--save_safetensors true \
|
|
--dataset 'liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT' \
|
|
--load_from_cache_file true \
|
|
--split_dataset_ratio 0.01 \
|
|
--tensor_model_parallel_size 4 \
|
|
--micro_batch_size 1 \
|
|
--global_batch_size 16 \
|
|
--packing true \
|
|
--recompute_granularity selective \
|
|
--train_iters 2000 \
|
|
--eval_iters 50 \
|
|
--finetune true \
|
|
--cross_entropy_loss_fusion true \
|
|
--lr 1e-5 \
|
|
--lr_warmup_fraction 0.05 \
|
|
--min_lr 1e-6 \
|
|
--output_dir megatron_output/Qwen2.5-14B \
|
|
--eval_steps 200 \
|
|
--save_steps 200 \
|
|
--max_length 8192 \
|
|
--dataloader_num_workers 8 \
|
|
--dataset_num_proc 8 \
|
|
--no_save_optim true \
|
|
--no_save_rng true \
|
|
--sequence_parallel true \
|
|
--attention_backend flash
|