Files
wehub-resource-sync a203934033
Lint test / lint (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:34:58 +08:00

45 lines
1.3 KiB
Bash

# 2 * 62GiB, 5.10s/it
PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
NPROC_PER_NODE=2 \
CUDA_VISIBLE_DEVICES=0,1 \
megatron sft \
--model Qwen/Qwen3-30B-A3B \
--save_safetensors true \
--merge_lora false \
--dataset 'swift/Qwen3-SFT-Mixin#2000' \
'swift/self-cognition:empty_think#600' \
--loss_scale ignore_empty_think \
--tuner_type lora \
--lora_rank 8 \
--lora_alpha 32 \
--target_modules all-linear \
--split_dataset_ratio 0.01 \
--expert_model_parallel_size 2 \
--moe_permute_fusion true \
--moe_grouped_gemm true \
--moe_shared_expert_overlap true \
--moe_aux_loss_coeff 1e-3 \
--micro_batch_size 8 \
--global_batch_size 16 \
--recompute_granularity full \
--recompute_method uniform \
--recompute_num_layers 1 \
--num_train_epochs 1 \
--finetune true \
--cross_entropy_loss_fusion true \
--lr 1e-4 \
--lr_warmup_fraction 0.05 \
--min_lr 1e-5 \
--output_dir megatron_output/Qwen3-30B-A3B \
--eval_steps 200 \
--save_steps 200 \
--max_length 2048 \
--dataloader_num_workers 8 \
--dataset_num_proc 8 \
--no_save_optim true \
--no_save_rng true \
--sequence_parallel true \
--attention_backend flash \
--model_author swift \
--model_name swift-robot