wehub-resource-sync
48 lines
1.4 KiB
Bash
48 lines
1.4 KiB
Bash
# 2 * 76GiB
|
|
PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
|
|
NPROC_PER_NODE=2 \
|
|
IMAGE_MAX_TOKEN_NUM=1024 \
|
|
VIDEO_MAX_TOKEN_NUM=128 \
|
|
FPS_MAX_FRAMES=16 \
|
|
CUDA_VISIBLE_DEVICES=0,1 \
|
|
megatron sft \
|
|
--model Qwen/Qwen3-VL-8B-Instruct \
|
|
--save_safetensors true \
|
|
--dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#5000' \
|
|
--load_from_cache_file true \
|
|
--tensor_model_parallel_size 2 \
|
|
--sequence_parallel true \
|
|
--packing true \
|
|
--freeze_llm false \
|
|
--freeze_vit true \
|
|
--freeze_aligner true \
|
|
--split_dataset_ratio 0.01 \
|
|
--micro_batch_size 1 \
|
|
--global_batch_size 4 \
|
|
--recompute_granularity full \
|
|
--recompute_method uniform \
|
|
--recompute_num_layers 1 \
|
|
--finetune true \
|
|
--cross_entropy_loss_fusion true \
|
|
--lr 1e-5 \
|
|
--lr_warmup_fraction 0.05 \
|
|
--min_lr 1e-6 \
|
|
--num_train_epochs 1 \
|
|
--output_dir megatron_output/Qwen3-VL-8B-Instruct \
|
|
--save_steps 200 \
|
|
--max_length 2048 \
|
|
--dataloader_num_workers 4 \
|
|
--no_save_optim true \
|
|
--no_save_rng true \
|
|
--dataset_num_proc 8
|
|
|
|
# PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
|
|
# IMAGE_MAX_TOKEN_NUM=1024 \
|
|
# VIDEO_MAX_TOKEN_NUM=128 \
|
|
# FPS_MAX_FRAMES=16 \
|
|
# CUDA_VISIBLE_DEVICES=0 \
|
|
# swift infer \
|
|
# --model megatron_output/Qwen3-VL-8B-Instruct/vx-xxx/checkpoint-xxx \
|
|
# --load_data_args true \
|
|
# --stream true
|