37 lines
1.2 KiB
Bash
37 lines
1.2 KiB
Bash
torchrun --nnodes 4 --nproc_per_node 4 \
|
|
--node_rank=3 \
|
|
--rdzv_id=456 \
|
|
--rdzv_backend=c10d \
|
|
--rdzv_endpoint=172.23.30.15:29500 \
|
|
fastvideo/train.py \
|
|
--seed 42 \
|
|
--pretrained_model_name_or_path data/mochi \
|
|
--cache_dir "data/.cache" \
|
|
--data_json_path "data/BLACK-MYTH-Finetune-Dataset/videos2caption.json" \
|
|
--validation_prompt_dir "data/BLACK-MYTH-Finetune-Dataset/validation_prompt_embed_mask" \
|
|
--uncond_prompt_dir "data/BLACK-MYTH-Finetune-Dataset/uncond_prompt_embed_mask" \
|
|
--gradient_checkpointing \
|
|
--train_batch_size=1 \
|
|
--num_latent_t 16 \
|
|
--sp_size 4 \
|
|
--train_sp_batch_size 4 \
|
|
--dataloader_num_workers 4 \
|
|
--gradient_accumulation_steps=1 \
|
|
--max_train_steps=4000 \
|
|
--learning_rate=2e-5 \
|
|
--mixed_precision="bf16" \
|
|
--checkpointing_steps=500 \
|
|
--validation_steps=100 \
|
|
--validation_sampling_steps 64 \
|
|
--checkpoints_total_limit 3 \
|
|
--allow_tf32 \
|
|
--ema_start_step 0 \
|
|
--cfg 0.0 \
|
|
--ema_decay 0.999 \
|
|
--log_validation \
|
|
--output_dir="data/outputs/black_myth_correct_video_mask" \
|
|
--weighting_scheme "uniform" \
|
|
--num_frames 91 \
|
|
--selective_checkpointing 1.0
|
|
|