Create Code

2024-09-10 10:29:13 +08:00
parent 3d3151f3f1
commit f660725fa5
38 changed files with 13656 additions and 4 deletions
@@ -0,0 +1,101 @@
+## Training Code
+
+The default training commands for the different versions are as follows:
+
+We can choose whether to use deep speed in CogVideoX-Arbitrary, which can save a lot of video memory. 
+
+CogVideoX-Arbitrary without deepspeed:
+```sh
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+# When train model with multi machines, use "--config_file accelerate.yaml" instead of "--mixed_precision='bf16'".
+accelerate launch --mixed_precision="bf16" scripts/train.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=4 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=2e-05 \
+  --lr_scheduler="constant_with_warmup" \
+  --lr_warmup_steps=100 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --enable_xformers_memory_efficient_attention \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --use_came \
+  --use_ema \
+  --train_mode="inpaint" \
+  --resume_from_checkpoint="latest" \
+  --trainable_modules "."
+```
+
+CogVideoX-Arbitrary with deepspeed:
+```sh
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/train.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=4 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=2e-05 \
+  --lr_scheduler="constant_with_warmup" \
+  --lr_warmup_steps=100 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --enable_xformers_memory_efficient_attention \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --use_came \
+  --use_deepspeed \
+  --use_ema \
+  --train_mode="inpaint" \
+  --resume_from_checkpoint="latest" \
+  --trainable_modules "."
+```
@@ -0,0 +1,88 @@
+## Lora Training Code
+
+We can choose whether to use deep speed in CogVideoX-Arbitrary, which can save a lot of video memory. 
+
+CogVideoX-Arbitrary without deepspeed:
+
+```sh
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+# When train model with multi machines, use "--config_file accelerate.yaml" instead of "--mixed_precision='bf16'".
+accelerate launch --mixed_precision="bf16" scripts/train_lora.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=1 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=1e-04 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --low_vram \
+  --train_mode="inpaint" 
+```
+
+```sh
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+# When train model with multi machines, use "--config_file accelerate.yaml" instead of "--mixed_precision='bf16'".
+accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/train_lora.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=1 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=1e-04 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --use_deepspeed \
+  --low_vram \
+  --train_mode="inpaint" 
+```
@@ -0,0 +1,42 @@
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+# When train model with multi machines, use "--config_file accelerate.yaml" instead of "--mixed_precision='bf16'".
+accelerate launch --mixed_precision="bf16" scripts/train.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=1 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=2e-05 \
+  --lr_scheduler="constant_with_warmup" \
+  --lr_warmup_steps=100 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --use_ema \
+  --train_mode="inpaint" \
+  --resume_from_checkpoint="latest" \
+  --trainable_modules "."
@@ -0,0 +1,38 @@
+export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
+export DATASET_NAME="datasets/internal_datasets/"
+export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
+export NCCL_IB_DISABLE=1
+export NCCL_P2P_DISABLE=1
+NCCL_DEBUG=INFO
+
+# When train model with multi machines, use "--config_file accelerate.yaml" instead of "--mixed_precision='bf16'".
+accelerate launch --mixed_precision="bf16" scripts/train_lora.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATASET_NAME \
+  --train_data_meta=$DATASET_META_NAME \
+  --image_sample_size=1280 \
+  --video_sample_size=256 \
+  --token_sample_size=512 \
+  --video_sample_stride=3 \
+  --video_sample_n_frames=49 \
+  --train_batch_size=1 \
+  --video_repeat=1 \
+  --gradient_accumulation_steps=1 \
+  --dataloader_num_workers=8 \
+  --num_train_epochs=100 \
+  --checkpointing_steps=50 \
+  --learning_rate=1e-04 \
+  --seed=42 \
+  --output_dir="output_dir" \
+  --gradient_checkpointing \
+  --mixed_precision="bf16" \
+  --adam_weight_decay=3e-2 \
+  --adam_epsilon=1e-10 \
+  --vae_mini_batch=1 \
+  --max_grad_norm=0.05 \
+  --random_hw_adapt \
+  --training_with_video_token_length \
+  --random_frame_crop \
+  --enable_bucket \
+  --low_vram \
+  --train_mode="inpaint"