| models: |
| student: |
| _target_: fastvideo.train.models.wan.WanModel |
| init_from: Wan-AI/Wan2.1-T2V-1.3B-Diffusers |
| trainable: true |
| attention_backend: VSA_QAT_TRAIN_C128 |
| enable_gradient_checkpointing_type: full |
| flow_shift: 8.0 |
| teacher: |
| _target_: fastvideo.train.models.wan.WanModel |
| init_from: /home/hal-ywu/.cache/huggingface/hub/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/0fad780a534b6463e45facd96134c9f345acfa5b |
| trainable: false |
| attention_backend: TORCH_SDPA |
| disable_custom_init_weights: true |
| flow_shift: 8.0 |
| critic: |
| _target_: fastvideo.train.models.wan.WanModel |
| init_from: /home/hal-ywu/.cache/huggingface/hub/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/0fad780a534b6463e45facd96134c9f345acfa5b |
| trainable: true |
| attention_backend: TORCH_SDPA |
| disable_custom_init_weights: true |
| enable_gradient_checkpointing_type: full |
| flow_shift: 8.0 |
| method: |
| _target_: fastvideo.train.methods.distribution_matching.dmd2.DMD2Method |
| rollout_mode: simulate |
| generator_update_interval: 1 |
| real_score_guidance_scale: 3.5 |
| dmd_denoising_steps: |
| - 1000 |
| - 750 |
| - 500 |
| - 250 |
| min_timestep_ratio: 0.02 |
| max_timestep_ratio: 0.98 |
| fake_score_learning_rate: 8.0e-06 |
| fake_score_betas: |
| - 0.0 |
| - 0.999 |
| fake_score_lr_scheduler: constant |
| training: |
| distributed: |
| num_gpus: 4 |
| sp_size: 1 |
| tp_size: 1 |
| hsdp_replicate_dim: 4 |
| hsdp_shard_dim: 1 |
| data: |
| data_path: /home/hal-ywu/git/vsqa/data/mixed/training_dataset |
| dataloader_num_workers: 0 |
| train_batch_size: 4 |
| training_cfg_rate: 0.0 |
| seed: 1000 |
| num_latent_t: 16 |
| num_height: 448 |
| num_width: 896 |
| num_frames: 61 |
| preprocessed_data_type: text_only |
| optimizer: |
| learning_rate: 2.0e-06 |
| betas: |
| - 0.0 |
| - 0.999 |
| weight_decay: 0.01 |
| lr_scheduler: constant |
| lr_warmup_steps: 0 |
| loop: |
| max_train_steps: 1000 |
| gradient_accumulation_steps: 1 |
| checkpoint: |
| output_dir: /home/hal-ywu/git/vsqa/logs/fastvideo-mixkit61f-vsqa-dmd_c256t8-1000-V0247-base-linfp4-mixed-b16-260919-030359/checkpoints |
| training_state_checkpointing_steps: 50 |
| checkpoints_total_limit: 0 |
| resume_from_checkpoint: '' |
| tracker: |
| trackers: |
| - wandb |
| project_name: fastvideo |
| run_name: fastvideo-mixkit61f-vsqa-dmd_c256t8-1000-V0247-base-linfp4-mixed-b16-260919-030359 |
| entity: alexzms-ucsd |
| vsa: |
| sparsity: 0.9 |
| cache_tile_buf: false |
| dit_precision: fp32 |
| callbacks: |
| grad_clip: |
| max_grad_norm: 1.0 |
| validation: |
| pipeline_target: fastvideo.pipelines.basic.wan.wan_dmd_pipeline.WanDMDPipeline |
| dataset_file: /home/hal-ywu/git/vsqa/logs/fastvideo-mixkit61f-vsqa-dmd_c256t8-1000-V0247-base-linfp4-mixed-b16-260919-030359/validation.json |
| every_steps: 50 |
| run_at_start: true |
| sampling_steps: |
| - 4 |
| sampling_timesteps: |
| - 1000 |
| - 750 |
| - 500 |
| - 250 |
| guidance_scale: 1.0 |
| height: 448 |
| width: 896 |
| num_frames: 61 |
| attn_qat_infer: false |
| pipeline: |
| flow_shift: 8.0 |
| dit_config: |
| quant_config: nvfp4_qat_train |
|
|
