| # PACE-SimplerEnv: model config of the released PACE checkpoint, read by the PACE code together with pytorch_model.pt | |
| # and dataset_statistics.json in this directory: | |
| # from pace.model.framework.base_framework import baseframework | |
| # policy = baseframework.from_pretrained("./PACE-SimplerEnv") | |
| # Training recipes and launchers are in the code repository (docs/TRAINING.md). | |
| run_id: PACE-SimplerEnv | |
| run_root_dir: runs | |
| seed: 42 | |
| trackers: [jsonl] # "jsonl" -> <run>/metrics.jsonl; add "wandb" for Weights & Biases (entity: wandb_entity or $WANDB_ENTITY) | |
| wandb_entity: null | |
| wandb_project: pace | |
| framework: | |
| # "PACE"; the long alias "ProgressVLA_DinoTargetQueryProgressTripleReadoutFullGoal" is the name used by the | |
| # original training runs and is still accepted. | |
| name: PACE | |
| qwenvl: | |
| base_vlm: Qwen/Qwen3-VL-4B-Instruct # env BASE_VLM (local directory or HF id) takes precedence | |
| attn_implementation: flash_attention_2 # env PACE_ATTN_IMPLEMENTATION (e.g. sdpa) overrides | |
| action_model: | |
| action_model_type: DiT-B # 12 heads x 64, 16 layers (diffusion_model_cfg.num_layers) | |
| hidden_size: 1024 | |
| add_pos_embed: true | |
| max_seq_len: 1024 | |
| action_dim: 7 | |
| state_dim: 7 # the state encoder exists in the checkpoint, but no proprioceptive state is fed | |
| future_action_window_size: 15 | |
| action_horizon: 16 # action chunk H = future_action_window_size + 1 | |
| past_action_window_size: 0 | |
| noise_beta_alpha: 1.5 | |
| noise_beta_beta: 1.0 | |
| noise_s: 0.999 | |
| num_timestep_buckets: 1000 | |
| num_inference_timesteps: 4 # flow-matching (Euler) denoising steps | |
| num_target_vision_tokens: 32 | |
| diffusion_model_cfg: | |
| dropout: 0.2 | |
| final_dropout: true | |
| interleave_self_attention: true | |
| norm_type: ada_norm | |
| num_layers: 16 | |
| output_dim: 1024 | |
| positional_embeddings: null | |
| progress: | |
| layer_idx: 18 # query readouts from the hidden states of VLM layer 18 | |
| num_goal_queries: 4 # K goal queries, mean-pooled into the foresight-anchor head | |
| use_goal_dit_token: true # the predicted anchor is a DiT conditioning token (besides p_cur and dp_cur) | |
| lambda_long: 0.1 # goal-anchor loss (MSE in DINOv2 space) | |
| lambda_pcur: 0.1 # current-progress loss | |
| lambda_dpcur: 0.1 # forward-commitment loss | |
| lambda_cons: 0.1 # consistency: p_cur readout vs projection onto the predicted anchor | |
| cons_detach_anchor: true | |
| query_init_std: 0.01 | |
| train_query_token_rows_only: true # new token rows are trained; the rest of the VLM is fully fine-tuned | |
| progress_future_offset: 15 # Delta (history / commitment horizon in env steps); equals datasets.vla_data value | |
| use_history_images: true # the frame at t - Delta is an extra VLM input | |
| use_dp_prev_input: true # the historical pace dp_prev enters the VLM as a token | |
| use_full_goal_anchor_at_inference: true | |
| infer_history_mode: step_aligned | |
| dino_variant: vitb14 # frozen DINOv2 ViT-B/14 (progress geometry) | |
| dino_target_dim: 768 | |
| dino_head_hidden_dim: 1024 | |
| dino_repo_root: null # null -> vendored third_party/dinov2 (env DINO_REPO_ROOT overrides) | |
| dino_weights: null # null -> $PACE_CACHE/dinov2 download (env DINOV2_WEIGHTS overrides) | |
| # Commitment audit (inference-time failure detector, never changes actions): alarm when the shortfall CUSUM | |
| # exceeds audit_threshold or p_cur has not risen for more than audit_stall_chunks action chunks. | |
| # audit_threshold is shared by all benchmarks (unmet commitments adding up to 0.4 of the task); the stall limit is | |
| # calibrated per benchmark on held-out checkpoints (2.5% false alarms on successful episodes); see docs/PROGRESS.md. | |
| audit_kappa: 0.0 | |
| audit_threshold: 0.4 | |
| audit_stall_chunks: 2.12 | |
| datasets: | |
| vla_data: | |
| dataset_py: lerobot_datasets | |
| image_size: [224, 224] # inference-time resize of the client images | |
| CoT_prompt: "Your task is {instruction}. To identify the key objects for your task. Locate their bounding boxes in [x1,y1,x2,y2] format." | |
| return_progress_anchors: true | |
| progress_future_offset: 15 | |
| trainer: # inference only reads these | |
| repeated_diffusion_steps: 4 | |
| pretrained_checkpoint: null | |