Initial pi0.7 minimal validation

2026-07-12 00:52:00 +08:00
commit b4c8db846b
27 changed files with 3724 additions and 0 deletions
@@ -0,0 +1,98 @@
+seed: 7
+device: auto
+output_dir: outputs/overfit
+
+data:
+  source_manifest: ../../alpamayo/alpamayo-qwen05b-validation/data/processed/overfit_manifest.jsonl
+  max_samples: 1
+  augmentation_factor: 1
+  image_size: 64
+  history_frames: 6
+  action_horizon: 16
+  policy_variants:
+    - expert
+    - fast
+    - slow
+    - understeer
+    - stop
+
+model:
+  patch_size: 16
+  d_model: 96
+  mem_d_model: 64
+  goal_d_model: 64
+  high_level_d_model: 64
+  n_heads: 4
+  n_layers: 3
+  mlp_ratio: 3
+  dropout: 0.0
+  max_text_tokens: 96
+  action_dim: 2
+  action_horizon: 16
+  goal_heatmap_size: 32
+
+memory:
+  enabled: true
+  history_frames: 6
+  ambiguous_pair_weight: 0.25
+
+goal:
+  enabled: true
+  heatmap_size: 32
+  heatmap_sigma: 1.5
+  xy_extent: [-8.0, 64.0, -16.0, 16.0]
+  endpoint_only_target: true
+
+high_level:
+  enabled: true
+  predict_goal: true
+  predict_metadata: true
+  metadata_fields:
+    - speed
+    - quality
+    - mistake
+    - control
+
+steering:
+  metadata_dropout: 0.25
+  preserve_task_prompt: true
+  cfg_training_dropout: 0.25
+  cfg_beta: 2.0
+
+rtc:
+  enabled: true
+  max_delay_steps: 12
+  include_executed_prefix: true
+  masked_loss: true
+
+flow:
+  timestep_beta_alpha: 1.5
+  timestep_beta_beta: 1.0
+  integration_steps: 10
+
+train:
+  goal_steps: 300
+  high_level_steps: 200
+  policy_steps: 900
+  batch_size: 5
+  learning_rate: 0.001
+  weight_decay: 0.0
+  grad_clip_norm: 1.0
+  goal_loss_weight: 1.0
+  high_level_loss_weight: 1.0
+  flow_loss_weight: 2.0
+  rtc_loss_weight: 1.0
+  log_every: 20
+
+evaluation:
+  fixed_noise_seed: 1
+  cfg_betas: [0.0, 1.0, 2.0]
+  ablations:
+    - full
+    - no_metadata
+    - no_goal
+    - no_history
+  compare_rtc_delays: [0, 4, 8, 12]
+  save_trajectory_plot: true
+  save_goal_plot: true
+  save_ablation_plot: true