{ "serializer": "vln_candidate_logits_v1", "template_sha256": "fb79cf3922f74475e9a5faaac8c08d2f79a3ca7bef5dbf434f3f7726119229b8", "actions": [ "MOVE_FORWARD", "TURN_LEFT", "TURN_RIGHT", "STOP" ], "habitat_ids": [ 1, 2, 3, 0 ], "action_token_ids": [ [ 28164, 61846, 248046 ], [ 15834, 18440, 248046 ], [ 15834, 20549, 248046 ], [ 48964, 248046 ] ], "eos": 248046, "separator_ids": [ 198 ], "rgb_shape": [ 480, 640, 3 ], "position_convention": "logical_text_plus_native_mrope_v1", "rotary_precision": "fp32_preserved_across_module_casts_v1", "config": { "model": { "backbone": "Qwen/Qwen3.5-4B", "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "output_mode": "candidate_logits", "action_head_mode": "lm_rows_trainable" }, "observations": { "expected_rgb_shape": [ 480, 640, 3 ], "expected_visual_tokens": 300, "max_prefix_tokens": 2048, "serializer_version": "vln_candidate_logits_v1", "max_step_group_tokens": 384, "append_action_tokens": true, "feedback_format": "candidate_token" }, "memory": { "mode": "window8", "kv_window_steps_including_current": 8, "evict_before_new_step": true, "kv_guard_tokens": 4096 }, "training": { "use_cache": false, "microbatch_episodes_per_rank": 1, "nominal_episodes_per_update": 8, "gradient_accumulation_steps": 2, "model_max_length": 262144, "epochs": 2, "backbone_lr": 5e-06, "classifier_lr": 5e-06, "weight_decay": 0.01, "warmup_steps": 232, "seed": 429, "checkpoint_decoder_layers": true, "length_bucket_pool_episodes": 64, "tail_policy": "accelerate_repeat", "activation_offload_min_tokens": 65536, "supervise_assistant_terminator": false, "expected_total_steps": 7704, "expected_warmup_steps": 232, "dataloader_num_workers": 4, "save_strategy": "epoch", "save_total_limit": null, "class_weighting": "none", "effective_number_beta": 0.9999, "action_class_counts": [ 1659308, 740699, 697802, 30815 ], "action_class_weights": [ 1.0, 1.0, 1.0, 1.0 ], "class_weight_normalization": "training_probability_mean_one_v1" }, "runtime": { "text_attention": "simplememvln_step_attention", "vision_attention": "flash_attention_2", "vision_microbatch_images": 4, "max_logical_context_tokens": 262144, "action_diagnostics": false, "profile_components": false }, "generation": { "max_response_tokens_including_eos": 16, "fixed_separator": "\n" } }, "candidate_tokens": [ "A", "B", "C", "D" ], "candidate_token_ids": [ 32, 33, 34, 35 ], "decision_cue": "Action:\n", "feedback_format": "candidate_token", "feedback_token_ids": [ [ 32, 248046, 198 ], [ 33, 248046, 198 ], [ 34, 248046, 198 ], [ 35, 248046, 198 ] ], "action_head_mode": "lm_rows_trainable" }