{
  "decoder_path": "./Qwen/Qwen2.5-VL-3B-Instruct",
  "use_token_mixer": true,
  "token_mixer_num_layers": 2,
  "token_mixer_num_heads": 16,
  "token_mixer_dropout": 0.1,
  "freeze_token_mixer": false,
  "use_local_c3": true,
  "local_c3_block_size": 4,
  "local_c3_num_heads": 8,
  "num_post_encoder_layers": 2,
  "use_rope_alignment": true,
  "use_kl_distillation": true,
  "kl_loss_weight": 0.5,
  "teacher_temperature": 1.0,
  "use_hidden_distillation": true,
  "hidden_loss_weight": 0.1,
  "use_decoder_lora": false,
  "data_path": "./data/train/stage2_mixed/combined_v4.jsonl",
  "max_length": 768,
  "max_samples": null,
  "max_image_size": 672,
  "output_dir": "./outputs/image_c3_v7_3b_16x_stage2_20260318_160014",
  "epochs": 3,
  "batch_size": 2,
  "gradient_accumulation_steps": 4,
  "lr_local_c3": 1e-05,
  "lr_token_mixer": 1e-05,
  "lr_decoder_lora": 1e-05,
  "weight_decay": 0.01,
  "warmup_ratio": 0.1,
  "max_grad_norm": 1.0,
  "log_steps": 50,
  "save_steps": 500,
  "gpu": 0,
  "num_workers": 4,
  "resume_from": null,
  "timestamp": "2026-03-18T19:00:35.309642",
  "world_size": 8
}