diff --git "a/train.log" "b/train.log" new file mode 100644--- /dev/null +++ "b/train.log" @@ -0,0 +1,4398 @@ +2025-10-09 19:45:13 - __main__ - INFO - Logging configured - Console and File: output_wildrgbd_gscollision/train.log +2025-10-09 19:45:24 - __main__ - INFO - Initializing model... +2025-10-09 19:45:32 - __main__ - INFO - Loading pretrained Pi3 model from /mnt/nfs_project_a/shared/models/shailab/pi3 +2025-10-09 19:47:14 - __main__ - INFO - Logging configured - Console and File: output_wildrgbd_gscollision/train.log +2025-10-09 19:47:18 - __main__ - INFO - Initializing model... +2025-10-09 19:47:26 - __main__ - INFO - Loading pretrained Pi3 model from /mnt/nfs_project_a/shared/models/shailab/pi3 +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: register_token +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: image_mean +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: image_std +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.cls_token +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.pos_embed +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.register_tokens +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls1.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls2.gamma +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.bias +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.weight +2025-10-09 19:47:35 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.bias +2025-10-09 19:47:35 - __main__ - INFO - Copying point decoder weights to feature decoder... +2025-10-09 19:47:35 - __main__ - INFO - Successfully copied 64 parameters from point_decoder to feature_decoder +2025-10-09 19:47:36 - __main__ - INFO - Freezing pretrained parameters... +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.projects.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.projects.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.0.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.5.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.10.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.16.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.19.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.0.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.bias +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.down_proj.weight +2025-10-09 19:47:36 - __main__ - INFO - Keeping trainable: feature_head.down_proj.bias +2025-10-09 19:47:36 - __main__ - INFO - Loaded 1210 pretrained parameters +2025-10-09 19:47:36 - __main__ - INFO - Frozen 958696732/1061946687 parameters (90.3%) +2025-10-09 19:47:36 - __main__ - INFO - Trainable parameters: 103249955 +2025-10-09 19:47:37 - __main__ - INFO - Total trainable parameters: 103,249,955 +2025-10-09 19:47:37 - __main__ - INFO - Loading dataset from ./datasets/ +2025-10-09 19:53:47 - __main__ - INFO - Logging configured - Console and File: output_wildrgbd_gscollision/train.log +2025-10-09 19:53:51 - __main__ - INFO - Initializing model... +2025-10-09 19:53:58 - __main__ - INFO - Loading pretrained Pi3 model from /mnt/nfs_project_a/shared/models/shailab/pi3 +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: register_token +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: image_mean +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: image_std +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.cls_token +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.pos_embed +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.register_tokens +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls1.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls2.gamma +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.bias +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.weight +2025-10-09 19:54:08 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.bias +2025-10-09 19:54:08 - __main__ - INFO - Copying point decoder weights to feature decoder... +2025-10-09 19:54:08 - __main__ - INFO - Successfully copied 64 parameters from point_decoder to feature_decoder +2025-10-09 19:54:09 - __main__ - INFO - Freezing pretrained parameters... +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.projects.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.projects.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.0.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.5.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.10.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.16.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.19.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.0.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.bias +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.down_proj.weight +2025-10-09 19:54:09 - __main__ - INFO - Keeping trainable: feature_head.down_proj.bias +2025-10-09 19:54:09 - __main__ - INFO - Loaded 1210 pretrained parameters +2025-10-09 19:54:09 - __main__ - INFO - Frozen 958696732/1061946687 parameters (90.3%) +2025-10-09 19:54:09 - __main__ - INFO - Trainable parameters: 103249955 +2025-10-09 19:54:09 - __main__ - INFO - Total trainable parameters: 103,249,955 +2025-10-09 19:54:09 - __main__ - INFO - Loading dataset from ./datasets/ +2025-10-09 19:54:21 - __main__ - INFO - ***** Running training ***** +2025-10-09 19:54:21 - __main__ - INFO - Num examples = 21889 +2025-10-09 19:54:21 - __main__ - INFO - Num Epochs = 50 +2025-10-09 19:54:21 - __main__ - INFO - Total optimization steps = 52150 +2025-10-09 19:55:30 - __main__ - INFO - Logging configured - Console and File: output_wildrgbd_gscollision/train.log +2025-10-09 19:55:34 - __main__ - INFO - Initializing model... +2025-10-09 19:55:42 - __main__ - INFO - Loading pretrained Pi3 model from /mnt/nfs_project_a/shared/models/shailab/pi3 +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: register_token +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: image_mean +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: image_std +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.cls_token +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.pos_embed +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.register_tokens +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.patch_embed.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.0.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.1.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.2.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.3.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.4.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.5.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.6.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.7.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.8.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.9.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.10.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.11.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.12.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.13.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.14.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.15.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.16.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.17.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.18.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.19.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.20.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.21.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.22.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.blocks.23.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: encoder.norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.0.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.1.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.2.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.3.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.4.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.5.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.6.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.7.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.8.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.9.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.10.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.11.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.12.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.13.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.14.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.15.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.16.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.17.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.18.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.19.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.20.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.21.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.22.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.23.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.24.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.25.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.26.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.27.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.28.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.29.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.30.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.31.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.32.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.33.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.34.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.q_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.attn.k_norm.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls1.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: decoder.35.ls2.gamma +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.projects.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_decoder.linear_out.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: point_head.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.projects.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_decoder.linear_out.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: conf_head.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.projects.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.attn.proj.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.norm2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_decoder.linear_out.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.0.res_conv3.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv1.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.res_conv.1.res_conv3.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.0.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.more_mlps.2.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_t.bias +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.weight +2025-10-09 19:55:51 - __main__ - INFO - Loaded pretrained parameter: camera_head.fc_rot.bias +2025-10-09 19:55:51 - __main__ - INFO - Copying point decoder weights to feature decoder... +2025-10-09 19:55:52 - __main__ - INFO - Successfully copied 64 parameters from point_decoder to feature_decoder +2025-10-09 19:55:52 - __main__ - INFO - Freezing pretrained parameters... +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.projects.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.projects.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.qkv.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.attn.proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.0.mlp.fc2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.qkv.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.attn.proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.1.mlp.fc2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.qkv.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.attn.proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.2.mlp.fc2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.qkv.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.attn.proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.3.mlp.fc2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.qkv.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.attn.proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.blocks.4.mlp.fc2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_decoder.linear_out.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.0.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.3.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.4.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.5.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.6.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.8.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.9.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.10.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.11.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.13.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.14.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.15.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.16.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.17.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.19.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.upsample_proj.model.20.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.0.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.0.1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.1.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.2.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm1.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.conv2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.conv_net.layers.3.norm2.bias +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.down_proj.weight +2025-10-09 19:55:52 - __main__ - INFO - Keeping trainable: feature_head.down_proj.bias +2025-10-09 19:55:52 - __main__ - INFO - Loaded 1210 pretrained parameters +2025-10-09 19:55:52 - __main__ - INFO - Frozen 958696732/1061946687 parameters (90.3%) +2025-10-09 19:55:52 - __main__ - INFO - Trainable parameters: 103249955 +2025-10-09 19:55:53 - __main__ - INFO - Total trainable parameters: 103,249,955 +2025-10-09 19:55:53 - __main__ - INFO - Loading dataset from ./datasets/ +2025-10-09 19:56:08 - __main__ - INFO - ***** Running training ***** +2025-10-09 19:56:08 - __main__ - INFO - Num examples = 26209 +2025-10-09 19:56:08 - __main__ - INFO - Num Epochs = 50 +2025-10-09 19:56:08 - __main__ - INFO - Total optimization steps = 62450 +2025-10-09 20:33:48 - __main__ - INFO - Epoch 0 completed: +2025-10-09 20:33:48 - __main__ - INFO - Average epoch_total_loss: 0.050772 +2025-10-09 20:33:48 - __main__ - INFO - Average epoch_mse_loss: 0.010668 +2025-10-09 20:33:48 - __main__ - INFO - Average epoch_lpips_loss: 0.033789 +2025-10-09 20:33:48 - __main__ - INFO - Average epoch_depth_loss: 0.006315 +2025-10-09 20:33:48 - __main__ - INFO - Steps in epoch: 1249 +2025-10-09 21:11:38 - __main__ - INFO - Epoch 1 completed: +2025-10-09 21:11:38 - __main__ - INFO - Average epoch_total_loss: 0.039127 +2025-10-09 21:11:38 - __main__ - INFO - Average epoch_mse_loss: 0.008279 +2025-10-09 21:11:38 - __main__ - INFO - Average epoch_lpips_loss: 0.026502 +2025-10-09 21:11:38 - __main__ - INFO - Average epoch_depth_loss: 0.004346 +2025-10-09 21:11:38 - __main__ - INFO - Steps in epoch: 1249 +2025-10-09 21:49:55 - __main__ - INFO - Epoch 2 completed: +2025-10-09 21:49:55 - __main__ - INFO - Average epoch_total_loss: 0.036375 +2025-10-09 21:49:55 - __main__ - INFO - Average epoch_mse_loss: 0.007677 +2025-10-09 21:49:55 - __main__ - INFO - Average epoch_lpips_loss: 0.024872 +2025-10-09 21:49:55 - __main__ - INFO - Average epoch_depth_loss: 0.003827 +2025-10-09 21:49:55 - __main__ - INFO - Steps in epoch: 1249 +2025-10-09 22:28:41 - __main__ - INFO - Epoch 3 completed: +2025-10-09 22:28:41 - __main__ - INFO - Average epoch_total_loss: 0.035246 +2025-10-09 22:28:41 - __main__ - INFO - Average epoch_mse_loss: 0.007401 +2025-10-09 22:28:41 - __main__ - INFO - Average epoch_lpips_loss: 0.024197 +2025-10-09 22:28:41 - __main__ - INFO - Average epoch_depth_loss: 0.003648 +2025-10-09 22:28:41 - __main__ - INFO - Steps in epoch: 1249 +2025-10-09 22:29:20 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-5000 +2025-10-09 22:29:22 - root - INFO - gcc -pthread -B /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/compiler_compat -fno-strict-overflow -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/include -fPIC -O2 -isystem /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/include -fPIC -c /tmp/tmpo9q_5f5g/test.c -o /tmp/tmpo9q_5f5g/test.o +2025-10-09 22:29:22 - root - INFO - gcc -pthread -B /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/compiler_compat /tmp/tmpo9q_5f5g/test.o -laio -o /tmp/tmpo9q_5f5g/a.out +2025-10-09 22:29:23 - root - INFO - gcc -pthread -B /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/compiler_compat -fno-strict-overflow -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/include -fPIC -O2 -isystem /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/include -fPIC -c /tmp/tmpypx_3_ko/test.c -o /tmp/tmpypx_3_ko/test.o +2025-10-09 22:29:23 - root - INFO - gcc -pthread -B /mnt/nfs_project_a/ruihong/anaconda3/envs/vggt/compiler_compat /tmp/tmpypx_3_ko/test.o -L/cm/shared/apps/cuda12.8/toolkit/12.8.0 -L/cm/shared/apps/cuda12.8/toolkit/12.8.0/lib64 -lcufile -o /tmp/tmpypx_3_ko/a.out +2025-10-09 22:29:54 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-5000/optimizer.bin +2025-10-09 22:29:54 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-5000/scheduler.bin +2025-10-09 22:29:54 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-5000/sampler.bin +2025-10-09 22:29:54 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-5000/random_states_0.pkl +2025-10-09 22:29:54 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-5000 +2025-10-09 23:09:48 - __main__ - INFO - Epoch 4 completed: +2025-10-09 23:09:48 - __main__ - INFO - Average epoch_total_loss: 0.033820 +2025-10-09 23:09:48 - __main__ - INFO - Average epoch_mse_loss: 0.007025 +2025-10-09 23:09:48 - __main__ - INFO - Average epoch_lpips_loss: 0.023476 +2025-10-09 23:09:48 - __main__ - INFO - Average epoch_depth_loss: 0.003320 +2025-10-09 23:09:48 - __main__ - INFO - Steps in epoch: 1249 +2025-10-09 23:49:59 - __main__ - INFO - Epoch 5 completed: +2025-10-09 23:49:59 - __main__ - INFO - Average epoch_total_loss: 0.032806 +2025-10-09 23:49:59 - __main__ - INFO - Average epoch_mse_loss: 0.006761 +2025-10-09 23:49:59 - __main__ - INFO - Average epoch_lpips_loss: 0.022902 +2025-10-09 23:49:59 - __main__ - INFO - Average epoch_depth_loss: 0.003143 +2025-10-09 23:49:59 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 00:30:17 - __main__ - INFO - Epoch 6 completed: +2025-10-10 00:30:17 - __main__ - INFO - Average epoch_total_loss: 0.032724 +2025-10-10 00:30:17 - __main__ - INFO - Average epoch_mse_loss: 0.006639 +2025-10-10 00:30:17 - __main__ - INFO - Average epoch_lpips_loss: 0.022872 +2025-10-10 00:30:17 - __main__ - INFO - Average epoch_depth_loss: 0.003213 +2025-10-10 00:30:17 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 01:10:37 - __main__ - INFO - Epoch 7 completed: +2025-10-10 01:10:37 - __main__ - INFO - Average epoch_total_loss: 0.031106 +2025-10-10 01:10:37 - __main__ - INFO - Average epoch_mse_loss: 0.006251 +2025-10-10 01:10:37 - __main__ - INFO - Average epoch_lpips_loss: 0.022037 +2025-10-10 01:10:37 - __main__ - INFO - Average epoch_depth_loss: 0.002818 +2025-10-10 01:10:37 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 01:11:23 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-10000 +2025-10-10 01:11:50 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-10000/optimizer.bin +2025-10-10 01:11:50 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-10000/scheduler.bin +2025-10-10 01:11:50 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-10000/sampler.bin +2025-10-10 01:11:50 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-10000/random_states_0.pkl +2025-10-10 01:11:50 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-10000 +2025-10-10 01:51:20 - __main__ - INFO - Epoch 8 completed: +2025-10-10 01:51:20 - __main__ - INFO - Average epoch_total_loss: 0.031667 +2025-10-10 01:51:20 - __main__ - INFO - Average epoch_mse_loss: 0.006343 +2025-10-10 01:51:20 - __main__ - INFO - Average epoch_lpips_loss: 0.022358 +2025-10-10 01:51:20 - __main__ - INFO - Average epoch_depth_loss: 0.002965 +2025-10-10 01:51:20 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 02:30:19 - __main__ - INFO - Epoch 9 completed: +2025-10-10 02:30:19 - __main__ - INFO - Average epoch_total_loss: 0.031828 +2025-10-10 02:30:19 - __main__ - INFO - Average epoch_mse_loss: 0.006375 +2025-10-10 02:30:19 - __main__ - INFO - Average epoch_lpips_loss: 0.022419 +2025-10-10 02:30:19 - __main__ - INFO - Average epoch_depth_loss: 0.003034 +2025-10-10 02:30:19 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 03:09:44 - __main__ - INFO - Epoch 10 completed: +2025-10-10 03:09:44 - __main__ - INFO - Average epoch_total_loss: 0.030508 +2025-10-10 03:09:44 - __main__ - INFO - Average epoch_mse_loss: 0.006016 +2025-10-10 03:09:44 - __main__ - INFO - Average epoch_lpips_loss: 0.021727 +2025-10-10 03:09:44 - __main__ - INFO - Average epoch_depth_loss: 0.002764 +2025-10-10 03:09:44 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 03:49:31 - __main__ - INFO - Epoch 11 completed: +2025-10-10 03:49:31 - __main__ - INFO - Average epoch_total_loss: 0.031971 +2025-10-10 03:49:31 - __main__ - INFO - Average epoch_mse_loss: 0.006298 +2025-10-10 03:49:31 - __main__ - INFO - Average epoch_lpips_loss: 0.022451 +2025-10-10 03:49:31 - __main__ - INFO - Average epoch_depth_loss: 0.003222 +2025-10-10 03:49:31 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 03:50:22 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-15000 +2025-10-10 03:50:47 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-15000/optimizer.bin +2025-10-10 03:50:47 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-15000/scheduler.bin +2025-10-10 03:50:47 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-15000/sampler.bin +2025-10-10 03:50:47 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-15000/random_states_0.pkl +2025-10-10 03:50:47 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-15000 +2025-10-10 04:30:21 - __main__ - INFO - Epoch 12 completed: +2025-10-10 04:30:21 - __main__ - INFO - Average epoch_total_loss: 0.029916 +2025-10-10 04:30:21 - __main__ - INFO - Average epoch_mse_loss: 0.005878 +2025-10-10 04:30:21 - __main__ - INFO - Average epoch_lpips_loss: 0.021320 +2025-10-10 04:30:21 - __main__ - INFO - Average epoch_depth_loss: 0.002718 +2025-10-10 04:30:21 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 05:10:40 - __main__ - INFO - Epoch 13 completed: +2025-10-10 05:10:40 - __main__ - INFO - Average epoch_total_loss: 0.029377 +2025-10-10 05:10:40 - __main__ - INFO - Average epoch_mse_loss: 0.005742 +2025-10-10 05:10:40 - __main__ - INFO - Average epoch_lpips_loss: 0.021048 +2025-10-10 05:10:40 - __main__ - INFO - Average epoch_depth_loss: 0.002586 +2025-10-10 05:10:40 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 05:51:20 - __main__ - INFO - Epoch 14 completed: +2025-10-10 05:51:20 - __main__ - INFO - Average epoch_total_loss: 0.029808 +2025-10-10 05:51:20 - __main__ - INFO - Average epoch_mse_loss: 0.005824 +2025-10-10 05:51:20 - __main__ - INFO - Average epoch_lpips_loss: 0.021250 +2025-10-10 05:51:20 - __main__ - INFO - Average epoch_depth_loss: 0.002734 +2025-10-10 05:51:20 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 06:32:19 - __main__ - INFO - Epoch 15 completed: +2025-10-10 06:32:19 - __main__ - INFO - Average epoch_total_loss: 0.029036 +2025-10-10 06:32:19 - __main__ - INFO - Average epoch_mse_loss: 0.005635 +2025-10-10 06:32:19 - __main__ - INFO - Average epoch_lpips_loss: 0.020737 +2025-10-10 06:32:19 - __main__ - INFO - Average epoch_depth_loss: 0.002664 +2025-10-10 06:32:19 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 06:33:20 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-20000 +2025-10-10 06:33:46 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-20000/optimizer.bin +2025-10-10 06:33:46 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-20000/scheduler.bin +2025-10-10 06:33:46 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-20000/sampler.bin +2025-10-10 06:33:46 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-20000/random_states_0.pkl +2025-10-10 06:33:46 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-20000 +2025-10-10 07:14:01 - __main__ - INFO - Epoch 16 completed: +2025-10-10 07:14:01 - __main__ - INFO - Average epoch_total_loss: 0.028473 +2025-10-10 07:14:01 - __main__ - INFO - Average epoch_mse_loss: 0.005474 +2025-10-10 07:14:01 - __main__ - INFO - Average epoch_lpips_loss: 0.020508 +2025-10-10 07:14:01 - __main__ - INFO - Average epoch_depth_loss: 0.002492 +2025-10-10 07:14:01 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 07:53:55 - __main__ - INFO - Epoch 17 completed: +2025-10-10 07:53:55 - __main__ - INFO - Average epoch_total_loss: 0.029371 +2025-10-10 07:53:55 - __main__ - INFO - Average epoch_mse_loss: 0.005677 +2025-10-10 07:53:55 - __main__ - INFO - Average epoch_lpips_loss: 0.021067 +2025-10-10 07:53:55 - __main__ - INFO - Average epoch_depth_loss: 0.002627 +2025-10-10 07:53:55 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 08:33:16 - __main__ - INFO - Epoch 18 completed: +2025-10-10 08:33:16 - __main__ - INFO - Average epoch_total_loss: 0.028648 +2025-10-10 08:33:16 - __main__ - INFO - Average epoch_mse_loss: 0.005469 +2025-10-10 08:33:16 - __main__ - INFO - Average epoch_lpips_loss: 0.020624 +2025-10-10 08:33:16 - __main__ - INFO - Average epoch_depth_loss: 0.002554 +2025-10-10 08:33:16 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 09:13:05 - __main__ - INFO - Epoch 19 completed: +2025-10-10 09:13:05 - __main__ - INFO - Average epoch_total_loss: 0.028673 +2025-10-10 09:13:05 - __main__ - INFO - Average epoch_mse_loss: 0.005502 +2025-10-10 09:13:05 - __main__ - INFO - Average epoch_lpips_loss: 0.020648 +2025-10-10 09:13:05 - __main__ - INFO - Average epoch_depth_loss: 0.002523 +2025-10-10 09:13:05 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 09:14:10 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-25000 +2025-10-10 09:14:34 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-25000/optimizer.bin +2025-10-10 09:14:34 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-25000/scheduler.bin +2025-10-10 09:14:34 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-25000/sampler.bin +2025-10-10 09:14:34 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-25000/random_states_0.pkl +2025-10-10 09:14:34 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-25000 +2025-10-10 09:54:25 - __main__ - INFO - Epoch 20 completed: +2025-10-10 09:54:25 - __main__ - INFO - Average epoch_total_loss: 0.028308 +2025-10-10 09:54:25 - __main__ - INFO - Average epoch_mse_loss: 0.005388 +2025-10-10 09:54:25 - __main__ - INFO - Average epoch_lpips_loss: 0.020426 +2025-10-10 09:54:25 - __main__ - INFO - Average epoch_depth_loss: 0.002494 +2025-10-10 09:54:25 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 10:35:20 - __main__ - INFO - Epoch 21 completed: +2025-10-10 10:35:20 - __main__ - INFO - Average epoch_total_loss: 0.027933 +2025-10-10 10:35:20 - __main__ - INFO - Average epoch_mse_loss: 0.005300 +2025-10-10 10:35:20 - __main__ - INFO - Average epoch_lpips_loss: 0.020227 +2025-10-10 10:35:20 - __main__ - INFO - Average epoch_depth_loss: 0.002406 +2025-10-10 10:35:20 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 11:16:20 - __main__ - INFO - Epoch 22 completed: +2025-10-10 11:16:20 - __main__ - INFO - Average epoch_total_loss: 0.027613 +2025-10-10 11:16:20 - __main__ - INFO - Average epoch_mse_loss: 0.005207 +2025-10-10 11:16:20 - __main__ - INFO - Average epoch_lpips_loss: 0.020018 +2025-10-10 11:16:20 - __main__ - INFO - Average epoch_depth_loss: 0.002388 +2025-10-10 11:16:20 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 11:57:02 - __main__ - INFO - Epoch 23 completed: +2025-10-10 11:57:02 - __main__ - INFO - Average epoch_total_loss: 0.027517 +2025-10-10 11:57:02 - __main__ - INFO - Average epoch_mse_loss: 0.005215 +2025-10-10 11:57:02 - __main__ - INFO - Average epoch_lpips_loss: 0.019881 +2025-10-10 11:57:02 - __main__ - INFO - Average epoch_depth_loss: 0.002421 +2025-10-10 11:57:02 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 11:58:15 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-30000 +2025-10-10 11:58:39 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-30000/optimizer.bin +2025-10-10 11:58:39 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-30000/scheduler.bin +2025-10-10 11:58:39 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-30000/sampler.bin +2025-10-10 11:58:39 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-30000/random_states_0.pkl +2025-10-10 11:58:39 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-30000 +2025-10-10 12:38:01 - __main__ - INFO - Epoch 24 completed: +2025-10-10 12:38:01 - __main__ - INFO - Average epoch_total_loss: 0.028260 +2025-10-10 12:38:01 - __main__ - INFO - Average epoch_mse_loss: 0.005394 +2025-10-10 12:38:01 - __main__ - INFO - Average epoch_lpips_loss: 0.020301 +2025-10-10 12:38:01 - __main__ - INFO - Average epoch_depth_loss: 0.002564 +2025-10-10 12:38:01 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 13:17:43 - __main__ - INFO - Epoch 25 completed: +2025-10-10 13:17:43 - __main__ - INFO - Average epoch_total_loss: 0.027963 +2025-10-10 13:17:43 - __main__ - INFO - Average epoch_mse_loss: 0.005314 +2025-10-10 13:17:43 - __main__ - INFO - Average epoch_lpips_loss: 0.020205 +2025-10-10 13:17:43 - __main__ - INFO - Average epoch_depth_loss: 0.002444 +2025-10-10 13:17:43 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 13:57:40 - __main__ - INFO - Epoch 26 completed: +2025-10-10 13:57:40 - __main__ - INFO - Average epoch_total_loss: 0.026895 +2025-10-10 13:57:40 - __main__ - INFO - Average epoch_mse_loss: 0.005051 +2025-10-10 13:57:40 - __main__ - INFO - Average epoch_lpips_loss: 0.019557 +2025-10-10 13:57:40 - __main__ - INFO - Average epoch_depth_loss: 0.002287 +2025-10-10 13:57:40 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 14:37:49 - __main__ - INFO - Epoch 27 completed: +2025-10-10 14:37:49 - __main__ - INFO - Average epoch_total_loss: 0.027154 +2025-10-10 14:37:49 - __main__ - INFO - Average epoch_mse_loss: 0.005088 +2025-10-10 14:37:49 - __main__ - INFO - Average epoch_lpips_loss: 0.019680 +2025-10-10 14:37:49 - __main__ - INFO - Average epoch_depth_loss: 0.002386 +2025-10-10 14:37:49 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 14:39:09 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-35000 +2025-10-10 14:39:34 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-35000/optimizer.bin +2025-10-10 14:39:34 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-35000/scheduler.bin +2025-10-10 14:39:34 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-35000/sampler.bin +2025-10-10 14:39:34 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-35000/random_states_0.pkl +2025-10-10 14:39:34 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-35000 +2025-10-10 15:19:12 - __main__ - INFO - Epoch 28 completed: +2025-10-10 15:19:12 - __main__ - INFO - Average epoch_total_loss: 0.027335 +2025-10-10 15:19:12 - __main__ - INFO - Average epoch_mse_loss: 0.005066 +2025-10-10 15:19:12 - __main__ - INFO - Average epoch_lpips_loss: 0.019806 +2025-10-10 15:19:12 - __main__ - INFO - Average epoch_depth_loss: 0.002462 +2025-10-10 15:19:12 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 16:00:02 - __main__ - INFO - Epoch 29 completed: +2025-10-10 16:00:02 - __main__ - INFO - Average epoch_total_loss: 0.027462 +2025-10-10 16:00:02 - __main__ - INFO - Average epoch_mse_loss: 0.005139 +2025-10-10 16:00:02 - __main__ - INFO - Average epoch_lpips_loss: 0.019871 +2025-10-10 16:00:02 - __main__ - INFO - Average epoch_depth_loss: 0.002453 +2025-10-10 16:00:02 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 16:40:58 - __main__ - INFO - Epoch 30 completed: +2025-10-10 16:40:58 - __main__ - INFO - Average epoch_total_loss: 0.026971 +2025-10-10 16:40:58 - __main__ - INFO - Average epoch_mse_loss: 0.005052 +2025-10-10 16:40:58 - __main__ - INFO - Average epoch_lpips_loss: 0.019617 +2025-10-10 16:40:58 - __main__ - INFO - Average epoch_depth_loss: 0.002301 +2025-10-10 16:40:58 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 17:21:50 - __main__ - INFO - Epoch 31 completed: +2025-10-10 17:21:50 - __main__ - INFO - Average epoch_total_loss: 0.026646 +2025-10-10 17:21:50 - __main__ - INFO - Average epoch_mse_loss: 0.004977 +2025-10-10 17:21:50 - __main__ - INFO - Average epoch_lpips_loss: 0.019345 +2025-10-10 17:21:50 - __main__ - INFO - Average epoch_depth_loss: 0.002324 +2025-10-10 17:21:50 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 17:23:17 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-40000 +2025-10-10 17:23:41 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-40000/optimizer.bin +2025-10-10 17:23:41 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-40000/scheduler.bin +2025-10-10 17:23:41 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-40000/sampler.bin +2025-10-10 17:23:41 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-40000/random_states_0.pkl +2025-10-10 17:23:41 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-40000 +2025-10-10 18:03:14 - __main__ - INFO - Epoch 32 completed: +2025-10-10 18:03:14 - __main__ - INFO - Average epoch_total_loss: 0.026585 +2025-10-10 18:03:14 - __main__ - INFO - Average epoch_mse_loss: 0.004967 +2025-10-10 18:03:14 - __main__ - INFO - Average epoch_lpips_loss: 0.019361 +2025-10-10 18:03:14 - __main__ - INFO - Average epoch_depth_loss: 0.002257 +2025-10-10 18:03:14 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 18:43:31 - __main__ - INFO - Epoch 33 completed: +2025-10-10 18:43:31 - __main__ - INFO - Average epoch_total_loss: 0.026801 +2025-10-10 18:43:31 - __main__ - INFO - Average epoch_mse_loss: 0.005020 +2025-10-10 18:43:31 - __main__ - INFO - Average epoch_lpips_loss: 0.019496 +2025-10-10 18:43:31 - __main__ - INFO - Average epoch_depth_loss: 0.002285 +2025-10-10 18:43:31 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 19:23:37 - __main__ - INFO - Epoch 34 completed: +2025-10-10 19:23:37 - __main__ - INFO - Average epoch_total_loss: 0.027022 +2025-10-10 19:23:37 - __main__ - INFO - Average epoch_mse_loss: 0.005057 +2025-10-10 19:23:37 - __main__ - INFO - Average epoch_lpips_loss: 0.019646 +2025-10-10 19:23:37 - __main__ - INFO - Average epoch_depth_loss: 0.002320 +2025-10-10 19:23:37 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 20:03:52 - __main__ - INFO - Epoch 35 completed: +2025-10-10 20:03:52 - __main__ - INFO - Average epoch_total_loss: 0.026400 +2025-10-10 20:03:52 - __main__ - INFO - Average epoch_mse_loss: 0.004879 +2025-10-10 20:03:52 - __main__ - INFO - Average epoch_lpips_loss: 0.019248 +2025-10-10 20:03:52 - __main__ - INFO - Average epoch_depth_loss: 0.002274 +2025-10-10 20:03:52 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 20:05:28 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-45000 +2025-10-10 20:05:52 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-45000/optimizer.bin +2025-10-10 20:05:52 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-45000/scheduler.bin +2025-10-10 20:05:52 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-45000/sampler.bin +2025-10-10 20:05:52 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-45000/random_states_0.pkl +2025-10-10 20:05:52 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-45000 +2025-10-10 20:45:22 - __main__ - INFO - Epoch 36 completed: +2025-10-10 20:45:22 - __main__ - INFO - Average epoch_total_loss: 0.026367 +2025-10-10 20:45:22 - __main__ - INFO - Average epoch_mse_loss: 0.004865 +2025-10-10 20:45:22 - __main__ - INFO - Average epoch_lpips_loss: 0.019218 +2025-10-10 20:45:22 - __main__ - INFO - Average epoch_depth_loss: 0.002284 +2025-10-10 20:45:22 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 21:26:08 - __main__ - INFO - Epoch 37 completed: +2025-10-10 21:26:08 - __main__ - INFO - Average epoch_total_loss: 0.026327 +2025-10-10 21:26:08 - __main__ - INFO - Average epoch_mse_loss: 0.004878 +2025-10-10 21:26:08 - __main__ - INFO - Average epoch_lpips_loss: 0.019213 +2025-10-10 21:26:08 - __main__ - INFO - Average epoch_depth_loss: 0.002236 +2025-10-10 21:26:08 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 22:06:57 - __main__ - INFO - Epoch 38 completed: +2025-10-10 22:06:57 - __main__ - INFO - Average epoch_total_loss: 0.025997 +2025-10-10 22:06:57 - __main__ - INFO - Average epoch_mse_loss: 0.004814 +2025-10-10 22:06:57 - __main__ - INFO - Average epoch_lpips_loss: 0.018939 +2025-10-10 22:06:57 - __main__ - INFO - Average epoch_depth_loss: 0.002244 +2025-10-10 22:06:57 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 22:47:47 - __main__ - INFO - Epoch 39 completed: +2025-10-10 22:47:47 - __main__ - INFO - Average epoch_total_loss: 0.026414 +2025-10-10 22:47:47 - __main__ - INFO - Average epoch_mse_loss: 0.004914 +2025-10-10 22:47:47 - __main__ - INFO - Average epoch_lpips_loss: 0.019216 +2025-10-10 22:47:47 - __main__ - INFO - Average epoch_depth_loss: 0.002283 +2025-10-10 22:47:47 - __main__ - INFO - Steps in epoch: 1249 +2025-10-10 22:49:30 - accelerate.accelerator - INFO - Saving current state to output_wildrgbd_gscollision/checkpoint-50000 +2025-10-10 22:49:53 - accelerate.checkpointing - INFO - Optimizer state saved in output_wildrgbd_gscollision/checkpoint-50000/optimizer.bin +2025-10-10 22:49:53 - accelerate.checkpointing - INFO - Scheduler state saved in output_wildrgbd_gscollision/checkpoint-50000/scheduler.bin +2025-10-10 22:49:53 - accelerate.checkpointing - INFO - Sampler state for dataloader 0 saved in output_wildrgbd_gscollision/checkpoint-50000/sampler.bin +2025-10-10 22:49:53 - accelerate.checkpointing - INFO - Random states saved in output_wildrgbd_gscollision/checkpoint-50000/random_states_0.pkl +2025-10-10 22:49:53 - __main__ - INFO - Saved checkpoint to output_wildrgbd_gscollision/checkpoint-50000