Add RoboDojo model (#7)
Browse files- Add RoboDojo model metadata (6fd149f2a019427d876207acf9ef26647f3089c2)
- Add PI0.5 tokenizer.json (6aad482459b443e0951db4b2e339c67a42e88192)
- Add PI0.5 tokenizer.model (9f6c787ade60c1f3f71492063230c6ae4b7da755)
- Add PI0 tokenizer.json (7d919c6dde35502c9931255561788e2266284faf)
- Add PI0 tokenizer.model (c38bbc5aad0142e43d81aaecb8de8b14b228a173)
- Add Cosmos3-Nano tokenizer.json (da806f6fc63b0ec61ac504245f6ee37cdc7642de)
- Add FastWAM spiece.model (61c3fc992aeefbd2d224dea1a2ea340a5b205944)
- Add FastWAM tokenizer.json (87fa2bd19f2d032cddbca68d5613c79e3d098fed)
- Add GR00T N1.7 tokenizer.json (a56823a7c900c2630988a5c50997d6ce41ef66ca)
- Add DiT4DiT tokenizer.json (5daec6a7e38f07ddb1062b359950cb333c54f36f)
- Add PI0.5 RoboDojo checkpoint (b241b6846222fcaaea6460486df5578201bc6009)
- Add PI0 RoboDojo checkpoint (c625b86f64f7fc65d4e170f99bb6fb3790daa927)
- Add GR00T N1.5 RoboDojo checkpoint (b199641ca905f9c740f19c2ff06ae86278d2deb0)
- Add SmolVLA RoboDojo checkpoint (9ce1d7adedff53b7c66a70959b52ad0fed5c77f0)
- Add Cosmos3-Nano RoboDojo checkpoint (3a8939105bca5c06281caef1a222e54427462eaa)
- Add FastWAM RoboDojo checkpoint (0f6b8a3cc3f35d8ae1c6d498fa45fa1b03f250df)
- Add GR00T N1.7 RoboDojo checkpoint (af0540210326f48ca5f2465226ca245afcf60b54)
- Add DiT4DiT RoboDojo checkpoint (0c2878ef6219c9fe9ea578967637cabd33c2dea7)
Co-authored-by: Jikun Rong <RJK@users.noreply.huggingface.co>
- .gitattributes +6 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/checkpoints/step-010000-epoch-11-loss=0.5575.safetensors +3 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/config.json +1499 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/config.yaml +1640 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/dataset_statistics.json +186 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/added_tokens.json +28 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/chat_template.jinja +120 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/merges.txt +0 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/special_tokens_map.json +31 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/tokenizer.json +3 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/tokenizer_config.json +239 -0
- cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/vocab.json +0 -0
- dit4dit_robodojo_full_finetune_bs128/checkpoints/step-120000-epoch-08-loss=0.0921.safetensors +3 -0
- dit4dit_robodojo_full_finetune_bs128/config.json +589 -0
- dit4dit_robodojo_full_finetune_bs128/config.yaml +494 -0
- dit4dit_robodojo_full_finetune_bs128/dataset_statistics.json +186 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/added_tokens.json +24 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/chat_template.jinja +7 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/merges.txt +0 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/special_tokens_map.json +31 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/tokenizer.json +3 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/tokenizer_config.json +207 -0
- dit4dit_robodojo_full_finetune_bs128/tokenizer/vocab.json +0 -0
- fastwam_robodojo_full_finetune_bs32/checkpoints/step-362452-epoch-06-loss=0.0978.safetensors +3 -0
- fastwam_robodojo_full_finetune_bs32/config.json +1024 -0
- fastwam_robodojo_full_finetune_bs32/config.yaml +880 -0
- fastwam_robodojo_full_finetune_bs32/dataset_statistics.json +186 -0
- fastwam_robodojo_full_finetune_bs32/tokenizer/special_tokens_map.json +308 -0
- fastwam_robodojo_full_finetune_bs32/tokenizer/spiece.model +3 -0
- fastwam_robodojo_full_finetune_bs32/tokenizer/tokenizer.json +3 -0
- fastwam_robodojo_full_finetune_bs32/tokenizer/tokenizer_config.json +2748 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/checkpoints/step-100000-epoch-34-loss=0.0064.safetensors +3 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/config.json +860 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/config.yaml +719 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/dataset_statistics.json +202 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/tokenizer/added_tokens.json +39 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/tokenizer/merges.txt +0 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/tokenizer/special_tokens_map.json +42 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/tokenizer/tokenizer_config.json +344 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/tokenizer/vocab.json +0 -0
- gr00t_eagle_3b_robodojo_full_finetune_bs640/vlm_backbone_config.json +115 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/checkpoints/step-065394-epoch-18-loss=0.0033.safetensors +3 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/config.json +0 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/config.yaml +0 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/dataset_statistics.json +622 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/added_tokens.json +48 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/merges.txt +0 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/special_tokens_map.json +31 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/tokenizer.json +3 -0
- gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/tokenizer_config.json +340 -0
|
@@ -64,3 +64,9 @@ Qwen3-VL-0.6B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 64 |
dit4dit_robocasa_full_data_full_finetune_bs64/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 65 |
dit4dit_robocasa_full_data_full_finetune_bs64/dit4dit_robocasa_full_data_full_finetune_2026_08_29_12_40_23.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 66 |
fastwam_robocasa_full_data_full_finetune_bs256/fastwam_robocasa_full_data_full_finetune_2026_08_28_13_54_01.jsonl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
dit4dit_robocasa_full_data_full_finetune_bs64/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 65 |
dit4dit_robocasa_full_data_full_finetune_bs64/dit4dit_robocasa_full_data_full_finetune_2026_08_29_12_40_23.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 66 |
fastwam_robocasa_full_data_full_finetune_bs256/fastwam_robocasa_full_data_full_finetune_2026_08_28_13_54_01.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
pi05_paligemma_robodojo_full_finetune_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
pi0_paligemma_robodojo_full_finetune_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
fastwam_robodojo_full_finetune_bs32/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
gr00t_n17_qwen3vl_2b_robodojo_full_finetune_freeze_vlm_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
dit4dit_robodojo_full_finetune_bs128/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e34e462b13decff981308acd779dea9785ce511f5246f8f6d33fa44ceda9406d
|
| 3 |
+
size 63511447112
|
|
@@ -0,0 +1,1499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_ACTION_DIM": 14,
|
| 3 |
+
"_ACTION_HORIZON": 32,
|
| 4 |
+
"_CONDITIONING_FPS": 25,
|
| 5 |
+
"_EMBODIMENT_ID": 31,
|
| 6 |
+
"_FRAME_WINDOW_SIZE": 33,
|
| 7 |
+
"_IMAGE_HEIGHT": 192,
|
| 8 |
+
"_IMAGE_WIDTH": 256,
|
| 9 |
+
"_MAX_ACTION_DIM": 64,
|
| 10 |
+
"_MAX_STATE_DIM": 64,
|
| 11 |
+
"_PREPEND_STATE_TO_ACTION": false,
|
| 12 |
+
"_ROBODOJO_ACTION_QUANTILES": {
|
| 13 |
+
"q01": [
|
| 14 |
+
-1.051365569829941,
|
| 15 |
+
-3.5348887174584814e-14,
|
| 16 |
+
1.741881830823392e-16,
|
| 17 |
+
-1.5984010362625123,
|
| 18 |
+
-0.6003574305772781,
|
| 19 |
+
-1.6678147149085998,
|
| 20 |
+
0,
|
| 21 |
+
-0.4509398394823074,
|
| 22 |
+
-2.5859282299029243e-14,
|
| 23 |
+
1.234041714549172e-16,
|
| 24 |
+
-1.64055180311203,
|
| 25 |
+
-1.2633746123313903,
|
| 26 |
+
-1.7645285475254058,
|
| 27 |
+
0
|
| 28 |
+
],
|
| 29 |
+
"q99": [
|
| 30 |
+
0.5431358617544174,
|
| 31 |
+
2.495765209197998,
|
| 32 |
+
2.492974226474762,
|
| 33 |
+
1.3241519677639007,
|
| 34 |
+
1.2496635341644287,
|
| 35 |
+
1.7392305016517635,
|
| 36 |
+
1,
|
| 37 |
+
1.0814965963363647,
|
| 38 |
+
2.4167031812667843,
|
| 39 |
+
2.3470158338546754,
|
| 40 |
+
1.141731116771698,
|
| 41 |
+
0.5208872479200363,
|
| 42 |
+
1.489715996980667,
|
| 43 |
+
1
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
"_ROBODOJO_DATA_ROOT": "./datasets/RoboDojo_lerobot_v21_video",
|
| 47 |
+
"_ROBODOJO_EPISODE_OVERRIDES": {
|
| 48 |
+
"arrange_largest_number": 25,
|
| 49 |
+
"arrange_largest_number_random": 25,
|
| 50 |
+
"fold_clothes": 25,
|
| 51 |
+
"fold_clothes_random": 25,
|
| 52 |
+
"hang_mugs": 25,
|
| 53 |
+
"hang_mugs_random": 25,
|
| 54 |
+
"make_toast": 25,
|
| 55 |
+
"make_toast_random": 25,
|
| 56 |
+
"pack_objects_into_box": 25,
|
| 57 |
+
"pack_objects_into_box_random": 25,
|
| 58 |
+
"pour_liquid_into_cup": 25,
|
| 59 |
+
"pour_liquid_into_cup_random": 25,
|
| 60 |
+
"push_T": 25,
|
| 61 |
+
"push_T_random": 25,
|
| 62 |
+
"sort_nesting_dolls_by_size": 25,
|
| 63 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 64 |
+
"stack_blocks": 25,
|
| 65 |
+
"stack_blocks_random": 25,
|
| 66 |
+
"stack_bowls": 25,
|
| 67 |
+
"stack_bowls_random": 25,
|
| 68 |
+
"store_laptop_and_headphones": 25,
|
| 69 |
+
"store_laptop_and_headphones_random": 25,
|
| 70 |
+
"sweep_blocks": 25,
|
| 71 |
+
"sweep_blocks_random": 25
|
| 72 |
+
},
|
| 73 |
+
"_ROBODOJO_GENERALIZATION_BASE_TASKS": [
|
| 74 |
+
"stack_bowls",
|
| 75 |
+
"push_T",
|
| 76 |
+
"pack_objects_into_box",
|
| 77 |
+
"fold_clothes",
|
| 78 |
+
"hang_mugs",
|
| 79 |
+
"sweep_blocks",
|
| 80 |
+
"pour_liquid_into_cup",
|
| 81 |
+
"make_toast",
|
| 82 |
+
"arrange_largest_number",
|
| 83 |
+
"sort_nesting_dolls_by_size",
|
| 84 |
+
"store_laptop_and_headphones",
|
| 85 |
+
"stack_blocks"
|
| 86 |
+
],
|
| 87 |
+
"_ROBODOJO_TRANSFORMS": [
|
| 88 |
+
{
|
| 89 |
+
"embodiment_id": 31,
|
| 90 |
+
"name_mappings": {
|
| 91 |
+
"actions": [
|
| 92 |
+
"actions"
|
| 93 |
+
],
|
| 94 |
+
"observation.state": [
|
| 95 |
+
"states"
|
| 96 |
+
]
|
| 97 |
+
},
|
| 98 |
+
"parquet_keys": [
|
| 99 |
+
"observation.state",
|
| 100 |
+
"timestamp",
|
| 101 |
+
"actions",
|
| 102 |
+
"info",
|
| 103 |
+
"stats",
|
| 104 |
+
"action_masks"
|
| 105 |
+
],
|
| 106 |
+
"type": "ProcessParquetInputs",
|
| 107 |
+
"video_keys": [
|
| 108 |
+
"observation.images.cam_high",
|
| 109 |
+
"observation.images.cam_left_wrist",
|
| 110 |
+
"observation.images.cam_right_wrist"
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"height": 192,
|
| 115 |
+
"type": "ResizeImages",
|
| 116 |
+
"width": 256
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"brightness_range": [
|
| 120 |
+
0.7,
|
| 121 |
+
1.3
|
| 122 |
+
],
|
| 123 |
+
"contrast_range": [
|
| 124 |
+
0.6,
|
| 125 |
+
1.4
|
| 126 |
+
],
|
| 127 |
+
"crop_ratio": [
|
| 128 |
+
1,
|
| 129 |
+
1
|
| 130 |
+
],
|
| 131 |
+
"crop_scale": [
|
| 132 |
+
0.95,
|
| 133 |
+
0.95
|
| 134 |
+
],
|
| 135 |
+
"hue_delta": 0.08,
|
| 136 |
+
"prob": 1,
|
| 137 |
+
"rotation_range": 0,
|
| 138 |
+
"saturation_range": [
|
| 139 |
+
0.5,
|
| 140 |
+
1.5
|
| 141 |
+
],
|
| 142 |
+
"type": "AugVideo"
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"action_metadata": {
|
| 146 |
+
"append_viewpoint": false,
|
| 147 |
+
"conditioning_fps": 25,
|
| 148 |
+
"frame_window_size": 33,
|
| 149 |
+
"video_height": 320,
|
| 150 |
+
"video_width": 256,
|
| 151 |
+
"viewpoint": "concat_view"
|
| 152 |
+
},
|
| 153 |
+
"cfg_dropout_rate": 0.1,
|
| 154 |
+
"format_prompt_as_json": true,
|
| 155 |
+
"max_len": 512,
|
| 156 |
+
"tokenizer": {
|
| 157 |
+
"model_max_length": 4096,
|
| 158 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 159 |
+
"padding_side": "right",
|
| 160 |
+
"trust_remote_code": true,
|
| 161 |
+
"type": "PretrainedTokenizer"
|
| 162 |
+
},
|
| 163 |
+
"type": "ProcessCosmos3Prompt"
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"type": "SimpleNormalizeImages"
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"action_dim": 64,
|
| 170 |
+
"action_key": "action",
|
| 171 |
+
"action_norm_type": "quantile",
|
| 172 |
+
"state_dim": 64,
|
| 173 |
+
"state_key": "proprio",
|
| 174 |
+
"state_norm_type": "none",
|
| 175 |
+
"type": "NormalizeStatesAndActions"
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"conditioning_fps": 25,
|
| 179 |
+
"frame_window_size": 33,
|
| 180 |
+
"mode": "wam",
|
| 181 |
+
"prepend_state_to_action": false,
|
| 182 |
+
"raw_action_dim": 14,
|
| 183 |
+
"type": "BuildCosmos3Sequence"
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"bottom_height_ratio": 0.5,
|
| 187 |
+
"bottom_views": [
|
| 188 |
+
1,
|
| 189 |
+
2
|
| 190 |
+
],
|
| 191 |
+
"frame_window_size": 33,
|
| 192 |
+
"num_views": 3,
|
| 193 |
+
"tile_direction": "top_bottom_pair",
|
| 194 |
+
"top_view": 0,
|
| 195 |
+
"type": "PrepareVideo"
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"height": 320,
|
| 199 |
+
"type": "ResizeAndReflectPad",
|
| 200 |
+
"width": 256
|
| 201 |
+
}
|
| 202 |
+
],
|
| 203 |
+
"_STATISTIC_NAME": "robodojo_arx_x5",
|
| 204 |
+
"_VAE_ENCODE_CHUNK_FRAMES": {
|
| 205 |
+
"256": 16,
|
| 206 |
+
"480": 24,
|
| 207 |
+
"720": 12
|
| 208 |
+
},
|
| 209 |
+
"_VIDEO_HEIGHT": 320,
|
| 210 |
+
"_VIDEO_WIDTH": 256,
|
| 211 |
+
"_action_dim": 10,
|
| 212 |
+
"_action_horizon": 16,
|
| 213 |
+
"_action_lr": 0.00025,
|
| 214 |
+
"_base_lr": "5e-05",
|
| 215 |
+
"_cfg_dropout_rate": 0.1,
|
| 216 |
+
"_ckpt_root": "./checkpoints",
|
| 217 |
+
"_conditioning_fps": 20,
|
| 218 |
+
"_cosmos3_nano_ckpt": "./checkpoints/Cosmos3-Nano",
|
| 219 |
+
"_cosmos3_nano_name_mapping": {
|
| 220 |
+
".self_attn.k_norm.": ".self_attn.norm_k.",
|
| 221 |
+
".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
|
| 222 |
+
".self_attn.k_proj.": ".self_attn.to_k.",
|
| 223 |
+
".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
|
| 224 |
+
".self_attn.o_proj.": ".self_attn.to_out.",
|
| 225 |
+
".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
|
| 226 |
+
".self_attn.q_norm.": ".self_attn.norm_q.",
|
| 227 |
+
".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
|
| 228 |
+
".self_attn.q_proj.": ".self_attn.to_q.",
|
| 229 |
+
".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
|
| 230 |
+
".self_attn.v_proj.": ".self_attn.to_v.",
|
| 231 |
+
".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
|
| 232 |
+
"action_in_proj.": "action_proj_in.",
|
| 233 |
+
"action_modality_embed": "action_modality_embed",
|
| 234 |
+
"action_out_proj.": "action_proj_out.",
|
| 235 |
+
"time_embedder.mlp.0.": "time_embedder.linear_1.",
|
| 236 |
+
"time_embedder.mlp.2.": "time_embedder.linear_2.",
|
| 237 |
+
"vision_in_proj.projector.": "proj_in.",
|
| 238 |
+
"vision_out_proj.projector.": "proj_out.",
|
| 239 |
+
"vlm_backbone.lm_head.weight": "lm_head.weight",
|
| 240 |
+
"vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
|
| 241 |
+
"vlm_backbone.model.language_model.layers.": "layers.",
|
| 242 |
+
"vlm_backbone.model.language_model.norm.weight": "norm.weight",
|
| 243 |
+
"vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
|
| 244 |
+
"vlm_backbone.model.visual.blocks.": "blocks.",
|
| 245 |
+
"vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
|
| 246 |
+
"vlm_backbone.model.visual.merger.": "merger.",
|
| 247 |
+
"vlm_backbone.model.visual.patch_embed.": "patch_embed.",
|
| 248 |
+
"vlm_backbone.model.visual.pos_embed.": "pos_embed."
|
| 249 |
+
},
|
| 250 |
+
"_cosmos3_nano_special_tokens": {
|
| 251 |
+
"end_of_generation": 151653,
|
| 252 |
+
"eos_token_id": 151645,
|
| 253 |
+
"start_of_generation": 151652
|
| 254 |
+
},
|
| 255 |
+
"_cosmos3_nano_tokenizer": {
|
| 256 |
+
"model_max_length": 4096,
|
| 257 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 258 |
+
"padding_side": "right",
|
| 259 |
+
"trust_remote_code": true,
|
| 260 |
+
"type": "PretrainedTokenizer"
|
| 261 |
+
},
|
| 262 |
+
"_cosmos3_nano_transformer": "./checkpoints/Cosmos3-Nano/transformer",
|
| 263 |
+
"_cosmos3_nano_vision_encoder": "./checkpoints/Cosmos3-Nano/vision_encoder",
|
| 264 |
+
"_cosmos3_nano_vlm_config": {
|
| 265 |
+
"image_token_id": 151655,
|
| 266 |
+
"model_type": "qwen3_vl",
|
| 267 |
+
"text_config": {
|
| 268 |
+
"attention_bias": false,
|
| 269 |
+
"attention_dropout": 0,
|
| 270 |
+
"bos_token_id": 151643,
|
| 271 |
+
"eos_token_id": 151645,
|
| 272 |
+
"head_dim": 128,
|
| 273 |
+
"hidden_act": "silu",
|
| 274 |
+
"hidden_size": 4096,
|
| 275 |
+
"intermediate_size": 12288,
|
| 276 |
+
"layer_types": [
|
| 277 |
+
"full_attention",
|
| 278 |
+
"full_attention",
|
| 279 |
+
"full_attention",
|
| 280 |
+
"full_attention",
|
| 281 |
+
"full_attention",
|
| 282 |
+
"full_attention",
|
| 283 |
+
"full_attention",
|
| 284 |
+
"full_attention",
|
| 285 |
+
"full_attention",
|
| 286 |
+
"full_attention",
|
| 287 |
+
"full_attention",
|
| 288 |
+
"full_attention",
|
| 289 |
+
"full_attention",
|
| 290 |
+
"full_attention",
|
| 291 |
+
"full_attention",
|
| 292 |
+
"full_attention",
|
| 293 |
+
"full_attention",
|
| 294 |
+
"full_attention",
|
| 295 |
+
"full_attention",
|
| 296 |
+
"full_attention",
|
| 297 |
+
"full_attention",
|
| 298 |
+
"full_attention",
|
| 299 |
+
"full_attention",
|
| 300 |
+
"full_attention",
|
| 301 |
+
"full_attention",
|
| 302 |
+
"full_attention",
|
| 303 |
+
"full_attention",
|
| 304 |
+
"full_attention",
|
| 305 |
+
"full_attention",
|
| 306 |
+
"full_attention",
|
| 307 |
+
"full_attention",
|
| 308 |
+
"full_attention",
|
| 309 |
+
"full_attention",
|
| 310 |
+
"full_attention",
|
| 311 |
+
"full_attention",
|
| 312 |
+
"full_attention"
|
| 313 |
+
],
|
| 314 |
+
"max_position_embeddings": 262144,
|
| 315 |
+
"model_type": "qwen3_vl_text",
|
| 316 |
+
"num_attention_heads": 32,
|
| 317 |
+
"num_hidden_layers": 36,
|
| 318 |
+
"num_key_value_heads": 8,
|
| 319 |
+
"pad_token_id": 0,
|
| 320 |
+
"rms_norm_eps": "1e-06",
|
| 321 |
+
"rope_scaling": {
|
| 322 |
+
"mrope_interleaved": true,
|
| 323 |
+
"mrope_section": [
|
| 324 |
+
24,
|
| 325 |
+
20,
|
| 326 |
+
20
|
| 327 |
+
],
|
| 328 |
+
"rope_type": "default"
|
| 329 |
+
},
|
| 330 |
+
"rope_theta": 5000000,
|
| 331 |
+
"tie_word_embeddings": false,
|
| 332 |
+
"vocab_size": 151936
|
| 333 |
+
},
|
| 334 |
+
"tie_word_embeddings": false,
|
| 335 |
+
"video_token_id": 151656,
|
| 336 |
+
"vision_config": {
|
| 337 |
+
"deepstack_visual_indexes": [
|
| 338 |
+
8,
|
| 339 |
+
16,
|
| 340 |
+
24
|
| 341 |
+
],
|
| 342 |
+
"depth": 27,
|
| 343 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 344 |
+
"hidden_size": 1152,
|
| 345 |
+
"in_channels": 3,
|
| 346 |
+
"initializer_range": 0.02,
|
| 347 |
+
"intermediate_size": 4304,
|
| 348 |
+
"model_type": "qwen3_vl",
|
| 349 |
+
"num_heads": 16,
|
| 350 |
+
"num_position_embeddings": 2304,
|
| 351 |
+
"out_hidden_size": 4096,
|
| 352 |
+
"patch_size": 16,
|
| 353 |
+
"spatial_merge_size": 2,
|
| 354 |
+
"temporal_patch_size": 2
|
| 355 |
+
},
|
| 356 |
+
"vision_end_token_id": 151653,
|
| 357 |
+
"vision_start_token_id": 151652,
|
| 358 |
+
"vocab_size": 151936
|
| 359 |
+
},
|
| 360 |
+
"_frame_window_size": 17,
|
| 361 |
+
"_grad_accumulation_steps": 8,
|
| 362 |
+
"_image_height": 256,
|
| 363 |
+
"_image_width": 256,
|
| 364 |
+
"_libero_action_stats": {
|
| 365 |
+
"max": [
|
| 366 |
+
0.9375,
|
| 367 |
+
0.9375,
|
| 368 |
+
0.9375,
|
| 369 |
+
1,
|
| 370 |
+
0.368853,
|
| 371 |
+
0.341214,
|
| 372 |
+
0.356395,
|
| 373 |
+
1,
|
| 374 |
+
0.348251,
|
| 375 |
+
1
|
| 376 |
+
],
|
| 377 |
+
"mean": [
|
| 378 |
+
0.050704,
|
| 379 |
+
0.097407,
|
| 380 |
+
-0.094833,
|
| 381 |
+
0.994873,
|
| 382 |
+
-0.004579,
|
| 383 |
+
-0.004288,
|
| 384 |
+
0.004389,
|
| 385 |
+
0.996104,
|
| 386 |
+
0.001109,
|
| 387 |
+
0.476725
|
| 388 |
+
],
|
| 389 |
+
"min": [
|
| 390 |
+
-0.9375,
|
| 391 |
+
-0.9375,
|
| 392 |
+
-0.9375,
|
| 393 |
+
0.902028,
|
| 394 |
+
-0.356085,
|
| 395 |
+
-0.367416,
|
| 396 |
+
-0.370434,
|
| 397 |
+
0.921907,
|
| 398 |
+
-0.255,
|
| 399 |
+
0
|
| 400 |
+
],
|
| 401 |
+
"q01": [
|
| 402 |
+
-0.723214,
|
| 403 |
+
-0.808929,
|
| 404 |
+
-0.9375,
|
| 405 |
+
0.934955,
|
| 406 |
+
-0.223431,
|
| 407 |
+
-0.189878,
|
| 408 |
+
-0.334735,
|
| 409 |
+
0.938516,
|
| 410 |
+
-0.107736,
|
| 411 |
+
0
|
| 412 |
+
],
|
| 413 |
+
"q99": [
|
| 414 |
+
0.9375,
|
| 415 |
+
0.870536,
|
| 416 |
+
0.9375,
|
| 417 |
+
1,
|
| 418 |
+
0.331,
|
| 419 |
+
0.163153,
|
| 420 |
+
0.226216,
|
| 421 |
+
1,
|
| 422 |
+
0.127158,
|
| 423 |
+
1
|
| 424 |
+
],
|
| 425 |
+
"std": [
|
| 426 |
+
0.333621,
|
| 427 |
+
0.387175,
|
| 428 |
+
0.45714,
|
| 429 |
+
0.010807,
|
| 430 |
+
0.077802,
|
| 431 |
+
0.063386,
|
| 432 |
+
0.078571,
|
| 433 |
+
0.009994,
|
| 434 |
+
0.038504,
|
| 435 |
+
0.49946
|
| 436 |
+
]
|
| 437 |
+
},
|
| 438 |
+
"_max_action_dim": 64,
|
| 439 |
+
"_max_state_dim": 64,
|
| 440 |
+
"_max_steps": 2000,
|
| 441 |
+
"_per_device_batch_size": 16,
|
| 442 |
+
"_prepend_state_to_action": false,
|
| 443 |
+
"_save_iter_interval": 500,
|
| 444 |
+
"_transforms": [
|
| 445 |
+
{
|
| 446 |
+
"embodiment_id": 5,
|
| 447 |
+
"name_mappings": {
|
| 448 |
+
"actions": [
|
| 449 |
+
"actions"
|
| 450 |
+
],
|
| 451 |
+
"observation.state": [
|
| 452 |
+
"states"
|
| 453 |
+
]
|
| 454 |
+
},
|
| 455 |
+
"parquet_keys": [
|
| 456 |
+
"observation.state",
|
| 457 |
+
"timestamp",
|
| 458 |
+
"actions",
|
| 459 |
+
"info",
|
| 460 |
+
"stats",
|
| 461 |
+
"action_masks"
|
| 462 |
+
],
|
| 463 |
+
"type": "ProcessParquetInputs",
|
| 464 |
+
"video_keys": [
|
| 465 |
+
"observation.images.image",
|
| 466 |
+
"observation.images.wrist_image"
|
| 467 |
+
]
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"type": "LiberoFramewiseActionToRot6D"
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"action_metadata": {
|
| 474 |
+
"append_viewpoint": false,
|
| 475 |
+
"conditioning_fps": 20,
|
| 476 |
+
"frame_window_size": 17,
|
| 477 |
+
"video_height": 192,
|
| 478 |
+
"video_width": 320
|
| 479 |
+
},
|
| 480 |
+
"cfg_dropout_rate": 0.1,
|
| 481 |
+
"format_prompt_as_json": true,
|
| 482 |
+
"max_len": 512,
|
| 483 |
+
"tokenizer": {
|
| 484 |
+
"model_max_length": 4096,
|
| 485 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 486 |
+
"padding_side": "right",
|
| 487 |
+
"trust_remote_code": true,
|
| 488 |
+
"type": "PretrainedTokenizer"
|
| 489 |
+
},
|
| 490 |
+
"type": "ProcessCosmos3Prompt"
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"height": 256,
|
| 494 |
+
"type": "ResizeImages",
|
| 495 |
+
"width": 256
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"type": "SimpleNormalizeImages"
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"action_dim": 64,
|
| 502 |
+
"action_key": "action",
|
| 503 |
+
"action_norm_type": "quantile",
|
| 504 |
+
"state_dim": 64,
|
| 505 |
+
"state_key": "proprio",
|
| 506 |
+
"state_norm_type": "none",
|
| 507 |
+
"type": "NormalizeStatesAndActions"
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"conditioning_fps": 20,
|
| 511 |
+
"frame_window_size": 17,
|
| 512 |
+
"mode": "wam",
|
| 513 |
+
"prepend_state_to_action": false,
|
| 514 |
+
"raw_action_dim": 10,
|
| 515 |
+
"type": "BuildCosmos3Sequence"
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"frame_window_size": 17,
|
| 519 |
+
"num_views": 2,
|
| 520 |
+
"tile_direction": "horizontal",
|
| 521 |
+
"type": "PrepareVideo"
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"height": 192,
|
| 525 |
+
"type": "ResizeAndReflectPad",
|
| 526 |
+
"width": 320
|
| 527 |
+
}
|
| 528 |
+
],
|
| 529 |
+
"_video_height": 192,
|
| 530 |
+
"_video_width": 320,
|
| 531 |
+
"_vision_vae": {
|
| 532 |
+
"encode_exact_durations": [
|
| 533 |
+
17
|
| 534 |
+
],
|
| 535 |
+
"pretrained_name_or_path": "./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
|
| 536 |
+
"type": "Cosmos3Wan22VAE"
|
| 537 |
+
},
|
| 538 |
+
"_wan22_vae_path": "./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
|
| 539 |
+
"eval": {
|
| 540 |
+
"dataset": {
|
| 541 |
+
"transforms": [
|
| 542 |
+
{
|
| 543 |
+
"embodiment_id": 31,
|
| 544 |
+
"img_keys": [
|
| 545 |
+
"cam_high",
|
| 546 |
+
"cam_left_wrist",
|
| 547 |
+
"cam_right_wrist"
|
| 548 |
+
],
|
| 549 |
+
"type": "ProcessEvalInputs"
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"conditioning_fps": 25,
|
| 553 |
+
"prepend_state_to_action": false,
|
| 554 |
+
"type": "SetCosmos3ActionMetadata"
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"action_metadata": {
|
| 558 |
+
"append_viewpoint": false,
|
| 559 |
+
"conditioning_fps": 25,
|
| 560 |
+
"frame_window_size": 33,
|
| 561 |
+
"video_height": 320,
|
| 562 |
+
"video_width": 256,
|
| 563 |
+
"viewpoint": "concat_view"
|
| 564 |
+
},
|
| 565 |
+
"cfg_dropout_rate": 0,
|
| 566 |
+
"format_prompt_as_json": true,
|
| 567 |
+
"max_len": 512,
|
| 568 |
+
"output_attention_mask_key": "lang_masks",
|
| 569 |
+
"output_key": "lang_tokens",
|
| 570 |
+
"tokenizer": {
|
| 571 |
+
"model_max_length": 4096,
|
| 572 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 573 |
+
"padding_side": "right",
|
| 574 |
+
"trust_remote_code": true,
|
| 575 |
+
"type": "PretrainedTokenizer"
|
| 576 |
+
},
|
| 577 |
+
"type": "ProcessCosmos3Prompt"
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"image_resize_strategy": "resize-naive",
|
| 581 |
+
"input_sizes": [
|
| 582 |
+
[
|
| 583 |
+
3,
|
| 584 |
+
256,
|
| 585 |
+
192
|
| 586 |
+
],
|
| 587 |
+
[
|
| 588 |
+
3,
|
| 589 |
+
256,
|
| 590 |
+
192
|
| 591 |
+
],
|
| 592 |
+
[
|
| 593 |
+
3,
|
| 594 |
+
256,
|
| 595 |
+
192
|
| 596 |
+
]
|
| 597 |
+
],
|
| 598 |
+
"means": [
|
| 599 |
+
[
|
| 600 |
+
127.5,
|
| 601 |
+
127.5,
|
| 602 |
+
127.5
|
| 603 |
+
],
|
| 604 |
+
[
|
| 605 |
+
127.5,
|
| 606 |
+
127.5,
|
| 607 |
+
127.5
|
| 608 |
+
],
|
| 609 |
+
[
|
| 610 |
+
127.5,
|
| 611 |
+
127.5,
|
| 612 |
+
127.5
|
| 613 |
+
]
|
| 614 |
+
],
|
| 615 |
+
"stds": [
|
| 616 |
+
[
|
| 617 |
+
127.5,
|
| 618 |
+
127.5,
|
| 619 |
+
127.5
|
| 620 |
+
],
|
| 621 |
+
[
|
| 622 |
+
127.5,
|
| 623 |
+
127.5,
|
| 624 |
+
127.5
|
| 625 |
+
],
|
| 626 |
+
[
|
| 627 |
+
127.5,
|
| 628 |
+
127.5,
|
| 629 |
+
127.5
|
| 630 |
+
]
|
| 631 |
+
],
|
| 632 |
+
"type": "TransformImage"
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"bottom_height_ratio": 0.5,
|
| 636 |
+
"bottom_views": [
|
| 637 |
+
1,
|
| 638 |
+
2
|
| 639 |
+
],
|
| 640 |
+
"frame_window_size": 1,
|
| 641 |
+
"num_views": 3,
|
| 642 |
+
"tile_direction": "top_bottom_pair",
|
| 643 |
+
"top_view": 0,
|
| 644 |
+
"type": "PrepareVideo"
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"height": 320,
|
| 648 |
+
"type": "ResizeAndReflectPad",
|
| 649 |
+
"width": 256
|
| 650 |
+
}
|
| 651 |
+
],
|
| 652 |
+
"type": "RoboDojoEvalDataset",
|
| 653 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 654 |
+
},
|
| 655 |
+
"denormalize_action": {
|
| 656 |
+
"action_dim": 14,
|
| 657 |
+
"norm_type": "quantile",
|
| 658 |
+
"statistic_name": "robodojo_arx_x5",
|
| 659 |
+
"type": "DenormalizePrivateAction"
|
| 660 |
+
},
|
| 661 |
+
"enable_mixed_precision_training": true,
|
| 662 |
+
"eval_chunk_size": 32,
|
| 663 |
+
"mixed_precision_dtype": "bf16",
|
| 664 |
+
"model_family": "cosmos3",
|
| 665 |
+
"num_trials_per_task": 50,
|
| 666 |
+
"num_trials_per_task_overrides": {
|
| 667 |
+
"arrange_largest_number": 25,
|
| 668 |
+
"arrange_largest_number_random": 25,
|
| 669 |
+
"fold_clothes": 25,
|
| 670 |
+
"fold_clothes_random": 25,
|
| 671 |
+
"hang_mugs": 25,
|
| 672 |
+
"hang_mugs_random": 25,
|
| 673 |
+
"make_toast": 25,
|
| 674 |
+
"make_toast_random": 25,
|
| 675 |
+
"pack_objects_into_box": 25,
|
| 676 |
+
"pack_objects_into_box_random": 25,
|
| 677 |
+
"pour_liquid_into_cup": 25,
|
| 678 |
+
"pour_liquid_into_cup_random": 25,
|
| 679 |
+
"push_T": 25,
|
| 680 |
+
"push_T_random": 25,
|
| 681 |
+
"sort_nesting_dolls_by_size": 25,
|
| 682 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 683 |
+
"stack_blocks": 25,
|
| 684 |
+
"stack_blocks_random": 25,
|
| 685 |
+
"stack_bowls": 25,
|
| 686 |
+
"stack_bowls_random": 25,
|
| 687 |
+
"store_laptop_and_headphones": 25,
|
| 688 |
+
"store_laptop_and_headphones_random": 25,
|
| 689 |
+
"sweep_blocks": 25,
|
| 690 |
+
"sweep_blocks_random": 25
|
| 691 |
+
},
|
| 692 |
+
"report_kind": "robodojo",
|
| 693 |
+
"task_suite_name": "robodojo"
|
| 694 |
+
},
|
| 695 |
+
"inference_model": {
|
| 696 |
+
"action_horizon": 32,
|
| 697 |
+
"action_in_proj": {
|
| 698 |
+
"input_size": 64,
|
| 699 |
+
"num_domains": 32,
|
| 700 |
+
"output_size": 4096,
|
| 701 |
+
"type": "DomainAwareLinear"
|
| 702 |
+
},
|
| 703 |
+
"action_out_proj": {
|
| 704 |
+
"input_size": 4096,
|
| 705 |
+
"num_domains": 32,
|
| 706 |
+
"output_size": 64,
|
| 707 |
+
"type": "DomainAwareLinear"
|
| 708 |
+
},
|
| 709 |
+
"base_fps": 24,
|
| 710 |
+
"enable_fps_modulation": true,
|
| 711 |
+
"enable_vision_loss": true,
|
| 712 |
+
"freeze_non_moe_vlm_backbone": true,
|
| 713 |
+
"freeze_vlm_backbone": false,
|
| 714 |
+
"latent_patch_size": 2,
|
| 715 |
+
"max_action_dim": 64,
|
| 716 |
+
"name_mapping": {
|
| 717 |
+
".self_attn.k_norm.": ".self_attn.norm_k.",
|
| 718 |
+
".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
|
| 719 |
+
".self_attn.k_proj.": ".self_attn.to_k.",
|
| 720 |
+
".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
|
| 721 |
+
".self_attn.o_proj.": ".self_attn.to_out.",
|
| 722 |
+
".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
|
| 723 |
+
".self_attn.q_norm.": ".self_attn.norm_q.",
|
| 724 |
+
".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
|
| 725 |
+
".self_attn.q_proj.": ".self_attn.to_q.",
|
| 726 |
+
".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
|
| 727 |
+
".self_attn.v_proj.": ".self_attn.to_v.",
|
| 728 |
+
".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
|
| 729 |
+
"action_in_proj.": "action_proj_in.",
|
| 730 |
+
"action_modality_embed": "action_modality_embed",
|
| 731 |
+
"action_out_proj.": "action_proj_out.",
|
| 732 |
+
"time_embedder.mlp.0.": "time_embedder.linear_1.",
|
| 733 |
+
"time_embedder.mlp.2.": "time_embedder.linear_2.",
|
| 734 |
+
"vision_in_proj.projector.": "proj_in.",
|
| 735 |
+
"vision_out_proj.projector.": "proj_out.",
|
| 736 |
+
"vlm_backbone.lm_head.weight": "lm_head.weight",
|
| 737 |
+
"vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
|
| 738 |
+
"vlm_backbone.model.language_model.layers.": "layers.",
|
| 739 |
+
"vlm_backbone.model.language_model.norm.weight": "norm.weight",
|
| 740 |
+
"vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
|
| 741 |
+
"vlm_backbone.model.visual.blocks.": "blocks.",
|
| 742 |
+
"vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
|
| 743 |
+
"vlm_backbone.model.visual.merger.": "merger.",
|
| 744 |
+
"vlm_backbone.model.visual.patch_embed.": "patch_embed.",
|
| 745 |
+
"vlm_backbone.model.visual.pos_embed.": "pos_embed."
|
| 746 |
+
},
|
| 747 |
+
"num_embodiment_domains": 32,
|
| 748 |
+
"ori_action_dim": 14,
|
| 749 |
+
"packed_attention_backend": "flash2",
|
| 750 |
+
"position_embedding_type": "unified_3d_mrope",
|
| 751 |
+
"pretrained_name_or_path": "./checkpoints/Cosmos3-Nano/transformer",
|
| 752 |
+
"rectified_flow_inference_config": {
|
| 753 |
+
"num_steps": 30,
|
| 754 |
+
"num_train_timesteps": 1000,
|
| 755 |
+
"scheduler_type": "unipc",
|
| 756 |
+
"shift": 10,
|
| 757 |
+
"use_dynamic_shifting": false,
|
| 758 |
+
"use_karras_sigmas": false
|
| 759 |
+
},
|
| 760 |
+
"rectified_flow_training_config": {
|
| 761 |
+
"action_loss_weight": 10,
|
| 762 |
+
"high_sigma_ratio": 0.05,
|
| 763 |
+
"high_sigma_timesteps_max": 1000,
|
| 764 |
+
"high_sigma_timesteps_min": 995,
|
| 765 |
+
"independent_action_schedule": false,
|
| 766 |
+
"normalize_loss_by_active": false,
|
| 767 |
+
"shift": {
|
| 768 |
+
"256": 3,
|
| 769 |
+
"480": 5,
|
| 770 |
+
"720": 10
|
| 771 |
+
},
|
| 772 |
+
"shift_action": null,
|
| 773 |
+
"train_time_action_distribution": "logitnormal",
|
| 774 |
+
"train_time_image_distribution": "logitnormal",
|
| 775 |
+
"train_time_video_distribution": "waver",
|
| 776 |
+
"train_time_weight": "uniform",
|
| 777 |
+
"use_discrete_rf": false,
|
| 778 |
+
"use_dynamic_shift": false,
|
| 779 |
+
"use_high_sigma_strategy": false,
|
| 780 |
+
"use_high_sigma_strategy_action": false,
|
| 781 |
+
"vision_loss_weight": 10
|
| 782 |
+
},
|
| 783 |
+
"reinitialize_action_policy": true,
|
| 784 |
+
"special_tokens": {
|
| 785 |
+
"end_of_generation": 151653,
|
| 786 |
+
"eos_token_id": 151645,
|
| 787 |
+
"start_of_generation": 151652
|
| 788 |
+
},
|
| 789 |
+
"timestep_scale": 0.001,
|
| 790 |
+
"type": "Cosmos3FlowMatching",
|
| 791 |
+
"unified_3d_mrope_reset_spatial_ids": true,
|
| 792 |
+
"unified_3d_mrope_temporal_modality_margin": 15000,
|
| 793 |
+
"vision_in_proj": {
|
| 794 |
+
"in_dim": 192,
|
| 795 |
+
"out_dim": 4096,
|
| 796 |
+
"type": "LinearProjector"
|
| 797 |
+
},
|
| 798 |
+
"vision_latent_dim": 48,
|
| 799 |
+
"vision_out_proj": {
|
| 800 |
+
"in_dim": 4096,
|
| 801 |
+
"out_dim": 192,
|
| 802 |
+
"type": "LinearProjector"
|
| 803 |
+
},
|
| 804 |
+
"vision_vae": {
|
| 805 |
+
"encode_exact_durations": [
|
| 806 |
+
33
|
| 807 |
+
],
|
| 808 |
+
"pretrained_name_or_path": null,
|
| 809 |
+
"type": "Cosmos3Wan22VAE"
|
| 810 |
+
},
|
| 811 |
+
"vlm_backbone": {
|
| 812 |
+
"include_visual": false,
|
| 813 |
+
"skip_init_weights": true,
|
| 814 |
+
"type": "Cosmos3MoTBackbone",
|
| 815 |
+
"vision_encoder_path": "./checkpoints/Cosmos3-Nano/vision_encoder",
|
| 816 |
+
"vlm_config": {
|
| 817 |
+
"image_token_id": 151655,
|
| 818 |
+
"model_type": "qwen3_vl",
|
| 819 |
+
"text_config": {
|
| 820 |
+
"attention_bias": false,
|
| 821 |
+
"attention_dropout": 0,
|
| 822 |
+
"bos_token_id": 151643,
|
| 823 |
+
"eos_token_id": 151645,
|
| 824 |
+
"head_dim": 128,
|
| 825 |
+
"hidden_act": "silu",
|
| 826 |
+
"hidden_size": 4096,
|
| 827 |
+
"intermediate_size": 12288,
|
| 828 |
+
"layer_types": [
|
| 829 |
+
"full_attention",
|
| 830 |
+
"full_attention",
|
| 831 |
+
"full_attention",
|
| 832 |
+
"full_attention",
|
| 833 |
+
"full_attention",
|
| 834 |
+
"full_attention",
|
| 835 |
+
"full_attention",
|
| 836 |
+
"full_attention",
|
| 837 |
+
"full_attention",
|
| 838 |
+
"full_attention",
|
| 839 |
+
"full_attention",
|
| 840 |
+
"full_attention",
|
| 841 |
+
"full_attention",
|
| 842 |
+
"full_attention",
|
| 843 |
+
"full_attention",
|
| 844 |
+
"full_attention",
|
| 845 |
+
"full_attention",
|
| 846 |
+
"full_attention",
|
| 847 |
+
"full_attention",
|
| 848 |
+
"full_attention",
|
| 849 |
+
"full_attention",
|
| 850 |
+
"full_attention",
|
| 851 |
+
"full_attention",
|
| 852 |
+
"full_attention",
|
| 853 |
+
"full_attention",
|
| 854 |
+
"full_attention",
|
| 855 |
+
"full_attention",
|
| 856 |
+
"full_attention",
|
| 857 |
+
"full_attention",
|
| 858 |
+
"full_attention",
|
| 859 |
+
"full_attention",
|
| 860 |
+
"full_attention",
|
| 861 |
+
"full_attention",
|
| 862 |
+
"full_attention",
|
| 863 |
+
"full_attention",
|
| 864 |
+
"full_attention"
|
| 865 |
+
],
|
| 866 |
+
"max_position_embeddings": 262144,
|
| 867 |
+
"model_type": "qwen3_vl_text",
|
| 868 |
+
"num_attention_heads": 32,
|
| 869 |
+
"num_hidden_layers": 36,
|
| 870 |
+
"num_key_value_heads": 8,
|
| 871 |
+
"pad_token_id": 0,
|
| 872 |
+
"rms_norm_eps": "1e-06",
|
| 873 |
+
"rope_scaling": {
|
| 874 |
+
"mrope_interleaved": true,
|
| 875 |
+
"mrope_section": [
|
| 876 |
+
24,
|
| 877 |
+
20,
|
| 878 |
+
20
|
| 879 |
+
],
|
| 880 |
+
"rope_type": "default"
|
| 881 |
+
},
|
| 882 |
+
"rope_theta": 5000000,
|
| 883 |
+
"tie_word_embeddings": false,
|
| 884 |
+
"vocab_size": 151936
|
| 885 |
+
},
|
| 886 |
+
"tie_word_embeddings": false,
|
| 887 |
+
"video_token_id": 151656,
|
| 888 |
+
"vision_config": {
|
| 889 |
+
"deepstack_visual_indexes": [
|
| 890 |
+
8,
|
| 891 |
+
16,
|
| 892 |
+
24
|
| 893 |
+
],
|
| 894 |
+
"depth": 27,
|
| 895 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 896 |
+
"hidden_size": 1152,
|
| 897 |
+
"in_channels": 3,
|
| 898 |
+
"initializer_range": 0.02,
|
| 899 |
+
"intermediate_size": 4304,
|
| 900 |
+
"model_type": "qwen3_vl",
|
| 901 |
+
"num_heads": 16,
|
| 902 |
+
"num_position_embeddings": 2304,
|
| 903 |
+
"out_hidden_size": 4096,
|
| 904 |
+
"patch_size": 16,
|
| 905 |
+
"spatial_merge_size": 2,
|
| 906 |
+
"temporal_patch_size": 2
|
| 907 |
+
},
|
| 908 |
+
"vision_end_token_id": 151653,
|
| 909 |
+
"vision_start_token_id": 151652,
|
| 910 |
+
"vocab_size": 151936
|
| 911 |
+
}
|
| 912 |
+
}
|
| 913 |
+
},
|
| 914 |
+
"model": {
|
| 915 |
+
"action_horizon": 32,
|
| 916 |
+
"action_in_proj": {
|
| 917 |
+
"input_size": 64,
|
| 918 |
+
"num_domains": 32,
|
| 919 |
+
"output_size": 4096,
|
| 920 |
+
"type": "DomainAwareLinear"
|
| 921 |
+
},
|
| 922 |
+
"action_out_proj": {
|
| 923 |
+
"input_size": 4096,
|
| 924 |
+
"num_domains": 32,
|
| 925 |
+
"output_size": 64,
|
| 926 |
+
"type": "DomainAwareLinear"
|
| 927 |
+
},
|
| 928 |
+
"base_fps": 24,
|
| 929 |
+
"enable_fps_modulation": true,
|
| 930 |
+
"enable_vision_loss": true,
|
| 931 |
+
"freeze_non_moe_vlm_backbone": true,
|
| 932 |
+
"freeze_vlm_backbone": false,
|
| 933 |
+
"latent_patch_size": 2,
|
| 934 |
+
"max_action_dim": 64,
|
| 935 |
+
"name_mapping": {
|
| 936 |
+
".self_attn.k_norm.": ".self_attn.norm_k.",
|
| 937 |
+
".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
|
| 938 |
+
".self_attn.k_proj.": ".self_attn.to_k.",
|
| 939 |
+
".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
|
| 940 |
+
".self_attn.o_proj.": ".self_attn.to_out.",
|
| 941 |
+
".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
|
| 942 |
+
".self_attn.q_norm.": ".self_attn.norm_q.",
|
| 943 |
+
".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
|
| 944 |
+
".self_attn.q_proj.": ".self_attn.to_q.",
|
| 945 |
+
".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
|
| 946 |
+
".self_attn.v_proj.": ".self_attn.to_v.",
|
| 947 |
+
".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
|
| 948 |
+
"action_in_proj.": "action_proj_in.",
|
| 949 |
+
"action_modality_embed": "action_modality_embed",
|
| 950 |
+
"action_out_proj.": "action_proj_out.",
|
| 951 |
+
"time_embedder.mlp.0.": "time_embedder.linear_1.",
|
| 952 |
+
"time_embedder.mlp.2.": "time_embedder.linear_2.",
|
| 953 |
+
"vision_in_proj.projector.": "proj_in.",
|
| 954 |
+
"vision_out_proj.projector.": "proj_out.",
|
| 955 |
+
"vlm_backbone.lm_head.weight": "lm_head.weight",
|
| 956 |
+
"vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
|
| 957 |
+
"vlm_backbone.model.language_model.layers.": "layers.",
|
| 958 |
+
"vlm_backbone.model.language_model.norm.weight": "norm.weight",
|
| 959 |
+
"vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
|
| 960 |
+
"vlm_backbone.model.visual.blocks.": "blocks.",
|
| 961 |
+
"vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
|
| 962 |
+
"vlm_backbone.model.visual.merger.": "merger.",
|
| 963 |
+
"vlm_backbone.model.visual.patch_embed.": "patch_embed.",
|
| 964 |
+
"vlm_backbone.model.visual.pos_embed.": "pos_embed."
|
| 965 |
+
},
|
| 966 |
+
"num_embodiment_domains": 32,
|
| 967 |
+
"ori_action_dim": 14,
|
| 968 |
+
"packed_attention_backend": "flash2",
|
| 969 |
+
"position_embedding_type": "unified_3d_mrope",
|
| 970 |
+
"pretrained_name_or_path": "./checkpoints/Cosmos3-Nano/transformer",
|
| 971 |
+
"rectified_flow_inference_config": {
|
| 972 |
+
"num_steps": 30,
|
| 973 |
+
"num_train_timesteps": 1000,
|
| 974 |
+
"scheduler_type": "unipc",
|
| 975 |
+
"shift": 10,
|
| 976 |
+
"use_dynamic_shifting": false,
|
| 977 |
+
"use_karras_sigmas": false
|
| 978 |
+
},
|
| 979 |
+
"rectified_flow_training_config": {
|
| 980 |
+
"action_loss_weight": 10,
|
| 981 |
+
"high_sigma_ratio": 0.05,
|
| 982 |
+
"high_sigma_timesteps_max": 1000,
|
| 983 |
+
"high_sigma_timesteps_min": 995,
|
| 984 |
+
"independent_action_schedule": false,
|
| 985 |
+
"normalize_loss_by_active": false,
|
| 986 |
+
"shift": {
|
| 987 |
+
"256": 3,
|
| 988 |
+
"480": 5,
|
| 989 |
+
"720": 10
|
| 990 |
+
},
|
| 991 |
+
"shift_action": null,
|
| 992 |
+
"train_time_action_distribution": "logitnormal",
|
| 993 |
+
"train_time_image_distribution": "logitnormal",
|
| 994 |
+
"train_time_video_distribution": "waver",
|
| 995 |
+
"train_time_weight": "uniform",
|
| 996 |
+
"use_discrete_rf": false,
|
| 997 |
+
"use_dynamic_shift": false,
|
| 998 |
+
"use_high_sigma_strategy": false,
|
| 999 |
+
"use_high_sigma_strategy_action": false,
|
| 1000 |
+
"vision_loss_weight": 10
|
| 1001 |
+
},
|
| 1002 |
+
"reinitialize_action_policy": true,
|
| 1003 |
+
"special_tokens": {
|
| 1004 |
+
"end_of_generation": 151653,
|
| 1005 |
+
"eos_token_id": 151645,
|
| 1006 |
+
"start_of_generation": 151652
|
| 1007 |
+
},
|
| 1008 |
+
"timestep_scale": 0.001,
|
| 1009 |
+
"type": "Cosmos3FlowMatching",
|
| 1010 |
+
"unified_3d_mrope_reset_spatial_ids": true,
|
| 1011 |
+
"unified_3d_mrope_temporal_modality_margin": 15000,
|
| 1012 |
+
"vision_in_proj": {
|
| 1013 |
+
"in_dim": 192,
|
| 1014 |
+
"out_dim": 4096,
|
| 1015 |
+
"type": "LinearProjector"
|
| 1016 |
+
},
|
| 1017 |
+
"vision_latent_dim": 48,
|
| 1018 |
+
"vision_out_proj": {
|
| 1019 |
+
"in_dim": 4096,
|
| 1020 |
+
"out_dim": 192,
|
| 1021 |
+
"type": "LinearProjector"
|
| 1022 |
+
},
|
| 1023 |
+
"vision_vae": {
|
| 1024 |
+
"encode_chunk_frames": {
|
| 1025 |
+
"256": 16,
|
| 1026 |
+
"480": 24,
|
| 1027 |
+
"720": 12
|
| 1028 |
+
},
|
| 1029 |
+
"encode_exact_durations": [
|
| 1030 |
+
33
|
| 1031 |
+
],
|
| 1032 |
+
"pretrained_name_or_path": "./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
|
| 1033 |
+
"type": "Cosmos3Wan22VAE"
|
| 1034 |
+
},
|
| 1035 |
+
"vlm_backbone": {
|
| 1036 |
+
"include_visual": false,
|
| 1037 |
+
"skip_init_weights": true,
|
| 1038 |
+
"type": "Cosmos3MoTBackbone",
|
| 1039 |
+
"vision_encoder_path": "./checkpoints/Cosmos3-Nano/vision_encoder",
|
| 1040 |
+
"vlm_config": {
|
| 1041 |
+
"image_token_id": 151655,
|
| 1042 |
+
"model_type": "qwen3_vl",
|
| 1043 |
+
"text_config": {
|
| 1044 |
+
"attention_bias": false,
|
| 1045 |
+
"attention_dropout": 0,
|
| 1046 |
+
"bos_token_id": 151643,
|
| 1047 |
+
"eos_token_id": 151645,
|
| 1048 |
+
"head_dim": 128,
|
| 1049 |
+
"hidden_act": "silu",
|
| 1050 |
+
"hidden_size": 4096,
|
| 1051 |
+
"intermediate_size": 12288,
|
| 1052 |
+
"layer_types": [
|
| 1053 |
+
"full_attention",
|
| 1054 |
+
"full_attention",
|
| 1055 |
+
"full_attention",
|
| 1056 |
+
"full_attention",
|
| 1057 |
+
"full_attention",
|
| 1058 |
+
"full_attention",
|
| 1059 |
+
"full_attention",
|
| 1060 |
+
"full_attention",
|
| 1061 |
+
"full_attention",
|
| 1062 |
+
"full_attention",
|
| 1063 |
+
"full_attention",
|
| 1064 |
+
"full_attention",
|
| 1065 |
+
"full_attention",
|
| 1066 |
+
"full_attention",
|
| 1067 |
+
"full_attention",
|
| 1068 |
+
"full_attention",
|
| 1069 |
+
"full_attention",
|
| 1070 |
+
"full_attention",
|
| 1071 |
+
"full_attention",
|
| 1072 |
+
"full_attention",
|
| 1073 |
+
"full_attention",
|
| 1074 |
+
"full_attention",
|
| 1075 |
+
"full_attention",
|
| 1076 |
+
"full_attention",
|
| 1077 |
+
"full_attention",
|
| 1078 |
+
"full_attention",
|
| 1079 |
+
"full_attention",
|
| 1080 |
+
"full_attention",
|
| 1081 |
+
"full_attention",
|
| 1082 |
+
"full_attention",
|
| 1083 |
+
"full_attention",
|
| 1084 |
+
"full_attention",
|
| 1085 |
+
"full_attention",
|
| 1086 |
+
"full_attention",
|
| 1087 |
+
"full_attention",
|
| 1088 |
+
"full_attention"
|
| 1089 |
+
],
|
| 1090 |
+
"max_position_embeddings": 262144,
|
| 1091 |
+
"model_type": "qwen3_vl_text",
|
| 1092 |
+
"num_attention_heads": 32,
|
| 1093 |
+
"num_hidden_layers": 36,
|
| 1094 |
+
"num_key_value_heads": 8,
|
| 1095 |
+
"pad_token_id": 0,
|
| 1096 |
+
"rms_norm_eps": "1e-06",
|
| 1097 |
+
"rope_scaling": {
|
| 1098 |
+
"mrope_interleaved": true,
|
| 1099 |
+
"mrope_section": [
|
| 1100 |
+
24,
|
| 1101 |
+
20,
|
| 1102 |
+
20
|
| 1103 |
+
],
|
| 1104 |
+
"rope_type": "default"
|
| 1105 |
+
},
|
| 1106 |
+
"rope_theta": 5000000,
|
| 1107 |
+
"tie_word_embeddings": false,
|
| 1108 |
+
"vocab_size": 151936
|
| 1109 |
+
},
|
| 1110 |
+
"tie_word_embeddings": false,
|
| 1111 |
+
"video_token_id": 151656,
|
| 1112 |
+
"vision_config": {
|
| 1113 |
+
"deepstack_visual_indexes": [
|
| 1114 |
+
8,
|
| 1115 |
+
16,
|
| 1116 |
+
24
|
| 1117 |
+
],
|
| 1118 |
+
"depth": 27,
|
| 1119 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 1120 |
+
"hidden_size": 1152,
|
| 1121 |
+
"in_channels": 3,
|
| 1122 |
+
"initializer_range": 0.02,
|
| 1123 |
+
"intermediate_size": 4304,
|
| 1124 |
+
"model_type": "qwen3_vl",
|
| 1125 |
+
"num_heads": 16,
|
| 1126 |
+
"num_position_embeddings": 2304,
|
| 1127 |
+
"out_hidden_size": 4096,
|
| 1128 |
+
"patch_size": 16,
|
| 1129 |
+
"spatial_merge_size": 2,
|
| 1130 |
+
"temporal_patch_size": 2
|
| 1131 |
+
},
|
| 1132 |
+
"vision_end_token_id": 151653,
|
| 1133 |
+
"vision_start_token_id": 151652,
|
| 1134 |
+
"vocab_size": 151936
|
| 1135 |
+
}
|
| 1136 |
+
}
|
| 1137 |
+
},
|
| 1138 |
+
"runner": {
|
| 1139 |
+
"args": "Namespace(config='configs/cosmos3/cosmos3nano_robodojo_full_finetune.py', work_dir='/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano', cfg_options=None, eval_after_train=False, resume_from=None)",
|
| 1140 |
+
"cfg": "Config (path: configs/cosmos3/cosmos3nano_robodojo_full_finetune.py): {'_ckpt_root': './checkpoints', '_cosmos3_nano_ckpt': './checkpoints/Cosmos3-Nano', '_cosmos3_nano_transformer': './checkpoints/Cosmos3-Nano/transformer', '_cosmos3_nano_vision_encoder': './checkpoints/Cosmos3-Nano/vision_encoder', '_cosmos3_nano_tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, '_wan22_vae_path': './checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth', '_vision_vae': {'type': 'Cosmos3Wan22VAE', 'pretrained_name_or_path': './checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth', 'encode_exact_durations': [17]}, '_action_dim': 10, '_max_action_dim': 64, '_max_state_dim': 64, '_action_horizon': 16, '_frame_window_size': 17, '_prepend_state_to_action': False, '_image_height': 256, '_image_width': 256, '_video_height': 192, '_video_width': 320, '_conditioning_fps': 20.0, '_libero_action_stats': {'mean': [0.050704, 0.097407, -0.094833, 0.994873, -0.004579, -0.004288, 0.004389, 0.996104, 0.001109, 0.476725], 'std': [0.333621, 0.387175, 0.45714, 0.010807, 0.077802, 0.063386, 0.078571, 0.009994, 0.038504, 0.49946], 'min': [-0.9375, -0.9375, -0.9375, 0.902028, -0.356085, -0.367416, -0.370434, 0.921907, -0.255, 0.0], 'max': [0.9375, 0.9375, 0.9375, 1.0, 0.368853, 0.341214, 0.356395, 1.0, 0.348251, 1.0], 'q01': [-0.723214, -0.808929, -0.9375, 0.934955, -0.223431, -0.189878, -0.334735, 0.938516, -0.107736, 0.0], 'q99': [0.9375, 0.870536, 0.9375, 1.0, 0.331, 0.163153, 0.226216, 1.0, 0.127158, 1.0]}, '_cfg_dropout_rate': 0.1, '_base_lr': 5e-05, '_action_lr': 0.00025, '_per_device_batch_size': 16, '_grad_accumulation_steps': 8, '_max_steps': 2000, '_save_iter_interval': 500, '_cosmos3_nano_special_tokens': {'eos_token_id': 151645, 'start_of_generation': 151652, 'end_of_generation': 151653}, '_cosmos3_nano_vlm_config': {'model_type': 'qwen3_vl', 'vocab_size': 151936, 'tie_word_embeddings': False, 'image_token_id': 151655, 'video_token_id': 151656, 'vision_start_token_id': 151652, 'vision_end_token_id': 151653, 'text_config': {'model_type': 'qwen3_vl_text', 'vocab_size': 151936, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'max_position_embeddings': 262144, 'rms_norm_eps': 1e-06, 'rope_theta': 5000000, 'attention_bias': False, 'attention_dropout': 0.0, 'bos_token_id': 151643, 'eos_token_id': 151645, 'pad_token_id': 0, 'tie_word_embeddings': False, 'rope_scaling': {'rope_type': 'default', 'mrope_interleaved': True, 'mrope_section': [24, 20, 20]}, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention']}, 'vision_config': {'model_type': 'qwen3_vl', 'hidden_size': 1152, 'hidden_act': 'gelu_pytorch_tanh', 'intermediate_size': 4304, 'depth': 27, 'num_heads': 16, 'in_channels': 3, 'initializer_range': 0.02, 'out_hidden_size': 4096, 'patch_size': 16, 'spatial_merge_size': 2, 'temporal_patch_size': 2, 'num_position_embeddings': 2304, 'deepstack_visual_indexes': [8, 16, 24]}}, '_cosmos3_nano_name_mapping': {'action_modality_embed': 'action_modality_embed', 'vlm_backbone.model.language_model.embed_tokens.weight': 'embed_tokens.weight', 'vlm_backbone.lm_head.weight': 'lm_head.weight', 'vlm_backbone.model.language_model.norm.weight': 'norm.weight', 'vlm_backbone.model.language_model.norm_moe_gen.weight': 'norm_moe_gen.weight', 'vlm_backbone.model.language_model.layers.': 'layers.', 'vision_in_proj.projector.': 'proj_in.', 'vision_out_proj.projector.': 'proj_out.', 'time_embedder.mlp.0.': 'time_embedder.linear_1.', 'time_embedder.mlp.2.': 'time_embedder.linear_2.', 'action_in_proj.': 'action_proj_in.', 'action_out_proj.': 'action_proj_out.', '.self_attn.q_proj.': '.self_attn.to_q.', '.self_attn.k_proj.': '.self_attn.to_k.', '.self_attn.v_proj.': '.self_attn.to_v.', '.self_attn.o_proj.': '.self_attn.to_out.', '.self_attn.q_proj_moe_gen.': '.self_attn.add_q_proj.', '.self_attn.k_proj_moe_gen.': '.self_attn.add_k_proj.', '.self_attn.v_proj_moe_gen.': '.self_attn.add_v_proj.', '.self_attn.o_proj_moe_gen.': '.self_attn.to_add_out.', '.self_attn.q_norm.': '.self_attn.norm_q.', '.self_attn.k_norm.': '.self_attn.norm_k.', '.self_attn.q_norm_moe_gen.': '.self_attn.norm_added_q.', '.self_attn.k_norm_moe_gen.': '.self_attn.norm_added_k.', 'vlm_backbone.model.visual.patch_embed.': 'patch_embed.', 'vlm_backbone.model.visual.blocks.': 'blocks.', 'vlm_backbone.model.visual.pos_embed.': 'pos_embed.', 'vlm_backbone.model.visual.merger.': 'merger.', 'vlm_backbone.model.visual.deepstack_merger_list.': 'deepstack_merger_list.'}, 'model': {'type': 'Cosmos3FlowMatching', 'vlm_backbone': {'type': 'Cosmos3MoTBackbone', 'vlm_config': {'model_type': 'qwen3_vl', 'vocab_size': 151936, 'tie_word_embeddings': False, 'image_token_id': 151655, 'video_token_id': 151656, 'vision_start_token_id': 151652, 'vision_end_token_id': 151653, 'text_config': {'model_type': 'qwen3_vl_text', 'vocab_size': 151936, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'max_position_embeddings': 262144, 'rms_norm_eps': 1e-06, 'rope_theta': 5000000, 'attention_bias': False, 'attention_dropout': 0.0, 'bos_token_id': 151643, 'eos_token_id': 151645, 'pad_token_id': 0, 'tie_word_embeddings': False, 'rope_scaling': {'rope_type': 'default', 'mrope_interleaved': True, 'mrope_section': [24, 20, 20]}, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention']}, 'vision_config': {'model_type': 'qwen3_vl', 'hidden_size': 1152, 'hidden_act': 'gelu_pytorch_tanh', 'intermediate_size': 4304, 'depth': 27, 'num_heads': 16, 'in_channels': 3, 'initializer_range': 0.02, 'out_hidden_size': 4096, 'patch_size': 16, 'spatial_merge_size': 2, 'temporal_patch_size': 2, 'num_position_embeddings': 2304, 'deepstack_visual_indexes': [8, 16, 24]}}, 'include_visual': False, 'vision_encoder_path': './checkpoints/Cosmos3-Nano/vision_encoder', 'skip_init_weights': True}, 'vision_latent_dim': 48, 'latent_patch_size': 2, 'max_action_dim': 64, 'num_embodiment_domains': 32, 'vision_in_proj': {'type': 'LinearProjector', 'in_dim': 192, 'out_dim': 4096}, 'vision_out_proj': {'type': 'LinearProjector', 'in_dim': 4096, 'out_dim': 192}, 'action_in_proj': {'type': 'DomainAwareLinear', 'input_size': 64, 'output_size': 4096, 'num_domains': 32}, 'action_out_proj': {'type': 'DomainAwareLinear', 'input_size': 4096, 'output_size': 64, 'num_domains': 32}, 'rectified_flow_training_config': {'shift': {'256': 3, '480': 5, '720': 10}, 'use_dynamic_shift': False, 'train_time_image_distribution': 'logitnormal', 'train_time_video_distribution': 'waver', 'train_time_action_distribution': 'logitnormal', 'train_time_weight': 'uniform', 'vision_loss_weight': 10.0, 'independent_action_schedule': False, 'shift_action': None, 'use_high_sigma_strategy': False, 'high_sigma_ratio': 0.05, 'high_sigma_timesteps_min': 995, 'high_sigma_timesteps_max': 1000, 'use_high_sigma_strategy_action': False, 'use_discrete_rf': False, 'normalize_loss_by_active': False, 'action_loss_weight': 10.0}, 'rectified_flow_inference_config': {'num_train_timesteps': 1000, 'scheduler_type': 'unipc', 'num_steps': 30, 'shift': 10.0, 'use_dynamic_shifting': False, 'use_karras_sigmas': False}, 'timestep_scale': 0.001, 'packed_attention_backend': 'flash2', 'position_embedding_type': 'unified_3d_mrope', 'unified_3d_mrope_reset_spatial_ids': True, 'unified_3d_mrope_temporal_modality_margin': 15000, 'enable_fps_modulation': True, 'base_fps': 24.0, 'special_tokens': {'eos_token_id': 151645, 'start_of_generation': 151652, 'end_of_generation': 151653}, 'pretrained_name_or_path': './checkpoints/Cosmos3-Nano/transformer', 'name_mapping': {'action_modality_embed': 'action_modality_embed', 'vlm_backbone.model.language_model.embed_tokens.weight': 'embed_tokens.weight', 'vlm_backbone.lm_head.weight': 'lm_head.weight', 'vlm_backbone.model.language_model.norm.weight': 'norm.weight', 'vlm_backbone.model.language_model.norm_moe_gen.weight': 'norm_moe_gen.weight', 'vlm_backbone.model.language_model.layers.': 'layers.', 'vision_in_proj.projector.': 'proj_in.', 'vision_out_proj.projector.': 'proj_out.', 'time_embedder.mlp.0.': 'time_embedder.linear_1.', 'time_embedder.mlp.2.': 'time_embedder.linear_2.', 'action_in_proj.': 'action_proj_in.', 'action_out_proj.': 'action_proj_out.', '.self_attn.q_proj.': '.self_attn.to_q.', '.self_attn.k_proj.': '.self_attn.to_k.', '.self_attn.v_proj.': '.self_attn.to_v.', '.self_attn.o_proj.': '.self_attn.to_out.', '.self_attn.q_proj_moe_gen.': '.self_attn.add_q_proj.', '.self_attn.k_proj_moe_gen.': '.self_attn.add_k_proj.', '.self_attn.v_proj_moe_gen.': '.self_attn.add_v_proj.', '.self_attn.o_proj_moe_gen.': '.self_attn.to_add_out.', '.self_attn.q_norm.': '.self_attn.norm_q.', '.self_attn.k_norm.': '.self_attn.norm_k.', '.self_attn.q_norm_moe_gen.': '.self_attn.norm_added_q.', '.self_attn.k_norm_moe_gen.': '.self_attn.norm_added_k.', 'vlm_backbone.model.visual.patch_embed.': 'patch_embed.', 'vlm_backbone.model.visual.blocks.': 'blocks.', 'vlm_backbone.model.visual.pos_embed.': 'pos_embed.', 'vlm_backbone.model.visual.merger.': 'merger.', 'vlm_backbone.model.visual.deepstack_merger_list.': 'deepstack_merger_list.'}, 'vision_vae': {'type': 'Cosmos3Wan22VAE', 'pretrained_name_or_path': './checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth', 'encode_exact_durations': [33], 'encode_chunk_frames': {'256': 16, '480': 24, '720': 12}}, 'ori_action_dim': 14, 'action_horizon': 32, 'freeze_vlm_backbone': False, 'freeze_non_moe_vlm_backbone': True, 'enable_vision_loss': True, 'reinitialize_action_policy': True}, 'inference_model': {'type': 'Cosmos3FlowMatching', 'vlm_backbone': {'type': 'Cosmos3MoTBackbone', 'vlm_config': {'model_type': 'qwen3_vl', 'vocab_size': 151936, 'tie_word_embeddings': False, 'image_token_id': 151655, 'video_token_id': 151656, 'vision_start_token_id': 151652, 'vision_end_token_id': 151653, 'text_config': {'model_type': 'qwen3_vl_text', 'vocab_size': 151936, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'max_position_embeddings': 262144, 'rms_norm_eps': 1e-06, 'rope_theta': 5000000, 'attention_bias': False, 'attention_dropout': 0.0, 'bos_token_id': 151643, 'eos_token_id': 151645, 'pad_token_id': 0, 'tie_word_embeddings': False, 'rope_scaling': {'rope_type': 'default', 'mrope_interleaved': True, 'mrope_section': [24, 20, 20]}, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention']}, 'vision_config': {'model_type': 'qwen3_vl', 'hidden_size': 1152, 'hidden_act': 'gelu_pytorch_tanh', 'intermediate_size': 4304, 'depth': 27, 'num_heads': 16, 'in_channels': 3, 'initializer_range': 0.02, 'out_hidden_size': 4096, 'patch_size': 16, 'spatial_merge_size': 2, 'temporal_patch_size': 2, 'num_position_embeddings': 2304, 'deepstack_visual_indexes': [8, 16, 24]}}, 'include_visual': False, 'vision_encoder_path': './checkpoints/Cosmos3-Nano/vision_encoder', 'skip_init_weights': True}, 'vision_latent_dim': 48, 'latent_patch_size': 2, 'max_action_dim': 64, 'num_embodiment_domains': 32, 'vision_in_proj': {'type': 'LinearProjector', 'in_dim': 192, 'out_dim': 4096}, 'vision_out_proj': {'type': 'LinearProjector', 'in_dim': 4096, 'out_dim': 192}, 'action_in_proj': {'type': 'DomainAwareLinear', 'input_size': 64, 'output_size': 4096, 'num_domains': 32}, 'action_out_proj': {'type': 'DomainAwareLinear', 'input_size': 4096, 'output_size': 64, 'num_domains': 32}, 'rectified_flow_training_config': {'shift': {'256': 3, '480': 5, '720': 10}, 'use_dynamic_shift': False, 'train_time_image_distribution': 'logitnormal', 'train_time_video_distribution': 'waver', 'train_time_action_distribution': 'logitnormal', 'train_time_weight': 'uniform', 'vision_loss_weight': 10.0, 'independent_action_schedule': False, 'shift_action': None, 'use_high_sigma_strategy': False, 'high_sigma_ratio': 0.05, 'high_sigma_timesteps_min': 995, 'high_sigma_timesteps_max': 1000, 'use_high_sigma_strategy_action': False, 'use_discrete_rf': False, 'normalize_loss_by_active': False, 'action_loss_weight': 10.0}, 'rectified_flow_inference_config': {'num_train_timesteps': 1000, 'scheduler_type': 'unipc', 'num_steps': 30, 'shift': 10.0, 'use_dynamic_shifting': False, 'use_karras_sigmas': False}, 'timestep_scale': 0.001, 'packed_attention_backend': 'flash2', 'position_embedding_type': 'unified_3d_mrope', 'unified_3d_mrope_reset_spatial_ids': True, 'unified_3d_mrope_temporal_modality_margin': 15000, 'enable_fps_modulation': True, 'base_fps': 24.0, 'special_tokens': {'eos_token_id': 151645, 'start_of_generation': 151652, 'end_of_generation': 151653}, 'pretrained_name_or_path': './checkpoints/Cosmos3-Nano/transformer', 'name_mapping': {'action_modality_embed': 'action_modality_embed', 'vlm_backbone.model.language_model.embed_tokens.weight': 'embed_tokens.weight', 'vlm_backbone.lm_head.weight': 'lm_head.weight', 'vlm_backbone.model.language_model.norm.weight': 'norm.weight', 'vlm_backbone.model.language_model.norm_moe_gen.weight': 'norm_moe_gen.weight', 'vlm_backbone.model.language_model.layers.': 'layers.', 'vision_in_proj.projector.': 'proj_in.', 'vision_out_proj.projector.': 'proj_out.', 'time_embedder.mlp.0.': 'time_embedder.linear_1.', 'time_embedder.mlp.2.': 'time_embedder.linear_2.', 'action_in_proj.': 'action_proj_in.', 'action_out_proj.': 'action_proj_out.', '.self_attn.q_proj.': '.self_attn.to_q.', '.self_attn.k_proj.': '.self_attn.to_k.', '.self_attn.v_proj.': '.self_attn.to_v.', '.self_attn.o_proj.': '.self_attn.to_out.', '.self_attn.q_proj_moe_gen.': '.self_attn.add_q_proj.', '.self_attn.k_proj_moe_gen.': '.self_attn.add_k_proj.', '.self_attn.v_proj_moe_gen.': '.self_attn.add_v_proj.', '.self_attn.o_proj_moe_gen.': '.self_attn.to_add_out.', '.self_attn.q_norm.': '.self_attn.norm_q.', '.self_attn.k_norm.': '.self_attn.norm_k.', '.self_attn.q_norm_moe_gen.': '.self_attn.norm_added_q.', '.self_attn.k_norm_moe_gen.': '.self_attn.norm_added_k.', 'vlm_backbone.model.visual.patch_embed.': 'patch_embed.', 'vlm_backbone.model.visual.blocks.': 'blocks.', 'vlm_backbone.model.visual.pos_embed.': 'pos_embed.', 'vlm_backbone.model.visual.merger.': 'merger.', 'vlm_backbone.model.visual.deepstack_merger_list.': 'deepstack_merger_list.'}, 'vision_vae': {'type': 'Cosmos3Wan22VAE', 'pretrained_name_or_path': None, 'encode_exact_durations': [33]}, 'ori_action_dim': 14, 'action_horizon': 32, 'freeze_vlm_backbone': False, 'freeze_non_moe_vlm_backbone': True, 'enable_vision_loss': True, 'reinitialize_action_policy': True}, '_transforms': [{'type': 'ProcessParquetInputs', 'parquet_keys': ['observation.state', 'timestamp', 'actions', 'info', 'stats', 'action_masks'], 'video_keys': ['observation.images.image', 'observation.images.wrist_image'], 'name_mappings': {'observation.state': ['states'], 'actions': ['actions']}, 'embodiment_id': 5}, {'type': 'LiberoFramewiseActionToRot6D'}, {'type': 'ProcessCosmos3Prompt', 'tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, 'max_len': 512, 'cfg_dropout_rate': 0.1, 'format_prompt_as_json': True, 'action_metadata': {'append_viewpoint': False, 'frame_window_size': 17, 'conditioning_fps': 20.0, 'video_height': 192, 'video_width': 320}}, {'type': 'ResizeImages', 'height': 256, 'width': 256}, {'type': 'SimpleNormalizeImages'}, {'type': 'NormalizeStatesAndActions', 'action_dim': 64, 'state_dim': 64, 'state_key': 'proprio', 'action_key': 'action', 'state_norm_type': 'none', 'action_norm_type': 'quantile'}, {'type': 'BuildCosmos3Sequence', 'raw_action_dim': 10, 'mode': 'wam', 'frame_window_size': 17, 'prepend_state_to_action': False, 'conditioning_fps': 20.0}, {'type': 'PrepareVideo', 'num_views': 2, 'frame_window_size': 17, 'tile_direction': 'horizontal'}, {'type': 'ResizeAndReflectPad', 'height': 192, 'width': 320}], 'train_dataloader': {'per_device_batch_size': 8, 'per_device_num_workers': 4, 'prefetch_factor': 1, 'dataset': {'type': 'DistributedRepeatingDataset', 'seed': 42, 'reshuffle_each_epoch': True, 'name_mappings': {'observation.state': ['proprio'], 'action': ['action']}, 'statistic_keys': ['observation.state', 'action', 'timestamp'], 'statistic_name': 'robodojo_arx_x5', 'statistics_overrides': {'robodojo_arx_x5': {'action': {'q01': [-1.051365569829941, -3.5348887174584814e-14, 1.741881830823392e-16, -1.5984010362625123, -0.6003574305772781, -1.6678147149085998, 0.0, -0.4509398394823074, -2.5859282299029243e-14, 1.234041714549172e-16, -1.64055180311203, -1.2633746123313903, -1.7645285475254058, 0.0], 'q99': [0.5431358617544174, 2.495765209197998, 2.492974226474762, 1.3241519677639007, 1.2496635341644287, 1.7392305016517635, 1.0, 1.0814965963363647, 2.4167031812667843, 2.3470158338546754, 1.141731116771698, 0.5208872479200363, 1.489715996980667, 1.0]}}}, 'datasets': {'type': 'ParquetDataset', 'data_root_path': ['./datasets/RoboDojo_lerobot_v21_video'], 'transforms': [{'type': 'ProcessParquetInputs', 'embodiment_id': 31, 'parquet_keys': ['observation.state', 'timestamp', 'actions', 'info', 'stats', 'action_masks'], 'video_keys': ['observation.images.cam_high', 'observation.images.cam_left_wrist', 'observation.images.cam_right_wrist'], 'name_mappings': {'observation.state': ['states'], 'actions': ['actions']}}, {'type': 'ResizeImages', 'height': 192, 'width': 256}, {'type': 'AugVideo', 'rotation_range': 0.0, 'brightness_range': (0.7, 1.3), 'contrast_range': (0.6, 1.4), 'crop_scale': (0.95, 0.95), 'crop_ratio': (1.0, 1.0), 'prob': 1.0, 'saturation_range': (0.5, 1.5), 'hue_delta': 0.08}, {'type': 'ProcessCosmos3Prompt', 'tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, 'max_len': 512, 'cfg_dropout_rate': 0.1, 'format_prompt_as_json': True, 'action_metadata': {'append_viewpoint': False, 'viewpoint': 'concat_view', 'frame_window_size': 33, 'conditioning_fps': 25.0, 'video_height': 320, 'video_width': 256}}, {'type': 'SimpleNormalizeImages'}, {'type': 'NormalizeStatesAndActions', 'action_dim': 64, 'state_dim': 64, 'state_key': 'proprio', 'action_key': 'action', 'state_norm_type': 'none', 'action_norm_type': 'quantile'}, {'type': 'BuildCosmos3Sequence', 'raw_action_dim': 14, 'mode': 'wam', 'frame_window_size': 33, 'prepend_state_to_action': False, 'conditioning_fps': 25.0}, {'type': 'PrepareVideo', 'num_views': 3, 'frame_window_size': 33, 'tile_direction': 'top_bottom_pair', 'top_view': 0, 'bottom_views': (1, 2), 'bottom_height_ratio': 0.5}, {'type': 'ResizeAndReflectPad', 'height': 320, 'width': 256}], 'action_window_size': 32, 'action_key': 'action', 'use_delta': False, 'statistic_name': 'robodojo_arx_x5', 'window_start_idx': 0, 'frame_window_size': 33, 'require_full_window': True}}}, 'runner': {'type': 'FSDPTrainRunner', 'max_steps': 10000, 'save_iter_interval': 1000, 'max_keep_ckpts': 2, 'optimizer': {'type': 'AdamW', 'lr': 5e-05, 'weight_decay': 0.05, 'betas': (0.9, 0.99), 'eps': 1e-08, 'fused': True, 'exclude_1d_from_weight_decay': False, 'paramwise_learning_rate': {'action_in_proj.': 0.00025, 'action_out_proj.': 0.00025, 'action_modality_embed': 0.00025}}, 'max_grad_norm': 1.0, 'tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, 'collator': {'type': 'DictCollator', 'keys': ['images', 'states', 'actions', 'action_masks', 'img_masks', 'frame_masks', 'embodiment_ids', 'raw_action_dim', 'conditioning_fps', 'action_fps'], 'meta_keys': ['text_token_ids', 'sequence_plan', 'task_description', 'stats', 'info', 'timestamp', 'viewpoint']}, 'sampler': None, 'grad_accumulation_steps': 16, 'metric': {'type': 'VLAMetric', 'active_trackers': ('jsonl', 'wandb'), 'run_dir': '/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano', 'grad_accumulation_steps': 16, 'window_size': 1}, 'lr_scheduler': {'type': 'linear-warmup+linear-decay', 'warmup_steps': 0, 'cycle_length': 100000}, 'enable_gradient_checkpointing': True, 'enable_mixed_precision_training': True, 'mixed_precision_dtype': 'bf16', 'sharding_strategy': 'full-shard', 'change_key_name': False, 'cfg': Config (path: configs/cosmos3/cosmos3nano_robodojo_full_finetune.py): {...}, 'args': Namespace(config='configs/cosmos3/cosmos3nano_robodojo_full_finetune.py', work_dir='/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano', cfg_options=None, eval_after_train=False, resume_from=None)}, 'eval': {'report_kind': 'robodojo', 'task_suite_name': 'robodojo', 'model_family': 'cosmos3', 'eval_chunk_size': 32, 'num_trials_per_task': 50, 'num_trials_per_task_overrides': {'stack_bowls': 25, 'stack_bowls_random': 25, 'push_T': 25, 'push_T_random': 25, 'pack_objects_into_box': 25, 'pack_objects_into_box_random': 25, 'fold_clothes': 25, 'fold_clothes_random': 25, 'hang_mugs': 25, 'hang_mugs_random': 25, 'sweep_blocks': 25, 'sweep_blocks_random': 25, 'pour_liquid_into_cup': 25, 'pour_liquid_into_cup_random': 25, 'make_toast': 25, 'make_toast_random': 25, 'arrange_largest_number': 25, 'arrange_largest_number_random': 25, 'sort_nesting_dolls_by_size': 25, 'sort_nesting_dolls_by_size_random': 25, 'store_laptop_and_headphones': 25, 'store_laptop_and_headphones_random': 25, 'stack_blocks': 25, 'stack_blocks_random': 25}, 'enable_mixed_precision_training': True, 'mixed_precision_dtype': 'bf16', 'dataset': {'type': 'RoboDojoEvalDataset', 'unnorm_key': 'robodojo_arx_x5', 'transforms': [{'type': 'ProcessEvalInputs', 'img_keys': ['cam_high', 'cam_left_wrist', 'cam_right_wrist'], 'embodiment_id': 31}, {'type': 'SetCosmos3ActionMetadata', 'conditioning_fps': 25.0, 'prepend_state_to_action': False}, {'type': 'ProcessCosmos3Prompt', 'tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, 'max_len': 512, 'cfg_dropout_rate': 0.0, 'format_prompt_as_json': True, 'action_metadata': {'append_viewpoint': False, 'viewpoint': 'concat_view', 'frame_window_size': 33, 'conditioning_fps': 25.0, 'video_height': 320, 'video_width': 256}, 'output_key': 'lang_tokens', 'output_attention_mask_key': 'lang_masks'}, {'type': 'TransformImage', 'image_resize_strategy': 'resize-naive', 'input_sizes': [[3, 256, 192], [3, 256, 192], [3, 256, 192]], 'means': [[127.5, 127.5, 127.5], [127.5, 127.5, 127.5], [127.5, 127.5, 127.5]], 'stds': [[127.5, 127.5, 127.5], [127.5, 127.5, 127.5], [127.5, 127.5, 127.5]]}, {'type': 'PrepareVideo', 'num_views': 3, 'frame_window_size': 1, 'tile_direction': 'top_bottom_pair', 'top_view': 0, 'bottom_views': (1, 2), 'bottom_height_ratio': 0.5}, {'type': 'ResizeAndReflectPad', 'height': 320, 'width': 256}]}, 'denormalize_action': {'type': 'DenormalizePrivateAction', 'norm_type': 'quantile', 'action_dim': 14, 'statistic_name': 'robodojo_arx_x5'}}, '_ROBODOJO_DATA_ROOT': './datasets/RoboDojo_lerobot_v21_video', '_STATISTIC_NAME': 'robodojo_arx_x5', '_ACTION_DIM': 14, '_MAX_ACTION_DIM': 64, '_MAX_STATE_DIM': 64, '_ACTION_HORIZON': 32, '_FRAME_WINDOW_SIZE': 33, '_CONDITIONING_FPS': 25.0, '_EMBODIMENT_ID': 31, '_PREPEND_STATE_TO_ACTION': False, '_ROBODOJO_ACTION_QUANTILES': {'q01': [-1.051365569829941, -3.5348887174584814e-14, 1.741881830823392e-16, -1.5984010362625123, -0.6003574305772781, -1.6678147149085998, 0.0, -0.4509398394823074, -2.5859282299029243e-14, 1.234041714549172e-16, -1.64055180311203, -1.2633746123313903, -1.7645285475254058, 0.0], 'q99': [0.5431358617544174, 2.495765209197998, 2.492974226474762, 1.3241519677639007, 1.2496635341644287, 1.7392305016517635, 1.0, 1.0814965963363647, 2.4167031812667843, 2.3470158338546754, 1.141731116771698, 0.5208872479200363, 1.489715996980667, 1.0]}, '_IMAGE_HEIGHT': 192, '_IMAGE_WIDTH': 256, '_VIDEO_HEIGHT': 320, '_VIDEO_WIDTH': 256, '_VAE_ENCODE_CHUNK_FRAMES': {'256': 16, '480': 24, '720': 12}, '_ROBODOJO_GENERALIZATION_BASE_TASKS': ('stack_bowls', 'push_T', 'pack_objects_into_box', 'fold_clothes', 'hang_mugs', 'sweep_blocks', 'pour_liquid_into_cup', 'make_toast', 'arrange_largest_number', 'sort_nesting_dolls_by_size', 'store_laptop_and_headphones', 'stack_blocks'), '_ROBODOJO_EPISODE_OVERRIDES': {'stack_bowls': 25, 'stack_bowls_random': 25, 'push_T': 25, 'push_T_random': 25, 'pack_objects_into_box': 25, 'pack_objects_into_box_random': 25, 'fold_clothes': 25, 'fold_clothes_random': 25, 'hang_mugs': 25, 'hang_mugs_random': 25, 'sweep_blocks': 25, 'sweep_blocks_random': 25, 'pour_liquid_into_cup': 25, 'pour_liquid_into_cup_random': 25, 'make_toast': 25, 'make_toast_random': 25, 'arrange_largest_number': 25, 'arrange_largest_number_random': 25, 'sort_nesting_dolls_by_size': 25, 'sort_nesting_dolls_by_size_random': 25, 'store_laptop_and_headphones': 25, 'store_laptop_and_headphones_random': 25, 'stack_blocks': 25, 'stack_blocks_random': 25}, '_ROBODOJO_TRANSFORMS': [{'type': 'ProcessParquetInputs', 'embodiment_id': 31, 'parquet_keys': ['observation.state', 'timestamp', 'actions', 'info', 'stats', 'action_masks'], 'video_keys': ['observation.images.cam_high', 'observation.images.cam_left_wrist', 'observation.images.cam_right_wrist'], 'name_mappings': {'observation.state': ['states'], 'actions': ['actions']}}, {'type': 'ResizeImages', 'height': 192, 'width': 256}, {'type': 'AugVideo', 'rotation_range': 0.0, 'brightness_range': (0.7, 1.3), 'contrast_range': (0.6, 1.4), 'crop_scale': (0.95, 0.95), 'crop_ratio': (1.0, 1.0), 'prob': 1.0, 'saturation_range': (0.5, 1.5), 'hue_delta': 0.08}, {'type': 'ProcessCosmos3Prompt', 'tokenizer': {'type': 'PretrainedTokenizer', 'model_path': './checkpoints/Cosmos3-Nano/text_tokenizer', 'model_max_length': 4096, 'padding_side': 'right', 'trust_remote_code': True}, 'max_len': 512, 'cfg_dropout_rate': 0.1, 'format_prompt_as_json': True, 'action_metadata': {'append_viewpoint': False, 'viewpoint': 'concat_view', 'frame_window_size': 33, 'conditioning_fps': 25.0, 'video_height': 320, 'video_width': 256}}, {'type': 'SimpleNormalizeImages'}, {'type': 'NormalizeStatesAndActions', 'action_dim': 64, 'state_dim': 64, 'state_key': 'proprio', 'action_key': 'action', 'state_norm_type': 'none', 'action_norm_type': 'quantile'}, {'type': 'BuildCosmos3Sequence', 'raw_action_dim': 14, 'mode': 'wam', 'frame_window_size': 33, 'prepend_state_to_action': False, 'conditioning_fps': 25.0}, {'type': 'PrepareVideo', 'num_views': 3, 'frame_window_size': 33, 'tile_direction': 'top_bottom_pair', 'top_view': 0, 'bottom_views': (1, 2), 'bottom_height_ratio': 0.5}, {'type': 'ResizeAndReflectPad', 'height': 320, 'width': 256}], 'themis': {'transport': {'host': '127.0.0.1', 'port': 5555, 'timeout_s': 30.0, 'image_keys': ['cam_high', 'cam_left_wrist', 'cam_right_wrist'], 'state_keys': ['states'], 'unnorm_key': 'robodojo_arx_x5', 'image_encoding': 'rgb8', 'report_service_name': '/fluxvla/report_evaluation'}, 'runner': {'type': 'EvalRunner', 'environment': {'type': 'RoboDojoEnvironment', 'task_name': 'all', 'env_cfg_type': 'arx_x5', 'robodojo_root': '/root/projects/RoboDojo', 'device_id': 1, 'action_mode': 'joint', 'headless': True, 'save_videos': False}, 'model_client': {'type': 'FluxVLAZMQModelClient'}, 'evaluator': {'type': 'SuccessRateEvaluator'}, 'seed': 0, 'episodes_per_task': 50, 'episodes_per_task_overrides': {'stack_bowls': 25, 'stack_bowls_random': 25, 'push_T': 25, 'push_T_random': 25, 'pack_objects_into_box': 25, 'pack_objects_into_box_random': 25, 'fold_clothes': 25, 'fold_clothes_random': 25, 'hang_mugs': 25, 'hang_mugs_random': 25, 'sweep_blocks': 25, 'sweep_blocks_random': 25, 'pour_liquid_into_cup': 25, 'pour_liquid_into_cup_random': 25, 'make_toast': 25, 'make_toast_random': 25, 'arrange_largest_number': 25, 'arrange_largest_number_random': 25, 'sort_nesting_dolls_by_size': 25, 'sort_nesting_dolls_by_size_random': 25, 'store_laptop_and_headphones': 25, 'store_laptop_and_headphones_random': 25, 'stack_blocks': 25, 'stack_blocks_random': 25}, 'max_episode_steps': 2000, 'execute_horizon': 32, 'stop_on_success': True, 'parallel_workers': 1, 'simulator_gpu_ids': None, 'work_dir': 'work_dirs/fluxthemis'}, 'ros_server': {'dataset_section': 'eval', 'evaluation_reporting': {'result_output_dir': 'work_dirs/fluxthemis', 'report_kind': 'robodojo'}, 'device': 'cuda:0', 'workers': {'startup_timeout_s': 900.0, 'request_timeout_s': 120.0, 'lease_timeout_s': 900.0}, 'mixed_precision_dtype': 'bf16', 'enable_mixed_precision': True, 'model_outputs_environment_actions': False, 'forward_seed': False, 'denormalize_context': {'task_suite_name': 'robodojo_arx_x5'}}}}",
|
| 1141 |
+
"change_key_name": false,
|
| 1142 |
+
"collator": {
|
| 1143 |
+
"keys": [
|
| 1144 |
+
"images",
|
| 1145 |
+
"states",
|
| 1146 |
+
"actions",
|
| 1147 |
+
"action_masks",
|
| 1148 |
+
"img_masks",
|
| 1149 |
+
"frame_masks",
|
| 1150 |
+
"embodiment_ids",
|
| 1151 |
+
"raw_action_dim",
|
| 1152 |
+
"conditioning_fps",
|
| 1153 |
+
"action_fps"
|
| 1154 |
+
],
|
| 1155 |
+
"meta_keys": [
|
| 1156 |
+
"text_token_ids",
|
| 1157 |
+
"sequence_plan",
|
| 1158 |
+
"task_description",
|
| 1159 |
+
"stats",
|
| 1160 |
+
"info",
|
| 1161 |
+
"timestamp",
|
| 1162 |
+
"viewpoint"
|
| 1163 |
+
],
|
| 1164 |
+
"type": "DictCollator"
|
| 1165 |
+
},
|
| 1166 |
+
"enable_gradient_checkpointing": true,
|
| 1167 |
+
"enable_mixed_precision_training": true,
|
| 1168 |
+
"grad_accumulation_steps": 16,
|
| 1169 |
+
"lr_scheduler": {
|
| 1170 |
+
"cycle_length": 100000,
|
| 1171 |
+
"type": "linear-warmup+linear-decay",
|
| 1172 |
+
"warmup_steps": 0
|
| 1173 |
+
},
|
| 1174 |
+
"max_grad_norm": 1,
|
| 1175 |
+
"max_keep_ckpts": 2,
|
| 1176 |
+
"max_steps": 10000,
|
| 1177 |
+
"metric": {
|
| 1178 |
+
"active_trackers": [
|
| 1179 |
+
"jsonl",
|
| 1180 |
+
"wandb"
|
| 1181 |
+
],
|
| 1182 |
+
"grad_accumulation_steps": 16,
|
| 1183 |
+
"run_dir": "/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano",
|
| 1184 |
+
"type": "VLAMetric",
|
| 1185 |
+
"window_size": 1
|
| 1186 |
+
},
|
| 1187 |
+
"mixed_precision_dtype": "bf16",
|
| 1188 |
+
"optimizer": {
|
| 1189 |
+
"betas": [
|
| 1190 |
+
0.9,
|
| 1191 |
+
0.99
|
| 1192 |
+
],
|
| 1193 |
+
"eps": "1e-08",
|
| 1194 |
+
"exclude_1d_from_weight_decay": false,
|
| 1195 |
+
"fused": true,
|
| 1196 |
+
"lr": "5e-05",
|
| 1197 |
+
"paramwise_learning_rate": {
|
| 1198 |
+
"action_in_proj.": 0.00025,
|
| 1199 |
+
"action_modality_embed": 0.00025,
|
| 1200 |
+
"action_out_proj.": 0.00025
|
| 1201 |
+
},
|
| 1202 |
+
"type": "AdamW",
|
| 1203 |
+
"weight_decay": 0.05
|
| 1204 |
+
},
|
| 1205 |
+
"sampler": null,
|
| 1206 |
+
"save_iter_interval": 1000,
|
| 1207 |
+
"sharding_strategy": "full-shard",
|
| 1208 |
+
"tokenizer": {
|
| 1209 |
+
"model_max_length": 4096,
|
| 1210 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 1211 |
+
"padding_side": "right",
|
| 1212 |
+
"trust_remote_code": true,
|
| 1213 |
+
"type": "PretrainedTokenizer"
|
| 1214 |
+
},
|
| 1215 |
+
"type": "FSDPTrainRunner"
|
| 1216 |
+
},
|
| 1217 |
+
"themis": {
|
| 1218 |
+
"ros_server": {
|
| 1219 |
+
"dataset_section": "eval",
|
| 1220 |
+
"denormalize_context": {
|
| 1221 |
+
"task_suite_name": "robodojo_arx_x5"
|
| 1222 |
+
},
|
| 1223 |
+
"device": "cuda:0",
|
| 1224 |
+
"enable_mixed_precision": true,
|
| 1225 |
+
"evaluation_reporting": {
|
| 1226 |
+
"report_kind": "robodojo",
|
| 1227 |
+
"result_output_dir": "work_dirs/fluxthemis"
|
| 1228 |
+
},
|
| 1229 |
+
"forward_seed": false,
|
| 1230 |
+
"mixed_precision_dtype": "bf16",
|
| 1231 |
+
"model_outputs_environment_actions": false,
|
| 1232 |
+
"workers": {
|
| 1233 |
+
"lease_timeout_s": 900,
|
| 1234 |
+
"request_timeout_s": 120,
|
| 1235 |
+
"startup_timeout_s": 900
|
| 1236 |
+
}
|
| 1237 |
+
},
|
| 1238 |
+
"runner": {
|
| 1239 |
+
"environment": {
|
| 1240 |
+
"action_mode": "joint",
|
| 1241 |
+
"device_id": 1,
|
| 1242 |
+
"env_cfg_type": "arx_x5",
|
| 1243 |
+
"headless": true,
|
| 1244 |
+
"robodojo_root": "/root/projects/RoboDojo",
|
| 1245 |
+
"save_videos": false,
|
| 1246 |
+
"task_name": "all",
|
| 1247 |
+
"type": "RoboDojoEnvironment"
|
| 1248 |
+
},
|
| 1249 |
+
"episodes_per_task": 50,
|
| 1250 |
+
"episodes_per_task_overrides": {
|
| 1251 |
+
"arrange_largest_number": 25,
|
| 1252 |
+
"arrange_largest_number_random": 25,
|
| 1253 |
+
"fold_clothes": 25,
|
| 1254 |
+
"fold_clothes_random": 25,
|
| 1255 |
+
"hang_mugs": 25,
|
| 1256 |
+
"hang_mugs_random": 25,
|
| 1257 |
+
"make_toast": 25,
|
| 1258 |
+
"make_toast_random": 25,
|
| 1259 |
+
"pack_objects_into_box": 25,
|
| 1260 |
+
"pack_objects_into_box_random": 25,
|
| 1261 |
+
"pour_liquid_into_cup": 25,
|
| 1262 |
+
"pour_liquid_into_cup_random": 25,
|
| 1263 |
+
"push_T": 25,
|
| 1264 |
+
"push_T_random": 25,
|
| 1265 |
+
"sort_nesting_dolls_by_size": 25,
|
| 1266 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 1267 |
+
"stack_blocks": 25,
|
| 1268 |
+
"stack_blocks_random": 25,
|
| 1269 |
+
"stack_bowls": 25,
|
| 1270 |
+
"stack_bowls_random": 25,
|
| 1271 |
+
"store_laptop_and_headphones": 25,
|
| 1272 |
+
"store_laptop_and_headphones_random": 25,
|
| 1273 |
+
"sweep_blocks": 25,
|
| 1274 |
+
"sweep_blocks_random": 25
|
| 1275 |
+
},
|
| 1276 |
+
"evaluator": {
|
| 1277 |
+
"type": "SuccessRateEvaluator"
|
| 1278 |
+
},
|
| 1279 |
+
"execute_horizon": 32,
|
| 1280 |
+
"max_episode_steps": 2000,
|
| 1281 |
+
"model_client": {
|
| 1282 |
+
"type": "FluxVLAZMQModelClient"
|
| 1283 |
+
},
|
| 1284 |
+
"parallel_workers": 1,
|
| 1285 |
+
"seed": 0,
|
| 1286 |
+
"simulator_gpu_ids": null,
|
| 1287 |
+
"stop_on_success": true,
|
| 1288 |
+
"type": "EvalRunner",
|
| 1289 |
+
"work_dir": "work_dirs/fluxthemis"
|
| 1290 |
+
},
|
| 1291 |
+
"transport": {
|
| 1292 |
+
"host": "127.0.0.1",
|
| 1293 |
+
"image_encoding": "rgb8",
|
| 1294 |
+
"image_keys": [
|
| 1295 |
+
"cam_high",
|
| 1296 |
+
"cam_left_wrist",
|
| 1297 |
+
"cam_right_wrist"
|
| 1298 |
+
],
|
| 1299 |
+
"port": 5555,
|
| 1300 |
+
"report_service_name": "/fluxvla/report_evaluation",
|
| 1301 |
+
"state_keys": [
|
| 1302 |
+
"states"
|
| 1303 |
+
],
|
| 1304 |
+
"timeout_s": 30,
|
| 1305 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 1306 |
+
}
|
| 1307 |
+
},
|
| 1308 |
+
"train_dataloader": {
|
| 1309 |
+
"dataset": {
|
| 1310 |
+
"datasets": {
|
| 1311 |
+
"action_key": "action",
|
| 1312 |
+
"action_window_size": 32,
|
| 1313 |
+
"data_root_path": [
|
| 1314 |
+
"./datasets/RoboDojo_lerobot_v21_video"
|
| 1315 |
+
],
|
| 1316 |
+
"frame_window_size": 33,
|
| 1317 |
+
"require_full_window": true,
|
| 1318 |
+
"statistic_name": "robodojo_arx_x5",
|
| 1319 |
+
"transforms": [
|
| 1320 |
+
{
|
| 1321 |
+
"embodiment_id": 31,
|
| 1322 |
+
"name_mappings": {
|
| 1323 |
+
"actions": [
|
| 1324 |
+
"actions"
|
| 1325 |
+
],
|
| 1326 |
+
"observation.state": [
|
| 1327 |
+
"states"
|
| 1328 |
+
]
|
| 1329 |
+
},
|
| 1330 |
+
"parquet_keys": [
|
| 1331 |
+
"observation.state",
|
| 1332 |
+
"timestamp",
|
| 1333 |
+
"actions",
|
| 1334 |
+
"info",
|
| 1335 |
+
"stats",
|
| 1336 |
+
"action_masks"
|
| 1337 |
+
],
|
| 1338 |
+
"type": "ProcessParquetInputs",
|
| 1339 |
+
"video_keys": [
|
| 1340 |
+
"observation.images.cam_high",
|
| 1341 |
+
"observation.images.cam_left_wrist",
|
| 1342 |
+
"observation.images.cam_right_wrist"
|
| 1343 |
+
]
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"height": 192,
|
| 1347 |
+
"type": "ResizeImages",
|
| 1348 |
+
"width": 256
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"brightness_range": [
|
| 1352 |
+
0.7,
|
| 1353 |
+
1.3
|
| 1354 |
+
],
|
| 1355 |
+
"contrast_range": [
|
| 1356 |
+
0.6,
|
| 1357 |
+
1.4
|
| 1358 |
+
],
|
| 1359 |
+
"crop_ratio": [
|
| 1360 |
+
1,
|
| 1361 |
+
1
|
| 1362 |
+
],
|
| 1363 |
+
"crop_scale": [
|
| 1364 |
+
0.95,
|
| 1365 |
+
0.95
|
| 1366 |
+
],
|
| 1367 |
+
"hue_delta": 0.08,
|
| 1368 |
+
"prob": 1,
|
| 1369 |
+
"rotation_range": 0,
|
| 1370 |
+
"saturation_range": [
|
| 1371 |
+
0.5,
|
| 1372 |
+
1.5
|
| 1373 |
+
],
|
| 1374 |
+
"type": "AugVideo"
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"action_metadata": {
|
| 1378 |
+
"append_viewpoint": false,
|
| 1379 |
+
"conditioning_fps": 25,
|
| 1380 |
+
"frame_window_size": 33,
|
| 1381 |
+
"video_height": 320,
|
| 1382 |
+
"video_width": 256,
|
| 1383 |
+
"viewpoint": "concat_view"
|
| 1384 |
+
},
|
| 1385 |
+
"cfg_dropout_rate": 0.1,
|
| 1386 |
+
"format_prompt_as_json": true,
|
| 1387 |
+
"max_len": 512,
|
| 1388 |
+
"tokenizer": {
|
| 1389 |
+
"model_max_length": 4096,
|
| 1390 |
+
"model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
|
| 1391 |
+
"padding_side": "right",
|
| 1392 |
+
"trust_remote_code": true,
|
| 1393 |
+
"type": "PretrainedTokenizer"
|
| 1394 |
+
},
|
| 1395 |
+
"type": "ProcessCosmos3Prompt"
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"type": "SimpleNormalizeImages"
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"action_dim": 64,
|
| 1402 |
+
"action_key": "action",
|
| 1403 |
+
"action_norm_type": "quantile",
|
| 1404 |
+
"state_dim": 64,
|
| 1405 |
+
"state_key": "proprio",
|
| 1406 |
+
"state_norm_type": "none",
|
| 1407 |
+
"type": "NormalizeStatesAndActions"
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"conditioning_fps": 25,
|
| 1411 |
+
"frame_window_size": 33,
|
| 1412 |
+
"mode": "wam",
|
| 1413 |
+
"prepend_state_to_action": false,
|
| 1414 |
+
"raw_action_dim": 14,
|
| 1415 |
+
"type": "BuildCosmos3Sequence"
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"bottom_height_ratio": 0.5,
|
| 1419 |
+
"bottom_views": [
|
| 1420 |
+
1,
|
| 1421 |
+
2
|
| 1422 |
+
],
|
| 1423 |
+
"frame_window_size": 33,
|
| 1424 |
+
"num_views": 3,
|
| 1425 |
+
"tile_direction": "top_bottom_pair",
|
| 1426 |
+
"top_view": 0,
|
| 1427 |
+
"type": "PrepareVideo"
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"height": 320,
|
| 1431 |
+
"type": "ResizeAndReflectPad",
|
| 1432 |
+
"width": 256
|
| 1433 |
+
}
|
| 1434 |
+
],
|
| 1435 |
+
"type": "ParquetDataset",
|
| 1436 |
+
"use_delta": false,
|
| 1437 |
+
"window_start_idx": 0
|
| 1438 |
+
},
|
| 1439 |
+
"name_mappings": {
|
| 1440 |
+
"action": [
|
| 1441 |
+
"action"
|
| 1442 |
+
],
|
| 1443 |
+
"observation.state": [
|
| 1444 |
+
"proprio"
|
| 1445 |
+
]
|
| 1446 |
+
},
|
| 1447 |
+
"reshuffle_each_epoch": true,
|
| 1448 |
+
"seed": 42,
|
| 1449 |
+
"statistic_keys": [
|
| 1450 |
+
"observation.state",
|
| 1451 |
+
"action",
|
| 1452 |
+
"timestamp"
|
| 1453 |
+
],
|
| 1454 |
+
"statistic_name": "robodojo_arx_x5",
|
| 1455 |
+
"statistics_overrides": {
|
| 1456 |
+
"robodojo_arx_x5": {
|
| 1457 |
+
"action": {
|
| 1458 |
+
"q01": [
|
| 1459 |
+
-1.051365569829941,
|
| 1460 |
+
-3.5348887174584814e-14,
|
| 1461 |
+
1.741881830823392e-16,
|
| 1462 |
+
-1.5984010362625123,
|
| 1463 |
+
-0.6003574305772781,
|
| 1464 |
+
-1.6678147149085998,
|
| 1465 |
+
0,
|
| 1466 |
+
-0.4509398394823074,
|
| 1467 |
+
-2.5859282299029243e-14,
|
| 1468 |
+
1.234041714549172e-16,
|
| 1469 |
+
-1.64055180311203,
|
| 1470 |
+
-1.2633746123313903,
|
| 1471 |
+
-1.7645285475254058,
|
| 1472 |
+
0
|
| 1473 |
+
],
|
| 1474 |
+
"q99": [
|
| 1475 |
+
0.5431358617544174,
|
| 1476 |
+
2.495765209197998,
|
| 1477 |
+
2.492974226474762,
|
| 1478 |
+
1.3241519677639007,
|
| 1479 |
+
1.2496635341644287,
|
| 1480 |
+
1.7392305016517635,
|
| 1481 |
+
1,
|
| 1482 |
+
1.0814965963363647,
|
| 1483 |
+
2.4167031812667843,
|
| 1484 |
+
2.3470158338546754,
|
| 1485 |
+
1.141731116771698,
|
| 1486 |
+
0.5208872479200363,
|
| 1487 |
+
1.489715996980667,
|
| 1488 |
+
1
|
| 1489 |
+
]
|
| 1490 |
+
}
|
| 1491 |
+
}
|
| 1492 |
+
},
|
| 1493 |
+
"type": "DistributedRepeatingDataset"
|
| 1494 |
+
},
|
| 1495 |
+
"per_device_batch_size": 8,
|
| 1496 |
+
"per_device_num_workers": 4,
|
| 1497 |
+
"prefetch_factor": 1
|
| 1498 |
+
}
|
| 1499 |
+
}
|
|
@@ -0,0 +1,1640 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ACTION_DIM: 14
|
| 2 |
+
_ACTION_HORIZON: 32
|
| 3 |
+
_CONDITIONING_FPS: 25
|
| 4 |
+
_EMBODIMENT_ID: 31
|
| 5 |
+
_FRAME_WINDOW_SIZE: 33
|
| 6 |
+
_IMAGE_HEIGHT: 192
|
| 7 |
+
_IMAGE_WIDTH: 256
|
| 8 |
+
_MAX_ACTION_DIM: 64
|
| 9 |
+
_MAX_STATE_DIM: 64
|
| 10 |
+
_PREPEND_STATE_TO_ACTION: false
|
| 11 |
+
_ROBODOJO_ACTION_QUANTILES:
|
| 12 |
+
q01:
|
| 13 |
+
- -1.051365569829941
|
| 14 |
+
- -3.5348887174584814e-14
|
| 15 |
+
- 1.741881830823392e-16
|
| 16 |
+
- -1.5984010362625123
|
| 17 |
+
- -0.6003574305772781
|
| 18 |
+
- -1.6678147149085998
|
| 19 |
+
- 0
|
| 20 |
+
- -0.4509398394823074
|
| 21 |
+
- -2.5859282299029243e-14
|
| 22 |
+
- 1.234041714549172e-16
|
| 23 |
+
- -1.64055180311203
|
| 24 |
+
- -1.2633746123313903
|
| 25 |
+
- -1.7645285475254058
|
| 26 |
+
- 0
|
| 27 |
+
q99:
|
| 28 |
+
- 0.5431358617544174
|
| 29 |
+
- 2.495765209197998
|
| 30 |
+
- 2.492974226474762
|
| 31 |
+
- 1.3241519677639007
|
| 32 |
+
- 1.2496635341644287
|
| 33 |
+
- 1.7392305016517635
|
| 34 |
+
- 1
|
| 35 |
+
- 1.0814965963363647
|
| 36 |
+
- 2.4167031812667843
|
| 37 |
+
- 2.3470158338546754
|
| 38 |
+
- 1.141731116771698
|
| 39 |
+
- 0.5208872479200363
|
| 40 |
+
- 1.489715996980667
|
| 41 |
+
- 1
|
| 42 |
+
_ROBODOJO_DATA_ROOT: ./datasets/RoboDojo_lerobot_v21_video
|
| 43 |
+
_ROBODOJO_EPISODE_OVERRIDES:
|
| 44 |
+
arrange_largest_number: 25
|
| 45 |
+
arrange_largest_number_random: 25
|
| 46 |
+
fold_clothes: 25
|
| 47 |
+
fold_clothes_random: 25
|
| 48 |
+
hang_mugs: 25
|
| 49 |
+
hang_mugs_random: 25
|
| 50 |
+
make_toast: 25
|
| 51 |
+
make_toast_random: 25
|
| 52 |
+
pack_objects_into_box: 25
|
| 53 |
+
pack_objects_into_box_random: 25
|
| 54 |
+
pour_liquid_into_cup: 25
|
| 55 |
+
pour_liquid_into_cup_random: 25
|
| 56 |
+
push_T: 25
|
| 57 |
+
push_T_random: 25
|
| 58 |
+
sort_nesting_dolls_by_size: 25
|
| 59 |
+
sort_nesting_dolls_by_size_random: 25
|
| 60 |
+
stack_blocks: 25
|
| 61 |
+
stack_blocks_random: 25
|
| 62 |
+
stack_bowls: 25
|
| 63 |
+
stack_bowls_random: 25
|
| 64 |
+
store_laptop_and_headphones: 25
|
| 65 |
+
store_laptop_and_headphones_random: 25
|
| 66 |
+
sweep_blocks: 25
|
| 67 |
+
sweep_blocks_random: 25
|
| 68 |
+
_ROBODOJO_GENERALIZATION_BASE_TASKS:
|
| 69 |
+
- stack_bowls
|
| 70 |
+
- push_T
|
| 71 |
+
- pack_objects_into_box
|
| 72 |
+
- fold_clothes
|
| 73 |
+
- hang_mugs
|
| 74 |
+
- sweep_blocks
|
| 75 |
+
- pour_liquid_into_cup
|
| 76 |
+
- make_toast
|
| 77 |
+
- arrange_largest_number
|
| 78 |
+
- sort_nesting_dolls_by_size
|
| 79 |
+
- store_laptop_and_headphones
|
| 80 |
+
- stack_blocks
|
| 81 |
+
_ROBODOJO_TRANSFORMS:
|
| 82 |
+
- embodiment_id: 31
|
| 83 |
+
name_mappings:
|
| 84 |
+
actions:
|
| 85 |
+
- actions
|
| 86 |
+
observation.state:
|
| 87 |
+
- states
|
| 88 |
+
parquet_keys:
|
| 89 |
+
- observation.state
|
| 90 |
+
- timestamp
|
| 91 |
+
- actions
|
| 92 |
+
- info
|
| 93 |
+
- stats
|
| 94 |
+
- action_masks
|
| 95 |
+
type: ProcessParquetInputs
|
| 96 |
+
video_keys:
|
| 97 |
+
- observation.images.cam_high
|
| 98 |
+
- observation.images.cam_left_wrist
|
| 99 |
+
- observation.images.cam_right_wrist
|
| 100 |
+
- height: 192
|
| 101 |
+
type: ResizeImages
|
| 102 |
+
width: 256
|
| 103 |
+
- brightness_range:
|
| 104 |
+
- 0.7
|
| 105 |
+
- 1.3
|
| 106 |
+
contrast_range:
|
| 107 |
+
- 0.6
|
| 108 |
+
- 1.4
|
| 109 |
+
crop_ratio:
|
| 110 |
+
- 1
|
| 111 |
+
- 1
|
| 112 |
+
crop_scale:
|
| 113 |
+
- 0.95
|
| 114 |
+
- 0.95
|
| 115 |
+
hue_delta: 0.08
|
| 116 |
+
prob: 1
|
| 117 |
+
rotation_range: 0
|
| 118 |
+
saturation_range:
|
| 119 |
+
- 0.5
|
| 120 |
+
- 1.5
|
| 121 |
+
type: AugVideo
|
| 122 |
+
- action_metadata:
|
| 123 |
+
append_viewpoint: false
|
| 124 |
+
conditioning_fps: 25
|
| 125 |
+
frame_window_size: 33
|
| 126 |
+
video_height: 320
|
| 127 |
+
video_width: 256
|
| 128 |
+
viewpoint: concat_view
|
| 129 |
+
cfg_dropout_rate: 0.1
|
| 130 |
+
format_prompt_as_json: true
|
| 131 |
+
max_len: 512
|
| 132 |
+
tokenizer:
|
| 133 |
+
model_max_length: 4096
|
| 134 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 135 |
+
padding_side: right
|
| 136 |
+
trust_remote_code: true
|
| 137 |
+
type: PretrainedTokenizer
|
| 138 |
+
type: ProcessCosmos3Prompt
|
| 139 |
+
- type: SimpleNormalizeImages
|
| 140 |
+
- action_dim: 64
|
| 141 |
+
action_key: action
|
| 142 |
+
action_norm_type: quantile
|
| 143 |
+
state_dim: 64
|
| 144 |
+
state_key: proprio
|
| 145 |
+
state_norm_type: none
|
| 146 |
+
type: NormalizeStatesAndActions
|
| 147 |
+
- conditioning_fps: 25
|
| 148 |
+
frame_window_size: 33
|
| 149 |
+
mode: wam
|
| 150 |
+
prepend_state_to_action: false
|
| 151 |
+
raw_action_dim: 14
|
| 152 |
+
type: BuildCosmos3Sequence
|
| 153 |
+
- bottom_height_ratio: 0.5
|
| 154 |
+
bottom_views:
|
| 155 |
+
- 1
|
| 156 |
+
- 2
|
| 157 |
+
frame_window_size: 33
|
| 158 |
+
num_views: 3
|
| 159 |
+
tile_direction: top_bottom_pair
|
| 160 |
+
top_view: 0
|
| 161 |
+
type: PrepareVideo
|
| 162 |
+
- height: 320
|
| 163 |
+
type: ResizeAndReflectPad
|
| 164 |
+
width: 256
|
| 165 |
+
_STATISTIC_NAME: robodojo_arx_x5
|
| 166 |
+
_VAE_ENCODE_CHUNK_FRAMES:
|
| 167 |
+
'256': 16
|
| 168 |
+
'480': 24
|
| 169 |
+
'720': 12
|
| 170 |
+
_VIDEO_HEIGHT: 320
|
| 171 |
+
_VIDEO_WIDTH: 256
|
| 172 |
+
_action_dim: 10
|
| 173 |
+
_action_horizon: 16
|
| 174 |
+
_action_lr: 0.00025
|
| 175 |
+
_base_lr: 5e-05
|
| 176 |
+
_cfg_dropout_rate: 0.1
|
| 177 |
+
_ckpt_root: ./checkpoints
|
| 178 |
+
_conditioning_fps: 20
|
| 179 |
+
_cosmos3_nano_ckpt: ./checkpoints/Cosmos3-Nano
|
| 180 |
+
_cosmos3_nano_name_mapping:
|
| 181 |
+
.self_attn.k_norm.: .self_attn.norm_k.
|
| 182 |
+
.self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
|
| 183 |
+
.self_attn.k_proj.: .self_attn.to_k.
|
| 184 |
+
.self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
|
| 185 |
+
.self_attn.o_proj.: .self_attn.to_out.
|
| 186 |
+
.self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
|
| 187 |
+
.self_attn.q_norm.: .self_attn.norm_q.
|
| 188 |
+
.self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
|
| 189 |
+
.self_attn.q_proj.: .self_attn.to_q.
|
| 190 |
+
.self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
|
| 191 |
+
.self_attn.v_proj.: .self_attn.to_v.
|
| 192 |
+
.self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
|
| 193 |
+
action_in_proj.: action_proj_in.
|
| 194 |
+
action_modality_embed: action_modality_embed
|
| 195 |
+
action_out_proj.: action_proj_out.
|
| 196 |
+
time_embedder.mlp.0.: time_embedder.linear_1.
|
| 197 |
+
time_embedder.mlp.2.: time_embedder.linear_2.
|
| 198 |
+
vision_in_proj.projector.: proj_in.
|
| 199 |
+
vision_out_proj.projector.: proj_out.
|
| 200 |
+
vlm_backbone.lm_head.weight: lm_head.weight
|
| 201 |
+
vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
|
| 202 |
+
vlm_backbone.model.language_model.layers.: layers.
|
| 203 |
+
vlm_backbone.model.language_model.norm.weight: norm.weight
|
| 204 |
+
vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
|
| 205 |
+
vlm_backbone.model.visual.blocks.: blocks.
|
| 206 |
+
vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
|
| 207 |
+
vlm_backbone.model.visual.merger.: merger.
|
| 208 |
+
vlm_backbone.model.visual.patch_embed.: patch_embed.
|
| 209 |
+
vlm_backbone.model.visual.pos_embed.: pos_embed.
|
| 210 |
+
_cosmos3_nano_special_tokens:
|
| 211 |
+
end_of_generation: 151653
|
| 212 |
+
eos_token_id: 151645
|
| 213 |
+
start_of_generation: 151652
|
| 214 |
+
_cosmos3_nano_tokenizer:
|
| 215 |
+
model_max_length: 4096
|
| 216 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 217 |
+
padding_side: right
|
| 218 |
+
trust_remote_code: true
|
| 219 |
+
type: PretrainedTokenizer
|
| 220 |
+
_cosmos3_nano_transformer: ./checkpoints/Cosmos3-Nano/transformer
|
| 221 |
+
_cosmos3_nano_vision_encoder: ./checkpoints/Cosmos3-Nano/vision_encoder
|
| 222 |
+
_cosmos3_nano_vlm_config:
|
| 223 |
+
image_token_id: 151655
|
| 224 |
+
model_type: qwen3_vl
|
| 225 |
+
text_config:
|
| 226 |
+
attention_bias: false
|
| 227 |
+
attention_dropout: 0
|
| 228 |
+
bos_token_id: 151643
|
| 229 |
+
eos_token_id: 151645
|
| 230 |
+
head_dim: 128
|
| 231 |
+
hidden_act: silu
|
| 232 |
+
hidden_size: 4096
|
| 233 |
+
intermediate_size: 12288
|
| 234 |
+
layer_types:
|
| 235 |
+
- full_attention
|
| 236 |
+
- full_attention
|
| 237 |
+
- full_attention
|
| 238 |
+
- full_attention
|
| 239 |
+
- full_attention
|
| 240 |
+
- full_attention
|
| 241 |
+
- full_attention
|
| 242 |
+
- full_attention
|
| 243 |
+
- full_attention
|
| 244 |
+
- full_attention
|
| 245 |
+
- full_attention
|
| 246 |
+
- full_attention
|
| 247 |
+
- full_attention
|
| 248 |
+
- full_attention
|
| 249 |
+
- full_attention
|
| 250 |
+
- full_attention
|
| 251 |
+
- full_attention
|
| 252 |
+
- full_attention
|
| 253 |
+
- full_attention
|
| 254 |
+
- full_attention
|
| 255 |
+
- full_attention
|
| 256 |
+
- full_attention
|
| 257 |
+
- full_attention
|
| 258 |
+
- full_attention
|
| 259 |
+
- full_attention
|
| 260 |
+
- full_attention
|
| 261 |
+
- full_attention
|
| 262 |
+
- full_attention
|
| 263 |
+
- full_attention
|
| 264 |
+
- full_attention
|
| 265 |
+
- full_attention
|
| 266 |
+
- full_attention
|
| 267 |
+
- full_attention
|
| 268 |
+
- full_attention
|
| 269 |
+
- full_attention
|
| 270 |
+
- full_attention
|
| 271 |
+
max_position_embeddings: 262144
|
| 272 |
+
model_type: qwen3_vl_text
|
| 273 |
+
num_attention_heads: 32
|
| 274 |
+
num_hidden_layers: 36
|
| 275 |
+
num_key_value_heads: 8
|
| 276 |
+
pad_token_id: 0
|
| 277 |
+
rms_norm_eps: 1e-06
|
| 278 |
+
rope_scaling:
|
| 279 |
+
mrope_interleaved: true
|
| 280 |
+
mrope_section:
|
| 281 |
+
- 24
|
| 282 |
+
- 20
|
| 283 |
+
- 20
|
| 284 |
+
rope_type: default
|
| 285 |
+
rope_theta: 5000000
|
| 286 |
+
tie_word_embeddings: false
|
| 287 |
+
vocab_size: 151936
|
| 288 |
+
tie_word_embeddings: false
|
| 289 |
+
video_token_id: 151656
|
| 290 |
+
vision_config:
|
| 291 |
+
deepstack_visual_indexes:
|
| 292 |
+
- 8
|
| 293 |
+
- 16
|
| 294 |
+
- 24
|
| 295 |
+
depth: 27
|
| 296 |
+
hidden_act: gelu_pytorch_tanh
|
| 297 |
+
hidden_size: 1152
|
| 298 |
+
in_channels: 3
|
| 299 |
+
initializer_range: 0.02
|
| 300 |
+
intermediate_size: 4304
|
| 301 |
+
model_type: qwen3_vl
|
| 302 |
+
num_heads: 16
|
| 303 |
+
num_position_embeddings: 2304
|
| 304 |
+
out_hidden_size: 4096
|
| 305 |
+
patch_size: 16
|
| 306 |
+
spatial_merge_size: 2
|
| 307 |
+
temporal_patch_size: 2
|
| 308 |
+
vision_end_token_id: 151653
|
| 309 |
+
vision_start_token_id: 151652
|
| 310 |
+
vocab_size: 151936
|
| 311 |
+
_frame_window_size: 17
|
| 312 |
+
_grad_accumulation_steps: 8
|
| 313 |
+
_image_height: 256
|
| 314 |
+
_image_width: 256
|
| 315 |
+
_libero_action_stats:
|
| 316 |
+
max:
|
| 317 |
+
- 0.9375
|
| 318 |
+
- 0.9375
|
| 319 |
+
- 0.9375
|
| 320 |
+
- 1
|
| 321 |
+
- 0.368853
|
| 322 |
+
- 0.341214
|
| 323 |
+
- 0.356395
|
| 324 |
+
- 1
|
| 325 |
+
- 0.348251
|
| 326 |
+
- 1
|
| 327 |
+
mean:
|
| 328 |
+
- 0.050704
|
| 329 |
+
- 0.097407
|
| 330 |
+
- -0.094833
|
| 331 |
+
- 0.994873
|
| 332 |
+
- -0.004579
|
| 333 |
+
- -0.004288
|
| 334 |
+
- 0.004389
|
| 335 |
+
- 0.996104
|
| 336 |
+
- 0.001109
|
| 337 |
+
- 0.476725
|
| 338 |
+
min:
|
| 339 |
+
- -0.9375
|
| 340 |
+
- -0.9375
|
| 341 |
+
- -0.9375
|
| 342 |
+
- 0.902028
|
| 343 |
+
- -0.356085
|
| 344 |
+
- -0.367416
|
| 345 |
+
- -0.370434
|
| 346 |
+
- 0.921907
|
| 347 |
+
- -0.255
|
| 348 |
+
- 0
|
| 349 |
+
q01:
|
| 350 |
+
- -0.723214
|
| 351 |
+
- -0.808929
|
| 352 |
+
- -0.9375
|
| 353 |
+
- 0.934955
|
| 354 |
+
- -0.223431
|
| 355 |
+
- -0.189878
|
| 356 |
+
- -0.334735
|
| 357 |
+
- 0.938516
|
| 358 |
+
- -0.107736
|
| 359 |
+
- 0
|
| 360 |
+
q99:
|
| 361 |
+
- 0.9375
|
| 362 |
+
- 0.870536
|
| 363 |
+
- 0.9375
|
| 364 |
+
- 1
|
| 365 |
+
- 0.331
|
| 366 |
+
- 0.163153
|
| 367 |
+
- 0.226216
|
| 368 |
+
- 1
|
| 369 |
+
- 0.127158
|
| 370 |
+
- 1
|
| 371 |
+
std:
|
| 372 |
+
- 0.333621
|
| 373 |
+
- 0.387175
|
| 374 |
+
- 0.45714
|
| 375 |
+
- 0.010807
|
| 376 |
+
- 0.077802
|
| 377 |
+
- 0.063386
|
| 378 |
+
- 0.078571
|
| 379 |
+
- 0.009994
|
| 380 |
+
- 0.038504
|
| 381 |
+
- 0.49946
|
| 382 |
+
_max_action_dim: 64
|
| 383 |
+
_max_state_dim: 64
|
| 384 |
+
_max_steps: 2000
|
| 385 |
+
_per_device_batch_size: 16
|
| 386 |
+
_prepend_state_to_action: false
|
| 387 |
+
_save_iter_interval: 500
|
| 388 |
+
_transforms:
|
| 389 |
+
- embodiment_id: 5
|
| 390 |
+
name_mappings:
|
| 391 |
+
actions:
|
| 392 |
+
- actions
|
| 393 |
+
observation.state:
|
| 394 |
+
- states
|
| 395 |
+
parquet_keys:
|
| 396 |
+
- observation.state
|
| 397 |
+
- timestamp
|
| 398 |
+
- actions
|
| 399 |
+
- info
|
| 400 |
+
- stats
|
| 401 |
+
- action_masks
|
| 402 |
+
type: ProcessParquetInputs
|
| 403 |
+
video_keys:
|
| 404 |
+
- observation.images.image
|
| 405 |
+
- observation.images.wrist_image
|
| 406 |
+
- type: LiberoFramewiseActionToRot6D
|
| 407 |
+
- action_metadata:
|
| 408 |
+
append_viewpoint: false
|
| 409 |
+
conditioning_fps: 20
|
| 410 |
+
frame_window_size: 17
|
| 411 |
+
video_height: 192
|
| 412 |
+
video_width: 320
|
| 413 |
+
cfg_dropout_rate: 0.1
|
| 414 |
+
format_prompt_as_json: true
|
| 415 |
+
max_len: 512
|
| 416 |
+
tokenizer:
|
| 417 |
+
model_max_length: 4096
|
| 418 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 419 |
+
padding_side: right
|
| 420 |
+
trust_remote_code: true
|
| 421 |
+
type: PretrainedTokenizer
|
| 422 |
+
type: ProcessCosmos3Prompt
|
| 423 |
+
- height: 256
|
| 424 |
+
type: ResizeImages
|
| 425 |
+
width: 256
|
| 426 |
+
- type: SimpleNormalizeImages
|
| 427 |
+
- action_dim: 64
|
| 428 |
+
action_key: action
|
| 429 |
+
action_norm_type: quantile
|
| 430 |
+
state_dim: 64
|
| 431 |
+
state_key: proprio
|
| 432 |
+
state_norm_type: none
|
| 433 |
+
type: NormalizeStatesAndActions
|
| 434 |
+
- conditioning_fps: 20
|
| 435 |
+
frame_window_size: 17
|
| 436 |
+
mode: wam
|
| 437 |
+
prepend_state_to_action: false
|
| 438 |
+
raw_action_dim: 10
|
| 439 |
+
type: BuildCosmos3Sequence
|
| 440 |
+
- frame_window_size: 17
|
| 441 |
+
num_views: 2
|
| 442 |
+
tile_direction: horizontal
|
| 443 |
+
type: PrepareVideo
|
| 444 |
+
- height: 192
|
| 445 |
+
type: ResizeAndReflectPad
|
| 446 |
+
width: 320
|
| 447 |
+
_video_height: 192
|
| 448 |
+
_video_width: 320
|
| 449 |
+
_vision_vae:
|
| 450 |
+
encode_exact_durations:
|
| 451 |
+
- 17
|
| 452 |
+
pretrained_name_or_path: ./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth
|
| 453 |
+
type: Cosmos3Wan22VAE
|
| 454 |
+
_wan22_vae_path: ./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth
|
| 455 |
+
eval:
|
| 456 |
+
dataset:
|
| 457 |
+
transforms:
|
| 458 |
+
- embodiment_id: 31
|
| 459 |
+
img_keys:
|
| 460 |
+
- cam_high
|
| 461 |
+
- cam_left_wrist
|
| 462 |
+
- cam_right_wrist
|
| 463 |
+
type: ProcessEvalInputs
|
| 464 |
+
- conditioning_fps: 25
|
| 465 |
+
prepend_state_to_action: false
|
| 466 |
+
type: SetCosmos3ActionMetadata
|
| 467 |
+
- action_metadata:
|
| 468 |
+
append_viewpoint: false
|
| 469 |
+
conditioning_fps: 25
|
| 470 |
+
frame_window_size: 33
|
| 471 |
+
video_height: 320
|
| 472 |
+
video_width: 256
|
| 473 |
+
viewpoint: concat_view
|
| 474 |
+
cfg_dropout_rate: 0
|
| 475 |
+
format_prompt_as_json: true
|
| 476 |
+
max_len: 512
|
| 477 |
+
output_attention_mask_key: lang_masks
|
| 478 |
+
output_key: lang_tokens
|
| 479 |
+
tokenizer:
|
| 480 |
+
model_max_length: 4096
|
| 481 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 482 |
+
padding_side: right
|
| 483 |
+
trust_remote_code: true
|
| 484 |
+
type: PretrainedTokenizer
|
| 485 |
+
type: ProcessCosmos3Prompt
|
| 486 |
+
- image_resize_strategy: resize-naive
|
| 487 |
+
input_sizes:
|
| 488 |
+
- - 3
|
| 489 |
+
- 256
|
| 490 |
+
- 192
|
| 491 |
+
- - 3
|
| 492 |
+
- 256
|
| 493 |
+
- 192
|
| 494 |
+
- - 3
|
| 495 |
+
- 256
|
| 496 |
+
- 192
|
| 497 |
+
means:
|
| 498 |
+
- - 127.5
|
| 499 |
+
- 127.5
|
| 500 |
+
- 127.5
|
| 501 |
+
- - 127.5
|
| 502 |
+
- 127.5
|
| 503 |
+
- 127.5
|
| 504 |
+
- - 127.5
|
| 505 |
+
- 127.5
|
| 506 |
+
- 127.5
|
| 507 |
+
stds:
|
| 508 |
+
- - 127.5
|
| 509 |
+
- 127.5
|
| 510 |
+
- 127.5
|
| 511 |
+
- - 127.5
|
| 512 |
+
- 127.5
|
| 513 |
+
- 127.5
|
| 514 |
+
- - 127.5
|
| 515 |
+
- 127.5
|
| 516 |
+
- 127.5
|
| 517 |
+
type: TransformImage
|
| 518 |
+
- bottom_height_ratio: 0.5
|
| 519 |
+
bottom_views:
|
| 520 |
+
- 1
|
| 521 |
+
- 2
|
| 522 |
+
frame_window_size: 1
|
| 523 |
+
num_views: 3
|
| 524 |
+
tile_direction: top_bottom_pair
|
| 525 |
+
top_view: 0
|
| 526 |
+
type: PrepareVideo
|
| 527 |
+
- height: 320
|
| 528 |
+
type: ResizeAndReflectPad
|
| 529 |
+
width: 256
|
| 530 |
+
type: RoboDojoEvalDataset
|
| 531 |
+
unnorm_key: robodojo_arx_x5
|
| 532 |
+
denormalize_action:
|
| 533 |
+
action_dim: 14
|
| 534 |
+
norm_type: quantile
|
| 535 |
+
statistic_name: robodojo_arx_x5
|
| 536 |
+
type: DenormalizePrivateAction
|
| 537 |
+
enable_mixed_precision_training: true
|
| 538 |
+
eval_chunk_size: 32
|
| 539 |
+
mixed_precision_dtype: bf16
|
| 540 |
+
model_family: cosmos3
|
| 541 |
+
num_trials_per_task: 50
|
| 542 |
+
num_trials_per_task_overrides:
|
| 543 |
+
arrange_largest_number: 25
|
| 544 |
+
arrange_largest_number_random: 25
|
| 545 |
+
fold_clothes: 25
|
| 546 |
+
fold_clothes_random: 25
|
| 547 |
+
hang_mugs: 25
|
| 548 |
+
hang_mugs_random: 25
|
| 549 |
+
make_toast: 25
|
| 550 |
+
make_toast_random: 25
|
| 551 |
+
pack_objects_into_box: 25
|
| 552 |
+
pack_objects_into_box_random: 25
|
| 553 |
+
pour_liquid_into_cup: 25
|
| 554 |
+
pour_liquid_into_cup_random: 25
|
| 555 |
+
push_T: 25
|
| 556 |
+
push_T_random: 25
|
| 557 |
+
sort_nesting_dolls_by_size: 25
|
| 558 |
+
sort_nesting_dolls_by_size_random: 25
|
| 559 |
+
stack_blocks: 25
|
| 560 |
+
stack_blocks_random: 25
|
| 561 |
+
stack_bowls: 25
|
| 562 |
+
stack_bowls_random: 25
|
| 563 |
+
store_laptop_and_headphones: 25
|
| 564 |
+
store_laptop_and_headphones_random: 25
|
| 565 |
+
sweep_blocks: 25
|
| 566 |
+
sweep_blocks_random: 25
|
| 567 |
+
report_kind: robodojo
|
| 568 |
+
task_suite_name: robodojo
|
| 569 |
+
inference_model:
|
| 570 |
+
action_horizon: 32
|
| 571 |
+
action_in_proj:
|
| 572 |
+
input_size: 64
|
| 573 |
+
num_domains: 32
|
| 574 |
+
output_size: 4096
|
| 575 |
+
type: DomainAwareLinear
|
| 576 |
+
action_out_proj:
|
| 577 |
+
input_size: 4096
|
| 578 |
+
num_domains: 32
|
| 579 |
+
output_size: 64
|
| 580 |
+
type: DomainAwareLinear
|
| 581 |
+
base_fps: 24
|
| 582 |
+
enable_fps_modulation: true
|
| 583 |
+
enable_vision_loss: true
|
| 584 |
+
freeze_non_moe_vlm_backbone: true
|
| 585 |
+
freeze_vlm_backbone: false
|
| 586 |
+
latent_patch_size: 2
|
| 587 |
+
max_action_dim: 64
|
| 588 |
+
name_mapping:
|
| 589 |
+
.self_attn.k_norm.: .self_attn.norm_k.
|
| 590 |
+
.self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
|
| 591 |
+
.self_attn.k_proj.: .self_attn.to_k.
|
| 592 |
+
.self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
|
| 593 |
+
.self_attn.o_proj.: .self_attn.to_out.
|
| 594 |
+
.self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
|
| 595 |
+
.self_attn.q_norm.: .self_attn.norm_q.
|
| 596 |
+
.self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
|
| 597 |
+
.self_attn.q_proj.: .self_attn.to_q.
|
| 598 |
+
.self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
|
| 599 |
+
.self_attn.v_proj.: .self_attn.to_v.
|
| 600 |
+
.self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
|
| 601 |
+
action_in_proj.: action_proj_in.
|
| 602 |
+
action_modality_embed: action_modality_embed
|
| 603 |
+
action_out_proj.: action_proj_out.
|
| 604 |
+
time_embedder.mlp.0.: time_embedder.linear_1.
|
| 605 |
+
time_embedder.mlp.2.: time_embedder.linear_2.
|
| 606 |
+
vision_in_proj.projector.: proj_in.
|
| 607 |
+
vision_out_proj.projector.: proj_out.
|
| 608 |
+
vlm_backbone.lm_head.weight: lm_head.weight
|
| 609 |
+
vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
|
| 610 |
+
vlm_backbone.model.language_model.layers.: layers.
|
| 611 |
+
vlm_backbone.model.language_model.norm.weight: norm.weight
|
| 612 |
+
vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
|
| 613 |
+
vlm_backbone.model.visual.blocks.: blocks.
|
| 614 |
+
vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
|
| 615 |
+
vlm_backbone.model.visual.merger.: merger.
|
| 616 |
+
vlm_backbone.model.visual.patch_embed.: patch_embed.
|
| 617 |
+
vlm_backbone.model.visual.pos_embed.: pos_embed.
|
| 618 |
+
num_embodiment_domains: 32
|
| 619 |
+
ori_action_dim: 14
|
| 620 |
+
packed_attention_backend: flash2
|
| 621 |
+
position_embedding_type: unified_3d_mrope
|
| 622 |
+
pretrained_name_or_path: ./checkpoints/Cosmos3-Nano/transformer
|
| 623 |
+
rectified_flow_inference_config:
|
| 624 |
+
num_steps: 30
|
| 625 |
+
num_train_timesteps: 1000
|
| 626 |
+
scheduler_type: unipc
|
| 627 |
+
shift: 10
|
| 628 |
+
use_dynamic_shifting: false
|
| 629 |
+
use_karras_sigmas: false
|
| 630 |
+
rectified_flow_training_config:
|
| 631 |
+
action_loss_weight: 10
|
| 632 |
+
high_sigma_ratio: 0.05
|
| 633 |
+
high_sigma_timesteps_max: 1000
|
| 634 |
+
high_sigma_timesteps_min: 995
|
| 635 |
+
independent_action_schedule: false
|
| 636 |
+
normalize_loss_by_active: false
|
| 637 |
+
shift:
|
| 638 |
+
'256': 3
|
| 639 |
+
'480': 5
|
| 640 |
+
'720': 10
|
| 641 |
+
shift_action: null
|
| 642 |
+
train_time_action_distribution: logitnormal
|
| 643 |
+
train_time_image_distribution: logitnormal
|
| 644 |
+
train_time_video_distribution: waver
|
| 645 |
+
train_time_weight: uniform
|
| 646 |
+
use_discrete_rf: false
|
| 647 |
+
use_dynamic_shift: false
|
| 648 |
+
use_high_sigma_strategy: false
|
| 649 |
+
use_high_sigma_strategy_action: false
|
| 650 |
+
vision_loss_weight: 10
|
| 651 |
+
reinitialize_action_policy: true
|
| 652 |
+
special_tokens:
|
| 653 |
+
end_of_generation: 151653
|
| 654 |
+
eos_token_id: 151645
|
| 655 |
+
start_of_generation: 151652
|
| 656 |
+
timestep_scale: 0.001
|
| 657 |
+
type: Cosmos3FlowMatching
|
| 658 |
+
unified_3d_mrope_reset_spatial_ids: true
|
| 659 |
+
unified_3d_mrope_temporal_modality_margin: 15000
|
| 660 |
+
vision_in_proj:
|
| 661 |
+
in_dim: 192
|
| 662 |
+
out_dim: 4096
|
| 663 |
+
type: LinearProjector
|
| 664 |
+
vision_latent_dim: 48
|
| 665 |
+
vision_out_proj:
|
| 666 |
+
in_dim: 4096
|
| 667 |
+
out_dim: 192
|
| 668 |
+
type: LinearProjector
|
| 669 |
+
vision_vae:
|
| 670 |
+
encode_exact_durations:
|
| 671 |
+
- 33
|
| 672 |
+
pretrained_name_or_path: null
|
| 673 |
+
type: Cosmos3Wan22VAE
|
| 674 |
+
vlm_backbone:
|
| 675 |
+
include_visual: false
|
| 676 |
+
skip_init_weights: true
|
| 677 |
+
type: Cosmos3MoTBackbone
|
| 678 |
+
vision_encoder_path: ./checkpoints/Cosmos3-Nano/vision_encoder
|
| 679 |
+
vlm_config:
|
| 680 |
+
image_token_id: 151655
|
| 681 |
+
model_type: qwen3_vl
|
| 682 |
+
text_config:
|
| 683 |
+
attention_bias: false
|
| 684 |
+
attention_dropout: 0
|
| 685 |
+
bos_token_id: 151643
|
| 686 |
+
eos_token_id: 151645
|
| 687 |
+
head_dim: 128
|
| 688 |
+
hidden_act: silu
|
| 689 |
+
hidden_size: 4096
|
| 690 |
+
intermediate_size: 12288
|
| 691 |
+
layer_types:
|
| 692 |
+
- full_attention
|
| 693 |
+
- full_attention
|
| 694 |
+
- full_attention
|
| 695 |
+
- full_attention
|
| 696 |
+
- full_attention
|
| 697 |
+
- full_attention
|
| 698 |
+
- full_attention
|
| 699 |
+
- full_attention
|
| 700 |
+
- full_attention
|
| 701 |
+
- full_attention
|
| 702 |
+
- full_attention
|
| 703 |
+
- full_attention
|
| 704 |
+
- full_attention
|
| 705 |
+
- full_attention
|
| 706 |
+
- full_attention
|
| 707 |
+
- full_attention
|
| 708 |
+
- full_attention
|
| 709 |
+
- full_attention
|
| 710 |
+
- full_attention
|
| 711 |
+
- full_attention
|
| 712 |
+
- full_attention
|
| 713 |
+
- full_attention
|
| 714 |
+
- full_attention
|
| 715 |
+
- full_attention
|
| 716 |
+
- full_attention
|
| 717 |
+
- full_attention
|
| 718 |
+
- full_attention
|
| 719 |
+
- full_attention
|
| 720 |
+
- full_attention
|
| 721 |
+
- full_attention
|
| 722 |
+
- full_attention
|
| 723 |
+
- full_attention
|
| 724 |
+
- full_attention
|
| 725 |
+
- full_attention
|
| 726 |
+
- full_attention
|
| 727 |
+
- full_attention
|
| 728 |
+
max_position_embeddings: 262144
|
| 729 |
+
model_type: qwen3_vl_text
|
| 730 |
+
num_attention_heads: 32
|
| 731 |
+
num_hidden_layers: 36
|
| 732 |
+
num_key_value_heads: 8
|
| 733 |
+
pad_token_id: 0
|
| 734 |
+
rms_norm_eps: 1e-06
|
| 735 |
+
rope_scaling:
|
| 736 |
+
mrope_interleaved: true
|
| 737 |
+
mrope_section:
|
| 738 |
+
- 24
|
| 739 |
+
- 20
|
| 740 |
+
- 20
|
| 741 |
+
rope_type: default
|
| 742 |
+
rope_theta: 5000000
|
| 743 |
+
tie_word_embeddings: false
|
| 744 |
+
vocab_size: 151936
|
| 745 |
+
tie_word_embeddings: false
|
| 746 |
+
video_token_id: 151656
|
| 747 |
+
vision_config:
|
| 748 |
+
deepstack_visual_indexes:
|
| 749 |
+
- 8
|
| 750 |
+
- 16
|
| 751 |
+
- 24
|
| 752 |
+
depth: 27
|
| 753 |
+
hidden_act: gelu_pytorch_tanh
|
| 754 |
+
hidden_size: 1152
|
| 755 |
+
in_channels: 3
|
| 756 |
+
initializer_range: 0.02
|
| 757 |
+
intermediate_size: 4304
|
| 758 |
+
model_type: qwen3_vl
|
| 759 |
+
num_heads: 16
|
| 760 |
+
num_position_embeddings: 2304
|
| 761 |
+
out_hidden_size: 4096
|
| 762 |
+
patch_size: 16
|
| 763 |
+
spatial_merge_size: 2
|
| 764 |
+
temporal_patch_size: 2
|
| 765 |
+
vision_end_token_id: 151653
|
| 766 |
+
vision_start_token_id: 151652
|
| 767 |
+
vocab_size: 151936
|
| 768 |
+
model:
|
| 769 |
+
action_horizon: 32
|
| 770 |
+
action_in_proj:
|
| 771 |
+
input_size: 64
|
| 772 |
+
num_domains: 32
|
| 773 |
+
output_size: 4096
|
| 774 |
+
type: DomainAwareLinear
|
| 775 |
+
action_out_proj:
|
| 776 |
+
input_size: 4096
|
| 777 |
+
num_domains: 32
|
| 778 |
+
output_size: 64
|
| 779 |
+
type: DomainAwareLinear
|
| 780 |
+
base_fps: 24
|
| 781 |
+
enable_fps_modulation: true
|
| 782 |
+
enable_vision_loss: true
|
| 783 |
+
freeze_non_moe_vlm_backbone: true
|
| 784 |
+
freeze_vlm_backbone: false
|
| 785 |
+
latent_patch_size: 2
|
| 786 |
+
max_action_dim: 64
|
| 787 |
+
name_mapping:
|
| 788 |
+
.self_attn.k_norm.: .self_attn.norm_k.
|
| 789 |
+
.self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
|
| 790 |
+
.self_attn.k_proj.: .self_attn.to_k.
|
| 791 |
+
.self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
|
| 792 |
+
.self_attn.o_proj.: .self_attn.to_out.
|
| 793 |
+
.self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
|
| 794 |
+
.self_attn.q_norm.: .self_attn.norm_q.
|
| 795 |
+
.self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
|
| 796 |
+
.self_attn.q_proj.: .self_attn.to_q.
|
| 797 |
+
.self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
|
| 798 |
+
.self_attn.v_proj.: .self_attn.to_v.
|
| 799 |
+
.self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
|
| 800 |
+
action_in_proj.: action_proj_in.
|
| 801 |
+
action_modality_embed: action_modality_embed
|
| 802 |
+
action_out_proj.: action_proj_out.
|
| 803 |
+
time_embedder.mlp.0.: time_embedder.linear_1.
|
| 804 |
+
time_embedder.mlp.2.: time_embedder.linear_2.
|
| 805 |
+
vision_in_proj.projector.: proj_in.
|
| 806 |
+
vision_out_proj.projector.: proj_out.
|
| 807 |
+
vlm_backbone.lm_head.weight: lm_head.weight
|
| 808 |
+
vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
|
| 809 |
+
vlm_backbone.model.language_model.layers.: layers.
|
| 810 |
+
vlm_backbone.model.language_model.norm.weight: norm.weight
|
| 811 |
+
vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
|
| 812 |
+
vlm_backbone.model.visual.blocks.: blocks.
|
| 813 |
+
vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
|
| 814 |
+
vlm_backbone.model.visual.merger.: merger.
|
| 815 |
+
vlm_backbone.model.visual.patch_embed.: patch_embed.
|
| 816 |
+
vlm_backbone.model.visual.pos_embed.: pos_embed.
|
| 817 |
+
num_embodiment_domains: 32
|
| 818 |
+
ori_action_dim: 14
|
| 819 |
+
packed_attention_backend: flash2
|
| 820 |
+
position_embedding_type: unified_3d_mrope
|
| 821 |
+
pretrained_name_or_path: ./checkpoints/Cosmos3-Nano/transformer
|
| 822 |
+
rectified_flow_inference_config:
|
| 823 |
+
num_steps: 30
|
| 824 |
+
num_train_timesteps: 1000
|
| 825 |
+
scheduler_type: unipc
|
| 826 |
+
shift: 10
|
| 827 |
+
use_dynamic_shifting: false
|
| 828 |
+
use_karras_sigmas: false
|
| 829 |
+
rectified_flow_training_config:
|
| 830 |
+
action_loss_weight: 10
|
| 831 |
+
high_sigma_ratio: 0.05
|
| 832 |
+
high_sigma_timesteps_max: 1000
|
| 833 |
+
high_sigma_timesteps_min: 995
|
| 834 |
+
independent_action_schedule: false
|
| 835 |
+
normalize_loss_by_active: false
|
| 836 |
+
shift:
|
| 837 |
+
'256': 3
|
| 838 |
+
'480': 5
|
| 839 |
+
'720': 10
|
| 840 |
+
shift_action: null
|
| 841 |
+
train_time_action_distribution: logitnormal
|
| 842 |
+
train_time_image_distribution: logitnormal
|
| 843 |
+
train_time_video_distribution: waver
|
| 844 |
+
train_time_weight: uniform
|
| 845 |
+
use_discrete_rf: false
|
| 846 |
+
use_dynamic_shift: false
|
| 847 |
+
use_high_sigma_strategy: false
|
| 848 |
+
use_high_sigma_strategy_action: false
|
| 849 |
+
vision_loss_weight: 10
|
| 850 |
+
reinitialize_action_policy: true
|
| 851 |
+
special_tokens:
|
| 852 |
+
end_of_generation: 151653
|
| 853 |
+
eos_token_id: 151645
|
| 854 |
+
start_of_generation: 151652
|
| 855 |
+
timestep_scale: 0.001
|
| 856 |
+
type: Cosmos3FlowMatching
|
| 857 |
+
unified_3d_mrope_reset_spatial_ids: true
|
| 858 |
+
unified_3d_mrope_temporal_modality_margin: 15000
|
| 859 |
+
vision_in_proj:
|
| 860 |
+
in_dim: 192
|
| 861 |
+
out_dim: 4096
|
| 862 |
+
type: LinearProjector
|
| 863 |
+
vision_latent_dim: 48
|
| 864 |
+
vision_out_proj:
|
| 865 |
+
in_dim: 4096
|
| 866 |
+
out_dim: 192
|
| 867 |
+
type: LinearProjector
|
| 868 |
+
vision_vae:
|
| 869 |
+
encode_chunk_frames:
|
| 870 |
+
'256': 16
|
| 871 |
+
'480': 24
|
| 872 |
+
'720': 12
|
| 873 |
+
encode_exact_durations:
|
| 874 |
+
- 33
|
| 875 |
+
pretrained_name_or_path: ./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth
|
| 876 |
+
type: Cosmos3Wan22VAE
|
| 877 |
+
vlm_backbone:
|
| 878 |
+
include_visual: false
|
| 879 |
+
skip_init_weights: true
|
| 880 |
+
type: Cosmos3MoTBackbone
|
| 881 |
+
vision_encoder_path: ./checkpoints/Cosmos3-Nano/vision_encoder
|
| 882 |
+
vlm_config:
|
| 883 |
+
image_token_id: 151655
|
| 884 |
+
model_type: qwen3_vl
|
| 885 |
+
text_config:
|
| 886 |
+
attention_bias: false
|
| 887 |
+
attention_dropout: 0
|
| 888 |
+
bos_token_id: 151643
|
| 889 |
+
eos_token_id: 151645
|
| 890 |
+
head_dim: 128
|
| 891 |
+
hidden_act: silu
|
| 892 |
+
hidden_size: 4096
|
| 893 |
+
intermediate_size: 12288
|
| 894 |
+
layer_types:
|
| 895 |
+
- full_attention
|
| 896 |
+
- full_attention
|
| 897 |
+
- full_attention
|
| 898 |
+
- full_attention
|
| 899 |
+
- full_attention
|
| 900 |
+
- full_attention
|
| 901 |
+
- full_attention
|
| 902 |
+
- full_attention
|
| 903 |
+
- full_attention
|
| 904 |
+
- full_attention
|
| 905 |
+
- full_attention
|
| 906 |
+
- full_attention
|
| 907 |
+
- full_attention
|
| 908 |
+
- full_attention
|
| 909 |
+
- full_attention
|
| 910 |
+
- full_attention
|
| 911 |
+
- full_attention
|
| 912 |
+
- full_attention
|
| 913 |
+
- full_attention
|
| 914 |
+
- full_attention
|
| 915 |
+
- full_attention
|
| 916 |
+
- full_attention
|
| 917 |
+
- full_attention
|
| 918 |
+
- full_attention
|
| 919 |
+
- full_attention
|
| 920 |
+
- full_attention
|
| 921 |
+
- full_attention
|
| 922 |
+
- full_attention
|
| 923 |
+
- full_attention
|
| 924 |
+
- full_attention
|
| 925 |
+
- full_attention
|
| 926 |
+
- full_attention
|
| 927 |
+
- full_attention
|
| 928 |
+
- full_attention
|
| 929 |
+
- full_attention
|
| 930 |
+
- full_attention
|
| 931 |
+
max_position_embeddings: 262144
|
| 932 |
+
model_type: qwen3_vl_text
|
| 933 |
+
num_attention_heads: 32
|
| 934 |
+
num_hidden_layers: 36
|
| 935 |
+
num_key_value_heads: 8
|
| 936 |
+
pad_token_id: 0
|
| 937 |
+
rms_norm_eps: 1e-06
|
| 938 |
+
rope_scaling:
|
| 939 |
+
mrope_interleaved: true
|
| 940 |
+
mrope_section:
|
| 941 |
+
- 24
|
| 942 |
+
- 20
|
| 943 |
+
- 20
|
| 944 |
+
rope_type: default
|
| 945 |
+
rope_theta: 5000000
|
| 946 |
+
tie_word_embeddings: false
|
| 947 |
+
vocab_size: 151936
|
| 948 |
+
tie_word_embeddings: false
|
| 949 |
+
video_token_id: 151656
|
| 950 |
+
vision_config:
|
| 951 |
+
deepstack_visual_indexes:
|
| 952 |
+
- 8
|
| 953 |
+
- 16
|
| 954 |
+
- 24
|
| 955 |
+
depth: 27
|
| 956 |
+
hidden_act: gelu_pytorch_tanh
|
| 957 |
+
hidden_size: 1152
|
| 958 |
+
in_channels: 3
|
| 959 |
+
initializer_range: 0.02
|
| 960 |
+
intermediate_size: 4304
|
| 961 |
+
model_type: qwen3_vl
|
| 962 |
+
num_heads: 16
|
| 963 |
+
num_position_embeddings: 2304
|
| 964 |
+
out_hidden_size: 4096
|
| 965 |
+
patch_size: 16
|
| 966 |
+
spatial_merge_size: 2
|
| 967 |
+
temporal_patch_size: 2
|
| 968 |
+
vision_end_token_id: 151653
|
| 969 |
+
vision_start_token_id: 151652
|
| 970 |
+
vocab_size: 151936
|
| 971 |
+
runner:
|
| 972 |
+
args: Namespace(config='configs/cosmos3/cosmos3nano_robodojo_full_finetune.py',
|
| 973 |
+
work_dir='/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano', cfg_options=None,
|
| 974 |
+
eval_after_train=False, resume_from=None)
|
| 975 |
+
cfg: 'Config (path: configs/cosmos3/cosmos3nano_robodojo_full_finetune.py): {''_ckpt_root'':
|
| 976 |
+
''./checkpoints'', ''_cosmos3_nano_ckpt'': ''./checkpoints/Cosmos3-Nano'', ''_cosmos3_nano_transformer'':
|
| 977 |
+
''./checkpoints/Cosmos3-Nano/transformer'', ''_cosmos3_nano_vision_encoder'':
|
| 978 |
+
''./checkpoints/Cosmos3-Nano/vision_encoder'', ''_cosmos3_nano_tokenizer'': {''type'':
|
| 979 |
+
''PretrainedTokenizer'', ''model_path'': ''./checkpoints/Cosmos3-Nano/text_tokenizer'',
|
| 980 |
+
''model_max_length'': 4096, ''padding_side'': ''right'', ''trust_remote_code'':
|
| 981 |
+
True}, ''_wan22_vae_path'': ''./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth'', ''_vision_vae'':
|
| 982 |
+
{''type'': ''Cosmos3Wan22VAE'', ''pretrained_name_or_path'': ''./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth'',
|
| 983 |
+
''encode_exact_durations'': [17]}, ''_action_dim'': 10, ''_max_action_dim'': 64,
|
| 984 |
+
''_max_state_dim'': 64, ''_action_horizon'': 16, ''_frame_window_size'': 17, ''_prepend_state_to_action'':
|
| 985 |
+
False, ''_image_height'': 256, ''_image_width'': 256, ''_video_height'': 192,
|
| 986 |
+
''_video_width'': 320, ''_conditioning_fps'': 20.0, ''_libero_action_stats'':
|
| 987 |
+
{''mean'': [0.050704, 0.097407, -0.094833, 0.994873, -0.004579, -0.004288, 0.004389,
|
| 988 |
+
0.996104, 0.001109, 0.476725], ''std'': [0.333621, 0.387175, 0.45714, 0.010807,
|
| 989 |
+
0.077802, 0.063386, 0.078571, 0.009994, 0.038504, 0.49946], ''min'': [-0.9375,
|
| 990 |
+
-0.9375, -0.9375, 0.902028, -0.356085, -0.367416, -0.370434, 0.921907, -0.255,
|
| 991 |
+
0.0], ''max'': [0.9375, 0.9375, 0.9375, 1.0, 0.368853, 0.341214, 0.356395, 1.0,
|
| 992 |
+
0.348251, 1.0], ''q01'': [-0.723214, -0.808929, -0.9375, 0.934955, -0.223431,
|
| 993 |
+
-0.189878, -0.334735, 0.938516, -0.107736, 0.0], ''q99'': [0.9375, 0.870536, 0.9375,
|
| 994 |
+
1.0, 0.331, 0.163153, 0.226216, 1.0, 0.127158, 1.0]}, ''_cfg_dropout_rate'': 0.1,
|
| 995 |
+
''_base_lr'': 5e-05, ''_action_lr'': 0.00025, ''_per_device_batch_size'': 16,
|
| 996 |
+
''_grad_accumulation_steps'': 8, ''_max_steps'': 2000, ''_save_iter_interval'':
|
| 997 |
+
500, ''_cosmos3_nano_special_tokens'': {''eos_token_id'': 151645, ''start_of_generation'':
|
| 998 |
+
151652, ''end_of_generation'': 151653}, ''_cosmos3_nano_vlm_config'': {''model_type'':
|
| 999 |
+
''qwen3_vl'', ''vocab_size'': 151936, ''tie_word_embeddings'': False, ''image_token_id'':
|
| 1000 |
+
151655, ''video_token_id'': 151656, ''vision_start_token_id'': 151652, ''vision_end_token_id'':
|
| 1001 |
+
151653, ''text_config'': {''model_type'': ''qwen3_vl_text'', ''vocab_size'': 151936,
|
| 1002 |
+
''hidden_size'': 4096, ''intermediate_size'': 12288, ''num_hidden_layers'': 36,
|
| 1003 |
+
''num_attention_heads'': 32, ''num_key_value_heads'': 8, ''head_dim'': 128, ''hidden_act'':
|
| 1004 |
+
''silu'', ''max_position_embeddings'': 262144, ''rms_norm_eps'': 1e-06, ''rope_theta'':
|
| 1005 |
+
5000000, ''attention_bias'': False, ''attention_dropout'': 0.0, ''bos_token_id'':
|
| 1006 |
+
151643, ''eos_token_id'': 151645, ''pad_token_id'': 0, ''tie_word_embeddings'':
|
| 1007 |
+
False, ''rope_scaling'': {''rope_type'': ''default'', ''mrope_interleaved'': True,
|
| 1008 |
+
''mrope_section'': [24, 20, 20]}, ''layer_types'': [''full_attention'', ''full_attention'',
|
| 1009 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1010 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1011 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1012 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1013 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1014 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1015 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1016 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1017 |
+
''full_attention'', ''full_attention'']}, ''vision_config'': {''model_type'':
|
| 1018 |
+
''qwen3_vl'', ''hidden_size'': 1152, ''hidden_act'': ''gelu_pytorch_tanh'', ''intermediate_size'':
|
| 1019 |
+
4304, ''depth'': 27, ''num_heads'': 16, ''in_channels'': 3, ''initializer_range'':
|
| 1020 |
+
0.02, ''out_hidden_size'': 4096, ''patch_size'': 16, ''spatial_merge_size'': 2,
|
| 1021 |
+
''temporal_patch_size'': 2, ''num_position_embeddings'': 2304, ''deepstack_visual_indexes'':
|
| 1022 |
+
[8, 16, 24]}}, ''_cosmos3_nano_name_mapping'': {''action_modality_embed'': ''action_modality_embed'',
|
| 1023 |
+
''vlm_backbone.model.language_model.embed_tokens.weight'': ''embed_tokens.weight'',
|
| 1024 |
+
''vlm_backbone.lm_head.weight'': ''lm_head.weight'', ''vlm_backbone.model.language_model.norm.weight'':
|
| 1025 |
+
''norm.weight'', ''vlm_backbone.model.language_model.norm_moe_gen.weight'': ''norm_moe_gen.weight'',
|
| 1026 |
+
''vlm_backbone.model.language_model.layers.'': ''layers.'', ''vision_in_proj.projector.'':
|
| 1027 |
+
''proj_in.'', ''vision_out_proj.projector.'': ''proj_out.'', ''time_embedder.mlp.0.'':
|
| 1028 |
+
''time_embedder.linear_1.'', ''time_embedder.mlp.2.'': ''time_embedder.linear_2.'',
|
| 1029 |
+
''action_in_proj.'': ''action_proj_in.'', ''action_out_proj.'': ''action_proj_out.'',
|
| 1030 |
+
''.self_attn.q_proj.'': ''.self_attn.to_q.'', ''.self_attn.k_proj.'': ''.self_attn.to_k.'',
|
| 1031 |
+
''.self_attn.v_proj.'': ''.self_attn.to_v.'', ''.self_attn.o_proj.'': ''.self_attn.to_out.'',
|
| 1032 |
+
''.self_attn.q_proj_moe_gen.'': ''.self_attn.add_q_proj.'', ''.self_attn.k_proj_moe_gen.'':
|
| 1033 |
+
''.self_attn.add_k_proj.'', ''.self_attn.v_proj_moe_gen.'': ''.self_attn.add_v_proj.'',
|
| 1034 |
+
''.self_attn.o_proj_moe_gen.'': ''.self_attn.to_add_out.'', ''.self_attn.q_norm.'':
|
| 1035 |
+
''.self_attn.norm_q.'', ''.self_attn.k_norm.'': ''.self_attn.norm_k.'', ''.self_attn.q_norm_moe_gen.'':
|
| 1036 |
+
''.self_attn.norm_added_q.'', ''.self_attn.k_norm_moe_gen.'': ''.self_attn.norm_added_k.'',
|
| 1037 |
+
''vlm_backbone.model.visual.patch_embed.'': ''patch_embed.'', ''vlm_backbone.model.visual.blocks.'':
|
| 1038 |
+
''blocks.'', ''vlm_backbone.model.visual.pos_embed.'': ''pos_embed.'', ''vlm_backbone.model.visual.merger.'':
|
| 1039 |
+
''merger.'', ''vlm_backbone.model.visual.deepstack_merger_list.'': ''deepstack_merger_list.''},
|
| 1040 |
+
''model'': {''type'': ''Cosmos3FlowMatching'', ''vlm_backbone'': {''type'': ''Cosmos3MoTBackbone'',
|
| 1041 |
+
''vlm_config'': {''model_type'': ''qwen3_vl'', ''vocab_size'': 151936, ''tie_word_embeddings'':
|
| 1042 |
+
False, ''image_token_id'': 151655, ''video_token_id'': 151656, ''vision_start_token_id'':
|
| 1043 |
+
151652, ''vision_end_token_id'': 151653, ''text_config'': {''model_type'': ''qwen3_vl_text'',
|
| 1044 |
+
''vocab_size'': 151936, ''hidden_size'': 4096, ''intermediate_size'': 12288, ''num_hidden_layers'':
|
| 1045 |
+
36, ''num_attention_heads'': 32, ''num_key_value_heads'': 8, ''head_dim'': 128,
|
| 1046 |
+
''hidden_act'': ''silu'', ''max_position_embeddings'': 262144, ''rms_norm_eps'':
|
| 1047 |
+
1e-06, ''rope_theta'': 5000000, ''attention_bias'': False, ''attention_dropout'':
|
| 1048 |
+
0.0, ''bos_token_id'': 151643, ''eos_token_id'': 151645, ''pad_token_id'': 0,
|
| 1049 |
+
''tie_word_embeddings'': False, ''rope_scaling'': {''rope_type'': ''default'',
|
| 1050 |
+
''mrope_interleaved'': True, ''mrope_section'': [24, 20, 20]}, ''layer_types'':
|
| 1051 |
+
[''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1052 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1053 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1054 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1055 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1056 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1057 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1058 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1059 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'']},
|
| 1060 |
+
''vision_config'': {''model_type'': ''qwen3_vl'', ''hidden_size'': 1152, ''hidden_act'':
|
| 1061 |
+
''gelu_pytorch_tanh'', ''intermediate_size'': 4304, ''depth'': 27, ''num_heads'':
|
| 1062 |
+
16, ''in_channels'': 3, ''initializer_range'': 0.02, ''out_hidden_size'': 4096,
|
| 1063 |
+
''patch_size'': 16, ''spatial_merge_size'': 2, ''temporal_patch_size'': 2, ''num_position_embeddings'':
|
| 1064 |
+
2304, ''deepstack_visual_indexes'': [8, 16, 24]}}, ''include_visual'': False,
|
| 1065 |
+
''vision_encoder_path'': ''./checkpoints/Cosmos3-Nano/vision_encoder'', ''skip_init_weights'':
|
| 1066 |
+
True}, ''vision_latent_dim'': 48, ''latent_patch_size'': 2, ''max_action_dim'':
|
| 1067 |
+
64, ''num_embodiment_domains'': 32, ''vision_in_proj'': {''type'': ''LinearProjector'',
|
| 1068 |
+
''in_dim'': 192, ''out_dim'': 4096}, ''vision_out_proj'': {''type'': ''LinearProjector'',
|
| 1069 |
+
''in_dim'': 4096, ''out_dim'': 192}, ''action_in_proj'': {''type'': ''DomainAwareLinear'',
|
| 1070 |
+
''input_size'': 64, ''output_size'': 4096, ''num_domains'': 32}, ''action_out_proj'':
|
| 1071 |
+
{''type'': ''DomainAwareLinear'', ''input_size'': 4096, ''output_size'': 64, ''num_domains'':
|
| 1072 |
+
32}, ''rectified_flow_training_config'': {''shift'': {''256'': 3, ''480'': 5,
|
| 1073 |
+
''720'': 10}, ''use_dynamic_shift'': False, ''train_time_image_distribution'':
|
| 1074 |
+
''logitnormal'', ''train_time_video_distribution'': ''waver'', ''train_time_action_distribution'':
|
| 1075 |
+
''logitnormal'', ''train_time_weight'': ''uniform'', ''vision_loss_weight'': 10.0,
|
| 1076 |
+
''independent_action_schedule'': False, ''shift_action'': None, ''use_high_sigma_strategy'':
|
| 1077 |
+
False, ''high_sigma_ratio'': 0.05, ''high_sigma_timesteps_min'': 995, ''high_sigma_timesteps_max'':
|
| 1078 |
+
1000, ''use_high_sigma_strategy_action'': False, ''use_discrete_rf'': False, ''normalize_loss_by_active'':
|
| 1079 |
+
False, ''action_loss_weight'': 10.0}, ''rectified_flow_inference_config'': {''num_train_timesteps'':
|
| 1080 |
+
1000, ''scheduler_type'': ''unipc'', ''num_steps'': 30, ''shift'': 10.0, ''use_dynamic_shifting'':
|
| 1081 |
+
False, ''use_karras_sigmas'': False}, ''timestep_scale'': 0.001, ''packed_attention_backend'':
|
| 1082 |
+
''flash2'', ''position_embedding_type'': ''unified_3d_mrope'', ''unified_3d_mrope_reset_spatial_ids'':
|
| 1083 |
+
True, ''unified_3d_mrope_temporal_modality_margin'': 15000, ''enable_fps_modulation'':
|
| 1084 |
+
True, ''base_fps'': 24.0, ''special_tokens'': {''eos_token_id'': 151645, ''start_of_generation'':
|
| 1085 |
+
151652, ''end_of_generation'': 151653}, ''pretrained_name_or_path'': ''./checkpoints/Cosmos3-Nano/transformer'',
|
| 1086 |
+
''name_mapping'': {''action_modality_embed'': ''action_modality_embed'', ''vlm_backbone.model.language_model.embed_tokens.weight'':
|
| 1087 |
+
''embed_tokens.weight'', ''vlm_backbone.lm_head.weight'': ''lm_head.weight'',
|
| 1088 |
+
''vlm_backbone.model.language_model.norm.weight'': ''norm.weight'', ''vlm_backbone.model.language_model.norm_moe_gen.weight'':
|
| 1089 |
+
''norm_moe_gen.weight'', ''vlm_backbone.model.language_model.layers.'': ''layers.'',
|
| 1090 |
+
''vision_in_proj.projector.'': ''proj_in.'', ''vision_out_proj.projector.'': ''proj_out.'',
|
| 1091 |
+
''time_embedder.mlp.0.'': ''time_embedder.linear_1.'', ''time_embedder.mlp.2.'':
|
| 1092 |
+
''time_embedder.linear_2.'', ''action_in_proj.'': ''action_proj_in.'', ''action_out_proj.'':
|
| 1093 |
+
''action_proj_out.'', ''.self_attn.q_proj.'': ''.self_attn.to_q.'', ''.self_attn.k_proj.'':
|
| 1094 |
+
''.self_attn.to_k.'', ''.self_attn.v_proj.'': ''.self_attn.to_v.'', ''.self_attn.o_proj.'':
|
| 1095 |
+
''.self_attn.to_out.'', ''.self_attn.q_proj_moe_gen.'': ''.self_attn.add_q_proj.'',
|
| 1096 |
+
''.self_attn.k_proj_moe_gen.'': ''.self_attn.add_k_proj.'', ''.self_attn.v_proj_moe_gen.'':
|
| 1097 |
+
''.self_attn.add_v_proj.'', ''.self_attn.o_proj_moe_gen.'': ''.self_attn.to_add_out.'',
|
| 1098 |
+
''.self_attn.q_norm.'': ''.self_attn.norm_q.'', ''.self_attn.k_norm.'': ''.self_attn.norm_k.'',
|
| 1099 |
+
''.self_attn.q_norm_moe_gen.'': ''.self_attn.norm_added_q.'', ''.self_attn.k_norm_moe_gen.'':
|
| 1100 |
+
''.self_attn.norm_added_k.'', ''vlm_backbone.model.visual.patch_embed.'': ''patch_embed.'',
|
| 1101 |
+
''vlm_backbone.model.visual.blocks.'': ''blocks.'', ''vlm_backbone.model.visual.pos_embed.'':
|
| 1102 |
+
''pos_embed.'', ''vlm_backbone.model.visual.merger.'': ''merger.'', ''vlm_backbone.model.visual.deepstack_merger_list.'':
|
| 1103 |
+
''deepstack_merger_list.''}, ''vision_vae'': {''type'': ''Cosmos3Wan22VAE'', ''pretrained_name_or_path'':
|
| 1104 |
+
''./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth'', ''encode_exact_durations'': [33],
|
| 1105 |
+
''encode_chunk_frames'': {''256'': 16, ''480'': 24, ''720'': 12}}, ''ori_action_dim'':
|
| 1106 |
+
14, ''action_horizon'': 32, ''freeze_vlm_backbone'': False, ''freeze_non_moe_vlm_backbone'':
|
| 1107 |
+
True, ''enable_vision_loss'': True, ''reinitialize_action_policy'': True}, ''inference_model'':
|
| 1108 |
+
{''type'': ''Cosmos3FlowMatching'', ''vlm_backbone'': {''type'': ''Cosmos3MoTBackbone'',
|
| 1109 |
+
''vlm_config'': {''model_type'': ''qwen3_vl'', ''vocab_size'': 151936, ''tie_word_embeddings'':
|
| 1110 |
+
False, ''image_token_id'': 151655, ''video_token_id'': 151656, ''vision_start_token_id'':
|
| 1111 |
+
151652, ''vision_end_token_id'': 151653, ''text_config'': {''model_type'': ''qwen3_vl_text'',
|
| 1112 |
+
''vocab_size'': 151936, ''hidden_size'': 4096, ''intermediate_size'': 12288, ''num_hidden_layers'':
|
| 1113 |
+
36, ''num_attention_heads'': 32, ''num_key_value_heads'': 8, ''head_dim'': 128,
|
| 1114 |
+
''hidden_act'': ''silu'', ''max_position_embeddings'': 262144, ''rms_norm_eps'':
|
| 1115 |
+
1e-06, ''rope_theta'': 5000000, ''attention_bias'': False, ''attention_dropout'':
|
| 1116 |
+
0.0, ''bos_token_id'': 151643, ''eos_token_id'': 151645, ''pad_token_id'': 0,
|
| 1117 |
+
''tie_word_embeddings'': False, ''rope_scaling'': {''rope_type'': ''default'',
|
| 1118 |
+
''mrope_interleaved'': True, ''mrope_section'': [24, 20, 20]}, ''layer_types'':
|
| 1119 |
+
[''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1120 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1121 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1122 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1123 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1124 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1125 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1126 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'',
|
| 1127 |
+
''full_attention'', ''full_attention'', ''full_attention'', ''full_attention'']},
|
| 1128 |
+
''vision_config'': {''model_type'': ''qwen3_vl'', ''hidden_size'': 1152, ''hidden_act'':
|
| 1129 |
+
''gelu_pytorch_tanh'', ''intermediate_size'': 4304, ''depth'': 27, ''num_heads'':
|
| 1130 |
+
16, ''in_channels'': 3, ''initializer_range'': 0.02, ''out_hidden_size'': 4096,
|
| 1131 |
+
''patch_size'': 16, ''spatial_merge_size'': 2, ''temporal_patch_size'': 2, ''num_position_embeddings'':
|
| 1132 |
+
2304, ''deepstack_visual_indexes'': [8, 16, 24]}}, ''include_visual'': False,
|
| 1133 |
+
''vision_encoder_path'': ''./checkpoints/Cosmos3-Nano/vision_encoder'', ''skip_init_weights'':
|
| 1134 |
+
True}, ''vision_latent_dim'': 48, ''latent_patch_size'': 2, ''max_action_dim'':
|
| 1135 |
+
64, ''num_embodiment_domains'': 32, ''vision_in_proj'': {''type'': ''LinearProjector'',
|
| 1136 |
+
''in_dim'': 192, ''out_dim'': 4096}, ''vision_out_proj'': {''type'': ''LinearProjector'',
|
| 1137 |
+
''in_dim'': 4096, ''out_dim'': 192}, ''action_in_proj'': {''type'': ''DomainAwareLinear'',
|
| 1138 |
+
''input_size'': 64, ''output_size'': 4096, ''num_domains'': 32}, ''action_out_proj'':
|
| 1139 |
+
{''type'': ''DomainAwareLinear'', ''input_size'': 4096, ''output_size'': 64, ''num_domains'':
|
| 1140 |
+
32}, ''rectified_flow_training_config'': {''shift'': {''256'': 3, ''480'': 5,
|
| 1141 |
+
''720'': 10}, ''use_dynamic_shift'': False, ''train_time_image_distribution'':
|
| 1142 |
+
''logitnormal'', ''train_time_video_distribution'': ''waver'', ''train_time_action_distribution'':
|
| 1143 |
+
''logitnormal'', ''train_time_weight'': ''uniform'', ''vision_loss_weight'': 10.0,
|
| 1144 |
+
''independent_action_schedule'': False, ''shift_action'': None, ''use_high_sigma_strategy'':
|
| 1145 |
+
False, ''high_sigma_ratio'': 0.05, ''high_sigma_timesteps_min'': 995, ''high_sigma_timesteps_max'':
|
| 1146 |
+
1000, ''use_high_sigma_strategy_action'': False, ''use_discrete_rf'': False, ''normalize_loss_by_active'':
|
| 1147 |
+
False, ''action_loss_weight'': 10.0}, ''rectified_flow_inference_config'': {''num_train_timesteps'':
|
| 1148 |
+
1000, ''scheduler_type'': ''unipc'', ''num_steps'': 30, ''shift'': 10.0, ''use_dynamic_shifting'':
|
| 1149 |
+
False, ''use_karras_sigmas'': False}, ''timestep_scale'': 0.001, ''packed_attention_backend'':
|
| 1150 |
+
''flash2'', ''position_embedding_type'': ''unified_3d_mrope'', ''unified_3d_mrope_reset_spatial_ids'':
|
| 1151 |
+
True, ''unified_3d_mrope_temporal_modality_margin'': 15000, ''enable_fps_modulation'':
|
| 1152 |
+
True, ''base_fps'': 24.0, ''special_tokens'': {''eos_token_id'': 151645, ''start_of_generation'':
|
| 1153 |
+
151652, ''end_of_generation'': 151653}, ''pretrained_name_or_path'': ''./checkpoints/Cosmos3-Nano/transformer'',
|
| 1154 |
+
''name_mapping'': {''action_modality_embed'': ''action_modality_embed'', ''vlm_backbone.model.language_model.embed_tokens.weight'':
|
| 1155 |
+
''embed_tokens.weight'', ''vlm_backbone.lm_head.weight'': ''lm_head.weight'',
|
| 1156 |
+
''vlm_backbone.model.language_model.norm.weight'': ''norm.weight'', ''vlm_backbone.model.language_model.norm_moe_gen.weight'':
|
| 1157 |
+
''norm_moe_gen.weight'', ''vlm_backbone.model.language_model.layers.'': ''layers.'',
|
| 1158 |
+
''vision_in_proj.projector.'': ''proj_in.'', ''vision_out_proj.projector.'': ''proj_out.'',
|
| 1159 |
+
''time_embedder.mlp.0.'': ''time_embedder.linear_1.'', ''time_embedder.mlp.2.'':
|
| 1160 |
+
''time_embedder.linear_2.'', ''action_in_proj.'': ''action_proj_in.'', ''action_out_proj.'':
|
| 1161 |
+
''action_proj_out.'', ''.self_attn.q_proj.'': ''.self_attn.to_q.'', ''.self_attn.k_proj.'':
|
| 1162 |
+
''.self_attn.to_k.'', ''.self_attn.v_proj.'': ''.self_attn.to_v.'', ''.self_attn.o_proj.'':
|
| 1163 |
+
''.self_attn.to_out.'', ''.self_attn.q_proj_moe_gen.'': ''.self_attn.add_q_proj.'',
|
| 1164 |
+
''.self_attn.k_proj_moe_gen.'': ''.self_attn.add_k_proj.'', ''.self_attn.v_proj_moe_gen.'':
|
| 1165 |
+
''.self_attn.add_v_proj.'', ''.self_attn.o_proj_moe_gen.'': ''.self_attn.to_add_out.'',
|
| 1166 |
+
''.self_attn.q_norm.'': ''.self_attn.norm_q.'', ''.self_attn.k_norm.'': ''.self_attn.norm_k.'',
|
| 1167 |
+
''.self_attn.q_norm_moe_gen.'': ''.self_attn.norm_added_q.'', ''.self_attn.k_norm_moe_gen.'':
|
| 1168 |
+
''.self_attn.norm_added_k.'', ''vlm_backbone.model.visual.patch_embed.'': ''patch_embed.'',
|
| 1169 |
+
''vlm_backbone.model.visual.blocks.'': ''blocks.'', ''vlm_backbone.model.visual.pos_embed.'':
|
| 1170 |
+
''pos_embed.'', ''vlm_backbone.model.visual.merger.'': ''merger.'', ''vlm_backbone.model.visual.deepstack_merger_list.'':
|
| 1171 |
+
''deepstack_merger_list.''}, ''vision_vae'': {''type'': ''Cosmos3Wan22VAE'', ''pretrained_name_or_path'':
|
| 1172 |
+
None, ''encode_exact_durations'': [33]}, ''ori_action_dim'': 14, ''action_horizon'':
|
| 1173 |
+
32, ''freeze_vlm_backbone'': False, ''freeze_non_moe_vlm_backbone'': True, ''enable_vision_loss'':
|
| 1174 |
+
True, ''reinitialize_action_policy'': True}, ''_transforms'': [{''type'': ''ProcessParquetInputs'',
|
| 1175 |
+
''parquet_keys'': [''observation.state'', ''timestamp'', ''actions'', ''info'',
|
| 1176 |
+
''stats'', ''action_masks''], ''video_keys'': [''observation.images.image'', ''observation.images.wrist_image''],
|
| 1177 |
+
''name_mappings'': {''observation.state'': [''states''], ''actions'': [''actions'']},
|
| 1178 |
+
''embodiment_id'': 5}, {''type'': ''LiberoFramewiseActionToRot6D''}, {''type'':
|
| 1179 |
+
''ProcessCosmos3Prompt'', ''tokenizer'': {''type'': ''PretrainedTokenizer'', ''model_path'':
|
| 1180 |
+
''./checkpoints/Cosmos3-Nano/text_tokenizer'', ''model_max_length'': 4096, ''padding_side'':
|
| 1181 |
+
''right'', ''trust_remote_code'': True}, ''max_len'': 512, ''cfg_dropout_rate'':
|
| 1182 |
+
0.1, ''format_prompt_as_json'': True, ''action_metadata'': {''append_viewpoint'':
|
| 1183 |
+
False, ''frame_window_size'': 17, ''conditioning_fps'': 20.0, ''video_height'':
|
| 1184 |
+
192, ''video_width'': 320}}, {''type'': ''ResizeImages'', ''height'': 256, ''width'':
|
| 1185 |
+
256}, {''type'': ''SimpleNormalizeImages''}, {''type'': ''NormalizeStatesAndActions'',
|
| 1186 |
+
''action_dim'': 64, ''state_dim'': 64, ''state_key'': ''proprio'', ''action_key'':
|
| 1187 |
+
''action'', ''state_norm_type'': ''none'', ''action_norm_type'': ''quantile''},
|
| 1188 |
+
{''type'': ''BuildCosmos3Sequence'', ''raw_action_dim'': 10, ''mode'': ''wam'',
|
| 1189 |
+
''frame_window_size'': 17, ''prepend_state_to_action'': False, ''conditioning_fps'':
|
| 1190 |
+
20.0}, {''type'': ''PrepareVideo'', ''num_views'': 2, ''frame_window_size'': 17,
|
| 1191 |
+
''tile_direction'': ''horizontal''}, {''type'': ''ResizeAndReflectPad'', ''height'':
|
| 1192 |
+
192, ''width'': 320}], ''train_dataloader'': {''per_device_batch_size'': 8, ''per_device_num_workers'':
|
| 1193 |
+
4, ''prefetch_factor'': 1, ''dataset'': {''type'': ''DistributedRepeatingDataset'',
|
| 1194 |
+
''seed'': 42, ''reshuffle_each_epoch'': True, ''name_mappings'': {''observation.state'':
|
| 1195 |
+
[''proprio''], ''action'': [''action'']}, ''statistic_keys'': [''observation.state'',
|
| 1196 |
+
''action'', ''timestamp''], ''statistic_name'': ''robodojo_arx_x5'', ''statistics_overrides'':
|
| 1197 |
+
{''robodojo_arx_x5'': {''action'': {''q01'': [-1.051365569829941, -3.5348887174584814e-14,
|
| 1198 |
+
1.741881830823392e-16, -1.5984010362625123, -0.6003574305772781, -1.6678147149085998,
|
| 1199 |
+
0.0, -0.4509398394823074, -2.5859282299029243e-14, 1.234041714549172e-16, -1.64055180311203,
|
| 1200 |
+
-1.2633746123313903, -1.7645285475254058, 0.0], ''q99'': [0.5431358617544174,
|
| 1201 |
+
2.495765209197998, 2.492974226474762, 1.3241519677639007, 1.2496635341644287,
|
| 1202 |
+
1.7392305016517635, 1.0, 1.0814965963363647, 2.4167031812667843, 2.3470158338546754,
|
| 1203 |
+
1.141731116771698, 0.5208872479200363, 1.489715996980667, 1.0]}}}, ''datasets'':
|
| 1204 |
+
{''type'': ''ParquetDataset'', ''data_root_path'': [''./datasets/RoboDojo_lerobot_v21_video''],
|
| 1205 |
+
''transforms'': [{''type'': ''ProcessParquetInputs'', ''embodiment_id'': 31, ''parquet_keys'':
|
| 1206 |
+
[''observation.state'', ''timestamp'', ''actions'', ''info'', ''stats'', ''action_masks''],
|
| 1207 |
+
''video_keys'': [''observation.images.cam_high'', ''observation.images.cam_left_wrist'',
|
| 1208 |
+
''observation.images.cam_right_wrist''], ''name_mappings'': {''observation.state'':
|
| 1209 |
+
[''states''], ''actions'': [''actions'']}}, {''type'': ''ResizeImages'', ''height'':
|
| 1210 |
+
192, ''width'': 256}, {''type'': ''AugVideo'', ''rotation_range'': 0.0, ''brightness_range'':
|
| 1211 |
+
(0.7, 1.3), ''contrast_range'': (0.6, 1.4), ''crop_scale'': (0.95, 0.95), ''crop_ratio'':
|
| 1212 |
+
(1.0, 1.0), ''prob'': 1.0, ''saturation_range'': (0.5, 1.5), ''hue_delta'': 0.08},
|
| 1213 |
+
{''type'': ''ProcessCosmos3Prompt'', ''tokenizer'': {''type'': ''PretrainedTokenizer'',
|
| 1214 |
+
''model_path'': ''./checkpoints/Cosmos3-Nano/text_tokenizer'', ''model_max_length'':
|
| 1215 |
+
4096, ''padding_side'': ''right'', ''trust_remote_code'': True}, ''max_len'':
|
| 1216 |
+
512, ''cfg_dropout_rate'': 0.1, ''format_prompt_as_json'': True, ''action_metadata'':
|
| 1217 |
+
{''append_viewpoint'': False, ''viewpoint'': ''concat_view'', ''frame_window_size'':
|
| 1218 |
+
33, ''conditioning_fps'': 25.0, ''video_height'': 320, ''video_width'': 256}},
|
| 1219 |
+
{''type'': ''SimpleNormalizeImages''}, {''type'': ''NormalizeStatesAndActions'',
|
| 1220 |
+
''action_dim'': 64, ''state_dim'': 64, ''state_key'': ''proprio'', ''action_key'':
|
| 1221 |
+
''action'', ''state_norm_type'': ''none'', ''action_norm_type'': ''quantile''},
|
| 1222 |
+
{''type'': ''BuildCosmos3Sequence'', ''raw_action_dim'': 14, ''mode'': ''wam'',
|
| 1223 |
+
''frame_window_size'': 33, ''prepend_state_to_action'': False, ''conditioning_fps'':
|
| 1224 |
+
25.0}, {''type'': ''PrepareVideo'', ''num_views'': 3, ''frame_window_size'': 33,
|
| 1225 |
+
''tile_direction'': ''top_bottom_pair'', ''top_view'': 0, ''bottom_views'': (1,
|
| 1226 |
+
2), ''bottom_height_ratio'': 0.5}, {''type'': ''ResizeAndReflectPad'', ''height'':
|
| 1227 |
+
320, ''width'': 256}], ''action_window_size'': 32, ''action_key'': ''action'',
|
| 1228 |
+
''use_delta'': False, ''statistic_name'': ''robodojo_arx_x5'', ''window_start_idx'':
|
| 1229 |
+
0, ''frame_window_size'': 33, ''require_full_window'': True}}}, ''runner'': {''type'':
|
| 1230 |
+
''FSDPTrainRunner'', ''max_steps'': 10000, ''save_iter_interval'': 1000, ''max_keep_ckpts'':
|
| 1231 |
+
2, ''optimizer'': {''type'': ''AdamW'', ''lr'': 5e-05, ''weight_decay'': 0.05,
|
| 1232 |
+
''betas'': (0.9, 0.99), ''eps'': 1e-08, ''fused'': True, ''exclude_1d_from_weight_decay'':
|
| 1233 |
+
False, ''paramwise_learning_rate'': {''action_in_proj.'': 0.00025, ''action_out_proj.'':
|
| 1234 |
+
0.00025, ''action_modality_embed'': 0.00025}}, ''max_grad_norm'': 1.0, ''tokenizer'':
|
| 1235 |
+
{''type'': ''PretrainedTokenizer'', ''model_path'': ''./checkpoints/Cosmos3-Nano/text_tokenizer'',
|
| 1236 |
+
''model_max_length'': 4096, ''padding_side'': ''right'', ''trust_remote_code'':
|
| 1237 |
+
True}, ''collator'': {''type'': ''DictCollator'', ''keys'': [''images'', ''states'',
|
| 1238 |
+
''actions'', ''action_masks'', ''img_masks'', ''frame_masks'', ''embodiment_ids'',
|
| 1239 |
+
''raw_action_dim'', ''conditioning_fps'', ''action_fps''], ''meta_keys'': [''text_token_ids'',
|
| 1240 |
+
''sequence_plan'', ''task_description'', ''stats'', ''info'', ''timestamp'', ''viewpoint'']},
|
| 1241 |
+
''sampler'': None, ''grad_accumulation_steps'': 16, ''metric'': {''type'': ''VLAMetric'',
|
| 1242 |
+
''active_trackers'': (''jsonl'', ''wandb''), ''run_dir'': ''/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano'',
|
| 1243 |
+
''grad_accumulation_steps'': 16, ''window_size'': 1}, ''lr_scheduler'': {''type'':
|
| 1244 |
+
''linear-warmup+linear-decay'', ''warmup_steps'': 0, ''cycle_length'': 100000},
|
| 1245 |
+
''enable_gradient_checkpointing'': True, ''enable_mixed_precision_training'':
|
| 1246 |
+
True, ''mixed_precision_dtype'': ''bf16'', ''sharding_strategy'': ''full-shard'',
|
| 1247 |
+
''change_key_name'': False, ''cfg'': Config (path: configs/cosmos3/cosmos3nano_robodojo_full_finetune.py):
|
| 1248 |
+
{...}, ''args'': Namespace(config=''configs/cosmos3/cosmos3nano_robodojo_full_finetune.py'',
|
| 1249 |
+
work_dir=''/mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano'', cfg_options=None,
|
| 1250 |
+
eval_after_train=False, resume_from=None)}, ''eval'': {''report_kind'': ''robodojo'',
|
| 1251 |
+
''task_suite_name'': ''robodojo'', ''model_family'': ''cosmos3'', ''eval_chunk_size'':
|
| 1252 |
+
32, ''num_trials_per_task'': 50, ''num_trials_per_task_overrides'': {''stack_bowls'':
|
| 1253 |
+
25, ''stack_bowls_random'': 25, ''push_T'': 25, ''push_T_random'': 25, ''pack_objects_into_box'':
|
| 1254 |
+
25, ''pack_objects_into_box_random'': 25, ''fold_clothes'': 25, ''fold_clothes_random'':
|
| 1255 |
+
25, ''hang_mugs'': 25, ''hang_mugs_random'': 25, ''sweep_blocks'': 25, ''sweep_blocks_random'':
|
| 1256 |
+
25, ''pour_liquid_into_cup'': 25, ''pour_liquid_into_cup_random'': 25, ''make_toast'':
|
| 1257 |
+
25, ''make_toast_random'': 25, ''arrange_largest_number'': 25, ''arrange_largest_number_random'':
|
| 1258 |
+
25, ''sort_nesting_dolls_by_size'': 25, ''sort_nesting_dolls_by_size_random'':
|
| 1259 |
+
25, ''store_laptop_and_headphones'': 25, ''store_laptop_and_headphones_random'':
|
| 1260 |
+
25, ''stack_blocks'': 25, ''stack_blocks_random'': 25}, ''enable_mixed_precision_training'':
|
| 1261 |
+
True, ''mixed_precision_dtype'': ''bf16'', ''dataset'': {''type'': ''RoboDojoEvalDataset'',
|
| 1262 |
+
''unnorm_key'': ''robodojo_arx_x5'', ''transforms'': [{''type'': ''ProcessEvalInputs'',
|
| 1263 |
+
''img_keys'': [''cam_high'', ''cam_left_wrist'', ''cam_right_wrist''], ''embodiment_id'':
|
| 1264 |
+
31}, {''type'': ''SetCosmos3ActionMetadata'', ''conditioning_fps'': 25.0, ''prepend_state_to_action'':
|
| 1265 |
+
False}, {''type'': ''ProcessCosmos3Prompt'', ''tokenizer'': {''type'': ''PretrainedTokenizer'',
|
| 1266 |
+
''model_path'': ''./checkpoints/Cosmos3-Nano/text_tokenizer'', ''model_max_length'':
|
| 1267 |
+
4096, ''padding_side'': ''right'', ''trust_remote_code'': True}, ''max_len'':
|
| 1268 |
+
512, ''cfg_dropout_rate'': 0.0, ''format_prompt_as_json'': True, ''action_metadata'':
|
| 1269 |
+
{''append_viewpoint'': False, ''viewpoint'': ''concat_view'', ''frame_window_size'':
|
| 1270 |
+
33, ''conditioning_fps'': 25.0, ''video_height'': 320, ''video_width'': 256},
|
| 1271 |
+
''output_key'': ''lang_tokens'', ''output_attention_mask_key'': ''lang_masks''},
|
| 1272 |
+
{''type'': ''TransformImage'', ''image_resize_strategy'': ''resize-naive'', ''input_sizes'':
|
| 1273 |
+
[[3, 256, 192], [3, 256, 192], [3, 256, 192]], ''means'': [[127.5, 127.5, 127.5],
|
| 1274 |
+
[127.5, 127.5, 127.5], [127.5, 127.5, 127.5]], ''stds'': [[127.5, 127.5, 127.5],
|
| 1275 |
+
[127.5, 127.5, 127.5], [127.5, 127.5, 127.5]]}, {''type'': ''PrepareVideo'', ''num_views'':
|
| 1276 |
+
3, ''frame_window_size'': 1, ''tile_direction'': ''top_bottom_pair'', ''top_view'':
|
| 1277 |
+
0, ''bottom_views'': (1, 2), ''bottom_height_ratio'': 0.5}, {''type'': ''ResizeAndReflectPad'',
|
| 1278 |
+
''height'': 320, ''width'': 256}]}, ''denormalize_action'': {''type'': ''DenormalizePrivateAction'',
|
| 1279 |
+
''norm_type'': ''quantile'', ''action_dim'': 14, ''statistic_name'': ''robodojo_arx_x5''}},
|
| 1280 |
+
''_ROBODOJO_DATA_ROOT'': ''./datasets/RoboDojo_lerobot_v21_video'', ''_STATISTIC_NAME'':
|
| 1281 |
+
''robodojo_arx_x5'', ''_ACTION_DIM'': 14, ''_MAX_ACTION_DIM'': 64, ''_MAX_STATE_DIM'':
|
| 1282 |
+
64, ''_ACTION_HORIZON'': 32, ''_FRAME_WINDOW_SIZE'': 33, ''_CONDITIONING_FPS'':
|
| 1283 |
+
25.0, ''_EMBODIMENT_ID'': 31, ''_PREPEND_STATE_TO_ACTION'': False, ''_ROBODOJO_ACTION_QUANTILES'':
|
| 1284 |
+
{''q01'': [-1.051365569829941, -3.5348887174584814e-14, 1.741881830823392e-16,
|
| 1285 |
+
-1.5984010362625123, -0.6003574305772781, -1.6678147149085998, 0.0, -0.4509398394823074,
|
| 1286 |
+
-2.5859282299029243e-14, 1.234041714549172e-16, -1.64055180311203, -1.2633746123313903,
|
| 1287 |
+
-1.7645285475254058, 0.0], ''q99'': [0.5431358617544174, 2.495765209197998, 2.492974226474762,
|
| 1288 |
+
1.3241519677639007, 1.2496635341644287, 1.7392305016517635, 1.0, 1.0814965963363647,
|
| 1289 |
+
2.4167031812667843, 2.3470158338546754, 1.141731116771698, 0.5208872479200363,
|
| 1290 |
+
1.489715996980667, 1.0]}, ''_IMAGE_HEIGHT'': 192, ''_IMAGE_WIDTH'': 256, ''_VIDEO_HEIGHT'':
|
| 1291 |
+
320, ''_VIDEO_WIDTH'': 256, ''_VAE_ENCODE_CHUNK_FRAMES'': {''256'': 16, ''480'':
|
| 1292 |
+
24, ''720'': 12}, ''_ROBODOJO_GENERALIZATION_BASE_TASKS'': (''stack_bowls'', ''push_T'',
|
| 1293 |
+
''pack_objects_into_box'', ''fold_clothes'', ''hang_mugs'', ''sweep_blocks'',
|
| 1294 |
+
''pour_liquid_into_cup'', ''make_toast'', ''arrange_largest_number'', ''sort_nesting_dolls_by_size'',
|
| 1295 |
+
''store_laptop_and_headphones'', ''stack_blocks''), ''_ROBODOJO_EPISODE_OVERRIDES'':
|
| 1296 |
+
{''stack_bowls'': 25, ''stack_bowls_random'': 25, ''push_T'': 25, ''push_T_random'':
|
| 1297 |
+
25, ''pack_objects_into_box'': 25, ''pack_objects_into_box_random'': 25, ''fold_clothes'':
|
| 1298 |
+
25, ''fold_clothes_random'': 25, ''hang_mugs'': 25, ''hang_mugs_random'': 25,
|
| 1299 |
+
''sweep_blocks'': 25, ''sweep_blocks_random'': 25, ''pour_liquid_into_cup'': 25,
|
| 1300 |
+
''pour_liquid_into_cup_random'': 25, ''make_toast'': 25, ''make_toast_random'':
|
| 1301 |
+
25, ''arrange_largest_number'': 25, ''arrange_largest_number_random'': 25, ''sort_nesting_dolls_by_size'':
|
| 1302 |
+
25, ''sort_nesting_dolls_by_size_random'': 25, ''store_laptop_and_headphones'':
|
| 1303 |
+
25, ''store_laptop_and_headphones_random'': 25, ''stack_blocks'': 25, ''stack_blocks_random'':
|
| 1304 |
+
25}, ''_ROBODOJO_TRANSFORMS'': [{''type'': ''ProcessParquetInputs'', ''embodiment_id'':
|
| 1305 |
+
31, ''parquet_keys'': [''observation.state'', ''timestamp'', ''actions'', ''info'',
|
| 1306 |
+
''stats'', ''action_masks''], ''video_keys'': [''observation.images.cam_high'',
|
| 1307 |
+
''observation.images.cam_left_wrist'', ''observation.images.cam_right_wrist''],
|
| 1308 |
+
''name_mappings'': {''observation.state'': [''states''], ''actions'': [''actions'']}},
|
| 1309 |
+
{''type'': ''ResizeImages'', ''height'': 192, ''width'': 256}, {''type'': ''AugVideo'',
|
| 1310 |
+
''rotation_range'': 0.0, ''brightness_range'': (0.7, 1.3), ''contrast_range'':
|
| 1311 |
+
(0.6, 1.4), ''crop_scale'': (0.95, 0.95), ''crop_ratio'': (1.0, 1.0), ''prob'':
|
| 1312 |
+
1.0, ''saturation_range'': (0.5, 1.5), ''hue_delta'': 0.08}, {''type'': ''ProcessCosmos3Prompt'',
|
| 1313 |
+
''tokenizer'': {''type'': ''PretrainedTokenizer'', ''model_path'': ''./checkpoints/Cosmos3-Nano/text_tokenizer'',
|
| 1314 |
+
''model_max_length'': 4096, ''padding_side'': ''right'', ''trust_remote_code'':
|
| 1315 |
+
True}, ''max_len'': 512, ''cfg_dropout_rate'': 0.1, ''format_prompt_as_json'':
|
| 1316 |
+
True, ''action_metadata'': {''append_viewpoint'': False, ''viewpoint'': ''concat_view'',
|
| 1317 |
+
''frame_window_size'': 33, ''conditioning_fps'': 25.0, ''video_height'': 320,
|
| 1318 |
+
''video_width'': 256}}, {''type'': ''SimpleNormalizeImages''}, {''type'': ''NormalizeStatesAndActions'',
|
| 1319 |
+
''action_dim'': 64, ''state_dim'': 64, ''state_key'': ''proprio'', ''action_key'':
|
| 1320 |
+
''action'', ''state_norm_type'': ''none'', ''action_norm_type'': ''quantile''},
|
| 1321 |
+
{''type'': ''BuildCosmos3Sequence'', ''raw_action_dim'': 14, ''mode'': ''wam'',
|
| 1322 |
+
''frame_window_size'': 33, ''prepend_state_to_action'': False, ''conditioning_fps'':
|
| 1323 |
+
25.0}, {''type'': ''PrepareVideo'', ''num_views'': 3, ''frame_window_size'': 33,
|
| 1324 |
+
''tile_direction'': ''top_bottom_pair'', ''top_view'': 0, ''bottom_views'': (1,
|
| 1325 |
+
2), ''bottom_height_ratio'': 0.5}, {''type'': ''ResizeAndReflectPad'', ''height'':
|
| 1326 |
+
320, ''width'': 256}], ''themis'': {''transport'': {''host'': ''127.0.0.1'', ''port'':
|
| 1327 |
+
5555, ''timeout_s'': 30.0, ''image_keys'': [''cam_high'', ''cam_left_wrist'',
|
| 1328 |
+
''cam_right_wrist''], ''state_keys'': [''states''], ''unnorm_key'': ''robodojo_arx_x5'',
|
| 1329 |
+
''image_encoding'': ''rgb8'', ''report_service_name'': ''/fluxvla/report_evaluation''},
|
| 1330 |
+
''runner'': {''type'': ''EvalRunner'', ''environment'': {''type'': ''RoboDojoEnvironment'',
|
| 1331 |
+
''task_name'': ''all'', ''env_cfg_type'': ''arx_x5'', ''robodojo_root'': ''/root/projects/RoboDojo'',
|
| 1332 |
+
''device_id'': 1, ''action_mode'': ''joint'', ''headless'': True, ''save_videos'':
|
| 1333 |
+
False}, ''model_client'': {''type'': ''FluxVLAZMQModelClient''}, ''evaluator'':
|
| 1334 |
+
{''type'': ''SuccessRateEvaluator''}, ''seed'': 0, ''episodes_per_task'': 50,
|
| 1335 |
+
''episodes_per_task_overrides'': {''stack_bowls'': 25, ''stack_bowls_random'':
|
| 1336 |
+
25, ''push_T'': 25, ''push_T_random'': 25, ''pack_objects_into_box'': 25, ''pack_objects_into_box_random'':
|
| 1337 |
+
25, ''fold_clothes'': 25, ''fold_clothes_random'': 25, ''hang_mugs'': 25, ''hang_mugs_random'':
|
| 1338 |
+
25, ''sweep_blocks'': 25, ''sweep_blocks_random'': 25, ''pour_liquid_into_cup'':
|
| 1339 |
+
25, ''pour_liquid_into_cup_random'': 25, ''make_toast'': 25, ''make_toast_random'':
|
| 1340 |
+
25, ''arrange_largest_number'': 25, ''arrange_largest_number_random'': 25, ''sort_nesting_dolls_by_size'':
|
| 1341 |
+
25, ''sort_nesting_dolls_by_size_random'': 25, ''store_laptop_and_headphones'':
|
| 1342 |
+
25, ''store_laptop_and_headphones_random'': 25, ''stack_blocks'': 25, ''stack_blocks_random'':
|
| 1343 |
+
25}, ''max_episode_steps'': 2000, ''execute_horizon'': 32, ''stop_on_success'':
|
| 1344 |
+
True, ''parallel_workers'': 1, ''simulator_gpu_ids'': None, ''work_dir'': ''work_dirs/fluxthemis''},
|
| 1345 |
+
''ros_server'': {''dataset_section'': ''eval'', ''evaluation_reporting'': {''result_output_dir'':
|
| 1346 |
+
''work_dirs/fluxthemis'', ''report_kind'': ''robodojo''}, ''device'': ''cuda:0'',
|
| 1347 |
+
''workers'': {''startup_timeout_s'': 900.0, ''request_timeout_s'': 120.0, ''lease_timeout_s'':
|
| 1348 |
+
900.0}, ''mixed_precision_dtype'': ''bf16'', ''enable_mixed_precision'': True,
|
| 1349 |
+
''model_outputs_environment_actions'': False, ''forward_seed'': False, ''denormalize_context'':
|
| 1350 |
+
{''task_suite_name'': ''robodojo_arx_x5''}}}}'
|
| 1351 |
+
change_key_name: false
|
| 1352 |
+
collator:
|
| 1353 |
+
keys:
|
| 1354 |
+
- images
|
| 1355 |
+
- states
|
| 1356 |
+
- actions
|
| 1357 |
+
- action_masks
|
| 1358 |
+
- img_masks
|
| 1359 |
+
- frame_masks
|
| 1360 |
+
- embodiment_ids
|
| 1361 |
+
- raw_action_dim
|
| 1362 |
+
- conditioning_fps
|
| 1363 |
+
- action_fps
|
| 1364 |
+
meta_keys:
|
| 1365 |
+
- text_token_ids
|
| 1366 |
+
- sequence_plan
|
| 1367 |
+
- task_description
|
| 1368 |
+
- stats
|
| 1369 |
+
- info
|
| 1370 |
+
- timestamp
|
| 1371 |
+
- viewpoint
|
| 1372 |
+
type: DictCollator
|
| 1373 |
+
enable_gradient_checkpointing: true
|
| 1374 |
+
enable_mixed_precision_training: true
|
| 1375 |
+
grad_accumulation_steps: 16
|
| 1376 |
+
lr_scheduler:
|
| 1377 |
+
cycle_length: 100000
|
| 1378 |
+
type: linear-warmup+linear-decay
|
| 1379 |
+
warmup_steps: 0
|
| 1380 |
+
max_grad_norm: 1
|
| 1381 |
+
max_keep_ckpts: 2
|
| 1382 |
+
max_steps: 10000
|
| 1383 |
+
metric:
|
| 1384 |
+
active_trackers:
|
| 1385 |
+
- jsonl
|
| 1386 |
+
- wandb
|
| 1387 |
+
grad_accumulation_steps: 16
|
| 1388 |
+
run_dir: /mnt/data/cpfs/users/jikun/wk_dir/robodojo/cosmos3_nano
|
| 1389 |
+
type: VLAMetric
|
| 1390 |
+
window_size: 1
|
| 1391 |
+
mixed_precision_dtype: bf16
|
| 1392 |
+
optimizer:
|
| 1393 |
+
betas:
|
| 1394 |
+
- 0.9
|
| 1395 |
+
- 0.99
|
| 1396 |
+
eps: 1e-08
|
| 1397 |
+
exclude_1d_from_weight_decay: false
|
| 1398 |
+
fused: true
|
| 1399 |
+
lr: 5e-05
|
| 1400 |
+
paramwise_learning_rate:
|
| 1401 |
+
action_in_proj.: 0.00025
|
| 1402 |
+
action_modality_embed: 0.00025
|
| 1403 |
+
action_out_proj.: 0.00025
|
| 1404 |
+
type: AdamW
|
| 1405 |
+
weight_decay: 0.05
|
| 1406 |
+
sampler: null
|
| 1407 |
+
save_iter_interval: 1000
|
| 1408 |
+
sharding_strategy: full-shard
|
| 1409 |
+
tokenizer:
|
| 1410 |
+
model_max_length: 4096
|
| 1411 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 1412 |
+
padding_side: right
|
| 1413 |
+
trust_remote_code: true
|
| 1414 |
+
type: PretrainedTokenizer
|
| 1415 |
+
type: FSDPTrainRunner
|
| 1416 |
+
themis:
|
| 1417 |
+
ros_server:
|
| 1418 |
+
dataset_section: eval
|
| 1419 |
+
denormalize_context:
|
| 1420 |
+
task_suite_name: robodojo_arx_x5
|
| 1421 |
+
device: cuda:0
|
| 1422 |
+
enable_mixed_precision: true
|
| 1423 |
+
evaluation_reporting:
|
| 1424 |
+
report_kind: robodojo
|
| 1425 |
+
result_output_dir: work_dirs/fluxthemis
|
| 1426 |
+
forward_seed: false
|
| 1427 |
+
mixed_precision_dtype: bf16
|
| 1428 |
+
model_outputs_environment_actions: false
|
| 1429 |
+
workers:
|
| 1430 |
+
lease_timeout_s: 900
|
| 1431 |
+
request_timeout_s: 120
|
| 1432 |
+
startup_timeout_s: 900
|
| 1433 |
+
runner:
|
| 1434 |
+
environment:
|
| 1435 |
+
action_mode: joint
|
| 1436 |
+
device_id: 1
|
| 1437 |
+
env_cfg_type: arx_x5
|
| 1438 |
+
headless: true
|
| 1439 |
+
robodojo_root: /root/projects/RoboDojo
|
| 1440 |
+
save_videos: false
|
| 1441 |
+
task_name: all
|
| 1442 |
+
type: RoboDojoEnvironment
|
| 1443 |
+
episodes_per_task: 50
|
| 1444 |
+
episodes_per_task_overrides:
|
| 1445 |
+
arrange_largest_number: 25
|
| 1446 |
+
arrange_largest_number_random: 25
|
| 1447 |
+
fold_clothes: 25
|
| 1448 |
+
fold_clothes_random: 25
|
| 1449 |
+
hang_mugs: 25
|
| 1450 |
+
hang_mugs_random: 25
|
| 1451 |
+
make_toast: 25
|
| 1452 |
+
make_toast_random: 25
|
| 1453 |
+
pack_objects_into_box: 25
|
| 1454 |
+
pack_objects_into_box_random: 25
|
| 1455 |
+
pour_liquid_into_cup: 25
|
| 1456 |
+
pour_liquid_into_cup_random: 25
|
| 1457 |
+
push_T: 25
|
| 1458 |
+
push_T_random: 25
|
| 1459 |
+
sort_nesting_dolls_by_size: 25
|
| 1460 |
+
sort_nesting_dolls_by_size_random: 25
|
| 1461 |
+
stack_blocks: 25
|
| 1462 |
+
stack_blocks_random: 25
|
| 1463 |
+
stack_bowls: 25
|
| 1464 |
+
stack_bowls_random: 25
|
| 1465 |
+
store_laptop_and_headphones: 25
|
| 1466 |
+
store_laptop_and_headphones_random: 25
|
| 1467 |
+
sweep_blocks: 25
|
| 1468 |
+
sweep_blocks_random: 25
|
| 1469 |
+
evaluator:
|
| 1470 |
+
type: SuccessRateEvaluator
|
| 1471 |
+
execute_horizon: 32
|
| 1472 |
+
max_episode_steps: 2000
|
| 1473 |
+
model_client:
|
| 1474 |
+
type: FluxVLAZMQModelClient
|
| 1475 |
+
parallel_workers: 1
|
| 1476 |
+
seed: 0
|
| 1477 |
+
simulator_gpu_ids: null
|
| 1478 |
+
stop_on_success: true
|
| 1479 |
+
type: EvalRunner
|
| 1480 |
+
work_dir: work_dirs/fluxthemis
|
| 1481 |
+
transport:
|
| 1482 |
+
host: 127.0.0.1
|
| 1483 |
+
image_encoding: rgb8
|
| 1484 |
+
image_keys:
|
| 1485 |
+
- cam_high
|
| 1486 |
+
- cam_left_wrist
|
| 1487 |
+
- cam_right_wrist
|
| 1488 |
+
port: 5555
|
| 1489 |
+
report_service_name: /fluxvla/report_evaluation
|
| 1490 |
+
state_keys:
|
| 1491 |
+
- states
|
| 1492 |
+
timeout_s: 30
|
| 1493 |
+
unnorm_key: robodojo_arx_x5
|
| 1494 |
+
train_dataloader:
|
| 1495 |
+
dataset:
|
| 1496 |
+
datasets:
|
| 1497 |
+
action_key: action
|
| 1498 |
+
action_window_size: 32
|
| 1499 |
+
data_root_path:
|
| 1500 |
+
- ./datasets/RoboDojo_lerobot_v21_video
|
| 1501 |
+
frame_window_size: 33
|
| 1502 |
+
require_full_window: true
|
| 1503 |
+
statistic_name: robodojo_arx_x5
|
| 1504 |
+
transforms:
|
| 1505 |
+
- embodiment_id: 31
|
| 1506 |
+
name_mappings:
|
| 1507 |
+
actions:
|
| 1508 |
+
- actions
|
| 1509 |
+
observation.state:
|
| 1510 |
+
- states
|
| 1511 |
+
parquet_keys:
|
| 1512 |
+
- observation.state
|
| 1513 |
+
- timestamp
|
| 1514 |
+
- actions
|
| 1515 |
+
- info
|
| 1516 |
+
- stats
|
| 1517 |
+
- action_masks
|
| 1518 |
+
type: ProcessParquetInputs
|
| 1519 |
+
video_keys:
|
| 1520 |
+
- observation.images.cam_high
|
| 1521 |
+
- observation.images.cam_left_wrist
|
| 1522 |
+
- observation.images.cam_right_wrist
|
| 1523 |
+
- height: 192
|
| 1524 |
+
type: ResizeImages
|
| 1525 |
+
width: 256
|
| 1526 |
+
- brightness_range:
|
| 1527 |
+
- 0.7
|
| 1528 |
+
- 1.3
|
| 1529 |
+
contrast_range:
|
| 1530 |
+
- 0.6
|
| 1531 |
+
- 1.4
|
| 1532 |
+
crop_ratio:
|
| 1533 |
+
- 1
|
| 1534 |
+
- 1
|
| 1535 |
+
crop_scale:
|
| 1536 |
+
- 0.95
|
| 1537 |
+
- 0.95
|
| 1538 |
+
hue_delta: 0.08
|
| 1539 |
+
prob: 1
|
| 1540 |
+
rotation_range: 0
|
| 1541 |
+
saturation_range:
|
| 1542 |
+
- 0.5
|
| 1543 |
+
- 1.5
|
| 1544 |
+
type: AugVideo
|
| 1545 |
+
- action_metadata:
|
| 1546 |
+
append_viewpoint: false
|
| 1547 |
+
conditioning_fps: 25
|
| 1548 |
+
frame_window_size: 33
|
| 1549 |
+
video_height: 320
|
| 1550 |
+
video_width: 256
|
| 1551 |
+
viewpoint: concat_view
|
| 1552 |
+
cfg_dropout_rate: 0.1
|
| 1553 |
+
format_prompt_as_json: true
|
| 1554 |
+
max_len: 512
|
| 1555 |
+
tokenizer:
|
| 1556 |
+
model_max_length: 4096
|
| 1557 |
+
model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
|
| 1558 |
+
padding_side: right
|
| 1559 |
+
trust_remote_code: true
|
| 1560 |
+
type: PretrainedTokenizer
|
| 1561 |
+
type: ProcessCosmos3Prompt
|
| 1562 |
+
- type: SimpleNormalizeImages
|
| 1563 |
+
- action_dim: 64
|
| 1564 |
+
action_key: action
|
| 1565 |
+
action_norm_type: quantile
|
| 1566 |
+
state_dim: 64
|
| 1567 |
+
state_key: proprio
|
| 1568 |
+
state_norm_type: none
|
| 1569 |
+
type: NormalizeStatesAndActions
|
| 1570 |
+
- conditioning_fps: 25
|
| 1571 |
+
frame_window_size: 33
|
| 1572 |
+
mode: wam
|
| 1573 |
+
prepend_state_to_action: false
|
| 1574 |
+
raw_action_dim: 14
|
| 1575 |
+
type: BuildCosmos3Sequence
|
| 1576 |
+
- bottom_height_ratio: 0.5
|
| 1577 |
+
bottom_views:
|
| 1578 |
+
- 1
|
| 1579 |
+
- 2
|
| 1580 |
+
frame_window_size: 33
|
| 1581 |
+
num_views: 3
|
| 1582 |
+
tile_direction: top_bottom_pair
|
| 1583 |
+
top_view: 0
|
| 1584 |
+
type: PrepareVideo
|
| 1585 |
+
- height: 320
|
| 1586 |
+
type: ResizeAndReflectPad
|
| 1587 |
+
width: 256
|
| 1588 |
+
type: ParquetDataset
|
| 1589 |
+
use_delta: false
|
| 1590 |
+
window_start_idx: 0
|
| 1591 |
+
name_mappings:
|
| 1592 |
+
action:
|
| 1593 |
+
- action
|
| 1594 |
+
observation.state:
|
| 1595 |
+
- proprio
|
| 1596 |
+
reshuffle_each_epoch: true
|
| 1597 |
+
seed: 42
|
| 1598 |
+
statistic_keys:
|
| 1599 |
+
- observation.state
|
| 1600 |
+
- action
|
| 1601 |
+
- timestamp
|
| 1602 |
+
statistic_name: robodojo_arx_x5
|
| 1603 |
+
statistics_overrides:
|
| 1604 |
+
robodojo_arx_x5:
|
| 1605 |
+
action:
|
| 1606 |
+
q01:
|
| 1607 |
+
- -1.051365569829941
|
| 1608 |
+
- -3.5348887174584814e-14
|
| 1609 |
+
- 1.741881830823392e-16
|
| 1610 |
+
- -1.5984010362625123
|
| 1611 |
+
- -0.6003574305772781
|
| 1612 |
+
- -1.6678147149085998
|
| 1613 |
+
- 0
|
| 1614 |
+
- -0.4509398394823074
|
| 1615 |
+
- -2.5859282299029243e-14
|
| 1616 |
+
- 1.234041714549172e-16
|
| 1617 |
+
- -1.64055180311203
|
| 1618 |
+
- -1.2633746123313903
|
| 1619 |
+
- -1.7645285475254058
|
| 1620 |
+
- 0
|
| 1621 |
+
q99:
|
| 1622 |
+
- 0.5431358617544174
|
| 1623 |
+
- 2.495765209197998
|
| 1624 |
+
- 2.492974226474762
|
| 1625 |
+
- 1.3241519677639007
|
| 1626 |
+
- 1.2496635341644287
|
| 1627 |
+
- 1.7392305016517635
|
| 1628 |
+
- 1
|
| 1629 |
+
- 1.0814965963363647
|
| 1630 |
+
- 2.4167031812667843
|
| 1631 |
+
- 2.3470158338546754
|
| 1632 |
+
- 1.141731116771698
|
| 1633 |
+
- 0.5208872479200363
|
| 1634 |
+
- 1.489715996980667
|
| 1635 |
+
- 1
|
| 1636 |
+
type: DistributedRepeatingDataset
|
| 1637 |
+
per_device_batch_size: 8
|
| 1638 |
+
per_device_num_workers: 4
|
| 1639 |
+
prefetch_factor: 1
|
| 1640 |
+
|
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robodojo_arx_x5": {
|
| 3 |
+
"proprio": {
|
| 4 |
+
"mean": [
|
| 5 |
+
-0.20040483290933933,
|
| 6 |
+
0.9260306606167606,
|
| 7 |
+
0.6881890325982686,
|
| 8 |
+
-0.3400483206709066,
|
| 9 |
+
0.06579394446194628,
|
| 10 |
+
0.004003346747695925,
|
| 11 |
+
0.7714465980721269,
|
| 12 |
+
0.1729983421764827,
|
| 13 |
+
0.8224942863743041,
|
| 14 |
+
0.6196512620467081,
|
| 15 |
+
-0.3604178425587031,
|
| 16 |
+
-0.06267070852548702,
|
| 17 |
+
0.0037534706356096253,
|
| 18 |
+
0.7860055662365837
|
| 19 |
+
],
|
| 20 |
+
"std": [
|
| 21 |
+
0.34305506149779086,
|
| 22 |
+
0.88803979292961,
|
| 23 |
+
0.7302414431033704,
|
| 24 |
+
0.6487680382543082,
|
| 25 |
+
0.29890958198694983,
|
| 26 |
+
0.5843008394814946,
|
| 27 |
+
0.343166656637697,
|
| 28 |
+
0.3198980322111088,
|
| 29 |
+
0.8736479484499943,
|
| 30 |
+
0.7135349837518498,
|
| 31 |
+
0.6027223232925302,
|
| 32 |
+
0.2836475903509877,
|
| 33 |
+
0.5368540927401809,
|
| 34 |
+
0.3406560199738384
|
| 35 |
+
],
|
| 36 |
+
"min": [
|
| 37 |
+
-1.4863648414611816,
|
| 38 |
+
-0.2586335241794586,
|
| 39 |
+
-0.06850092858076096,
|
| 40 |
+
-2.2642147541046143,
|
| 41 |
+
-1.4876768589019775,
|
| 42 |
+
-3.0168392658233643,
|
| 43 |
+
-3.212450869184004e-17,
|
| 44 |
+
-1.4924354553222656,
|
| 45 |
+
-0.27809593081474304,
|
| 46 |
+
-0.18774886429309845,
|
| 47 |
+
-2.5354628562927246,
|
| 48 |
+
-3.0663280487060547,
|
| 49 |
+
-3.0486762523651123,
|
| 50 |
+
-3.212450869184004e-17
|
| 51 |
+
],
|
| 52 |
+
"max": [
|
| 53 |
+
1.7537026405334473,
|
| 54 |
+
3.0546703338623047,
|
| 55 |
+
3.8525187969207764,
|
| 56 |
+
2.0974574089050293,
|
| 57 |
+
1.8103265762329102,
|
| 58 |
+
3.1366536617279053,
|
| 59 |
+
1.0,
|
| 60 |
+
1.6732014417648315,
|
| 61 |
+
3.3797459602355957,
|
| 62 |
+
4.252756595611572,
|
| 63 |
+
2.5287232398986816,
|
| 64 |
+
3.1440579891204834,
|
| 65 |
+
3.0381109714508057,
|
| 66 |
+
1.0
|
| 67 |
+
],
|
| 68 |
+
"q01": null,
|
| 69 |
+
"q99": null
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"mean": [
|
| 73 |
+
-0.20044206015317542,
|
| 74 |
+
0.9262120117772524,
|
| 75 |
+
0.6882954361000181,
|
| 76 |
+
-0.34006418745617883,
|
| 77 |
+
0.0658081773254239,
|
| 78 |
+
0.0039689747289930934,
|
| 79 |
+
0.7713835451223375,
|
| 80 |
+
0.1729873784174943,
|
| 81 |
+
0.8228202306896505,
|
| 82 |
+
0.61992379065145,
|
| 83 |
+
-0.36062264651275594,
|
| 84 |
+
-0.06273007512256629,
|
| 85 |
+
0.003626950967936429,
|
| 86 |
+
0.7859185929400508
|
| 87 |
+
],
|
| 88 |
+
"std": [
|
| 89 |
+
0.3430578526958288,
|
| 90 |
+
0.8880320168409441,
|
| 91 |
+
0.7302223166171972,
|
| 92 |
+
0.6488505412449643,
|
| 93 |
+
0.29892352527661153,
|
| 94 |
+
0.5843509710911197,
|
| 95 |
+
0.34319546515299043,
|
| 96 |
+
0.3199443326985692,
|
| 97 |
+
0.8737037084051896,
|
| 98 |
+
0.7136346922036603,
|
| 99 |
+
0.6029010762371366,
|
| 100 |
+
0.2837157953906254,
|
| 101 |
+
0.5371882124069792,
|
| 102 |
+
0.3407070568392383
|
| 103 |
+
],
|
| 104 |
+
"min": [
|
| 105 |
+
-1.4863648414611816,
|
| 106 |
+
-0.2586335241794586,
|
| 107 |
+
-0.06850092858076096,
|
| 108 |
+
-2.2642147541046143,
|
| 109 |
+
-1.4876768589019775,
|
| 110 |
+
-3.0168392658233643,
|
| 111 |
+
-3.212450869184004e-17,
|
| 112 |
+
-1.4924354553222656,
|
| 113 |
+
-0.27809593081474304,
|
| 114 |
+
-0.18774886429309845,
|
| 115 |
+
-2.5354628562927246,
|
| 116 |
+
-3.0663280487060547,
|
| 117 |
+
-3.0486762523651123,
|
| 118 |
+
-3.212450869184004e-17
|
| 119 |
+
],
|
| 120 |
+
"max": [
|
| 121 |
+
1.7537026405334473,
|
| 122 |
+
3.0546703338623047,
|
| 123 |
+
3.8525187969207764,
|
| 124 |
+
2.0974574089050293,
|
| 125 |
+
1.8103265762329102,
|
| 126 |
+
3.1366536617279053,
|
| 127 |
+
1.0,
|
| 128 |
+
1.6732014417648315,
|
| 129 |
+
3.3797459602355957,
|
| 130 |
+
4.252756595611572,
|
| 131 |
+
2.5287232398986816,
|
| 132 |
+
3.1440579891204834,
|
| 133 |
+
3.0381109714508057,
|
| 134 |
+
1.0
|
| 135 |
+
],
|
| 136 |
+
"q01": [
|
| 137 |
+
-1.051365569829941,
|
| 138 |
+
-3.5348887174584814e-14,
|
| 139 |
+
1.741881830823392e-16,
|
| 140 |
+
-1.5984010362625123,
|
| 141 |
+
-0.6003574305772781,
|
| 142 |
+
-1.6678147149085998,
|
| 143 |
+
0.0,
|
| 144 |
+
-0.4509398394823074,
|
| 145 |
+
-2.5859282299029243e-14,
|
| 146 |
+
1.234041714549172e-16,
|
| 147 |
+
-1.64055180311203,
|
| 148 |
+
-1.2633746123313903,
|
| 149 |
+
-1.7645285475254058,
|
| 150 |
+
0.0
|
| 151 |
+
],
|
| 152 |
+
"q99": [
|
| 153 |
+
0.5431358617544174,
|
| 154 |
+
2.495765209197998,
|
| 155 |
+
2.492974226474762,
|
| 156 |
+
1.3241519677639007,
|
| 157 |
+
1.2496635341644287,
|
| 158 |
+
1.7392305016517635,
|
| 159 |
+
1.0,
|
| 160 |
+
1.0814965963363647,
|
| 161 |
+
2.4167031812667843,
|
| 162 |
+
2.3470158338546754,
|
| 163 |
+
1.141731116771698,
|
| 164 |
+
0.5208872479200363,
|
| 165 |
+
1.489715996980667,
|
| 166 |
+
1.0
|
| 167 |
+
]
|
| 168 |
+
},
|
| 169 |
+
"timestamp": {
|
| 170 |
+
"mean": [
|
| 171 |
+
13.704522752718054
|
| 172 |
+
],
|
| 173 |
+
"std": [
|
| 174 |
+
11.04044022225918
|
| 175 |
+
],
|
| 176 |
+
"min": [
|
| 177 |
+
0.0
|
| 178 |
+
],
|
| 179 |
+
"max": [
|
| 180 |
+
61.44
|
| 181 |
+
],
|
| 182 |
+
"q01": null,
|
| 183 |
+
"q99": null
|
| 184 |
+
}
|
| 185 |
+
}
|
| 186 |
+
}
|
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ff997c98bc5e49cf25e70b25641ed2032081ebf063de8c365c4cbdd0c94e8cc
|
| 3 |
+
size 25727629118
|
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_ROBODOJO_DATA_ROOT": "/mnt/data/cpfs/users/jikun/robodojo/RoboDojo_lerobot_v21_video",
|
| 3 |
+
"_ROBODOJO_EPISODE_OVERRIDES": {
|
| 4 |
+
"arrange_largest_number": 25,
|
| 5 |
+
"arrange_largest_number_random": 25,
|
| 6 |
+
"fold_clothes": 25,
|
| 7 |
+
"fold_clothes_random": 25,
|
| 8 |
+
"hang_mugs": 25,
|
| 9 |
+
"hang_mugs_random": 25,
|
| 10 |
+
"make_toast": 25,
|
| 11 |
+
"make_toast_random": 25,
|
| 12 |
+
"pack_objects_into_box": 25,
|
| 13 |
+
"pack_objects_into_box_random": 25,
|
| 14 |
+
"pour_liquid_into_cup": 25,
|
| 15 |
+
"pour_liquid_into_cup_random": 25,
|
| 16 |
+
"push_T": 25,
|
| 17 |
+
"push_T_random": 25,
|
| 18 |
+
"sort_nesting_dolls_by_size": 25,
|
| 19 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 20 |
+
"stack_blocks": 25,
|
| 21 |
+
"stack_blocks_random": 25,
|
| 22 |
+
"stack_bowls": 25,
|
| 23 |
+
"stack_bowls_random": 25,
|
| 24 |
+
"store_laptop_and_headphones": 25,
|
| 25 |
+
"store_laptop_and_headphones_random": 25,
|
| 26 |
+
"sweep_blocks": 25,
|
| 27 |
+
"sweep_blocks_random": 25
|
| 28 |
+
},
|
| 29 |
+
"_ROBODOJO_GENERALIZATION_BASE_TASKS": [
|
| 30 |
+
"stack_bowls",
|
| 31 |
+
"push_T",
|
| 32 |
+
"pack_objects_into_box",
|
| 33 |
+
"fold_clothes",
|
| 34 |
+
"hang_mugs",
|
| 35 |
+
"sweep_blocks",
|
| 36 |
+
"pour_liquid_into_cup",
|
| 37 |
+
"make_toast",
|
| 38 |
+
"arrange_largest_number",
|
| 39 |
+
"sort_nesting_dolls_by_size",
|
| 40 |
+
"store_laptop_and_headphones",
|
| 41 |
+
"stack_blocks"
|
| 42 |
+
],
|
| 43 |
+
"_action_dim": 16,
|
| 44 |
+
"_action_horizon": 16,
|
| 45 |
+
"_camera_keys": [
|
| 46 |
+
"cam_high",
|
| 47 |
+
"cam_left_wrist",
|
| 48 |
+
"cam_right_wrist"
|
| 49 |
+
],
|
| 50 |
+
"_cosmos_base_model": "./checkpoints/Cosmos-Predict2.5-2B",
|
| 51 |
+
"_cosmos_tokenizer": {
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
|
| 54 |
+
"type": "PretrainedTokenizer"
|
| 55 |
+
},
|
| 56 |
+
"_frame_sample_stride": 2,
|
| 57 |
+
"_frame_window_size": 9,
|
| 58 |
+
"_grad_accumulation_steps": 4,
|
| 59 |
+
"_image_size": 224,
|
| 60 |
+
"_ori_action_dim": 14,
|
| 61 |
+
"_prompt": {
|
| 62 |
+
"input_key": "task_description",
|
| 63 |
+
"remove_input_key": true,
|
| 64 |
+
"tokenizer": {
|
| 65 |
+
"model_max_length": 512,
|
| 66 |
+
"model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
|
| 67 |
+
"type": "PretrainedTokenizer"
|
| 68 |
+
},
|
| 69 |
+
"type": "ProcessCosmos25Prompt"
|
| 70 |
+
},
|
| 71 |
+
"_resize": {
|
| 72 |
+
"backend": "torch",
|
| 73 |
+
"height": 224,
|
| 74 |
+
"output_layout": "flattened_chw",
|
| 75 |
+
"scale_divisor": 255.0,
|
| 76 |
+
"type": "ResizeImages",
|
| 77 |
+
"width": 224
|
| 78 |
+
},
|
| 79 |
+
"_state_dim": 32,
|
| 80 |
+
"_state_encoding": {
|
| 81 |
+
"backend": "torch",
|
| 82 |
+
"expand_axis": 0,
|
| 83 |
+
"interleave": true,
|
| 84 |
+
"keys": [
|
| 85 |
+
"states"
|
| 86 |
+
],
|
| 87 |
+
"target_dims": {
|
| 88 |
+
"states": 32
|
| 89 |
+
},
|
| 90 |
+
"type": "SinCosKeys"
|
| 91 |
+
},
|
| 92 |
+
"_statistic_name": "robodojo_arx_x5",
|
| 93 |
+
"_video": {
|
| 94 |
+
"combine_view_masks": true,
|
| 95 |
+
"num_views": 3,
|
| 96 |
+
"tile_direction": "horizontal",
|
| 97 |
+
"type": "PrepareVideo"
|
| 98 |
+
},
|
| 99 |
+
"eval": {
|
| 100 |
+
"dataset": {
|
| 101 |
+
"state_dtype": "fp32",
|
| 102 |
+
"transforms": [
|
| 103 |
+
{
|
| 104 |
+
"img_keys": [
|
| 105 |
+
"cam_high",
|
| 106 |
+
"cam_left_wrist",
|
| 107 |
+
"cam_right_wrist"
|
| 108 |
+
],
|
| 109 |
+
"type": "ProcessEvalInputs"
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"input_key": "task_description",
|
| 113 |
+
"remove_input_key": true,
|
| 114 |
+
"tokenizer": {
|
| 115 |
+
"model_max_length": 512,
|
| 116 |
+
"model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
|
| 117 |
+
"type": "PretrainedTokenizer"
|
| 118 |
+
},
|
| 119 |
+
"type": "ProcessCosmos25Prompt"
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"backend": "torch",
|
| 123 |
+
"height": 224,
|
| 124 |
+
"key": "pixel_values",
|
| 125 |
+
"output_layout": "flattened_chw",
|
| 126 |
+
"scale_divisor": 255.0,
|
| 127 |
+
"type": "ResizeImages",
|
| 128 |
+
"width": 224
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"combine_view_masks": true,
|
| 132 |
+
"frame_window_size": 1,
|
| 133 |
+
"num_views": 3,
|
| 134 |
+
"tile_direction": "horizontal",
|
| 135 |
+
"type": "PrepareVideo"
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"backend": "torch",
|
| 139 |
+
"expand_axis": 0,
|
| 140 |
+
"interleave": true,
|
| 141 |
+
"keys": [
|
| 142 |
+
"states"
|
| 143 |
+
],
|
| 144 |
+
"target_dims": {
|
| 145 |
+
"states": 32
|
| 146 |
+
},
|
| 147 |
+
"type": "SinCosKeys"
|
| 148 |
+
}
|
| 149 |
+
],
|
| 150 |
+
"type": "RoboDojoEvalDataset",
|
| 151 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 152 |
+
},
|
| 153 |
+
"denormalize_action": {
|
| 154 |
+
"action_dim": 14,
|
| 155 |
+
"clip_normalized_action": true,
|
| 156 |
+
"norm_type": "min_max",
|
| 157 |
+
"statistic_name": "robodojo_arx_x5",
|
| 158 |
+
"type": "DenormalizePrivateAction"
|
| 159 |
+
},
|
| 160 |
+
"model_family": "dit4dit",
|
| 161 |
+
"num_trials_per_task": 50,
|
| 162 |
+
"num_trials_per_task_overrides": {
|
| 163 |
+
"arrange_largest_number": 25,
|
| 164 |
+
"arrange_largest_number_random": 25,
|
| 165 |
+
"fold_clothes": 25,
|
| 166 |
+
"fold_clothes_random": 25,
|
| 167 |
+
"hang_mugs": 25,
|
| 168 |
+
"hang_mugs_random": 25,
|
| 169 |
+
"make_toast": 25,
|
| 170 |
+
"make_toast_random": 25,
|
| 171 |
+
"pack_objects_into_box": 25,
|
| 172 |
+
"pack_objects_into_box_random": 25,
|
| 173 |
+
"pour_liquid_into_cup": 25,
|
| 174 |
+
"pour_liquid_into_cup_random": 25,
|
| 175 |
+
"push_T": 25,
|
| 176 |
+
"push_T_random": 25,
|
| 177 |
+
"sort_nesting_dolls_by_size": 25,
|
| 178 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 179 |
+
"stack_blocks": 25,
|
| 180 |
+
"stack_blocks_random": 25,
|
| 181 |
+
"stack_bowls": 25,
|
| 182 |
+
"stack_bowls_random": 25,
|
| 183 |
+
"store_laptop_and_headphones": 25,
|
| 184 |
+
"store_laptop_and_headphones_random": 25,
|
| 185 |
+
"sweep_blocks": 25,
|
| 186 |
+
"sweep_blocks_random": 25
|
| 187 |
+
},
|
| 188 |
+
"report_kind": "robodojo",
|
| 189 |
+
"task_suite_name": "robodojo"
|
| 190 |
+
},
|
| 191 |
+
"inference_model": {
|
| 192 |
+
"freeze_vlm_backbone": false,
|
| 193 |
+
"init_empty_weights": true,
|
| 194 |
+
"repeated_diffusion_steps": 4,
|
| 195 |
+
"type": "DiT4DiTVLA",
|
| 196 |
+
"vla_head": {
|
| 197 |
+
"action_dim": 16,
|
| 198 |
+
"action_horizon": 16,
|
| 199 |
+
"action_model_type": "DiT-B",
|
| 200 |
+
"add_pos_embed": true,
|
| 201 |
+
"diffusion_model_cfg": {
|
| 202 |
+
"cross_attention_dim": 2048,
|
| 203 |
+
"dropout": 0.2,
|
| 204 |
+
"final_dropout": true,
|
| 205 |
+
"interleave_self_attention": true,
|
| 206 |
+
"norm_type": "ada_norm",
|
| 207 |
+
"num_layers": 16,
|
| 208 |
+
"output_dim": 2560,
|
| 209 |
+
"positional_embeddings": null
|
| 210 |
+
},
|
| 211 |
+
"future_action_window_size": 15,
|
| 212 |
+
"hidden_size": 2560,
|
| 213 |
+
"max_seq_len": 1024,
|
| 214 |
+
"noise_beta_alpha": 1.5,
|
| 215 |
+
"noise_beta_beta": 1.0,
|
| 216 |
+
"noise_s": 0.999,
|
| 217 |
+
"num_inference_timesteps": 4,
|
| 218 |
+
"num_timestep_buckets": 1000,
|
| 219 |
+
"ori_action_dim": 14,
|
| 220 |
+
"state_dim": 32,
|
| 221 |
+
"type": "DiT4DiTActionHead"
|
| 222 |
+
},
|
| 223 |
+
"vlm_backbone": {
|
| 224 |
+
"base_model": "./checkpoints/Cosmos-Predict2.5-2B",
|
| 225 |
+
"conditional_frame_timestep": 0.0001,
|
| 226 |
+
"detach_hidden_states": true,
|
| 227 |
+
"extract_layer": 17,
|
| 228 |
+
"fixed_seed": null,
|
| 229 |
+
"flow_matching_high_sigma_min": null,
|
| 230 |
+
"flow_matching_high_sigma_ratio": null,
|
| 231 |
+
"flow_matching_time_distribution": "uniform",
|
| 232 |
+
"frozen_submodules": [
|
| 233 |
+
"text_encoder",
|
| 234 |
+
"vae"
|
| 235 |
+
],
|
| 236 |
+
"fsdp_min_num_params": 0,
|
| 237 |
+
"future_loss_type": "flow_matching",
|
| 238 |
+
"load_pretrained_weights": false,
|
| 239 |
+
"local_files_only": true,
|
| 240 |
+
"num_frames_out": 9,
|
| 241 |
+
"num_inference_steps": 1,
|
| 242 |
+
"revision": "diffusers/base/post-trained",
|
| 243 |
+
"split_future_frames": true,
|
| 244 |
+
"torch_dtype": "bf16",
|
| 245 |
+
"trainable": true,
|
| 246 |
+
"type": "Cosmos25Backbone"
|
| 247 |
+
}
|
| 248 |
+
},
|
| 249 |
+
"model": {
|
| 250 |
+
"freeze_vlm_backbone": false,
|
| 251 |
+
"repeated_diffusion_steps": 4,
|
| 252 |
+
"type": "DiT4DiTVLA",
|
| 253 |
+
"vla_head": {
|
| 254 |
+
"action_dim": 16,
|
| 255 |
+
"action_horizon": 16,
|
| 256 |
+
"action_model_type": "DiT-B",
|
| 257 |
+
"add_pos_embed": true,
|
| 258 |
+
"diffusion_model_cfg": {
|
| 259 |
+
"cross_attention_dim": 2048,
|
| 260 |
+
"dropout": 0.2,
|
| 261 |
+
"final_dropout": true,
|
| 262 |
+
"interleave_self_attention": true,
|
| 263 |
+
"norm_type": "ada_norm",
|
| 264 |
+
"num_layers": 16,
|
| 265 |
+
"output_dim": 2560,
|
| 266 |
+
"positional_embeddings": null
|
| 267 |
+
},
|
| 268 |
+
"future_action_window_size": 15,
|
| 269 |
+
"hidden_size": 2560,
|
| 270 |
+
"max_seq_len": 1024,
|
| 271 |
+
"noise_beta_alpha": 1.5,
|
| 272 |
+
"noise_beta_beta": 1.0,
|
| 273 |
+
"noise_s": 0.999,
|
| 274 |
+
"num_inference_timesteps": 4,
|
| 275 |
+
"num_timestep_buckets": 1000,
|
| 276 |
+
"ori_action_dim": 14,
|
| 277 |
+
"state_dim": 32,
|
| 278 |
+
"type": "DiT4DiTActionHead"
|
| 279 |
+
},
|
| 280 |
+
"vlm_backbone": {
|
| 281 |
+
"base_model": "./checkpoints/Cosmos-Predict2.5-2B",
|
| 282 |
+
"conditional_frame_timestep": 0.0001,
|
| 283 |
+
"detach_hidden_states": true,
|
| 284 |
+
"extract_layer": 17,
|
| 285 |
+
"fixed_seed": null,
|
| 286 |
+
"flow_matching_high_sigma_min": null,
|
| 287 |
+
"flow_matching_high_sigma_ratio": null,
|
| 288 |
+
"flow_matching_time_distribution": "uniform",
|
| 289 |
+
"frozen_submodules": [
|
| 290 |
+
"text_encoder",
|
| 291 |
+
"vae"
|
| 292 |
+
],
|
| 293 |
+
"fsdp_min_num_params": 0,
|
| 294 |
+
"future_loss_type": "flow_matching",
|
| 295 |
+
"load_pretrained_weights": true,
|
| 296 |
+
"local_files_only": true,
|
| 297 |
+
"num_frames_out": 9,
|
| 298 |
+
"num_inference_steps": 1,
|
| 299 |
+
"revision": "diffusers/base/post-trained",
|
| 300 |
+
"split_future_frames": true,
|
| 301 |
+
"torch_dtype": "bf16",
|
| 302 |
+
"trainable": true,
|
| 303 |
+
"type": "Cosmos25Backbone"
|
| 304 |
+
}
|
| 305 |
+
},
|
| 306 |
+
"runner": {
|
| 307 |
+
"change_key_name": false,
|
| 308 |
+
"collator": {
|
| 309 |
+
"keys": [
|
| 310 |
+
"states",
|
| 311 |
+
"timestamp",
|
| 312 |
+
"images",
|
| 313 |
+
"img_masks",
|
| 314 |
+
"actions",
|
| 315 |
+
"action_masks",
|
| 316 |
+
"frame_masks",
|
| 317 |
+
"lang_tokens",
|
| 318 |
+
"lang_masks"
|
| 319 |
+
],
|
| 320 |
+
"meta_keys": [
|
| 321 |
+
"info",
|
| 322 |
+
"stats"
|
| 323 |
+
],
|
| 324 |
+
"type": "DictCollator"
|
| 325 |
+
},
|
| 326 |
+
"enable_gradient_checkpointing": true,
|
| 327 |
+
"enable_mixed_precision_training": true,
|
| 328 |
+
"grad_accumulation_steps": 4,
|
| 329 |
+
"lr_scheduler": {
|
| 330 |
+
"min_lr": 5e-07,
|
| 331 |
+
"type": "linear-warmup+cosine-decay",
|
| 332 |
+
"warmup_steps": 2000
|
| 333 |
+
},
|
| 334 |
+
"max_epochs": null,
|
| 335 |
+
"max_grad_norm": 1.0,
|
| 336 |
+
"max_keep_ckpts": 3,
|
| 337 |
+
"max_steps": 120000,
|
| 338 |
+
"metric": {
|
| 339 |
+
"active_trackers": [
|
| 340 |
+
"jsonl",
|
| 341 |
+
"wandb"
|
| 342 |
+
],
|
| 343 |
+
"grad_accumulation_steps": 4,
|
| 344 |
+
"run_dir": "work_dirs",
|
| 345 |
+
"type": "VLAMetric",
|
| 346 |
+
"window_size": 1
|
| 347 |
+
},
|
| 348 |
+
"mixed_precision_dtype": "bf16",
|
| 349 |
+
"optimizer": {
|
| 350 |
+
"betas": [
|
| 351 |
+
0.9,
|
| 352 |
+
0.95
|
| 353 |
+
],
|
| 354 |
+
"eps": 1e-08,
|
| 355 |
+
"fused": true,
|
| 356 |
+
"lr": 1e-05,
|
| 357 |
+
"paramwise_learning_rate": {
|
| 358 |
+
"vla_head": 0.0001,
|
| 359 |
+
"vlm_backbone.transformer": 1e-05
|
| 360 |
+
},
|
| 361 |
+
"type": "AdamW",
|
| 362 |
+
"weight_decay": 1e-08,
|
| 363 |
+
"weight_decay_all_params": true
|
| 364 |
+
},
|
| 365 |
+
"pre_fsdp_param_dtype": "fp32",
|
| 366 |
+
"reduce_in_full_precision": false,
|
| 367 |
+
"sampler": null,
|
| 368 |
+
"save_iter_interval": 2000,
|
| 369 |
+
"sharding_strategy": "full-shard",
|
| 370 |
+
"tokenizer": {
|
| 371 |
+
"model_max_length": 512,
|
| 372 |
+
"model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
|
| 373 |
+
"type": "PretrainedTokenizer"
|
| 374 |
+
},
|
| 375 |
+
"type": "FSDPTrainRunner"
|
| 376 |
+
},
|
| 377 |
+
"seed": 42,
|
| 378 |
+
"themis": {
|
| 379 |
+
"ros_server": {
|
| 380 |
+
"dataset_section": "eval",
|
| 381 |
+
"denormalize_context": {
|
| 382 |
+
"task_suite_name": "robodojo_arx_x5"
|
| 383 |
+
},
|
| 384 |
+
"device": "cuda:0",
|
| 385 |
+
"enable_mixed_precision": true,
|
| 386 |
+
"evaluation_reporting": {
|
| 387 |
+
"result_output_dir": "work_dirs/dit4dit_robodojo_eval"
|
| 388 |
+
},
|
| 389 |
+
"forward_seed": false,
|
| 390 |
+
"mixed_precision_dtype": "bf16",
|
| 391 |
+
"model_outputs_environment_actions": false,
|
| 392 |
+
"workers": {
|
| 393 |
+
"lease_timeout_s": 900.0,
|
| 394 |
+
"request_timeout_s": 120.0,
|
| 395 |
+
"startup_timeout_s": 900.0
|
| 396 |
+
}
|
| 397 |
+
},
|
| 398 |
+
"runner": {
|
| 399 |
+
"environment": {
|
| 400 |
+
"action_mode": "joint",
|
| 401 |
+
"device_id": 1,
|
| 402 |
+
"env_cfg_type": "arx_x5",
|
| 403 |
+
"headless": true,
|
| 404 |
+
"robodojo_root": "/root/projects/RoboDojo",
|
| 405 |
+
"save_videos": false,
|
| 406 |
+
"task_name": "all",
|
| 407 |
+
"type": "RoboDojoEnvironment"
|
| 408 |
+
},
|
| 409 |
+
"episodes_per_task": 50,
|
| 410 |
+
"episodes_per_task_overrides": {
|
| 411 |
+
"arrange_largest_number": 25,
|
| 412 |
+
"arrange_largest_number_random": 25,
|
| 413 |
+
"fold_clothes": 25,
|
| 414 |
+
"fold_clothes_random": 25,
|
| 415 |
+
"hang_mugs": 25,
|
| 416 |
+
"hang_mugs_random": 25,
|
| 417 |
+
"make_toast": 25,
|
| 418 |
+
"make_toast_random": 25,
|
| 419 |
+
"pack_objects_into_box": 25,
|
| 420 |
+
"pack_objects_into_box_random": 25,
|
| 421 |
+
"pour_liquid_into_cup": 25,
|
| 422 |
+
"pour_liquid_into_cup_random": 25,
|
| 423 |
+
"push_T": 25,
|
| 424 |
+
"push_T_random": 25,
|
| 425 |
+
"sort_nesting_dolls_by_size": 25,
|
| 426 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 427 |
+
"stack_blocks": 25,
|
| 428 |
+
"stack_blocks_random": 25,
|
| 429 |
+
"stack_bowls": 25,
|
| 430 |
+
"stack_bowls_random": 25,
|
| 431 |
+
"store_laptop_and_headphones": 25,
|
| 432 |
+
"store_laptop_and_headphones_random": 25,
|
| 433 |
+
"sweep_blocks": 25,
|
| 434 |
+
"sweep_blocks_random": 25
|
| 435 |
+
},
|
| 436 |
+
"evaluator": {
|
| 437 |
+
"type": "SuccessRateEvaluator"
|
| 438 |
+
},
|
| 439 |
+
"execute_horizon": 12,
|
| 440 |
+
"max_episode_steps": 2000,
|
| 441 |
+
"model_client": {
|
| 442 |
+
"type": "FluxVLAZMQModelClient"
|
| 443 |
+
},
|
| 444 |
+
"parallel_workers": 1,
|
| 445 |
+
"seed": 0,
|
| 446 |
+
"simulator_gpu_ids": null,
|
| 447 |
+
"stop_on_success": true,
|
| 448 |
+
"type": "EvalRunner",
|
| 449 |
+
"work_dir": "work_dirs/dit4dit_robodojo_eval"
|
| 450 |
+
},
|
| 451 |
+
"transport": {
|
| 452 |
+
"host": "127.0.0.1",
|
| 453 |
+
"image_encoding": "rgb8",
|
| 454 |
+
"image_keys": [
|
| 455 |
+
"cam_high",
|
| 456 |
+
"cam_left_wrist",
|
| 457 |
+
"cam_right_wrist"
|
| 458 |
+
],
|
| 459 |
+
"port": 5555,
|
| 460 |
+
"report_service_name": "/fluxvla/report_evaluation",
|
| 461 |
+
"state_keys": [
|
| 462 |
+
"states"
|
| 463 |
+
],
|
| 464 |
+
"timeout_s": 30.0,
|
| 465 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 466 |
+
}
|
| 467 |
+
},
|
| 468 |
+
"train_dataloader": {
|
| 469 |
+
"dataset": {
|
| 470 |
+
"datasets": {
|
| 471 |
+
"action_dtype": null,
|
| 472 |
+
"action_key": "action",
|
| 473 |
+
"action_window_size": 16,
|
| 474 |
+
"data_root_path": [
|
| 475 |
+
"/mnt/data/cpfs/users/jikun/robodojo/RoboDojo_lerobot_v21_video"
|
| 476 |
+
],
|
| 477 |
+
"frame_sample_stride": 2,
|
| 478 |
+
"frame_window_size": 9,
|
| 479 |
+
"statistic_name": "robodojo_arx_x5",
|
| 480 |
+
"supervise_terminal_padding": true,
|
| 481 |
+
"transforms": [
|
| 482 |
+
{
|
| 483 |
+
"name_mappings": {
|
| 484 |
+
"actions": [
|
| 485 |
+
"actions"
|
| 486 |
+
],
|
| 487 |
+
"observation.state": [
|
| 488 |
+
"states"
|
| 489 |
+
]
|
| 490 |
+
},
|
| 491 |
+
"parquet_keys": [
|
| 492 |
+
"observation.state",
|
| 493 |
+
"timestamp",
|
| 494 |
+
"actions",
|
| 495 |
+
"info",
|
| 496 |
+
"stats",
|
| 497 |
+
"action_masks"
|
| 498 |
+
],
|
| 499 |
+
"type": "ProcessParquetInputs",
|
| 500 |
+
"video_backend": "torchcodec",
|
| 501 |
+
"video_keys": [
|
| 502 |
+
"observation.images.cam_high",
|
| 503 |
+
"observation.images.cam_left_wrist",
|
| 504 |
+
"observation.images.cam_right_wrist"
|
| 505 |
+
]
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"input_key": "task_description",
|
| 509 |
+
"remove_input_key": true,
|
| 510 |
+
"tokenizer": {
|
| 511 |
+
"model_max_length": 512,
|
| 512 |
+
"model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
|
| 513 |
+
"type": "PretrainedTokenizer"
|
| 514 |
+
},
|
| 515 |
+
"type": "ProcessCosmos25Prompt"
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"backend": "torch",
|
| 519 |
+
"height": 224,
|
| 520 |
+
"output_layout": "flattened_chw",
|
| 521 |
+
"scale_divisor": 255.0,
|
| 522 |
+
"type": "ResizeImages",
|
| 523 |
+
"width": 224
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"combine_view_masks": true,
|
| 527 |
+
"frame_window_size": 9,
|
| 528 |
+
"num_views": 3,
|
| 529 |
+
"tile_direction": "horizontal",
|
| 530 |
+
"type": "PrepareVideo"
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"backend": "torch",
|
| 534 |
+
"expand_axis": 0,
|
| 535 |
+
"interleave": true,
|
| 536 |
+
"keys": [
|
| 537 |
+
"states"
|
| 538 |
+
],
|
| 539 |
+
"target_dims": {
|
| 540 |
+
"states": 32
|
| 541 |
+
},
|
| 542 |
+
"type": "SinCosKeys"
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"action_dim": 16,
|
| 546 |
+
"action_key": "action",
|
| 547 |
+
"action_norm_type": "min_max",
|
| 548 |
+
"clip_norm": false,
|
| 549 |
+
"mark_all_action_steps_valid": true,
|
| 550 |
+
"norm_type": "min_max",
|
| 551 |
+
"normalization_epsilon": 0.0,
|
| 552 |
+
"normalize_states": false,
|
| 553 |
+
"output_dtype": "float16",
|
| 554 |
+
"preserve_input_dtype": true,
|
| 555 |
+
"state_dim": 32,
|
| 556 |
+
"state_key": "proprio",
|
| 557 |
+
"state_norm_type": "none",
|
| 558 |
+
"type": "NormalizeStatesAndActions",
|
| 559 |
+
"valid_action_dim": 14,
|
| 560 |
+
"zero_constant_min_max_dims": true
|
| 561 |
+
}
|
| 562 |
+
],
|
| 563 |
+
"type": "ParquetDataset",
|
| 564 |
+
"use_delta": false,
|
| 565 |
+
"window_start_idx": 0
|
| 566 |
+
},
|
| 567 |
+
"name_mappings": {
|
| 568 |
+
"action": [
|
| 569 |
+
"action"
|
| 570 |
+
],
|
| 571 |
+
"observation.state": [
|
| 572 |
+
"proprio"
|
| 573 |
+
]
|
| 574 |
+
},
|
| 575 |
+
"reshuffle_each_epoch": true,
|
| 576 |
+
"seed": 42,
|
| 577 |
+
"shuffle": true,
|
| 578 |
+
"statistic_keys": [
|
| 579 |
+
"observation.state",
|
| 580 |
+
"timestamp",
|
| 581 |
+
"action"
|
| 582 |
+
],
|
| 583 |
+
"statistic_name": "robodojo_arx_x5",
|
| 584 |
+
"type": "DistributedRepeatingDataset"
|
| 585 |
+
},
|
| 586 |
+
"per_device_batch_size": 2,
|
| 587 |
+
"per_device_num_workers": 4
|
| 588 |
+
}
|
| 589 |
+
}
|
|
@@ -0,0 +1,494 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ROBODOJO_DATA_ROOT: /mnt/data/cpfs/users/jikun/robodojo/RoboDojo_lerobot_v21_video
|
| 2 |
+
_ROBODOJO_EPISODE_OVERRIDES:
|
| 3 |
+
arrange_largest_number: 25
|
| 4 |
+
arrange_largest_number_random: 25
|
| 5 |
+
fold_clothes: 25
|
| 6 |
+
fold_clothes_random: 25
|
| 7 |
+
hang_mugs: 25
|
| 8 |
+
hang_mugs_random: 25
|
| 9 |
+
make_toast: 25
|
| 10 |
+
make_toast_random: 25
|
| 11 |
+
pack_objects_into_box: 25
|
| 12 |
+
pack_objects_into_box_random: 25
|
| 13 |
+
pour_liquid_into_cup: 25
|
| 14 |
+
pour_liquid_into_cup_random: 25
|
| 15 |
+
push_T: 25
|
| 16 |
+
push_T_random: 25
|
| 17 |
+
sort_nesting_dolls_by_size: 25
|
| 18 |
+
sort_nesting_dolls_by_size_random: 25
|
| 19 |
+
stack_blocks: 25
|
| 20 |
+
stack_blocks_random: 25
|
| 21 |
+
stack_bowls: 25
|
| 22 |
+
stack_bowls_random: 25
|
| 23 |
+
store_laptop_and_headphones: 25
|
| 24 |
+
store_laptop_and_headphones_random: 25
|
| 25 |
+
sweep_blocks: 25
|
| 26 |
+
sweep_blocks_random: 25
|
| 27 |
+
_ROBODOJO_GENERALIZATION_BASE_TASKS:
|
| 28 |
+
- stack_bowls
|
| 29 |
+
- push_T
|
| 30 |
+
- pack_objects_into_box
|
| 31 |
+
- fold_clothes
|
| 32 |
+
- hang_mugs
|
| 33 |
+
- sweep_blocks
|
| 34 |
+
- pour_liquid_into_cup
|
| 35 |
+
- make_toast
|
| 36 |
+
- arrange_largest_number
|
| 37 |
+
- sort_nesting_dolls_by_size
|
| 38 |
+
- store_laptop_and_headphones
|
| 39 |
+
- stack_blocks
|
| 40 |
+
_action_dim: 16
|
| 41 |
+
_action_horizon: 16
|
| 42 |
+
_camera_keys:
|
| 43 |
+
- cam_high
|
| 44 |
+
- cam_left_wrist
|
| 45 |
+
- cam_right_wrist
|
| 46 |
+
_cosmos_base_model: ./checkpoints/Cosmos-Predict2.5-2B
|
| 47 |
+
_cosmos_tokenizer:
|
| 48 |
+
model_max_length: 512
|
| 49 |
+
model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
|
| 50 |
+
type: PretrainedTokenizer
|
| 51 |
+
_frame_sample_stride: 2
|
| 52 |
+
_frame_window_size: 9
|
| 53 |
+
_grad_accumulation_steps: 4
|
| 54 |
+
_image_size: 224
|
| 55 |
+
_ori_action_dim: 14
|
| 56 |
+
_prompt:
|
| 57 |
+
input_key: task_description
|
| 58 |
+
remove_input_key: true
|
| 59 |
+
tokenizer:
|
| 60 |
+
model_max_length: 512
|
| 61 |
+
model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
|
| 62 |
+
type: PretrainedTokenizer
|
| 63 |
+
type: ProcessCosmos25Prompt
|
| 64 |
+
_resize:
|
| 65 |
+
backend: torch
|
| 66 |
+
height: 224
|
| 67 |
+
output_layout: flattened_chw
|
| 68 |
+
scale_divisor: 255.0
|
| 69 |
+
type: ResizeImages
|
| 70 |
+
width: 224
|
| 71 |
+
_state_dim: 32
|
| 72 |
+
_state_encoding:
|
| 73 |
+
backend: torch
|
| 74 |
+
expand_axis: 0
|
| 75 |
+
interleave: true
|
| 76 |
+
keys:
|
| 77 |
+
- states
|
| 78 |
+
target_dims:
|
| 79 |
+
states: 32
|
| 80 |
+
type: SinCosKeys
|
| 81 |
+
_statistic_name: robodojo_arx_x5
|
| 82 |
+
_video:
|
| 83 |
+
combine_view_masks: true
|
| 84 |
+
num_views: 3
|
| 85 |
+
tile_direction: horizontal
|
| 86 |
+
type: PrepareVideo
|
| 87 |
+
eval:
|
| 88 |
+
dataset:
|
| 89 |
+
state_dtype: fp32
|
| 90 |
+
transforms:
|
| 91 |
+
- img_keys:
|
| 92 |
+
- cam_high
|
| 93 |
+
- cam_left_wrist
|
| 94 |
+
- cam_right_wrist
|
| 95 |
+
type: ProcessEvalInputs
|
| 96 |
+
- input_key: task_description
|
| 97 |
+
remove_input_key: true
|
| 98 |
+
tokenizer:
|
| 99 |
+
model_max_length: 512
|
| 100 |
+
model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
|
| 101 |
+
type: PretrainedTokenizer
|
| 102 |
+
type: ProcessCosmos25Prompt
|
| 103 |
+
- backend: torch
|
| 104 |
+
height: 224
|
| 105 |
+
key: pixel_values
|
| 106 |
+
output_layout: flattened_chw
|
| 107 |
+
scale_divisor: 255.0
|
| 108 |
+
type: ResizeImages
|
| 109 |
+
width: 224
|
| 110 |
+
- combine_view_masks: true
|
| 111 |
+
frame_window_size: 1
|
| 112 |
+
num_views: 3
|
| 113 |
+
tile_direction: horizontal
|
| 114 |
+
type: PrepareVideo
|
| 115 |
+
- backend: torch
|
| 116 |
+
expand_axis: 0
|
| 117 |
+
interleave: true
|
| 118 |
+
keys:
|
| 119 |
+
- states
|
| 120 |
+
target_dims:
|
| 121 |
+
states: 32
|
| 122 |
+
type: SinCosKeys
|
| 123 |
+
type: RoboDojoEvalDataset
|
| 124 |
+
unnorm_key: robodojo_arx_x5
|
| 125 |
+
denormalize_action:
|
| 126 |
+
action_dim: 14
|
| 127 |
+
clip_normalized_action: true
|
| 128 |
+
norm_type: min_max
|
| 129 |
+
statistic_name: robodojo_arx_x5
|
| 130 |
+
type: DenormalizePrivateAction
|
| 131 |
+
model_family: dit4dit
|
| 132 |
+
num_trials_per_task: 50
|
| 133 |
+
num_trials_per_task_overrides:
|
| 134 |
+
arrange_largest_number: 25
|
| 135 |
+
arrange_largest_number_random: 25
|
| 136 |
+
fold_clothes: 25
|
| 137 |
+
fold_clothes_random: 25
|
| 138 |
+
hang_mugs: 25
|
| 139 |
+
hang_mugs_random: 25
|
| 140 |
+
make_toast: 25
|
| 141 |
+
make_toast_random: 25
|
| 142 |
+
pack_objects_into_box: 25
|
| 143 |
+
pack_objects_into_box_random: 25
|
| 144 |
+
pour_liquid_into_cup: 25
|
| 145 |
+
pour_liquid_into_cup_random: 25
|
| 146 |
+
push_T: 25
|
| 147 |
+
push_T_random: 25
|
| 148 |
+
sort_nesting_dolls_by_size: 25
|
| 149 |
+
sort_nesting_dolls_by_size_random: 25
|
| 150 |
+
stack_blocks: 25
|
| 151 |
+
stack_blocks_random: 25
|
| 152 |
+
stack_bowls: 25
|
| 153 |
+
stack_bowls_random: 25
|
| 154 |
+
store_laptop_and_headphones: 25
|
| 155 |
+
store_laptop_and_headphones_random: 25
|
| 156 |
+
sweep_blocks: 25
|
| 157 |
+
sweep_blocks_random: 25
|
| 158 |
+
report_kind: robodojo
|
| 159 |
+
task_suite_name: robodojo
|
| 160 |
+
inference_model:
|
| 161 |
+
freeze_vlm_backbone: false
|
| 162 |
+
init_empty_weights: true
|
| 163 |
+
repeated_diffusion_steps: 4
|
| 164 |
+
type: DiT4DiTVLA
|
| 165 |
+
vla_head:
|
| 166 |
+
action_dim: 16
|
| 167 |
+
action_horizon: 16
|
| 168 |
+
action_model_type: DiT-B
|
| 169 |
+
add_pos_embed: true
|
| 170 |
+
diffusion_model_cfg:
|
| 171 |
+
cross_attention_dim: 2048
|
| 172 |
+
dropout: 0.2
|
| 173 |
+
final_dropout: true
|
| 174 |
+
interleave_self_attention: true
|
| 175 |
+
norm_type: ada_norm
|
| 176 |
+
num_layers: 16
|
| 177 |
+
output_dim: 2560
|
| 178 |
+
positional_embeddings: null
|
| 179 |
+
future_action_window_size: 15
|
| 180 |
+
hidden_size: 2560
|
| 181 |
+
max_seq_len: 1024
|
| 182 |
+
noise_beta_alpha: 1.5
|
| 183 |
+
noise_beta_beta: 1.0
|
| 184 |
+
noise_s: 0.999
|
| 185 |
+
num_inference_timesteps: 4
|
| 186 |
+
num_timestep_buckets: 1000
|
| 187 |
+
ori_action_dim: 14
|
| 188 |
+
state_dim: 32
|
| 189 |
+
type: DiT4DiTActionHead
|
| 190 |
+
vlm_backbone:
|
| 191 |
+
base_model: ./checkpoints/Cosmos-Predict2.5-2B
|
| 192 |
+
conditional_frame_timestep: 0.0001
|
| 193 |
+
detach_hidden_states: true
|
| 194 |
+
extract_layer: 17
|
| 195 |
+
fixed_seed: null
|
| 196 |
+
flow_matching_high_sigma_min: null
|
| 197 |
+
flow_matching_high_sigma_ratio: null
|
| 198 |
+
flow_matching_time_distribution: uniform
|
| 199 |
+
frozen_submodules:
|
| 200 |
+
- text_encoder
|
| 201 |
+
- vae
|
| 202 |
+
fsdp_min_num_params: 0
|
| 203 |
+
future_loss_type: flow_matching
|
| 204 |
+
load_pretrained_weights: false
|
| 205 |
+
local_files_only: true
|
| 206 |
+
num_frames_out: 9
|
| 207 |
+
num_inference_steps: 1
|
| 208 |
+
revision: diffusers/base/post-trained
|
| 209 |
+
split_future_frames: true
|
| 210 |
+
torch_dtype: bf16
|
| 211 |
+
trainable: true
|
| 212 |
+
type: Cosmos25Backbone
|
| 213 |
+
model:
|
| 214 |
+
freeze_vlm_backbone: false
|
| 215 |
+
repeated_diffusion_steps: 4
|
| 216 |
+
type: DiT4DiTVLA
|
| 217 |
+
vla_head:
|
| 218 |
+
action_dim: 16
|
| 219 |
+
action_horizon: 16
|
| 220 |
+
action_model_type: DiT-B
|
| 221 |
+
add_pos_embed: true
|
| 222 |
+
diffusion_model_cfg:
|
| 223 |
+
cross_attention_dim: 2048
|
| 224 |
+
dropout: 0.2
|
| 225 |
+
final_dropout: true
|
| 226 |
+
interleave_self_attention: true
|
| 227 |
+
norm_type: ada_norm
|
| 228 |
+
num_layers: 16
|
| 229 |
+
output_dim: 2560
|
| 230 |
+
positional_embeddings: null
|
| 231 |
+
future_action_window_size: 15
|
| 232 |
+
hidden_size: 2560
|
| 233 |
+
max_seq_len: 1024
|
| 234 |
+
noise_beta_alpha: 1.5
|
| 235 |
+
noise_beta_beta: 1.0
|
| 236 |
+
noise_s: 0.999
|
| 237 |
+
num_inference_timesteps: 4
|
| 238 |
+
num_timestep_buckets: 1000
|
| 239 |
+
ori_action_dim: 14
|
| 240 |
+
state_dim: 32
|
| 241 |
+
type: DiT4DiTActionHead
|
| 242 |
+
vlm_backbone:
|
| 243 |
+
base_model: ./checkpoints/Cosmos-Predict2.5-2B
|
| 244 |
+
conditional_frame_timestep: 0.0001
|
| 245 |
+
detach_hidden_states: true
|
| 246 |
+
extract_layer: 17
|
| 247 |
+
fixed_seed: null
|
| 248 |
+
flow_matching_high_sigma_min: null
|
| 249 |
+
flow_matching_high_sigma_ratio: null
|
| 250 |
+
flow_matching_time_distribution: uniform
|
| 251 |
+
frozen_submodules:
|
| 252 |
+
- text_encoder
|
| 253 |
+
- vae
|
| 254 |
+
fsdp_min_num_params: 0
|
| 255 |
+
future_loss_type: flow_matching
|
| 256 |
+
load_pretrained_weights: true
|
| 257 |
+
local_files_only: true
|
| 258 |
+
num_frames_out: 9
|
| 259 |
+
num_inference_steps: 1
|
| 260 |
+
revision: diffusers/base/post-trained
|
| 261 |
+
split_future_frames: true
|
| 262 |
+
torch_dtype: bf16
|
| 263 |
+
trainable: true
|
| 264 |
+
type: Cosmos25Backbone
|
| 265 |
+
runner:
|
| 266 |
+
change_key_name: false
|
| 267 |
+
collator:
|
| 268 |
+
keys:
|
| 269 |
+
- states
|
| 270 |
+
- timestamp
|
| 271 |
+
- images
|
| 272 |
+
- img_masks
|
| 273 |
+
- actions
|
| 274 |
+
- action_masks
|
| 275 |
+
- frame_masks
|
| 276 |
+
- lang_tokens
|
| 277 |
+
- lang_masks
|
| 278 |
+
meta_keys:
|
| 279 |
+
- info
|
| 280 |
+
- stats
|
| 281 |
+
type: DictCollator
|
| 282 |
+
enable_gradient_checkpointing: true
|
| 283 |
+
enable_mixed_precision_training: true
|
| 284 |
+
grad_accumulation_steps: 4
|
| 285 |
+
lr_scheduler:
|
| 286 |
+
min_lr: 5.0e-07
|
| 287 |
+
type: linear-warmup+cosine-decay
|
| 288 |
+
warmup_steps: 2000
|
| 289 |
+
max_epochs: null
|
| 290 |
+
max_grad_norm: 1.0
|
| 291 |
+
max_keep_ckpts: 3
|
| 292 |
+
max_steps: 120000
|
| 293 |
+
metric:
|
| 294 |
+
active_trackers:
|
| 295 |
+
- jsonl
|
| 296 |
+
- wandb
|
| 297 |
+
grad_accumulation_steps: 4
|
| 298 |
+
run_dir: work_dirs
|
| 299 |
+
type: VLAMetric
|
| 300 |
+
window_size: 1
|
| 301 |
+
mixed_precision_dtype: bf16
|
| 302 |
+
optimizer:
|
| 303 |
+
betas:
|
| 304 |
+
- 0.9
|
| 305 |
+
- 0.95
|
| 306 |
+
eps: 1.0e-08
|
| 307 |
+
fused: true
|
| 308 |
+
lr: 1.0e-05
|
| 309 |
+
paramwise_learning_rate:
|
| 310 |
+
vla_head: 0.0001
|
| 311 |
+
vlm_backbone.transformer: 1.0e-05
|
| 312 |
+
type: AdamW
|
| 313 |
+
weight_decay: 1.0e-08
|
| 314 |
+
weight_decay_all_params: true
|
| 315 |
+
pre_fsdp_param_dtype: fp32
|
| 316 |
+
reduce_in_full_precision: false
|
| 317 |
+
sampler: null
|
| 318 |
+
save_iter_interval: 2000
|
| 319 |
+
sharding_strategy: full-shard
|
| 320 |
+
tokenizer:
|
| 321 |
+
model_max_length: 512
|
| 322 |
+
model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
|
| 323 |
+
type: PretrainedTokenizer
|
| 324 |
+
type: FSDPTrainRunner
|
| 325 |
+
seed: 42
|
| 326 |
+
themis:
|
| 327 |
+
ros_server:
|
| 328 |
+
dataset_section: eval
|
| 329 |
+
denormalize_context:
|
| 330 |
+
task_suite_name: robodojo_arx_x5
|
| 331 |
+
device: cuda:0
|
| 332 |
+
enable_mixed_precision: true
|
| 333 |
+
evaluation_reporting:
|
| 334 |
+
result_output_dir: work_dirs/dit4dit_robodojo_eval
|
| 335 |
+
forward_seed: false
|
| 336 |
+
mixed_precision_dtype: bf16
|
| 337 |
+
model_outputs_environment_actions: false
|
| 338 |
+
workers:
|
| 339 |
+
lease_timeout_s: 900.0
|
| 340 |
+
request_timeout_s: 120.0
|
| 341 |
+
startup_timeout_s: 900.0
|
| 342 |
+
runner:
|
| 343 |
+
environment:
|
| 344 |
+
action_mode: joint
|
| 345 |
+
device_id: 1
|
| 346 |
+
env_cfg_type: arx_x5
|
| 347 |
+
headless: true
|
| 348 |
+
robodojo_root: /root/projects/RoboDojo
|
| 349 |
+
save_videos: false
|
| 350 |
+
task_name: all
|
| 351 |
+
type: RoboDojoEnvironment
|
| 352 |
+
episodes_per_task: 50
|
| 353 |
+
episodes_per_task_overrides:
|
| 354 |
+
arrange_largest_number: 25
|
| 355 |
+
arrange_largest_number_random: 25
|
| 356 |
+
fold_clothes: 25
|
| 357 |
+
fold_clothes_random: 25
|
| 358 |
+
hang_mugs: 25
|
| 359 |
+
hang_mugs_random: 25
|
| 360 |
+
make_toast: 25
|
| 361 |
+
make_toast_random: 25
|
| 362 |
+
pack_objects_into_box: 25
|
| 363 |
+
pack_objects_into_box_random: 25
|
| 364 |
+
pour_liquid_into_cup: 25
|
| 365 |
+
pour_liquid_into_cup_random: 25
|
| 366 |
+
push_T: 25
|
| 367 |
+
push_T_random: 25
|
| 368 |
+
sort_nesting_dolls_by_size: 25
|
| 369 |
+
sort_nesting_dolls_by_size_random: 25
|
| 370 |
+
stack_blocks: 25
|
| 371 |
+
stack_blocks_random: 25
|
| 372 |
+
stack_bowls: 25
|
| 373 |
+
stack_bowls_random: 25
|
| 374 |
+
store_laptop_and_headphones: 25
|
| 375 |
+
store_laptop_and_headphones_random: 25
|
| 376 |
+
sweep_blocks: 25
|
| 377 |
+
sweep_blocks_random: 25
|
| 378 |
+
evaluator:
|
| 379 |
+
type: SuccessRateEvaluator
|
| 380 |
+
execute_horizon: 12
|
| 381 |
+
max_episode_steps: 2000
|
| 382 |
+
model_client:
|
| 383 |
+
type: FluxVLAZMQModelClient
|
| 384 |
+
parallel_workers: 1
|
| 385 |
+
seed: 0
|
| 386 |
+
simulator_gpu_ids: null
|
| 387 |
+
stop_on_success: true
|
| 388 |
+
type: EvalRunner
|
| 389 |
+
work_dir: work_dirs/dit4dit_robodojo_eval
|
| 390 |
+
transport:
|
| 391 |
+
host: 127.0.0.1
|
| 392 |
+
image_encoding: rgb8
|
| 393 |
+
image_keys:
|
| 394 |
+
- cam_high
|
| 395 |
+
- cam_left_wrist
|
| 396 |
+
- cam_right_wrist
|
| 397 |
+
port: 5555
|
| 398 |
+
report_service_name: /fluxvla/report_evaluation
|
| 399 |
+
state_keys:
|
| 400 |
+
- states
|
| 401 |
+
timeout_s: 30.0
|
| 402 |
+
unnorm_key: robodojo_arx_x5
|
| 403 |
+
train_dataloader:
|
| 404 |
+
dataset:
|
| 405 |
+
datasets:
|
| 406 |
+
action_dtype: null
|
| 407 |
+
action_key: action
|
| 408 |
+
action_window_size: 16
|
| 409 |
+
data_root_path:
|
| 410 |
+
- /mnt/data/cpfs/users/jikun/robodojo/RoboDojo_lerobot_v21_video
|
| 411 |
+
frame_sample_stride: 2
|
| 412 |
+
frame_window_size: 9
|
| 413 |
+
statistic_name: robodojo_arx_x5
|
| 414 |
+
supervise_terminal_padding: true
|
| 415 |
+
transforms:
|
| 416 |
+
- name_mappings:
|
| 417 |
+
actions:
|
| 418 |
+
- actions
|
| 419 |
+
observation.state:
|
| 420 |
+
- states
|
| 421 |
+
parquet_keys:
|
| 422 |
+
- observation.state
|
| 423 |
+
- timestamp
|
| 424 |
+
- actions
|
| 425 |
+
- info
|
| 426 |
+
- stats
|
| 427 |
+
- action_masks
|
| 428 |
+
type: ProcessParquetInputs
|
| 429 |
+
video_backend: torchcodec
|
| 430 |
+
video_keys:
|
| 431 |
+
- observation.images.cam_high
|
| 432 |
+
- observation.images.cam_left_wrist
|
| 433 |
+
- observation.images.cam_right_wrist
|
| 434 |
+
- input_key: task_description
|
| 435 |
+
remove_input_key: true
|
| 436 |
+
tokenizer:
|
| 437 |
+
model_max_length: 512
|
| 438 |
+
model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
|
| 439 |
+
type: PretrainedTokenizer
|
| 440 |
+
type: ProcessCosmos25Prompt
|
| 441 |
+
- backend: torch
|
| 442 |
+
height: 224
|
| 443 |
+
output_layout: flattened_chw
|
| 444 |
+
scale_divisor: 255.0
|
| 445 |
+
type: ResizeImages
|
| 446 |
+
width: 224
|
| 447 |
+
- combine_view_masks: true
|
| 448 |
+
frame_window_size: 9
|
| 449 |
+
num_views: 3
|
| 450 |
+
tile_direction: horizontal
|
| 451 |
+
type: PrepareVideo
|
| 452 |
+
- backend: torch
|
| 453 |
+
expand_axis: 0
|
| 454 |
+
interleave: true
|
| 455 |
+
keys:
|
| 456 |
+
- states
|
| 457 |
+
target_dims:
|
| 458 |
+
states: 32
|
| 459 |
+
type: SinCosKeys
|
| 460 |
+
- action_dim: 16
|
| 461 |
+
action_key: action
|
| 462 |
+
action_norm_type: min_max
|
| 463 |
+
clip_norm: false
|
| 464 |
+
mark_all_action_steps_valid: true
|
| 465 |
+
norm_type: min_max
|
| 466 |
+
normalization_epsilon: 0.0
|
| 467 |
+
normalize_states: false
|
| 468 |
+
output_dtype: float16
|
| 469 |
+
preserve_input_dtype: true
|
| 470 |
+
state_dim: 32
|
| 471 |
+
state_key: proprio
|
| 472 |
+
state_norm_type: none
|
| 473 |
+
type: NormalizeStatesAndActions
|
| 474 |
+
valid_action_dim: 14
|
| 475 |
+
zero_constant_min_max_dims: true
|
| 476 |
+
type: ParquetDataset
|
| 477 |
+
use_delta: false
|
| 478 |
+
window_start_idx: 0
|
| 479 |
+
name_mappings:
|
| 480 |
+
action:
|
| 481 |
+
- action
|
| 482 |
+
observation.state:
|
| 483 |
+
- proprio
|
| 484 |
+
reshuffle_each_epoch: true
|
| 485 |
+
seed: 42
|
| 486 |
+
shuffle: true
|
| 487 |
+
statistic_keys:
|
| 488 |
+
- observation.state
|
| 489 |
+
- timestamp
|
| 490 |
+
- action
|
| 491 |
+
statistic_name: robodojo_arx_x5
|
| 492 |
+
type: DistributedRepeatingDataset
|
| 493 |
+
per_device_batch_size: 2
|
| 494 |
+
per_device_num_workers: 4
|
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robodojo_arx_x5": {
|
| 3 |
+
"proprio": {
|
| 4 |
+
"mean": [
|
| 5 |
+
-0.20040483290933933,
|
| 6 |
+
0.9260306606167606,
|
| 7 |
+
0.6881890325982686,
|
| 8 |
+
-0.3400483206709066,
|
| 9 |
+
0.06579394446194628,
|
| 10 |
+
0.004003346747695925,
|
| 11 |
+
0.7714465980721269,
|
| 12 |
+
0.1729983421764827,
|
| 13 |
+
0.8224942863743041,
|
| 14 |
+
0.6196512620467081,
|
| 15 |
+
-0.3604178425587031,
|
| 16 |
+
-0.06267070852548702,
|
| 17 |
+
0.0037534706356096253,
|
| 18 |
+
0.7860055662365837
|
| 19 |
+
],
|
| 20 |
+
"std": [
|
| 21 |
+
0.34305506149779086,
|
| 22 |
+
0.88803979292961,
|
| 23 |
+
0.7302414431033704,
|
| 24 |
+
0.6487680382543082,
|
| 25 |
+
0.29890958198694983,
|
| 26 |
+
0.5843008394814946,
|
| 27 |
+
0.343166656637697,
|
| 28 |
+
0.3198980322111088,
|
| 29 |
+
0.8736479484499943,
|
| 30 |
+
0.7135349837518498,
|
| 31 |
+
0.6027223232925302,
|
| 32 |
+
0.2836475903509877,
|
| 33 |
+
0.5368540927401809,
|
| 34 |
+
0.3406560199738384
|
| 35 |
+
],
|
| 36 |
+
"min": [
|
| 37 |
+
-1.4863648414611816,
|
| 38 |
+
-0.2586335241794586,
|
| 39 |
+
-0.06850092858076096,
|
| 40 |
+
-2.2642147541046143,
|
| 41 |
+
-1.4876768589019775,
|
| 42 |
+
-3.0168392658233643,
|
| 43 |
+
-3.212450869184004e-17,
|
| 44 |
+
-1.4924354553222656,
|
| 45 |
+
-0.27809593081474304,
|
| 46 |
+
-0.18774886429309845,
|
| 47 |
+
-2.5354628562927246,
|
| 48 |
+
-3.0663280487060547,
|
| 49 |
+
-3.0486762523651123,
|
| 50 |
+
-3.212450869184004e-17
|
| 51 |
+
],
|
| 52 |
+
"max": [
|
| 53 |
+
1.7537026405334473,
|
| 54 |
+
3.0546703338623047,
|
| 55 |
+
3.8525187969207764,
|
| 56 |
+
2.0974574089050293,
|
| 57 |
+
1.8103265762329102,
|
| 58 |
+
3.1366536617279053,
|
| 59 |
+
1.0,
|
| 60 |
+
1.6732014417648315,
|
| 61 |
+
3.3797459602355957,
|
| 62 |
+
4.252756595611572,
|
| 63 |
+
2.5287232398986816,
|
| 64 |
+
3.1440579891204834,
|
| 65 |
+
3.0381109714508057,
|
| 66 |
+
1.0
|
| 67 |
+
],
|
| 68 |
+
"q01": null,
|
| 69 |
+
"q99": null
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"mean": [
|
| 73 |
+
-0.20044206015317542,
|
| 74 |
+
0.9262120117772524,
|
| 75 |
+
0.6882954361000181,
|
| 76 |
+
-0.34006418745617883,
|
| 77 |
+
0.0658081773254239,
|
| 78 |
+
0.0039689747289930934,
|
| 79 |
+
0.7713835451223375,
|
| 80 |
+
0.1729873784174943,
|
| 81 |
+
0.8228202306896505,
|
| 82 |
+
0.61992379065145,
|
| 83 |
+
-0.36062264651275594,
|
| 84 |
+
-0.06273007512256629,
|
| 85 |
+
0.003626950967936429,
|
| 86 |
+
0.7859185929400508
|
| 87 |
+
],
|
| 88 |
+
"std": [
|
| 89 |
+
0.3430578526958288,
|
| 90 |
+
0.8880320168409441,
|
| 91 |
+
0.7302223166171972,
|
| 92 |
+
0.6488505412449643,
|
| 93 |
+
0.29892352527661153,
|
| 94 |
+
0.5843509710911197,
|
| 95 |
+
0.34319546515299043,
|
| 96 |
+
0.3199443326985692,
|
| 97 |
+
0.8737037084051896,
|
| 98 |
+
0.7136346922036603,
|
| 99 |
+
0.6029010762371366,
|
| 100 |
+
0.2837157953906254,
|
| 101 |
+
0.5371882124069792,
|
| 102 |
+
0.3407070568392383
|
| 103 |
+
],
|
| 104 |
+
"min": [
|
| 105 |
+
-1.4863648414611816,
|
| 106 |
+
-0.2586335241794586,
|
| 107 |
+
-0.06850092858076096,
|
| 108 |
+
-2.2642147541046143,
|
| 109 |
+
-1.4876768589019775,
|
| 110 |
+
-3.0168392658233643,
|
| 111 |
+
-3.212450869184004e-17,
|
| 112 |
+
-1.4924354553222656,
|
| 113 |
+
-0.27809593081474304,
|
| 114 |
+
-0.18774886429309845,
|
| 115 |
+
-2.5354628562927246,
|
| 116 |
+
-3.0663280487060547,
|
| 117 |
+
-3.0486762523651123,
|
| 118 |
+
-3.212450869184004e-17
|
| 119 |
+
],
|
| 120 |
+
"max": [
|
| 121 |
+
1.7537026405334473,
|
| 122 |
+
3.0546703338623047,
|
| 123 |
+
3.8525187969207764,
|
| 124 |
+
2.0974574089050293,
|
| 125 |
+
1.8103265762329102,
|
| 126 |
+
3.1366536617279053,
|
| 127 |
+
1.0,
|
| 128 |
+
1.6732014417648315,
|
| 129 |
+
3.3797459602355957,
|
| 130 |
+
4.252756595611572,
|
| 131 |
+
2.5287232398986816,
|
| 132 |
+
3.1440579891204834,
|
| 133 |
+
3.0381109714508057,
|
| 134 |
+
1.0
|
| 135 |
+
],
|
| 136 |
+
"q01": [
|
| 137 |
+
-1.051365569829941,
|
| 138 |
+
-3.5348887174584814e-14,
|
| 139 |
+
1.741881830823392e-16,
|
| 140 |
+
-1.5984010362625123,
|
| 141 |
+
-0.6003574305772781,
|
| 142 |
+
-1.6678147149085998,
|
| 143 |
+
0.0,
|
| 144 |
+
-0.4509398394823074,
|
| 145 |
+
-2.5859282299029243e-14,
|
| 146 |
+
1.234041714549172e-16,
|
| 147 |
+
-1.64055180311203,
|
| 148 |
+
-1.2633746123313903,
|
| 149 |
+
-1.7645285475254058,
|
| 150 |
+
0.0
|
| 151 |
+
],
|
| 152 |
+
"q99": [
|
| 153 |
+
0.5431358617544174,
|
| 154 |
+
2.495765209197998,
|
| 155 |
+
2.492974226474762,
|
| 156 |
+
1.3241519677639007,
|
| 157 |
+
1.2496635341644287,
|
| 158 |
+
1.7392305016517635,
|
| 159 |
+
1.0,
|
| 160 |
+
1.0814965963363647,
|
| 161 |
+
2.4167031812667843,
|
| 162 |
+
2.3470158338546754,
|
| 163 |
+
1.141731116771698,
|
| 164 |
+
0.5208872479200363,
|
| 165 |
+
1.489715996980667,
|
| 166 |
+
1.0
|
| 167 |
+
]
|
| 168 |
+
},
|
| 169 |
+
"timestamp": {
|
| 170 |
+
"mean": [
|
| 171 |
+
13.704522752718054
|
| 172 |
+
],
|
| 173 |
+
"std": [
|
| 174 |
+
11.04044022225918
|
| 175 |
+
],
|
| 176 |
+
"min": [
|
| 177 |
+
0.0
|
| 178 |
+
],
|
| 179 |
+
"max": [
|
| 180 |
+
61.44
|
| 181 |
+
],
|
| 182 |
+
"q01": null,
|
| 183 |
+
"q99": null
|
| 184 |
+
}
|
| 185 |
+
}
|
| 186 |
+
}
|
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b03a6058f081a6b593c391d9c20e6424d69b8b0916d611dec838128b02508cbb
|
| 3 |
+
size 36854471528
|
|
@@ -0,0 +1,1024 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_ROBODOJO_DATA_ROOT": "./datasets/RoboDojo_lerobot_v21_video",
|
| 3 |
+
"_ROBODOJO_EPISODE_OVERRIDES": {
|
| 4 |
+
"arrange_largest_number": 25,
|
| 5 |
+
"arrange_largest_number_random": 25,
|
| 6 |
+
"fold_clothes": 25,
|
| 7 |
+
"fold_clothes_random": 25,
|
| 8 |
+
"hang_mugs": 25,
|
| 9 |
+
"hang_mugs_random": 25,
|
| 10 |
+
"make_toast": 25,
|
| 11 |
+
"make_toast_random": 25,
|
| 12 |
+
"pack_objects_into_box": 25,
|
| 13 |
+
"pack_objects_into_box_random": 25,
|
| 14 |
+
"pour_liquid_into_cup": 25,
|
| 15 |
+
"pour_liquid_into_cup_random": 25,
|
| 16 |
+
"push_T": 25,
|
| 17 |
+
"push_T_random": 25,
|
| 18 |
+
"sort_nesting_dolls_by_size": 25,
|
| 19 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 20 |
+
"stack_blocks": 25,
|
| 21 |
+
"stack_blocks_random": 25,
|
| 22 |
+
"stack_bowls": 25,
|
| 23 |
+
"stack_bowls_random": 25,
|
| 24 |
+
"store_laptop_and_headphones": 25,
|
| 25 |
+
"store_laptop_and_headphones_random": 25,
|
| 26 |
+
"sweep_blocks": 25,
|
| 27 |
+
"sweep_blocks_random": 25
|
| 28 |
+
},
|
| 29 |
+
"_ROBODOJO_GENERALIZATION_BASE_TASKS": [
|
| 30 |
+
"stack_bowls",
|
| 31 |
+
"push_T",
|
| 32 |
+
"pack_objects_into_box",
|
| 33 |
+
"fold_clothes",
|
| 34 |
+
"hang_mugs",
|
| 35 |
+
"sweep_blocks",
|
| 36 |
+
"pour_liquid_into_cup",
|
| 37 |
+
"make_toast",
|
| 38 |
+
"arrange_largest_number",
|
| 39 |
+
"sort_nesting_dolls_by_size",
|
| 40 |
+
"store_laptop_and_headphones",
|
| 41 |
+
"stack_blocks"
|
| 42 |
+
],
|
| 43 |
+
"_ROBODOJO_STATS": {
|
| 44 |
+
"robodojo_arx_x5": {
|
| 45 |
+
"action": {
|
| 46 |
+
"count": 1859602,
|
| 47 |
+
"max": [
|
| 48 |
+
1.7537026405334473,
|
| 49 |
+
3.0546703338623047,
|
| 50 |
+
3.8525187969207764,
|
| 51 |
+
2.0974574089050293,
|
| 52 |
+
1.8103265762329102,
|
| 53 |
+
3.1366536617279053,
|
| 54 |
+
1.0,
|
| 55 |
+
1.6732014417648315,
|
| 56 |
+
3.3797459602355957,
|
| 57 |
+
4.252756595611572,
|
| 58 |
+
2.5287232398986816,
|
| 59 |
+
3.1440579891204834,
|
| 60 |
+
3.0381109714508057,
|
| 61 |
+
1.0
|
| 62 |
+
],
|
| 63 |
+
"mean": [
|
| 64 |
+
-0.20032191276550293,
|
| 65 |
+
0.925260603427887,
|
| 66 |
+
0.6879700422286987,
|
| 67 |
+
-0.33993399143218994,
|
| 68 |
+
0.06580745428800583,
|
| 69 |
+
0.003984309732913971,
|
| 70 |
+
0.771653950214386,
|
| 71 |
+
0.17281471192836761,
|
| 72 |
+
0.8216421008110046,
|
| 73 |
+
0.6193687319755554,
|
| 74 |
+
-0.3603578805923462,
|
| 75 |
+
-0.06270533800125122,
|
| 76 |
+
0.0036061492282897234,
|
| 77 |
+
0.7855709195137024
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-1.4863648414611816,
|
| 81 |
+
-0.2586335241794586,
|
| 82 |
+
-0.06850092858076096,
|
| 83 |
+
-2.2642147541046143,
|
| 84 |
+
-1.4876768589019775,
|
| 85 |
+
-3.0168392658233643,
|
| 86 |
+
-3.212450869184004e-17,
|
| 87 |
+
-1.4924354553222656,
|
| 88 |
+
-0.27809593081474304,
|
| 89 |
+
-0.18774886429309845,
|
| 90 |
+
-2.5354628562927246,
|
| 91 |
+
-3.0663280487060547,
|
| 92 |
+
-3.0486762523651123,
|
| 93 |
+
-3.212450869184004e-17
|
| 94 |
+
],
|
| 95 |
+
"q01": [
|
| 96 |
+
-1.051365569829941,
|
| 97 |
+
-3.5348887174584814e-14,
|
| 98 |
+
1.741881830823392e-16,
|
| 99 |
+
-1.5984010362625123,
|
| 100 |
+
-0.6003574305772781,
|
| 101 |
+
-1.6678147149085998,
|
| 102 |
+
0.0,
|
| 103 |
+
-0.4509398394823074,
|
| 104 |
+
-2.5859282299029243e-14,
|
| 105 |
+
1.234041714549172e-16,
|
| 106 |
+
-1.64055180311203,
|
| 107 |
+
-1.2633746123313903,
|
| 108 |
+
-1.7645285475254058,
|
| 109 |
+
0.0
|
| 110 |
+
],
|
| 111 |
+
"q99": [
|
| 112 |
+
0.5431358617544174,
|
| 113 |
+
2.495765209197998,
|
| 114 |
+
2.492974226474762,
|
| 115 |
+
1.3241519677639007,
|
| 116 |
+
1.2496635341644287,
|
| 117 |
+
1.7392305016517635,
|
| 118 |
+
1.0,
|
| 119 |
+
1.0814965963363647,
|
| 120 |
+
2.4167031812667843,
|
| 121 |
+
2.3470158338546754,
|
| 122 |
+
1.141731116771698,
|
| 123 |
+
0.5208872479200363,
|
| 124 |
+
1.489715996980667,
|
| 125 |
+
1.0
|
| 126 |
+
],
|
| 127 |
+
"std": [
|
| 128 |
+
0.34360724687576294,
|
| 129 |
+
0.8902974724769592,
|
| 130 |
+
0.7318998575210571,
|
| 131 |
+
0.6505846977233887,
|
| 132 |
+
0.29849204421043396,
|
| 133 |
+
0.5843351483345032,
|
| 134 |
+
0.34186822175979614,
|
| 135 |
+
0.3206902742385864,
|
| 136 |
+
0.8718543648719788,
|
| 137 |
+
0.7120647430419922,
|
| 138 |
+
0.6016045212745667,
|
| 139 |
+
0.28415030241012573,
|
| 140 |
+
0.5370385050773621,
|
| 141 |
+
0.34119123220443726
|
| 142 |
+
]
|
| 143 |
+
},
|
| 144 |
+
"proprio": {
|
| 145 |
+
"count": 1859602,
|
| 146 |
+
"max": [
|
| 147 |
+
1.7537026405334473,
|
| 148 |
+
3.0546703338623047,
|
| 149 |
+
3.8525187969207764,
|
| 150 |
+
2.0974574089050293,
|
| 151 |
+
1.8103265762329102,
|
| 152 |
+
3.1366536617279053,
|
| 153 |
+
1.0,
|
| 154 |
+
1.6732014417648315,
|
| 155 |
+
3.3797459602355957,
|
| 156 |
+
4.252756595611572,
|
| 157 |
+
2.5287232398986816,
|
| 158 |
+
3.1440579891204834,
|
| 159 |
+
3.0381109714508057,
|
| 160 |
+
1.0
|
| 161 |
+
],
|
| 162 |
+
"mean": [
|
| 163 |
+
-0.20028550922870636,
|
| 164 |
+
0.9250829815864563,
|
| 165 |
+
0.6878653764724731,
|
| 166 |
+
-0.3399182856082916,
|
| 167 |
+
0.06579338014125824,
|
| 168 |
+
0.004018673673272133,
|
| 169 |
+
0.7717168927192688,
|
| 170 |
+
0.17282654345035553,
|
| 171 |
+
0.8213191032409668,
|
| 172 |
+
0.6190997958183289,
|
| 173 |
+
-0.3601549565792084,
|
| 174 |
+
-0.06264610588550568,
|
| 175 |
+
0.0037324042059481144,
|
| 176 |
+
0.7856565713882446
|
| 177 |
+
],
|
| 178 |
+
"min": [
|
| 179 |
+
-1.4863648414611816,
|
| 180 |
+
-0.2586335241794586,
|
| 181 |
+
-0.06850092858076096,
|
| 182 |
+
-2.2642147541046143,
|
| 183 |
+
-1.4876768589019775,
|
| 184 |
+
-3.0168392658233643,
|
| 185 |
+
-3.212450869184004e-17,
|
| 186 |
+
-1.4924354553222656,
|
| 187 |
+
-0.27809593081474304,
|
| 188 |
+
-0.18774886429309845,
|
| 189 |
+
-2.5354628562927246,
|
| 190 |
+
-3.0663280487060547,
|
| 191 |
+
-3.0486762523651123,
|
| 192 |
+
-3.212450869184004e-17
|
| 193 |
+
],
|
| 194 |
+
"q01": [
|
| 195 |
+
-1.051365569829941,
|
| 196 |
+
-3.52302449637288e-14,
|
| 197 |
+
1.6996893991849812e-16,
|
| 198 |
+
-1.5984010362625123,
|
| 199 |
+
-0.6003412520885467,
|
| 200 |
+
-1.6678147149085998,
|
| 201 |
+
0.0,
|
| 202 |
+
-0.4500492787361145,
|
| 203 |
+
-2.5859282299029243e-14,
|
| 204 |
+
1.194697284288627e-16,
|
| 205 |
+
-1.6398817586898804,
|
| 206 |
+
-1.263367258310318,
|
| 207 |
+
-1.760098042488098,
|
| 208 |
+
0.0
|
| 209 |
+
],
|
| 210 |
+
"q99": [
|
| 211 |
+
0.5431358617544174,
|
| 212 |
+
2.495765209197998,
|
| 213 |
+
2.492974226474762,
|
| 214 |
+
1.323737324476242,
|
| 215 |
+
1.2496635341644287,
|
| 216 |
+
1.7391636216640465,
|
| 217 |
+
1.0,
|
| 218 |
+
1.0814965963363647,
|
| 219 |
+
2.416655488014221,
|
| 220 |
+
2.346989154815674,
|
| 221 |
+
1.1415718960762022,
|
| 222 |
+
0.5208872479200363,
|
| 223 |
+
1.4889542925357817,
|
| 224 |
+
1.0
|
| 225 |
+
],
|
| 226 |
+
"std": [
|
| 227 |
+
0.34361061453819275,
|
| 228 |
+
0.8903892636299133,
|
| 229 |
+
0.7319481372833252,
|
| 230 |
+
0.6505074501037598,
|
| 231 |
+
0.29847919940948486,
|
| 232 |
+
0.5842824578285217,
|
| 233 |
+
0.34185686707496643,
|
| 234 |
+
0.3206428587436676,
|
| 235 |
+
0.8718962669372559,
|
| 236 |
+
0.7120621204376221,
|
| 237 |
+
0.6014657616615295,
|
| 238 |
+
0.2840825021266937,
|
| 239 |
+
0.5366978049278259,
|
| 240 |
+
0.3415590524673462
|
| 241 |
+
]
|
| 242 |
+
}
|
| 243 |
+
}
|
| 244 |
+
},
|
| 245 |
+
"_action_window_size": 32,
|
| 246 |
+
"_ckpt_root": "./checkpoints",
|
| 247 |
+
"_data_root_paths": [
|
| 248 |
+
"datasets/libero_spatial_no_noops_lerobotv2.1",
|
| 249 |
+
"datasets/libero_object_no_noops_lerobotv2.1",
|
| 250 |
+
"datasets/libero_goal_no_noops_lerobotv2.1",
|
| 251 |
+
"datasets/libero_10_no_noops_lerobotv2.1"
|
| 252 |
+
],
|
| 253 |
+
"_frame_sample_stride": 4,
|
| 254 |
+
"_frame_window_size": 9,
|
| 255 |
+
"_statistic_name": "robodojo_arx_x5",
|
| 256 |
+
"_text_prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
|
| 257 |
+
"_tokenizer": "./checkpoints/fastwam_base_full/tokenizer",
|
| 258 |
+
"eval": {
|
| 259 |
+
"dataset": {
|
| 260 |
+
"state_dtype": "fp32",
|
| 261 |
+
"transforms": [
|
| 262 |
+
{
|
| 263 |
+
"img_keys": [
|
| 264 |
+
"cam_high",
|
| 265 |
+
"cam_left_wrist",
|
| 266 |
+
"cam_right_wrist"
|
| 267 |
+
],
|
| 268 |
+
"type": "ProcessEvalInputs"
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"image_resize_strategy": "resize-naive",
|
| 272 |
+
"input_sizes": [
|
| 273 |
+
[
|
| 274 |
+
3,
|
| 275 |
+
224,
|
| 276 |
+
224
|
| 277 |
+
],
|
| 278 |
+
[
|
| 279 |
+
3,
|
| 280 |
+
224,
|
| 281 |
+
224
|
| 282 |
+
],
|
| 283 |
+
[
|
| 284 |
+
3,
|
| 285 |
+
224,
|
| 286 |
+
224
|
| 287 |
+
]
|
| 288 |
+
],
|
| 289 |
+
"means": [
|
| 290 |
+
[
|
| 291 |
+
127.5,
|
| 292 |
+
127.5,
|
| 293 |
+
127.5
|
| 294 |
+
],
|
| 295 |
+
[
|
| 296 |
+
127.5,
|
| 297 |
+
127.5,
|
| 298 |
+
127.5
|
| 299 |
+
],
|
| 300 |
+
[
|
| 301 |
+
127.5,
|
| 302 |
+
127.5,
|
| 303 |
+
127.5
|
| 304 |
+
]
|
| 305 |
+
],
|
| 306 |
+
"stds": [
|
| 307 |
+
[
|
| 308 |
+
127.5,
|
| 309 |
+
127.5,
|
| 310 |
+
127.5
|
| 311 |
+
],
|
| 312 |
+
[
|
| 313 |
+
127.5,
|
| 314 |
+
127.5,
|
| 315 |
+
127.5
|
| 316 |
+
],
|
| 317 |
+
[
|
| 318 |
+
127.5,
|
| 319 |
+
127.5,
|
| 320 |
+
127.5
|
| 321 |
+
]
|
| 322 |
+
],
|
| 323 |
+
"type": "TransformImage"
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"norm_type": "min_max",
|
| 327 |
+
"stat_key": "proprio",
|
| 328 |
+
"state_dim": 14,
|
| 329 |
+
"type": "StateFromInputs"
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"max_len": 128,
|
| 333 |
+
"prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
|
| 334 |
+
"tokenizer": {
|
| 335 |
+
"model_path": "./checkpoints/fastwam_base_full/tokenizer",
|
| 336 |
+
"type": "PretrainedTokenizer"
|
| 337 |
+
},
|
| 338 |
+
"type": "LiberoPromptFromInputs",
|
| 339 |
+
"use_conversation": false
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"combine_view_masks": true,
|
| 343 |
+
"frame_window_size": 1,
|
| 344 |
+
"num_views": 3,
|
| 345 |
+
"tile_direction": "horizontal",
|
| 346 |
+
"type": "PrepareVideo"
|
| 347 |
+
}
|
| 348 |
+
],
|
| 349 |
+
"type": "RoboDojoEvalDataset"
|
| 350 |
+
},
|
| 351 |
+
"denormalize_action": {
|
| 352 |
+
"action_dim": 14,
|
| 353 |
+
"norm_type": "min_max",
|
| 354 |
+
"statistic_name": "robodojo_arx_x5",
|
| 355 |
+
"type": "DenormalizePrivateAction"
|
| 356 |
+
},
|
| 357 |
+
"model_family": "fastwam",
|
| 358 |
+
"num_trials_per_task": 50,
|
| 359 |
+
"num_trials_per_task_overrides": {
|
| 360 |
+
"arrange_largest_number": 25,
|
| 361 |
+
"arrange_largest_number_random": 25,
|
| 362 |
+
"fold_clothes": 25,
|
| 363 |
+
"fold_clothes_random": 25,
|
| 364 |
+
"hang_mugs": 25,
|
| 365 |
+
"hang_mugs_random": 25,
|
| 366 |
+
"make_toast": 25,
|
| 367 |
+
"make_toast_random": 25,
|
| 368 |
+
"pack_objects_into_box": 25,
|
| 369 |
+
"pack_objects_into_box_random": 25,
|
| 370 |
+
"pour_liquid_into_cup": 25,
|
| 371 |
+
"pour_liquid_into_cup_random": 25,
|
| 372 |
+
"push_T": 25,
|
| 373 |
+
"push_T_random": 25,
|
| 374 |
+
"sort_nesting_dolls_by_size": 25,
|
| 375 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 376 |
+
"stack_blocks": 25,
|
| 377 |
+
"stack_blocks_random": 25,
|
| 378 |
+
"stack_bowls": 25,
|
| 379 |
+
"stack_bowls_random": 25,
|
| 380 |
+
"store_laptop_and_headphones": 25,
|
| 381 |
+
"store_laptop_and_headphones_random": 25,
|
| 382 |
+
"sweep_blocks": 25,
|
| 383 |
+
"sweep_blocks_random": 25
|
| 384 |
+
},
|
| 385 |
+
"report_kind": "robodojo",
|
| 386 |
+
"task_suite_name": "robodojo"
|
| 387 |
+
},
|
| 388 |
+
"eval_dataset": null,
|
| 389 |
+
"inference_model": {
|
| 390 |
+
"action_horizon": 32,
|
| 391 |
+
"action_norm_type": "min_max",
|
| 392 |
+
"frame_window_size": 9,
|
| 393 |
+
"mot_checkpoint_mixed_attn": true,
|
| 394 |
+
"num_inference_steps": 10,
|
| 395 |
+
"num_views": 3,
|
| 396 |
+
"pretrained_name_or_path": "./checkpoints/fastwam_base_full/fastwam_base_full.safetensors",
|
| 397 |
+
"pretrained_skip_prefixes": [
|
| 398 |
+
"vla_head.mot.mixtures.action.action_encoder.",
|
| 399 |
+
"vla_head.mot.mixtures.action.head.",
|
| 400 |
+
"vla_head.proprio_encoder."
|
| 401 |
+
],
|
| 402 |
+
"proprio_dim": 14,
|
| 403 |
+
"torch_dtype": "bf16",
|
| 404 |
+
"type": "FastWAMVLA",
|
| 405 |
+
"vla_head": {
|
| 406 |
+
"action_dit_config": {
|
| 407 |
+
"action_dim": 14,
|
| 408 |
+
"attn_head_dim": 128,
|
| 409 |
+
"eps": 1e-06,
|
| 410 |
+
"ffn_dim": 4096,
|
| 411 |
+
"freq_dim": 256,
|
| 412 |
+
"hidden_dim": 1024,
|
| 413 |
+
"num_heads": 24,
|
| 414 |
+
"num_layers": 30,
|
| 415 |
+
"text_dim": 4096,
|
| 416 |
+
"use_gradient_checkpointing": true
|
| 417 |
+
},
|
| 418 |
+
"action_scheduler": {
|
| 419 |
+
"infer_shift": 5.0,
|
| 420 |
+
"num_train_timesteps": 1000,
|
| 421 |
+
"train_shift": 5.0
|
| 422 |
+
},
|
| 423 |
+
"loss": {
|
| 424 |
+
"lambda_action": 1.0,
|
| 425 |
+
"lambda_video": 1.0
|
| 426 |
+
},
|
| 427 |
+
"type": "FastWAMHead",
|
| 428 |
+
"video_dit_config": {
|
| 429 |
+
"action_conditioned": false,
|
| 430 |
+
"action_dim": 14,
|
| 431 |
+
"action_group_causal_mask_mode": "group_diagonal",
|
| 432 |
+
"attn_head_dim": 128,
|
| 433 |
+
"eps": 1e-06,
|
| 434 |
+
"ffn_dim": 14336,
|
| 435 |
+
"freq_dim": 256,
|
| 436 |
+
"fuse_vae_embedding_in_latents": true,
|
| 437 |
+
"has_image_input": false,
|
| 438 |
+
"hidden_dim": 3072,
|
| 439 |
+
"in_dim": 48,
|
| 440 |
+
"num_heads": 24,
|
| 441 |
+
"num_layers": 30,
|
| 442 |
+
"out_dim": 48,
|
| 443 |
+
"patch_size": [
|
| 444 |
+
1,
|
| 445 |
+
2,
|
| 446 |
+
2
|
| 447 |
+
],
|
| 448 |
+
"require_clip_embedding": false,
|
| 449 |
+
"require_vae_embedding": false,
|
| 450 |
+
"seperated_timestep": true,
|
| 451 |
+
"text_dim": 4096,
|
| 452 |
+
"use_gradient_checkpointing": true,
|
| 453 |
+
"video_attention_mask_mode": "first_frame_causal"
|
| 454 |
+
},
|
| 455 |
+
"video_scheduler": {
|
| 456 |
+
"infer_shift": 5.0,
|
| 457 |
+
"num_train_timesteps": 1000,
|
| 458 |
+
"train_shift": 5.0
|
| 459 |
+
}
|
| 460 |
+
},
|
| 461 |
+
"vlm_backbone": {
|
| 462 |
+
"text_embed_cache_context_len": 128,
|
| 463 |
+
"text_embed_cache_device": "cpu",
|
| 464 |
+
"text_embed_cache_size": 256,
|
| 465 |
+
"type": "Wan22Backbone"
|
| 466 |
+
}
|
| 467 |
+
},
|
| 468 |
+
"model": {
|
| 469 |
+
"action_horizon": 32,
|
| 470 |
+
"action_norm_type": "min_max",
|
| 471 |
+
"frame_window_size": 9,
|
| 472 |
+
"mot_checkpoint_mixed_attn": true,
|
| 473 |
+
"num_inference_steps": 10,
|
| 474 |
+
"num_views": 3,
|
| 475 |
+
"pretrained_name_or_path": "./checkpoints/fastwam_base_full/fastwam_base_full.safetensors",
|
| 476 |
+
"pretrained_skip_prefixes": [
|
| 477 |
+
"vla_head.mot.mixtures.action.action_encoder.",
|
| 478 |
+
"vla_head.mot.mixtures.action.head.",
|
| 479 |
+
"vla_head.proprio_encoder."
|
| 480 |
+
],
|
| 481 |
+
"proprio_dim": 14,
|
| 482 |
+
"torch_dtype": "bf16",
|
| 483 |
+
"type": "FastWAMVLA",
|
| 484 |
+
"vla_head": {
|
| 485 |
+
"action_dit_config": {
|
| 486 |
+
"action_dim": 14,
|
| 487 |
+
"attn_head_dim": 128,
|
| 488 |
+
"eps": 1e-06,
|
| 489 |
+
"ffn_dim": 4096,
|
| 490 |
+
"freq_dim": 256,
|
| 491 |
+
"hidden_dim": 1024,
|
| 492 |
+
"num_heads": 24,
|
| 493 |
+
"num_layers": 30,
|
| 494 |
+
"text_dim": 4096,
|
| 495 |
+
"use_gradient_checkpointing": true
|
| 496 |
+
},
|
| 497 |
+
"action_scheduler": {
|
| 498 |
+
"infer_shift": 5.0,
|
| 499 |
+
"num_train_timesteps": 1000,
|
| 500 |
+
"train_shift": 5.0
|
| 501 |
+
},
|
| 502 |
+
"loss": {
|
| 503 |
+
"lambda_action": 1.0,
|
| 504 |
+
"lambda_video": 1.0
|
| 505 |
+
},
|
| 506 |
+
"type": "FastWAMHead",
|
| 507 |
+
"video_dit_config": {
|
| 508 |
+
"action_conditioned": false,
|
| 509 |
+
"action_dim": 14,
|
| 510 |
+
"action_group_causal_mask_mode": "group_diagonal",
|
| 511 |
+
"attn_head_dim": 128,
|
| 512 |
+
"eps": 1e-06,
|
| 513 |
+
"ffn_dim": 14336,
|
| 514 |
+
"freq_dim": 256,
|
| 515 |
+
"fuse_vae_embedding_in_latents": true,
|
| 516 |
+
"has_image_input": false,
|
| 517 |
+
"hidden_dim": 3072,
|
| 518 |
+
"in_dim": 48,
|
| 519 |
+
"num_heads": 24,
|
| 520 |
+
"num_layers": 30,
|
| 521 |
+
"out_dim": 48,
|
| 522 |
+
"patch_size": [
|
| 523 |
+
1,
|
| 524 |
+
2,
|
| 525 |
+
2
|
| 526 |
+
],
|
| 527 |
+
"require_clip_embedding": false,
|
| 528 |
+
"require_vae_embedding": false,
|
| 529 |
+
"seperated_timestep": true,
|
| 530 |
+
"text_dim": 4096,
|
| 531 |
+
"use_gradient_checkpointing": true,
|
| 532 |
+
"video_attention_mask_mode": "first_frame_causal"
|
| 533 |
+
},
|
| 534 |
+
"video_scheduler": {
|
| 535 |
+
"infer_shift": 5.0,
|
| 536 |
+
"num_train_timesteps": 1000,
|
| 537 |
+
"train_shift": 5.0
|
| 538 |
+
}
|
| 539 |
+
},
|
| 540 |
+
"vlm_backbone": {
|
| 541 |
+
"text_embed_cache_context_len": 128,
|
| 542 |
+
"text_embed_cache_device": "cpu",
|
| 543 |
+
"text_embed_cache_size": 256,
|
| 544 |
+
"type": "Wan22Backbone"
|
| 545 |
+
}
|
| 546 |
+
},
|
| 547 |
+
"runner": {
|
| 548 |
+
"collator": {
|
| 549 |
+
"keys": [
|
| 550 |
+
"states",
|
| 551 |
+
"images",
|
| 552 |
+
"img_masks",
|
| 553 |
+
"actions",
|
| 554 |
+
"action_masks",
|
| 555 |
+
"embodiment_ids",
|
| 556 |
+
"frame_masks",
|
| 557 |
+
"lang_tokens",
|
| 558 |
+
"lang_masks"
|
| 559 |
+
],
|
| 560 |
+
"meta_keys": [
|
| 561 |
+
"task_description",
|
| 562 |
+
"info",
|
| 563 |
+
"stats",
|
| 564 |
+
"timestamp"
|
| 565 |
+
],
|
| 566 |
+
"type": "DictCollator"
|
| 567 |
+
},
|
| 568 |
+
"dataset_sharding_strategy": "blockwise",
|
| 569 |
+
"enable_gradient_checkpointing": false,
|
| 570 |
+
"enable_mixed_precision_training": true,
|
| 571 |
+
"evaluator": {
|
| 572 |
+
"eval_every": 1000,
|
| 573 |
+
"num_inference_steps": 10,
|
| 574 |
+
"save_video": true,
|
| 575 |
+
"seed": 42,
|
| 576 |
+
"type": "training-eval",
|
| 577 |
+
"video_fps": 8
|
| 578 |
+
},
|
| 579 |
+
"fsdp_wrap_policy": "execution-block",
|
| 580 |
+
"grad_accumulation_steps": 1,
|
| 581 |
+
"lr_scheduler": {
|
| 582 |
+
"betas": [
|
| 583 |
+
0.9,
|
| 584 |
+
0.95
|
| 585 |
+
],
|
| 586 |
+
"min_lr_ratio": 1.0,
|
| 587 |
+
"type": "linear-warmup+cosine-decay-min-lr",
|
| 588 |
+
"warmup_ratio": 0.0,
|
| 589 |
+
"weight_decay_style": "uniform"
|
| 590 |
+
},
|
| 591 |
+
"max_epochs": 6,
|
| 592 |
+
"max_grad_norm": 1.0,
|
| 593 |
+
"max_keep_ckpts": 6,
|
| 594 |
+
"max_steps": null,
|
| 595 |
+
"metric": {
|
| 596 |
+
"active_trackers": [
|
| 597 |
+
"jsonl",
|
| 598 |
+
"wandb"
|
| 599 |
+
],
|
| 600 |
+
"grad_accumulation_steps": 1,
|
| 601 |
+
"run_dir": "work_dirs",
|
| 602 |
+
"type": "VLAMetric",
|
| 603 |
+
"window_size": 1
|
| 604 |
+
},
|
| 605 |
+
"mixed_precision_dtype": "bf16",
|
| 606 |
+
"optimizer": {
|
| 607 |
+
"fused": true,
|
| 608 |
+
"lr": 1e-06,
|
| 609 |
+
"type": "AdamW",
|
| 610 |
+
"weight_decay": 0.01
|
| 611 |
+
},
|
| 612 |
+
"reduce_in_full_precision": true,
|
| 613 |
+
"sampler": null,
|
| 614 |
+
"save_epoch_interval": 1,
|
| 615 |
+
"save_iter_interval": 10000,
|
| 616 |
+
"sharding_strategy": "full-shard",
|
| 617 |
+
"type": "FSDPTrainRunner"
|
| 618 |
+
},
|
| 619 |
+
"seed": 42,
|
| 620 |
+
"themis": {
|
| 621 |
+
"ros_server": {
|
| 622 |
+
"dataset_section": "eval",
|
| 623 |
+
"denormalize_context": {
|
| 624 |
+
"task_suite_name": "robodojo_arx_x5"
|
| 625 |
+
},
|
| 626 |
+
"device": "cuda:0",
|
| 627 |
+
"enable_mixed_precision": true,
|
| 628 |
+
"evaluation_reporting": {
|
| 629 |
+
"result_output_dir": "work_dirs/fastwam_robodojo_eval"
|
| 630 |
+
},
|
| 631 |
+
"forward_seed": false,
|
| 632 |
+
"mixed_precision_dtype": "bf16",
|
| 633 |
+
"model_outputs_environment_actions": false,
|
| 634 |
+
"workers": {
|
| 635 |
+
"lease_timeout_s": 900.0,
|
| 636 |
+
"request_timeout_s": 120.0,
|
| 637 |
+
"startup_timeout_s": 900.0
|
| 638 |
+
}
|
| 639 |
+
},
|
| 640 |
+
"runner": {
|
| 641 |
+
"environment": {
|
| 642 |
+
"action_mode": "joint",
|
| 643 |
+
"device_id": 1,
|
| 644 |
+
"env_cfg_type": "arx_x5",
|
| 645 |
+
"headless": true,
|
| 646 |
+
"robodojo_root": "/root/projects/RoboDojo",
|
| 647 |
+
"save_videos": false,
|
| 648 |
+
"task_name": "all",
|
| 649 |
+
"type": "RoboDojoEnvironment"
|
| 650 |
+
},
|
| 651 |
+
"episodes_per_task": 50,
|
| 652 |
+
"episodes_per_task_overrides": {
|
| 653 |
+
"arrange_largest_number": 25,
|
| 654 |
+
"arrange_largest_number_random": 25,
|
| 655 |
+
"fold_clothes": 25,
|
| 656 |
+
"fold_clothes_random": 25,
|
| 657 |
+
"hang_mugs": 25,
|
| 658 |
+
"hang_mugs_random": 25,
|
| 659 |
+
"make_toast": 25,
|
| 660 |
+
"make_toast_random": 25,
|
| 661 |
+
"pack_objects_into_box": 25,
|
| 662 |
+
"pack_objects_into_box_random": 25,
|
| 663 |
+
"pour_liquid_into_cup": 25,
|
| 664 |
+
"pour_liquid_into_cup_random": 25,
|
| 665 |
+
"push_T": 25,
|
| 666 |
+
"push_T_random": 25,
|
| 667 |
+
"sort_nesting_dolls_by_size": 25,
|
| 668 |
+
"sort_nesting_dolls_by_size_random": 25,
|
| 669 |
+
"stack_blocks": 25,
|
| 670 |
+
"stack_blocks_random": 25,
|
| 671 |
+
"stack_bowls": 25,
|
| 672 |
+
"stack_bowls_random": 25,
|
| 673 |
+
"store_laptop_and_headphones": 25,
|
| 674 |
+
"store_laptop_and_headphones_random": 25,
|
| 675 |
+
"sweep_blocks": 25,
|
| 676 |
+
"sweep_blocks_random": 25
|
| 677 |
+
},
|
| 678 |
+
"evaluator": {
|
| 679 |
+
"type": "SuccessRateEvaluator"
|
| 680 |
+
},
|
| 681 |
+
"execute_horizon": 16,
|
| 682 |
+
"max_episode_steps": 2000,
|
| 683 |
+
"model_client": {
|
| 684 |
+
"type": "FluxVLAZMQModelClient"
|
| 685 |
+
},
|
| 686 |
+
"parallel_workers": 1,
|
| 687 |
+
"seed": 0,
|
| 688 |
+
"simulator_gpu_ids": null,
|
| 689 |
+
"stop_on_success": true,
|
| 690 |
+
"type": "EvalRunner",
|
| 691 |
+
"work_dir": "work_dirs/fastwam_robodojo_eval"
|
| 692 |
+
},
|
| 693 |
+
"transport": {
|
| 694 |
+
"host": "127.0.0.1",
|
| 695 |
+
"image_encoding": "rgb8",
|
| 696 |
+
"image_keys": [
|
| 697 |
+
"cam_high",
|
| 698 |
+
"cam_left_wrist",
|
| 699 |
+
"cam_right_wrist"
|
| 700 |
+
],
|
| 701 |
+
"port": 5555,
|
| 702 |
+
"report_service_name": "/fluxvla/report_evaluation",
|
| 703 |
+
"state_keys": [
|
| 704 |
+
"states"
|
| 705 |
+
],
|
| 706 |
+
"timeout_s": 30.0,
|
| 707 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 708 |
+
}
|
| 709 |
+
},
|
| 710 |
+
"train_dataloader": {
|
| 711 |
+
"dataset": {
|
| 712 |
+
"dataset_statistics": {
|
| 713 |
+
"robodojo_arx_x5": {
|
| 714 |
+
"action": {
|
| 715 |
+
"count": 1859602,
|
| 716 |
+
"max": [
|
| 717 |
+
1.7537026405334473,
|
| 718 |
+
3.0546703338623047,
|
| 719 |
+
3.8525187969207764,
|
| 720 |
+
2.0974574089050293,
|
| 721 |
+
1.8103265762329102,
|
| 722 |
+
3.1366536617279053,
|
| 723 |
+
1.0,
|
| 724 |
+
1.6732014417648315,
|
| 725 |
+
3.3797459602355957,
|
| 726 |
+
4.252756595611572,
|
| 727 |
+
2.5287232398986816,
|
| 728 |
+
3.1440579891204834,
|
| 729 |
+
3.0381109714508057,
|
| 730 |
+
1.0
|
| 731 |
+
],
|
| 732 |
+
"mean": [
|
| 733 |
+
-0.20032191276550293,
|
| 734 |
+
0.925260603427887,
|
| 735 |
+
0.6879700422286987,
|
| 736 |
+
-0.33993399143218994,
|
| 737 |
+
0.06580745428800583,
|
| 738 |
+
0.003984309732913971,
|
| 739 |
+
0.771653950214386,
|
| 740 |
+
0.17281471192836761,
|
| 741 |
+
0.8216421008110046,
|
| 742 |
+
0.6193687319755554,
|
| 743 |
+
-0.3603578805923462,
|
| 744 |
+
-0.06270533800125122,
|
| 745 |
+
0.0036061492282897234,
|
| 746 |
+
0.7855709195137024
|
| 747 |
+
],
|
| 748 |
+
"min": [
|
| 749 |
+
-1.4863648414611816,
|
| 750 |
+
-0.2586335241794586,
|
| 751 |
+
-0.06850092858076096,
|
| 752 |
+
-2.2642147541046143,
|
| 753 |
+
-1.4876768589019775,
|
| 754 |
+
-3.0168392658233643,
|
| 755 |
+
-3.212450869184004e-17,
|
| 756 |
+
-1.4924354553222656,
|
| 757 |
+
-0.27809593081474304,
|
| 758 |
+
-0.18774886429309845,
|
| 759 |
+
-2.5354628562927246,
|
| 760 |
+
-3.0663280487060547,
|
| 761 |
+
-3.0486762523651123,
|
| 762 |
+
-3.212450869184004e-17
|
| 763 |
+
],
|
| 764 |
+
"q01": [
|
| 765 |
+
-1.051365569829941,
|
| 766 |
+
-3.5348887174584814e-14,
|
| 767 |
+
1.741881830823392e-16,
|
| 768 |
+
-1.5984010362625123,
|
| 769 |
+
-0.6003574305772781,
|
| 770 |
+
-1.6678147149085998,
|
| 771 |
+
0.0,
|
| 772 |
+
-0.4509398394823074,
|
| 773 |
+
-2.5859282299029243e-14,
|
| 774 |
+
1.234041714549172e-16,
|
| 775 |
+
-1.64055180311203,
|
| 776 |
+
-1.2633746123313903,
|
| 777 |
+
-1.7645285475254058,
|
| 778 |
+
0.0
|
| 779 |
+
],
|
| 780 |
+
"q99": [
|
| 781 |
+
0.5431358617544174,
|
| 782 |
+
2.495765209197998,
|
| 783 |
+
2.492974226474762,
|
| 784 |
+
1.3241519677639007,
|
| 785 |
+
1.2496635341644287,
|
| 786 |
+
1.7392305016517635,
|
| 787 |
+
1.0,
|
| 788 |
+
1.0814965963363647,
|
| 789 |
+
2.4167031812667843,
|
| 790 |
+
2.3470158338546754,
|
| 791 |
+
1.141731116771698,
|
| 792 |
+
0.5208872479200363,
|
| 793 |
+
1.489715996980667,
|
| 794 |
+
1.0
|
| 795 |
+
],
|
| 796 |
+
"std": [
|
| 797 |
+
0.34360724687576294,
|
| 798 |
+
0.8902974724769592,
|
| 799 |
+
0.7318998575210571,
|
| 800 |
+
0.6505846977233887,
|
| 801 |
+
0.29849204421043396,
|
| 802 |
+
0.5843351483345032,
|
| 803 |
+
0.34186822175979614,
|
| 804 |
+
0.3206902742385864,
|
| 805 |
+
0.8718543648719788,
|
| 806 |
+
0.7120647430419922,
|
| 807 |
+
0.6016045212745667,
|
| 808 |
+
0.28415030241012573,
|
| 809 |
+
0.5370385050773621,
|
| 810 |
+
0.34119123220443726
|
| 811 |
+
]
|
| 812 |
+
},
|
| 813 |
+
"proprio": {
|
| 814 |
+
"count": 1859602,
|
| 815 |
+
"max": [
|
| 816 |
+
1.7537026405334473,
|
| 817 |
+
3.0546703338623047,
|
| 818 |
+
3.8525187969207764,
|
| 819 |
+
2.0974574089050293,
|
| 820 |
+
1.8103265762329102,
|
| 821 |
+
3.1366536617279053,
|
| 822 |
+
1.0,
|
| 823 |
+
1.6732014417648315,
|
| 824 |
+
3.3797459602355957,
|
| 825 |
+
4.252756595611572,
|
| 826 |
+
2.5287232398986816,
|
| 827 |
+
3.1440579891204834,
|
| 828 |
+
3.0381109714508057,
|
| 829 |
+
1.0
|
| 830 |
+
],
|
| 831 |
+
"mean": [
|
| 832 |
+
-0.20028550922870636,
|
| 833 |
+
0.9250829815864563,
|
| 834 |
+
0.6878653764724731,
|
| 835 |
+
-0.3399182856082916,
|
| 836 |
+
0.06579338014125824,
|
| 837 |
+
0.004018673673272133,
|
| 838 |
+
0.7717168927192688,
|
| 839 |
+
0.17282654345035553,
|
| 840 |
+
0.8213191032409668,
|
| 841 |
+
0.6190997958183289,
|
| 842 |
+
-0.3601549565792084,
|
| 843 |
+
-0.06264610588550568,
|
| 844 |
+
0.0037324042059481144,
|
| 845 |
+
0.7856565713882446
|
| 846 |
+
],
|
| 847 |
+
"min": [
|
| 848 |
+
-1.4863648414611816,
|
| 849 |
+
-0.2586335241794586,
|
| 850 |
+
-0.06850092858076096,
|
| 851 |
+
-2.2642147541046143,
|
| 852 |
+
-1.4876768589019775,
|
| 853 |
+
-3.0168392658233643,
|
| 854 |
+
-3.212450869184004e-17,
|
| 855 |
+
-1.4924354553222656,
|
| 856 |
+
-0.27809593081474304,
|
| 857 |
+
-0.18774886429309845,
|
| 858 |
+
-2.5354628562927246,
|
| 859 |
+
-3.0663280487060547,
|
| 860 |
+
-3.0486762523651123,
|
| 861 |
+
-3.212450869184004e-17
|
| 862 |
+
],
|
| 863 |
+
"q01": [
|
| 864 |
+
-1.051365569829941,
|
| 865 |
+
-3.52302449637288e-14,
|
| 866 |
+
1.6996893991849812e-16,
|
| 867 |
+
-1.5984010362625123,
|
| 868 |
+
-0.6003412520885467,
|
| 869 |
+
-1.6678147149085998,
|
| 870 |
+
0.0,
|
| 871 |
+
-0.4500492787361145,
|
| 872 |
+
-2.5859282299029243e-14,
|
| 873 |
+
1.194697284288627e-16,
|
| 874 |
+
-1.6398817586898804,
|
| 875 |
+
-1.263367258310318,
|
| 876 |
+
-1.760098042488098,
|
| 877 |
+
0.0
|
| 878 |
+
],
|
| 879 |
+
"q99": [
|
| 880 |
+
0.5431358617544174,
|
| 881 |
+
2.495765209197998,
|
| 882 |
+
2.492974226474762,
|
| 883 |
+
1.323737324476242,
|
| 884 |
+
1.2496635341644287,
|
| 885 |
+
1.7391636216640465,
|
| 886 |
+
1.0,
|
| 887 |
+
1.0814965963363647,
|
| 888 |
+
2.416655488014221,
|
| 889 |
+
2.346989154815674,
|
| 890 |
+
1.1415718960762022,
|
| 891 |
+
0.5208872479200363,
|
| 892 |
+
1.4889542925357817,
|
| 893 |
+
1.0
|
| 894 |
+
],
|
| 895 |
+
"std": [
|
| 896 |
+
0.34361061453819275,
|
| 897 |
+
0.8903892636299133,
|
| 898 |
+
0.7319481372833252,
|
| 899 |
+
0.6505074501037598,
|
| 900 |
+
0.29847919940948486,
|
| 901 |
+
0.5842824578285217,
|
| 902 |
+
0.34185686707496643,
|
| 903 |
+
0.3206428587436676,
|
| 904 |
+
0.8718962669372559,
|
| 905 |
+
0.7120621204376221,
|
| 906 |
+
0.6014657616615295,
|
| 907 |
+
0.2840825021266937,
|
| 908 |
+
0.5366978049278259,
|
| 909 |
+
0.3415590524673462
|
| 910 |
+
]
|
| 911 |
+
}
|
| 912 |
+
}
|
| 913 |
+
},
|
| 914 |
+
"datasets": {
|
| 915 |
+
"action_key": "action",
|
| 916 |
+
"action_window_size": 32,
|
| 917 |
+
"data_root_path": [
|
| 918 |
+
"./datasets/RoboDojo_lerobot_v21_video"
|
| 919 |
+
],
|
| 920 |
+
"frame_sample_stride": 4,
|
| 921 |
+
"frame_window_size": 9,
|
| 922 |
+
"statistic_name": "robodojo_arx_x5",
|
| 923 |
+
"supervise_terminal_padding": true,
|
| 924 |
+
"transforms": [
|
| 925 |
+
{
|
| 926 |
+
"embodiment_id": 0,
|
| 927 |
+
"name_mappings": {
|
| 928 |
+
"actions": [
|
| 929 |
+
"actions"
|
| 930 |
+
],
|
| 931 |
+
"observation.state": [
|
| 932 |
+
"states"
|
| 933 |
+
]
|
| 934 |
+
},
|
| 935 |
+
"parquet_keys": [
|
| 936 |
+
"observation.state",
|
| 937 |
+
"timestamp",
|
| 938 |
+
"actions",
|
| 939 |
+
"info",
|
| 940 |
+
"stats",
|
| 941 |
+
"action_masks"
|
| 942 |
+
],
|
| 943 |
+
"type": "ProcessParquetInputs",
|
| 944 |
+
"video_backend": "torchcodec",
|
| 945 |
+
"video_keys": [
|
| 946 |
+
"observation.images.cam_high",
|
| 947 |
+
"observation.images.cam_left_wrist",
|
| 948 |
+
"observation.images.cam_right_wrist"
|
| 949 |
+
]
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"backend": "torchvision",
|
| 953 |
+
"height": 224,
|
| 954 |
+
"scale_to_unit_interval": true,
|
| 955 |
+
"type": "ResizeImages",
|
| 956 |
+
"width": 224
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"means": [
|
| 960 |
+
0.5,
|
| 961 |
+
0.5,
|
| 962 |
+
0.5
|
| 963 |
+
],
|
| 964 |
+
"stds": [
|
| 965 |
+
0.5,
|
| 966 |
+
0.5,
|
| 967 |
+
0.5
|
| 968 |
+
],
|
| 969 |
+
"type": "NormalizeImages"
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"action_dim": 14,
|
| 973 |
+
"action_key": "action",
|
| 974 |
+
"norm_type": "min_max",
|
| 975 |
+
"output_dtype": "float32",
|
| 976 |
+
"state_dim": 14,
|
| 977 |
+
"state_key": "proprio",
|
| 978 |
+
"type": "NormalizeStatesAndActions"
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"combine_view_masks": true,
|
| 982 |
+
"frame_window_size": 9,
|
| 983 |
+
"num_views": 3,
|
| 984 |
+
"tile_direction": "horizontal",
|
| 985 |
+
"type": "PrepareVideo"
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"max_len": 128,
|
| 989 |
+
"prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
|
| 990 |
+
"tokenizer": {
|
| 991 |
+
"model_path": "./checkpoints/fastwam_base_full/tokenizer",
|
| 992 |
+
"type": "PretrainedTokenizer"
|
| 993 |
+
},
|
| 994 |
+
"type": "LiberoPromptFromInputs",
|
| 995 |
+
"use_conversation": false
|
| 996 |
+
}
|
| 997 |
+
],
|
| 998 |
+
"type": "ParquetDataset",
|
| 999 |
+
"use_delta": false,
|
| 1000 |
+
"window_start_idx": 0
|
| 1001 |
+
},
|
| 1002 |
+
"name_mappings": {
|
| 1003 |
+
"action": [
|
| 1004 |
+
"action"
|
| 1005 |
+
],
|
| 1006 |
+
"observation.state": [
|
| 1007 |
+
"proprio"
|
| 1008 |
+
]
|
| 1009 |
+
},
|
| 1010 |
+
"reshuffle_each_epoch": true,
|
| 1011 |
+
"seed": 42,
|
| 1012 |
+
"statistic_keys": [
|
| 1013 |
+
"observation.state",
|
| 1014 |
+
"timestamp",
|
| 1015 |
+
"action"
|
| 1016 |
+
],
|
| 1017 |
+
"statistic_name": "robodojo_arx_x5",
|
| 1018 |
+
"type": "DistributedRepeatingDataset"
|
| 1019 |
+
},
|
| 1020 |
+
"per_device_batch_size": 2,
|
| 1021 |
+
"per_device_num_workers": 8
|
| 1022 |
+
},
|
| 1023 |
+
"val_dataloader": null
|
| 1024 |
+
}
|
|
@@ -0,0 +1,880 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ROBODOJO_DATA_ROOT: ./datasets/RoboDojo_lerobot_v21_video
|
| 2 |
+
_ROBODOJO_EPISODE_OVERRIDES:
|
| 3 |
+
arrange_largest_number: 25
|
| 4 |
+
arrange_largest_number_random: 25
|
| 5 |
+
fold_clothes: 25
|
| 6 |
+
fold_clothes_random: 25
|
| 7 |
+
hang_mugs: 25
|
| 8 |
+
hang_mugs_random: 25
|
| 9 |
+
make_toast: 25
|
| 10 |
+
make_toast_random: 25
|
| 11 |
+
pack_objects_into_box: 25
|
| 12 |
+
pack_objects_into_box_random: 25
|
| 13 |
+
pour_liquid_into_cup: 25
|
| 14 |
+
pour_liquid_into_cup_random: 25
|
| 15 |
+
push_T: 25
|
| 16 |
+
push_T_random: 25
|
| 17 |
+
sort_nesting_dolls_by_size: 25
|
| 18 |
+
sort_nesting_dolls_by_size_random: 25
|
| 19 |
+
stack_blocks: 25
|
| 20 |
+
stack_blocks_random: 25
|
| 21 |
+
stack_bowls: 25
|
| 22 |
+
stack_bowls_random: 25
|
| 23 |
+
store_laptop_and_headphones: 25
|
| 24 |
+
store_laptop_and_headphones_random: 25
|
| 25 |
+
sweep_blocks: 25
|
| 26 |
+
sweep_blocks_random: 25
|
| 27 |
+
_ROBODOJO_GENERALIZATION_BASE_TASKS:
|
| 28 |
+
- stack_bowls
|
| 29 |
+
- push_T
|
| 30 |
+
- pack_objects_into_box
|
| 31 |
+
- fold_clothes
|
| 32 |
+
- hang_mugs
|
| 33 |
+
- sweep_blocks
|
| 34 |
+
- pour_liquid_into_cup
|
| 35 |
+
- make_toast
|
| 36 |
+
- arrange_largest_number
|
| 37 |
+
- sort_nesting_dolls_by_size
|
| 38 |
+
- store_laptop_and_headphones
|
| 39 |
+
- stack_blocks
|
| 40 |
+
_ROBODOJO_STATS:
|
| 41 |
+
robodojo_arx_x5:
|
| 42 |
+
action:
|
| 43 |
+
count: 1859602
|
| 44 |
+
max:
|
| 45 |
+
- 1.7537026405334473
|
| 46 |
+
- 3.0546703338623047
|
| 47 |
+
- 3.8525187969207764
|
| 48 |
+
- 2.0974574089050293
|
| 49 |
+
- 1.8103265762329102
|
| 50 |
+
- 3.1366536617279053
|
| 51 |
+
- 1.0
|
| 52 |
+
- 1.6732014417648315
|
| 53 |
+
- 3.3797459602355957
|
| 54 |
+
- 4.252756595611572
|
| 55 |
+
- 2.5287232398986816
|
| 56 |
+
- 3.1440579891204834
|
| 57 |
+
- 3.0381109714508057
|
| 58 |
+
- 1.0
|
| 59 |
+
mean:
|
| 60 |
+
- -0.20032191276550293
|
| 61 |
+
- 0.925260603427887
|
| 62 |
+
- 0.6879700422286987
|
| 63 |
+
- -0.33993399143218994
|
| 64 |
+
- 0.06580745428800583
|
| 65 |
+
- 0.003984309732913971
|
| 66 |
+
- 0.771653950214386
|
| 67 |
+
- 0.17281471192836761
|
| 68 |
+
- 0.8216421008110046
|
| 69 |
+
- 0.6193687319755554
|
| 70 |
+
- -0.3603578805923462
|
| 71 |
+
- -0.06270533800125122
|
| 72 |
+
- 0.0036061492282897234
|
| 73 |
+
- 0.7855709195137024
|
| 74 |
+
min:
|
| 75 |
+
- -1.4863648414611816
|
| 76 |
+
- -0.2586335241794586
|
| 77 |
+
- -0.06850092858076096
|
| 78 |
+
- -2.2642147541046143
|
| 79 |
+
- -1.4876768589019775
|
| 80 |
+
- -3.0168392658233643
|
| 81 |
+
- -3.212450869184004e-17
|
| 82 |
+
- -1.4924354553222656
|
| 83 |
+
- -0.27809593081474304
|
| 84 |
+
- -0.18774886429309845
|
| 85 |
+
- -2.5354628562927246
|
| 86 |
+
- -3.0663280487060547
|
| 87 |
+
- -3.0486762523651123
|
| 88 |
+
- -3.212450869184004e-17
|
| 89 |
+
q01:
|
| 90 |
+
- -1.051365569829941
|
| 91 |
+
- -3.5348887174584814e-14
|
| 92 |
+
- 1.741881830823392e-16
|
| 93 |
+
- -1.5984010362625123
|
| 94 |
+
- -0.6003574305772781
|
| 95 |
+
- -1.6678147149085998
|
| 96 |
+
- 0.0
|
| 97 |
+
- -0.4509398394823074
|
| 98 |
+
- -2.5859282299029243e-14
|
| 99 |
+
- 1.234041714549172e-16
|
| 100 |
+
- -1.64055180311203
|
| 101 |
+
- -1.2633746123313903
|
| 102 |
+
- -1.7645285475254058
|
| 103 |
+
- 0.0
|
| 104 |
+
q99:
|
| 105 |
+
- 0.5431358617544174
|
| 106 |
+
- 2.495765209197998
|
| 107 |
+
- 2.492974226474762
|
| 108 |
+
- 1.3241519677639007
|
| 109 |
+
- 1.2496635341644287
|
| 110 |
+
- 1.7392305016517635
|
| 111 |
+
- 1.0
|
| 112 |
+
- 1.0814965963363647
|
| 113 |
+
- 2.4167031812667843
|
| 114 |
+
- 2.3470158338546754
|
| 115 |
+
- 1.141731116771698
|
| 116 |
+
- 0.5208872479200363
|
| 117 |
+
- 1.489715996980667
|
| 118 |
+
- 1.0
|
| 119 |
+
std:
|
| 120 |
+
- 0.34360724687576294
|
| 121 |
+
- 0.8902974724769592
|
| 122 |
+
- 0.7318998575210571
|
| 123 |
+
- 0.6505846977233887
|
| 124 |
+
- 0.29849204421043396
|
| 125 |
+
- 0.5843351483345032
|
| 126 |
+
- 0.34186822175979614
|
| 127 |
+
- 0.3206902742385864
|
| 128 |
+
- 0.8718543648719788
|
| 129 |
+
- 0.7120647430419922
|
| 130 |
+
- 0.6016045212745667
|
| 131 |
+
- 0.28415030241012573
|
| 132 |
+
- 0.5370385050773621
|
| 133 |
+
- 0.34119123220443726
|
| 134 |
+
proprio:
|
| 135 |
+
count: 1859602
|
| 136 |
+
max:
|
| 137 |
+
- 1.7537026405334473
|
| 138 |
+
- 3.0546703338623047
|
| 139 |
+
- 3.8525187969207764
|
| 140 |
+
- 2.0974574089050293
|
| 141 |
+
- 1.8103265762329102
|
| 142 |
+
- 3.1366536617279053
|
| 143 |
+
- 1.0
|
| 144 |
+
- 1.6732014417648315
|
| 145 |
+
- 3.3797459602355957
|
| 146 |
+
- 4.252756595611572
|
| 147 |
+
- 2.5287232398986816
|
| 148 |
+
- 3.1440579891204834
|
| 149 |
+
- 3.0381109714508057
|
| 150 |
+
- 1.0
|
| 151 |
+
mean:
|
| 152 |
+
- -0.20028550922870636
|
| 153 |
+
- 0.9250829815864563
|
| 154 |
+
- 0.6878653764724731
|
| 155 |
+
- -0.3399182856082916
|
| 156 |
+
- 0.06579338014125824
|
| 157 |
+
- 0.004018673673272133
|
| 158 |
+
- 0.7717168927192688
|
| 159 |
+
- 0.17282654345035553
|
| 160 |
+
- 0.8213191032409668
|
| 161 |
+
- 0.6190997958183289
|
| 162 |
+
- -0.3601549565792084
|
| 163 |
+
- -0.06264610588550568
|
| 164 |
+
- 0.0037324042059481144
|
| 165 |
+
- 0.7856565713882446
|
| 166 |
+
min:
|
| 167 |
+
- -1.4863648414611816
|
| 168 |
+
- -0.2586335241794586
|
| 169 |
+
- -0.06850092858076096
|
| 170 |
+
- -2.2642147541046143
|
| 171 |
+
- -1.4876768589019775
|
| 172 |
+
- -3.0168392658233643
|
| 173 |
+
- -3.212450869184004e-17
|
| 174 |
+
- -1.4924354553222656
|
| 175 |
+
- -0.27809593081474304
|
| 176 |
+
- -0.18774886429309845
|
| 177 |
+
- -2.5354628562927246
|
| 178 |
+
- -3.0663280487060547
|
| 179 |
+
- -3.0486762523651123
|
| 180 |
+
- -3.212450869184004e-17
|
| 181 |
+
q01:
|
| 182 |
+
- -1.051365569829941
|
| 183 |
+
- -3.52302449637288e-14
|
| 184 |
+
- 1.6996893991849812e-16
|
| 185 |
+
- -1.5984010362625123
|
| 186 |
+
- -0.6003412520885467
|
| 187 |
+
- -1.6678147149085998
|
| 188 |
+
- 0.0
|
| 189 |
+
- -0.4500492787361145
|
| 190 |
+
- -2.5859282299029243e-14
|
| 191 |
+
- 1.194697284288627e-16
|
| 192 |
+
- -1.6398817586898804
|
| 193 |
+
- -1.263367258310318
|
| 194 |
+
- -1.760098042488098
|
| 195 |
+
- 0.0
|
| 196 |
+
q99:
|
| 197 |
+
- 0.5431358617544174
|
| 198 |
+
- 2.495765209197998
|
| 199 |
+
- 2.492974226474762
|
| 200 |
+
- 1.323737324476242
|
| 201 |
+
- 1.2496635341644287
|
| 202 |
+
- 1.7391636216640465
|
| 203 |
+
- 1.0
|
| 204 |
+
- 1.0814965963363647
|
| 205 |
+
- 2.416655488014221
|
| 206 |
+
- 2.346989154815674
|
| 207 |
+
- 1.1415718960762022
|
| 208 |
+
- 0.5208872479200363
|
| 209 |
+
- 1.4889542925357817
|
| 210 |
+
- 1.0
|
| 211 |
+
std:
|
| 212 |
+
- 0.34361061453819275
|
| 213 |
+
- 0.8903892636299133
|
| 214 |
+
- 0.7319481372833252
|
| 215 |
+
- 0.6505074501037598
|
| 216 |
+
- 0.29847919940948486
|
| 217 |
+
- 0.5842824578285217
|
| 218 |
+
- 0.34185686707496643
|
| 219 |
+
- 0.3206428587436676
|
| 220 |
+
- 0.8718962669372559
|
| 221 |
+
- 0.7120621204376221
|
| 222 |
+
- 0.6014657616615295
|
| 223 |
+
- 0.2840825021266937
|
| 224 |
+
- 0.5366978049278259
|
| 225 |
+
- 0.3415590524673462
|
| 226 |
+
_action_window_size: 32
|
| 227 |
+
_ckpt_root: ./checkpoints
|
| 228 |
+
_data_root_paths:
|
| 229 |
+
- datasets/libero_spatial_no_noops_lerobotv2.1
|
| 230 |
+
- datasets/libero_object_no_noops_lerobotv2.1
|
| 231 |
+
- datasets/libero_goal_no_noops_lerobotv2.1
|
| 232 |
+
- datasets/libero_10_no_noops_lerobotv2.1
|
| 233 |
+
_frame_sample_stride: 4
|
| 234 |
+
_frame_window_size: 9
|
| 235 |
+
_statistic_name: robodojo_arx_x5
|
| 236 |
+
_text_prompt_template: 'A video recorded from a robot''s point of view executing the
|
| 237 |
+
following instruction: {task}'
|
| 238 |
+
_tokenizer: ./checkpoints/fastwam_base_full/tokenizer
|
| 239 |
+
eval:
|
| 240 |
+
dataset:
|
| 241 |
+
state_dtype: fp32
|
| 242 |
+
transforms:
|
| 243 |
+
- img_keys:
|
| 244 |
+
- cam_high
|
| 245 |
+
- cam_left_wrist
|
| 246 |
+
- cam_right_wrist
|
| 247 |
+
type: ProcessEvalInputs
|
| 248 |
+
- image_resize_strategy: resize-naive
|
| 249 |
+
input_sizes:
|
| 250 |
+
- - 3
|
| 251 |
+
- 224
|
| 252 |
+
- 224
|
| 253 |
+
- - 3
|
| 254 |
+
- 224
|
| 255 |
+
- 224
|
| 256 |
+
- - 3
|
| 257 |
+
- 224
|
| 258 |
+
- 224
|
| 259 |
+
means:
|
| 260 |
+
- - 127.5
|
| 261 |
+
- 127.5
|
| 262 |
+
- 127.5
|
| 263 |
+
- - 127.5
|
| 264 |
+
- 127.5
|
| 265 |
+
- 127.5
|
| 266 |
+
- - 127.5
|
| 267 |
+
- 127.5
|
| 268 |
+
- 127.5
|
| 269 |
+
stds:
|
| 270 |
+
- - 127.5
|
| 271 |
+
- 127.5
|
| 272 |
+
- 127.5
|
| 273 |
+
- - 127.5
|
| 274 |
+
- 127.5
|
| 275 |
+
- 127.5
|
| 276 |
+
- - 127.5
|
| 277 |
+
- 127.5
|
| 278 |
+
- 127.5
|
| 279 |
+
type: TransformImage
|
| 280 |
+
- norm_type: min_max
|
| 281 |
+
stat_key: proprio
|
| 282 |
+
state_dim: 14
|
| 283 |
+
type: StateFromInputs
|
| 284 |
+
- max_len: 128
|
| 285 |
+
prompt_template: 'A video recorded from a robot''s point of view executing the
|
| 286 |
+
following instruction: {task}'
|
| 287 |
+
tokenizer:
|
| 288 |
+
model_path: ./checkpoints/fastwam_base_full/tokenizer
|
| 289 |
+
type: PretrainedTokenizer
|
| 290 |
+
type: LiberoPromptFromInputs
|
| 291 |
+
use_conversation: false
|
| 292 |
+
- combine_view_masks: true
|
| 293 |
+
frame_window_size: 1
|
| 294 |
+
num_views: 3
|
| 295 |
+
tile_direction: horizontal
|
| 296 |
+
type: PrepareVideo
|
| 297 |
+
type: RoboDojoEvalDataset
|
| 298 |
+
denormalize_action:
|
| 299 |
+
action_dim: 14
|
| 300 |
+
norm_type: min_max
|
| 301 |
+
statistic_name: robodojo_arx_x5
|
| 302 |
+
type: DenormalizePrivateAction
|
| 303 |
+
model_family: fastwam
|
| 304 |
+
num_trials_per_task: 50
|
| 305 |
+
num_trials_per_task_overrides:
|
| 306 |
+
arrange_largest_number: 25
|
| 307 |
+
arrange_largest_number_random: 25
|
| 308 |
+
fold_clothes: 25
|
| 309 |
+
fold_clothes_random: 25
|
| 310 |
+
hang_mugs: 25
|
| 311 |
+
hang_mugs_random: 25
|
| 312 |
+
make_toast: 25
|
| 313 |
+
make_toast_random: 25
|
| 314 |
+
pack_objects_into_box: 25
|
| 315 |
+
pack_objects_into_box_random: 25
|
| 316 |
+
pour_liquid_into_cup: 25
|
| 317 |
+
pour_liquid_into_cup_random: 25
|
| 318 |
+
push_T: 25
|
| 319 |
+
push_T_random: 25
|
| 320 |
+
sort_nesting_dolls_by_size: 25
|
| 321 |
+
sort_nesting_dolls_by_size_random: 25
|
| 322 |
+
stack_blocks: 25
|
| 323 |
+
stack_blocks_random: 25
|
| 324 |
+
stack_bowls: 25
|
| 325 |
+
stack_bowls_random: 25
|
| 326 |
+
store_laptop_and_headphones: 25
|
| 327 |
+
store_laptop_and_headphones_random: 25
|
| 328 |
+
sweep_blocks: 25
|
| 329 |
+
sweep_blocks_random: 25
|
| 330 |
+
report_kind: robodojo
|
| 331 |
+
task_suite_name: robodojo
|
| 332 |
+
eval_dataset: null
|
| 333 |
+
inference_model:
|
| 334 |
+
action_horizon: 32
|
| 335 |
+
action_norm_type: min_max
|
| 336 |
+
frame_window_size: 9
|
| 337 |
+
mot_checkpoint_mixed_attn: true
|
| 338 |
+
num_inference_steps: 10
|
| 339 |
+
num_views: 3
|
| 340 |
+
pretrained_name_or_path: ./checkpoints/fastwam_base_full/fastwam_base_full.safetensors
|
| 341 |
+
pretrained_skip_prefixes:
|
| 342 |
+
- vla_head.mot.mixtures.action.action_encoder.
|
| 343 |
+
- vla_head.mot.mixtures.action.head.
|
| 344 |
+
- vla_head.proprio_encoder.
|
| 345 |
+
proprio_dim: 14
|
| 346 |
+
torch_dtype: bf16
|
| 347 |
+
type: FastWAMVLA
|
| 348 |
+
vla_head:
|
| 349 |
+
action_dit_config:
|
| 350 |
+
action_dim: 14
|
| 351 |
+
attn_head_dim: 128
|
| 352 |
+
eps: 1.0e-06
|
| 353 |
+
ffn_dim: 4096
|
| 354 |
+
freq_dim: 256
|
| 355 |
+
hidden_dim: 1024
|
| 356 |
+
num_heads: 24
|
| 357 |
+
num_layers: 30
|
| 358 |
+
text_dim: 4096
|
| 359 |
+
use_gradient_checkpointing: true
|
| 360 |
+
action_scheduler:
|
| 361 |
+
infer_shift: 5.0
|
| 362 |
+
num_train_timesteps: 1000
|
| 363 |
+
train_shift: 5.0
|
| 364 |
+
loss:
|
| 365 |
+
lambda_action: 1.0
|
| 366 |
+
lambda_video: 1.0
|
| 367 |
+
type: FastWAMHead
|
| 368 |
+
video_dit_config:
|
| 369 |
+
action_conditioned: false
|
| 370 |
+
action_dim: 14
|
| 371 |
+
action_group_causal_mask_mode: group_diagonal
|
| 372 |
+
attn_head_dim: 128
|
| 373 |
+
eps: 1.0e-06
|
| 374 |
+
ffn_dim: 14336
|
| 375 |
+
freq_dim: 256
|
| 376 |
+
fuse_vae_embedding_in_latents: true
|
| 377 |
+
has_image_input: false
|
| 378 |
+
hidden_dim: 3072
|
| 379 |
+
in_dim: 48
|
| 380 |
+
num_heads: 24
|
| 381 |
+
num_layers: 30
|
| 382 |
+
out_dim: 48
|
| 383 |
+
patch_size:
|
| 384 |
+
- 1
|
| 385 |
+
- 2
|
| 386 |
+
- 2
|
| 387 |
+
require_clip_embedding: false
|
| 388 |
+
require_vae_embedding: false
|
| 389 |
+
seperated_timestep: true
|
| 390 |
+
text_dim: 4096
|
| 391 |
+
use_gradient_checkpointing: true
|
| 392 |
+
video_attention_mask_mode: first_frame_causal
|
| 393 |
+
video_scheduler:
|
| 394 |
+
infer_shift: 5.0
|
| 395 |
+
num_train_timesteps: 1000
|
| 396 |
+
train_shift: 5.0
|
| 397 |
+
vlm_backbone:
|
| 398 |
+
text_embed_cache_context_len: 128
|
| 399 |
+
text_embed_cache_device: cpu
|
| 400 |
+
text_embed_cache_size: 256
|
| 401 |
+
type: Wan22Backbone
|
| 402 |
+
model:
|
| 403 |
+
action_horizon: 32
|
| 404 |
+
action_norm_type: min_max
|
| 405 |
+
frame_window_size: 9
|
| 406 |
+
mot_checkpoint_mixed_attn: true
|
| 407 |
+
num_inference_steps: 10
|
| 408 |
+
num_views: 3
|
| 409 |
+
pretrained_name_or_path: ./checkpoints/fastwam_base_full/fastwam_base_full.safetensors
|
| 410 |
+
pretrained_skip_prefixes:
|
| 411 |
+
- vla_head.mot.mixtures.action.action_encoder.
|
| 412 |
+
- vla_head.mot.mixtures.action.head.
|
| 413 |
+
- vla_head.proprio_encoder.
|
| 414 |
+
proprio_dim: 14
|
| 415 |
+
torch_dtype: bf16
|
| 416 |
+
type: FastWAMVLA
|
| 417 |
+
vla_head:
|
| 418 |
+
action_dit_config:
|
| 419 |
+
action_dim: 14
|
| 420 |
+
attn_head_dim: 128
|
| 421 |
+
eps: 1.0e-06
|
| 422 |
+
ffn_dim: 4096
|
| 423 |
+
freq_dim: 256
|
| 424 |
+
hidden_dim: 1024
|
| 425 |
+
num_heads: 24
|
| 426 |
+
num_layers: 30
|
| 427 |
+
text_dim: 4096
|
| 428 |
+
use_gradient_checkpointing: true
|
| 429 |
+
action_scheduler:
|
| 430 |
+
infer_shift: 5.0
|
| 431 |
+
num_train_timesteps: 1000
|
| 432 |
+
train_shift: 5.0
|
| 433 |
+
loss:
|
| 434 |
+
lambda_action: 1.0
|
| 435 |
+
lambda_video: 1.0
|
| 436 |
+
type: FastWAMHead
|
| 437 |
+
video_dit_config:
|
| 438 |
+
action_conditioned: false
|
| 439 |
+
action_dim: 14
|
| 440 |
+
action_group_causal_mask_mode: group_diagonal
|
| 441 |
+
attn_head_dim: 128
|
| 442 |
+
eps: 1.0e-06
|
| 443 |
+
ffn_dim: 14336
|
| 444 |
+
freq_dim: 256
|
| 445 |
+
fuse_vae_embedding_in_latents: true
|
| 446 |
+
has_image_input: false
|
| 447 |
+
hidden_dim: 3072
|
| 448 |
+
in_dim: 48
|
| 449 |
+
num_heads: 24
|
| 450 |
+
num_layers: 30
|
| 451 |
+
out_dim: 48
|
| 452 |
+
patch_size:
|
| 453 |
+
- 1
|
| 454 |
+
- 2
|
| 455 |
+
- 2
|
| 456 |
+
require_clip_embedding: false
|
| 457 |
+
require_vae_embedding: false
|
| 458 |
+
seperated_timestep: true
|
| 459 |
+
text_dim: 4096
|
| 460 |
+
use_gradient_checkpointing: true
|
| 461 |
+
video_attention_mask_mode: first_frame_causal
|
| 462 |
+
video_scheduler:
|
| 463 |
+
infer_shift: 5.0
|
| 464 |
+
num_train_timesteps: 1000
|
| 465 |
+
train_shift: 5.0
|
| 466 |
+
vlm_backbone:
|
| 467 |
+
text_embed_cache_context_len: 128
|
| 468 |
+
text_embed_cache_device: cpu
|
| 469 |
+
text_embed_cache_size: 256
|
| 470 |
+
type: Wan22Backbone
|
| 471 |
+
runner:
|
| 472 |
+
collator:
|
| 473 |
+
keys:
|
| 474 |
+
- states
|
| 475 |
+
- images
|
| 476 |
+
- img_masks
|
| 477 |
+
- actions
|
| 478 |
+
- action_masks
|
| 479 |
+
- embodiment_ids
|
| 480 |
+
- frame_masks
|
| 481 |
+
- lang_tokens
|
| 482 |
+
- lang_masks
|
| 483 |
+
meta_keys:
|
| 484 |
+
- task_description
|
| 485 |
+
- info
|
| 486 |
+
- stats
|
| 487 |
+
- timestamp
|
| 488 |
+
type: DictCollator
|
| 489 |
+
dataset_sharding_strategy: blockwise
|
| 490 |
+
enable_gradient_checkpointing: false
|
| 491 |
+
enable_mixed_precision_training: true
|
| 492 |
+
evaluator:
|
| 493 |
+
eval_every: 1000
|
| 494 |
+
num_inference_steps: 10
|
| 495 |
+
save_video: true
|
| 496 |
+
seed: 42
|
| 497 |
+
type: training-eval
|
| 498 |
+
video_fps: 8
|
| 499 |
+
fsdp_wrap_policy: execution-block
|
| 500 |
+
grad_accumulation_steps: 1
|
| 501 |
+
lr_scheduler:
|
| 502 |
+
betas:
|
| 503 |
+
- 0.9
|
| 504 |
+
- 0.95
|
| 505 |
+
min_lr_ratio: 1.0
|
| 506 |
+
type: linear-warmup+cosine-decay-min-lr
|
| 507 |
+
warmup_ratio: 0.0
|
| 508 |
+
weight_decay_style: uniform
|
| 509 |
+
max_epochs: 6
|
| 510 |
+
max_grad_norm: 1.0
|
| 511 |
+
max_keep_ckpts: 6
|
| 512 |
+
max_steps: null
|
| 513 |
+
metric:
|
| 514 |
+
active_trackers:
|
| 515 |
+
- jsonl
|
| 516 |
+
- wandb
|
| 517 |
+
grad_accumulation_steps: 1
|
| 518 |
+
run_dir: work_dirs
|
| 519 |
+
type: VLAMetric
|
| 520 |
+
window_size: 1
|
| 521 |
+
mixed_precision_dtype: bf16
|
| 522 |
+
optimizer:
|
| 523 |
+
fused: true
|
| 524 |
+
lr: 1.0e-06
|
| 525 |
+
type: AdamW
|
| 526 |
+
weight_decay: 0.01
|
| 527 |
+
reduce_in_full_precision: true
|
| 528 |
+
sampler: null
|
| 529 |
+
save_epoch_interval: 1
|
| 530 |
+
save_iter_interval: 10000
|
| 531 |
+
sharding_strategy: full-shard
|
| 532 |
+
type: FSDPTrainRunner
|
| 533 |
+
seed: 42
|
| 534 |
+
themis:
|
| 535 |
+
ros_server:
|
| 536 |
+
dataset_section: eval
|
| 537 |
+
denormalize_context:
|
| 538 |
+
task_suite_name: robodojo_arx_x5
|
| 539 |
+
device: cuda:0
|
| 540 |
+
enable_mixed_precision: true
|
| 541 |
+
evaluation_reporting:
|
| 542 |
+
result_output_dir: work_dirs/fastwam_robodojo_eval
|
| 543 |
+
forward_seed: false
|
| 544 |
+
mixed_precision_dtype: bf16
|
| 545 |
+
model_outputs_environment_actions: false
|
| 546 |
+
workers:
|
| 547 |
+
lease_timeout_s: 900.0
|
| 548 |
+
request_timeout_s: 120.0
|
| 549 |
+
startup_timeout_s: 900.0
|
| 550 |
+
runner:
|
| 551 |
+
environment:
|
| 552 |
+
action_mode: joint
|
| 553 |
+
device_id: 1
|
| 554 |
+
env_cfg_type: arx_x5
|
| 555 |
+
headless: true
|
| 556 |
+
robodojo_root: /root/projects/RoboDojo
|
| 557 |
+
save_videos: false
|
| 558 |
+
task_name: all
|
| 559 |
+
type: RoboDojoEnvironment
|
| 560 |
+
episodes_per_task: 50
|
| 561 |
+
episodes_per_task_overrides:
|
| 562 |
+
arrange_largest_number: 25
|
| 563 |
+
arrange_largest_number_random: 25
|
| 564 |
+
fold_clothes: 25
|
| 565 |
+
fold_clothes_random: 25
|
| 566 |
+
hang_mugs: 25
|
| 567 |
+
hang_mugs_random: 25
|
| 568 |
+
make_toast: 25
|
| 569 |
+
make_toast_random: 25
|
| 570 |
+
pack_objects_into_box: 25
|
| 571 |
+
pack_objects_into_box_random: 25
|
| 572 |
+
pour_liquid_into_cup: 25
|
| 573 |
+
pour_liquid_into_cup_random: 25
|
| 574 |
+
push_T: 25
|
| 575 |
+
push_T_random: 25
|
| 576 |
+
sort_nesting_dolls_by_size: 25
|
| 577 |
+
sort_nesting_dolls_by_size_random: 25
|
| 578 |
+
stack_blocks: 25
|
| 579 |
+
stack_blocks_random: 25
|
| 580 |
+
stack_bowls: 25
|
| 581 |
+
stack_bowls_random: 25
|
| 582 |
+
store_laptop_and_headphones: 25
|
| 583 |
+
store_laptop_and_headphones_random: 25
|
| 584 |
+
sweep_blocks: 25
|
| 585 |
+
sweep_blocks_random: 25
|
| 586 |
+
evaluator:
|
| 587 |
+
type: SuccessRateEvaluator
|
| 588 |
+
execute_horizon: 16
|
| 589 |
+
max_episode_steps: 2000
|
| 590 |
+
model_client:
|
| 591 |
+
type: FluxVLAZMQModelClient
|
| 592 |
+
parallel_workers: 1
|
| 593 |
+
seed: 0
|
| 594 |
+
simulator_gpu_ids: null
|
| 595 |
+
stop_on_success: true
|
| 596 |
+
type: EvalRunner
|
| 597 |
+
work_dir: work_dirs/fastwam_robodojo_eval
|
| 598 |
+
transport:
|
| 599 |
+
host: 127.0.0.1
|
| 600 |
+
image_encoding: rgb8
|
| 601 |
+
image_keys:
|
| 602 |
+
- cam_high
|
| 603 |
+
- cam_left_wrist
|
| 604 |
+
- cam_right_wrist
|
| 605 |
+
port: 5555
|
| 606 |
+
report_service_name: /fluxvla/report_evaluation
|
| 607 |
+
state_keys:
|
| 608 |
+
- states
|
| 609 |
+
timeout_s: 30.0
|
| 610 |
+
unnorm_key: robodojo_arx_x5
|
| 611 |
+
train_dataloader:
|
| 612 |
+
dataset:
|
| 613 |
+
dataset_statistics:
|
| 614 |
+
robodojo_arx_x5:
|
| 615 |
+
action:
|
| 616 |
+
count: 1859602
|
| 617 |
+
max:
|
| 618 |
+
- 1.7537026405334473
|
| 619 |
+
- 3.0546703338623047
|
| 620 |
+
- 3.8525187969207764
|
| 621 |
+
- 2.0974574089050293
|
| 622 |
+
- 1.8103265762329102
|
| 623 |
+
- 3.1366536617279053
|
| 624 |
+
- 1.0
|
| 625 |
+
- 1.6732014417648315
|
| 626 |
+
- 3.3797459602355957
|
| 627 |
+
- 4.252756595611572
|
| 628 |
+
- 2.5287232398986816
|
| 629 |
+
- 3.1440579891204834
|
| 630 |
+
- 3.0381109714508057
|
| 631 |
+
- 1.0
|
| 632 |
+
mean:
|
| 633 |
+
- -0.20032191276550293
|
| 634 |
+
- 0.925260603427887
|
| 635 |
+
- 0.6879700422286987
|
| 636 |
+
- -0.33993399143218994
|
| 637 |
+
- 0.06580745428800583
|
| 638 |
+
- 0.003984309732913971
|
| 639 |
+
- 0.771653950214386
|
| 640 |
+
- 0.17281471192836761
|
| 641 |
+
- 0.8216421008110046
|
| 642 |
+
- 0.6193687319755554
|
| 643 |
+
- -0.3603578805923462
|
| 644 |
+
- -0.06270533800125122
|
| 645 |
+
- 0.0036061492282897234
|
| 646 |
+
- 0.7855709195137024
|
| 647 |
+
min:
|
| 648 |
+
- -1.4863648414611816
|
| 649 |
+
- -0.2586335241794586
|
| 650 |
+
- -0.06850092858076096
|
| 651 |
+
- -2.2642147541046143
|
| 652 |
+
- -1.4876768589019775
|
| 653 |
+
- -3.0168392658233643
|
| 654 |
+
- -3.212450869184004e-17
|
| 655 |
+
- -1.4924354553222656
|
| 656 |
+
- -0.27809593081474304
|
| 657 |
+
- -0.18774886429309845
|
| 658 |
+
- -2.5354628562927246
|
| 659 |
+
- -3.0663280487060547
|
| 660 |
+
- -3.0486762523651123
|
| 661 |
+
- -3.212450869184004e-17
|
| 662 |
+
q01:
|
| 663 |
+
- -1.051365569829941
|
| 664 |
+
- -3.5348887174584814e-14
|
| 665 |
+
- 1.741881830823392e-16
|
| 666 |
+
- -1.5984010362625123
|
| 667 |
+
- -0.6003574305772781
|
| 668 |
+
- -1.6678147149085998
|
| 669 |
+
- 0.0
|
| 670 |
+
- -0.4509398394823074
|
| 671 |
+
- -2.5859282299029243e-14
|
| 672 |
+
- 1.234041714549172e-16
|
| 673 |
+
- -1.64055180311203
|
| 674 |
+
- -1.2633746123313903
|
| 675 |
+
- -1.7645285475254058
|
| 676 |
+
- 0.0
|
| 677 |
+
q99:
|
| 678 |
+
- 0.5431358617544174
|
| 679 |
+
- 2.495765209197998
|
| 680 |
+
- 2.492974226474762
|
| 681 |
+
- 1.3241519677639007
|
| 682 |
+
- 1.2496635341644287
|
| 683 |
+
- 1.7392305016517635
|
| 684 |
+
- 1.0
|
| 685 |
+
- 1.0814965963363647
|
| 686 |
+
- 2.4167031812667843
|
| 687 |
+
- 2.3470158338546754
|
| 688 |
+
- 1.141731116771698
|
| 689 |
+
- 0.5208872479200363
|
| 690 |
+
- 1.489715996980667
|
| 691 |
+
- 1.0
|
| 692 |
+
std:
|
| 693 |
+
- 0.34360724687576294
|
| 694 |
+
- 0.8902974724769592
|
| 695 |
+
- 0.7318998575210571
|
| 696 |
+
- 0.6505846977233887
|
| 697 |
+
- 0.29849204421043396
|
| 698 |
+
- 0.5843351483345032
|
| 699 |
+
- 0.34186822175979614
|
| 700 |
+
- 0.3206902742385864
|
| 701 |
+
- 0.8718543648719788
|
| 702 |
+
- 0.7120647430419922
|
| 703 |
+
- 0.6016045212745667
|
| 704 |
+
- 0.28415030241012573
|
| 705 |
+
- 0.5370385050773621
|
| 706 |
+
- 0.34119123220443726
|
| 707 |
+
proprio:
|
| 708 |
+
count: 1859602
|
| 709 |
+
max:
|
| 710 |
+
- 1.7537026405334473
|
| 711 |
+
- 3.0546703338623047
|
| 712 |
+
- 3.8525187969207764
|
| 713 |
+
- 2.0974574089050293
|
| 714 |
+
- 1.8103265762329102
|
| 715 |
+
- 3.1366536617279053
|
| 716 |
+
- 1.0
|
| 717 |
+
- 1.6732014417648315
|
| 718 |
+
- 3.3797459602355957
|
| 719 |
+
- 4.252756595611572
|
| 720 |
+
- 2.5287232398986816
|
| 721 |
+
- 3.1440579891204834
|
| 722 |
+
- 3.0381109714508057
|
| 723 |
+
- 1.0
|
| 724 |
+
mean:
|
| 725 |
+
- -0.20028550922870636
|
| 726 |
+
- 0.9250829815864563
|
| 727 |
+
- 0.6878653764724731
|
| 728 |
+
- -0.3399182856082916
|
| 729 |
+
- 0.06579338014125824
|
| 730 |
+
- 0.004018673673272133
|
| 731 |
+
- 0.7717168927192688
|
| 732 |
+
- 0.17282654345035553
|
| 733 |
+
- 0.8213191032409668
|
| 734 |
+
- 0.6190997958183289
|
| 735 |
+
- -0.3601549565792084
|
| 736 |
+
- -0.06264610588550568
|
| 737 |
+
- 0.0037324042059481144
|
| 738 |
+
- 0.7856565713882446
|
| 739 |
+
min:
|
| 740 |
+
- -1.4863648414611816
|
| 741 |
+
- -0.2586335241794586
|
| 742 |
+
- -0.06850092858076096
|
| 743 |
+
- -2.2642147541046143
|
| 744 |
+
- -1.4876768589019775
|
| 745 |
+
- -3.0168392658233643
|
| 746 |
+
- -3.212450869184004e-17
|
| 747 |
+
- -1.4924354553222656
|
| 748 |
+
- -0.27809593081474304
|
| 749 |
+
- -0.18774886429309845
|
| 750 |
+
- -2.5354628562927246
|
| 751 |
+
- -3.0663280487060547
|
| 752 |
+
- -3.0486762523651123
|
| 753 |
+
- -3.212450869184004e-17
|
| 754 |
+
q01:
|
| 755 |
+
- -1.051365569829941
|
| 756 |
+
- -3.52302449637288e-14
|
| 757 |
+
- 1.6996893991849812e-16
|
| 758 |
+
- -1.5984010362625123
|
| 759 |
+
- -0.6003412520885467
|
| 760 |
+
- -1.6678147149085998
|
| 761 |
+
- 0.0
|
| 762 |
+
- -0.4500492787361145
|
| 763 |
+
- -2.5859282299029243e-14
|
| 764 |
+
- 1.194697284288627e-16
|
| 765 |
+
- -1.6398817586898804
|
| 766 |
+
- -1.263367258310318
|
| 767 |
+
- -1.760098042488098
|
| 768 |
+
- 0.0
|
| 769 |
+
q99:
|
| 770 |
+
- 0.5431358617544174
|
| 771 |
+
- 2.495765209197998
|
| 772 |
+
- 2.492974226474762
|
| 773 |
+
- 1.323737324476242
|
| 774 |
+
- 1.2496635341644287
|
| 775 |
+
- 1.7391636216640465
|
| 776 |
+
- 1.0
|
| 777 |
+
- 1.0814965963363647
|
| 778 |
+
- 2.416655488014221
|
| 779 |
+
- 2.346989154815674
|
| 780 |
+
- 1.1415718960762022
|
| 781 |
+
- 0.5208872479200363
|
| 782 |
+
- 1.4889542925357817
|
| 783 |
+
- 1.0
|
| 784 |
+
std:
|
| 785 |
+
- 0.34361061453819275
|
| 786 |
+
- 0.8903892636299133
|
| 787 |
+
- 0.7319481372833252
|
| 788 |
+
- 0.6505074501037598
|
| 789 |
+
- 0.29847919940948486
|
| 790 |
+
- 0.5842824578285217
|
| 791 |
+
- 0.34185686707496643
|
| 792 |
+
- 0.3206428587436676
|
| 793 |
+
- 0.8718962669372559
|
| 794 |
+
- 0.7120621204376221
|
| 795 |
+
- 0.6014657616615295
|
| 796 |
+
- 0.2840825021266937
|
| 797 |
+
- 0.5366978049278259
|
| 798 |
+
- 0.3415590524673462
|
| 799 |
+
datasets:
|
| 800 |
+
action_key: action
|
| 801 |
+
action_window_size: 32
|
| 802 |
+
data_root_path:
|
| 803 |
+
- ./datasets/RoboDojo_lerobot_v21_video
|
| 804 |
+
frame_sample_stride: 4
|
| 805 |
+
frame_window_size: 9
|
| 806 |
+
statistic_name: robodojo_arx_x5
|
| 807 |
+
supervise_terminal_padding: true
|
| 808 |
+
transforms:
|
| 809 |
+
- embodiment_id: 0
|
| 810 |
+
name_mappings:
|
| 811 |
+
actions:
|
| 812 |
+
- actions
|
| 813 |
+
observation.state:
|
| 814 |
+
- states
|
| 815 |
+
parquet_keys:
|
| 816 |
+
- observation.state
|
| 817 |
+
- timestamp
|
| 818 |
+
- actions
|
| 819 |
+
- info
|
| 820 |
+
- stats
|
| 821 |
+
- action_masks
|
| 822 |
+
type: ProcessParquetInputs
|
| 823 |
+
video_backend: torchcodec
|
| 824 |
+
video_keys:
|
| 825 |
+
- observation.images.cam_high
|
| 826 |
+
- observation.images.cam_left_wrist
|
| 827 |
+
- observation.images.cam_right_wrist
|
| 828 |
+
- backend: torchvision
|
| 829 |
+
height: 224
|
| 830 |
+
scale_to_unit_interval: true
|
| 831 |
+
type: ResizeImages
|
| 832 |
+
width: 224
|
| 833 |
+
- means:
|
| 834 |
+
- 0.5
|
| 835 |
+
- 0.5
|
| 836 |
+
- 0.5
|
| 837 |
+
stds:
|
| 838 |
+
- 0.5
|
| 839 |
+
- 0.5
|
| 840 |
+
- 0.5
|
| 841 |
+
type: NormalizeImages
|
| 842 |
+
- action_dim: 14
|
| 843 |
+
action_key: action
|
| 844 |
+
norm_type: min_max
|
| 845 |
+
output_dtype: float32
|
| 846 |
+
state_dim: 14
|
| 847 |
+
state_key: proprio
|
| 848 |
+
type: NormalizeStatesAndActions
|
| 849 |
+
- combine_view_masks: true
|
| 850 |
+
frame_window_size: 9
|
| 851 |
+
num_views: 3
|
| 852 |
+
tile_direction: horizontal
|
| 853 |
+
type: PrepareVideo
|
| 854 |
+
- max_len: 128
|
| 855 |
+
prompt_template: 'A video recorded from a robot''s point of view executing
|
| 856 |
+
the following instruction: {task}'
|
| 857 |
+
tokenizer:
|
| 858 |
+
model_path: ./checkpoints/fastwam_base_full/tokenizer
|
| 859 |
+
type: PretrainedTokenizer
|
| 860 |
+
type: LiberoPromptFromInputs
|
| 861 |
+
use_conversation: false
|
| 862 |
+
type: ParquetDataset
|
| 863 |
+
use_delta: false
|
| 864 |
+
window_start_idx: 0
|
| 865 |
+
name_mappings:
|
| 866 |
+
action:
|
| 867 |
+
- action
|
| 868 |
+
observation.state:
|
| 869 |
+
- proprio
|
| 870 |
+
reshuffle_each_epoch: true
|
| 871 |
+
seed: 42
|
| 872 |
+
statistic_keys:
|
| 873 |
+
- observation.state
|
| 874 |
+
- timestamp
|
| 875 |
+
- action
|
| 876 |
+
statistic_name: robodojo_arx_x5
|
| 877 |
+
type: DistributedRepeatingDataset
|
| 878 |
+
per_device_batch_size: 2
|
| 879 |
+
per_device_num_workers: 8
|
| 880 |
+
val_dataloader: null
|
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robodojo_arx_x5": {
|
| 3 |
+
"proprio": {
|
| 4 |
+
"mean": [
|
| 5 |
+
-0.20040483290933933,
|
| 6 |
+
0.9260306606167606,
|
| 7 |
+
0.6881890325982686,
|
| 8 |
+
-0.3400483206709066,
|
| 9 |
+
0.06579394446194628,
|
| 10 |
+
0.004003346747695925,
|
| 11 |
+
0.7714465980721269,
|
| 12 |
+
0.1729983421764827,
|
| 13 |
+
0.8224942863743041,
|
| 14 |
+
0.6196512620467081,
|
| 15 |
+
-0.3604178425587031,
|
| 16 |
+
-0.06267070852548702,
|
| 17 |
+
0.0037534706356096253,
|
| 18 |
+
0.7860055662365837
|
| 19 |
+
],
|
| 20 |
+
"std": [
|
| 21 |
+
0.34305506149779086,
|
| 22 |
+
0.88803979292961,
|
| 23 |
+
0.7302414431033704,
|
| 24 |
+
0.6487680382543082,
|
| 25 |
+
0.29890958198694983,
|
| 26 |
+
0.5843008394814946,
|
| 27 |
+
0.343166656637697,
|
| 28 |
+
0.3198980322111088,
|
| 29 |
+
0.8736479484499943,
|
| 30 |
+
0.7135349837518498,
|
| 31 |
+
0.6027223232925302,
|
| 32 |
+
0.2836475903509877,
|
| 33 |
+
0.5368540927401809,
|
| 34 |
+
0.3406560199738384
|
| 35 |
+
],
|
| 36 |
+
"min": [
|
| 37 |
+
-1.4863648414611816,
|
| 38 |
+
-0.2586335241794586,
|
| 39 |
+
-0.06850092858076096,
|
| 40 |
+
-2.2642147541046143,
|
| 41 |
+
-1.4876768589019775,
|
| 42 |
+
-3.0168392658233643,
|
| 43 |
+
-3.212450869184004e-17,
|
| 44 |
+
-1.4924354553222656,
|
| 45 |
+
-0.27809593081474304,
|
| 46 |
+
-0.18774886429309845,
|
| 47 |
+
-2.5354628562927246,
|
| 48 |
+
-3.0663280487060547,
|
| 49 |
+
-3.0486762523651123,
|
| 50 |
+
-3.212450869184004e-17
|
| 51 |
+
],
|
| 52 |
+
"max": [
|
| 53 |
+
1.7537026405334473,
|
| 54 |
+
3.0546703338623047,
|
| 55 |
+
3.8525187969207764,
|
| 56 |
+
2.0974574089050293,
|
| 57 |
+
1.8103265762329102,
|
| 58 |
+
3.1366536617279053,
|
| 59 |
+
1.0,
|
| 60 |
+
1.6732014417648315,
|
| 61 |
+
3.3797459602355957,
|
| 62 |
+
4.252756595611572,
|
| 63 |
+
2.5287232398986816,
|
| 64 |
+
3.1440579891204834,
|
| 65 |
+
3.0381109714508057,
|
| 66 |
+
1.0
|
| 67 |
+
],
|
| 68 |
+
"q01": null,
|
| 69 |
+
"q99": null
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"mean": [
|
| 73 |
+
-0.20044206015317542,
|
| 74 |
+
0.9262120117772524,
|
| 75 |
+
0.6882954361000181,
|
| 76 |
+
-0.34006418745617883,
|
| 77 |
+
0.0658081773254239,
|
| 78 |
+
0.0039689747289930934,
|
| 79 |
+
0.7713835451223375,
|
| 80 |
+
0.1729873784174943,
|
| 81 |
+
0.8228202306896505,
|
| 82 |
+
0.61992379065145,
|
| 83 |
+
-0.36062264651275594,
|
| 84 |
+
-0.06273007512256629,
|
| 85 |
+
0.003626950967936429,
|
| 86 |
+
0.7859185929400508
|
| 87 |
+
],
|
| 88 |
+
"std": [
|
| 89 |
+
0.3430578526958288,
|
| 90 |
+
0.8880320168409441,
|
| 91 |
+
0.7302223166171972,
|
| 92 |
+
0.6488505412449643,
|
| 93 |
+
0.29892352527661153,
|
| 94 |
+
0.5843509710911197,
|
| 95 |
+
0.34319546515299043,
|
| 96 |
+
0.3199443326985692,
|
| 97 |
+
0.8737037084051896,
|
| 98 |
+
0.7136346922036603,
|
| 99 |
+
0.6029010762371366,
|
| 100 |
+
0.2837157953906254,
|
| 101 |
+
0.5371882124069792,
|
| 102 |
+
0.3407070568392383
|
| 103 |
+
],
|
| 104 |
+
"min": [
|
| 105 |
+
-1.4863648414611816,
|
| 106 |
+
-0.2586335241794586,
|
| 107 |
+
-0.06850092858076096,
|
| 108 |
+
-2.2642147541046143,
|
| 109 |
+
-1.4876768589019775,
|
| 110 |
+
-3.0168392658233643,
|
| 111 |
+
-3.212450869184004e-17,
|
| 112 |
+
-1.4924354553222656,
|
| 113 |
+
-0.27809593081474304,
|
| 114 |
+
-0.18774886429309845,
|
| 115 |
+
-2.5354628562927246,
|
| 116 |
+
-3.0663280487060547,
|
| 117 |
+
-3.0486762523651123,
|
| 118 |
+
-3.212450869184004e-17
|
| 119 |
+
],
|
| 120 |
+
"max": [
|
| 121 |
+
1.7537026405334473,
|
| 122 |
+
3.0546703338623047,
|
| 123 |
+
3.8525187969207764,
|
| 124 |
+
2.0974574089050293,
|
| 125 |
+
1.8103265762329102,
|
| 126 |
+
3.1366536617279053,
|
| 127 |
+
1.0,
|
| 128 |
+
1.6732014417648315,
|
| 129 |
+
3.3797459602355957,
|
| 130 |
+
4.252756595611572,
|
| 131 |
+
2.5287232398986816,
|
| 132 |
+
3.1440579891204834,
|
| 133 |
+
3.0381109714508057,
|
| 134 |
+
1.0
|
| 135 |
+
],
|
| 136 |
+
"q01": [
|
| 137 |
+
-1.051365569829941,
|
| 138 |
+
-3.5348887174584814e-14,
|
| 139 |
+
1.741881830823392e-16,
|
| 140 |
+
-1.5984010362625123,
|
| 141 |
+
-0.6003574305772781,
|
| 142 |
+
-1.6678147149085998,
|
| 143 |
+
0.0,
|
| 144 |
+
-0.4509398394823074,
|
| 145 |
+
-2.5859282299029243e-14,
|
| 146 |
+
1.234041714549172e-16,
|
| 147 |
+
-1.64055180311203,
|
| 148 |
+
-1.2633746123313903,
|
| 149 |
+
-1.7645285475254058,
|
| 150 |
+
0.0
|
| 151 |
+
],
|
| 152 |
+
"q99": [
|
| 153 |
+
0.5431358617544174,
|
| 154 |
+
2.495765209197998,
|
| 155 |
+
2.492974226474762,
|
| 156 |
+
1.3241519677639007,
|
| 157 |
+
1.2496635341644287,
|
| 158 |
+
1.7392305016517635,
|
| 159 |
+
1.0,
|
| 160 |
+
1.0814965963363647,
|
| 161 |
+
2.4167031812667843,
|
| 162 |
+
2.3470158338546754,
|
| 163 |
+
1.141731116771698,
|
| 164 |
+
0.5208872479200363,
|
| 165 |
+
1.489715996980667,
|
| 166 |
+
1.0
|
| 167 |
+
]
|
| 168 |
+
},
|
| 169 |
+
"timestamp": {
|
| 170 |
+
"mean": [
|
| 171 |
+
13.704522752718054
|
| 172 |
+
],
|
| 173 |
+
"std": [
|
| 174 |
+
11.04044022225918
|
| 175 |
+
],
|
| 176 |
+
"min": [
|
| 177 |
+
0.0
|
| 178 |
+
],
|
| 179 |
+
"max": [
|
| 180 |
+
61.44
|
| 181 |
+
],
|
| 182 |
+
"q01": null,
|
| 183 |
+
"q99": null
|
| 184 |
+
}
|
| 185 |
+
}
|
| 186 |
+
}
|
|
@@ -0,0 +1,308 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>",
|
| 128 |
+
"<extra_id_125>",
|
| 129 |
+
"<extra_id_126>",
|
| 130 |
+
"<extra_id_127>",
|
| 131 |
+
"<extra_id_128>",
|
| 132 |
+
"<extra_id_129>",
|
| 133 |
+
"<extra_id_130>",
|
| 134 |
+
"<extra_id_131>",
|
| 135 |
+
"<extra_id_132>",
|
| 136 |
+
"<extra_id_133>",
|
| 137 |
+
"<extra_id_134>",
|
| 138 |
+
"<extra_id_135>",
|
| 139 |
+
"<extra_id_136>",
|
| 140 |
+
"<extra_id_137>",
|
| 141 |
+
"<extra_id_138>",
|
| 142 |
+
"<extra_id_139>",
|
| 143 |
+
"<extra_id_140>",
|
| 144 |
+
"<extra_id_141>",
|
| 145 |
+
"<extra_id_142>",
|
| 146 |
+
"<extra_id_143>",
|
| 147 |
+
"<extra_id_144>",
|
| 148 |
+
"<extra_id_145>",
|
| 149 |
+
"<extra_id_146>",
|
| 150 |
+
"<extra_id_147>",
|
| 151 |
+
"<extra_id_148>",
|
| 152 |
+
"<extra_id_149>",
|
| 153 |
+
"<extra_id_150>",
|
| 154 |
+
"<extra_id_151>",
|
| 155 |
+
"<extra_id_152>",
|
| 156 |
+
"<extra_id_153>",
|
| 157 |
+
"<extra_id_154>",
|
| 158 |
+
"<extra_id_155>",
|
| 159 |
+
"<extra_id_156>",
|
| 160 |
+
"<extra_id_157>",
|
| 161 |
+
"<extra_id_158>",
|
| 162 |
+
"<extra_id_159>",
|
| 163 |
+
"<extra_id_160>",
|
| 164 |
+
"<extra_id_161>",
|
| 165 |
+
"<extra_id_162>",
|
| 166 |
+
"<extra_id_163>",
|
| 167 |
+
"<extra_id_164>",
|
| 168 |
+
"<extra_id_165>",
|
| 169 |
+
"<extra_id_166>",
|
| 170 |
+
"<extra_id_167>",
|
| 171 |
+
"<extra_id_168>",
|
| 172 |
+
"<extra_id_169>",
|
| 173 |
+
"<extra_id_170>",
|
| 174 |
+
"<extra_id_171>",
|
| 175 |
+
"<extra_id_172>",
|
| 176 |
+
"<extra_id_173>",
|
| 177 |
+
"<extra_id_174>",
|
| 178 |
+
"<extra_id_175>",
|
| 179 |
+
"<extra_id_176>",
|
| 180 |
+
"<extra_id_177>",
|
| 181 |
+
"<extra_id_178>",
|
| 182 |
+
"<extra_id_179>",
|
| 183 |
+
"<extra_id_180>",
|
| 184 |
+
"<extra_id_181>",
|
| 185 |
+
"<extra_id_182>",
|
| 186 |
+
"<extra_id_183>",
|
| 187 |
+
"<extra_id_184>",
|
| 188 |
+
"<extra_id_185>",
|
| 189 |
+
"<extra_id_186>",
|
| 190 |
+
"<extra_id_187>",
|
| 191 |
+
"<extra_id_188>",
|
| 192 |
+
"<extra_id_189>",
|
| 193 |
+
"<extra_id_190>",
|
| 194 |
+
"<extra_id_191>",
|
| 195 |
+
"<extra_id_192>",
|
| 196 |
+
"<extra_id_193>",
|
| 197 |
+
"<extra_id_194>",
|
| 198 |
+
"<extra_id_195>",
|
| 199 |
+
"<extra_id_196>",
|
| 200 |
+
"<extra_id_197>",
|
| 201 |
+
"<extra_id_198>",
|
| 202 |
+
"<extra_id_199>",
|
| 203 |
+
"<extra_id_200>",
|
| 204 |
+
"<extra_id_201>",
|
| 205 |
+
"<extra_id_202>",
|
| 206 |
+
"<extra_id_203>",
|
| 207 |
+
"<extra_id_204>",
|
| 208 |
+
"<extra_id_205>",
|
| 209 |
+
"<extra_id_206>",
|
| 210 |
+
"<extra_id_207>",
|
| 211 |
+
"<extra_id_208>",
|
| 212 |
+
"<extra_id_209>",
|
| 213 |
+
"<extra_id_210>",
|
| 214 |
+
"<extra_id_211>",
|
| 215 |
+
"<extra_id_212>",
|
| 216 |
+
"<extra_id_213>",
|
| 217 |
+
"<extra_id_214>",
|
| 218 |
+
"<extra_id_215>",
|
| 219 |
+
"<extra_id_216>",
|
| 220 |
+
"<extra_id_217>",
|
| 221 |
+
"<extra_id_218>",
|
| 222 |
+
"<extra_id_219>",
|
| 223 |
+
"<extra_id_220>",
|
| 224 |
+
"<extra_id_221>",
|
| 225 |
+
"<extra_id_222>",
|
| 226 |
+
"<extra_id_223>",
|
| 227 |
+
"<extra_id_224>",
|
| 228 |
+
"<extra_id_225>",
|
| 229 |
+
"<extra_id_226>",
|
| 230 |
+
"<extra_id_227>",
|
| 231 |
+
"<extra_id_228>",
|
| 232 |
+
"<extra_id_229>",
|
| 233 |
+
"<extra_id_230>",
|
| 234 |
+
"<extra_id_231>",
|
| 235 |
+
"<extra_id_232>",
|
| 236 |
+
"<extra_id_233>",
|
| 237 |
+
"<extra_id_234>",
|
| 238 |
+
"<extra_id_235>",
|
| 239 |
+
"<extra_id_236>",
|
| 240 |
+
"<extra_id_237>",
|
| 241 |
+
"<extra_id_238>",
|
| 242 |
+
"<extra_id_239>",
|
| 243 |
+
"<extra_id_240>",
|
| 244 |
+
"<extra_id_241>",
|
| 245 |
+
"<extra_id_242>",
|
| 246 |
+
"<extra_id_243>",
|
| 247 |
+
"<extra_id_244>",
|
| 248 |
+
"<extra_id_245>",
|
| 249 |
+
"<extra_id_246>",
|
| 250 |
+
"<extra_id_247>",
|
| 251 |
+
"<extra_id_248>",
|
| 252 |
+
"<extra_id_249>",
|
| 253 |
+
"<extra_id_250>",
|
| 254 |
+
"<extra_id_251>",
|
| 255 |
+
"<extra_id_252>",
|
| 256 |
+
"<extra_id_253>",
|
| 257 |
+
"<extra_id_254>",
|
| 258 |
+
"<extra_id_255>",
|
| 259 |
+
"<extra_id_256>",
|
| 260 |
+
"<extra_id_257>",
|
| 261 |
+
"<extra_id_258>",
|
| 262 |
+
"<extra_id_259>",
|
| 263 |
+
"<extra_id_260>",
|
| 264 |
+
"<extra_id_261>",
|
| 265 |
+
"<extra_id_262>",
|
| 266 |
+
"<extra_id_263>",
|
| 267 |
+
"<extra_id_264>",
|
| 268 |
+
"<extra_id_265>",
|
| 269 |
+
"<extra_id_266>",
|
| 270 |
+
"<extra_id_267>",
|
| 271 |
+
"<extra_id_268>",
|
| 272 |
+
"<extra_id_269>",
|
| 273 |
+
"<extra_id_270>",
|
| 274 |
+
"<extra_id_271>",
|
| 275 |
+
"<extra_id_272>",
|
| 276 |
+
"<extra_id_273>",
|
| 277 |
+
"<extra_id_274>",
|
| 278 |
+
"<extra_id_275>",
|
| 279 |
+
"<extra_id_276>",
|
| 280 |
+
"<extra_id_277>",
|
| 281 |
+
"<extra_id_278>",
|
| 282 |
+
"<extra_id_279>",
|
| 283 |
+
"<extra_id_280>",
|
| 284 |
+
"<extra_id_281>",
|
| 285 |
+
"<extra_id_282>",
|
| 286 |
+
"<extra_id_283>",
|
| 287 |
+
"<extra_id_284>",
|
| 288 |
+
"<extra_id_285>",
|
| 289 |
+
"<extra_id_286>",
|
| 290 |
+
"<extra_id_287>",
|
| 291 |
+
"<extra_id_288>",
|
| 292 |
+
"<extra_id_289>",
|
| 293 |
+
"<extra_id_290>",
|
| 294 |
+
"<extra_id_291>",
|
| 295 |
+
"<extra_id_292>",
|
| 296 |
+
"<extra_id_293>",
|
| 297 |
+
"<extra_id_294>",
|
| 298 |
+
"<extra_id_295>",
|
| 299 |
+
"<extra_id_296>",
|
| 300 |
+
"<extra_id_297>",
|
| 301 |
+
"<extra_id_298>",
|
| 302 |
+
"<extra_id_299>"
|
| 303 |
+
],
|
| 304 |
+
"bos_token": "<s>",
|
| 305 |
+
"eos_token": "</s>",
|
| 306 |
+
"pad_token": "<pad>",
|
| 307 |
+
"unk_token": "<unk>"
|
| 308 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3909a67b780650b35cf529ac782ad2b6b26e6d1f849d3fbb6a872905f452458
|
| 3 |
+
size 4548313
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e197b4d3dbd71da14b4eb255f4fa91c9c1f2068b20a2de2472967ca3d22602b
|
| 3 |
+
size 16837417
|
|
@@ -0,0 +1,2748 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"256000": {
|
| 36 |
+
"content": "<extra_id_299>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"256001": {
|
| 44 |
+
"content": "<extra_id_298>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"256002": {
|
| 52 |
+
"content": "<extra_id_297>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"256003": {
|
| 60 |
+
"content": "<extra_id_296>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"256004": {
|
| 68 |
+
"content": "<extra_id_295>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"256005": {
|
| 76 |
+
"content": "<extra_id_294>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"256006": {
|
| 84 |
+
"content": "<extra_id_293>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"256007": {
|
| 92 |
+
"content": "<extra_id_292>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"256008": {
|
| 100 |
+
"content": "<extra_id_291>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"256009": {
|
| 108 |
+
"content": "<extra_id_290>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"256010": {
|
| 116 |
+
"content": "<extra_id_289>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"256011": {
|
| 124 |
+
"content": "<extra_id_288>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"256012": {
|
| 132 |
+
"content": "<extra_id_287>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"256013": {
|
| 140 |
+
"content": "<extra_id_286>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"256014": {
|
| 148 |
+
"content": "<extra_id_285>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"256015": {
|
| 156 |
+
"content": "<extra_id_284>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"256016": {
|
| 164 |
+
"content": "<extra_id_283>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"256017": {
|
| 172 |
+
"content": "<extra_id_282>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"256018": {
|
| 180 |
+
"content": "<extra_id_281>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"256019": {
|
| 188 |
+
"content": "<extra_id_280>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"256020": {
|
| 196 |
+
"content": "<extra_id_279>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"256021": {
|
| 204 |
+
"content": "<extra_id_278>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"256022": {
|
| 212 |
+
"content": "<extra_id_277>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"256023": {
|
| 220 |
+
"content": "<extra_id_276>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"256024": {
|
| 228 |
+
"content": "<extra_id_275>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"256025": {
|
| 236 |
+
"content": "<extra_id_274>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"256026": {
|
| 244 |
+
"content": "<extra_id_273>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"256027": {
|
| 252 |
+
"content": "<extra_id_272>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"256028": {
|
| 260 |
+
"content": "<extra_id_271>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"256029": {
|
| 268 |
+
"content": "<extra_id_270>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"256030": {
|
| 276 |
+
"content": "<extra_id_269>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"256031": {
|
| 284 |
+
"content": "<extra_id_268>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"256032": {
|
| 292 |
+
"content": "<extra_id_267>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"256033": {
|
| 300 |
+
"content": "<extra_id_266>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"256034": {
|
| 308 |
+
"content": "<extra_id_265>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"256035": {
|
| 316 |
+
"content": "<extra_id_264>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"256036": {
|
| 324 |
+
"content": "<extra_id_263>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"256037": {
|
| 332 |
+
"content": "<extra_id_262>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"256038": {
|
| 340 |
+
"content": "<extra_id_261>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"256039": {
|
| 348 |
+
"content": "<extra_id_260>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"256040": {
|
| 356 |
+
"content": "<extra_id_259>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"256041": {
|
| 364 |
+
"content": "<extra_id_258>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"256042": {
|
| 372 |
+
"content": "<extra_id_257>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"256043": {
|
| 380 |
+
"content": "<extra_id_256>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"256044": {
|
| 388 |
+
"content": "<extra_id_255>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"256045": {
|
| 396 |
+
"content": "<extra_id_254>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"256046": {
|
| 404 |
+
"content": "<extra_id_253>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"256047": {
|
| 412 |
+
"content": "<extra_id_252>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"256048": {
|
| 420 |
+
"content": "<extra_id_251>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"256049": {
|
| 428 |
+
"content": "<extra_id_250>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"256050": {
|
| 436 |
+
"content": "<extra_id_249>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"256051": {
|
| 444 |
+
"content": "<extra_id_248>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"256052": {
|
| 452 |
+
"content": "<extra_id_247>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"256053": {
|
| 460 |
+
"content": "<extra_id_246>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"256054": {
|
| 468 |
+
"content": "<extra_id_245>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"256055": {
|
| 476 |
+
"content": "<extra_id_244>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"256056": {
|
| 484 |
+
"content": "<extra_id_243>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"256057": {
|
| 492 |
+
"content": "<extra_id_242>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"256058": {
|
| 500 |
+
"content": "<extra_id_241>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"256059": {
|
| 508 |
+
"content": "<extra_id_240>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"256060": {
|
| 516 |
+
"content": "<extra_id_239>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"256061": {
|
| 524 |
+
"content": "<extra_id_238>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"256062": {
|
| 532 |
+
"content": "<extra_id_237>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"256063": {
|
| 540 |
+
"content": "<extra_id_236>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"256064": {
|
| 548 |
+
"content": "<extra_id_235>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"256065": {
|
| 556 |
+
"content": "<extra_id_234>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"256066": {
|
| 564 |
+
"content": "<extra_id_233>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"256067": {
|
| 572 |
+
"content": "<extra_id_232>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"256068": {
|
| 580 |
+
"content": "<extra_id_231>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"256069": {
|
| 588 |
+
"content": "<extra_id_230>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"256070": {
|
| 596 |
+
"content": "<extra_id_229>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"256071": {
|
| 604 |
+
"content": "<extra_id_228>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"256072": {
|
| 612 |
+
"content": "<extra_id_227>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"256073": {
|
| 620 |
+
"content": "<extra_id_226>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"256074": {
|
| 628 |
+
"content": "<extra_id_225>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"256075": {
|
| 636 |
+
"content": "<extra_id_224>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"256076": {
|
| 644 |
+
"content": "<extra_id_223>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"256077": {
|
| 652 |
+
"content": "<extra_id_222>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"256078": {
|
| 660 |
+
"content": "<extra_id_221>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"256079": {
|
| 668 |
+
"content": "<extra_id_220>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"256080": {
|
| 676 |
+
"content": "<extra_id_219>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"256081": {
|
| 684 |
+
"content": "<extra_id_218>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"256082": {
|
| 692 |
+
"content": "<extra_id_217>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"256083": {
|
| 700 |
+
"content": "<extra_id_216>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"256084": {
|
| 708 |
+
"content": "<extra_id_215>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"256085": {
|
| 716 |
+
"content": "<extra_id_214>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"256086": {
|
| 724 |
+
"content": "<extra_id_213>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"256087": {
|
| 732 |
+
"content": "<extra_id_212>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"256088": {
|
| 740 |
+
"content": "<extra_id_211>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"256089": {
|
| 748 |
+
"content": "<extra_id_210>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"256090": {
|
| 756 |
+
"content": "<extra_id_209>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"256091": {
|
| 764 |
+
"content": "<extra_id_208>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"256092": {
|
| 772 |
+
"content": "<extra_id_207>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"256093": {
|
| 780 |
+
"content": "<extra_id_206>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"256094": {
|
| 788 |
+
"content": "<extra_id_205>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"256095": {
|
| 796 |
+
"content": "<extra_id_204>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"256096": {
|
| 804 |
+
"content": "<extra_id_203>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"256097": {
|
| 812 |
+
"content": "<extra_id_202>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"256098": {
|
| 820 |
+
"content": "<extra_id_201>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"256099": {
|
| 828 |
+
"content": "<extra_id_200>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"256100": {
|
| 836 |
+
"content": "<extra_id_199>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"256101": {
|
| 844 |
+
"content": "<extra_id_198>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"256102": {
|
| 852 |
+
"content": "<extra_id_197>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"256103": {
|
| 860 |
+
"content": "<extra_id_196>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"256104": {
|
| 868 |
+
"content": "<extra_id_195>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"256105": {
|
| 876 |
+
"content": "<extra_id_194>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"256106": {
|
| 884 |
+
"content": "<extra_id_193>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"256107": {
|
| 892 |
+
"content": "<extra_id_192>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"256108": {
|
| 900 |
+
"content": "<extra_id_191>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"256109": {
|
| 908 |
+
"content": "<extra_id_190>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"256110": {
|
| 916 |
+
"content": "<extra_id_189>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"256111": {
|
| 924 |
+
"content": "<extra_id_188>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"256112": {
|
| 932 |
+
"content": "<extra_id_187>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"256113": {
|
| 940 |
+
"content": "<extra_id_186>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"256114": {
|
| 948 |
+
"content": "<extra_id_185>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"256115": {
|
| 956 |
+
"content": "<extra_id_184>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"256116": {
|
| 964 |
+
"content": "<extra_id_183>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"256117": {
|
| 972 |
+
"content": "<extra_id_182>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"256118": {
|
| 980 |
+
"content": "<extra_id_181>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"256119": {
|
| 988 |
+
"content": "<extra_id_180>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"256120": {
|
| 996 |
+
"content": "<extra_id_179>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"256121": {
|
| 1004 |
+
"content": "<extra_id_178>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"256122": {
|
| 1012 |
+
"content": "<extra_id_177>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"256123": {
|
| 1020 |
+
"content": "<extra_id_176>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"256124": {
|
| 1028 |
+
"content": "<extra_id_175>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"256125": {
|
| 1036 |
+
"content": "<extra_id_174>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"256126": {
|
| 1044 |
+
"content": "<extra_id_173>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"256127": {
|
| 1052 |
+
"content": "<extra_id_172>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"256128": {
|
| 1060 |
+
"content": "<extra_id_171>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"256129": {
|
| 1068 |
+
"content": "<extra_id_170>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"256130": {
|
| 1076 |
+
"content": "<extra_id_169>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"256131": {
|
| 1084 |
+
"content": "<extra_id_168>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"256132": {
|
| 1092 |
+
"content": "<extra_id_167>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"256133": {
|
| 1100 |
+
"content": "<extra_id_166>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"256134": {
|
| 1108 |
+
"content": "<extra_id_165>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"256135": {
|
| 1116 |
+
"content": "<extra_id_164>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"256136": {
|
| 1124 |
+
"content": "<extra_id_163>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"256137": {
|
| 1132 |
+
"content": "<extra_id_162>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"256138": {
|
| 1140 |
+
"content": "<extra_id_161>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"256139": {
|
| 1148 |
+
"content": "<extra_id_160>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"256140": {
|
| 1156 |
+
"content": "<extra_id_159>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"256141": {
|
| 1164 |
+
"content": "<extra_id_158>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"256142": {
|
| 1172 |
+
"content": "<extra_id_157>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"256143": {
|
| 1180 |
+
"content": "<extra_id_156>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"256144": {
|
| 1188 |
+
"content": "<extra_id_155>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"256145": {
|
| 1196 |
+
"content": "<extra_id_154>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"256146": {
|
| 1204 |
+
"content": "<extra_id_153>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"256147": {
|
| 1212 |
+
"content": "<extra_id_152>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"256148": {
|
| 1220 |
+
"content": "<extra_id_151>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"256149": {
|
| 1228 |
+
"content": "<extra_id_150>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"256150": {
|
| 1236 |
+
"content": "<extra_id_149>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"256151": {
|
| 1244 |
+
"content": "<extra_id_148>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"256152": {
|
| 1252 |
+
"content": "<extra_id_147>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"256153": {
|
| 1260 |
+
"content": "<extra_id_146>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"256154": {
|
| 1268 |
+
"content": "<extra_id_145>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"256155": {
|
| 1276 |
+
"content": "<extra_id_144>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"256156": {
|
| 1284 |
+
"content": "<extra_id_143>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"256157": {
|
| 1292 |
+
"content": "<extra_id_142>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"256158": {
|
| 1300 |
+
"content": "<extra_id_141>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"256159": {
|
| 1308 |
+
"content": "<extra_id_140>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"256160": {
|
| 1316 |
+
"content": "<extra_id_139>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"256161": {
|
| 1324 |
+
"content": "<extra_id_138>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"256162": {
|
| 1332 |
+
"content": "<extra_id_137>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"256163": {
|
| 1340 |
+
"content": "<extra_id_136>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"256164": {
|
| 1348 |
+
"content": "<extra_id_135>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"256165": {
|
| 1356 |
+
"content": "<extra_id_134>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"256166": {
|
| 1364 |
+
"content": "<extra_id_133>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"256167": {
|
| 1372 |
+
"content": "<extra_id_132>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"256168": {
|
| 1380 |
+
"content": "<extra_id_131>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"256169": {
|
| 1388 |
+
"content": "<extra_id_130>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"256170": {
|
| 1396 |
+
"content": "<extra_id_129>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"256171": {
|
| 1404 |
+
"content": "<extra_id_128>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"256172": {
|
| 1412 |
+
"content": "<extra_id_127>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"256173": {
|
| 1420 |
+
"content": "<extra_id_126>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"256174": {
|
| 1428 |
+
"content": "<extra_id_125>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"256175": {
|
| 1436 |
+
"content": "<extra_id_124>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"256176": {
|
| 1444 |
+
"content": "<extra_id_123>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"256177": {
|
| 1452 |
+
"content": "<extra_id_122>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"256178": {
|
| 1460 |
+
"content": "<extra_id_121>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"256179": {
|
| 1468 |
+
"content": "<extra_id_120>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"256180": {
|
| 1476 |
+
"content": "<extra_id_119>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"256181": {
|
| 1484 |
+
"content": "<extra_id_118>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"256182": {
|
| 1492 |
+
"content": "<extra_id_117>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"256183": {
|
| 1500 |
+
"content": "<extra_id_116>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"256184": {
|
| 1508 |
+
"content": "<extra_id_115>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"256185": {
|
| 1516 |
+
"content": "<extra_id_114>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"256186": {
|
| 1524 |
+
"content": "<extra_id_113>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"256187": {
|
| 1532 |
+
"content": "<extra_id_112>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"256188": {
|
| 1540 |
+
"content": "<extra_id_111>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"256189": {
|
| 1548 |
+
"content": "<extra_id_110>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"256190": {
|
| 1556 |
+
"content": "<extra_id_109>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"256191": {
|
| 1564 |
+
"content": "<extra_id_108>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"256192": {
|
| 1572 |
+
"content": "<extra_id_107>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"256193": {
|
| 1580 |
+
"content": "<extra_id_106>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"256194": {
|
| 1588 |
+
"content": "<extra_id_105>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"256195": {
|
| 1596 |
+
"content": "<extra_id_104>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"256196": {
|
| 1604 |
+
"content": "<extra_id_103>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"256197": {
|
| 1612 |
+
"content": "<extra_id_102>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"256198": {
|
| 1620 |
+
"content": "<extra_id_101>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"256199": {
|
| 1628 |
+
"content": "<extra_id_100>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"256200": {
|
| 1636 |
+
"content": "<extra_id_99>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"256201": {
|
| 1644 |
+
"content": "<extra_id_98>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"256202": {
|
| 1652 |
+
"content": "<extra_id_97>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"256203": {
|
| 1660 |
+
"content": "<extra_id_96>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"256204": {
|
| 1668 |
+
"content": "<extra_id_95>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"256205": {
|
| 1676 |
+
"content": "<extra_id_94>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"256206": {
|
| 1684 |
+
"content": "<extra_id_93>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"256207": {
|
| 1692 |
+
"content": "<extra_id_92>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"256208": {
|
| 1700 |
+
"content": "<extra_id_91>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"256209": {
|
| 1708 |
+
"content": "<extra_id_90>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"256210": {
|
| 1716 |
+
"content": "<extra_id_89>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"256211": {
|
| 1724 |
+
"content": "<extra_id_88>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"256212": {
|
| 1732 |
+
"content": "<extra_id_87>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"256213": {
|
| 1740 |
+
"content": "<extra_id_86>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"256214": {
|
| 1748 |
+
"content": "<extra_id_85>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"256215": {
|
| 1756 |
+
"content": "<extra_id_84>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"256216": {
|
| 1764 |
+
"content": "<extra_id_83>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"256217": {
|
| 1772 |
+
"content": "<extra_id_82>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"256218": {
|
| 1780 |
+
"content": "<extra_id_81>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"256219": {
|
| 1788 |
+
"content": "<extra_id_80>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"256220": {
|
| 1796 |
+
"content": "<extra_id_79>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"256221": {
|
| 1804 |
+
"content": "<extra_id_78>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"256222": {
|
| 1812 |
+
"content": "<extra_id_77>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"256223": {
|
| 1820 |
+
"content": "<extra_id_76>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"256224": {
|
| 1828 |
+
"content": "<extra_id_75>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"256225": {
|
| 1836 |
+
"content": "<extra_id_74>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"256226": {
|
| 1844 |
+
"content": "<extra_id_73>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"256227": {
|
| 1852 |
+
"content": "<extra_id_72>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"256228": {
|
| 1860 |
+
"content": "<extra_id_71>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"256229": {
|
| 1868 |
+
"content": "<extra_id_70>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"256230": {
|
| 1876 |
+
"content": "<extra_id_69>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"256231": {
|
| 1884 |
+
"content": "<extra_id_68>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"256232": {
|
| 1892 |
+
"content": "<extra_id_67>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"256233": {
|
| 1900 |
+
"content": "<extra_id_66>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"256234": {
|
| 1908 |
+
"content": "<extra_id_65>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"256235": {
|
| 1916 |
+
"content": "<extra_id_64>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"256236": {
|
| 1924 |
+
"content": "<extra_id_63>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"256237": {
|
| 1932 |
+
"content": "<extra_id_62>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"256238": {
|
| 1940 |
+
"content": "<extra_id_61>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"256239": {
|
| 1948 |
+
"content": "<extra_id_60>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"256240": {
|
| 1956 |
+
"content": "<extra_id_59>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"256241": {
|
| 1964 |
+
"content": "<extra_id_58>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"256242": {
|
| 1972 |
+
"content": "<extra_id_57>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"256243": {
|
| 1980 |
+
"content": "<extra_id_56>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"256244": {
|
| 1988 |
+
"content": "<extra_id_55>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"256245": {
|
| 1996 |
+
"content": "<extra_id_54>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"256246": {
|
| 2004 |
+
"content": "<extra_id_53>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"256247": {
|
| 2012 |
+
"content": "<extra_id_52>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"256248": {
|
| 2020 |
+
"content": "<extra_id_51>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"256249": {
|
| 2028 |
+
"content": "<extra_id_50>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"256250": {
|
| 2036 |
+
"content": "<extra_id_49>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"256251": {
|
| 2044 |
+
"content": "<extra_id_48>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"256252": {
|
| 2052 |
+
"content": "<extra_id_47>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
},
|
| 2059 |
+
"256253": {
|
| 2060 |
+
"content": "<extra_id_46>",
|
| 2061 |
+
"lstrip": false,
|
| 2062 |
+
"normalized": false,
|
| 2063 |
+
"rstrip": false,
|
| 2064 |
+
"single_word": false,
|
| 2065 |
+
"special": true
|
| 2066 |
+
},
|
| 2067 |
+
"256254": {
|
| 2068 |
+
"content": "<extra_id_45>",
|
| 2069 |
+
"lstrip": false,
|
| 2070 |
+
"normalized": false,
|
| 2071 |
+
"rstrip": false,
|
| 2072 |
+
"single_word": false,
|
| 2073 |
+
"special": true
|
| 2074 |
+
},
|
| 2075 |
+
"256255": {
|
| 2076 |
+
"content": "<extra_id_44>",
|
| 2077 |
+
"lstrip": false,
|
| 2078 |
+
"normalized": false,
|
| 2079 |
+
"rstrip": false,
|
| 2080 |
+
"single_word": false,
|
| 2081 |
+
"special": true
|
| 2082 |
+
},
|
| 2083 |
+
"256256": {
|
| 2084 |
+
"content": "<extra_id_43>",
|
| 2085 |
+
"lstrip": false,
|
| 2086 |
+
"normalized": false,
|
| 2087 |
+
"rstrip": false,
|
| 2088 |
+
"single_word": false,
|
| 2089 |
+
"special": true
|
| 2090 |
+
},
|
| 2091 |
+
"256257": {
|
| 2092 |
+
"content": "<extra_id_42>",
|
| 2093 |
+
"lstrip": false,
|
| 2094 |
+
"normalized": false,
|
| 2095 |
+
"rstrip": false,
|
| 2096 |
+
"single_word": false,
|
| 2097 |
+
"special": true
|
| 2098 |
+
},
|
| 2099 |
+
"256258": {
|
| 2100 |
+
"content": "<extra_id_41>",
|
| 2101 |
+
"lstrip": false,
|
| 2102 |
+
"normalized": false,
|
| 2103 |
+
"rstrip": false,
|
| 2104 |
+
"single_word": false,
|
| 2105 |
+
"special": true
|
| 2106 |
+
},
|
| 2107 |
+
"256259": {
|
| 2108 |
+
"content": "<extra_id_40>",
|
| 2109 |
+
"lstrip": false,
|
| 2110 |
+
"normalized": false,
|
| 2111 |
+
"rstrip": false,
|
| 2112 |
+
"single_word": false,
|
| 2113 |
+
"special": true
|
| 2114 |
+
},
|
| 2115 |
+
"256260": {
|
| 2116 |
+
"content": "<extra_id_39>",
|
| 2117 |
+
"lstrip": false,
|
| 2118 |
+
"normalized": false,
|
| 2119 |
+
"rstrip": false,
|
| 2120 |
+
"single_word": false,
|
| 2121 |
+
"special": true
|
| 2122 |
+
},
|
| 2123 |
+
"256261": {
|
| 2124 |
+
"content": "<extra_id_38>",
|
| 2125 |
+
"lstrip": false,
|
| 2126 |
+
"normalized": false,
|
| 2127 |
+
"rstrip": false,
|
| 2128 |
+
"single_word": false,
|
| 2129 |
+
"special": true
|
| 2130 |
+
},
|
| 2131 |
+
"256262": {
|
| 2132 |
+
"content": "<extra_id_37>",
|
| 2133 |
+
"lstrip": false,
|
| 2134 |
+
"normalized": false,
|
| 2135 |
+
"rstrip": false,
|
| 2136 |
+
"single_word": false,
|
| 2137 |
+
"special": true
|
| 2138 |
+
},
|
| 2139 |
+
"256263": {
|
| 2140 |
+
"content": "<extra_id_36>",
|
| 2141 |
+
"lstrip": false,
|
| 2142 |
+
"normalized": false,
|
| 2143 |
+
"rstrip": false,
|
| 2144 |
+
"single_word": false,
|
| 2145 |
+
"special": true
|
| 2146 |
+
},
|
| 2147 |
+
"256264": {
|
| 2148 |
+
"content": "<extra_id_35>",
|
| 2149 |
+
"lstrip": false,
|
| 2150 |
+
"normalized": false,
|
| 2151 |
+
"rstrip": false,
|
| 2152 |
+
"single_word": false,
|
| 2153 |
+
"special": true
|
| 2154 |
+
},
|
| 2155 |
+
"256265": {
|
| 2156 |
+
"content": "<extra_id_34>",
|
| 2157 |
+
"lstrip": false,
|
| 2158 |
+
"normalized": false,
|
| 2159 |
+
"rstrip": false,
|
| 2160 |
+
"single_word": false,
|
| 2161 |
+
"special": true
|
| 2162 |
+
},
|
| 2163 |
+
"256266": {
|
| 2164 |
+
"content": "<extra_id_33>",
|
| 2165 |
+
"lstrip": false,
|
| 2166 |
+
"normalized": false,
|
| 2167 |
+
"rstrip": false,
|
| 2168 |
+
"single_word": false,
|
| 2169 |
+
"special": true
|
| 2170 |
+
},
|
| 2171 |
+
"256267": {
|
| 2172 |
+
"content": "<extra_id_32>",
|
| 2173 |
+
"lstrip": false,
|
| 2174 |
+
"normalized": false,
|
| 2175 |
+
"rstrip": false,
|
| 2176 |
+
"single_word": false,
|
| 2177 |
+
"special": true
|
| 2178 |
+
},
|
| 2179 |
+
"256268": {
|
| 2180 |
+
"content": "<extra_id_31>",
|
| 2181 |
+
"lstrip": false,
|
| 2182 |
+
"normalized": false,
|
| 2183 |
+
"rstrip": false,
|
| 2184 |
+
"single_word": false,
|
| 2185 |
+
"special": true
|
| 2186 |
+
},
|
| 2187 |
+
"256269": {
|
| 2188 |
+
"content": "<extra_id_30>",
|
| 2189 |
+
"lstrip": false,
|
| 2190 |
+
"normalized": false,
|
| 2191 |
+
"rstrip": false,
|
| 2192 |
+
"single_word": false,
|
| 2193 |
+
"special": true
|
| 2194 |
+
},
|
| 2195 |
+
"256270": {
|
| 2196 |
+
"content": "<extra_id_29>",
|
| 2197 |
+
"lstrip": false,
|
| 2198 |
+
"normalized": false,
|
| 2199 |
+
"rstrip": false,
|
| 2200 |
+
"single_word": false,
|
| 2201 |
+
"special": true
|
| 2202 |
+
},
|
| 2203 |
+
"256271": {
|
| 2204 |
+
"content": "<extra_id_28>",
|
| 2205 |
+
"lstrip": false,
|
| 2206 |
+
"normalized": false,
|
| 2207 |
+
"rstrip": false,
|
| 2208 |
+
"single_word": false,
|
| 2209 |
+
"special": true
|
| 2210 |
+
},
|
| 2211 |
+
"256272": {
|
| 2212 |
+
"content": "<extra_id_27>",
|
| 2213 |
+
"lstrip": false,
|
| 2214 |
+
"normalized": false,
|
| 2215 |
+
"rstrip": false,
|
| 2216 |
+
"single_word": false,
|
| 2217 |
+
"special": true
|
| 2218 |
+
},
|
| 2219 |
+
"256273": {
|
| 2220 |
+
"content": "<extra_id_26>",
|
| 2221 |
+
"lstrip": false,
|
| 2222 |
+
"normalized": false,
|
| 2223 |
+
"rstrip": false,
|
| 2224 |
+
"single_word": false,
|
| 2225 |
+
"special": true
|
| 2226 |
+
},
|
| 2227 |
+
"256274": {
|
| 2228 |
+
"content": "<extra_id_25>",
|
| 2229 |
+
"lstrip": false,
|
| 2230 |
+
"normalized": false,
|
| 2231 |
+
"rstrip": false,
|
| 2232 |
+
"single_word": false,
|
| 2233 |
+
"special": true
|
| 2234 |
+
},
|
| 2235 |
+
"256275": {
|
| 2236 |
+
"content": "<extra_id_24>",
|
| 2237 |
+
"lstrip": false,
|
| 2238 |
+
"normalized": false,
|
| 2239 |
+
"rstrip": false,
|
| 2240 |
+
"single_word": false,
|
| 2241 |
+
"special": true
|
| 2242 |
+
},
|
| 2243 |
+
"256276": {
|
| 2244 |
+
"content": "<extra_id_23>",
|
| 2245 |
+
"lstrip": false,
|
| 2246 |
+
"normalized": false,
|
| 2247 |
+
"rstrip": false,
|
| 2248 |
+
"single_word": false,
|
| 2249 |
+
"special": true
|
| 2250 |
+
},
|
| 2251 |
+
"256277": {
|
| 2252 |
+
"content": "<extra_id_22>",
|
| 2253 |
+
"lstrip": false,
|
| 2254 |
+
"normalized": false,
|
| 2255 |
+
"rstrip": false,
|
| 2256 |
+
"single_word": false,
|
| 2257 |
+
"special": true
|
| 2258 |
+
},
|
| 2259 |
+
"256278": {
|
| 2260 |
+
"content": "<extra_id_21>",
|
| 2261 |
+
"lstrip": false,
|
| 2262 |
+
"normalized": false,
|
| 2263 |
+
"rstrip": false,
|
| 2264 |
+
"single_word": false,
|
| 2265 |
+
"special": true
|
| 2266 |
+
},
|
| 2267 |
+
"256279": {
|
| 2268 |
+
"content": "<extra_id_20>",
|
| 2269 |
+
"lstrip": false,
|
| 2270 |
+
"normalized": false,
|
| 2271 |
+
"rstrip": false,
|
| 2272 |
+
"single_word": false,
|
| 2273 |
+
"special": true
|
| 2274 |
+
},
|
| 2275 |
+
"256280": {
|
| 2276 |
+
"content": "<extra_id_19>",
|
| 2277 |
+
"lstrip": false,
|
| 2278 |
+
"normalized": false,
|
| 2279 |
+
"rstrip": false,
|
| 2280 |
+
"single_word": false,
|
| 2281 |
+
"special": true
|
| 2282 |
+
},
|
| 2283 |
+
"256281": {
|
| 2284 |
+
"content": "<extra_id_18>",
|
| 2285 |
+
"lstrip": false,
|
| 2286 |
+
"normalized": false,
|
| 2287 |
+
"rstrip": false,
|
| 2288 |
+
"single_word": false,
|
| 2289 |
+
"special": true
|
| 2290 |
+
},
|
| 2291 |
+
"256282": {
|
| 2292 |
+
"content": "<extra_id_17>",
|
| 2293 |
+
"lstrip": false,
|
| 2294 |
+
"normalized": false,
|
| 2295 |
+
"rstrip": false,
|
| 2296 |
+
"single_word": false,
|
| 2297 |
+
"special": true
|
| 2298 |
+
},
|
| 2299 |
+
"256283": {
|
| 2300 |
+
"content": "<extra_id_16>",
|
| 2301 |
+
"lstrip": false,
|
| 2302 |
+
"normalized": false,
|
| 2303 |
+
"rstrip": false,
|
| 2304 |
+
"single_word": false,
|
| 2305 |
+
"special": true
|
| 2306 |
+
},
|
| 2307 |
+
"256284": {
|
| 2308 |
+
"content": "<extra_id_15>",
|
| 2309 |
+
"lstrip": false,
|
| 2310 |
+
"normalized": false,
|
| 2311 |
+
"rstrip": false,
|
| 2312 |
+
"single_word": false,
|
| 2313 |
+
"special": true
|
| 2314 |
+
},
|
| 2315 |
+
"256285": {
|
| 2316 |
+
"content": "<extra_id_14>",
|
| 2317 |
+
"lstrip": false,
|
| 2318 |
+
"normalized": false,
|
| 2319 |
+
"rstrip": false,
|
| 2320 |
+
"single_word": false,
|
| 2321 |
+
"special": true
|
| 2322 |
+
},
|
| 2323 |
+
"256286": {
|
| 2324 |
+
"content": "<extra_id_13>",
|
| 2325 |
+
"lstrip": false,
|
| 2326 |
+
"normalized": false,
|
| 2327 |
+
"rstrip": false,
|
| 2328 |
+
"single_word": false,
|
| 2329 |
+
"special": true
|
| 2330 |
+
},
|
| 2331 |
+
"256287": {
|
| 2332 |
+
"content": "<extra_id_12>",
|
| 2333 |
+
"lstrip": false,
|
| 2334 |
+
"normalized": false,
|
| 2335 |
+
"rstrip": false,
|
| 2336 |
+
"single_word": false,
|
| 2337 |
+
"special": true
|
| 2338 |
+
},
|
| 2339 |
+
"256288": {
|
| 2340 |
+
"content": "<extra_id_11>",
|
| 2341 |
+
"lstrip": false,
|
| 2342 |
+
"normalized": false,
|
| 2343 |
+
"rstrip": false,
|
| 2344 |
+
"single_word": false,
|
| 2345 |
+
"special": true
|
| 2346 |
+
},
|
| 2347 |
+
"256289": {
|
| 2348 |
+
"content": "<extra_id_10>",
|
| 2349 |
+
"lstrip": false,
|
| 2350 |
+
"normalized": false,
|
| 2351 |
+
"rstrip": false,
|
| 2352 |
+
"single_word": false,
|
| 2353 |
+
"special": true
|
| 2354 |
+
},
|
| 2355 |
+
"256290": {
|
| 2356 |
+
"content": "<extra_id_9>",
|
| 2357 |
+
"lstrip": false,
|
| 2358 |
+
"normalized": false,
|
| 2359 |
+
"rstrip": false,
|
| 2360 |
+
"single_word": false,
|
| 2361 |
+
"special": true
|
| 2362 |
+
},
|
| 2363 |
+
"256291": {
|
| 2364 |
+
"content": "<extra_id_8>",
|
| 2365 |
+
"lstrip": false,
|
| 2366 |
+
"normalized": false,
|
| 2367 |
+
"rstrip": false,
|
| 2368 |
+
"single_word": false,
|
| 2369 |
+
"special": true
|
| 2370 |
+
},
|
| 2371 |
+
"256292": {
|
| 2372 |
+
"content": "<extra_id_7>",
|
| 2373 |
+
"lstrip": false,
|
| 2374 |
+
"normalized": false,
|
| 2375 |
+
"rstrip": false,
|
| 2376 |
+
"single_word": false,
|
| 2377 |
+
"special": true
|
| 2378 |
+
},
|
| 2379 |
+
"256293": {
|
| 2380 |
+
"content": "<extra_id_6>",
|
| 2381 |
+
"lstrip": false,
|
| 2382 |
+
"normalized": false,
|
| 2383 |
+
"rstrip": false,
|
| 2384 |
+
"single_word": false,
|
| 2385 |
+
"special": true
|
| 2386 |
+
},
|
| 2387 |
+
"256294": {
|
| 2388 |
+
"content": "<extra_id_5>",
|
| 2389 |
+
"lstrip": false,
|
| 2390 |
+
"normalized": false,
|
| 2391 |
+
"rstrip": false,
|
| 2392 |
+
"single_word": false,
|
| 2393 |
+
"special": true
|
| 2394 |
+
},
|
| 2395 |
+
"256295": {
|
| 2396 |
+
"content": "<extra_id_4>",
|
| 2397 |
+
"lstrip": false,
|
| 2398 |
+
"normalized": false,
|
| 2399 |
+
"rstrip": false,
|
| 2400 |
+
"single_word": false,
|
| 2401 |
+
"special": true
|
| 2402 |
+
},
|
| 2403 |
+
"256296": {
|
| 2404 |
+
"content": "<extra_id_3>",
|
| 2405 |
+
"lstrip": false,
|
| 2406 |
+
"normalized": false,
|
| 2407 |
+
"rstrip": false,
|
| 2408 |
+
"single_word": false,
|
| 2409 |
+
"special": true
|
| 2410 |
+
},
|
| 2411 |
+
"256297": {
|
| 2412 |
+
"content": "<extra_id_2>",
|
| 2413 |
+
"lstrip": false,
|
| 2414 |
+
"normalized": false,
|
| 2415 |
+
"rstrip": false,
|
| 2416 |
+
"single_word": false,
|
| 2417 |
+
"special": true
|
| 2418 |
+
},
|
| 2419 |
+
"256298": {
|
| 2420 |
+
"content": "<extra_id_1>",
|
| 2421 |
+
"lstrip": false,
|
| 2422 |
+
"normalized": false,
|
| 2423 |
+
"rstrip": false,
|
| 2424 |
+
"single_word": false,
|
| 2425 |
+
"special": true
|
| 2426 |
+
},
|
| 2427 |
+
"256299": {
|
| 2428 |
+
"content": "<extra_id_0>",
|
| 2429 |
+
"lstrip": false,
|
| 2430 |
+
"normalized": false,
|
| 2431 |
+
"rstrip": false,
|
| 2432 |
+
"single_word": false,
|
| 2433 |
+
"special": true
|
| 2434 |
+
}
|
| 2435 |
+
},
|
| 2436 |
+
"additional_special_tokens": [
|
| 2437 |
+
"<extra_id_0>",
|
| 2438 |
+
"<extra_id_1>",
|
| 2439 |
+
"<extra_id_2>",
|
| 2440 |
+
"<extra_id_3>",
|
| 2441 |
+
"<extra_id_4>",
|
| 2442 |
+
"<extra_id_5>",
|
| 2443 |
+
"<extra_id_6>",
|
| 2444 |
+
"<extra_id_7>",
|
| 2445 |
+
"<extra_id_8>",
|
| 2446 |
+
"<extra_id_9>",
|
| 2447 |
+
"<extra_id_10>",
|
| 2448 |
+
"<extra_id_11>",
|
| 2449 |
+
"<extra_id_12>",
|
| 2450 |
+
"<extra_id_13>",
|
| 2451 |
+
"<extra_id_14>",
|
| 2452 |
+
"<extra_id_15>",
|
| 2453 |
+
"<extra_id_16>",
|
| 2454 |
+
"<extra_id_17>",
|
| 2455 |
+
"<extra_id_18>",
|
| 2456 |
+
"<extra_id_19>",
|
| 2457 |
+
"<extra_id_20>",
|
| 2458 |
+
"<extra_id_21>",
|
| 2459 |
+
"<extra_id_22>",
|
| 2460 |
+
"<extra_id_23>",
|
| 2461 |
+
"<extra_id_24>",
|
| 2462 |
+
"<extra_id_25>",
|
| 2463 |
+
"<extra_id_26>",
|
| 2464 |
+
"<extra_id_27>",
|
| 2465 |
+
"<extra_id_28>",
|
| 2466 |
+
"<extra_id_29>",
|
| 2467 |
+
"<extra_id_30>",
|
| 2468 |
+
"<extra_id_31>",
|
| 2469 |
+
"<extra_id_32>",
|
| 2470 |
+
"<extra_id_33>",
|
| 2471 |
+
"<extra_id_34>",
|
| 2472 |
+
"<extra_id_35>",
|
| 2473 |
+
"<extra_id_36>",
|
| 2474 |
+
"<extra_id_37>",
|
| 2475 |
+
"<extra_id_38>",
|
| 2476 |
+
"<extra_id_39>",
|
| 2477 |
+
"<extra_id_40>",
|
| 2478 |
+
"<extra_id_41>",
|
| 2479 |
+
"<extra_id_42>",
|
| 2480 |
+
"<extra_id_43>",
|
| 2481 |
+
"<extra_id_44>",
|
| 2482 |
+
"<extra_id_45>",
|
| 2483 |
+
"<extra_id_46>",
|
| 2484 |
+
"<extra_id_47>",
|
| 2485 |
+
"<extra_id_48>",
|
| 2486 |
+
"<extra_id_49>",
|
| 2487 |
+
"<extra_id_50>",
|
| 2488 |
+
"<extra_id_51>",
|
| 2489 |
+
"<extra_id_52>",
|
| 2490 |
+
"<extra_id_53>",
|
| 2491 |
+
"<extra_id_54>",
|
| 2492 |
+
"<extra_id_55>",
|
| 2493 |
+
"<extra_id_56>",
|
| 2494 |
+
"<extra_id_57>",
|
| 2495 |
+
"<extra_id_58>",
|
| 2496 |
+
"<extra_id_59>",
|
| 2497 |
+
"<extra_id_60>",
|
| 2498 |
+
"<extra_id_61>",
|
| 2499 |
+
"<extra_id_62>",
|
| 2500 |
+
"<extra_id_63>",
|
| 2501 |
+
"<extra_id_64>",
|
| 2502 |
+
"<extra_id_65>",
|
| 2503 |
+
"<extra_id_66>",
|
| 2504 |
+
"<extra_id_67>",
|
| 2505 |
+
"<extra_id_68>",
|
| 2506 |
+
"<extra_id_69>",
|
| 2507 |
+
"<extra_id_70>",
|
| 2508 |
+
"<extra_id_71>",
|
| 2509 |
+
"<extra_id_72>",
|
| 2510 |
+
"<extra_id_73>",
|
| 2511 |
+
"<extra_id_74>",
|
| 2512 |
+
"<extra_id_75>",
|
| 2513 |
+
"<extra_id_76>",
|
| 2514 |
+
"<extra_id_77>",
|
| 2515 |
+
"<extra_id_78>",
|
| 2516 |
+
"<extra_id_79>",
|
| 2517 |
+
"<extra_id_80>",
|
| 2518 |
+
"<extra_id_81>",
|
| 2519 |
+
"<extra_id_82>",
|
| 2520 |
+
"<extra_id_83>",
|
| 2521 |
+
"<extra_id_84>",
|
| 2522 |
+
"<extra_id_85>",
|
| 2523 |
+
"<extra_id_86>",
|
| 2524 |
+
"<extra_id_87>",
|
| 2525 |
+
"<extra_id_88>",
|
| 2526 |
+
"<extra_id_89>",
|
| 2527 |
+
"<extra_id_90>",
|
| 2528 |
+
"<extra_id_91>",
|
| 2529 |
+
"<extra_id_92>",
|
| 2530 |
+
"<extra_id_93>",
|
| 2531 |
+
"<extra_id_94>",
|
| 2532 |
+
"<extra_id_95>",
|
| 2533 |
+
"<extra_id_96>",
|
| 2534 |
+
"<extra_id_97>",
|
| 2535 |
+
"<extra_id_98>",
|
| 2536 |
+
"<extra_id_99>",
|
| 2537 |
+
"<extra_id_100>",
|
| 2538 |
+
"<extra_id_101>",
|
| 2539 |
+
"<extra_id_102>",
|
| 2540 |
+
"<extra_id_103>",
|
| 2541 |
+
"<extra_id_104>",
|
| 2542 |
+
"<extra_id_105>",
|
| 2543 |
+
"<extra_id_106>",
|
| 2544 |
+
"<extra_id_107>",
|
| 2545 |
+
"<extra_id_108>",
|
| 2546 |
+
"<extra_id_109>",
|
| 2547 |
+
"<extra_id_110>",
|
| 2548 |
+
"<extra_id_111>",
|
| 2549 |
+
"<extra_id_112>",
|
| 2550 |
+
"<extra_id_113>",
|
| 2551 |
+
"<extra_id_114>",
|
| 2552 |
+
"<extra_id_115>",
|
| 2553 |
+
"<extra_id_116>",
|
| 2554 |
+
"<extra_id_117>",
|
| 2555 |
+
"<extra_id_118>",
|
| 2556 |
+
"<extra_id_119>",
|
| 2557 |
+
"<extra_id_120>",
|
| 2558 |
+
"<extra_id_121>",
|
| 2559 |
+
"<extra_id_122>",
|
| 2560 |
+
"<extra_id_123>",
|
| 2561 |
+
"<extra_id_124>",
|
| 2562 |
+
"<extra_id_125>",
|
| 2563 |
+
"<extra_id_126>",
|
| 2564 |
+
"<extra_id_127>",
|
| 2565 |
+
"<extra_id_128>",
|
| 2566 |
+
"<extra_id_129>",
|
| 2567 |
+
"<extra_id_130>",
|
| 2568 |
+
"<extra_id_131>",
|
| 2569 |
+
"<extra_id_132>",
|
| 2570 |
+
"<extra_id_133>",
|
| 2571 |
+
"<extra_id_134>",
|
| 2572 |
+
"<extra_id_135>",
|
| 2573 |
+
"<extra_id_136>",
|
| 2574 |
+
"<extra_id_137>",
|
| 2575 |
+
"<extra_id_138>",
|
| 2576 |
+
"<extra_id_139>",
|
| 2577 |
+
"<extra_id_140>",
|
| 2578 |
+
"<extra_id_141>",
|
| 2579 |
+
"<extra_id_142>",
|
| 2580 |
+
"<extra_id_143>",
|
| 2581 |
+
"<extra_id_144>",
|
| 2582 |
+
"<extra_id_145>",
|
| 2583 |
+
"<extra_id_146>",
|
| 2584 |
+
"<extra_id_147>",
|
| 2585 |
+
"<extra_id_148>",
|
| 2586 |
+
"<extra_id_149>",
|
| 2587 |
+
"<extra_id_150>",
|
| 2588 |
+
"<extra_id_151>",
|
| 2589 |
+
"<extra_id_152>",
|
| 2590 |
+
"<extra_id_153>",
|
| 2591 |
+
"<extra_id_154>",
|
| 2592 |
+
"<extra_id_155>",
|
| 2593 |
+
"<extra_id_156>",
|
| 2594 |
+
"<extra_id_157>",
|
| 2595 |
+
"<extra_id_158>",
|
| 2596 |
+
"<extra_id_159>",
|
| 2597 |
+
"<extra_id_160>",
|
| 2598 |
+
"<extra_id_161>",
|
| 2599 |
+
"<extra_id_162>",
|
| 2600 |
+
"<extra_id_163>",
|
| 2601 |
+
"<extra_id_164>",
|
| 2602 |
+
"<extra_id_165>",
|
| 2603 |
+
"<extra_id_166>",
|
| 2604 |
+
"<extra_id_167>",
|
| 2605 |
+
"<extra_id_168>",
|
| 2606 |
+
"<extra_id_169>",
|
| 2607 |
+
"<extra_id_170>",
|
| 2608 |
+
"<extra_id_171>",
|
| 2609 |
+
"<extra_id_172>",
|
| 2610 |
+
"<extra_id_173>",
|
| 2611 |
+
"<extra_id_174>",
|
| 2612 |
+
"<extra_id_175>",
|
| 2613 |
+
"<extra_id_176>",
|
| 2614 |
+
"<extra_id_177>",
|
| 2615 |
+
"<extra_id_178>",
|
| 2616 |
+
"<extra_id_179>",
|
| 2617 |
+
"<extra_id_180>",
|
| 2618 |
+
"<extra_id_181>",
|
| 2619 |
+
"<extra_id_182>",
|
| 2620 |
+
"<extra_id_183>",
|
| 2621 |
+
"<extra_id_184>",
|
| 2622 |
+
"<extra_id_185>",
|
| 2623 |
+
"<extra_id_186>",
|
| 2624 |
+
"<extra_id_187>",
|
| 2625 |
+
"<extra_id_188>",
|
| 2626 |
+
"<extra_id_189>",
|
| 2627 |
+
"<extra_id_190>",
|
| 2628 |
+
"<extra_id_191>",
|
| 2629 |
+
"<extra_id_192>",
|
| 2630 |
+
"<extra_id_193>",
|
| 2631 |
+
"<extra_id_194>",
|
| 2632 |
+
"<extra_id_195>",
|
| 2633 |
+
"<extra_id_196>",
|
| 2634 |
+
"<extra_id_197>",
|
| 2635 |
+
"<extra_id_198>",
|
| 2636 |
+
"<extra_id_199>",
|
| 2637 |
+
"<extra_id_200>",
|
| 2638 |
+
"<extra_id_201>",
|
| 2639 |
+
"<extra_id_202>",
|
| 2640 |
+
"<extra_id_203>",
|
| 2641 |
+
"<extra_id_204>",
|
| 2642 |
+
"<extra_id_205>",
|
| 2643 |
+
"<extra_id_206>",
|
| 2644 |
+
"<extra_id_207>",
|
| 2645 |
+
"<extra_id_208>",
|
| 2646 |
+
"<extra_id_209>",
|
| 2647 |
+
"<extra_id_210>",
|
| 2648 |
+
"<extra_id_211>",
|
| 2649 |
+
"<extra_id_212>",
|
| 2650 |
+
"<extra_id_213>",
|
| 2651 |
+
"<extra_id_214>",
|
| 2652 |
+
"<extra_id_215>",
|
| 2653 |
+
"<extra_id_216>",
|
| 2654 |
+
"<extra_id_217>",
|
| 2655 |
+
"<extra_id_218>",
|
| 2656 |
+
"<extra_id_219>",
|
| 2657 |
+
"<extra_id_220>",
|
| 2658 |
+
"<extra_id_221>",
|
| 2659 |
+
"<extra_id_222>",
|
| 2660 |
+
"<extra_id_223>",
|
| 2661 |
+
"<extra_id_224>",
|
| 2662 |
+
"<extra_id_225>",
|
| 2663 |
+
"<extra_id_226>",
|
| 2664 |
+
"<extra_id_227>",
|
| 2665 |
+
"<extra_id_228>",
|
| 2666 |
+
"<extra_id_229>",
|
| 2667 |
+
"<extra_id_230>",
|
| 2668 |
+
"<extra_id_231>",
|
| 2669 |
+
"<extra_id_232>",
|
| 2670 |
+
"<extra_id_233>",
|
| 2671 |
+
"<extra_id_234>",
|
| 2672 |
+
"<extra_id_235>",
|
| 2673 |
+
"<extra_id_236>",
|
| 2674 |
+
"<extra_id_237>",
|
| 2675 |
+
"<extra_id_238>",
|
| 2676 |
+
"<extra_id_239>",
|
| 2677 |
+
"<extra_id_240>",
|
| 2678 |
+
"<extra_id_241>",
|
| 2679 |
+
"<extra_id_242>",
|
| 2680 |
+
"<extra_id_243>",
|
| 2681 |
+
"<extra_id_244>",
|
| 2682 |
+
"<extra_id_245>",
|
| 2683 |
+
"<extra_id_246>",
|
| 2684 |
+
"<extra_id_247>",
|
| 2685 |
+
"<extra_id_248>",
|
| 2686 |
+
"<extra_id_249>",
|
| 2687 |
+
"<extra_id_250>",
|
| 2688 |
+
"<extra_id_251>",
|
| 2689 |
+
"<extra_id_252>",
|
| 2690 |
+
"<extra_id_253>",
|
| 2691 |
+
"<extra_id_254>",
|
| 2692 |
+
"<extra_id_255>",
|
| 2693 |
+
"<extra_id_256>",
|
| 2694 |
+
"<extra_id_257>",
|
| 2695 |
+
"<extra_id_258>",
|
| 2696 |
+
"<extra_id_259>",
|
| 2697 |
+
"<extra_id_260>",
|
| 2698 |
+
"<extra_id_261>",
|
| 2699 |
+
"<extra_id_262>",
|
| 2700 |
+
"<extra_id_263>",
|
| 2701 |
+
"<extra_id_264>",
|
| 2702 |
+
"<extra_id_265>",
|
| 2703 |
+
"<extra_id_266>",
|
| 2704 |
+
"<extra_id_267>",
|
| 2705 |
+
"<extra_id_268>",
|
| 2706 |
+
"<extra_id_269>",
|
| 2707 |
+
"<extra_id_270>",
|
| 2708 |
+
"<extra_id_271>",
|
| 2709 |
+
"<extra_id_272>",
|
| 2710 |
+
"<extra_id_273>",
|
| 2711 |
+
"<extra_id_274>",
|
| 2712 |
+
"<extra_id_275>",
|
| 2713 |
+
"<extra_id_276>",
|
| 2714 |
+
"<extra_id_277>",
|
| 2715 |
+
"<extra_id_278>",
|
| 2716 |
+
"<extra_id_279>",
|
| 2717 |
+
"<extra_id_280>",
|
| 2718 |
+
"<extra_id_281>",
|
| 2719 |
+
"<extra_id_282>",
|
| 2720 |
+
"<extra_id_283>",
|
| 2721 |
+
"<extra_id_284>",
|
| 2722 |
+
"<extra_id_285>",
|
| 2723 |
+
"<extra_id_286>",
|
| 2724 |
+
"<extra_id_287>",
|
| 2725 |
+
"<extra_id_288>",
|
| 2726 |
+
"<extra_id_289>",
|
| 2727 |
+
"<extra_id_290>",
|
| 2728 |
+
"<extra_id_291>",
|
| 2729 |
+
"<extra_id_292>",
|
| 2730 |
+
"<extra_id_293>",
|
| 2731 |
+
"<extra_id_294>",
|
| 2732 |
+
"<extra_id_295>",
|
| 2733 |
+
"<extra_id_296>",
|
| 2734 |
+
"<extra_id_297>",
|
| 2735 |
+
"<extra_id_298>",
|
| 2736 |
+
"<extra_id_299>"
|
| 2737 |
+
],
|
| 2738 |
+
"bos_token": "<s>",
|
| 2739 |
+
"clean_up_tokenization_spaces": true,
|
| 2740 |
+
"eos_token": "</s>",
|
| 2741 |
+
"extra_ids": 300,
|
| 2742 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2743 |
+
"pad_token": "<pad>",
|
| 2744 |
+
"sp_model_kwargs": {},
|
| 2745 |
+
"spaces_between_special_tokens": false,
|
| 2746 |
+
"tokenizer_class": "T5Tokenizer",
|
| 2747 |
+
"unk_token": "<unk>"
|
| 2748 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bf1fb8b03a7c43dc88e8ddb313b68b3a0e1bc37b702867eeb558c9d8f3b6301
|
| 3 |
+
size 5448457056
|
|
@@ -0,0 +1,860 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_GR00T_ROBODOJO_DELTA_MASK": [
|
| 3 |
+
true,
|
| 4 |
+
true,
|
| 5 |
+
true,
|
| 6 |
+
true,
|
| 7 |
+
true,
|
| 8 |
+
true,
|
| 9 |
+
true,
|
| 10 |
+
true,
|
| 11 |
+
true,
|
| 12 |
+
true,
|
| 13 |
+
true,
|
| 14 |
+
true,
|
| 15 |
+
true,
|
| 16 |
+
true
|
| 17 |
+
],
|
| 18 |
+
"_GR00T_ROBODOJO_STATS": {
|
| 19 |
+
"robodojo_arx_x5": {
|
| 20 |
+
"action": {
|
| 21 |
+
"count": 29333632,
|
| 22 |
+
"max": [
|
| 23 |
+
1.8887031078338623,
|
| 24 |
+
2.241629123687744,
|
| 25 |
+
2.3643198013305664,
|
| 26 |
+
2.353733539581299,
|
| 27 |
+
1.684847116470337,
|
| 28 |
+
2.5986948013305664,
|
| 29 |
+
1.0,
|
| 30 |
+
1.6447105407714844,
|
| 31 |
+
2.472832202911377,
|
| 32 |
+
3.1138815879821777,
|
| 33 |
+
2.544224500656128,
|
| 34 |
+
2.4465250968933105,
|
| 35 |
+
2.3557143211364746,
|
| 36 |
+
1.0
|
| 37 |
+
],
|
| 38 |
+
"mean": [
|
| 39 |
+
-0.00016787611640384256,
|
| 40 |
+
3.640991079951193e-05,
|
| 41 |
+
-0.0001244129093475812,
|
| 42 |
+
0.0009861263907153927,
|
| 43 |
+
4.007764372684936e-05,
|
| 44 |
+
-0.0005710965315355596,
|
| 45 |
+
-0.00033464226771561873,
|
| 46 |
+
0.00014757256047559194,
|
| 47 |
+
0.002926647213791033,
|
| 48 |
+
0.002445220311756816,
|
| 49 |
+
-0.0017966633835313532,
|
| 50 |
+
-0.00034538796665606477,
|
| 51 |
+
-0.0010489735053372264,
|
| 52 |
+
-0.0008483530749860559
|
| 53 |
+
],
|
| 54 |
+
"min": [
|
| 55 |
+
-1.9831359386444092,
|
| 56 |
+
-2.3307759761810303,
|
| 57 |
+
-2.36329984664917,
|
| 58 |
+
-2.3512368202209473,
|
| 59 |
+
-1.7914525270462036,
|
| 60 |
+
-2.4492745399475098,
|
| 61 |
+
-1.0,
|
| 62 |
+
-1.6693108081817627,
|
| 63 |
+
-2.261469841003418,
|
| 64 |
+
-2.36698317527771,
|
| 65 |
+
-2.53256893157959,
|
| 66 |
+
-2.4855473041534424,
|
| 67 |
+
-2.839830160140991,
|
| 68 |
+
-1.0
|
| 69 |
+
],
|
| 70 |
+
"q01": [
|
| 71 |
+
-0.5563330262899399,
|
| 72 |
+
-1.164183863401413,
|
| 73 |
+
-0.9725008648633957,
|
| 74 |
+
-0.7879389774799347,
|
| 75 |
+
-0.35899992257356644,
|
| 76 |
+
-0.8268111473321915,
|
| 77 |
+
-0.6629222631454468,
|
| 78 |
+
-0.48305779963731765,
|
| 79 |
+
-1.1301205492019653,
|
| 80 |
+
-0.9574322783946991,
|
| 81 |
+
-0.7862630712985993,
|
| 82 |
+
-0.3646536460518837,
|
| 83 |
+
-0.8233565813302994,
|
| 84 |
+
-0.6629220247268677
|
| 85 |
+
],
|
| 86 |
+
"q99": [
|
| 87 |
+
0.5548361170291902,
|
| 88 |
+
1.0296359968185431,
|
| 89 |
+
0.8563214296102533,
|
| 90 |
+
0.8150562870502474,
|
| 91 |
+
0.39599745541810993,
|
| 92 |
+
0.8352749580144907,
|
| 93 |
+
0.6292134523391724,
|
| 94 |
+
0.4990877494215987,
|
| 95 |
+
1.0044999086856863,
|
| 96 |
+
0.8432489860057832,
|
| 97 |
+
0.78897400379181,
|
| 98 |
+
0.32408514618873596,
|
| 99 |
+
0.7997124117612857,
|
| 100 |
+
0.6112149953842163
|
| 101 |
+
],
|
| 102 |
+
"std": [
|
| 103 |
+
0.1524663344569265,
|
| 104 |
+
0.29040871843218186,
|
| 105 |
+
0.25021202987482355,
|
| 106 |
+
0.2233514194013506,
|
| 107 |
+
0.10648562443390856,
|
| 108 |
+
0.2295837861601856,
|
| 109 |
+
0.16658472644994762,
|
| 110 |
+
0.13469893280906062,
|
| 111 |
+
0.27712445038284145,
|
| 112 |
+
0.24285089420664013,
|
| 113 |
+
0.21544770406738722,
|
| 114 |
+
0.09925954744044597,
|
| 115 |
+
0.22253717352947505,
|
| 116 |
+
0.16110866685153383
|
| 117 |
+
]
|
| 118 |
+
},
|
| 119 |
+
"proprio": {
|
| 120 |
+
"count": 1859602,
|
| 121 |
+
"max": [
|
| 122 |
+
1.7537026405334473,
|
| 123 |
+
3.0546703338623047,
|
| 124 |
+
3.8525187969207764,
|
| 125 |
+
2.0974574089050293,
|
| 126 |
+
1.8103265762329102,
|
| 127 |
+
3.1366536617279053,
|
| 128 |
+
1.0,
|
| 129 |
+
1.6732014417648315,
|
| 130 |
+
3.3797459602355957,
|
| 131 |
+
4.252756595611572,
|
| 132 |
+
2.5287232398986816,
|
| 133 |
+
3.1440579891204834,
|
| 134 |
+
3.0381109714508057,
|
| 135 |
+
1.0
|
| 136 |
+
],
|
| 137 |
+
"mean": [
|
| 138 |
+
-0.20040483418845204,
|
| 139 |
+
0.9260308650671458,
|
| 140 |
+
0.6881893789087474,
|
| 141 |
+
-0.3400484544283471,
|
| 142 |
+
0.06579394032953159,
|
| 143 |
+
0.004003331131509558,
|
| 144 |
+
0.771446548553906,
|
| 145 |
+
0.17299834959584776,
|
| 146 |
+
0.8224941837716736,
|
| 147 |
+
0.6196513047400859,
|
| 148 |
+
-0.3604178625374315,
|
| 149 |
+
-0.06267071413702419,
|
| 150 |
+
0.0037534824507240434,
|
| 151 |
+
0.7860054714056368
|
| 152 |
+
],
|
| 153 |
+
"min": [
|
| 154 |
+
-1.4863648414611816,
|
| 155 |
+
-0.2586335241794586,
|
| 156 |
+
-0.06850092858076096,
|
| 157 |
+
-2.2642147541046143,
|
| 158 |
+
-1.4876768589019775,
|
| 159 |
+
-3.0168392658233643,
|
| 160 |
+
-3.212450869184004e-17,
|
| 161 |
+
-1.4924354553222656,
|
| 162 |
+
-0.27809593081474304,
|
| 163 |
+
-0.18774886429309845,
|
| 164 |
+
-2.5354628562927246,
|
| 165 |
+
-3.0663280487060547,
|
| 166 |
+
-3.0486762523651123,
|
| 167 |
+
-3.212450869184004e-17
|
| 168 |
+
],
|
| 169 |
+
"q01": [
|
| 170 |
+
-1.051365569829941,
|
| 171 |
+
-3.52302449637288e-14,
|
| 172 |
+
1.6996893991849812e-16,
|
| 173 |
+
-1.5984010362625123,
|
| 174 |
+
-0.6003412520885467,
|
| 175 |
+
-1.6678147149085998,
|
| 176 |
+
0.0,
|
| 177 |
+
-0.4500492787361145,
|
| 178 |
+
-2.5859282299029243e-14,
|
| 179 |
+
1.194697284288627e-16,
|
| 180 |
+
-1.6398817586898804,
|
| 181 |
+
-1.263367258310318,
|
| 182 |
+
-1.760098042488098,
|
| 183 |
+
0.0
|
| 184 |
+
],
|
| 185 |
+
"q99": [
|
| 186 |
+
0.5431358617544174,
|
| 187 |
+
2.495765209197998,
|
| 188 |
+
2.492974226474762,
|
| 189 |
+
1.323737324476242,
|
| 190 |
+
1.2496635341644287,
|
| 191 |
+
1.7391636216640465,
|
| 192 |
+
1.0,
|
| 193 |
+
1.0814965963363647,
|
| 194 |
+
2.416655488014221,
|
| 195 |
+
2.346989154815674,
|
| 196 |
+
1.1415718960762022,
|
| 197 |
+
0.5208872479200363,
|
| 198 |
+
1.4889542925357817,
|
| 199 |
+
1.0
|
| 200 |
+
],
|
| 201 |
+
"std": [
|
| 202 |
+
0.34305506136703257,
|
| 203 |
+
0.8880398716756615,
|
| 204 |
+
0.7302413867018247,
|
| 205 |
+
0.6487680858145891,
|
| 206 |
+
0.2989095916390101,
|
| 207 |
+
0.584300843989697,
|
| 208 |
+
0.34316664624786114,
|
| 209 |
+
0.31989806135013626,
|
| 210 |
+
0.8736479432260295,
|
| 211 |
+
0.7135350385777451,
|
| 212 |
+
0.6027223159771133,
|
| 213 |
+
0.2836475966439172,
|
| 214 |
+
0.5368540820848867,
|
| 215 |
+
0.3406560080480477
|
| 216 |
+
]
|
| 217 |
+
}
|
| 218 |
+
}
|
| 219 |
+
},
|
| 220 |
+
"eval": {
|
| 221 |
+
"dataset": {
|
| 222 |
+
"transforms": [
|
| 223 |
+
{
|
| 224 |
+
"embodiment_id": 31,
|
| 225 |
+
"img_keys": [
|
| 226 |
+
"cam_high",
|
| 227 |
+
"cam_left_wrist",
|
| 228 |
+
"cam_right_wrist"
|
| 229 |
+
],
|
| 230 |
+
"type": "ProcessEvalInputs"
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"clip_norm": true,
|
| 234 |
+
"norm_type": "quantile",
|
| 235 |
+
"stat_key": "proprio",
|
| 236 |
+
"state_dim": 64,
|
| 237 |
+
"type": "StateFromInputs"
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"max_len": 1100,
|
| 241 |
+
"num_images": 3,
|
| 242 |
+
"tokenizer": {
|
| 243 |
+
"model_path": "fluxvla/models/third_party_models/eagle2_hg_model",
|
| 244 |
+
"type": "PretrainedTokenizer"
|
| 245 |
+
},
|
| 246 |
+
"type": "ProcessPromptsWithImage"
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"image_resize_strategy": "letterbox",
|
| 250 |
+
"input_sizes": [
|
| 251 |
+
[
|
| 252 |
+
3,
|
| 253 |
+
224,
|
| 254 |
+
224
|
| 255 |
+
],
|
| 256 |
+
[
|
| 257 |
+
3,
|
| 258 |
+
224,
|
| 259 |
+
224
|
| 260 |
+
],
|
| 261 |
+
[
|
| 262 |
+
3,
|
| 263 |
+
224,
|
| 264 |
+
224
|
| 265 |
+
]
|
| 266 |
+
],
|
| 267 |
+
"letterbox_crop_fraction": 0.95,
|
| 268 |
+
"letterbox_fill": [
|
| 269 |
+
0,
|
| 270 |
+
0,
|
| 271 |
+
0
|
| 272 |
+
],
|
| 273 |
+
"letterbox_pad_position": "center",
|
| 274 |
+
"means": [
|
| 275 |
+
[
|
| 276 |
+
127.5,
|
| 277 |
+
127.5,
|
| 278 |
+
127.5
|
| 279 |
+
],
|
| 280 |
+
[
|
| 281 |
+
127.5,
|
| 282 |
+
127.5,
|
| 283 |
+
127.5
|
| 284 |
+
],
|
| 285 |
+
[
|
| 286 |
+
127.5,
|
| 287 |
+
127.5,
|
| 288 |
+
127.5
|
| 289 |
+
]
|
| 290 |
+
],
|
| 291 |
+
"stds": [
|
| 292 |
+
[
|
| 293 |
+
127.5,
|
| 294 |
+
127.5,
|
| 295 |
+
127.5
|
| 296 |
+
],
|
| 297 |
+
[
|
| 298 |
+
127.5,
|
| 299 |
+
127.5,
|
| 300 |
+
127.5
|
| 301 |
+
],
|
| 302 |
+
[
|
| 303 |
+
127.5,
|
| 304 |
+
127.5,
|
| 305 |
+
127.5
|
| 306 |
+
]
|
| 307 |
+
],
|
| 308 |
+
"type": "TransformImage"
|
| 309 |
+
}
|
| 310 |
+
],
|
| 311 |
+
"type": "RoboDojoEvalDataset"
|
| 312 |
+
},
|
| 313 |
+
"denormalize_action": {
|
| 314 |
+
"action_dim": 14,
|
| 315 |
+
"delta_action_mask": [
|
| 316 |
+
true,
|
| 317 |
+
true,
|
| 318 |
+
true,
|
| 319 |
+
true,
|
| 320 |
+
true,
|
| 321 |
+
true,
|
| 322 |
+
true,
|
| 323 |
+
true,
|
| 324 |
+
true,
|
| 325 |
+
true,
|
| 326 |
+
true,
|
| 327 |
+
true,
|
| 328 |
+
true,
|
| 329 |
+
true
|
| 330 |
+
],
|
| 331 |
+
"norm_type": "quantile",
|
| 332 |
+
"statistic_name": "robodojo_arx_x5",
|
| 333 |
+
"type": "DenormalizeDeltaAction"
|
| 334 |
+
},
|
| 335 |
+
"model_family": "groot",
|
| 336 |
+
"num_trials_per_task": 25,
|
| 337 |
+
"report_kind": "robodojo",
|
| 338 |
+
"task_suite_name": "robodojo"
|
| 339 |
+
},
|
| 340 |
+
"inference_model": {
|
| 341 |
+
"pretrained_name_or_path": "./checkpoints/GR00T-N1.5-3B",
|
| 342 |
+
"type": "LlavaVLA",
|
| 343 |
+
"vla_head": {
|
| 344 |
+
"action_dim": 32,
|
| 345 |
+
"diffusion_model_cfg": {
|
| 346 |
+
"attention_head_dim": 48,
|
| 347 |
+
"cross_attention_dim": 2048,
|
| 348 |
+
"dropout": 0.2,
|
| 349 |
+
"final_dropout": true,
|
| 350 |
+
"interleave_self_attention": true,
|
| 351 |
+
"norm_type": "ada_norm",
|
| 352 |
+
"num_attention_heads": 32,
|
| 353 |
+
"num_layers": 16,
|
| 354 |
+
"output_dim": 1024,
|
| 355 |
+
"positional_embeddings": null
|
| 356 |
+
},
|
| 357 |
+
"hidden_size": 1024,
|
| 358 |
+
"input_embedding_dim": 1536,
|
| 359 |
+
"max_input_seq_len": 1100,
|
| 360 |
+
"num_inference_timesteps": 4,
|
| 361 |
+
"num_steps": 16,
|
| 362 |
+
"ori_action_dim": 14,
|
| 363 |
+
"state_dim": 64,
|
| 364 |
+
"type": "FlowMatchingInferenceHead"
|
| 365 |
+
},
|
| 366 |
+
"vlm_backbone": {
|
| 367 |
+
"type": "EagleInferenceBackbone",
|
| 368 |
+
"vlm_config": {
|
| 369 |
+
"max_input_seq_len": 1100
|
| 370 |
+
},
|
| 371 |
+
"vlm_path": "fluxvla/models/third_party_models/eagle2_hg_model"
|
| 372 |
+
}
|
| 373 |
+
},
|
| 374 |
+
"model": {
|
| 375 |
+
"freeze_projector": false,
|
| 376 |
+
"freeze_vlm_backbone": false,
|
| 377 |
+
"name_mapping": {
|
| 378 |
+
"vla_head": "action_head",
|
| 379 |
+
"vlm_backbone.vlm": "backbone.eagle_model"
|
| 380 |
+
},
|
| 381 |
+
"pretrained_name_or_path": "./checkpoints/GR00T-N1.5-3B",
|
| 382 |
+
"type": "LlavaVLA",
|
| 383 |
+
"vla_head": {
|
| 384 |
+
"action_dim": 32,
|
| 385 |
+
"hidden_size": 1024,
|
| 386 |
+
"input_embedding_dim": 1536,
|
| 387 |
+
"noise_beta_alpha": 1.5,
|
| 388 |
+
"noise_beta_beta": 1.0,
|
| 389 |
+
"num_inference_timesteps": 4,
|
| 390 |
+
"num_steps": 16,
|
| 391 |
+
"ori_action_dim": 14,
|
| 392 |
+
"state_dim": 64,
|
| 393 |
+
"state_dropout_prob": 0.2,
|
| 394 |
+
"type": "FlowMatchingHead"
|
| 395 |
+
},
|
| 396 |
+
"vlm_backbone": {
|
| 397 |
+
"dtype": "bf16",
|
| 398 |
+
"tune_llm": false,
|
| 399 |
+
"tune_visual": false,
|
| 400 |
+
"type": "EagleBackbone",
|
| 401 |
+
"vlm_config": {
|
| 402 |
+
"max_input_seq_len": 1100
|
| 403 |
+
},
|
| 404 |
+
"vlm_path": "fluxvla/models/third_party_models/eagle2_hg_model"
|
| 405 |
+
}
|
| 406 |
+
},
|
| 407 |
+
"runner": {
|
| 408 |
+
"change_key_name": false,
|
| 409 |
+
"collator": {
|
| 410 |
+
"keys": [
|
| 411 |
+
"states",
|
| 412 |
+
"timestamp",
|
| 413 |
+
"images",
|
| 414 |
+
"img_masks",
|
| 415 |
+
"lang_tokens",
|
| 416 |
+
"lang_masks",
|
| 417 |
+
"actions",
|
| 418 |
+
"action_masks",
|
| 419 |
+
"embodiment_ids"
|
| 420 |
+
],
|
| 421 |
+
"meta_keys": [
|
| 422 |
+
"task_description",
|
| 423 |
+
"prompt",
|
| 424 |
+
"info",
|
| 425 |
+
"stats"
|
| 426 |
+
],
|
| 427 |
+
"type": "DictCollator"
|
| 428 |
+
},
|
| 429 |
+
"enable_gradient_checkpointing": false,
|
| 430 |
+
"enable_mixed_precision_training": true,
|
| 431 |
+
"grad_accumulation_steps": 5,
|
| 432 |
+
"lr_scheduler": {
|
| 433 |
+
"type": "linear-warmup+cosine-decay",
|
| 434 |
+
"warmup_ratio": 0.05
|
| 435 |
+
},
|
| 436 |
+
"max_epochs": null,
|
| 437 |
+
"max_grad_norm": 1.0,
|
| 438 |
+
"max_keep_ckpts": 5,
|
| 439 |
+
"max_steps": 100000,
|
| 440 |
+
"metric": {
|
| 441 |
+
"active_trackers": [
|
| 442 |
+
"jsonl",
|
| 443 |
+
"wandb"
|
| 444 |
+
],
|
| 445 |
+
"grad_accumulation_steps": 5,
|
| 446 |
+
"run_dir": "work_dirs",
|
| 447 |
+
"type": "VLAMetric",
|
| 448 |
+
"window_size": 1
|
| 449 |
+
},
|
| 450 |
+
"mixed_precision_dtype": "bf16",
|
| 451 |
+
"optimizer": {
|
| 452 |
+
"lr": 0.0001,
|
| 453 |
+
"type": "AdamW",
|
| 454 |
+
"weight_decay": 1e-05
|
| 455 |
+
},
|
| 456 |
+
"sampler": null,
|
| 457 |
+
"save_epoch_interval": 1,
|
| 458 |
+
"save_iter_interval": 1000,
|
| 459 |
+
"sharding_strategy": "no-shard",
|
| 460 |
+
"tokenizer": {
|
| 461 |
+
"model_path": "fluxvla/models/third_party_models/eagle2_hg_model",
|
| 462 |
+
"type": "PretrainedTokenizer"
|
| 463 |
+
},
|
| 464 |
+
"type": "FSDPTrainRunner"
|
| 465 |
+
},
|
| 466 |
+
"themis": {
|
| 467 |
+
"ros_server": {
|
| 468 |
+
"dataset_section": "eval",
|
| 469 |
+
"denormalize_context": {
|
| 470 |
+
"task_suite_name": "robodojo_arx_x5"
|
| 471 |
+
},
|
| 472 |
+
"device": "cuda:0",
|
| 473 |
+
"enable_mixed_precision": true,
|
| 474 |
+
"evaluation_reporting": {
|
| 475 |
+
"result_output_dir": "work_dirs/fluxthemis"
|
| 476 |
+
},
|
| 477 |
+
"forward_seed": false,
|
| 478 |
+
"mixed_precision_dtype": "bf16",
|
| 479 |
+
"model_outputs_environment_actions": false,
|
| 480 |
+
"workers": {
|
| 481 |
+
"lease_timeout_s": 900.0,
|
| 482 |
+
"request_timeout_s": 120.0,
|
| 483 |
+
"startup_timeout_s": 900.0
|
| 484 |
+
}
|
| 485 |
+
},
|
| 486 |
+
"runner": {
|
| 487 |
+
"environment": {
|
| 488 |
+
"action_mode": "joint",
|
| 489 |
+
"device_id": 1,
|
| 490 |
+
"env_cfg_type": "arx_x5",
|
| 491 |
+
"headless": true,
|
| 492 |
+
"robodojo_root": "/root/projects/RoboDojo",
|
| 493 |
+
"save_videos": false,
|
| 494 |
+
"task_name": "all",
|
| 495 |
+
"type": "RoboDojoEnvironment"
|
| 496 |
+
},
|
| 497 |
+
"episodes_per_task": 25,
|
| 498 |
+
"evaluator": {
|
| 499 |
+
"type": "SuccessRateEvaluator"
|
| 500 |
+
},
|
| 501 |
+
"execute_horizon": 16,
|
| 502 |
+
"max_episode_steps": 2000,
|
| 503 |
+
"model_client": {
|
| 504 |
+
"type": "FluxVLAZMQModelClient"
|
| 505 |
+
},
|
| 506 |
+
"parallel_workers": 1,
|
| 507 |
+
"seed": 0,
|
| 508 |
+
"simulator_gpu_ids": null,
|
| 509 |
+
"stop_on_success": true,
|
| 510 |
+
"type": "EvalRunner",
|
| 511 |
+
"work_dir": "work_dirs/fluxthemis"
|
| 512 |
+
},
|
| 513 |
+
"transport": {
|
| 514 |
+
"host": "127.0.0.1",
|
| 515 |
+
"image_encoding": "rgb8",
|
| 516 |
+
"image_keys": [
|
| 517 |
+
"cam_high",
|
| 518 |
+
"cam_left_wrist",
|
| 519 |
+
"cam_right_wrist"
|
| 520 |
+
],
|
| 521 |
+
"port": 5555,
|
| 522 |
+
"report_service_name": "/fluxvla/report_evaluation",
|
| 523 |
+
"state_keys": [
|
| 524 |
+
"states"
|
| 525 |
+
],
|
| 526 |
+
"timeout_s": 30.0,
|
| 527 |
+
"unnorm_key": "robodojo_arx_x5"
|
| 528 |
+
}
|
| 529 |
+
},
|
| 530 |
+
"train_dataloader": {
|
| 531 |
+
"dataset": {
|
| 532 |
+
"dataset_statistics": {
|
| 533 |
+
"robodojo_arx_x5": {
|
| 534 |
+
"action": {
|
| 535 |
+
"count": 29333632,
|
| 536 |
+
"max": [
|
| 537 |
+
1.8887031078338623,
|
| 538 |
+
2.241629123687744,
|
| 539 |
+
2.3643198013305664,
|
| 540 |
+
2.353733539581299,
|
| 541 |
+
1.684847116470337,
|
| 542 |
+
2.5986948013305664,
|
| 543 |
+
1.0,
|
| 544 |
+
1.6447105407714844,
|
| 545 |
+
2.472832202911377,
|
| 546 |
+
3.1138815879821777,
|
| 547 |
+
2.544224500656128,
|
| 548 |
+
2.4465250968933105,
|
| 549 |
+
2.3557143211364746,
|
| 550 |
+
1.0
|
| 551 |
+
],
|
| 552 |
+
"mean": [
|
| 553 |
+
-0.00016787611640384256,
|
| 554 |
+
3.640991079951193e-05,
|
| 555 |
+
-0.0001244129093475812,
|
| 556 |
+
0.0009861263907153927,
|
| 557 |
+
4.007764372684936e-05,
|
| 558 |
+
-0.0005710965315355596,
|
| 559 |
+
-0.00033464226771561873,
|
| 560 |
+
0.00014757256047559194,
|
| 561 |
+
0.002926647213791033,
|
| 562 |
+
0.002445220311756816,
|
| 563 |
+
-0.0017966633835313532,
|
| 564 |
+
-0.00034538796665606477,
|
| 565 |
+
-0.0010489735053372264,
|
| 566 |
+
-0.0008483530749860559
|
| 567 |
+
],
|
| 568 |
+
"min": [
|
| 569 |
+
-1.9831359386444092,
|
| 570 |
+
-2.3307759761810303,
|
| 571 |
+
-2.36329984664917,
|
| 572 |
+
-2.3512368202209473,
|
| 573 |
+
-1.7914525270462036,
|
| 574 |
+
-2.4492745399475098,
|
| 575 |
+
-1.0,
|
| 576 |
+
-1.6693108081817627,
|
| 577 |
+
-2.261469841003418,
|
| 578 |
+
-2.36698317527771,
|
| 579 |
+
-2.53256893157959,
|
| 580 |
+
-2.4855473041534424,
|
| 581 |
+
-2.839830160140991,
|
| 582 |
+
-1.0
|
| 583 |
+
],
|
| 584 |
+
"q01": [
|
| 585 |
+
-0.5563330262899399,
|
| 586 |
+
-1.164183863401413,
|
| 587 |
+
-0.9725008648633957,
|
| 588 |
+
-0.7879389774799347,
|
| 589 |
+
-0.35899992257356644,
|
| 590 |
+
-0.8268111473321915,
|
| 591 |
+
-0.6629222631454468,
|
| 592 |
+
-0.48305779963731765,
|
| 593 |
+
-1.1301205492019653,
|
| 594 |
+
-0.9574322783946991,
|
| 595 |
+
-0.7862630712985993,
|
| 596 |
+
-0.3646536460518837,
|
| 597 |
+
-0.8233565813302994,
|
| 598 |
+
-0.6629220247268677
|
| 599 |
+
],
|
| 600 |
+
"q99": [
|
| 601 |
+
0.5548361170291902,
|
| 602 |
+
1.0296359968185431,
|
| 603 |
+
0.8563214296102533,
|
| 604 |
+
0.8150562870502474,
|
| 605 |
+
0.39599745541810993,
|
| 606 |
+
0.8352749580144907,
|
| 607 |
+
0.6292134523391724,
|
| 608 |
+
0.4990877494215987,
|
| 609 |
+
1.0044999086856863,
|
| 610 |
+
0.8432489860057832,
|
| 611 |
+
0.78897400379181,
|
| 612 |
+
0.32408514618873596,
|
| 613 |
+
0.7997124117612857,
|
| 614 |
+
0.6112149953842163
|
| 615 |
+
],
|
| 616 |
+
"std": [
|
| 617 |
+
0.1524663344569265,
|
| 618 |
+
0.29040871843218186,
|
| 619 |
+
0.25021202987482355,
|
| 620 |
+
0.2233514194013506,
|
| 621 |
+
0.10648562443390856,
|
| 622 |
+
0.2295837861601856,
|
| 623 |
+
0.16658472644994762,
|
| 624 |
+
0.13469893280906062,
|
| 625 |
+
0.27712445038284145,
|
| 626 |
+
0.24285089420664013,
|
| 627 |
+
0.21544770406738722,
|
| 628 |
+
0.09925954744044597,
|
| 629 |
+
0.22253717352947505,
|
| 630 |
+
0.16110866685153383
|
| 631 |
+
]
|
| 632 |
+
},
|
| 633 |
+
"proprio": {
|
| 634 |
+
"count": 1859602,
|
| 635 |
+
"max": [
|
| 636 |
+
1.7537026405334473,
|
| 637 |
+
3.0546703338623047,
|
| 638 |
+
3.8525187969207764,
|
| 639 |
+
2.0974574089050293,
|
| 640 |
+
1.8103265762329102,
|
| 641 |
+
3.1366536617279053,
|
| 642 |
+
1.0,
|
| 643 |
+
1.6732014417648315,
|
| 644 |
+
3.3797459602355957,
|
| 645 |
+
4.252756595611572,
|
| 646 |
+
2.5287232398986816,
|
| 647 |
+
3.1440579891204834,
|
| 648 |
+
3.0381109714508057,
|
| 649 |
+
1.0
|
| 650 |
+
],
|
| 651 |
+
"mean": [
|
| 652 |
+
-0.20040483418845204,
|
| 653 |
+
0.9260308650671458,
|
| 654 |
+
0.6881893789087474,
|
| 655 |
+
-0.3400484544283471,
|
| 656 |
+
0.06579394032953159,
|
| 657 |
+
0.004003331131509558,
|
| 658 |
+
0.771446548553906,
|
| 659 |
+
0.17299834959584776,
|
| 660 |
+
0.8224941837716736,
|
| 661 |
+
0.6196513047400859,
|
| 662 |
+
-0.3604178625374315,
|
| 663 |
+
-0.06267071413702419,
|
| 664 |
+
0.0037534824507240434,
|
| 665 |
+
0.7860054714056368
|
| 666 |
+
],
|
| 667 |
+
"min": [
|
| 668 |
+
-1.4863648414611816,
|
| 669 |
+
-0.2586335241794586,
|
| 670 |
+
-0.06850092858076096,
|
| 671 |
+
-2.2642147541046143,
|
| 672 |
+
-1.4876768589019775,
|
| 673 |
+
-3.0168392658233643,
|
| 674 |
+
-3.212450869184004e-17,
|
| 675 |
+
-1.4924354553222656,
|
| 676 |
+
-0.27809593081474304,
|
| 677 |
+
-0.18774886429309845,
|
| 678 |
+
-2.5354628562927246,
|
| 679 |
+
-3.0663280487060547,
|
| 680 |
+
-3.0486762523651123,
|
| 681 |
+
-3.212450869184004e-17
|
| 682 |
+
],
|
| 683 |
+
"q01": [
|
| 684 |
+
-1.051365569829941,
|
| 685 |
+
-3.52302449637288e-14,
|
| 686 |
+
1.6996893991849812e-16,
|
| 687 |
+
-1.5984010362625123,
|
| 688 |
+
-0.6003412520885467,
|
| 689 |
+
-1.6678147149085998,
|
| 690 |
+
0.0,
|
| 691 |
+
-0.4500492787361145,
|
| 692 |
+
-2.5859282299029243e-14,
|
| 693 |
+
1.194697284288627e-16,
|
| 694 |
+
-1.6398817586898804,
|
| 695 |
+
-1.263367258310318,
|
| 696 |
+
-1.760098042488098,
|
| 697 |
+
0.0
|
| 698 |
+
],
|
| 699 |
+
"q99": [
|
| 700 |
+
0.5431358617544174,
|
| 701 |
+
2.495765209197998,
|
| 702 |
+
2.492974226474762,
|
| 703 |
+
1.323737324476242,
|
| 704 |
+
1.2496635341644287,
|
| 705 |
+
1.7391636216640465,
|
| 706 |
+
1.0,
|
| 707 |
+
1.0814965963363647,
|
| 708 |
+
2.416655488014221,
|
| 709 |
+
2.346989154815674,
|
| 710 |
+
1.1415718960762022,
|
| 711 |
+
0.5208872479200363,
|
| 712 |
+
1.4889542925357817,
|
| 713 |
+
1.0
|
| 714 |
+
],
|
| 715 |
+
"std": [
|
| 716 |
+
0.34305506136703257,
|
| 717 |
+
0.8880398716756615,
|
| 718 |
+
0.7302413867018247,
|
| 719 |
+
0.6487680858145891,
|
| 720 |
+
0.2989095916390101,
|
| 721 |
+
0.584300843989697,
|
| 722 |
+
0.34316664624786114,
|
| 723 |
+
0.31989806135013626,
|
| 724 |
+
0.8736479432260295,
|
| 725 |
+
0.7135350385777451,
|
| 726 |
+
0.6027223159771133,
|
| 727 |
+
0.2836475966439172,
|
| 728 |
+
0.5368540820848867,
|
| 729 |
+
0.3406560080480477
|
| 730 |
+
]
|
| 731 |
+
}
|
| 732 |
+
}
|
| 733 |
+
},
|
| 734 |
+
"datasets": [
|
| 735 |
+
{
|
| 736 |
+
"action_key": "action",
|
| 737 |
+
"action_window_size": 16,
|
| 738 |
+
"data_root_path": [
|
| 739 |
+
"./datasets/RoboDojo_lerobot_v21_video"
|
| 740 |
+
],
|
| 741 |
+
"statistic_name": "robodojo_arx_x5",
|
| 742 |
+
"transforms": [
|
| 743 |
+
{
|
| 744 |
+
"embodiment_id": 31,
|
| 745 |
+
"name_mappings": {
|
| 746 |
+
"actions": [
|
| 747 |
+
"actions"
|
| 748 |
+
],
|
| 749 |
+
"observation.state": [
|
| 750 |
+
"states"
|
| 751 |
+
]
|
| 752 |
+
},
|
| 753 |
+
"parquet_keys": [
|
| 754 |
+
"observation.state",
|
| 755 |
+
"timestamp",
|
| 756 |
+
"actions",
|
| 757 |
+
"info",
|
| 758 |
+
"stats",
|
| 759 |
+
"action_masks"
|
| 760 |
+
],
|
| 761 |
+
"type": "ProcessParquetInputs",
|
| 762 |
+
"video_keys": [
|
| 763 |
+
"observation.images.cam_high",
|
| 764 |
+
"observation.images.cam_left_wrist",
|
| 765 |
+
"observation.images.cam_right_wrist"
|
| 766 |
+
]
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"mask": [
|
| 770 |
+
true,
|
| 771 |
+
true,
|
| 772 |
+
true,
|
| 773 |
+
true,
|
| 774 |
+
true,
|
| 775 |
+
true,
|
| 776 |
+
true,
|
| 777 |
+
true,
|
| 778 |
+
true,
|
| 779 |
+
true,
|
| 780 |
+
true,
|
| 781 |
+
true,
|
| 782 |
+
true,
|
| 783 |
+
true
|
| 784 |
+
],
|
| 785 |
+
"type": "DeltaActions"
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"type": "ParquetPrompter"
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"max_len": 1100,
|
| 792 |
+
"num_images": 3,
|
| 793 |
+
"tokenizer": {
|
| 794 |
+
"model_path": "fluxvla/models/third_party_models/eagle2_hg_model",
|
| 795 |
+
"type": "PretrainedTokenizer"
|
| 796 |
+
},
|
| 797 |
+
"type": "ProcessPromptsWithImage"
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"height": 224,
|
| 801 |
+
"pad_direction": "center",
|
| 802 |
+
"pad_value": 0,
|
| 803 |
+
"type": "ResizeImagesWithPad",
|
| 804 |
+
"width": 224
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"scale": 0.95,
|
| 808 |
+
"type": "RandomCropImages"
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"height": 224,
|
| 812 |
+
"type": "ResizeImages",
|
| 813 |
+
"width": 224
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"brightness": 0.3,
|
| 817 |
+
"contrast": 0.4,
|
| 818 |
+
"hue": 0.08,
|
| 819 |
+
"saturation": 0.5,
|
| 820 |
+
"type": "ColorJitterImages"
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"type": "SimpleNormalizeImages"
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"action_dim": 32,
|
| 827 |
+
"action_key": "action",
|
| 828 |
+
"clip_norm": true,
|
| 829 |
+
"norm_type": "quantile",
|
| 830 |
+
"normalize_states": true,
|
| 831 |
+
"state_dim": 64,
|
| 832 |
+
"state_key": "proprio",
|
| 833 |
+
"type": "NormalizeStatesAndActions"
|
| 834 |
+
}
|
| 835 |
+
],
|
| 836 |
+
"type": "ParquetDataset",
|
| 837 |
+
"use_delta": false,
|
| 838 |
+
"window_start_idx": 0
|
| 839 |
+
}
|
| 840 |
+
],
|
| 841 |
+
"name_mappings": {
|
| 842 |
+
"action": [
|
| 843 |
+
"action"
|
| 844 |
+
],
|
| 845 |
+
"observation.state": [
|
| 846 |
+
"proprio"
|
| 847 |
+
]
|
| 848 |
+
},
|
| 849 |
+
"statistic_keys": [
|
| 850 |
+
"observation.state",
|
| 851 |
+
"action",
|
| 852 |
+
"timestamp"
|
| 853 |
+
],
|
| 854 |
+
"statistic_name": "robodojo_arx_x5",
|
| 855 |
+
"type": "DistributedRepeatingDataset"
|
| 856 |
+
},
|
| 857 |
+
"per_device_batch_size": 8,
|
| 858 |
+
"per_device_num_workers": 4
|
| 859 |
+
}
|
| 860 |
+
}
|
|
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_GR00T_ROBODOJO_DELTA_MASK:
|
| 2 |
+
- true
|
| 3 |
+
- true
|
| 4 |
+
- true
|
| 5 |
+
- true
|
| 6 |
+
- true
|
| 7 |
+
- true
|
| 8 |
+
- true
|
| 9 |
+
- true
|
| 10 |
+
- true
|
| 11 |
+
- true
|
| 12 |
+
- true
|
| 13 |
+
- true
|
| 14 |
+
- true
|
| 15 |
+
- true
|
| 16 |
+
_GR00T_ROBODOJO_STATS:
|
| 17 |
+
robodojo_arx_x5:
|
| 18 |
+
action:
|
| 19 |
+
count: 29333632
|
| 20 |
+
max:
|
| 21 |
+
- 1.8887031078338623
|
| 22 |
+
- 2.241629123687744
|
| 23 |
+
- 2.3643198013305664
|
| 24 |
+
- 2.353733539581299
|
| 25 |
+
- 1.684847116470337
|
| 26 |
+
- 2.5986948013305664
|
| 27 |
+
- 1.0
|
| 28 |
+
- 1.6447105407714844
|
| 29 |
+
- 2.472832202911377
|
| 30 |
+
- 3.1138815879821777
|
| 31 |
+
- 2.544224500656128
|
| 32 |
+
- 2.4465250968933105
|
| 33 |
+
- 2.3557143211364746
|
| 34 |
+
- 1.0
|
| 35 |
+
mean:
|
| 36 |
+
- -0.00016787611640384256
|
| 37 |
+
- 3.640991079951193e-05
|
| 38 |
+
- -0.0001244129093475812
|
| 39 |
+
- 0.0009861263907153927
|
| 40 |
+
- 4.007764372684936e-05
|
| 41 |
+
- -0.0005710965315355596
|
| 42 |
+
- -0.00033464226771561873
|
| 43 |
+
- 0.00014757256047559194
|
| 44 |
+
- 0.002926647213791033
|
| 45 |
+
- 0.002445220311756816
|
| 46 |
+
- -0.0017966633835313532
|
| 47 |
+
- -0.00034538796665606477
|
| 48 |
+
- -0.0010489735053372264
|
| 49 |
+
- -0.0008483530749860559
|
| 50 |
+
min:
|
| 51 |
+
- -1.9831359386444092
|
| 52 |
+
- -2.3307759761810303
|
| 53 |
+
- -2.36329984664917
|
| 54 |
+
- -2.3512368202209473
|
| 55 |
+
- -1.7914525270462036
|
| 56 |
+
- -2.4492745399475098
|
| 57 |
+
- -1.0
|
| 58 |
+
- -1.6693108081817627
|
| 59 |
+
- -2.261469841003418
|
| 60 |
+
- -2.36698317527771
|
| 61 |
+
- -2.53256893157959
|
| 62 |
+
- -2.4855473041534424
|
| 63 |
+
- -2.839830160140991
|
| 64 |
+
- -1.0
|
| 65 |
+
q01:
|
| 66 |
+
- -0.5563330262899399
|
| 67 |
+
- -1.164183863401413
|
| 68 |
+
- -0.9725008648633957
|
| 69 |
+
- -0.7879389774799347
|
| 70 |
+
- -0.35899992257356644
|
| 71 |
+
- -0.8268111473321915
|
| 72 |
+
- -0.6629222631454468
|
| 73 |
+
- -0.48305779963731765
|
| 74 |
+
- -1.1301205492019653
|
| 75 |
+
- -0.9574322783946991
|
| 76 |
+
- -0.7862630712985993
|
| 77 |
+
- -0.3646536460518837
|
| 78 |
+
- -0.8233565813302994
|
| 79 |
+
- -0.6629220247268677
|
| 80 |
+
q99:
|
| 81 |
+
- 0.5548361170291902
|
| 82 |
+
- 1.0296359968185431
|
| 83 |
+
- 0.8563214296102533
|
| 84 |
+
- 0.8150562870502474
|
| 85 |
+
- 0.39599745541810993
|
| 86 |
+
- 0.8352749580144907
|
| 87 |
+
- 0.6292134523391724
|
| 88 |
+
- 0.4990877494215987
|
| 89 |
+
- 1.0044999086856863
|
| 90 |
+
- 0.8432489860057832
|
| 91 |
+
- 0.78897400379181
|
| 92 |
+
- 0.32408514618873596
|
| 93 |
+
- 0.7997124117612857
|
| 94 |
+
- 0.6112149953842163
|
| 95 |
+
std:
|
| 96 |
+
- 0.1524663344569265
|
| 97 |
+
- 0.29040871843218186
|
| 98 |
+
- 0.25021202987482355
|
| 99 |
+
- 0.2233514194013506
|
| 100 |
+
- 0.10648562443390856
|
| 101 |
+
- 0.2295837861601856
|
| 102 |
+
- 0.16658472644994762
|
| 103 |
+
- 0.13469893280906062
|
| 104 |
+
- 0.27712445038284145
|
| 105 |
+
- 0.24285089420664013
|
| 106 |
+
- 0.21544770406738722
|
| 107 |
+
- 0.09925954744044597
|
| 108 |
+
- 0.22253717352947505
|
| 109 |
+
- 0.16110866685153383
|
| 110 |
+
proprio:
|
| 111 |
+
count: 1859602
|
| 112 |
+
max:
|
| 113 |
+
- 1.7537026405334473
|
| 114 |
+
- 3.0546703338623047
|
| 115 |
+
- 3.8525187969207764
|
| 116 |
+
- 2.0974574089050293
|
| 117 |
+
- 1.8103265762329102
|
| 118 |
+
- 3.1366536617279053
|
| 119 |
+
- 1.0
|
| 120 |
+
- 1.6732014417648315
|
| 121 |
+
- 3.3797459602355957
|
| 122 |
+
- 4.252756595611572
|
| 123 |
+
- 2.5287232398986816
|
| 124 |
+
- 3.1440579891204834
|
| 125 |
+
- 3.0381109714508057
|
| 126 |
+
- 1.0
|
| 127 |
+
mean:
|
| 128 |
+
- -0.20040483418845204
|
| 129 |
+
- 0.9260308650671458
|
| 130 |
+
- 0.6881893789087474
|
| 131 |
+
- -0.3400484544283471
|
| 132 |
+
- 0.06579394032953159
|
| 133 |
+
- 0.004003331131509558
|
| 134 |
+
- 0.771446548553906
|
| 135 |
+
- 0.17299834959584776
|
| 136 |
+
- 0.8224941837716736
|
| 137 |
+
- 0.6196513047400859
|
| 138 |
+
- -0.3604178625374315
|
| 139 |
+
- -0.06267071413702419
|
| 140 |
+
- 0.0037534824507240434
|
| 141 |
+
- 0.7860054714056368
|
| 142 |
+
min:
|
| 143 |
+
- -1.4863648414611816
|
| 144 |
+
- -0.2586335241794586
|
| 145 |
+
- -0.06850092858076096
|
| 146 |
+
- -2.2642147541046143
|
| 147 |
+
- -1.4876768589019775
|
| 148 |
+
- -3.0168392658233643
|
| 149 |
+
- -3.212450869184004e-17
|
| 150 |
+
- -1.4924354553222656
|
| 151 |
+
- -0.27809593081474304
|
| 152 |
+
- -0.18774886429309845
|
| 153 |
+
- -2.5354628562927246
|
| 154 |
+
- -3.0663280487060547
|
| 155 |
+
- -3.0486762523651123
|
| 156 |
+
- -3.212450869184004e-17
|
| 157 |
+
q01:
|
| 158 |
+
- -1.051365569829941
|
| 159 |
+
- -3.52302449637288e-14
|
| 160 |
+
- 1.6996893991849812e-16
|
| 161 |
+
- -1.5984010362625123
|
| 162 |
+
- -0.6003412520885467
|
| 163 |
+
- -1.6678147149085998
|
| 164 |
+
- 0.0
|
| 165 |
+
- -0.4500492787361145
|
| 166 |
+
- -2.5859282299029243e-14
|
| 167 |
+
- 1.194697284288627e-16
|
| 168 |
+
- -1.6398817586898804
|
| 169 |
+
- -1.263367258310318
|
| 170 |
+
- -1.760098042488098
|
| 171 |
+
- 0.0
|
| 172 |
+
q99:
|
| 173 |
+
- 0.5431358617544174
|
| 174 |
+
- 2.495765209197998
|
| 175 |
+
- 2.492974226474762
|
| 176 |
+
- 1.323737324476242
|
| 177 |
+
- 1.2496635341644287
|
| 178 |
+
- 1.7391636216640465
|
| 179 |
+
- 1.0
|
| 180 |
+
- 1.0814965963363647
|
| 181 |
+
- 2.416655488014221
|
| 182 |
+
- 2.346989154815674
|
| 183 |
+
- 1.1415718960762022
|
| 184 |
+
- 0.5208872479200363
|
| 185 |
+
- 1.4889542925357817
|
| 186 |
+
- 1.0
|
| 187 |
+
std:
|
| 188 |
+
- 0.34305506136703257
|
| 189 |
+
- 0.8880398716756615
|
| 190 |
+
- 0.7302413867018247
|
| 191 |
+
- 0.6487680858145891
|
| 192 |
+
- 0.2989095916390101
|
| 193 |
+
- 0.584300843989697
|
| 194 |
+
- 0.34316664624786114
|
| 195 |
+
- 0.31989806135013626
|
| 196 |
+
- 0.8736479432260295
|
| 197 |
+
- 0.7135350385777451
|
| 198 |
+
- 0.6027223159771133
|
| 199 |
+
- 0.2836475966439172
|
| 200 |
+
- 0.5368540820848867
|
| 201 |
+
- 0.3406560080480477
|
| 202 |
+
eval:
|
| 203 |
+
dataset:
|
| 204 |
+
transforms:
|
| 205 |
+
- embodiment_id: 31
|
| 206 |
+
img_keys:
|
| 207 |
+
- cam_high
|
| 208 |
+
- cam_left_wrist
|
| 209 |
+
- cam_right_wrist
|
| 210 |
+
type: ProcessEvalInputs
|
| 211 |
+
- clip_norm: true
|
| 212 |
+
norm_type: quantile
|
| 213 |
+
stat_key: proprio
|
| 214 |
+
state_dim: 64
|
| 215 |
+
type: StateFromInputs
|
| 216 |
+
- max_len: 1100
|
| 217 |
+
num_images: 3
|
| 218 |
+
tokenizer:
|
| 219 |
+
model_path: fluxvla/models/third_party_models/eagle2_hg_model
|
| 220 |
+
type: PretrainedTokenizer
|
| 221 |
+
type: ProcessPromptsWithImage
|
| 222 |
+
- image_resize_strategy: letterbox
|
| 223 |
+
input_sizes:
|
| 224 |
+
- - 3
|
| 225 |
+
- 224
|
| 226 |
+
- 224
|
| 227 |
+
- - 3
|
| 228 |
+
- 224
|
| 229 |
+
- 224
|
| 230 |
+
- - 3
|
| 231 |
+
- 224
|
| 232 |
+
- 224
|
| 233 |
+
letterbox_crop_fraction: 0.95
|
| 234 |
+
letterbox_fill:
|
| 235 |
+
- 0
|
| 236 |
+
- 0
|
| 237 |
+
- 0
|
| 238 |
+
letterbox_pad_position: center
|
| 239 |
+
means:
|
| 240 |
+
- - 127.5
|
| 241 |
+
- 127.5
|
| 242 |
+
- 127.5
|
| 243 |
+
- - 127.5
|
| 244 |
+
- 127.5
|
| 245 |
+
- 127.5
|
| 246 |
+
- - 127.5
|
| 247 |
+
- 127.5
|
| 248 |
+
- 127.5
|
| 249 |
+
stds:
|
| 250 |
+
- - 127.5
|
| 251 |
+
- 127.5
|
| 252 |
+
- 127.5
|
| 253 |
+
- - 127.5
|
| 254 |
+
- 127.5
|
| 255 |
+
- 127.5
|
| 256 |
+
- - 127.5
|
| 257 |
+
- 127.5
|
| 258 |
+
- 127.5
|
| 259 |
+
type: TransformImage
|
| 260 |
+
type: RoboDojoEvalDataset
|
| 261 |
+
denormalize_action:
|
| 262 |
+
action_dim: 14
|
| 263 |
+
delta_action_mask:
|
| 264 |
+
- true
|
| 265 |
+
- true
|
| 266 |
+
- true
|
| 267 |
+
- true
|
| 268 |
+
- true
|
| 269 |
+
- true
|
| 270 |
+
- true
|
| 271 |
+
- true
|
| 272 |
+
- true
|
| 273 |
+
- true
|
| 274 |
+
- true
|
| 275 |
+
- true
|
| 276 |
+
- true
|
| 277 |
+
- true
|
| 278 |
+
norm_type: quantile
|
| 279 |
+
statistic_name: robodojo_arx_x5
|
| 280 |
+
type: DenormalizeDeltaAction
|
| 281 |
+
model_family: groot
|
| 282 |
+
num_trials_per_task: 25
|
| 283 |
+
report_kind: robodojo
|
| 284 |
+
task_suite_name: robodojo
|
| 285 |
+
inference_model:
|
| 286 |
+
pretrained_name_or_path: ./checkpoints/GR00T-N1.5-3B
|
| 287 |
+
type: LlavaVLA
|
| 288 |
+
vla_head:
|
| 289 |
+
action_dim: 32
|
| 290 |
+
diffusion_model_cfg:
|
| 291 |
+
attention_head_dim: 48
|
| 292 |
+
cross_attention_dim: 2048
|
| 293 |
+
dropout: 0.2
|
| 294 |
+
final_dropout: true
|
| 295 |
+
interleave_self_attention: true
|
| 296 |
+
norm_type: ada_norm
|
| 297 |
+
num_attention_heads: 32
|
| 298 |
+
num_layers: 16
|
| 299 |
+
output_dim: 1024
|
| 300 |
+
positional_embeddings: null
|
| 301 |
+
hidden_size: 1024
|
| 302 |
+
input_embedding_dim: 1536
|
| 303 |
+
max_input_seq_len: 1100
|
| 304 |
+
num_inference_timesteps: 4
|
| 305 |
+
num_steps: 16
|
| 306 |
+
ori_action_dim: 14
|
| 307 |
+
state_dim: 64
|
| 308 |
+
type: FlowMatchingInferenceHead
|
| 309 |
+
vlm_backbone:
|
| 310 |
+
type: EagleInferenceBackbone
|
| 311 |
+
vlm_config:
|
| 312 |
+
max_input_seq_len: 1100
|
| 313 |
+
vlm_path: fluxvla/models/third_party_models/eagle2_hg_model
|
| 314 |
+
model:
|
| 315 |
+
freeze_projector: false
|
| 316 |
+
freeze_vlm_backbone: false
|
| 317 |
+
name_mapping:
|
| 318 |
+
vla_head: action_head
|
| 319 |
+
vlm_backbone.vlm: backbone.eagle_model
|
| 320 |
+
pretrained_name_or_path: ./checkpoints/GR00T-N1.5-3B
|
| 321 |
+
type: LlavaVLA
|
| 322 |
+
vla_head:
|
| 323 |
+
action_dim: 32
|
| 324 |
+
hidden_size: 1024
|
| 325 |
+
input_embedding_dim: 1536
|
| 326 |
+
noise_beta_alpha: 1.5
|
| 327 |
+
noise_beta_beta: 1.0
|
| 328 |
+
num_inference_timesteps: 4
|
| 329 |
+
num_steps: 16
|
| 330 |
+
ori_action_dim: 14
|
| 331 |
+
state_dim: 64
|
| 332 |
+
state_dropout_prob: 0.2
|
| 333 |
+
type: FlowMatchingHead
|
| 334 |
+
vlm_backbone:
|
| 335 |
+
dtype: bf16
|
| 336 |
+
tune_llm: false
|
| 337 |
+
tune_visual: false
|
| 338 |
+
type: EagleBackbone
|
| 339 |
+
vlm_config:
|
| 340 |
+
max_input_seq_len: 1100
|
| 341 |
+
vlm_path: fluxvla/models/third_party_models/eagle2_hg_model
|
| 342 |
+
runner:
|
| 343 |
+
change_key_name: false
|
| 344 |
+
collator:
|
| 345 |
+
keys:
|
| 346 |
+
- states
|
| 347 |
+
- timestamp
|
| 348 |
+
- images
|
| 349 |
+
- img_masks
|
| 350 |
+
- lang_tokens
|
| 351 |
+
- lang_masks
|
| 352 |
+
- actions
|
| 353 |
+
- action_masks
|
| 354 |
+
- embodiment_ids
|
| 355 |
+
meta_keys:
|
| 356 |
+
- task_description
|
| 357 |
+
- prompt
|
| 358 |
+
- info
|
| 359 |
+
- stats
|
| 360 |
+
type: DictCollator
|
| 361 |
+
enable_gradient_checkpointing: false
|
| 362 |
+
enable_mixed_precision_training: true
|
| 363 |
+
grad_accumulation_steps: 5
|
| 364 |
+
lr_scheduler:
|
| 365 |
+
type: linear-warmup+cosine-decay
|
| 366 |
+
warmup_ratio: 0.05
|
| 367 |
+
max_epochs: null
|
| 368 |
+
max_grad_norm: 1.0
|
| 369 |
+
max_keep_ckpts: 5
|
| 370 |
+
max_steps: 100000
|
| 371 |
+
metric:
|
| 372 |
+
active_trackers:
|
| 373 |
+
- jsonl
|
| 374 |
+
- wandb
|
| 375 |
+
grad_accumulation_steps: 5
|
| 376 |
+
run_dir: work_dirs
|
| 377 |
+
type: VLAMetric
|
| 378 |
+
window_size: 1
|
| 379 |
+
mixed_precision_dtype: bf16
|
| 380 |
+
optimizer:
|
| 381 |
+
lr: 0.0001
|
| 382 |
+
type: AdamW
|
| 383 |
+
weight_decay: 1.0e-05
|
| 384 |
+
sampler: null
|
| 385 |
+
save_epoch_interval: 1
|
| 386 |
+
save_iter_interval: 1000
|
| 387 |
+
sharding_strategy: no-shard
|
| 388 |
+
tokenizer:
|
| 389 |
+
model_path: fluxvla/models/third_party_models/eagle2_hg_model
|
| 390 |
+
type: PretrainedTokenizer
|
| 391 |
+
type: FSDPTrainRunner
|
| 392 |
+
themis:
|
| 393 |
+
ros_server:
|
| 394 |
+
dataset_section: eval
|
| 395 |
+
denormalize_context:
|
| 396 |
+
task_suite_name: robodojo_arx_x5
|
| 397 |
+
device: cuda:0
|
| 398 |
+
enable_mixed_precision: true
|
| 399 |
+
evaluation_reporting:
|
| 400 |
+
result_output_dir: work_dirs/fluxthemis
|
| 401 |
+
forward_seed: false
|
| 402 |
+
mixed_precision_dtype: bf16
|
| 403 |
+
model_outputs_environment_actions: false
|
| 404 |
+
workers:
|
| 405 |
+
lease_timeout_s: 900.0
|
| 406 |
+
request_timeout_s: 120.0
|
| 407 |
+
startup_timeout_s: 900.0
|
| 408 |
+
runner:
|
| 409 |
+
environment:
|
| 410 |
+
action_mode: joint
|
| 411 |
+
device_id: 1
|
| 412 |
+
env_cfg_type: arx_x5
|
| 413 |
+
headless: true
|
| 414 |
+
robodojo_root: /root/projects/RoboDojo
|
| 415 |
+
save_videos: false
|
| 416 |
+
task_name: all
|
| 417 |
+
type: RoboDojoEnvironment
|
| 418 |
+
episodes_per_task: 25
|
| 419 |
+
evaluator:
|
| 420 |
+
type: SuccessRateEvaluator
|
| 421 |
+
execute_horizon: 16
|
| 422 |
+
max_episode_steps: 2000
|
| 423 |
+
model_client:
|
| 424 |
+
type: FluxVLAZMQModelClient
|
| 425 |
+
parallel_workers: 1
|
| 426 |
+
seed: 0
|
| 427 |
+
simulator_gpu_ids: null
|
| 428 |
+
stop_on_success: true
|
| 429 |
+
type: EvalRunner
|
| 430 |
+
work_dir: work_dirs/fluxthemis
|
| 431 |
+
transport:
|
| 432 |
+
host: 127.0.0.1
|
| 433 |
+
image_encoding: rgb8
|
| 434 |
+
image_keys:
|
| 435 |
+
- cam_high
|
| 436 |
+
- cam_left_wrist
|
| 437 |
+
- cam_right_wrist
|
| 438 |
+
port: 5555
|
| 439 |
+
report_service_name: /fluxvla/report_evaluation
|
| 440 |
+
state_keys:
|
| 441 |
+
- states
|
| 442 |
+
timeout_s: 30.0
|
| 443 |
+
unnorm_key: robodojo_arx_x5
|
| 444 |
+
train_dataloader:
|
| 445 |
+
dataset:
|
| 446 |
+
dataset_statistics:
|
| 447 |
+
robodojo_arx_x5:
|
| 448 |
+
action:
|
| 449 |
+
count: 29333632
|
| 450 |
+
max:
|
| 451 |
+
- 1.8887031078338623
|
| 452 |
+
- 2.241629123687744
|
| 453 |
+
- 2.3643198013305664
|
| 454 |
+
- 2.353733539581299
|
| 455 |
+
- 1.684847116470337
|
| 456 |
+
- 2.5986948013305664
|
| 457 |
+
- 1.0
|
| 458 |
+
- 1.6447105407714844
|
| 459 |
+
- 2.472832202911377
|
| 460 |
+
- 3.1138815879821777
|
| 461 |
+
- 2.544224500656128
|
| 462 |
+
- 2.4465250968933105
|
| 463 |
+
- 2.3557143211364746
|
| 464 |
+
- 1.0
|
| 465 |
+
mean:
|
| 466 |
+
- -0.00016787611640384256
|
| 467 |
+
- 3.640991079951193e-05
|
| 468 |
+
- -0.0001244129093475812
|
| 469 |
+
- 0.0009861263907153927
|
| 470 |
+
- 4.007764372684936e-05
|
| 471 |
+
- -0.0005710965315355596
|
| 472 |
+
- -0.00033464226771561873
|
| 473 |
+
- 0.00014757256047559194
|
| 474 |
+
- 0.002926647213791033
|
| 475 |
+
- 0.002445220311756816
|
| 476 |
+
- -0.0017966633835313532
|
| 477 |
+
- -0.00034538796665606477
|
| 478 |
+
- -0.0010489735053372264
|
| 479 |
+
- -0.0008483530749860559
|
| 480 |
+
min:
|
| 481 |
+
- -1.9831359386444092
|
| 482 |
+
- -2.3307759761810303
|
| 483 |
+
- -2.36329984664917
|
| 484 |
+
- -2.3512368202209473
|
| 485 |
+
- -1.7914525270462036
|
| 486 |
+
- -2.4492745399475098
|
| 487 |
+
- -1.0
|
| 488 |
+
- -1.6693108081817627
|
| 489 |
+
- -2.261469841003418
|
| 490 |
+
- -2.36698317527771
|
| 491 |
+
- -2.53256893157959
|
| 492 |
+
- -2.4855473041534424
|
| 493 |
+
- -2.839830160140991
|
| 494 |
+
- -1.0
|
| 495 |
+
q01:
|
| 496 |
+
- -0.5563330262899399
|
| 497 |
+
- -1.164183863401413
|
| 498 |
+
- -0.9725008648633957
|
| 499 |
+
- -0.7879389774799347
|
| 500 |
+
- -0.35899992257356644
|
| 501 |
+
- -0.8268111473321915
|
| 502 |
+
- -0.6629222631454468
|
| 503 |
+
- -0.48305779963731765
|
| 504 |
+
- -1.1301205492019653
|
| 505 |
+
- -0.9574322783946991
|
| 506 |
+
- -0.7862630712985993
|
| 507 |
+
- -0.3646536460518837
|
| 508 |
+
- -0.8233565813302994
|
| 509 |
+
- -0.6629220247268677
|
| 510 |
+
q99:
|
| 511 |
+
- 0.5548361170291902
|
| 512 |
+
- 1.0296359968185431
|
| 513 |
+
- 0.8563214296102533
|
| 514 |
+
- 0.8150562870502474
|
| 515 |
+
- 0.39599745541810993
|
| 516 |
+
- 0.8352749580144907
|
| 517 |
+
- 0.6292134523391724
|
| 518 |
+
- 0.4990877494215987
|
| 519 |
+
- 1.0044999086856863
|
| 520 |
+
- 0.8432489860057832
|
| 521 |
+
- 0.78897400379181
|
| 522 |
+
- 0.32408514618873596
|
| 523 |
+
- 0.7997124117612857
|
| 524 |
+
- 0.6112149953842163
|
| 525 |
+
std:
|
| 526 |
+
- 0.1524663344569265
|
| 527 |
+
- 0.29040871843218186
|
| 528 |
+
- 0.25021202987482355
|
| 529 |
+
- 0.2233514194013506
|
| 530 |
+
- 0.10648562443390856
|
| 531 |
+
- 0.2295837861601856
|
| 532 |
+
- 0.16658472644994762
|
| 533 |
+
- 0.13469893280906062
|
| 534 |
+
- 0.27712445038284145
|
| 535 |
+
- 0.24285089420664013
|
| 536 |
+
- 0.21544770406738722
|
| 537 |
+
- 0.09925954744044597
|
| 538 |
+
- 0.22253717352947505
|
| 539 |
+
- 0.16110866685153383
|
| 540 |
+
proprio:
|
| 541 |
+
count: 1859602
|
| 542 |
+
max:
|
| 543 |
+
- 1.7537026405334473
|
| 544 |
+
- 3.0546703338623047
|
| 545 |
+
- 3.8525187969207764
|
| 546 |
+
- 2.0974574089050293
|
| 547 |
+
- 1.8103265762329102
|
| 548 |
+
- 3.1366536617279053
|
| 549 |
+
- 1.0
|
| 550 |
+
- 1.6732014417648315
|
| 551 |
+
- 3.3797459602355957
|
| 552 |
+
- 4.252756595611572
|
| 553 |
+
- 2.5287232398986816
|
| 554 |
+
- 3.1440579891204834
|
| 555 |
+
- 3.0381109714508057
|
| 556 |
+
- 1.0
|
| 557 |
+
mean:
|
| 558 |
+
- -0.20040483418845204
|
| 559 |
+
- 0.9260308650671458
|
| 560 |
+
- 0.6881893789087474
|
| 561 |
+
- -0.3400484544283471
|
| 562 |
+
- 0.06579394032953159
|
| 563 |
+
- 0.004003331131509558
|
| 564 |
+
- 0.771446548553906
|
| 565 |
+
- 0.17299834959584776
|
| 566 |
+
- 0.8224941837716736
|
| 567 |
+
- 0.6196513047400859
|
| 568 |
+
- -0.3604178625374315
|
| 569 |
+
- -0.06267071413702419
|
| 570 |
+
- 0.0037534824507240434
|
| 571 |
+
- 0.7860054714056368
|
| 572 |
+
min:
|
| 573 |
+
- -1.4863648414611816
|
| 574 |
+
- -0.2586335241794586
|
| 575 |
+
- -0.06850092858076096
|
| 576 |
+
- -2.2642147541046143
|
| 577 |
+
- -1.4876768589019775
|
| 578 |
+
- -3.0168392658233643
|
| 579 |
+
- -3.212450869184004e-17
|
| 580 |
+
- -1.4924354553222656
|
| 581 |
+
- -0.27809593081474304
|
| 582 |
+
- -0.18774886429309845
|
| 583 |
+
- -2.5354628562927246
|
| 584 |
+
- -3.0663280487060547
|
| 585 |
+
- -3.0486762523651123
|
| 586 |
+
- -3.212450869184004e-17
|
| 587 |
+
q01:
|
| 588 |
+
- -1.051365569829941
|
| 589 |
+
- -3.52302449637288e-14
|
| 590 |
+
- 1.6996893991849812e-16
|
| 591 |
+
- -1.5984010362625123
|
| 592 |
+
- -0.6003412520885467
|
| 593 |
+
- -1.6678147149085998
|
| 594 |
+
- 0.0
|
| 595 |
+
- -0.4500492787361145
|
| 596 |
+
- -2.5859282299029243e-14
|
| 597 |
+
- 1.194697284288627e-16
|
| 598 |
+
- -1.6398817586898804
|
| 599 |
+
- -1.263367258310318
|
| 600 |
+
- -1.760098042488098
|
| 601 |
+
- 0.0
|
| 602 |
+
q99:
|
| 603 |
+
- 0.5431358617544174
|
| 604 |
+
- 2.495765209197998
|
| 605 |
+
- 2.492974226474762
|
| 606 |
+
- 1.323737324476242
|
| 607 |
+
- 1.2496635341644287
|
| 608 |
+
- 1.7391636216640465
|
| 609 |
+
- 1.0
|
| 610 |
+
- 1.0814965963363647
|
| 611 |
+
- 2.416655488014221
|
| 612 |
+
- 2.346989154815674
|
| 613 |
+
- 1.1415718960762022
|
| 614 |
+
- 0.5208872479200363
|
| 615 |
+
- 1.4889542925357817
|
| 616 |
+
- 1.0
|
| 617 |
+
std:
|
| 618 |
+
- 0.34305506136703257
|
| 619 |
+
- 0.8880398716756615
|
| 620 |
+
- 0.7302413867018247
|
| 621 |
+
- 0.6487680858145891
|
| 622 |
+
- 0.2989095916390101
|
| 623 |
+
- 0.584300843989697
|
| 624 |
+
- 0.34316664624786114
|
| 625 |
+
- 0.31989806135013626
|
| 626 |
+
- 0.8736479432260295
|
| 627 |
+
- 0.7135350385777451
|
| 628 |
+
- 0.6027223159771133
|
| 629 |
+
- 0.2836475966439172
|
| 630 |
+
- 0.5368540820848867
|
| 631 |
+
- 0.3406560080480477
|
| 632 |
+
datasets:
|
| 633 |
+
- action_key: action
|
| 634 |
+
action_window_size: 16
|
| 635 |
+
data_root_path:
|
| 636 |
+
- ./datasets/RoboDojo_lerobot_v21_video
|
| 637 |
+
statistic_name: robodojo_arx_x5
|
| 638 |
+
transforms:
|
| 639 |
+
- embodiment_id: 31
|
| 640 |
+
name_mappings:
|
| 641 |
+
actions:
|
| 642 |
+
- actions
|
| 643 |
+
observation.state:
|
| 644 |
+
- states
|
| 645 |
+
parquet_keys:
|
| 646 |
+
- observation.state
|
| 647 |
+
- timestamp
|
| 648 |
+
- actions
|
| 649 |
+
- info
|
| 650 |
+
- stats
|
| 651 |
+
- action_masks
|
| 652 |
+
type: ProcessParquetInputs
|
| 653 |
+
video_keys:
|
| 654 |
+
- observation.images.cam_high
|
| 655 |
+
- observation.images.cam_left_wrist
|
| 656 |
+
- observation.images.cam_right_wrist
|
| 657 |
+
- mask:
|
| 658 |
+
- true
|
| 659 |
+
- true
|
| 660 |
+
- true
|
| 661 |
+
- true
|
| 662 |
+
- true
|
| 663 |
+
- true
|
| 664 |
+
- true
|
| 665 |
+
- true
|
| 666 |
+
- true
|
| 667 |
+
- true
|
| 668 |
+
- true
|
| 669 |
+
- true
|
| 670 |
+
- true
|
| 671 |
+
- true
|
| 672 |
+
type: DeltaActions
|
| 673 |
+
- type: ParquetPrompter
|
| 674 |
+
- max_len: 1100
|
| 675 |
+
num_images: 3
|
| 676 |
+
tokenizer:
|
| 677 |
+
model_path: fluxvla/models/third_party_models/eagle2_hg_model
|
| 678 |
+
type: PretrainedTokenizer
|
| 679 |
+
type: ProcessPromptsWithImage
|
| 680 |
+
- height: 224
|
| 681 |
+
pad_direction: center
|
| 682 |
+
pad_value: 0
|
| 683 |
+
type: ResizeImagesWithPad
|
| 684 |
+
width: 224
|
| 685 |
+
- scale: 0.95
|
| 686 |
+
type: RandomCropImages
|
| 687 |
+
- height: 224
|
| 688 |
+
type: ResizeImages
|
| 689 |
+
width: 224
|
| 690 |
+
- brightness: 0.3
|
| 691 |
+
contrast: 0.4
|
| 692 |
+
hue: 0.08
|
| 693 |
+
saturation: 0.5
|
| 694 |
+
type: ColorJitterImages
|
| 695 |
+
- type: SimpleNormalizeImages
|
| 696 |
+
- action_dim: 32
|
| 697 |
+
action_key: action
|
| 698 |
+
clip_norm: true
|
| 699 |
+
norm_type: quantile
|
| 700 |
+
normalize_states: true
|
| 701 |
+
state_dim: 64
|
| 702 |
+
state_key: proprio
|
| 703 |
+
type: NormalizeStatesAndActions
|
| 704 |
+
type: ParquetDataset
|
| 705 |
+
use_delta: false
|
| 706 |
+
window_start_idx: 0
|
| 707 |
+
name_mappings:
|
| 708 |
+
action:
|
| 709 |
+
- action
|
| 710 |
+
observation.state:
|
| 711 |
+
- proprio
|
| 712 |
+
statistic_keys:
|
| 713 |
+
- observation.state
|
| 714 |
+
- action
|
| 715 |
+
- timestamp
|
| 716 |
+
statistic_name: robodojo_arx_x5
|
| 717 |
+
type: DistributedRepeatingDataset
|
| 718 |
+
per_device_batch_size: 8
|
| 719 |
+
per_device_num_workers: 4
|
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robodojo_arx_x5": {
|
| 3 |
+
"proprio": {
|
| 4 |
+
"mean": [
|
| 5 |
+
-0.20040483418845204,
|
| 6 |
+
0.9260308650671458,
|
| 7 |
+
0.6881893789087474,
|
| 8 |
+
-0.3400484544283471,
|
| 9 |
+
0.06579394032953159,
|
| 10 |
+
0.004003331131509558,
|
| 11 |
+
0.771446548553906,
|
| 12 |
+
0.17299834959584776,
|
| 13 |
+
0.8224941837716736,
|
| 14 |
+
0.6196513047400859,
|
| 15 |
+
-0.3604178625374315,
|
| 16 |
+
-0.06267071413702419,
|
| 17 |
+
0.0037534824507240434,
|
| 18 |
+
0.7860054714056368
|
| 19 |
+
],
|
| 20 |
+
"std": [
|
| 21 |
+
0.34305506136703257,
|
| 22 |
+
0.8880398716756615,
|
| 23 |
+
0.7302413867018247,
|
| 24 |
+
0.6487680858145891,
|
| 25 |
+
0.2989095916390101,
|
| 26 |
+
0.584300843989697,
|
| 27 |
+
0.34316664624786114,
|
| 28 |
+
0.31989806135013626,
|
| 29 |
+
0.8736479432260295,
|
| 30 |
+
0.7135350385777451,
|
| 31 |
+
0.6027223159771133,
|
| 32 |
+
0.2836475966439172,
|
| 33 |
+
0.5368540820848867,
|
| 34 |
+
0.3406560080480477
|
| 35 |
+
],
|
| 36 |
+
"min": [
|
| 37 |
+
-1.4863648414611816,
|
| 38 |
+
-0.2586335241794586,
|
| 39 |
+
-0.06850092858076096,
|
| 40 |
+
-2.2642147541046143,
|
| 41 |
+
-1.4876768589019775,
|
| 42 |
+
-3.0168392658233643,
|
| 43 |
+
-3.212450869184004e-17,
|
| 44 |
+
-1.4924354553222656,
|
| 45 |
+
-0.27809593081474304,
|
| 46 |
+
-0.18774886429309845,
|
| 47 |
+
-2.5354628562927246,
|
| 48 |
+
-3.0663280487060547,
|
| 49 |
+
-3.0486762523651123,
|
| 50 |
+
-3.212450869184004e-17
|
| 51 |
+
],
|
| 52 |
+
"max": [
|
| 53 |
+
1.7537026405334473,
|
| 54 |
+
3.0546703338623047,
|
| 55 |
+
3.8525187969207764,
|
| 56 |
+
2.0974574089050293,
|
| 57 |
+
1.8103265762329102,
|
| 58 |
+
3.1366536617279053,
|
| 59 |
+
1.0,
|
| 60 |
+
1.6732014417648315,
|
| 61 |
+
3.3797459602355957,
|
| 62 |
+
4.252756595611572,
|
| 63 |
+
2.5287232398986816,
|
| 64 |
+
3.1440579891204834,
|
| 65 |
+
3.0381109714508057,
|
| 66 |
+
1.0
|
| 67 |
+
],
|
| 68 |
+
"q01": [
|
| 69 |
+
-1.051365569829941,
|
| 70 |
+
-3.52302449637288e-14,
|
| 71 |
+
1.6996893991849812e-16,
|
| 72 |
+
-1.5984010362625123,
|
| 73 |
+
-0.6003412520885467,
|
| 74 |
+
-1.6678147149085998,
|
| 75 |
+
0.0,
|
| 76 |
+
-0.4500492787361145,
|
| 77 |
+
-2.5859282299029243e-14,
|
| 78 |
+
1.194697284288627e-16,
|
| 79 |
+
-1.6398817586898804,
|
| 80 |
+
-1.263367258310318,
|
| 81 |
+
-1.760098042488098,
|
| 82 |
+
0.0
|
| 83 |
+
],
|
| 84 |
+
"q99": [
|
| 85 |
+
0.5431358617544174,
|
| 86 |
+
2.495765209197998,
|
| 87 |
+
2.492974226474762,
|
| 88 |
+
1.323737324476242,
|
| 89 |
+
1.2496635341644287,
|
| 90 |
+
1.7391636216640465,
|
| 91 |
+
1.0,
|
| 92 |
+
1.0814965963363647,
|
| 93 |
+
2.416655488014221,
|
| 94 |
+
2.346989154815674,
|
| 95 |
+
1.1415718960762022,
|
| 96 |
+
0.5208872479200363,
|
| 97 |
+
1.4889542925357817,
|
| 98 |
+
1.0
|
| 99 |
+
],
|
| 100 |
+
"count": 1859602
|
| 101 |
+
},
|
| 102 |
+
"action": {
|
| 103 |
+
"mean": [
|
| 104 |
+
-0.00016787611640384256,
|
| 105 |
+
3.640991079951193e-05,
|
| 106 |
+
-0.0001244129093475812,
|
| 107 |
+
0.0009861263907153927,
|
| 108 |
+
4.007764372684936e-05,
|
| 109 |
+
-0.0005710965315355596,
|
| 110 |
+
-0.00033464226771561873,
|
| 111 |
+
0.00014757256047559194,
|
| 112 |
+
0.002926647213791033,
|
| 113 |
+
0.002445220311756816,
|
| 114 |
+
-0.0017966633835313532,
|
| 115 |
+
-0.00034538796665606477,
|
| 116 |
+
-0.0010489735053372264,
|
| 117 |
+
-0.0008483530749860559
|
| 118 |
+
],
|
| 119 |
+
"std": [
|
| 120 |
+
0.1524663344569265,
|
| 121 |
+
0.29040871843218186,
|
| 122 |
+
0.25021202987482355,
|
| 123 |
+
0.2233514194013506,
|
| 124 |
+
0.10648562443390856,
|
| 125 |
+
0.2295837861601856,
|
| 126 |
+
0.16658472644994762,
|
| 127 |
+
0.13469893280906062,
|
| 128 |
+
0.27712445038284145,
|
| 129 |
+
0.24285089420664013,
|
| 130 |
+
0.21544770406738722,
|
| 131 |
+
0.09925954744044597,
|
| 132 |
+
0.22253717352947505,
|
| 133 |
+
0.16110866685153383
|
| 134 |
+
],
|
| 135 |
+
"min": [
|
| 136 |
+
-1.9831359386444092,
|
| 137 |
+
-2.3307759761810303,
|
| 138 |
+
-2.36329984664917,
|
| 139 |
+
-2.3512368202209473,
|
| 140 |
+
-1.7914525270462036,
|
| 141 |
+
-2.4492745399475098,
|
| 142 |
+
-1.0,
|
| 143 |
+
-1.6693108081817627,
|
| 144 |
+
-2.261469841003418,
|
| 145 |
+
-2.36698317527771,
|
| 146 |
+
-2.53256893157959,
|
| 147 |
+
-2.4855473041534424,
|
| 148 |
+
-2.839830160140991,
|
| 149 |
+
-1.0
|
| 150 |
+
],
|
| 151 |
+
"max": [
|
| 152 |
+
1.8887031078338623,
|
| 153 |
+
2.241629123687744,
|
| 154 |
+
2.3643198013305664,
|
| 155 |
+
2.353733539581299,
|
| 156 |
+
1.684847116470337,
|
| 157 |
+
2.5986948013305664,
|
| 158 |
+
1.0,
|
| 159 |
+
1.6447105407714844,
|
| 160 |
+
2.472832202911377,
|
| 161 |
+
3.1138815879821777,
|
| 162 |
+
2.544224500656128,
|
| 163 |
+
2.4465250968933105,
|
| 164 |
+
2.3557143211364746,
|
| 165 |
+
1.0
|
| 166 |
+
],
|
| 167 |
+
"q01": [
|
| 168 |
+
-0.5563330262899399,
|
| 169 |
+
-1.164183863401413,
|
| 170 |
+
-0.9725008648633957,
|
| 171 |
+
-0.7879389774799347,
|
| 172 |
+
-0.35899992257356644,
|
| 173 |
+
-0.8268111473321915,
|
| 174 |
+
-0.6629222631454468,
|
| 175 |
+
-0.48305779963731765,
|
| 176 |
+
-1.1301205492019653,
|
| 177 |
+
-0.9574322783946991,
|
| 178 |
+
-0.7862630712985993,
|
| 179 |
+
-0.3646536460518837,
|
| 180 |
+
-0.8233565813302994,
|
| 181 |
+
-0.6629220247268677
|
| 182 |
+
],
|
| 183 |
+
"q99": [
|
| 184 |
+
0.5548361170291902,
|
| 185 |
+
1.0296359968185431,
|
| 186 |
+
0.8563214296102533,
|
| 187 |
+
0.8150562870502474,
|
| 188 |
+
0.39599745541810993,
|
| 189 |
+
0.8352749580144907,
|
| 190 |
+
0.6292134523391724,
|
| 191 |
+
0.4990877494215987,
|
| 192 |
+
1.0044999086856863,
|
| 193 |
+
0.8432489860057832,
|
| 194 |
+
0.78897400379181,
|
| 195 |
+
0.32408514618873596,
|
| 196 |
+
0.7997124117612857,
|
| 197 |
+
0.6112149953842163
|
| 198 |
+
],
|
| 199 |
+
"count": 29333632
|
| 200 |
+
}
|
| 201 |
+
}
|
| 202 |
+
}
|
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151673,
|
| 3 |
+
"</img>": 151671,
|
| 4 |
+
"</interval>": 151679,
|
| 5 |
+
"</quad>": 151675,
|
| 6 |
+
"</ref>": 151677,
|
| 7 |
+
"</think>": 151668,
|
| 8 |
+
"</tool_call>": 151658,
|
| 9 |
+
"</tool_response>": 151666,
|
| 10 |
+
"<IMG_CONTEXT>": 151669,
|
| 11 |
+
"<box>": 151672,
|
| 12 |
+
"<img>": 151670,
|
| 13 |
+
"<interval>": 151678,
|
| 14 |
+
"<quad>": 151674,
|
| 15 |
+
"<ref>": 151676,
|
| 16 |
+
"<think>": 151667,
|
| 17 |
+
"<tool_call>": 151657,
|
| 18 |
+
"<tool_response>": 151665,
|
| 19 |
+
"<|box_end|>": 151649,
|
| 20 |
+
"<|box_start|>": 151648,
|
| 21 |
+
"<|endoftext|>": 151643,
|
| 22 |
+
"<|file_sep|>": 151664,
|
| 23 |
+
"<|fim_middle|>": 151660,
|
| 24 |
+
"<|fim_pad|>": 151662,
|
| 25 |
+
"<|fim_prefix|>": 151659,
|
| 26 |
+
"<|fim_suffix|>": 151661,
|
| 27 |
+
"<|im_end|>": 151645,
|
| 28 |
+
"<|im_start|>": 151644,
|
| 29 |
+
"<|image_pad|>": 151655,
|
| 30 |
+
"<|object_ref_end|>": 151647,
|
| 31 |
+
"<|object_ref_start|>": 151646,
|
| 32 |
+
"<|quad_end|>": 151651,
|
| 33 |
+
"<|quad_start|>": 151650,
|
| 34 |
+
"<|repo_name|>": 151663,
|
| 35 |
+
"<|video_pad|>": 151656,
|
| 36 |
+
"<|vision_end|>": 151653,
|
| 37 |
+
"<|vision_pad|>": 151654,
|
| 38 |
+
"<|vision_start|>": 151652
|
| 39 |
+
}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<IMG_CONTEXT>",
|
| 17 |
+
"<img>",
|
| 18 |
+
"</img>",
|
| 19 |
+
"<box>",
|
| 20 |
+
"</box>",
|
| 21 |
+
"<quad>",
|
| 22 |
+
"</quad>",
|
| 23 |
+
"<ref>",
|
| 24 |
+
"</ref>",
|
| 25 |
+
"<interval>",
|
| 26 |
+
"</interval>"
|
| 27 |
+
],
|
| 28 |
+
"eos_token": {
|
| 29 |
+
"content": "<|im_end|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"pad_token": {
|
| 36 |
+
"content": "<|endoftext|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
|
@@ -0,0 +1,344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<IMG_CONTEXT>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "<img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "</img>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<box>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</box>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<quad>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</quad>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<ref>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</ref>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<interval>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "</interval>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
}
|
| 302 |
+
},
|
| 303 |
+
"additional_special_tokens": [
|
| 304 |
+
"<|im_start|>",
|
| 305 |
+
"<|im_end|>",
|
| 306 |
+
"<|object_ref_start|>",
|
| 307 |
+
"<|object_ref_end|>",
|
| 308 |
+
"<|box_start|>",
|
| 309 |
+
"<|box_end|>",
|
| 310 |
+
"<|quad_start|>",
|
| 311 |
+
"<|quad_end|>",
|
| 312 |
+
"<|vision_start|>",
|
| 313 |
+
"<|vision_end|>",
|
| 314 |
+
"<|vision_pad|>",
|
| 315 |
+
"<|image_pad|>",
|
| 316 |
+
"<|video_pad|>",
|
| 317 |
+
"<IMG_CONTEXT>",
|
| 318 |
+
"<img>",
|
| 319 |
+
"</img>",
|
| 320 |
+
"<box>",
|
| 321 |
+
"</box>",
|
| 322 |
+
"<quad>",
|
| 323 |
+
"</quad>",
|
| 324 |
+
"<ref>",
|
| 325 |
+
"</ref>",
|
| 326 |
+
"<interval>",
|
| 327 |
+
"</interval>"
|
| 328 |
+
],
|
| 329 |
+
"auto_map": {
|
| 330 |
+
"AutoProcessor": "processing_eagle2_5_vl.Eagle2_5_VLProcessor"
|
| 331 |
+
},
|
| 332 |
+
"bos_token": null,
|
| 333 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 334 |
+
"clean_up_tokenization_spaces": false,
|
| 335 |
+
"eos_token": "<|im_end|>",
|
| 336 |
+
"errors": "replace",
|
| 337 |
+
"extra_special_tokens": {},
|
| 338 |
+
"model_max_length": 16384,
|
| 339 |
+
"pad_token": "<|endoftext|>",
|
| 340 |
+
"processor_class": "Eagle2_5_VLProcessor",
|
| 341 |
+
"split_special_tokens": false,
|
| 342 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 343 |
+
"unk_token": null
|
| 344 |
+
}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation": "flash_attention_2",
|
| 3 |
+
"_attn_implementation_autoset": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Eagle2_5_VLForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attn_implementation": "flash_attention_2",
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_eagle2_5_vl.Eagle2_5_VLConfig",
|
| 10 |
+
"AutoModel": "modeling_eagle2_5_vl.Eagle2_5_VLForConditionalGeneration"
|
| 11 |
+
},
|
| 12 |
+
"downsample_ratio": 0.5,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"dynamic_image_size": true,
|
| 15 |
+
"force_image_size": 224,
|
| 16 |
+
"image_token_index": 151669,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"loss_version": "efficient_v2_cp_head",
|
| 19 |
+
"max_dynamic_tiles": 12,
|
| 20 |
+
"min_dynamic_tiles": 1,
|
| 21 |
+
"mlp_checkpoint": false,
|
| 22 |
+
"mlp_connector_layers": 1,
|
| 23 |
+
"model_type": "eagle_2_5_vl",
|
| 24 |
+
"output_attentions": false,
|
| 25 |
+
"pad2square": false,
|
| 26 |
+
"select_layer": -1,
|
| 27 |
+
"template": "qwen3-chat",
|
| 28 |
+
"text_config": {
|
| 29 |
+
"_attn_implementation_autoset": true,
|
| 30 |
+
"_name_or_path": "Qwen/Qwen3-1.7B",
|
| 31 |
+
"architectures": [
|
| 32 |
+
"Qwen3ForCausalLM"
|
| 33 |
+
],
|
| 34 |
+
"attention_bias": false,
|
| 35 |
+
"attention_dropout": 0,
|
| 36 |
+
"attn_implementation": "flash_attention_2",
|
| 37 |
+
"bos_token_id": 151643,
|
| 38 |
+
"dtype": "bfloat16",
|
| 39 |
+
"eos_token_id": 151645,
|
| 40 |
+
"head_dim": 128,
|
| 41 |
+
"hidden_act": "silu",
|
| 42 |
+
"hidden_size": 2048,
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 6144,
|
| 45 |
+
"layer_types": [
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention"
|
| 74 |
+
],
|
| 75 |
+
"max_position_embeddings": 40960,
|
| 76 |
+
"max_window_layers": 28,
|
| 77 |
+
"model_type": "qwen3",
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"num_key_value_heads": 8,
|
| 81 |
+
"pad_token_id": null,
|
| 82 |
+
"rms_norm_eps": 1e-06,
|
| 83 |
+
"rope_parameters": {
|
| 84 |
+
"rope_theta": 1000000,
|
| 85 |
+
"rope_type": "default"
|
| 86 |
+
},
|
| 87 |
+
"sliding_window": null,
|
| 88 |
+
"tie_word_embeddings": true,
|
| 89 |
+
"use_cache": false,
|
| 90 |
+
"use_sliding_window": false,
|
| 91 |
+
"vocab_size": 151680
|
| 92 |
+
},
|
| 93 |
+
"tie_word_embeddings": true,
|
| 94 |
+
"transformers_version": null,
|
| 95 |
+
"use_backbone_lora": 0,
|
| 96 |
+
"use_llm_lora": 0,
|
| 97 |
+
"use_pixel_shuffle": false,
|
| 98 |
+
"use_thumbnail": true,
|
| 99 |
+
"vision_config": {
|
| 100 |
+
"_attn_implementation_autoset": true,
|
| 101 |
+
"attention_dropout": 0,
|
| 102 |
+
"attn_implementation": "flash_attention_2",
|
| 103 |
+
"dtype": "bfloat16",
|
| 104 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 105 |
+
"hidden_size": 1152,
|
| 106 |
+
"image_size": 224,
|
| 107 |
+
"intermediate_size": 4304,
|
| 108 |
+
"layer_norm_eps": 1e-06,
|
| 109 |
+
"model_type": "siglip_vision_model",
|
| 110 |
+
"num_attention_heads": 16,
|
| 111 |
+
"num_channels": 3,
|
| 112 |
+
"num_hidden_layers": 27,
|
| 113 |
+
"patch_size": 14
|
| 114 |
+
}
|
| 115 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89bcfc2ed1744b6b78cc55bfe9d88c01ce77327ec1637e2e326db7c90967d1fc
|
| 3 |
+
size 13820861200
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robodojo_arx_x5_relative": {
|
| 3 |
+
"proprio": {
|
| 4 |
+
"max": [
|
| 5 |
+
1.7537026405334473,
|
| 6 |
+
3.0546703338623047,
|
| 7 |
+
3.8525187969207764,
|
| 8 |
+
2.0974574089050293,
|
| 9 |
+
1.8103265762329102,
|
| 10 |
+
3.1366536617279053,
|
| 11 |
+
1.0,
|
| 12 |
+
1.6732014417648315,
|
| 13 |
+
3.3797459602355957,
|
| 14 |
+
4.252756595611572,
|
| 15 |
+
2.5287232398986816,
|
| 16 |
+
3.1440579891204834,
|
| 17 |
+
3.0381109714508057,
|
| 18 |
+
1.0
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-0.20040483418845204,
|
| 22 |
+
0.9260308650671458,
|
| 23 |
+
0.6881893789087474,
|
| 24 |
+
-0.3400484544283471,
|
| 25 |
+
0.06579394032953159,
|
| 26 |
+
0.004003331131509558,
|
| 27 |
+
0.771446548553906,
|
| 28 |
+
0.17299834959584776,
|
| 29 |
+
0.8224941837716736,
|
| 30 |
+
0.6196513047400859,
|
| 31 |
+
-0.3604178625374315,
|
| 32 |
+
-0.06267071413702419,
|
| 33 |
+
0.0037534824507240434,
|
| 34 |
+
0.7860054714056368
|
| 35 |
+
],
|
| 36 |
+
"min": [
|
| 37 |
+
-1.4863648414611816,
|
| 38 |
+
-0.2586335241794586,
|
| 39 |
+
-0.06850092858076096,
|
| 40 |
+
-2.2642147541046143,
|
| 41 |
+
-1.4876768589019775,
|
| 42 |
+
-3.0168392658233643,
|
| 43 |
+
-3.212450869184004e-17,
|
| 44 |
+
-1.4924354553222656,
|
| 45 |
+
-0.27809593081474304,
|
| 46 |
+
-0.18774886429309845,
|
| 47 |
+
-2.5354628562927246,
|
| 48 |
+
-3.0663280487060547,
|
| 49 |
+
-3.0486762523651123,
|
| 50 |
+
-3.212450869184004e-17
|
| 51 |
+
],
|
| 52 |
+
"q01": [
|
| 53 |
+
-1.051365569829941,
|
| 54 |
+
-3.52302449637288e-14,
|
| 55 |
+
1.6996893991849812e-16,
|
| 56 |
+
-1.5984010362625123,
|
| 57 |
+
-0.6003412520885467,
|
| 58 |
+
-1.6678147149085998,
|
| 59 |
+
0.0,
|
| 60 |
+
-0.4500492787361145,
|
| 61 |
+
-2.5859282299029243e-14,
|
| 62 |
+
1.194697284288627e-16,
|
| 63 |
+
-1.6398817586898804,
|
| 64 |
+
-1.263367258310318,
|
| 65 |
+
-1.760098042488098,
|
| 66 |
+
0.0
|
| 67 |
+
],
|
| 68 |
+
"q99": [
|
| 69 |
+
0.5431358617544174,
|
| 70 |
+
2.495765209197998,
|
| 71 |
+
2.492974226474762,
|
| 72 |
+
1.323737324476242,
|
| 73 |
+
1.2496635341644287,
|
| 74 |
+
1.7391636216640465,
|
| 75 |
+
1.0,
|
| 76 |
+
1.0814965963363647,
|
| 77 |
+
2.416655488014221,
|
| 78 |
+
2.346989154815674,
|
| 79 |
+
1.1415718960762022,
|
| 80 |
+
0.5208872479200363,
|
| 81 |
+
1.4889542925357817,
|
| 82 |
+
1.0
|
| 83 |
+
],
|
| 84 |
+
"std": [
|
| 85 |
+
0.34305506136703257,
|
| 86 |
+
0.8880398716756615,
|
| 87 |
+
0.7302413867018247,
|
| 88 |
+
0.6487680858145891,
|
| 89 |
+
0.2989095916390101,
|
| 90 |
+
0.584300843989697,
|
| 91 |
+
0.34316664624786114,
|
| 92 |
+
0.31989806135013626,
|
| 93 |
+
0.8736479432260295,
|
| 94 |
+
0.7135350385777451,
|
| 95 |
+
0.6027223159771133,
|
| 96 |
+
0.2836475966439172,
|
| 97 |
+
0.5368540820848867,
|
| 98 |
+
0.3406560080480477
|
| 99 |
+
],
|
| 100 |
+
"count": 1859602
|
| 101 |
+
},
|
| 102 |
+
"action": {
|
| 103 |
+
"max": [
|
| 104 |
+
[
|
| 105 |
+
0.15498490631580353,
|
| 106 |
+
0.20005442202091217,
|
| 107 |
+
0.20005667209625244,
|
| 108 |
+
0.19985514879226685,
|
| 109 |
+
0.1528162956237793,
|
| 110 |
+
0.2001188099384308,
|
| 111 |
+
0.7361559867858887,
|
| 112 |
+
0.15474265813827515,
|
| 113 |
+
0.1993194818496704,
|
| 114 |
+
0.20014739036560059,
|
| 115 |
+
0.18120431900024414,
|
| 116 |
+
0.17337381839752197,
|
| 117 |
+
0.20011717081069946,
|
| 118 |
+
0.4975297749042511
|
| 119 |
+
],
|
| 120 |
+
[
|
| 121 |
+
0.3098543882369995,
|
| 122 |
+
0.3882911205291748,
|
| 123 |
+
0.3993988037109375,
|
| 124 |
+
0.37138789892196655,
|
| 125 |
+
0.30559873580932617,
|
| 126 |
+
0.3999616503715515,
|
| 127 |
+
0.7361559867858887,
|
| 128 |
+
0.309272825717926,
|
| 129 |
+
0.3684011697769165,
|
| 130 |
+
0.40029096603393555,
|
| 131 |
+
0.36051416397094727,
|
| 132 |
+
0.3459423780441284,
|
| 133 |
+
0.39881736040115356,
|
| 134 |
+
0.4975297749042511
|
| 135 |
+
],
|
| 136 |
+
[
|
| 137 |
+
0.46472346782684326,
|
| 138 |
+
0.5428702235221863,
|
| 139 |
+
0.5929223299026489,
|
| 140 |
+
0.5528702735900879,
|
| 141 |
+
0.4583788216114044,
|
| 142 |
+
0.5914298295974731,
|
| 143 |
+
0.800000011920929,
|
| 144 |
+
0.4624479115009308,
|
| 145 |
+
0.5494232177734375,
|
| 146 |
+
0.6004343032836914,
|
| 147 |
+
0.539147675037384,
|
| 148 |
+
0.5179338455200195,
|
| 149 |
+
0.5909121632575989,
|
| 150 |
+
0.5006457567214966
|
| 151 |
+
],
|
| 152 |
+
[
|
| 153 |
+
0.6195164322853088,
|
| 154 |
+
0.7208306193351746,
|
| 155 |
+
0.7284860610961914,
|
| 156 |
+
0.7331912517547607,
|
| 157 |
+
0.6110378503799438,
|
| 158 |
+
0.7748094797134399,
|
| 159 |
+
0.800000011920929,
|
| 160 |
+
0.6139634847640991,
|
| 161 |
+
0.7279764413833618,
|
| 162 |
+
0.8005720376968384,
|
| 163 |
+
0.7136830687522888,
|
| 164 |
+
0.6876122951507568,
|
| 165 |
+
0.7716678380966187,
|
| 166 |
+
0.595525324344635
|
| 167 |
+
],
|
| 168 |
+
[
|
| 169 |
+
0.764305591583252,
|
| 170 |
+
0.8910004496574402,
|
| 171 |
+
0.9017477035522461,
|
| 172 |
+
0.9056982398033142,
|
| 173 |
+
0.7636865973472595,
|
| 174 |
+
0.9420505166053772,
|
| 175 |
+
0.800000011920929,
|
| 176 |
+
0.7645533084869385,
|
| 177 |
+
0.9014805555343628,
|
| 178 |
+
1.0007017850875854,
|
| 179 |
+
0.8882356286048889,
|
| 180 |
+
0.855940580368042,
|
| 181 |
+
0.9409557580947876,
|
| 182 |
+
0.6337910890579224
|
| 183 |
+
],
|
| 184 |
+
[
|
| 185 |
+
0.9164008498191833,
|
| 186 |
+
1.060915231704712,
|
| 187 |
+
1.0708266496658325,
|
| 188 |
+
1.076215386390686,
|
| 189 |
+
0.9149380326271057,
|
| 190 |
+
1.1029270887374878,
|
| 191 |
+
0.800000011920929,
|
| 192 |
+
0.9161303043365479,
|
| 193 |
+
1.0712734460830688,
|
| 194 |
+
1.200827956199646,
|
| 195 |
+
1.0608360767364502,
|
| 196 |
+
1.020771861076355,
|
| 197 |
+
1.0990257263183594,
|
| 198 |
+
0.7253433465957642
|
| 199 |
+
],
|
| 200 |
+
[
|
| 201 |
+
1.0687614679336548,
|
| 202 |
+
1.2189595699310303,
|
| 203 |
+
1.2328071594238281,
|
| 204 |
+
1.2352322340011597,
|
| 205 |
+
1.04792320728302,
|
| 206 |
+
1.250866413116455,
|
| 207 |
+
0.8189886808395386,
|
| 208 |
+
1.0687918663024902,
|
| 209 |
+
1.232945442199707,
|
| 210 |
+
1.4009488821029663,
|
| 211 |
+
1.2299710512161255,
|
| 212 |
+
1.1832053661346436,
|
| 213 |
+
1.2447912693023682,
|
| 214 |
+
0.8168955445289612
|
| 215 |
+
],
|
| 216 |
+
[
|
| 217 |
+
1.2193883657455444,
|
| 218 |
+
1.3759491443634033,
|
| 219 |
+
1.387863278388977,
|
| 220 |
+
1.3918373584747314,
|
| 221 |
+
1.1360324621200562,
|
| 222 |
+
1.4218342304229736,
|
| 223 |
+
0.9094943404197693,
|
| 224 |
+
1.2182191610336304,
|
| 225 |
+
1.3915128707885742,
|
| 226 |
+
1.6010628938674927,
|
| 227 |
+
1.3963547945022583,
|
| 228 |
+
1.3427485227584839,
|
| 229 |
+
1.3800389766693115,
|
| 230 |
+
0.908447802066803
|
| 231 |
+
],
|
| 232 |
+
[
|
| 233 |
+
1.355455756187439,
|
| 234 |
+
1.5183275938034058,
|
| 235 |
+
1.5341678857803345,
|
| 236 |
+
1.5329556465148926,
|
| 237 |
+
1.2271716594696045,
|
| 238 |
+
1.5852620601654053,
|
| 239 |
+
1.0,
|
| 240 |
+
1.3591952323913574,
|
| 241 |
+
1.5365383625030518,
|
| 242 |
+
1.8011744022369385,
|
| 243 |
+
1.5581185817718506,
|
| 244 |
+
1.4983609914779663,
|
| 245 |
+
1.5022748708724976,
|
| 246 |
+
1.0
|
| 247 |
+
],
|
| 248 |
+
[
|
| 249 |
+
1.4792304039001465,
|
| 250 |
+
1.6571649312973022,
|
| 251 |
+
1.6717768907546997,
|
| 252 |
+
1.6718776226043701,
|
| 253 |
+
1.2969082593917847,
|
| 254 |
+
1.748584270477295,
|
| 255 |
+
1.0,
|
| 256 |
+
1.438840627670288,
|
| 257 |
+
1.680770993232727,
|
| 258 |
+
2.001260757446289,
|
| 259 |
+
1.7163355350494385,
|
| 260 |
+
1.6504261493682861,
|
| 261 |
+
1.637952208518982,
|
| 262 |
+
1.0
|
| 263 |
+
],
|
| 264 |
+
[
|
| 265 |
+
1.59755277633667,
|
| 266 |
+
1.780563235282898,
|
| 267 |
+
1.7978901863098145,
|
| 268 |
+
1.7908905744552612,
|
| 269 |
+
1.3609228134155273,
|
| 270 |
+
1.9024004936218262,
|
| 271 |
+
1.0,
|
| 272 |
+
1.5139979124069214,
|
| 273 |
+
1.8205636739730835,
|
| 274 |
+
2.2013132572174072,
|
| 275 |
+
1.8687841892242432,
|
| 276 |
+
1.7970800399780273,
|
| 277 |
+
1.7705798149108887,
|
| 278 |
+
1.0
|
| 279 |
+
],
|
| 280 |
+
[
|
| 281 |
+
1.6876590251922607,
|
| 282 |
+
1.897180199623108,
|
| 283 |
+
1.9143023490905762,
|
| 284 |
+
1.9089956283569336,
|
| 285 |
+
1.4201512336730957,
|
| 286 |
+
2.056192398071289,
|
| 287 |
+
1.0,
|
| 288 |
+
1.5542269945144653,
|
| 289 |
+
1.9613847732543945,
|
| 290 |
+
2.399487257003784,
|
| 291 |
+
2.0168910026550293,
|
| 292 |
+
1.939436435699463,
|
| 293 |
+
1.8979809284210205,
|
| 294 |
+
1.0
|
| 295 |
+
],
|
| 296 |
+
[
|
| 297 |
+
1.7561901807785034,
|
| 298 |
+
1.9981712102890015,
|
| 299 |
+
2.017350435256958,
|
| 300 |
+
2.0107533931732178,
|
| 301 |
+
1.481030821800232,
|
| 302 |
+
2.198575973510742,
|
| 303 |
+
1.0,
|
| 304 |
+
1.5896430015563965,
|
| 305 |
+
2.101799964904785,
|
| 306 |
+
2.596306324005127,
|
| 307 |
+
2.1580772399902344,
|
| 308 |
+
2.0752532482147217,
|
| 309 |
+
2.013698101043701,
|
| 310 |
+
1.0
|
| 311 |
+
],
|
| 312 |
+
[
|
| 313 |
+
1.8167648315429688,
|
| 314 |
+
2.0911967754364014,
|
| 315 |
+
2.1412651538848877,
|
| 316 |
+
2.1323399543762207,
|
| 317 |
+
1.5314565896987915,
|
| 318 |
+
2.3408408164978027,
|
| 319 |
+
1.0,
|
| 320 |
+
1.605363368988037,
|
| 321 |
+
2.2302868366241455,
|
| 322 |
+
2.7773444652557373,
|
| 323 |
+
2.294142484664917,
|
| 324 |
+
2.206042528152466,
|
| 325 |
+
2.1297073364257812,
|
| 326 |
+
1.0
|
| 327 |
+
],
|
| 328 |
+
[
|
| 329 |
+
1.8602198362350464,
|
| 330 |
+
2.168449878692627,
|
| 331 |
+
2.2537410259246826,
|
| 332 |
+
2.2472739219665527,
|
| 333 |
+
1.6166343688964844,
|
| 334 |
+
2.469943046569824,
|
| 335 |
+
1.0,
|
| 336 |
+
1.6166977882385254,
|
| 337 |
+
2.3583338260650635,
|
| 338 |
+
2.952298402786255,
|
| 339 |
+
2.4221291542053223,
|
| 340 |
+
2.329159736633301,
|
| 341 |
+
2.2449960708618164,
|
| 342 |
+
1.0
|
| 343 |
+
],
|
| 344 |
+
[
|
| 345 |
+
1.8887031078338623,
|
| 346 |
+
2.241629123687744,
|
| 347 |
+
2.3643198013305664,
|
| 348 |
+
2.353733539581299,
|
| 349 |
+
1.684847116470337,
|
| 350 |
+
2.5986948013305664,
|
| 351 |
+
1.0,
|
| 352 |
+
1.6447105407714844,
|
| 353 |
+
2.472832202911377,
|
| 354 |
+
3.1138815879821777,
|
| 355 |
+
2.544224500656128,
|
| 356 |
+
2.4465250968933105,
|
| 357 |
+
2.3557143211364746,
|
| 358 |
+
1.0
|
| 359 |
+
]
|
| 360 |
+
],
|
| 361 |
+
"min": [
|
| 362 |
+
[
|
| 363 |
+
-0.15623462200164795,
|
| 364 |
+
-0.16764605045318604,
|
| 365 |
+
-0.16970443725585938,
|
| 366 |
+
-0.20000940561294556,
|
| 367 |
+
-0.15340250730514526,
|
| 368 |
+
-0.20000168681144714,
|
| 369 |
+
-0.37838685512542725,
|
| 370 |
+
-0.15502718091011047,
|
| 371 |
+
-0.20030677318572998,
|
| 372 |
+
-0.1721888780593872,
|
| 373 |
+
-0.18998387455940247,
|
| 374 |
+
-0.17636358737945557,
|
| 375 |
+
-0.20000112056732178,
|
| 376 |
+
-0.22537416219711304
|
| 377 |
+
],
|
| 378 |
+
[
|
| 379 |
+
-0.31191617250442505,
|
| 380 |
+
-0.3346027135848999,
|
| 381 |
+
-0.3386315107345581,
|
| 382 |
+
-0.4000183045864105,
|
| 383 |
+
-0.3058469295501709,
|
| 384 |
+
-0.3976632058620453,
|
| 385 |
+
-0.614814817905426,
|
| 386 |
+
-0.3095979392528534,
|
| 387 |
+
-0.38268542289733887,
|
| 388 |
+
-0.3433429002761841,
|
| 389 |
+
-0.3798891305923462,
|
| 390 |
+
-0.35257601737976074,
|
| 391 |
+
-0.3995015025138855,
|
| 392 |
+
-0.3294653594493866
|
| 393 |
+
],
|
| 394 |
+
[
|
| 395 |
+
-0.4649693965911865,
|
| 396 |
+
-0.5009051561355591,
|
| 397 |
+
-0.50676429271698,
|
| 398 |
+
-0.5988031029701233,
|
| 399 |
+
-0.458637535572052,
|
| 400 |
+
-0.5907891988754272,
|
| 401 |
+
-0.614814817905426,
|
| 402 |
+
-0.4638020694255829,
|
| 403 |
+
-0.48982203006744385,
|
| 404 |
+
-0.5141981840133667,
|
| 405 |
+
-0.5652948617935181,
|
| 406 |
+
-0.5271042585372925,
|
| 407 |
+
-0.5919855833053589,
|
| 408 |
+
-0.41561105847358704
|
| 409 |
+
],
|
| 410 |
+
[
|
| 411 |
+
-0.6162660121917725,
|
| 412 |
+
-0.6651163101196289,
|
| 413 |
+
-0.6723255515098572,
|
| 414 |
+
-0.7199233174324036,
|
| 415 |
+
-0.6113623380661011,
|
| 416 |
+
-0.7699707746505737,
|
| 417 |
+
-0.614814817905426,
|
| 418 |
+
-0.6179124116897583,
|
| 419 |
+
-0.6490402817726135,
|
| 420 |
+
-0.6819474697113037,
|
| 421 |
+
-0.7501269578933716,
|
| 422 |
+
-0.7011628150939941,
|
| 423 |
+
-0.776836633682251,
|
| 424 |
+
-0.5020262002944946
|
| 425 |
+
],
|
| 426 |
+
[
|
| 427 |
+
-0.7658684253692627,
|
| 428 |
+
-0.8280415534973145,
|
| 429 |
+
-0.83699631690979,
|
| 430 |
+
-0.8334474563598633,
|
| 431 |
+
-0.7640075087547302,
|
| 432 |
+
-0.9420039057731628,
|
| 433 |
+
-0.614814817905426,
|
| 434 |
+
-0.7617644667625427,
|
| 435 |
+
-0.8069799542427063,
|
| 436 |
+
-0.8491307497024536,
|
| 437 |
+
-0.9262538552284241,
|
| 438 |
+
-0.8718715906143188,
|
| 439 |
+
-0.9684793949127197,
|
| 440 |
+
-0.594243586063385
|
| 441 |
+
],
|
| 442 |
+
[
|
| 443 |
+
-0.9164783954620361,
|
| 444 |
+
-0.9874361753463745,
|
| 445 |
+
-0.9975383281707764,
|
| 446 |
+
-1.00400972366333,
|
| 447 |
+
-0.911322832107544,
|
| 448 |
+
-1.1168217658996582,
|
| 449 |
+
-0.7080556750297546,
|
| 450 |
+
-0.8916434645652771,
|
| 451 |
+
-0.9603351950645447,
|
| 452 |
+
-1.011122703552246,
|
| 453 |
+
-1.101320505142212,
|
| 454 |
+
-1.0417617559432983,
|
| 455 |
+
-1.1566747426986694,
|
| 456 |
+
-0.6864609718322754
|
| 457 |
+
],
|
| 458 |
+
[
|
| 459 |
+
-1.0691542625427246,
|
| 460 |
+
-1.1449098587036133,
|
| 461 |
+
-1.1576461791992188,
|
| 462 |
+
-1.1332952976226807,
|
| 463 |
+
-1.051412582397461,
|
| 464 |
+
-1.287815809249878,
|
| 465 |
+
-0.7865169048309326,
|
| 466 |
+
-0.9929096102714539,
|
| 467 |
+
-1.1108429431915283,
|
| 468 |
+
-1.1723419427871704,
|
| 469 |
+
-1.2636971473693848,
|
| 470 |
+
-1.2066856622695923,
|
| 471 |
+
-1.3440144062042236,
|
| 472 |
+
-0.7865169048309326
|
| 473 |
+
],
|
| 474 |
+
[
|
| 475 |
+
-1.2218137979507446,
|
| 476 |
+
-1.2974035739898682,
|
| 477 |
+
-1.3112123012542725,
|
| 478 |
+
-1.2611026763916016,
|
| 479 |
+
-1.1617908477783203,
|
| 480 |
+
-1.4546704292297363,
|
| 481 |
+
-0.898876428604126,
|
| 482 |
+
-1.0969961881637573,
|
| 483 |
+
-1.2596454620361328,
|
| 484 |
+
-1.3262594938278198,
|
| 485 |
+
-1.4245195388793945,
|
| 486 |
+
-1.3703924417495728,
|
| 487 |
+
-1.5263135433197021,
|
| 488 |
+
-0.898876428604126
|
| 489 |
+
],
|
| 490 |
+
[
|
| 491 |
+
-1.372441053390503,
|
| 492 |
+
-1.447338342666626,
|
| 493 |
+
-1.4640965461730957,
|
| 494 |
+
-1.4069215059280396,
|
| 495 |
+
-1.2578787803649902,
|
| 496 |
+
-1.6121726036071777,
|
| 497 |
+
-1.0,
|
| 498 |
+
-1.19899320602417,
|
| 499 |
+
-1.4018747806549072,
|
| 500 |
+
-1.479310154914856,
|
| 501 |
+
-1.5692541599273682,
|
| 502 |
+
-1.5275609493255615,
|
| 503 |
+
-1.7078077793121338,
|
| 504 |
+
-1.0
|
| 505 |
+
],
|
| 506 |
+
[
|
| 507 |
+
-1.5110177993774414,
|
| 508 |
+
-1.5908403396606445,
|
| 509 |
+
-1.608689546585083,
|
| 510 |
+
-1.54514479637146,
|
| 511 |
+
-1.3541831970214844,
|
| 512 |
+
-1.7634245157241821,
|
| 513 |
+
-1.0,
|
| 514 |
+
-1.293934941291809,
|
| 515 |
+
-1.5438759326934814,
|
| 516 |
+
-1.6229406595230103,
|
| 517 |
+
-1.7178936004638672,
|
| 518 |
+
-1.683074951171875,
|
| 519 |
+
-1.882439374923706,
|
| 520 |
+
-1.0
|
| 521 |
+
],
|
| 522 |
+
[
|
| 523 |
+
-1.6355321407318115,
|
| 524 |
+
-1.7311643362045288,
|
| 525 |
+
-1.7522717714309692,
|
| 526 |
+
-1.6814210414886475,
|
| 527 |
+
-1.446195363998413,
|
| 528 |
+
-1.9041634798049927,
|
| 529 |
+
-1.0,
|
| 530 |
+
-1.3676434755325317,
|
| 531 |
+
-1.6762027740478516,
|
| 532 |
+
-1.7657626867294312,
|
| 533 |
+
-1.871291160583496,
|
| 534 |
+
-1.8305044174194336,
|
| 535 |
+
-2.056593179702759,
|
| 536 |
+
-1.0
|
| 537 |
+
],
|
| 538 |
+
[
|
| 539 |
+
-1.7275934219360352,
|
| 540 |
+
-1.8636142015457153,
|
| 541 |
+
-1.885910153388977,
|
| 542 |
+
-1.8326873779296875,
|
| 543 |
+
-1.5357747077941895,
|
| 544 |
+
-2.0358989238739014,
|
| 545 |
+
-1.0,
|
| 546 |
+
-1.4295730590820312,
|
| 547 |
+
-1.808150053024292,
|
| 548 |
+
-1.8981581926345825,
|
| 549 |
+
-2.0156409740448,
|
| 550 |
+
-1.9758203029632568,
|
| 551 |
+
-2.221961736679077,
|
| 552 |
+
-1.0
|
| 553 |
+
],
|
| 554 |
+
[
|
| 555 |
+
-1.8188360929489136,
|
| 556 |
+
-1.992261290550232,
|
| 557 |
+
-2.018099784851074,
|
| 558 |
+
-1.9831218719482422,
|
| 559 |
+
-1.6140577793121338,
|
| 560 |
+
-2.1567585468292236,
|
| 561 |
+
-1.0,
|
| 562 |
+
-1.4801898002624512,
|
| 563 |
+
-1.9286596775054932,
|
| 564 |
+
-2.02775239944458,
|
| 565 |
+
-2.157339572906494,
|
| 566 |
+
-2.111522912979126,
|
| 567 |
+
-2.387108564376831,
|
| 568 |
+
-1.0
|
| 569 |
+
],
|
| 570 |
+
[
|
| 571 |
+
-1.8810598850250244,
|
| 572 |
+
-2.1116244792938232,
|
| 573 |
+
-2.1388092041015625,
|
| 574 |
+
-2.1139721870422363,
|
| 575 |
+
-1.6771425008773804,
|
| 576 |
+
-2.265713930130005,
|
| 577 |
+
-1.0,
|
| 578 |
+
-1.5542949438095093,
|
| 579 |
+
-2.0486526489257812,
|
| 580 |
+
-2.147879123687744,
|
| 581 |
+
-2.2884902954101562,
|
| 582 |
+
-2.244635820388794,
|
| 583 |
+
-2.542330026626587,
|
| 584 |
+
-1.0
|
| 585 |
+
],
|
| 586 |
+
[
|
| 587 |
+
-1.936772346496582,
|
| 588 |
+
-2.2265307903289795,
|
| 589 |
+
-2.257511854171753,
|
| 590 |
+
-2.2445836067199707,
|
| 591 |
+
-1.740214467048645,
|
| 592 |
+
-2.3640151023864746,
|
| 593 |
+
-1.0,
|
| 594 |
+
-1.6143319606781006,
|
| 595 |
+
-2.1553502082824707,
|
| 596 |
+
-2.261636734008789,
|
| 597 |
+
-2.416691780090332,
|
| 598 |
+
-2.3666346073150635,
|
| 599 |
+
-2.6961402893066406,
|
| 600 |
+
-1.0
|
| 601 |
+
],
|
| 602 |
+
[
|
| 603 |
+
-1.9831359386444092,
|
| 604 |
+
-2.3307759761810303,
|
| 605 |
+
-2.36329984664917,
|
| 606 |
+
-2.3512368202209473,
|
| 607 |
+
-1.7914525270462036,
|
| 608 |
+
-2.4492745399475098,
|
| 609 |
+
-1.0,
|
| 610 |
+
-1.6693108081817627,
|
| 611 |
+
-2.261469841003418,
|
| 612 |
+
-2.36698317527771,
|
| 613 |
+
-2.53256893157959,
|
| 614 |
+
-2.4855473041534424,
|
| 615 |
+
-2.839830160140991,
|
| 616 |
+
-1.0
|
| 617 |
+
]
|
| 618 |
+
],
|
| 619 |
+
"count": 1807102
|
| 620 |
+
}
|
| 621 |
+
}
|
| 622 |
+
}
|
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<action_end>": 151675,
|
| 6 |
+
"<action_pad>": 151673,
|
| 7 |
+
"<action_start>": 151674,
|
| 8 |
+
"<action_video>": 151669,
|
| 9 |
+
"<box2d_end>": 151679,
|
| 10 |
+
"<box2d_start>": 151678,
|
| 11 |
+
"<future_video_pad>": 151670,
|
| 12 |
+
"<future_vision_end>": 151672,
|
| 13 |
+
"<future_vision_start>": 151671,
|
| 14 |
+
"<ignore_pad>": 151688,
|
| 15 |
+
"<point2d_end>": 151681,
|
| 16 |
+
"<point2d_start>": 151680,
|
| 17 |
+
"<ref_end>": 151683,
|
| 18 |
+
"<ref_keypoint_end>": 151685,
|
| 19 |
+
"<ref_keypoint_start>": 151684,
|
| 20 |
+
"<ref_start>": 151682,
|
| 21 |
+
"<think>": 151667,
|
| 22 |
+
"<think_end>": 151677,
|
| 23 |
+
"<think_start>": 151676,
|
| 24 |
+
"<tool_call>": 151657,
|
| 25 |
+
"<tool_response>": 151665,
|
| 26 |
+
"<traj2d_end>": 151687,
|
| 27 |
+
"<traj2d_start>": 151686,
|
| 28 |
+
"<|box_end|>": 151649,
|
| 29 |
+
"<|box_start|>": 151648,
|
| 30 |
+
"<|endoftext|>": 151643,
|
| 31 |
+
"<|file_sep|>": 151664,
|
| 32 |
+
"<|fim_middle|>": 151660,
|
| 33 |
+
"<|fim_pad|>": 151662,
|
| 34 |
+
"<|fim_prefix|>": 151659,
|
| 35 |
+
"<|fim_suffix|>": 151661,
|
| 36 |
+
"<|im_end|>": 151645,
|
| 37 |
+
"<|im_start|>": 151644,
|
| 38 |
+
"<|image_pad|>": 151655,
|
| 39 |
+
"<|object_ref_end|>": 151647,
|
| 40 |
+
"<|object_ref_start|>": 151646,
|
| 41 |
+
"<|quad_end|>": 151651,
|
| 42 |
+
"<|quad_start|>": 151650,
|
| 43 |
+
"<|repo_name|>": 151663,
|
| 44 |
+
"<|video_pad|>": 151656,
|
| 45 |
+
"<|vision_end|>": 151653,
|
| 46 |
+
"<|vision_pad|>": 151654,
|
| 47 |
+
"<|vision_start|>": 151652
|
| 48 |
+
}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b7a88bc82340dd4205b97b9c287df826cf386b31ac9ecd9e648073d940355e1
|
| 3 |
+
size 11426476
|
|
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<IMG_CONTEXT>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "<img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "</img>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<box>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</box>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<quad>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</quad>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<ref>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</ref>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<interval>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "</interval>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
}
|
| 302 |
+
},
|
| 303 |
+
"additional_special_tokens": [
|
| 304 |
+
"<|im_start|>",
|
| 305 |
+
"<|im_end|>",
|
| 306 |
+
"<|object_ref_start|>",
|
| 307 |
+
"<|object_ref_end|>",
|
| 308 |
+
"<|box_start|>",
|
| 309 |
+
"<|box_end|>",
|
| 310 |
+
"<|quad_start|>",
|
| 311 |
+
"<|quad_end|>",
|
| 312 |
+
"<|vision_start|>",
|
| 313 |
+
"<|vision_end|>",
|
| 314 |
+
"<|vision_pad|>",
|
| 315 |
+
"<|image_pad|>",
|
| 316 |
+
"<|video_pad|>",
|
| 317 |
+
"<IMG_CONTEXT>",
|
| 318 |
+
"<img>",
|
| 319 |
+
"</img>",
|
| 320 |
+
"<box>",
|
| 321 |
+
"</box>",
|
| 322 |
+
"<quad>",
|
| 323 |
+
"</quad>",
|
| 324 |
+
"<ref>",
|
| 325 |
+
"</ref>",
|
| 326 |
+
"<interval>",
|
| 327 |
+
"</interval>"
|
| 328 |
+
],
|
| 329 |
+
"bos_token": null,
|
| 330 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 331 |
+
"clean_up_tokenization_spaces": false,
|
| 332 |
+
"eos_token": "<|im_end|>",
|
| 333 |
+
"errors": "replace",
|
| 334 |
+
"extra_special_tokens": {},
|
| 335 |
+
"model_max_length": 16384,
|
| 336 |
+
"pad_token": "<|endoftext|>",
|
| 337 |
+
"split_special_tokens": false,
|
| 338 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 339 |
+
"unk_token": null
|
| 340 |
+
}
|