Hugging Face's logo

limxdynamics
/
FluxVLAEngine

Safetensors
Model card Files
xet
 Community
8

Add RoboTwin models

#8
by ShenBW - opened
base: refs/heads/main
←
from: refs/pr/8
Discussion Files changed
+1225867
-0
This view is limited to 50 files because it contains too many changes. See the raw diff here.
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/checkpoints/step-047464-epoch-08-loss=0.0888.safetensors +3 -0
  3. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/config.json +1153 -0
  4. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/config.yaml +994 -0
  5. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/dataset_statistics.json +156 -0
  6. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/added_tokens.json +28 -0
  7. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/chat_template.jinja +120 -0
  8. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/merges.txt +0 -0
  9. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/special_tokens_map.json +31 -0
  10. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/tokenizer.json +3 -0
  11. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/tokenizer_config.json +239 -0
  12. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/vocab.json +0 -0
  13. cosmos3_nano_robotwin_all_data_full_finetune_bs1024/vlm_backbone_config.json +100 -0
  14. dit4dit_robotwin_all_data_full_finetune_bs256/checkpoints/step-129501-epoch-03-loss=0.1024.safetensors +3 -0
  15. dit4dit_robotwin_all_data_full_finetune_bs256/config.json +549 -0
  16. dit4dit_robotwin_all_data_full_finetune_bs256/config.yaml +459 -0
  17. dit4dit_robotwin_all_data_full_finetune_bs256/dataset_statistics.json +202 -0
  18. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/added_tokens.json +24 -0
  19. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/chat_template.jinja +7 -0
  20. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/merges.txt +0 -0
  21. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/special_tokens_map.json +31 -0
  22. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json +3 -0
  23. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer_config.json +207 -0
  24. dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/vocab.json +0 -0
  25. fastwam_robotwin_all_data_full_finetune_bs256/checkpoints/step-118655-epoch-05-loss=0.0985.safetensors +3 -0
  26. fastwam_robotwin_all_data_full_finetune_bs256/config.json +538 -0
  27. fastwam_robotwin_all_data_full_finetune_bs256/config.yaml +456 -0
  28. fastwam_robotwin_all_data_full_finetune_bs256/dataset_statistics.json +156 -0
  29. fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/special_tokens_map.json +308 -0
  30. fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/spiece.model +3 -0
  31. fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json +3 -0
  32. fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer_config.json +2748 -0
  33. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/checkpoints/step-142386-epoch-03-loss=0.0027.safetensors +3 -0
  34. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/config.json +419 -0
  35. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/config.yaml +326 -0
  36. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/dataset_statistics.json +156 -0
  37. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/added_tokens.json +39 -0
  38. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/chat_template.json +3 -0
  39. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/merges.txt +0 -0
  40. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/special_tokens_map.json +42 -0
  41. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/tokenizer_config.json +344 -0
  42. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/vocab.json +0 -0
  43. gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/vlm_backbone_config.json +115 -0
  44. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/checkpoints/step-118655-epoch-05-loss=0.0067.safetensors +3 -0
  45. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/config.json +1235 -0
  46. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/config.yaml +1045 -0
  47. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/dataset_statistics.json +156 -0
  48. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/added_tokens.json +39 -0
  49. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/chat_template.jinja +85 -0
  50. gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/merges.txt +0 -0
.gitattributes CHANGED
@@ -70,3 +70,9 @@ cosmos3_nano_robodojo_full_finetune_bs2048/tokenizer/tokenizer.json filter=lfs d
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
 
 
 
 
 
 
 
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
73
+ pi0_paligemma_robotwin_all_data_full_finetune_bs128/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ pi05_paligemma_robotwin_all_data_full_finetune_bs128/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/checkpoints/step-047464-epoch-08-loss=0.0888.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727e238c60577296709acf5981472dfea5b5b9efa975ddf3e542788806d30ede
3
+ size 63511447112
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/config.json ADDED
@@ -0,0 +1,1153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_ACTION_DIM": 14,
3
+ "_ACTION_HORIZON": 32,
4
+ "_ACTION_LR": 0.00025,
5
+ "_ACTION_PROMPT_METADATA": {
6
+ "append_viewpoint": false,
7
+ "conditioning_fps": 15.0,
8
+ "frame_window_size": 33,
9
+ "video_height": 384,
10
+ "video_width": 256
11
+ },
12
+ "_BASE_LR": 5e-05,
13
+ "_CFG_DROPOUT_RATE": 0.1,
14
+ "_CKPT_ROOT": "./checkpoints",
15
+ "_CONDITIONING_FPS": 15.0,
16
+ "_COSMOS3_NANO_CKPT": "./checkpoints/Cosmos3-Nano",
17
+ "_COSMOS3_NANO_NAME_MAPPING": {
18
+ ".self_attn.k_norm.": ".self_attn.norm_k.",
19
+ ".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
20
+ ".self_attn.k_proj.": ".self_attn.to_k.",
21
+ ".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
22
+ ".self_attn.o_proj.": ".self_attn.to_out.",
23
+ ".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
24
+ ".self_attn.q_norm.": ".self_attn.norm_q.",
25
+ ".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
26
+ ".self_attn.q_proj.": ".self_attn.to_q.",
27
+ ".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
28
+ ".self_attn.v_proj.": ".self_attn.to_v.",
29
+ ".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
30
+ "action_in_proj.": "action_proj_in.",
31
+ "action_modality_embed": "action_modality_embed",
32
+ "action_out_proj.": "action_proj_out.",
33
+ "time_embedder.mlp.0.": "time_embedder.linear_1.",
34
+ "time_embedder.mlp.2.": "time_embedder.linear_2.",
35
+ "vision_in_proj.projector.": "proj_in.",
36
+ "vision_out_proj.projector.": "proj_out.",
37
+ "vlm_backbone.lm_head.weight": "lm_head.weight",
38
+ "vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
39
+ "vlm_backbone.model.language_model.layers.": "layers.",
40
+ "vlm_backbone.model.language_model.norm.weight": "norm.weight",
41
+ "vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
42
+ "vlm_backbone.model.visual.blocks.": "blocks.",
43
+ "vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
44
+ "vlm_backbone.model.visual.merger.": "merger.",
45
+ "vlm_backbone.model.visual.patch_embed.": "patch_embed.",
46
+ "vlm_backbone.model.visual.pos_embed.": "pos_embed."
47
+ },
48
+ "_COSMOS3_NANO_SPECIAL_TOKENS": {
49
+ "end_of_generation": 151653,
50
+ "eos_token_id": 151645,
51
+ "start_of_generation": 151652
52
+ },
53
+ "_COSMOS3_NANO_TOKENIZER": {
54
+ "model_max_length": 4096,
55
+ "model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
56
+ "padding_side": "right",
57
+ "trust_remote_code": true,
58
+ "type": "PretrainedTokenizer"
59
+ },
60
+ "_COSMOS3_NANO_TRANSFORMER": "./checkpoints/Cosmos3-Nano/transformer",
61
+ "_COSMOS3_NANO_VISION_ENCODER": "./checkpoints/Cosmos3-Nano/vision_encoder",
62
+ "_COSMOS3_NANO_VLM_CONFIG": {
63
+ "image_token_id": 151655,
64
+ "model_type": "qwen3_vl",
65
+ "text_config": {
66
+ "attention_bias": false,
67
+ "attention_dropout": 0.0,
68
+ "bos_token_id": 151643,
69
+ "eos_token_id": 151645,
70
+ "head_dim": 128,
71
+ "hidden_act": "silu",
72
+ "hidden_size": 4096,
73
+ "intermediate_size": 12288,
74
+ "layer_types": [
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention",
107
+ "full_attention",
108
+ "full_attention",
109
+ "full_attention",
110
+ "full_attention"
111
+ ],
112
+ "max_position_embeddings": 262144,
113
+ "model_type": "qwen3_vl_text",
114
+ "num_attention_heads": 32,
115
+ "num_hidden_layers": 36,
116
+ "num_key_value_heads": 8,
117
+ "pad_token_id": 0,
118
+ "rms_norm_eps": 1e-06,
119
+ "rope_scaling": {
120
+ "mrope_interleaved": true,
121
+ "mrope_section": [
122
+ 24,
123
+ 20,
124
+ 20
125
+ ],
126
+ "rope_type": "default"
127
+ },
128
+ "rope_theta": 5000000,
129
+ "tie_word_embeddings": false,
130
+ "vocab_size": 151936
131
+ },
132
+ "tie_word_embeddings": false,
133
+ "video_token_id": 151656,
134
+ "vision_config": {
135
+ "deepstack_visual_indexes": [
136
+ 8,
137
+ 16,
138
+ 24
139
+ ],
140
+ "depth": 27,
141
+ "hidden_act": "gelu_pytorch_tanh",
142
+ "hidden_size": 1152,
143
+ "in_channels": 3,
144
+ "initializer_range": 0.02,
145
+ "intermediate_size": 4304,
146
+ "model_type": "qwen3_vl",
147
+ "num_heads": 16,
148
+ "num_position_embeddings": 2304,
149
+ "out_hidden_size": 4096,
150
+ "patch_size": 16,
151
+ "spatial_merge_size": 2,
152
+ "temporal_patch_size": 2
153
+ },
154
+ "vision_end_token_id": 151653,
155
+ "vision_start_token_id": 151652,
156
+ "vocab_size": 151936
157
+ },
158
+ "_FRAME_WINDOW_SIZE": 33,
159
+ "_GRAD_ACCUMULATION_STEPS": 1,
160
+ "_IMAGE_HEIGHT": 256,
161
+ "_IMAGE_WIDTH": 256,
162
+ "_MAX_ACTION_DIM": 64,
163
+ "_MAX_EPOCHS": 8,
164
+ "_MAX_STATE_DIM": 64,
165
+ "_MAX_STEPS": null,
166
+ "_PER_DEVICE_BATCH_SIZE": 16,
167
+ "_PREPEND_STATE_TO_ACTION": true,
168
+ "_ROBOTWIN_DATA_ROOTS": [
169
+ "./datasets/robotwin_clean_lerobotv2.1",
170
+ "./datasets/robotwin_randomized_lerobotv2.1"
171
+ ],
172
+ "_ROBOTWIN_EMBODIMENT_ID": 21,
173
+ "_ROBOTWIN_TASK_LIST": [
174
+ "adjust_bottle",
175
+ "beat_block_hammer",
176
+ "blocks_ranking_rgb",
177
+ "blocks_ranking_size",
178
+ "click_alarmclock",
179
+ "click_bell",
180
+ "dump_bin_bigbin",
181
+ "grab_roller",
182
+ "handover_block",
183
+ "handover_mic",
184
+ "hanging_mug",
185
+ "lift_pot",
186
+ "move_can_pot",
187
+ "move_pillbottle_pad",
188
+ "move_playingcard_away",
189
+ "move_stapler_pad",
190
+ "open_laptop",
191
+ "open_microwave",
192
+ "pick_diverse_bottles",
193
+ "pick_dual_bottles",
194
+ "place_a2b_left",
195
+ "place_a2b_right",
196
+ "place_bread_basket",
197
+ "place_bread_skillet",
198
+ "place_burger_fries",
199
+ "place_can_basket",
200
+ "place_cans_plasticbox",
201
+ "place_container_plate",
202
+ "place_dual_shoes",
203
+ "place_empty_cup",
204
+ "place_fan",
205
+ "place_mouse_pad",
206
+ "place_object_basket",
207
+ "place_object_scale",
208
+ "place_object_stand",
209
+ "place_phone_stand",
210
+ "place_shoe",
211
+ "press_stapler",
212
+ "put_bottles_dustbin",
213
+ "put_object_cabinet",
214
+ "rotate_qrcode",
215
+ "scan_object",
216
+ "shake_bottle",
217
+ "shake_bottle_horizontally",
218
+ "stack_blocks_three",
219
+ "stack_blocks_two",
220
+ "stack_bowls_three",
221
+ "stack_bowls_two",
222
+ "stamp_seal",
223
+ "turn_switch"
224
+ ],
225
+ "_SAVE_EPOCH_INTERVAL": 1,
226
+ "_SAVE_ITER_INTERVAL": 500,
227
+ "_STATISTIC_NAME": "robotwin_all",
228
+ "_TRANSFORMS": [
229
+ {
230
+ "embodiment_id": 21,
231
+ "name_mappings": {
232
+ "actions": [
233
+ "actions"
234
+ ],
235
+ "observation.state": [
236
+ "states"
237
+ ]
238
+ },
239
+ "parquet_keys": [
240
+ "observation.state",
241
+ "timestamp",
242
+ "actions",
243
+ "info",
244
+ "stats",
245
+ "action_masks"
246
+ ],
247
+ "type": "ProcessParquetInputs",
248
+ "video_keys": [
249
+ "observation.images.cam_high",
250
+ "observation.images.cam_left_wrist",
251
+ "observation.images.cam_right_wrist"
252
+ ]
253
+ },
254
+ {
255
+ "height": 256,
256
+ "type": "ResizeImages",
257
+ "width": 256
258
+ },
259
+ {
260
+ "brightness_range": [
261
+ 0.7,
262
+ 1.3
263
+ ],
264
+ "contrast_range": [
265
+ 0.6,
266
+ 1.4
267
+ ],
268
+ "crop_ratio": [
269
+ 1.0,
270
+ 1.0
271
+ ],
272
+ "crop_scale": [
273
+ 0.95,
274
+ 0.95
275
+ ],
276
+ "hue_delta": 0.08,
277
+ "prob": 1.0,
278
+ "rotation_range": 0.0,
279
+ "saturation_range": [
280
+ 0.5,
281
+ 1.5
282
+ ],
283
+ "type": "AugVideo"
284
+ },
285
+ {
286
+ "action_metadata": {
287
+ "append_viewpoint": false,
288
+ "conditioning_fps": 15.0,
289
+ "frame_window_size": 33,
290
+ "video_height": 384,
291
+ "video_width": 256
292
+ },
293
+ "cfg_dropout_rate": 0.1,
294
+ "max_len": 512,
295
+ "tokenizer": {
296
+ "model_max_length": 4096,
297
+ "model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
298
+ "padding_side": "right",
299
+ "trust_remote_code": true,
300
+ "type": "PretrainedTokenizer"
301
+ },
302
+ "type": "ProcessCosmos3Prompt"
303
+ },
304
+ {
305
+ "type": "SimpleNormalizeImages"
306
+ },
307
+ {
308
+ "action_dim": 64,
309
+ "action_key": "action",
310
+ "norm_type": "mean_std",
311
+ "state_dim": 64,
312
+ "state_key": "proprio",
313
+ "type": "NormalizeStatesAndActions"
314
+ },
315
+ {
316
+ "conditioning_fps": 15.0,
317
+ "frame_window_size": 33,
318
+ "mode": "wam",
319
+ "prepend_state_to_action": true,
320
+ "raw_action_dim": 14,
321
+ "type": "BuildCosmos3Sequence"
322
+ },
323
+ {
324
+ "bottom_height_ratio": 0.5,
325
+ "bottom_views": [
326
+ 1,
327
+ 2
328
+ ],
329
+ "frame_window_size": 33,
330
+ "num_views": 3,
331
+ "tile_direction": "top_bottom_pair",
332
+ "top_view": 0,
333
+ "type": "PrepareVideo"
334
+ }
335
+ ],
336
+ "_VIDEO_HEIGHT": 384,
337
+ "_VIDEO_WIDTH": 256,
338
+ "_WAN22_VAE_PATH": "./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
339
+ "eval": {
340
+ "manager": {
341
+ "launch_delay": 0.5,
342
+ "master_port_base": 29690,
343
+ "max_tasks_per_gpu": 1,
344
+ "monitor_interval": 5,
345
+ "num_gpus": 8,
346
+ "status_interval": 30
347
+ },
348
+ "runner": {
349
+ "dataset": {
350
+ "embodiment_id": 21,
351
+ "extra_tensor_keys": [
352
+ "conditioning_fps",
353
+ "prepend_state_to_action"
354
+ ],
355
+ "img_keys": [
356
+ "cam_high",
357
+ "cam_left_wrist",
358
+ "cam_right_wrist"
359
+ ],
360
+ "inject_model_path": false,
361
+ "transforms": [
362
+ {
363
+ "conditioning_fps": 15.0,
364
+ "prepend_state_to_action": true,
365
+ "type": "SetCosmos3ActionMetadata"
366
+ },
367
+ {
368
+ "action_metadata": {
369
+ "append_viewpoint": false,
370
+ "conditioning_fps": 15.0,
371
+ "frame_window_size": 33,
372
+ "video_height": 384,
373
+ "video_width": 256
374
+ },
375
+ "cfg_dropout_rate": 0.0,
376
+ "max_len": 512,
377
+ "output_attention_mask_key": "lang_masks",
378
+ "output_key": "lang_tokens",
379
+ "tokenizer": {
380
+ "model_max_length": 4096,
381
+ "model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
382
+ "padding_side": "right",
383
+ "trust_remote_code": true,
384
+ "type": "PretrainedTokenizer"
385
+ },
386
+ "type": "ProcessCosmos3Prompt"
387
+ },
388
+ {
389
+ "height": 256,
390
+ "type": "ResizeImages",
391
+ "width": 256
392
+ },
393
+ {
394
+ "type": "SimpleNormalizeImages"
395
+ },
396
+ {
397
+ "action_dim": 64,
398
+ "action_key": "action",
399
+ "norm_type": "mean_std",
400
+ "state_dim": 64,
401
+ "state_key": "proprio",
402
+ "type": "NormalizeStatesAndActions"
403
+ },
404
+ {
405
+ "bottom_height_ratio": 0.5,
406
+ "bottom_views": [
407
+ 1,
408
+ 2
409
+ ],
410
+ "frame_window_size": 1,
411
+ "num_views": 3,
412
+ "tile_direction": "top_bottom_pair",
413
+ "top_view": 0,
414
+ "type": "PrepareVideo"
415
+ }
416
+ ],
417
+ "type": "PrivateInferenceDataset"
418
+ },
419
+ "denormalize_action": {
420
+ "action_dim": 14,
421
+ "norm_type": "mean_std",
422
+ "type": "DenormalizePrivateAction"
423
+ },
424
+ "enable_model_dtype_cast": true,
425
+ "eval_chunk_size": 24,
426
+ "instruction_type": "unseen",
427
+ "mixed_precision_dtype": "bf16",
428
+ "model_family": "cosmos3",
429
+ "num_trials_per_task": 100,
430
+ "save_video": false,
431
+ "seed": 7,
432
+ "task_list": [
433
+ "adjust_bottle",
434
+ "beat_block_hammer",
435
+ "blocks_ranking_rgb",
436
+ "blocks_ranking_size",
437
+ "click_alarmclock",
438
+ "click_bell",
439
+ "dump_bin_bigbin",
440
+ "grab_roller",
441
+ "handover_block",
442
+ "handover_mic",
443
+ "hanging_mug",
444
+ "lift_pot",
445
+ "move_can_pot",
446
+ "move_pillbottle_pad",
447
+ "move_playingcard_away",
448
+ "move_stapler_pad",
449
+ "open_laptop",
450
+ "open_microwave",
451
+ "pick_diverse_bottles",
452
+ "pick_dual_bottles",
453
+ "place_a2b_left",
454
+ "place_a2b_right",
455
+ "place_bread_basket",
456
+ "place_bread_skillet",
457
+ "place_burger_fries",
458
+ "place_can_basket",
459
+ "place_cans_plasticbox",
460
+ "place_container_plate",
461
+ "place_dual_shoes",
462
+ "place_empty_cup",
463
+ "place_fan",
464
+ "place_mouse_pad",
465
+ "place_object_basket",
466
+ "place_object_scale",
467
+ "place_object_stand",
468
+ "place_phone_stand",
469
+ "place_shoe",
470
+ "press_stapler",
471
+ "put_bottles_dustbin",
472
+ "put_object_cabinet",
473
+ "rotate_qrcode",
474
+ "scan_object",
475
+ "shake_bottle",
476
+ "shake_bottle_horizontally",
477
+ "stack_blocks_three",
478
+ "stack_blocks_two",
479
+ "stack_bowls_three",
480
+ "stack_bowls_two",
481
+ "stamp_seal",
482
+ "turn_switch"
483
+ ],
484
+ "task_suite_name": [
485
+ "clean",
486
+ "random"
487
+ ],
488
+ "type": "RobotwinEvalRunner",
489
+ "unnorm_key": "robotwin_all"
490
+ }
491
+ },
492
+ "inference_model": {
493
+ "action_horizon": 32,
494
+ "action_in_proj": {
495
+ "input_size": 64,
496
+ "num_domains": 32,
497
+ "output_size": 4096,
498
+ "type": "DomainAwareLinear"
499
+ },
500
+ "action_out_proj": {
501
+ "input_size": 4096,
502
+ "num_domains": 32,
503
+ "output_size": 64,
504
+ "type": "DomainAwareLinear"
505
+ },
506
+ "base_fps": 24.0,
507
+ "enable_fps_modulation": true,
508
+ "enable_vision_loss": true,
509
+ "freeze_non_moe_vlm_backbone": true,
510
+ "freeze_vlm_backbone": false,
511
+ "latent_patch_size": 2,
512
+ "max_action_dim": 64,
513
+ "name_mapping": {
514
+ ".self_attn.k_norm.": ".self_attn.norm_k.",
515
+ ".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
516
+ ".self_attn.k_proj.": ".self_attn.to_k.",
517
+ ".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
518
+ ".self_attn.o_proj.": ".self_attn.to_out.",
519
+ ".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
520
+ ".self_attn.q_norm.": ".self_attn.norm_q.",
521
+ ".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
522
+ ".self_attn.q_proj.": ".self_attn.to_q.",
523
+ ".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
524
+ ".self_attn.v_proj.": ".self_attn.to_v.",
525
+ ".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
526
+ "action_in_proj.": "action_proj_in.",
527
+ "action_modality_embed": "action_modality_embed",
528
+ "action_out_proj.": "action_proj_out.",
529
+ "time_embedder.mlp.0.": "time_embedder.linear_1.",
530
+ "time_embedder.mlp.2.": "time_embedder.linear_2.",
531
+ "vision_in_proj.projector.": "proj_in.",
532
+ "vision_out_proj.projector.": "proj_out.",
533
+ "vlm_backbone.lm_head.weight": "lm_head.weight",
534
+ "vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
535
+ "vlm_backbone.model.language_model.layers.": "layers.",
536
+ "vlm_backbone.model.language_model.norm.weight": "norm.weight",
537
+ "vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
538
+ "vlm_backbone.model.visual.blocks.": "blocks.",
539
+ "vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
540
+ "vlm_backbone.model.visual.merger.": "merger.",
541
+ "vlm_backbone.model.visual.patch_embed.": "patch_embed.",
542
+ "vlm_backbone.model.visual.pos_embed.": "pos_embed."
543
+ },
544
+ "num_embodiment_domains": 32,
545
+ "ori_action_dim": 14,
546
+ "packed_attention_backend": "flash2",
547
+ "position_embedding_type": "unified_3d_mrope",
548
+ "pretrained_name_or_path": "./checkpoints/Cosmos3-Nano/transformer",
549
+ "rectified_flow_inference_config": {
550
+ "num_steps": 30,
551
+ "num_train_timesteps": 1000,
552
+ "scheduler_type": "unipc",
553
+ "shift": 10.0,
554
+ "use_dynamic_shifting": false,
555
+ "use_karras_sigmas": false
556
+ },
557
+ "rectified_flow_training_config": {
558
+ "action_loss_weight": 10.0,
559
+ "high_sigma_ratio": 0.05,
560
+ "high_sigma_timesteps_max": 1000,
561
+ "high_sigma_timesteps_min": 995,
562
+ "independent_action_schedule": false,
563
+ "normalize_loss_by_active": false,
564
+ "shift": {
565
+ "256": 3,
566
+ "480": 5,
567
+ "720": 10
568
+ },
569
+ "shift_action": null,
570
+ "train_time_action_distribution": "logitnormal",
571
+ "train_time_image_distribution": "logitnormal",
572
+ "train_time_video_distribution": "waver",
573
+ "train_time_weight": "uniform",
574
+ "use_discrete_rf": false,
575
+ "use_dynamic_shift": false,
576
+ "use_high_sigma_strategy": false,
577
+ "use_high_sigma_strategy_action": false,
578
+ "vision_loss_weight": 1.0
579
+ },
580
+ "reinitialize_action_policy": true,
581
+ "special_tokens": {
582
+ "end_of_generation": 151653,
583
+ "eos_token_id": 151645,
584
+ "start_of_generation": 151652
585
+ },
586
+ "timestep_scale": 0.001,
587
+ "type": "Cosmos3FlowMatching",
588
+ "unified_3d_mrope_reset_spatial_ids": true,
589
+ "unified_3d_mrope_temporal_modality_margin": 15000,
590
+ "vision_in_proj": {
591
+ "in_dim": 192,
592
+ "out_dim": 4096,
593
+ "type": "LinearProjector"
594
+ },
595
+ "vision_latent_dim": 48,
596
+ "vision_out_proj": {
597
+ "in_dim": 4096,
598
+ "out_dim": 192,
599
+ "type": "LinearProjector"
600
+ },
601
+ "vision_vae": {
602
+ "encode_exact_durations": [
603
+ 33
604
+ ],
605
+ "pretrained_name_or_path": null,
606
+ "type": "Cosmos3Wan22VAE"
607
+ },
608
+ "vlm_backbone": {
609
+ "include_visual": false,
610
+ "skip_init_weights": true,
611
+ "type": "Cosmos3MoTBackbone",
612
+ "vision_encoder_path": "./checkpoints/Cosmos3-Nano/vision_encoder",
613
+ "vlm_config": {
614
+ "image_token_id": 151655,
615
+ "model_type": "qwen3_vl",
616
+ "text_config": {
617
+ "attention_bias": false,
618
+ "attention_dropout": 0.0,
619
+ "bos_token_id": 151643,
620
+ "eos_token_id": 151645,
621
+ "head_dim": 128,
622
+ "hidden_act": "silu",
623
+ "hidden_size": 4096,
624
+ "intermediate_size": 12288,
625
+ "layer_types": [
626
+ "full_attention",
627
+ "full_attention",
628
+ "full_attention",
629
+ "full_attention",
630
+ "full_attention",
631
+ "full_attention",
632
+ "full_attention",
633
+ "full_attention",
634
+ "full_attention",
635
+ "full_attention",
636
+ "full_attention",
637
+ "full_attention",
638
+ "full_attention",
639
+ "full_attention",
640
+ "full_attention",
641
+ "full_attention",
642
+ "full_attention",
643
+ "full_attention",
644
+ "full_attention",
645
+ "full_attention",
646
+ "full_attention",
647
+ "full_attention",
648
+ "full_attention",
649
+ "full_attention",
650
+ "full_attention",
651
+ "full_attention",
652
+ "full_attention",
653
+ "full_attention",
654
+ "full_attention",
655
+ "full_attention",
656
+ "full_attention",
657
+ "full_attention",
658
+ "full_attention",
659
+ "full_attention",
660
+ "full_attention",
661
+ "full_attention"
662
+ ],
663
+ "max_position_embeddings": 262144,
664
+ "model_type": "qwen3_vl_text",
665
+ "num_attention_heads": 32,
666
+ "num_hidden_layers": 36,
667
+ "num_key_value_heads": 8,
668
+ "pad_token_id": 0,
669
+ "rms_norm_eps": 1e-06,
670
+ "rope_scaling": {
671
+ "mrope_interleaved": true,
672
+ "mrope_section": [
673
+ 24,
674
+ 20,
675
+ 20
676
+ ],
677
+ "rope_type": "default"
678
+ },
679
+ "rope_theta": 5000000,
680
+ "tie_word_embeddings": false,
681
+ "vocab_size": 151936
682
+ },
683
+ "tie_word_embeddings": false,
684
+ "video_token_id": 151656,
685
+ "vision_config": {
686
+ "deepstack_visual_indexes": [
687
+ 8,
688
+ 16,
689
+ 24
690
+ ],
691
+ "depth": 27,
692
+ "hidden_act": "gelu_pytorch_tanh",
693
+ "hidden_size": 1152,
694
+ "in_channels": 3,
695
+ "initializer_range": 0.02,
696
+ "intermediate_size": 4304,
697
+ "model_type": "qwen3_vl",
698
+ "num_heads": 16,
699
+ "num_position_embeddings": 2304,
700
+ "out_hidden_size": 4096,
701
+ "patch_size": 16,
702
+ "spatial_merge_size": 2,
703
+ "temporal_patch_size": 2
704
+ },
705
+ "vision_end_token_id": 151653,
706
+ "vision_start_token_id": 151652,
707
+ "vocab_size": 151936
708
+ }
709
+ }
710
+ },
711
+ "model": {
712
+ "action_horizon": 32,
713
+ "action_in_proj": {
714
+ "input_size": 64,
715
+ "num_domains": 32,
716
+ "output_size": 4096,
717
+ "type": "DomainAwareLinear"
718
+ },
719
+ "action_out_proj": {
720
+ "input_size": 4096,
721
+ "num_domains": 32,
722
+ "output_size": 64,
723
+ "type": "DomainAwareLinear"
724
+ },
725
+ "base_fps": 24.0,
726
+ "enable_fps_modulation": true,
727
+ "enable_vision_loss": true,
728
+ "freeze_non_moe_vlm_backbone": true,
729
+ "freeze_vlm_backbone": false,
730
+ "latent_patch_size": 2,
731
+ "max_action_dim": 64,
732
+ "name_mapping": {
733
+ ".self_attn.k_norm.": ".self_attn.norm_k.",
734
+ ".self_attn.k_norm_moe_gen.": ".self_attn.norm_added_k.",
735
+ ".self_attn.k_proj.": ".self_attn.to_k.",
736
+ ".self_attn.k_proj_moe_gen.": ".self_attn.add_k_proj.",
737
+ ".self_attn.o_proj.": ".self_attn.to_out.",
738
+ ".self_attn.o_proj_moe_gen.": ".self_attn.to_add_out.",
739
+ ".self_attn.q_norm.": ".self_attn.norm_q.",
740
+ ".self_attn.q_norm_moe_gen.": ".self_attn.norm_added_q.",
741
+ ".self_attn.q_proj.": ".self_attn.to_q.",
742
+ ".self_attn.q_proj_moe_gen.": ".self_attn.add_q_proj.",
743
+ ".self_attn.v_proj.": ".self_attn.to_v.",
744
+ ".self_attn.v_proj_moe_gen.": ".self_attn.add_v_proj.",
745
+ "action_in_proj.": "action_proj_in.",
746
+ "action_modality_embed": "action_modality_embed",
747
+ "action_out_proj.": "action_proj_out.",
748
+ "time_embedder.mlp.0.": "time_embedder.linear_1.",
749
+ "time_embedder.mlp.2.": "time_embedder.linear_2.",
750
+ "vision_in_proj.projector.": "proj_in.",
751
+ "vision_out_proj.projector.": "proj_out.",
752
+ "vlm_backbone.lm_head.weight": "lm_head.weight",
753
+ "vlm_backbone.model.language_model.embed_tokens.weight": "embed_tokens.weight",
754
+ "vlm_backbone.model.language_model.layers.": "layers.",
755
+ "vlm_backbone.model.language_model.norm.weight": "norm.weight",
756
+ "vlm_backbone.model.language_model.norm_moe_gen.weight": "norm_moe_gen.weight",
757
+ "vlm_backbone.model.visual.blocks.": "blocks.",
758
+ "vlm_backbone.model.visual.deepstack_merger_list.": "deepstack_merger_list.",
759
+ "vlm_backbone.model.visual.merger.": "merger.",
760
+ "vlm_backbone.model.visual.patch_embed.": "patch_embed.",
761
+ "vlm_backbone.model.visual.pos_embed.": "pos_embed."
762
+ },
763
+ "num_embodiment_domains": 32,
764
+ "ori_action_dim": 14,
765
+ "packed_attention_backend": "flash2",
766
+ "position_embedding_type": "unified_3d_mrope",
767
+ "pretrained_name_or_path": "./checkpoints/Cosmos3-Nano/transformer",
768
+ "rectified_flow_inference_config": {
769
+ "num_steps": 30,
770
+ "num_train_timesteps": 1000,
771
+ "scheduler_type": "unipc",
772
+ "shift": 10.0,
773
+ "use_dynamic_shifting": false,
774
+ "use_karras_sigmas": false
775
+ },
776
+ "rectified_flow_training_config": {
777
+ "action_loss_weight": 10.0,
778
+ "high_sigma_ratio": 0.05,
779
+ "high_sigma_timesteps_max": 1000,
780
+ "high_sigma_timesteps_min": 995,
781
+ "independent_action_schedule": false,
782
+ "normalize_loss_by_active": false,
783
+ "shift": {
784
+ "256": 3,
785
+ "480": 5,
786
+ "720": 10
787
+ },
788
+ "shift_action": null,
789
+ "train_time_action_distribution": "logitnormal",
790
+ "train_time_image_distribution": "logitnormal",
791
+ "train_time_video_distribution": "waver",
792
+ "train_time_weight": "uniform",
793
+ "use_discrete_rf": false,
794
+ "use_dynamic_shift": false,
795
+ "use_high_sigma_strategy": false,
796
+ "use_high_sigma_strategy_action": false,
797
+ "vision_loss_weight": 1.0
798
+ },
799
+ "reinitialize_action_policy": true,
800
+ "special_tokens": {
801
+ "end_of_generation": 151653,
802
+ "eos_token_id": 151645,
803
+ "start_of_generation": 151652
804
+ },
805
+ "timestep_scale": 0.001,
806
+ "type": "Cosmos3FlowMatching",
807
+ "unified_3d_mrope_reset_spatial_ids": true,
808
+ "unified_3d_mrope_temporal_modality_margin": 15000,
809
+ "vision_in_proj": {
810
+ "in_dim": 192,
811
+ "out_dim": 4096,
812
+ "type": "LinearProjector"
813
+ },
814
+ "vision_latent_dim": 48,
815
+ "vision_out_proj": {
816
+ "in_dim": 4096,
817
+ "out_dim": 192,
818
+ "type": "LinearProjector"
819
+ },
820
+ "vision_vae": {
821
+ "encode_exact_durations": [
822
+ 33
823
+ ],
824
+ "pretrained_name_or_path": "./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
825
+ "type": "Cosmos3Wan22VAE"
826
+ },
827
+ "vlm_backbone": {
828
+ "include_visual": false,
829
+ "skip_init_weights": true,
830
+ "type": "Cosmos3MoTBackbone",
831
+ "vision_encoder_path": "./checkpoints/Cosmos3-Nano/vision_encoder",
832
+ "vlm_config": {
833
+ "image_token_id": 151655,
834
+ "model_type": "qwen3_vl",
835
+ "text_config": {
836
+ "attention_bias": false,
837
+ "attention_dropout": 0.0,
838
+ "bos_token_id": 151643,
839
+ "eos_token_id": 151645,
840
+ "head_dim": 128,
841
+ "hidden_act": "silu",
842
+ "hidden_size": 4096,
843
+ "intermediate_size": 12288,
844
+ "layer_types": [
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
+ "full_attention",
866
+ "full_attention",
867
+ "full_attention",
868
+ "full_attention",
869
+ "full_attention",
870
+ "full_attention",
871
+ "full_attention",
872
+ "full_attention",
873
+ "full_attention",
874
+ "full_attention",
875
+ "full_attention",
876
+ "full_attention",
877
+ "full_attention",
878
+ "full_attention",
879
+ "full_attention",
880
+ "full_attention"
881
+ ],
882
+ "max_position_embeddings": 262144,
883
+ "model_type": "qwen3_vl_text",
884
+ "num_attention_heads": 32,
885
+ "num_hidden_layers": 36,
886
+ "num_key_value_heads": 8,
887
+ "pad_token_id": 0,
888
+ "rms_norm_eps": 1e-06,
889
+ "rope_scaling": {
890
+ "mrope_interleaved": true,
891
+ "mrope_section": [
892
+ 24,
893
+ 20,
894
+ 20
895
+ ],
896
+ "rope_type": "default"
897
+ },
898
+ "rope_theta": 5000000,
899
+ "tie_word_embeddings": false,
900
+ "vocab_size": 151936
901
+ },
902
+ "tie_word_embeddings": false,
903
+ "video_token_id": 151656,
904
+ "vision_config": {
905
+ "deepstack_visual_indexes": [
906
+ 8,
907
+ 16,
908
+ 24
909
+ ],
910
+ "depth": 27,
911
+ "hidden_act": "gelu_pytorch_tanh",
912
+ "hidden_size": 1152,
913
+ "in_channels": 3,
914
+ "initializer_range": 0.02,
915
+ "intermediate_size": 4304,
916
+ "model_type": "qwen3_vl",
917
+ "num_heads": 16,
918
+ "num_position_embeddings": 2304,
919
+ "out_hidden_size": 4096,
920
+ "patch_size": 16,
921
+ "spatial_merge_size": 2,
922
+ "temporal_patch_size": 2
923
+ },
924
+ "vision_end_token_id": 151653,
925
+ "vision_start_token_id": 151652,
926
+ "vocab_size": 151936
927
+ }
928
+ }
929
+ },
930
+ "runner": {
931
+ "change_key_name": false,
932
+ "collator": {
933
+ "keys": [
934
+ "images",
935
+ "states",
936
+ "actions",
937
+ "action_masks",
938
+ "img_masks",
939
+ "frame_masks",
940
+ "embodiment_ids",
941
+ "raw_action_dim",
942
+ "conditioning_fps",
943
+ "action_fps"
944
+ ],
945
+ "meta_keys": [
946
+ "text_token_ids",
947
+ "sequence_plan",
948
+ "task_description",
949
+ "stats",
950
+ "info",
951
+ "timestamp",
952
+ "viewpoint"
953
+ ],
954
+ "type": "DictCollator"
955
+ },
956
+ "enable_gradient_checkpointing": true,
957
+ "enable_mixed_precision_training": true,
958
+ "grad_accumulation_steps": 1,
959
+ "lr_scheduler": {
960
+ "type": "linear-warmup+linear-decay",
961
+ "warmup_steps": 500
962
+ },
963
+ "max_epochs": 8,
964
+ "max_grad_norm": 1.0,
965
+ "max_keep_ckpts": 3,
966
+ "max_steps": null,
967
+ "metric": {
968
+ "active_trackers": [
969
+ "jsonl",
970
+ "wandb"
971
+ ],
972
+ "grad_accumulation_steps": 1,
973
+ "run_dir": "work_dirs",
974
+ "type": "VLAMetric",
975
+ "window_size": 1
976
+ },
977
+ "mixed_precision_dtype": "bf16",
978
+ "optimizer": {
979
+ "betas": [
980
+ 0.9,
981
+ 0.99
982
+ ],
983
+ "eps": 1e-08,
984
+ "exclude_1d_from_weight_decay": false,
985
+ "fused": true,
986
+ "lr": 5e-05,
987
+ "paramwise_learning_rate": {
988
+ "action_in_proj.": 0.00025,
989
+ "action_modality_embed": 0.00025,
990
+ "action_out_proj.": 0.00025
991
+ },
992
+ "type": "AdamW",
993
+ "weight_decay": 0.05
994
+ },
995
+ "sampler": null,
996
+ "save_epoch_interval": 1,
997
+ "save_iter_interval": 500,
998
+ "sharding_strategy": "full-shard",
999
+ "tokenizer": {
1000
+ "model_max_length": 4096,
1001
+ "model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
1002
+ "padding_side": "right",
1003
+ "trust_remote_code": true,
1004
+ "type": "PretrainedTokenizer"
1005
+ },
1006
+ "type": "FSDPTrainRunner"
1007
+ },
1008
+ "seed": 7,
1009
+ "train_dataloader": {
1010
+ "dataset": {
1011
+ "datasets": {
1012
+ "action_key": "action",
1013
+ "action_window_size": 32,
1014
+ "data_root_path": [
1015
+ "./datasets/robotwin_clean_lerobotv2.1",
1016
+ "./datasets/robotwin_randomized_lerobotv2.1"
1017
+ ],
1018
+ "frame_window_size": 33,
1019
+ "require_full_window": true,
1020
+ "statistic_name": "robotwin_all",
1021
+ "transforms": [
1022
+ {
1023
+ "embodiment_id": 21,
1024
+ "name_mappings": {
1025
+ "actions": [
1026
+ "actions"
1027
+ ],
1028
+ "observation.state": [
1029
+ "states"
1030
+ ]
1031
+ },
1032
+ "parquet_keys": [
1033
+ "observation.state",
1034
+ "timestamp",
1035
+ "actions",
1036
+ "info",
1037
+ "stats",
1038
+ "action_masks"
1039
+ ],
1040
+ "type": "ProcessParquetInputs",
1041
+ "video_keys": [
1042
+ "observation.images.cam_high",
1043
+ "observation.images.cam_left_wrist",
1044
+ "observation.images.cam_right_wrist"
1045
+ ]
1046
+ },
1047
+ {
1048
+ "height": 256,
1049
+ "type": "ResizeImages",
1050
+ "width": 256
1051
+ },
1052
+ {
1053
+ "brightness_range": [
1054
+ 0.7,
1055
+ 1.3
1056
+ ],
1057
+ "contrast_range": [
1058
+ 0.6,
1059
+ 1.4
1060
+ ],
1061
+ "crop_ratio": [
1062
+ 1.0,
1063
+ 1.0
1064
+ ],
1065
+ "crop_scale": [
1066
+ 0.95,
1067
+ 0.95
1068
+ ],
1069
+ "hue_delta": 0.08,
1070
+ "prob": 1.0,
1071
+ "rotation_range": 0.0,
1072
+ "saturation_range": [
1073
+ 0.5,
1074
+ 1.5
1075
+ ],
1076
+ "type": "AugVideo"
1077
+ },
1078
+ {
1079
+ "action_metadata": {
1080
+ "append_viewpoint": false,
1081
+ "conditioning_fps": 15.0,
1082
+ "frame_window_size": 33,
1083
+ "video_height": 384,
1084
+ "video_width": 256
1085
+ },
1086
+ "cfg_dropout_rate": 0.1,
1087
+ "max_len": 512,
1088
+ "tokenizer": {
1089
+ "model_max_length": 4096,
1090
+ "model_path": "./checkpoints/Cosmos3-Nano/text_tokenizer",
1091
+ "padding_side": "right",
1092
+ "trust_remote_code": true,
1093
+ "type": "PretrainedTokenizer"
1094
+ },
1095
+ "type": "ProcessCosmos3Prompt"
1096
+ },
1097
+ {
1098
+ "type": "SimpleNormalizeImages"
1099
+ },
1100
+ {
1101
+ "action_dim": 64,
1102
+ "action_key": "action",
1103
+ "norm_type": "mean_std",
1104
+ "state_dim": 64,
1105
+ "state_key": "proprio",
1106
+ "type": "NormalizeStatesAndActions"
1107
+ },
1108
+ {
1109
+ "conditioning_fps": 15.0,
1110
+ "frame_window_size": 33,
1111
+ "mode": "wam",
1112
+ "prepend_state_to_action": true,
1113
+ "raw_action_dim": 14,
1114
+ "type": "BuildCosmos3Sequence"
1115
+ },
1116
+ {
1117
+ "bottom_height_ratio": 0.5,
1118
+ "bottom_views": [
1119
+ 1,
1120
+ 2
1121
+ ],
1122
+ "frame_window_size": 33,
1123
+ "num_views": 3,
1124
+ "tile_direction": "top_bottom_pair",
1125
+ "top_view": 0,
1126
+ "type": "PrepareVideo"
1127
+ }
1128
+ ],
1129
+ "type": "ParquetDataset",
1130
+ "use_delta": false,
1131
+ "window_start_idx": 0
1132
+ },
1133
+ "name_mappings": {
1134
+ "action": [
1135
+ "action"
1136
+ ],
1137
+ "observation.state": [
1138
+ "proprio"
1139
+ ]
1140
+ },
1141
+ "statistic_keys": [
1142
+ "observation.state",
1143
+ "timestamp",
1144
+ "action"
1145
+ ],
1146
+ "statistic_name": "robotwin_all",
1147
+ "type": "DistributedRepeatingDataset"
1148
+ },
1149
+ "per_device_batch_size": 16,
1150
+ "per_device_num_workers": 4,
1151
+ "prefetch_factor": 1
1152
+ }
1153
+ }
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/config.yaml ADDED
@@ -0,0 +1,994 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ACTION_DIM: 14
2
+ _ACTION_HORIZON: 32
3
+ _ACTION_LR: 0.00025
4
+ _ACTION_PROMPT_METADATA:
5
+ append_viewpoint: false
6
+ conditioning_fps: 15.0
7
+ frame_window_size: 33
8
+ video_height: 384
9
+ video_width: 256
10
+ _BASE_LR: 5.0e-05
11
+ _CFG_DROPOUT_RATE: 0.1
12
+ _CKPT_ROOT: ./checkpoints
13
+ _CONDITIONING_FPS: 15.0
14
+ _COSMOS3_NANO_CKPT: ./checkpoints/Cosmos3-Nano
15
+ _COSMOS3_NANO_NAME_MAPPING:
16
+ .self_attn.k_norm.: .self_attn.norm_k.
17
+ .self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
18
+ .self_attn.k_proj.: .self_attn.to_k.
19
+ .self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
20
+ .self_attn.o_proj.: .self_attn.to_out.
21
+ .self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
22
+ .self_attn.q_norm.: .self_attn.norm_q.
23
+ .self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
24
+ .self_attn.q_proj.: .self_attn.to_q.
25
+ .self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
26
+ .self_attn.v_proj.: .self_attn.to_v.
27
+ .self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
28
+ action_in_proj.: action_proj_in.
29
+ action_modality_embed: action_modality_embed
30
+ action_out_proj.: action_proj_out.
31
+ time_embedder.mlp.0.: time_embedder.linear_1.
32
+ time_embedder.mlp.2.: time_embedder.linear_2.
33
+ vision_in_proj.projector.: proj_in.
34
+ vision_out_proj.projector.: proj_out.
35
+ vlm_backbone.lm_head.weight: lm_head.weight
36
+ vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
37
+ vlm_backbone.model.language_model.layers.: layers.
38
+ vlm_backbone.model.language_model.norm.weight: norm.weight
39
+ vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
40
+ vlm_backbone.model.visual.blocks.: blocks.
41
+ vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
42
+ vlm_backbone.model.visual.merger.: merger.
43
+ vlm_backbone.model.visual.patch_embed.: patch_embed.
44
+ vlm_backbone.model.visual.pos_embed.: pos_embed.
45
+ _COSMOS3_NANO_SPECIAL_TOKENS:
46
+ end_of_generation: 151653
47
+ eos_token_id: 151645
48
+ start_of_generation: 151652
49
+ _COSMOS3_NANO_TOKENIZER:
50
+ model_max_length: 4096
51
+ model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
52
+ padding_side: right
53
+ trust_remote_code: true
54
+ type: PretrainedTokenizer
55
+ _COSMOS3_NANO_TRANSFORMER: ./checkpoints/Cosmos3-Nano/transformer
56
+ _COSMOS3_NANO_VISION_ENCODER: ./checkpoints/Cosmos3-Nano/vision_encoder
57
+ _COSMOS3_NANO_VLM_CONFIG:
58
+ image_token_id: 151655
59
+ model_type: qwen3_vl
60
+ text_config:
61
+ attention_bias: false
62
+ attention_dropout: 0.0
63
+ bos_token_id: 151643
64
+ eos_token_id: 151645
65
+ head_dim: 128
66
+ hidden_act: silu
67
+ hidden_size: 4096
68
+ intermediate_size: 12288
69
+ layer_types:
70
+ - full_attention
71
+ - full_attention
72
+ - full_attention
73
+ - full_attention
74
+ - full_attention
75
+ - full_attention
76
+ - full_attention
77
+ - full_attention
78
+ - full_attention
79
+ - full_attention
80
+ - full_attention
81
+ - full_attention
82
+ - full_attention
83
+ - full_attention
84
+ - full_attention
85
+ - full_attention
86
+ - full_attention
87
+ - full_attention
88
+ - full_attention
89
+ - full_attention
90
+ - full_attention
91
+ - full_attention
92
+ - full_attention
93
+ - full_attention
94
+ - full_attention
95
+ - full_attention
96
+ - full_attention
97
+ - full_attention
98
+ - full_attention
99
+ - full_attention
100
+ - full_attention
101
+ - full_attention
102
+ - full_attention
103
+ - full_attention
104
+ - full_attention
105
+ - full_attention
106
+ max_position_embeddings: 262144
107
+ model_type: qwen3_vl_text
108
+ num_attention_heads: 32
109
+ num_hidden_layers: 36
110
+ num_key_value_heads: 8
111
+ pad_token_id: 0
112
+ rms_norm_eps: 1.0e-06
113
+ rope_scaling:
114
+ mrope_interleaved: true
115
+ mrope_section:
116
+ - 24
117
+ - 20
118
+ - 20
119
+ rope_type: default
120
+ rope_theta: 5000000
121
+ tie_word_embeddings: false
122
+ vocab_size: 151936
123
+ tie_word_embeddings: false
124
+ video_token_id: 151656
125
+ vision_config:
126
+ deepstack_visual_indexes:
127
+ - 8
128
+ - 16
129
+ - 24
130
+ depth: 27
131
+ hidden_act: gelu_pytorch_tanh
132
+ hidden_size: 1152
133
+ in_channels: 3
134
+ initializer_range: 0.02
135
+ intermediate_size: 4304
136
+ model_type: qwen3_vl
137
+ num_heads: 16
138
+ num_position_embeddings: 2304
139
+ out_hidden_size: 4096
140
+ patch_size: 16
141
+ spatial_merge_size: 2
142
+ temporal_patch_size: 2
143
+ vision_end_token_id: 151653
144
+ vision_start_token_id: 151652
145
+ vocab_size: 151936
146
+ _FRAME_WINDOW_SIZE: 33
147
+ _GRAD_ACCUMULATION_STEPS: 1
148
+ _IMAGE_HEIGHT: 256
149
+ _IMAGE_WIDTH: 256
150
+ _MAX_ACTION_DIM: 64
151
+ _MAX_EPOCHS: 8
152
+ _MAX_STATE_DIM: 64
153
+ _MAX_STEPS: null
154
+ _PER_DEVICE_BATCH_SIZE: 16
155
+ _PREPEND_STATE_TO_ACTION: true
156
+ _ROBOTWIN_DATA_ROOTS:
157
+ - ./datasets/robotwin_clean_lerobotv2.1
158
+ - ./datasets/robotwin_randomized_lerobotv2.1
159
+ _ROBOTWIN_EMBODIMENT_ID: 21
160
+ _ROBOTWIN_TASK_LIST:
161
+ - adjust_bottle
162
+ - beat_block_hammer
163
+ - blocks_ranking_rgb
164
+ - blocks_ranking_size
165
+ - click_alarmclock
166
+ - click_bell
167
+ - dump_bin_bigbin
168
+ - grab_roller
169
+ - handover_block
170
+ - handover_mic
171
+ - hanging_mug
172
+ - lift_pot
173
+ - move_can_pot
174
+ - move_pillbottle_pad
175
+ - move_playingcard_away
176
+ - move_stapler_pad
177
+ - open_laptop
178
+ - open_microwave
179
+ - pick_diverse_bottles
180
+ - pick_dual_bottles
181
+ - place_a2b_left
182
+ - place_a2b_right
183
+ - place_bread_basket
184
+ - place_bread_skillet
185
+ - place_burger_fries
186
+ - place_can_basket
187
+ - place_cans_plasticbox
188
+ - place_container_plate
189
+ - place_dual_shoes
190
+ - place_empty_cup
191
+ - place_fan
192
+ - place_mouse_pad
193
+ - place_object_basket
194
+ - place_object_scale
195
+ - place_object_stand
196
+ - place_phone_stand
197
+ - place_shoe
198
+ - press_stapler
199
+ - put_bottles_dustbin
200
+ - put_object_cabinet
201
+ - rotate_qrcode
202
+ - scan_object
203
+ - shake_bottle
204
+ - shake_bottle_horizontally
205
+ - stack_blocks_three
206
+ - stack_blocks_two
207
+ - stack_bowls_three
208
+ - stack_bowls_two
209
+ - stamp_seal
210
+ - turn_switch
211
+ _SAVE_EPOCH_INTERVAL: 1
212
+ _SAVE_ITER_INTERVAL: 500
213
+ _STATISTIC_NAME: robotwin_all
214
+ _TRANSFORMS:
215
+ - embodiment_id: 21
216
+ name_mappings:
217
+ actions:
218
+ - actions
219
+ observation.state:
220
+ - states
221
+ parquet_keys:
222
+ - observation.state
223
+ - timestamp
224
+ - actions
225
+ - info
226
+ - stats
227
+ - action_masks
228
+ type: ProcessParquetInputs
229
+ video_keys:
230
+ - observation.images.cam_high
231
+ - observation.images.cam_left_wrist
232
+ - observation.images.cam_right_wrist
233
+ - height: 256
234
+ type: ResizeImages
235
+ width: 256
236
+ - brightness_range:
237
+ - 0.7
238
+ - 1.3
239
+ contrast_range:
240
+ - 0.6
241
+ - 1.4
242
+ crop_ratio:
243
+ - 1.0
244
+ - 1.0
245
+ crop_scale:
246
+ - 0.95
247
+ - 0.95
248
+ hue_delta: 0.08
249
+ prob: 1.0
250
+ rotation_range: 0.0
251
+ saturation_range:
252
+ - 0.5
253
+ - 1.5
254
+ type: AugVideo
255
+ - action_metadata:
256
+ append_viewpoint: false
257
+ conditioning_fps: 15.0
258
+ frame_window_size: 33
259
+ video_height: 384
260
+ video_width: 256
261
+ cfg_dropout_rate: 0.1
262
+ max_len: 512
263
+ tokenizer:
264
+ model_max_length: 4096
265
+ model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
266
+ padding_side: right
267
+ trust_remote_code: true
268
+ type: PretrainedTokenizer
269
+ type: ProcessCosmos3Prompt
270
+ - type: SimpleNormalizeImages
271
+ - action_dim: 64
272
+ action_key: action
273
+ norm_type: mean_std
274
+ state_dim: 64
275
+ state_key: proprio
276
+ type: NormalizeStatesAndActions
277
+ - conditioning_fps: 15.0
278
+ frame_window_size: 33
279
+ mode: wam
280
+ prepend_state_to_action: true
281
+ raw_action_dim: 14
282
+ type: BuildCosmos3Sequence
283
+ - bottom_height_ratio: 0.5
284
+ bottom_views:
285
+ - 1
286
+ - 2
287
+ frame_window_size: 33
288
+ num_views: 3
289
+ tile_direction: top_bottom_pair
290
+ top_view: 0
291
+ type: PrepareVideo
292
+ _VIDEO_HEIGHT: 384
293
+ _VIDEO_WIDTH: 256
294
+ _WAN22_VAE_PATH: ./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth
295
+ eval:
296
+ manager:
297
+ launch_delay: 0.5
298
+ master_port_base: 29690
299
+ max_tasks_per_gpu: 1
300
+ monitor_interval: 5
301
+ num_gpus: 8
302
+ status_interval: 30
303
+ runner:
304
+ dataset:
305
+ embodiment_id: 21
306
+ extra_tensor_keys:
307
+ - conditioning_fps
308
+ - prepend_state_to_action
309
+ img_keys:
310
+ - cam_high
311
+ - cam_left_wrist
312
+ - cam_right_wrist
313
+ inject_model_path: false
314
+ transforms:
315
+ - conditioning_fps: 15.0
316
+ prepend_state_to_action: true
317
+ type: SetCosmos3ActionMetadata
318
+ - action_metadata:
319
+ append_viewpoint: false
320
+ conditioning_fps: 15.0
321
+ frame_window_size: 33
322
+ video_height: 384
323
+ video_width: 256
324
+ cfg_dropout_rate: 0.0
325
+ max_len: 512
326
+ output_attention_mask_key: lang_masks
327
+ output_key: lang_tokens
328
+ tokenizer:
329
+ model_max_length: 4096
330
+ model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
331
+ padding_side: right
332
+ trust_remote_code: true
333
+ type: PretrainedTokenizer
334
+ type: ProcessCosmos3Prompt
335
+ - height: 256
336
+ type: ResizeImages
337
+ width: 256
338
+ - type: SimpleNormalizeImages
339
+ - action_dim: 64
340
+ action_key: action
341
+ norm_type: mean_std
342
+ state_dim: 64
343
+ state_key: proprio
344
+ type: NormalizeStatesAndActions
345
+ - bottom_height_ratio: 0.5
346
+ bottom_views:
347
+ - 1
348
+ - 2
349
+ frame_window_size: 1
350
+ num_views: 3
351
+ tile_direction: top_bottom_pair
352
+ top_view: 0
353
+ type: PrepareVideo
354
+ type: PrivateInferenceDataset
355
+ denormalize_action:
356
+ action_dim: 14
357
+ norm_type: mean_std
358
+ type: DenormalizePrivateAction
359
+ enable_model_dtype_cast: true
360
+ eval_chunk_size: 24
361
+ instruction_type: unseen
362
+ mixed_precision_dtype: bf16
363
+ model_family: cosmos3
364
+ num_trials_per_task: 100
365
+ save_video: false
366
+ seed: 7
367
+ task_list:
368
+ - adjust_bottle
369
+ - beat_block_hammer
370
+ - blocks_ranking_rgb
371
+ - blocks_ranking_size
372
+ - click_alarmclock
373
+ - click_bell
374
+ - dump_bin_bigbin
375
+ - grab_roller
376
+ - handover_block
377
+ - handover_mic
378
+ - hanging_mug
379
+ - lift_pot
380
+ - move_can_pot
381
+ - move_pillbottle_pad
382
+ - move_playingcard_away
383
+ - move_stapler_pad
384
+ - open_laptop
385
+ - open_microwave
386
+ - pick_diverse_bottles
387
+ - pick_dual_bottles
388
+ - place_a2b_left
389
+ - place_a2b_right
390
+ - place_bread_basket
391
+ - place_bread_skillet
392
+ - place_burger_fries
393
+ - place_can_basket
394
+ - place_cans_plasticbox
395
+ - place_container_plate
396
+ - place_dual_shoes
397
+ - place_empty_cup
398
+ - place_fan
399
+ - place_mouse_pad
400
+ - place_object_basket
401
+ - place_object_scale
402
+ - place_object_stand
403
+ - place_phone_stand
404
+ - place_shoe
405
+ - press_stapler
406
+ - put_bottles_dustbin
407
+ - put_object_cabinet
408
+ - rotate_qrcode
409
+ - scan_object
410
+ - shake_bottle
411
+ - shake_bottle_horizontally
412
+ - stack_blocks_three
413
+ - stack_blocks_two
414
+ - stack_bowls_three
415
+ - stack_bowls_two
416
+ - stamp_seal
417
+ - turn_switch
418
+ task_suite_name:
419
+ - clean
420
+ - random
421
+ type: RobotwinEvalRunner
422
+ unnorm_key: robotwin_all
423
+ inference_model:
424
+ action_horizon: 32
425
+ action_in_proj:
426
+ input_size: 64
427
+ num_domains: 32
428
+ output_size: 4096
429
+ type: DomainAwareLinear
430
+ action_out_proj:
431
+ input_size: 4096
432
+ num_domains: 32
433
+ output_size: 64
434
+ type: DomainAwareLinear
435
+ base_fps: 24.0
436
+ enable_fps_modulation: true
437
+ enable_vision_loss: true
438
+ freeze_non_moe_vlm_backbone: true
439
+ freeze_vlm_backbone: false
440
+ latent_patch_size: 2
441
+ max_action_dim: 64
442
+ name_mapping:
443
+ .self_attn.k_norm.: .self_attn.norm_k.
444
+ .self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
445
+ .self_attn.k_proj.: .self_attn.to_k.
446
+ .self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
447
+ .self_attn.o_proj.: .self_attn.to_out.
448
+ .self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
449
+ .self_attn.q_norm.: .self_attn.norm_q.
450
+ .self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
451
+ .self_attn.q_proj.: .self_attn.to_q.
452
+ .self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
453
+ .self_attn.v_proj.: .self_attn.to_v.
454
+ .self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
455
+ action_in_proj.: action_proj_in.
456
+ action_modality_embed: action_modality_embed
457
+ action_out_proj.: action_proj_out.
458
+ time_embedder.mlp.0.: time_embedder.linear_1.
459
+ time_embedder.mlp.2.: time_embedder.linear_2.
460
+ vision_in_proj.projector.: proj_in.
461
+ vision_out_proj.projector.: proj_out.
462
+ vlm_backbone.lm_head.weight: lm_head.weight
463
+ vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
464
+ vlm_backbone.model.language_model.layers.: layers.
465
+ vlm_backbone.model.language_model.norm.weight: norm.weight
466
+ vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
467
+ vlm_backbone.model.visual.blocks.: blocks.
468
+ vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
469
+ vlm_backbone.model.visual.merger.: merger.
470
+ vlm_backbone.model.visual.patch_embed.: patch_embed.
471
+ vlm_backbone.model.visual.pos_embed.: pos_embed.
472
+ num_embodiment_domains: 32
473
+ ori_action_dim: 14
474
+ packed_attention_backend: flash2
475
+ position_embedding_type: unified_3d_mrope
476
+ pretrained_name_or_path: ./checkpoints/Cosmos3-Nano/transformer
477
+ rectified_flow_inference_config:
478
+ num_steps: 30
479
+ num_train_timesteps: 1000
480
+ scheduler_type: unipc
481
+ shift: 10.0
482
+ use_dynamic_shifting: false
483
+ use_karras_sigmas: false
484
+ rectified_flow_training_config:
485
+ action_loss_weight: 10.0
486
+ high_sigma_ratio: 0.05
487
+ high_sigma_timesteps_max: 1000
488
+ high_sigma_timesteps_min: 995
489
+ independent_action_schedule: false
490
+ normalize_loss_by_active: false
491
+ shift:
492
+ '256': 3
493
+ '480': 5
494
+ '720': 10
495
+ shift_action: null
496
+ train_time_action_distribution: logitnormal
497
+ train_time_image_distribution: logitnormal
498
+ train_time_video_distribution: waver
499
+ train_time_weight: uniform
500
+ use_discrete_rf: false
501
+ use_dynamic_shift: false
502
+ use_high_sigma_strategy: false
503
+ use_high_sigma_strategy_action: false
504
+ vision_loss_weight: 1.0
505
+ reinitialize_action_policy: true
506
+ special_tokens:
507
+ end_of_generation: 151653
508
+ eos_token_id: 151645
509
+ start_of_generation: 151652
510
+ timestep_scale: 0.001
511
+ type: Cosmos3FlowMatching
512
+ unified_3d_mrope_reset_spatial_ids: true
513
+ unified_3d_mrope_temporal_modality_margin: 15000
514
+ vision_in_proj:
515
+ in_dim: 192
516
+ out_dim: 4096
517
+ type: LinearProjector
518
+ vision_latent_dim: 48
519
+ vision_out_proj:
520
+ in_dim: 4096
521
+ out_dim: 192
522
+ type: LinearProjector
523
+ vision_vae:
524
+ encode_exact_durations:
525
+ - 33
526
+ pretrained_name_or_path: null
527
+ type: Cosmos3Wan22VAE
528
+ vlm_backbone:
529
+ include_visual: false
530
+ skip_init_weights: true
531
+ type: Cosmos3MoTBackbone
532
+ vision_encoder_path: ./checkpoints/Cosmos3-Nano/vision_encoder
533
+ vlm_config:
534
+ image_token_id: 151655
535
+ model_type: qwen3_vl
536
+ text_config:
537
+ attention_bias: false
538
+ attention_dropout: 0.0
539
+ bos_token_id: 151643
540
+ eos_token_id: 151645
541
+ head_dim: 128
542
+ hidden_act: silu
543
+ hidden_size: 4096
544
+ intermediate_size: 12288
545
+ layer_types:
546
+ - full_attention
547
+ - full_attention
548
+ - full_attention
549
+ - full_attention
550
+ - full_attention
551
+ - full_attention
552
+ - full_attention
553
+ - full_attention
554
+ - full_attention
555
+ - full_attention
556
+ - full_attention
557
+ - full_attention
558
+ - full_attention
559
+ - full_attention
560
+ - full_attention
561
+ - full_attention
562
+ - full_attention
563
+ - full_attention
564
+ - full_attention
565
+ - full_attention
566
+ - full_attention
567
+ - full_attention
568
+ - full_attention
569
+ - full_attention
570
+ - full_attention
571
+ - full_attention
572
+ - full_attention
573
+ - full_attention
574
+ - full_attention
575
+ - full_attention
576
+ - full_attention
577
+ - full_attention
578
+ - full_attention
579
+ - full_attention
580
+ - full_attention
581
+ - full_attention
582
+ max_position_embeddings: 262144
583
+ model_type: qwen3_vl_text
584
+ num_attention_heads: 32
585
+ num_hidden_layers: 36
586
+ num_key_value_heads: 8
587
+ pad_token_id: 0
588
+ rms_norm_eps: 1.0e-06
589
+ rope_scaling:
590
+ mrope_interleaved: true
591
+ mrope_section:
592
+ - 24
593
+ - 20
594
+ - 20
595
+ rope_type: default
596
+ rope_theta: 5000000
597
+ tie_word_embeddings: false
598
+ vocab_size: 151936
599
+ tie_word_embeddings: false
600
+ video_token_id: 151656
601
+ vision_config:
602
+ deepstack_visual_indexes:
603
+ - 8
604
+ - 16
605
+ - 24
606
+ depth: 27
607
+ hidden_act: gelu_pytorch_tanh
608
+ hidden_size: 1152
609
+ in_channels: 3
610
+ initializer_range: 0.02
611
+ intermediate_size: 4304
612
+ model_type: qwen3_vl
613
+ num_heads: 16
614
+ num_position_embeddings: 2304
615
+ out_hidden_size: 4096
616
+ patch_size: 16
617
+ spatial_merge_size: 2
618
+ temporal_patch_size: 2
619
+ vision_end_token_id: 151653
620
+ vision_start_token_id: 151652
621
+ vocab_size: 151936
622
+ model:
623
+ action_horizon: 32
624
+ action_in_proj:
625
+ input_size: 64
626
+ num_domains: 32
627
+ output_size: 4096
628
+ type: DomainAwareLinear
629
+ action_out_proj:
630
+ input_size: 4096
631
+ num_domains: 32
632
+ output_size: 64
633
+ type: DomainAwareLinear
634
+ base_fps: 24.0
635
+ enable_fps_modulation: true
636
+ enable_vision_loss: true
637
+ freeze_non_moe_vlm_backbone: true
638
+ freeze_vlm_backbone: false
639
+ latent_patch_size: 2
640
+ max_action_dim: 64
641
+ name_mapping:
642
+ .self_attn.k_norm.: .self_attn.norm_k.
643
+ .self_attn.k_norm_moe_gen.: .self_attn.norm_added_k.
644
+ .self_attn.k_proj.: .self_attn.to_k.
645
+ .self_attn.k_proj_moe_gen.: .self_attn.add_k_proj.
646
+ .self_attn.o_proj.: .self_attn.to_out.
647
+ .self_attn.o_proj_moe_gen.: .self_attn.to_add_out.
648
+ .self_attn.q_norm.: .self_attn.norm_q.
649
+ .self_attn.q_norm_moe_gen.: .self_attn.norm_added_q.
650
+ .self_attn.q_proj.: .self_attn.to_q.
651
+ .self_attn.q_proj_moe_gen.: .self_attn.add_q_proj.
652
+ .self_attn.v_proj.: .self_attn.to_v.
653
+ .self_attn.v_proj_moe_gen.: .self_attn.add_v_proj.
654
+ action_in_proj.: action_proj_in.
655
+ action_modality_embed: action_modality_embed
656
+ action_out_proj.: action_proj_out.
657
+ time_embedder.mlp.0.: time_embedder.linear_1.
658
+ time_embedder.mlp.2.: time_embedder.linear_2.
659
+ vision_in_proj.projector.: proj_in.
660
+ vision_out_proj.projector.: proj_out.
661
+ vlm_backbone.lm_head.weight: lm_head.weight
662
+ vlm_backbone.model.language_model.embed_tokens.weight: embed_tokens.weight
663
+ vlm_backbone.model.language_model.layers.: layers.
664
+ vlm_backbone.model.language_model.norm.weight: norm.weight
665
+ vlm_backbone.model.language_model.norm_moe_gen.weight: norm_moe_gen.weight
666
+ vlm_backbone.model.visual.blocks.: blocks.
667
+ vlm_backbone.model.visual.deepstack_merger_list.: deepstack_merger_list.
668
+ vlm_backbone.model.visual.merger.: merger.
669
+ vlm_backbone.model.visual.patch_embed.: patch_embed.
670
+ vlm_backbone.model.visual.pos_embed.: pos_embed.
671
+ num_embodiment_domains: 32
672
+ ori_action_dim: 14
673
+ packed_attention_backend: flash2
674
+ position_embedding_type: unified_3d_mrope
675
+ pretrained_name_or_path: ./checkpoints/Cosmos3-Nano/transformer
676
+ rectified_flow_inference_config:
677
+ num_steps: 30
678
+ num_train_timesteps: 1000
679
+ scheduler_type: unipc
680
+ shift: 10.0
681
+ use_dynamic_shifting: false
682
+ use_karras_sigmas: false
683
+ rectified_flow_training_config:
684
+ action_loss_weight: 10.0
685
+ high_sigma_ratio: 0.05
686
+ high_sigma_timesteps_max: 1000
687
+ high_sigma_timesteps_min: 995
688
+ independent_action_schedule: false
689
+ normalize_loss_by_active: false
690
+ shift:
691
+ '256': 3
692
+ '480': 5
693
+ '720': 10
694
+ shift_action: null
695
+ train_time_action_distribution: logitnormal
696
+ train_time_image_distribution: logitnormal
697
+ train_time_video_distribution: waver
698
+ train_time_weight: uniform
699
+ use_discrete_rf: false
700
+ use_dynamic_shift: false
701
+ use_high_sigma_strategy: false
702
+ use_high_sigma_strategy_action: false
703
+ vision_loss_weight: 1.0
704
+ reinitialize_action_policy: true
705
+ special_tokens:
706
+ end_of_generation: 151653
707
+ eos_token_id: 151645
708
+ start_of_generation: 151652
709
+ timestep_scale: 0.001
710
+ type: Cosmos3FlowMatching
711
+ unified_3d_mrope_reset_spatial_ids: true
712
+ unified_3d_mrope_temporal_modality_margin: 15000
713
+ vision_in_proj:
714
+ in_dim: 192
715
+ out_dim: 4096
716
+ type: LinearProjector
717
+ vision_latent_dim: 48
718
+ vision_out_proj:
719
+ in_dim: 4096
720
+ out_dim: 192
721
+ type: LinearProjector
722
+ vision_vae:
723
+ encode_exact_durations:
724
+ - 33
725
+ pretrained_name_or_path: ./checkpoints/Wan2.2-TI2V-5B/Wan2.2_VAE.pth
726
+ type: Cosmos3Wan22VAE
727
+ vlm_backbone:
728
+ include_visual: false
729
+ skip_init_weights: true
730
+ type: Cosmos3MoTBackbone
731
+ vision_encoder_path: ./checkpoints/Cosmos3-Nano/vision_encoder
732
+ vlm_config:
733
+ image_token_id: 151655
734
+ model_type: qwen3_vl
735
+ text_config:
736
+ attention_bias: false
737
+ attention_dropout: 0.0
738
+ bos_token_id: 151643
739
+ eos_token_id: 151645
740
+ head_dim: 128
741
+ hidden_act: silu
742
+ hidden_size: 4096
743
+ intermediate_size: 12288
744
+ layer_types:
745
+ - full_attention
746
+ - full_attention
747
+ - full_attention
748
+ - full_attention
749
+ - full_attention
750
+ - full_attention
751
+ - full_attention
752
+ - full_attention
753
+ - full_attention
754
+ - full_attention
755
+ - full_attention
756
+ - full_attention
757
+ - full_attention
758
+ - full_attention
759
+ - full_attention
760
+ - full_attention
761
+ - full_attention
762
+ - full_attention
763
+ - full_attention
764
+ - full_attention
765
+ - full_attention
766
+ - full_attention
767
+ - full_attention
768
+ - full_attention
769
+ - full_attention
770
+ - full_attention
771
+ - full_attention
772
+ - full_attention
773
+ - full_attention
774
+ - full_attention
775
+ - full_attention
776
+ - full_attention
777
+ - full_attention
778
+ - full_attention
779
+ - full_attention
780
+ - full_attention
781
+ max_position_embeddings: 262144
782
+ model_type: qwen3_vl_text
783
+ num_attention_heads: 32
784
+ num_hidden_layers: 36
785
+ num_key_value_heads: 8
786
+ pad_token_id: 0
787
+ rms_norm_eps: 1.0e-06
788
+ rope_scaling:
789
+ mrope_interleaved: true
790
+ mrope_section:
791
+ - 24
792
+ - 20
793
+ - 20
794
+ rope_type: default
795
+ rope_theta: 5000000
796
+ tie_word_embeddings: false
797
+ vocab_size: 151936
798
+ tie_word_embeddings: false
799
+ video_token_id: 151656
800
+ vision_config:
801
+ deepstack_visual_indexes:
802
+ - 8
803
+ - 16
804
+ - 24
805
+ depth: 27
806
+ hidden_act: gelu_pytorch_tanh
807
+ hidden_size: 1152
808
+ in_channels: 3
809
+ initializer_range: 0.02
810
+ intermediate_size: 4304
811
+ model_type: qwen3_vl
812
+ num_heads: 16
813
+ num_position_embeddings: 2304
814
+ out_hidden_size: 4096
815
+ patch_size: 16
816
+ spatial_merge_size: 2
817
+ temporal_patch_size: 2
818
+ vision_end_token_id: 151653
819
+ vision_start_token_id: 151652
820
+ vocab_size: 151936
821
+ runner:
822
+ change_key_name: false
823
+ collator:
824
+ keys:
825
+ - images
826
+ - states
827
+ - actions
828
+ - action_masks
829
+ - img_masks
830
+ - frame_masks
831
+ - embodiment_ids
832
+ - raw_action_dim
833
+ - conditioning_fps
834
+ - action_fps
835
+ meta_keys:
836
+ - text_token_ids
837
+ - sequence_plan
838
+ - task_description
839
+ - stats
840
+ - info
841
+ - timestamp
842
+ - viewpoint
843
+ type: DictCollator
844
+ enable_gradient_checkpointing: true
845
+ enable_mixed_precision_training: true
846
+ grad_accumulation_steps: 1
847
+ lr_scheduler:
848
+ type: linear-warmup+linear-decay
849
+ warmup_steps: 500
850
+ max_epochs: 8
851
+ max_grad_norm: 1.0
852
+ max_keep_ckpts: 3
853
+ max_steps: null
854
+ metric:
855
+ active_trackers:
856
+ - jsonl
857
+ - wandb
858
+ grad_accumulation_steps: 1
859
+ run_dir: work_dirs
860
+ type: VLAMetric
861
+ window_size: 1
862
+ mixed_precision_dtype: bf16
863
+ optimizer:
864
+ betas:
865
+ - 0.9
866
+ - 0.99
867
+ eps: 1.0e-08
868
+ exclude_1d_from_weight_decay: false
869
+ fused: true
870
+ lr: 5.0e-05
871
+ paramwise_learning_rate:
872
+ action_in_proj.: 0.00025
873
+ action_modality_embed: 0.00025
874
+ action_out_proj.: 0.00025
875
+ type: AdamW
876
+ weight_decay: 0.05
877
+ sampler: null
878
+ save_epoch_interval: 1
879
+ save_iter_interval: 500
880
+ sharding_strategy: full-shard
881
+ tokenizer:
882
+ model_max_length: 4096
883
+ model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
884
+ padding_side: right
885
+ trust_remote_code: true
886
+ type: PretrainedTokenizer
887
+ type: FSDPTrainRunner
888
+ seed: 7
889
+ train_dataloader:
890
+ dataset:
891
+ datasets:
892
+ action_key: action
893
+ action_window_size: 32
894
+ data_root_path:
895
+ - ./datasets/robotwin_clean_lerobotv2.1
896
+ - ./datasets/robotwin_randomized_lerobotv2.1
897
+ frame_window_size: 33
898
+ require_full_window: true
899
+ statistic_name: robotwin_all
900
+ transforms:
901
+ - embodiment_id: 21
902
+ name_mappings:
903
+ actions:
904
+ - actions
905
+ observation.state:
906
+ - states
907
+ parquet_keys:
908
+ - observation.state
909
+ - timestamp
910
+ - actions
911
+ - info
912
+ - stats
913
+ - action_masks
914
+ type: ProcessParquetInputs
915
+ video_keys:
916
+ - observation.images.cam_high
917
+ - observation.images.cam_left_wrist
918
+ - observation.images.cam_right_wrist
919
+ - height: 256
920
+ type: ResizeImages
921
+ width: 256
922
+ - brightness_range:
923
+ - 0.7
924
+ - 1.3
925
+ contrast_range:
926
+ - 0.6
927
+ - 1.4
928
+ crop_ratio:
929
+ - 1.0
930
+ - 1.0
931
+ crop_scale:
932
+ - 0.95
933
+ - 0.95
934
+ hue_delta: 0.08
935
+ prob: 1.0
936
+ rotation_range: 0.0
937
+ saturation_range:
938
+ - 0.5
939
+ - 1.5
940
+ type: AugVideo
941
+ - action_metadata:
942
+ append_viewpoint: false
943
+ conditioning_fps: 15.0
944
+ frame_window_size: 33
945
+ video_height: 384
946
+ video_width: 256
947
+ cfg_dropout_rate: 0.1
948
+ max_len: 512
949
+ tokenizer:
950
+ model_max_length: 4096
951
+ model_path: ./checkpoints/Cosmos3-Nano/text_tokenizer
952
+ padding_side: right
953
+ trust_remote_code: true
954
+ type: PretrainedTokenizer
955
+ type: ProcessCosmos3Prompt
956
+ - type: SimpleNormalizeImages
957
+ - action_dim: 64
958
+ action_key: action
959
+ norm_type: mean_std
960
+ state_dim: 64
961
+ state_key: proprio
962
+ type: NormalizeStatesAndActions
963
+ - conditioning_fps: 15.0
964
+ frame_window_size: 33
965
+ mode: wam
966
+ prepend_state_to_action: true
967
+ raw_action_dim: 14
968
+ type: BuildCosmos3Sequence
969
+ - bottom_height_ratio: 0.5
970
+ bottom_views:
971
+ - 1
972
+ - 2
973
+ frame_window_size: 33
974
+ num_views: 3
975
+ tile_direction: top_bottom_pair
976
+ top_view: 0
977
+ type: PrepareVideo
978
+ type: ParquetDataset
979
+ use_delta: false
980
+ window_start_idx: 0
981
+ name_mappings:
982
+ action:
983
+ - action
984
+ observation.state:
985
+ - proprio
986
+ statistic_keys:
987
+ - observation.state
988
+ - timestamp
989
+ - action
990
+ statistic_name: robotwin_all
991
+ type: DistributedRepeatingDataset
992
+ per_device_batch_size: 16
993
+ per_device_num_workers: 4
994
+ prefetch_factor: 1
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/dataset_statistics.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "robotwin_all": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.23836564500637852,
6
+ 1.129817402830952,
7
+ 0.8068359079301254,
8
+ -0.31024214960817226,
9
+ 0.05489044029082383,
10
+ -0.03797947365911228,
11
+ 0.6655638025405416,
12
+ 0.21664742843549212,
13
+ 1.0790448055651551,
14
+ 0.7875585893326063,
15
+ -0.3211320959513645,
16
+ -0.017501951884490514,
17
+ 0.03539706856287519,
18
+ 0.6794509037859313
19
+ ],
20
+ "std": [
21
+ 0.41515260848742136,
22
+ 1.0045809755922652,
23
+ 0.7768178536932145,
24
+ 0.6732816910017168,
25
+ 0.2708186547486596,
26
+ 0.6197771059972782,
27
+ 0.45465163653888563,
28
+ 0.34920798291604505,
29
+ 1.0249604849195586,
30
+ 0.794372303822,
31
+ 0.6847885016239902,
32
+ 0.24437403723179849,
33
+ 0.6142938232023921,
34
+ 0.44978408667126524
35
+ ],
36
+ "min": [
37
+ -7.552278995513916,
38
+ -0.36354875564575195,
39
+ -0.18577136099338531,
40
+ -1.956291913986206,
41
+ -1.6801013946533203,
42
+ -7.678869724273682,
43
+ 0.0,
44
+ -8.539926528930664,
45
+ -0.6294453740119934,
46
+ -0.07775841653347015,
47
+ -2.1328067779541016,
48
+ -2.1285502910614014,
49
+ -8.228925704956055,
50
+ 0.0
51
+ ],
52
+ "max": [
53
+ 6.45659065246582,
54
+ 4.179152488708496,
55
+ 5.346591472625732,
56
+ 1.7942548990249634,
57
+ 1.8604620695114136,
58
+ 5.43813943862915,
59
+ 1.0,
60
+ 7.142920017242432,
61
+ 4.157068729400635,
62
+ 5.672450065612793,
63
+ 1.95806884765625,
64
+ 1.5663840770721436,
65
+ 5.278968811035156,
66
+ 1.0
67
+ ],
68
+ "q01": null,
69
+ "q99": null
70
+ },
71
+ "timestamp": {
72
+ "mean": [
73
+ 9.822102670522625
74
+ ],
75
+ "std": [
76
+ 8.539596174071674
77
+ ],
78
+ "min": [
79
+ 0.0
80
+ ],
81
+ "max": [
82
+ 72.2
83
+ ],
84
+ "q01": null,
85
+ "q99": null
86
+ },
87
+ "action": {
88
+ "mean": [
89
+ -0.23943633195674233,
90
+ 1.1345611370099242,
91
+ 0.8102948556347407,
92
+ -0.31155664203396427,
93
+ 0.055179529382087596,
94
+ -0.03851684881837727,
95
+ 0.6643150995848328,
96
+ 0.2180408921138067,
97
+ 1.084594298787433,
98
+ 0.7916076777904834,
99
+ -0.3226336790356457,
100
+ -0.017651344197297695,
101
+ 0.036046095670276106,
102
+ 0.6783459021336998
103
+ ],
104
+ "std": [
105
+ 0.41571822839412337,
106
+ 1.0039769594416716,
107
+ 0.776858413838075,
108
+ 0.6748144778640579,
109
+ 0.271547410486253,
110
+ 0.6218771922320094,
111
+ 0.4551044161133153,
112
+ 0.3498656750012986,
113
+ 1.024847904429167,
114
+ 0.7946977748066826,
115
+ 0.6867041229584827,
116
+ 0.24531770744314874,
117
+ 0.6170235462820901,
118
+ 0.4502233751205138
119
+ ],
120
+ "min": [
121
+ -7.552278995513916,
122
+ -0.36354875564575195,
123
+ -0.18577136099338531,
124
+ -1.956291913986206,
125
+ -1.6801013946533203,
126
+ -7.678869724273682,
127
+ 0.0,
128
+ -8.539926528930664,
129
+ -0.6294453740119934,
130
+ -0.07775841653347015,
131
+ -2.1328067779541016,
132
+ -2.1285502910614014,
133
+ -8.228925704956055,
134
+ 0.0
135
+ ],
136
+ "max": [
137
+ 6.45659065246582,
138
+ 4.179152488708496,
139
+ 5.346591472625732,
140
+ 1.7942548990249634,
141
+ 1.8604620695114136,
142
+ 5.43813943862915,
143
+ 1.0,
144
+ 7.142920017242432,
145
+ 4.157068729400635,
146
+ 5.672450065612793,
147
+ 1.95806884765625,
148
+ 1.5663840770721436,
149
+ 5.278968811035156,
150
+ 1.0
151
+ ],
152
+ "q01": null,
153
+ "q99": null
154
+ }
155
+ }
156
+ }
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/added_tokens.json ADDED
@@ -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
+ }
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/chat_template.jinja ADDED
@@ -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 %}
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/special_tokens_map.json ADDED
@@ -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
+ }
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/tokenizer_config.json ADDED
@@ -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
+ }
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cosmos3_nano_robotwin_all_data_full_finetune_bs1024/vlm_backbone_config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token_id": 151655,
3
+ "model_type": "qwen3_vl",
4
+ "text_config": {
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 262144,
53
+ "model_type": "qwen3_vl_text",
54
+ "num_attention_heads": 32,
55
+ "num_hidden_layers": 36,
56
+ "num_key_value_heads": 8,
57
+ "packed_attention_backend": "flash2",
58
+ "pad_token_id": 0,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_parameters": {
61
+ "mrope_interleaved": true,
62
+ "mrope_section": [
63
+ 24,
64
+ 20,
65
+ 20
66
+ ],
67
+ "rope_theta": 5000000,
68
+ "rope_type": "default"
69
+ },
70
+ "tie_word_embeddings": false,
71
+ "use_cache": true,
72
+ "vocab_size": 151936
73
+ },
74
+ "tie_word_embeddings": false,
75
+ "transformers_version": "5.3.0",
76
+ "video_token_id": 151656,
77
+ "vision_config": {
78
+ "deepstack_visual_indexes": [
79
+ 8,
80
+ 16,
81
+ 24
82
+ ],
83
+ "depth": 27,
84
+ "hidden_act": "gelu_pytorch_tanh",
85
+ "hidden_size": 1152,
86
+ "in_channels": 3,
87
+ "initializer_range": 0.02,
88
+ "intermediate_size": 4304,
89
+ "model_type": "qwen3_vl",
90
+ "num_heads": 16,
91
+ "num_position_embeddings": 2304,
92
+ "out_hidden_size": 4096,
93
+ "patch_size": 16,
94
+ "spatial_merge_size": 2,
95
+ "temporal_patch_size": 2
96
+ },
97
+ "vision_end_token_id": 151653,
98
+ "vision_start_token_id": 151652,
99
+ "vocab_size": 151936
100
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/checkpoints/step-129501-epoch-03-loss=0.1024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e7d66477a8f6cb32750958ea9eebefcc8c149bfb3a73025025a792d6433a8a
3
+ size 25727629118
dit4dit_robotwin_all_data_full_finetune_bs256/config.json ADDED
@@ -0,0 +1,549 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_DATA_ROOTS": [
3
+ "datasets/robotwin_clean_lerobotv2.1",
4
+ "datasets/robotwin_randomized_lerobotv2.1"
5
+ ],
6
+ "_TASK_LIST": [
7
+ "adjust_bottle",
8
+ "beat_block_hammer",
9
+ "blocks_ranking_rgb",
10
+ "blocks_ranking_size",
11
+ "click_alarmclock",
12
+ "click_bell",
13
+ "dump_bin_bigbin",
14
+ "grab_roller",
15
+ "handover_block",
16
+ "handover_mic",
17
+ "hanging_mug",
18
+ "lift_pot",
19
+ "move_can_pot",
20
+ "move_pillbottle_pad",
21
+ "move_playingcard_away",
22
+ "move_stapler_pad",
23
+ "open_laptop",
24
+ "open_microwave",
25
+ "pick_diverse_bottles",
26
+ "pick_dual_bottles",
27
+ "place_a2b_left",
28
+ "place_a2b_right",
29
+ "place_bread_basket",
30
+ "place_bread_skillet",
31
+ "place_burger_fries",
32
+ "place_can_basket",
33
+ "place_cans_plasticbox",
34
+ "place_container_plate",
35
+ "place_dual_shoes",
36
+ "place_empty_cup",
37
+ "place_fan",
38
+ "place_mouse_pad",
39
+ "place_object_basket",
40
+ "place_object_scale",
41
+ "place_object_stand",
42
+ "place_phone_stand",
43
+ "place_shoe",
44
+ "press_stapler",
45
+ "put_bottles_dustbin",
46
+ "put_object_cabinet",
47
+ "rotate_qrcode",
48
+ "scan_object",
49
+ "shake_bottle",
50
+ "shake_bottle_horizontally",
51
+ "stack_blocks_three",
52
+ "stack_blocks_two",
53
+ "stack_bowls_three",
54
+ "stack_bowls_two",
55
+ "stamp_seal",
56
+ "turn_switch"
57
+ ],
58
+ "_TOKENIZER_PATH": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
59
+ "eval": {
60
+ "dataset": {
61
+ "img_keys": [
62
+ "cam_high",
63
+ "cam_left_wrist",
64
+ "cam_right_wrist"
65
+ ],
66
+ "inject_model_path": false,
67
+ "transforms": [
68
+ {
69
+ "input_key": "task_description",
70
+ "remove_input_key": true,
71
+ "tokenizer": {
72
+ "model_max_length": 512,
73
+ "model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
74
+ "type": "PretrainedTokenizer"
75
+ },
76
+ "type": "ProcessCosmos25Prompt"
77
+ },
78
+ {
79
+ "backend": "torch",
80
+ "height": 224,
81
+ "output_layout": "flattened_chw",
82
+ "scale_divisor": 255.0,
83
+ "type": "ResizeImages",
84
+ "width": 224
85
+ },
86
+ {
87
+ "means": [
88
+ 0.5,
89
+ 0.5,
90
+ 0.5
91
+ ],
92
+ "stds": [
93
+ 0.5,
94
+ 0.5,
95
+ 0.5
96
+ ],
97
+ "type": "NormalizeImages"
98
+ },
99
+ {
100
+ "bottom_height_ratio": 0.5,
101
+ "bottom_views": [
102
+ 1,
103
+ 2
104
+ ],
105
+ "combine_view_masks": true,
106
+ "frame_window_size": 1,
107
+ "num_views": 3,
108
+ "tile_direction": "top_bottom_pair",
109
+ "top_view": 0,
110
+ "type": "PrepareVideo"
111
+ },
112
+ {
113
+ "backend": "torch",
114
+ "expand_axis": 0,
115
+ "interleave": true,
116
+ "keys": [
117
+ "states"
118
+ ],
119
+ "target_dims": {
120
+ "states": 32
121
+ },
122
+ "type": "SinCosKeys"
123
+ },
124
+ {
125
+ "action_dim": 16,
126
+ "action_key": "action",
127
+ "norm_type": "min_max",
128
+ "normalization_epsilon": 1e-06,
129
+ "output_dtype": "float32",
130
+ "state_dim": null,
131
+ "state_key": "proprio",
132
+ "state_norm_type": "none",
133
+ "type": "NormalizeStatesAndActions"
134
+ },
135
+ {
136
+ "action_horizon": 32,
137
+ "state_history_length": 1,
138
+ "type": "PrepareStateActionTargets",
139
+ "valid_action_dim": 14
140
+ }
141
+ ],
142
+ "type": "PrivateInferenceDataset"
143
+ },
144
+ "denormalize_action": {
145
+ "action_dim": 14,
146
+ "norm_type": "min_max",
147
+ "statistic_name": "robotwin_all",
148
+ "type": "DenormalizePrivateAction"
149
+ },
150
+ "eval_chunk_size": 24,
151
+ "instruction_type": "unseen",
152
+ "mixed_precision_dtype": "bf16",
153
+ "model_family": "dit4dit",
154
+ "num_trials_per_task": 100,
155
+ "seed": 7,
156
+ "task_list": [
157
+ "adjust_bottle",
158
+ "beat_block_hammer",
159
+ "blocks_ranking_rgb",
160
+ "blocks_ranking_size",
161
+ "click_alarmclock",
162
+ "click_bell",
163
+ "dump_bin_bigbin",
164
+ "grab_roller",
165
+ "handover_block",
166
+ "handover_mic",
167
+ "hanging_mug",
168
+ "lift_pot",
169
+ "move_can_pot",
170
+ "move_pillbottle_pad",
171
+ "move_playingcard_away",
172
+ "move_stapler_pad",
173
+ "open_laptop",
174
+ "open_microwave",
175
+ "pick_diverse_bottles",
176
+ "pick_dual_bottles",
177
+ "place_a2b_left",
178
+ "place_a2b_right",
179
+ "place_bread_basket",
180
+ "place_bread_skillet",
181
+ "place_burger_fries",
182
+ "place_can_basket",
183
+ "place_cans_plasticbox",
184
+ "place_container_plate",
185
+ "place_dual_shoes",
186
+ "place_empty_cup",
187
+ "place_fan",
188
+ "place_mouse_pad",
189
+ "place_object_basket",
190
+ "place_object_scale",
191
+ "place_object_stand",
192
+ "place_phone_stand",
193
+ "place_shoe",
194
+ "press_stapler",
195
+ "put_bottles_dustbin",
196
+ "put_object_cabinet",
197
+ "rotate_qrcode",
198
+ "scan_object",
199
+ "shake_bottle",
200
+ "shake_bottle_horizontally",
201
+ "stack_blocks_three",
202
+ "stack_blocks_two",
203
+ "stack_bowls_three",
204
+ "stack_bowls_two",
205
+ "stamp_seal",
206
+ "turn_switch"
207
+ ],
208
+ "task_suite_name": [
209
+ "clean",
210
+ "random"
211
+ ],
212
+ "type": "RobotwinEvalRunner",
213
+ "unnorm_key": "robotwin_all"
214
+ },
215
+ "inference_model": {
216
+ "freeze_vlm_backbone": false,
217
+ "init_empty_weights": true,
218
+ "repeated_diffusion_steps": 4,
219
+ "type": "DiT4DiTVLA",
220
+ "vla_head": {
221
+ "action_dim": 16,
222
+ "action_horizon": 32,
223
+ "action_model_type": "DiT-B",
224
+ "add_pos_embed": true,
225
+ "diffusion_model_cfg": {
226
+ "cross_attention_dim": 2048,
227
+ "dropout": 0.2,
228
+ "final_dropout": true,
229
+ "interleave_self_attention": true,
230
+ "norm_type": "ada_norm",
231
+ "num_layers": 16,
232
+ "output_dim": 2560,
233
+ "positional_embeddings": null
234
+ },
235
+ "future_action_window_size": 31,
236
+ "hidden_size": 2560,
237
+ "max_seq_len": 1024,
238
+ "noise_beta_alpha": 1.5,
239
+ "noise_beta_beta": 1.0,
240
+ "noise_s": 0.999,
241
+ "num_inference_timesteps": 4,
242
+ "num_timestep_buckets": 1000,
243
+ "ori_action_dim": 14,
244
+ "state_dim": 32,
245
+ "type": "DiT4DiTActionHead"
246
+ },
247
+ "vlm_backbone": {
248
+ "base_model": "./checkpoints/Cosmos-Predict2.5-2B",
249
+ "conditional_frame_timestep": 0.0001,
250
+ "detach_hidden_states": true,
251
+ "extract_layer": 17,
252
+ "fixed_seed": null,
253
+ "flow_matching_high_sigma_min": null,
254
+ "flow_matching_high_sigma_ratio": null,
255
+ "flow_matching_time_distribution": "uniform",
256
+ "frozen_submodules": [
257
+ "text_encoder",
258
+ "vae"
259
+ ],
260
+ "fsdp_min_num_params": 0,
261
+ "future_loss_type": "flow_matching",
262
+ "load_pretrained_weights": false,
263
+ "local_files_only": true,
264
+ "num_frames_out": 9,
265
+ "num_inference_steps": 1,
266
+ "revision": "diffusers/base/post-trained",
267
+ "split_future_frames": true,
268
+ "torch_dtype": "bf16",
269
+ "trainable": true,
270
+ "type": "Cosmos25Backbone"
271
+ }
272
+ },
273
+ "model": {
274
+ "freeze_vlm_backbone": false,
275
+ "repeated_diffusion_steps": 4,
276
+ "type": "DiT4DiTVLA",
277
+ "vla_head": {
278
+ "action_dim": 16,
279
+ "action_horizon": 32,
280
+ "action_model_type": "DiT-B",
281
+ "add_pos_embed": true,
282
+ "diffusion_model_cfg": {
283
+ "cross_attention_dim": 2048,
284
+ "dropout": 0.2,
285
+ "final_dropout": true,
286
+ "interleave_self_attention": true,
287
+ "norm_type": "ada_norm",
288
+ "num_layers": 16,
289
+ "output_dim": 2560,
290
+ "positional_embeddings": null
291
+ },
292
+ "future_action_window_size": 31,
293
+ "hidden_size": 2560,
294
+ "max_seq_len": 1024,
295
+ "noise_beta_alpha": 1.5,
296
+ "noise_beta_beta": 1.0,
297
+ "noise_s": 0.999,
298
+ "num_inference_timesteps": 4,
299
+ "num_timestep_buckets": 1000,
300
+ "ori_action_dim": 14,
301
+ "state_dim": 32,
302
+ "type": "DiT4DiTActionHead"
303
+ },
304
+ "vlm_backbone": {
305
+ "base_model": "./checkpoints/Cosmos-Predict2.5-2B",
306
+ "conditional_frame_timestep": 0.0001,
307
+ "detach_hidden_states": true,
308
+ "extract_layer": 17,
309
+ "fixed_seed": null,
310
+ "flow_matching_high_sigma_min": null,
311
+ "flow_matching_high_sigma_ratio": null,
312
+ "flow_matching_time_distribution": "uniform",
313
+ "frozen_submodules": [
314
+ "text_encoder",
315
+ "vae"
316
+ ],
317
+ "fsdp_min_num_params": 0,
318
+ "future_loss_type": "flow_matching",
319
+ "local_files_only": true,
320
+ "num_frames_out": 9,
321
+ "num_inference_steps": 1,
322
+ "revision": "diffusers/base/post-trained",
323
+ "split_future_frames": true,
324
+ "torch_dtype": "bf16",
325
+ "trainable": true,
326
+ "type": "Cosmos25Backbone"
327
+ }
328
+ },
329
+ "runner": {
330
+ "change_key_name": false,
331
+ "collator": {
332
+ "keys": [
333
+ "states",
334
+ "timestamp",
335
+ "images",
336
+ "img_masks",
337
+ "actions",
338
+ "action_masks",
339
+ "frame_masks",
340
+ "lang_tokens",
341
+ "lang_masks"
342
+ ],
343
+ "meta_keys": [
344
+ "info",
345
+ "stats"
346
+ ],
347
+ "type": "DictCollator"
348
+ },
349
+ "enable_gradient_checkpointing": false,
350
+ "enable_mixed_precision_training": true,
351
+ "grad_accumulation_steps": 1,
352
+ "lr_scheduler": {
353
+ "min_lr": 5e-07,
354
+ "type": "linear-warmup+cosine-decay",
355
+ "warmup_ratio": 0.05
356
+ },
357
+ "max_epochs": 3,
358
+ "max_grad_norm": 1.0,
359
+ "max_keep_ckpts": 3,
360
+ "max_steps": null,
361
+ "metric": {
362
+ "active_trackers": [
363
+ "jsonl",
364
+ "wandb"
365
+ ],
366
+ "grad_accumulation_steps": 1,
367
+ "run_dir": "work_dirs",
368
+ "type": "VLAMetric",
369
+ "window_size": 100
370
+ },
371
+ "mixed_precision_dtype": "bf16",
372
+ "optimizer": {
373
+ "betas": [
374
+ 0.9,
375
+ 0.95
376
+ ],
377
+ "eps": 1e-08,
378
+ "lr": 3e-05,
379
+ "paramwise_learning_rate": {
380
+ "vla_head": 0.0001,
381
+ "vlm_backbone.transformer": 1e-05
382
+ },
383
+ "type": "AdamW",
384
+ "weight_decay": 1e-08,
385
+ "weight_decay_all_params": true
386
+ },
387
+ "pre_fsdp_param_dtype": "fp32",
388
+ "reduce_in_full_precision": false,
389
+ "sampler": null,
390
+ "save_epoch_interval": 1,
391
+ "save_iter_interval": 10000000,
392
+ "seed": 42,
393
+ "sharding_strategy": "global-shard-grad-op",
394
+ "tokenizer": {
395
+ "model_max_length": 512,
396
+ "model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
397
+ "type": "PretrainedTokenizer"
398
+ },
399
+ "type": "FSDPTrainRunner"
400
+ },
401
+ "train_dataloader": {
402
+ "dataset": {
403
+ "auto_compute_statistics": {
404
+ "profile": "absolute"
405
+ },
406
+ "dataset_statistics_path": "/mnt/data/cpfs/mnt/data/william/robotwin/work_dirs/dit4dit_robotwin_horizion32_exec24/dataset_statistics.json",
407
+ "datasets": {
408
+ "action_key": "action",
409
+ "action_window_size": 32,
410
+ "data_root_path": [
411
+ "datasets/robotwin_clean_lerobotv2.1",
412
+ "datasets/robotwin_randomized_lerobotv2.1"
413
+ ],
414
+ "frame_sample_stride": 4,
415
+ "frame_window_size": 9,
416
+ "statistic_name": "robotwin_all",
417
+ "supervise_terminal_padding": true,
418
+ "transforms": [
419
+ {
420
+ "name_mappings": {
421
+ "actions": [
422
+ "actions"
423
+ ],
424
+ "observation.state": [
425
+ "states"
426
+ ]
427
+ },
428
+ "parquet_keys": [
429
+ "observation.state",
430
+ "timestamp",
431
+ "actions",
432
+ "info",
433
+ "stats",
434
+ "action_masks"
435
+ ],
436
+ "type": "ProcessParquetInputs",
437
+ "video_backend": "pyav",
438
+ "video_keys": [
439
+ "observation.images.cam_high",
440
+ "observation.images.cam_left_wrist",
441
+ "observation.images.cam_right_wrist"
442
+ ]
443
+ },
444
+ {
445
+ "input_key": "task_description",
446
+ "remove_input_key": true,
447
+ "tokenizer": {
448
+ "model_max_length": 512,
449
+ "model_path": "./checkpoints/Cosmos-Predict2.5-2B/tokenizer",
450
+ "type": "PretrainedTokenizer"
451
+ },
452
+ "type": "ProcessCosmos25Prompt"
453
+ },
454
+ {
455
+ "backend": "torch",
456
+ "height": 224,
457
+ "output_layout": "flattened_chw",
458
+ "scale_divisor": 255.0,
459
+ "type": "ResizeImages",
460
+ "width": 224
461
+ },
462
+ {
463
+ "means": [
464
+ 0.5,
465
+ 0.5,
466
+ 0.5
467
+ ],
468
+ "stds": [
469
+ 0.5,
470
+ 0.5,
471
+ 0.5
472
+ ],
473
+ "type": "NormalizeImages"
474
+ },
475
+ {
476
+ "bottom_height_ratio": 0.5,
477
+ "bottom_views": [
478
+ 1,
479
+ 2
480
+ ],
481
+ "combine_view_masks": true,
482
+ "frame_window_size": 9,
483
+ "num_views": 3,
484
+ "tile_direction": "top_bottom_pair",
485
+ "top_view": 0,
486
+ "type": "PrepareVideo"
487
+ },
488
+ {
489
+ "backend": "torch",
490
+ "expand_axis": 0,
491
+ "interleave": true,
492
+ "keys": [
493
+ "states"
494
+ ],
495
+ "target_dims": {
496
+ "states": 32
497
+ },
498
+ "type": "SinCosKeys"
499
+ },
500
+ {
501
+ "action_dim": 16,
502
+ "action_key": "action",
503
+ "norm_type": "min_max",
504
+ "normalization_epsilon": 1e-06,
505
+ "output_dtype": "float32",
506
+ "state_dim": null,
507
+ "state_key": "proprio",
508
+ "state_norm_type": "none",
509
+ "type": "NormalizeStatesAndActions"
510
+ },
511
+ {
512
+ "action_horizon": 32,
513
+ "state_history_length": 1,
514
+ "type": "PrepareStateActionTargets",
515
+ "valid_action_dim": 14
516
+ }
517
+ ],
518
+ "type": "ParquetDataset",
519
+ "use_delta": false,
520
+ "window_start_idx": 0
521
+ },
522
+ "name_mappings": {
523
+ "action": [
524
+ "action"
525
+ ],
526
+ "observation.state": [
527
+ "proprio"
528
+ ]
529
+ },
530
+ "reshuffle_each_epoch": true,
531
+ "sampling_unit": "episode",
532
+ "sampling_weights": [
533
+ 1.0,
534
+ 1.0
535
+ ],
536
+ "seed": 42,
537
+ "shuffle": true,
538
+ "statistic_keys": [
539
+ "observation.state",
540
+ "timestamp",
541
+ "action"
542
+ ],
543
+ "statistic_name": "robotwin_all",
544
+ "type": "DistributedBalancedRepeatingDataset"
545
+ },
546
+ "per_device_batch_size": 8,
547
+ "per_device_num_workers": 4
548
+ }
549
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/config.yaml ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _DATA_ROOTS:
2
+ - datasets/robotwin_clean_lerobotv2.1
3
+ - datasets/robotwin_randomized_lerobotv2.1
4
+ _TASK_LIST:
5
+ - adjust_bottle
6
+ - beat_block_hammer
7
+ - blocks_ranking_rgb
8
+ - blocks_ranking_size
9
+ - click_alarmclock
10
+ - click_bell
11
+ - dump_bin_bigbin
12
+ - grab_roller
13
+ - handover_block
14
+ - handover_mic
15
+ - hanging_mug
16
+ - lift_pot
17
+ - move_can_pot
18
+ - move_pillbottle_pad
19
+ - move_playingcard_away
20
+ - move_stapler_pad
21
+ - open_laptop
22
+ - open_microwave
23
+ - pick_diverse_bottles
24
+ - pick_dual_bottles
25
+ - place_a2b_left
26
+ - place_a2b_right
27
+ - place_bread_basket
28
+ - place_bread_skillet
29
+ - place_burger_fries
30
+ - place_can_basket
31
+ - place_cans_plasticbox
32
+ - place_container_plate
33
+ - place_dual_shoes
34
+ - place_empty_cup
35
+ - place_fan
36
+ - place_mouse_pad
37
+ - place_object_basket
38
+ - place_object_scale
39
+ - place_object_stand
40
+ - place_phone_stand
41
+ - place_shoe
42
+ - press_stapler
43
+ - put_bottles_dustbin
44
+ - put_object_cabinet
45
+ - rotate_qrcode
46
+ - scan_object
47
+ - shake_bottle
48
+ - shake_bottle_horizontally
49
+ - stack_blocks_three
50
+ - stack_blocks_two
51
+ - stack_bowls_three
52
+ - stack_bowls_two
53
+ - stamp_seal
54
+ - turn_switch
55
+ _TOKENIZER_PATH: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
56
+ eval:
57
+ dataset:
58
+ img_keys:
59
+ - cam_high
60
+ - cam_left_wrist
61
+ - cam_right_wrist
62
+ inject_model_path: false
63
+ transforms:
64
+ - input_key: task_description
65
+ remove_input_key: true
66
+ tokenizer:
67
+ model_max_length: 512
68
+ model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
69
+ type: PretrainedTokenizer
70
+ type: ProcessCosmos25Prompt
71
+ - backend: torch
72
+ height: 224
73
+ output_layout: flattened_chw
74
+ scale_divisor: 255.0
75
+ type: ResizeImages
76
+ width: 224
77
+ - means:
78
+ - 0.5
79
+ - 0.5
80
+ - 0.5
81
+ stds:
82
+ - 0.5
83
+ - 0.5
84
+ - 0.5
85
+ type: NormalizeImages
86
+ - bottom_height_ratio: 0.5
87
+ bottom_views:
88
+ - 1
89
+ - 2
90
+ combine_view_masks: true
91
+ frame_window_size: 1
92
+ num_views: 3
93
+ tile_direction: top_bottom_pair
94
+ top_view: 0
95
+ type: PrepareVideo
96
+ - backend: torch
97
+ expand_axis: 0
98
+ interleave: true
99
+ keys:
100
+ - states
101
+ target_dims:
102
+ states: 32
103
+ type: SinCosKeys
104
+ - action_dim: 16
105
+ action_key: action
106
+ norm_type: min_max
107
+ normalization_epsilon: 1.0e-06
108
+ output_dtype: float32
109
+ state_dim: null
110
+ state_key: proprio
111
+ state_norm_type: none
112
+ type: NormalizeStatesAndActions
113
+ - action_horizon: 32
114
+ state_history_length: 1
115
+ type: PrepareStateActionTargets
116
+ valid_action_dim: 14
117
+ type: PrivateInferenceDataset
118
+ denormalize_action:
119
+ action_dim: 14
120
+ norm_type: min_max
121
+ statistic_name: robotwin_all
122
+ type: DenormalizePrivateAction
123
+ eval_chunk_size: 24
124
+ instruction_type: unseen
125
+ mixed_precision_dtype: bf16
126
+ model_family: dit4dit
127
+ num_trials_per_task: 100
128
+ seed: 7
129
+ task_list:
130
+ - adjust_bottle
131
+ - beat_block_hammer
132
+ - blocks_ranking_rgb
133
+ - blocks_ranking_size
134
+ - click_alarmclock
135
+ - click_bell
136
+ - dump_bin_bigbin
137
+ - grab_roller
138
+ - handover_block
139
+ - handover_mic
140
+ - hanging_mug
141
+ - lift_pot
142
+ - move_can_pot
143
+ - move_pillbottle_pad
144
+ - move_playingcard_away
145
+ - move_stapler_pad
146
+ - open_laptop
147
+ - open_microwave
148
+ - pick_diverse_bottles
149
+ - pick_dual_bottles
150
+ - place_a2b_left
151
+ - place_a2b_right
152
+ - place_bread_basket
153
+ - place_bread_skillet
154
+ - place_burger_fries
155
+ - place_can_basket
156
+ - place_cans_plasticbox
157
+ - place_container_plate
158
+ - place_dual_shoes
159
+ - place_empty_cup
160
+ - place_fan
161
+ - place_mouse_pad
162
+ - place_object_basket
163
+ - place_object_scale
164
+ - place_object_stand
165
+ - place_phone_stand
166
+ - place_shoe
167
+ - press_stapler
168
+ - put_bottles_dustbin
169
+ - put_object_cabinet
170
+ - rotate_qrcode
171
+ - scan_object
172
+ - shake_bottle
173
+ - shake_bottle_horizontally
174
+ - stack_blocks_three
175
+ - stack_blocks_two
176
+ - stack_bowls_three
177
+ - stack_bowls_two
178
+ - stamp_seal
179
+ - turn_switch
180
+ task_suite_name:
181
+ - clean
182
+ - random
183
+ type: RobotwinEvalRunner
184
+ unnorm_key: robotwin_all
185
+ inference_model:
186
+ freeze_vlm_backbone: false
187
+ init_empty_weights: true
188
+ repeated_diffusion_steps: 4
189
+ type: DiT4DiTVLA
190
+ vla_head:
191
+ action_dim: 16
192
+ action_horizon: 32
193
+ action_model_type: DiT-B
194
+ add_pos_embed: true
195
+ diffusion_model_cfg:
196
+ cross_attention_dim: 2048
197
+ dropout: 0.2
198
+ final_dropout: true
199
+ interleave_self_attention: true
200
+ norm_type: ada_norm
201
+ num_layers: 16
202
+ output_dim: 2560
203
+ positional_embeddings: null
204
+ future_action_window_size: 31
205
+ hidden_size: 2560
206
+ max_seq_len: 1024
207
+ noise_beta_alpha: 1.5
208
+ noise_beta_beta: 1.0
209
+ noise_s: 0.999
210
+ num_inference_timesteps: 4
211
+ num_timestep_buckets: 1000
212
+ ori_action_dim: 14
213
+ state_dim: 32
214
+ type: DiT4DiTActionHead
215
+ vlm_backbone:
216
+ base_model: ./checkpoints/Cosmos-Predict2.5-2B
217
+ conditional_frame_timestep: 0.0001
218
+ detach_hidden_states: true
219
+ extract_layer: 17
220
+ fixed_seed: null
221
+ flow_matching_high_sigma_min: null
222
+ flow_matching_high_sigma_ratio: null
223
+ flow_matching_time_distribution: uniform
224
+ frozen_submodules:
225
+ - text_encoder
226
+ - vae
227
+ fsdp_min_num_params: 0
228
+ future_loss_type: flow_matching
229
+ load_pretrained_weights: false
230
+ local_files_only: true
231
+ num_frames_out: 9
232
+ num_inference_steps: 1
233
+ revision: diffusers/base/post-trained
234
+ split_future_frames: true
235
+ torch_dtype: bf16
236
+ trainable: true
237
+ type: Cosmos25Backbone
238
+ model:
239
+ freeze_vlm_backbone: false
240
+ repeated_diffusion_steps: 4
241
+ type: DiT4DiTVLA
242
+ vla_head:
243
+ action_dim: 16
244
+ action_horizon: 32
245
+ action_model_type: DiT-B
246
+ add_pos_embed: true
247
+ diffusion_model_cfg:
248
+ cross_attention_dim: 2048
249
+ dropout: 0.2
250
+ final_dropout: true
251
+ interleave_self_attention: true
252
+ norm_type: ada_norm
253
+ num_layers: 16
254
+ output_dim: 2560
255
+ positional_embeddings: null
256
+ future_action_window_size: 31
257
+ hidden_size: 2560
258
+ max_seq_len: 1024
259
+ noise_beta_alpha: 1.5
260
+ noise_beta_beta: 1.0
261
+ noise_s: 0.999
262
+ num_inference_timesteps: 4
263
+ num_timestep_buckets: 1000
264
+ ori_action_dim: 14
265
+ state_dim: 32
266
+ type: DiT4DiTActionHead
267
+ vlm_backbone:
268
+ base_model: ./checkpoints/Cosmos-Predict2.5-2B
269
+ conditional_frame_timestep: 0.0001
270
+ detach_hidden_states: true
271
+ extract_layer: 17
272
+ fixed_seed: null
273
+ flow_matching_high_sigma_min: null
274
+ flow_matching_high_sigma_ratio: null
275
+ flow_matching_time_distribution: uniform
276
+ frozen_submodules:
277
+ - text_encoder
278
+ - vae
279
+ fsdp_min_num_params: 0
280
+ future_loss_type: flow_matching
281
+ local_files_only: true
282
+ num_frames_out: 9
283
+ num_inference_steps: 1
284
+ revision: diffusers/base/post-trained
285
+ split_future_frames: true
286
+ torch_dtype: bf16
287
+ trainable: true
288
+ type: Cosmos25Backbone
289
+ runner:
290
+ change_key_name: false
291
+ collator:
292
+ keys:
293
+ - states
294
+ - timestamp
295
+ - images
296
+ - img_masks
297
+ - actions
298
+ - action_masks
299
+ - frame_masks
300
+ - lang_tokens
301
+ - lang_masks
302
+ meta_keys:
303
+ - info
304
+ - stats
305
+ type: DictCollator
306
+ enable_gradient_checkpointing: false
307
+ enable_mixed_precision_training: true
308
+ grad_accumulation_steps: 1
309
+ lr_scheduler:
310
+ min_lr: 5.0e-07
311
+ type: linear-warmup+cosine-decay
312
+ warmup_ratio: 0.05
313
+ max_epochs: 3
314
+ max_grad_norm: 1.0
315
+ max_keep_ckpts: 3
316
+ max_steps: null
317
+ metric:
318
+ active_trackers:
319
+ - jsonl
320
+ - wandb
321
+ grad_accumulation_steps: 1
322
+ run_dir: work_dirs
323
+ type: VLAMetric
324
+ window_size: 100
325
+ mixed_precision_dtype: bf16
326
+ optimizer:
327
+ betas:
328
+ - 0.9
329
+ - 0.95
330
+ eps: 1.0e-08
331
+ lr: 3.0e-05
332
+ paramwise_learning_rate:
333
+ vla_head: 0.0001
334
+ vlm_backbone.transformer: 1.0e-05
335
+ type: AdamW
336
+ weight_decay: 1.0e-08
337
+ weight_decay_all_params: true
338
+ pre_fsdp_param_dtype: fp32
339
+ reduce_in_full_precision: false
340
+ sampler: null
341
+ save_epoch_interval: 1
342
+ save_iter_interval: 10000000
343
+ seed: 42
344
+ sharding_strategy: global-shard-grad-op
345
+ tokenizer:
346
+ model_max_length: 512
347
+ model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
348
+ type: PretrainedTokenizer
349
+ type: FSDPTrainRunner
350
+ train_dataloader:
351
+ dataset:
352
+ auto_compute_statistics:
353
+ profile: absolute
354
+ dataset_statistics_path: /mnt/data/cpfs/mnt/data/william/robotwin/work_dirs/dit4dit_robotwin_horizion32_exec24/dataset_statistics.json
355
+ datasets:
356
+ action_key: action
357
+ action_window_size: 32
358
+ data_root_path:
359
+ - datasets/robotwin_clean_lerobotv2.1
360
+ - datasets/robotwin_randomized_lerobotv2.1
361
+ frame_sample_stride: 4
362
+ frame_window_size: 9
363
+ statistic_name: robotwin_all
364
+ supervise_terminal_padding: true
365
+ transforms:
366
+ - name_mappings:
367
+ actions:
368
+ - actions
369
+ observation.state:
370
+ - states
371
+ parquet_keys:
372
+ - observation.state
373
+ - timestamp
374
+ - actions
375
+ - info
376
+ - stats
377
+ - action_masks
378
+ type: ProcessParquetInputs
379
+ video_backend: pyav
380
+ video_keys:
381
+ - observation.images.cam_high
382
+ - observation.images.cam_left_wrist
383
+ - observation.images.cam_right_wrist
384
+ - input_key: task_description
385
+ remove_input_key: true
386
+ tokenizer:
387
+ model_max_length: 512
388
+ model_path: ./checkpoints/Cosmos-Predict2.5-2B/tokenizer
389
+ type: PretrainedTokenizer
390
+ type: ProcessCosmos25Prompt
391
+ - backend: torch
392
+ height: 224
393
+ output_layout: flattened_chw
394
+ scale_divisor: 255.0
395
+ type: ResizeImages
396
+ width: 224
397
+ - means:
398
+ - 0.5
399
+ - 0.5
400
+ - 0.5
401
+ stds:
402
+ - 0.5
403
+ - 0.5
404
+ - 0.5
405
+ type: NormalizeImages
406
+ - bottom_height_ratio: 0.5
407
+ bottom_views:
408
+ - 1
409
+ - 2
410
+ combine_view_masks: true
411
+ frame_window_size: 9
412
+ num_views: 3
413
+ tile_direction: top_bottom_pair
414
+ top_view: 0
415
+ type: PrepareVideo
416
+ - backend: torch
417
+ expand_axis: 0
418
+ interleave: true
419
+ keys:
420
+ - states
421
+ target_dims:
422
+ states: 32
423
+ type: SinCosKeys
424
+ - action_dim: 16
425
+ action_key: action
426
+ norm_type: min_max
427
+ normalization_epsilon: 1.0e-06
428
+ output_dtype: float32
429
+ state_dim: null
430
+ state_key: proprio
431
+ state_norm_type: none
432
+ type: NormalizeStatesAndActions
433
+ - action_horizon: 32
434
+ state_history_length: 1
435
+ type: PrepareStateActionTargets
436
+ valid_action_dim: 14
437
+ type: ParquetDataset
438
+ use_delta: false
439
+ window_start_idx: 0
440
+ name_mappings:
441
+ action:
442
+ - action
443
+ observation.state:
444
+ - proprio
445
+ reshuffle_each_epoch: true
446
+ sampling_unit: episode
447
+ sampling_weights:
448
+ - 1.0
449
+ - 1.0
450
+ seed: 42
451
+ shuffle: true
452
+ statistic_keys:
453
+ - observation.state
454
+ - timestamp
455
+ - action
456
+ statistic_name: robotwin_all
457
+ type: DistributedBalancedRepeatingDataset
458
+ per_device_batch_size: 8
459
+ per_device_num_workers: 4
dit4dit_robotwin_all_data_full_finetune_bs256/dataset_statistics.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "robotwin_all": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.23836578982314696,
6
+ 1.1298174457722125,
7
+ 0.8068365622397999,
8
+ -0.31024205976923314,
9
+ 0.05489046602657658,
10
+ -0.03797952133058626,
11
+ 0.6655638063536832,
12
+ 0.21664745657075993,
13
+ 1.0790455135726966,
14
+ 0.7875586714060262,
15
+ -0.3211318581147203,
16
+ -0.01750195667000284,
17
+ 0.03539713811747996,
18
+ 0.6794509068373863
19
+ ],
20
+ "std": [
21
+ 0.4151526770142024,
22
+ 1.004581002114008,
23
+ 0.7768177975025599,
24
+ 0.6732816994178228,
25
+ 0.27081867657629666,
26
+ 0.6197771066833538,
27
+ 0.454651637795559,
28
+ 0.34920797694011796,
29
+ 1.0249604576643263,
30
+ 0.7943722761565686,
31
+ 0.6847884512724388,
32
+ 0.24437404726809553,
33
+ 0.6142938396132972,
34
+ 0.44978408948808124
35
+ ],
36
+ "min": [
37
+ -7.552278995513916,
38
+ -0.36354875564575195,
39
+ -0.18577136099338531,
40
+ -1.956291913986206,
41
+ -1.6801013946533203,
42
+ -7.678869724273682,
43
+ 0.0,
44
+ -8.539926528930664,
45
+ -0.6294453740119934,
46
+ -0.07775841653347015,
47
+ -2.1328067779541016,
48
+ -2.1285502910614014,
49
+ -8.228925704956055,
50
+ 0.0
51
+ ],
52
+ "max": [
53
+ 6.45659065246582,
54
+ 4.179152488708496,
55
+ 5.346591472625732,
56
+ 1.7942548990249634,
57
+ 1.8604620695114136,
58
+ 5.43813943862915,
59
+ 1.0,
60
+ 7.142920017242432,
61
+ 4.157068729400635,
62
+ 5.672450065612793,
63
+ 1.95806884765625,
64
+ 1.5663840770721436,
65
+ 5.278968811035156,
66
+ 1.0
67
+ ],
68
+ "q01": [
69
+ -1.0126575303077698,
70
+ -5.257390398583084e-07,
71
+ -2.8215323254698887e-05,
72
+ -1.5635129809379578,
73
+ -0.6461568164825439,
74
+ -2.2244577407836914,
75
+ 0.0,
76
+ -0.1690114441514015,
77
+ 0.0,
78
+ -2.81171942333458e-05,
79
+ -1.6413878035545348,
80
+ -1.0220032143592834,
81
+ -1.6422083234786986,
82
+ 0.0
83
+ ],
84
+ "q99": [
85
+ 0.17374197930097574,
86
+ 2.602391481399536,
87
+ 2.4499925279617276,
88
+ 1.351163625717163,
89
+ 1.2348779439926147,
90
+ 1.6033015251159668,
91
+ 1.0,
92
+ 0.9967232346534729,
93
+ 2.6186706876754755,
94
+ 2.4520904397964403,
95
+ 1.291067123413086,
96
+ 0.8747973608970588,
97
+ 2.2670195341110118,
98
+ 1.0
99
+ ],
100
+ "count": 6075103
101
+ },
102
+ "action": {
103
+ "mean": [
104
+ -0.2520778376296883,
105
+ 1.1850720454152766,
106
+ 0.8463635513872634,
107
+ -0.32170768938995004,
108
+ 0.05836593476707814,
109
+ -0.047009579259007395,
110
+ 0.6459757061337159,
111
+ 0.23613831894636023,
112
+ 1.1499042732131481,
113
+ 0.8381827384224907,
114
+ -0.33540205675934687,
115
+ -0.01963055875970896,
116
+ 0.04568921604517659,
117
+ 0.6622663938976167
118
+ ],
119
+ "std": [
120
+ 0.4248377447940459,
121
+ 1.0055959718792558,
122
+ 0.7843761483314764,
123
+ 0.695804624051617,
124
+ 0.2812322261529959,
125
+ 0.6501131906725712,
126
+ 0.46179677530217805,
127
+ 0.3599664397795572,
128
+ 1.0307301365174235,
129
+ 0.8047042310821478,
130
+ 0.7142964613182307,
131
+ 0.25882870106807826,
132
+ 0.6546476377063773,
133
+ 0.45675020849497266
134
+ ],
135
+ "min": [
136
+ -7.552278995513916,
137
+ -0.36354875564575195,
138
+ -0.18577136099338531,
139
+ -1.956291913986206,
140
+ -1.6801013946533203,
141
+ -7.678869724273682,
142
+ 0.0,
143
+ -8.539926528930664,
144
+ -0.6294453740119934,
145
+ -0.07775841653347015,
146
+ -2.1328067779541016,
147
+ -2.1285502910614014,
148
+ -8.228925704956055,
149
+ 0.0
150
+ ],
151
+ "max": [
152
+ 6.45659065246582,
153
+ 4.179152488708496,
154
+ 5.346591472625732,
155
+ 1.7942548990249634,
156
+ 1.8604620695114136,
157
+ 5.43813943862915,
158
+ 1.0,
159
+ 7.142920017242432,
160
+ 4.157068729400635,
161
+ 5.672450065612793,
162
+ 1.95806884765625,
163
+ 1.5663840770721436,
164
+ 5.278968811035156,
165
+ 1.0
166
+ ],
167
+ "q01": [
168
+ -1.026803731918335,
169
+ -5.257390398583084e-07,
170
+ -2.8215323254698887e-05,
171
+ -1.5867787599563599,
172
+ -0.6817835569381714,
173
+ -2.2976155281066895,
174
+ 0.0,
175
+ -0.1809745579957962,
176
+ 0.0,
177
+ -2.81171942333458e-05,
178
+ -1.6533960103988647,
179
+ -1.0314260721206665,
180
+ -1.7116937637329102,
181
+ 0.0
182
+ ],
183
+ "q99": [
184
+ 0.20549810975792404,
185
+ 2.607667922973633,
186
+ 2.469137668609619,
187
+ 1.3703088760375977,
188
+ 1.2604563236236572,
189
+ 1.6216325759887695,
190
+ 1.0,
191
+ 1.0141181945800781,
192
+ 2.646111249923706,
193
+ 2.48582124710083,
194
+ 1.3271214962005615,
195
+ 0.9085489511489868,
196
+ 2.3036928176879883,
197
+ 1.0
198
+ ],
199
+ "count": 194403296
200
+ }
201
+ }
202
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/added_tokens.json ADDED
@@ -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
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/chat_template.jinja ADDED
@@ -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 %}
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/special_tokens_map.json ADDED
@@ -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
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer_config.json ADDED
@@ -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
+ }
dit4dit_robotwin_all_data_full_finetune_bs256/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
fastwam_robotwin_all_data_full_finetune_bs256/checkpoints/step-118655-epoch-05-loss=0.0985.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9729869925b6f6cf845aae9922f1a6d42821b949dba578eb202ac68a46e049e
3
+ size 24812972868
fastwam_robotwin_all_data_full_finetune_bs256/config.json ADDED
@@ -0,0 +1,538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_ACTION_DIM": 14,
3
+ "_ACTION_NORM_TYPE": "mean_std",
4
+ "_ACTION_WINDOW_SIZE": 32,
5
+ "_CKPT_ROOT": "./checkpoints",
6
+ "_FASTWAM_CHECKPOINT": "./checkpoints/fastwam_base_full/fastwam_base_full.safetensors",
7
+ "_FASTWAM_ROOT": "./checkpoints/fastwam_base_full",
8
+ "_FASTWAM_TOKENIZER": "./checkpoints/fastwam_base_full/tokenizer",
9
+ "_FRAME_SAMPLE_STRIDE": 4,
10
+ "_FRAME_WINDOW_SIZE": 9,
11
+ "_ROBOTWIN_DATA_ROOTS": [
12
+ "datasets/robotwin_clean_lerobotv2.1",
13
+ "datasets/robotwin_randomized_lerobotv2.1"
14
+ ],
15
+ "_ROBOTWIN_TASK_LIST": [
16
+ "adjust_bottle",
17
+ "beat_block_hammer",
18
+ "blocks_ranking_rgb",
19
+ "blocks_ranking_size",
20
+ "click_alarmclock",
21
+ "click_bell",
22
+ "dump_bin_bigbin",
23
+ "grab_roller",
24
+ "handover_block",
25
+ "handover_mic",
26
+ "hanging_mug",
27
+ "lift_pot",
28
+ "move_can_pot",
29
+ "move_pillbottle_pad",
30
+ "move_playingcard_away",
31
+ "move_stapler_pad",
32
+ "open_laptop",
33
+ "open_microwave",
34
+ "pick_diverse_bottles",
35
+ "pick_dual_bottles",
36
+ "place_a2b_left",
37
+ "place_a2b_right",
38
+ "place_bread_basket",
39
+ "place_bread_skillet",
40
+ "place_burger_fries",
41
+ "place_can_basket",
42
+ "place_cans_plasticbox",
43
+ "place_container_plate",
44
+ "place_dual_shoes",
45
+ "place_empty_cup",
46
+ "place_fan",
47
+ "place_mouse_pad",
48
+ "place_object_basket",
49
+ "place_object_scale",
50
+ "place_object_stand",
51
+ "place_phone_stand",
52
+ "place_shoe",
53
+ "press_stapler",
54
+ "put_bottles_dustbin",
55
+ "put_object_cabinet",
56
+ "rotate_qrcode",
57
+ "scan_object",
58
+ "shake_bottle",
59
+ "shake_bottle_horizontally",
60
+ "stack_blocks_three",
61
+ "stack_blocks_two",
62
+ "stack_bowls_three",
63
+ "stack_bowls_two",
64
+ "stamp_seal",
65
+ "turn_switch"
66
+ ],
67
+ "_STATE_DIM": 14,
68
+ "_STATISTIC_NAME": "robotwin_all",
69
+ "_TEXT_PROMPT_TEMPLATE": "A video recorded from a robot's point of view executing the following instruction: {task}",
70
+ "eval": {
71
+ "runner": {
72
+ "dataset": {
73
+ "img_keys": [
74
+ "cam_high",
75
+ "cam_left_wrist",
76
+ "cam_right_wrist"
77
+ ],
78
+ "transforms": [
79
+ {
80
+ "action_dim": 14,
81
+ "action_key": "action",
82
+ "norm_type": "mean_std",
83
+ "state_dim": 14,
84
+ "state_key": "proprio",
85
+ "type": "NormalizeStatesAndActions"
86
+ },
87
+ {
88
+ "max_len": 128,
89
+ "prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
90
+ "tokenizer": {
91
+ "model_path": "./checkpoints/fastwam_base_full/tokenizer",
92
+ "type": "PretrainedTokenizer"
93
+ },
94
+ "type": "LiberoPromptFromInputs",
95
+ "use_conversation": false
96
+ },
97
+ {
98
+ "height": 256,
99
+ "type": "ResizeImages",
100
+ "width": 320
101
+ },
102
+ {
103
+ "type": "SimpleNormalizeImages"
104
+ },
105
+ {
106
+ "bottom_height_ratio": 0.5,
107
+ "bottom_views": [
108
+ 1,
109
+ 2
110
+ ],
111
+ "frame_window_size": 1,
112
+ "num_views": 3,
113
+ "tile_direction": "top_bottom_pair",
114
+ "top_view": 0,
115
+ "type": "PrepareVideo"
116
+ }
117
+ ],
118
+ "type": "PrivateInferenceDataset"
119
+ },
120
+ "denormalize_action": {
121
+ "action_dim": 14,
122
+ "norm_type": "mean_std",
123
+ "type": "DenormalizePrivateAction"
124
+ },
125
+ "eval_chunk_size": 24,
126
+ "instruction_type": "unseen",
127
+ "mixed_precision_dtype": "bf16",
128
+ "model_family": "fastwam",
129
+ "num_trials_per_task": 100,
130
+ "save_video": false,
131
+ "seed": 42,
132
+ "task_list": [
133
+ "adjust_bottle",
134
+ "beat_block_hammer",
135
+ "blocks_ranking_rgb",
136
+ "blocks_ranking_size",
137
+ "click_alarmclock",
138
+ "click_bell",
139
+ "dump_bin_bigbin",
140
+ "grab_roller",
141
+ "handover_block",
142
+ "handover_mic",
143
+ "hanging_mug",
144
+ "lift_pot",
145
+ "move_can_pot",
146
+ "move_pillbottle_pad",
147
+ "move_playingcard_away",
148
+ "move_stapler_pad",
149
+ "open_laptop",
150
+ "open_microwave",
151
+ "pick_diverse_bottles",
152
+ "pick_dual_bottles",
153
+ "place_a2b_left",
154
+ "place_a2b_right",
155
+ "place_bread_basket",
156
+ "place_bread_skillet",
157
+ "place_burger_fries",
158
+ "place_can_basket",
159
+ "place_cans_plasticbox",
160
+ "place_container_plate",
161
+ "place_dual_shoes",
162
+ "place_empty_cup",
163
+ "place_fan",
164
+ "place_mouse_pad",
165
+ "place_object_basket",
166
+ "place_object_scale",
167
+ "place_object_stand",
168
+ "place_phone_stand",
169
+ "place_shoe",
170
+ "press_stapler",
171
+ "put_bottles_dustbin",
172
+ "put_object_cabinet",
173
+ "rotate_qrcode",
174
+ "scan_object",
175
+ "shake_bottle",
176
+ "shake_bottle_horizontally",
177
+ "stack_blocks_three",
178
+ "stack_blocks_two",
179
+ "stack_bowls_three",
180
+ "stack_bowls_two",
181
+ "stamp_seal",
182
+ "turn_switch"
183
+ ],
184
+ "task_suite_name": [
185
+ "clean",
186
+ "random"
187
+ ],
188
+ "type": "RobotwinEvalRunner",
189
+ "unnorm_key": "robotwin_all"
190
+ }
191
+ },
192
+ "eval_dataset": null,
193
+ "inference_model": {
194
+ "action_horizon": 32,
195
+ "frame_window_size": 9,
196
+ "mot_checkpoint_mixed_attn": true,
197
+ "num_views": 3,
198
+ "pretrained_name_or_path": "./checkpoints/fastwam_base_full/fastwam_base_full.safetensors",
199
+ "pretrained_skip_prefixes": [
200
+ "vla_head.mot.mixtures.action.action_encoder.",
201
+ "vla_head.mot.mixtures.action.head.",
202
+ "vla_head.proprio_encoder."
203
+ ],
204
+ "proprio_dim": 14,
205
+ "torch_dtype": "bf16",
206
+ "type": "FastWAMVLA",
207
+ "vla_head": {
208
+ "action_dit_config": {
209
+ "action_dim": 14,
210
+ "attn_head_dim": 128,
211
+ "eps": 1e-06,
212
+ "ffn_dim": 4096,
213
+ "freq_dim": 256,
214
+ "hidden_dim": 1024,
215
+ "num_heads": 24,
216
+ "num_layers": 30,
217
+ "text_dim": 4096,
218
+ "use_gradient_checkpointing": true
219
+ },
220
+ "action_scheduler": {
221
+ "infer_shift": 1.0,
222
+ "num_train_timesteps": 1000,
223
+ "train_shift": 1.0
224
+ },
225
+ "loss": {
226
+ "lambda_action": 1.0,
227
+ "lambda_video": 1.0
228
+ },
229
+ "type": "FastWAMHead",
230
+ "video_dit_config": {
231
+ "action_conditioned": false,
232
+ "action_dim": 14,
233
+ "action_group_causal_mask_mode": "group_diagonal",
234
+ "attn_head_dim": 128,
235
+ "eps": 1e-06,
236
+ "ffn_dim": 14336,
237
+ "freq_dim": 256,
238
+ "fuse_vae_embedding_in_latents": true,
239
+ "has_image_input": false,
240
+ "hidden_dim": 3072,
241
+ "in_dim": 48,
242
+ "num_heads": 24,
243
+ "num_layers": 30,
244
+ "out_dim": 48,
245
+ "patch_size": [
246
+ 1,
247
+ 2,
248
+ 2
249
+ ],
250
+ "require_clip_embedding": false,
251
+ "require_vae_embedding": false,
252
+ "seperated_timestep": true,
253
+ "text_dim": 4096,
254
+ "use_gradient_checkpointing": true,
255
+ "video_attention_mask_mode": "first_frame_causal"
256
+ },
257
+ "video_scheduler": {
258
+ "infer_shift": 5.0,
259
+ "num_train_timesteps": 1000,
260
+ "train_shift": 5.0
261
+ }
262
+ },
263
+ "vlm_backbone": {
264
+ "text_embed_cache_context_len": 128,
265
+ "text_embed_cache_device": "cpu",
266
+ "text_embed_cache_size": 256,
267
+ "type": "Wan22Backbone"
268
+ }
269
+ },
270
+ "model": {
271
+ "action_horizon": 32,
272
+ "frame_window_size": 9,
273
+ "mot_checkpoint_mixed_attn": true,
274
+ "num_views": 3,
275
+ "pretrained_name_or_path": "./checkpoints/fastwam_base_full/fastwam_base_full.safetensors",
276
+ "pretrained_skip_prefixes": [
277
+ "vla_head.mot.mixtures.action.action_encoder.",
278
+ "vla_head.mot.mixtures.action.head.",
279
+ "vla_head.proprio_encoder."
280
+ ],
281
+ "proprio_dim": 14,
282
+ "torch_dtype": "bf16",
283
+ "type": "FastWAMVLA",
284
+ "vla_head": {
285
+ "action_dit_config": {
286
+ "action_dim": 14,
287
+ "attn_head_dim": 128,
288
+ "eps": 1e-06,
289
+ "ffn_dim": 4096,
290
+ "freq_dim": 256,
291
+ "hidden_dim": 1024,
292
+ "num_heads": 24,
293
+ "num_layers": 30,
294
+ "text_dim": 4096,
295
+ "use_gradient_checkpointing": true
296
+ },
297
+ "action_scheduler": {
298
+ "infer_shift": 1.0,
299
+ "num_train_timesteps": 1000,
300
+ "train_shift": 1.0
301
+ },
302
+ "loss": {
303
+ "lambda_action": 1.0,
304
+ "lambda_video": 1.0
305
+ },
306
+ "type": "FastWAMHead",
307
+ "video_dit_config": {
308
+ "action_conditioned": false,
309
+ "action_dim": 14,
310
+ "action_group_causal_mask_mode": "group_diagonal",
311
+ "attn_head_dim": 128,
312
+ "eps": 1e-06,
313
+ "ffn_dim": 14336,
314
+ "freq_dim": 256,
315
+ "fuse_vae_embedding_in_latents": true,
316
+ "has_image_input": false,
317
+ "hidden_dim": 3072,
318
+ "in_dim": 48,
319
+ "num_heads": 24,
320
+ "num_layers": 30,
321
+ "out_dim": 48,
322
+ "patch_size": [
323
+ 1,
324
+ 2,
325
+ 2
326
+ ],
327
+ "require_clip_embedding": false,
328
+ "require_vae_embedding": false,
329
+ "seperated_timestep": true,
330
+ "text_dim": 4096,
331
+ "use_gradient_checkpointing": true,
332
+ "video_attention_mask_mode": "first_frame_causal"
333
+ },
334
+ "video_scheduler": {
335
+ "infer_shift": 5.0,
336
+ "num_train_timesteps": 1000,
337
+ "train_shift": 5.0
338
+ }
339
+ },
340
+ "vlm_backbone": {
341
+ "text_embed_cache_context_len": 128,
342
+ "text_embed_cache_device": "cpu",
343
+ "text_embed_cache_size": 256,
344
+ "type": "Wan22Backbone"
345
+ }
346
+ },
347
+ "runner": {
348
+ "collator": {
349
+ "keys": [
350
+ "states",
351
+ "images",
352
+ "img_masks",
353
+ "actions",
354
+ "action_masks",
355
+ "embodiment_ids",
356
+ "frame_masks",
357
+ "lang_tokens",
358
+ "lang_masks"
359
+ ],
360
+ "meta_keys": [
361
+ "task_description",
362
+ "info",
363
+ "stats",
364
+ "timestamp"
365
+ ],
366
+ "type": "DictCollator"
367
+ },
368
+ "dataset_sharding_strategy": "blockwise",
369
+ "enable_gradient_checkpointing": false,
370
+ "enable_mixed_precision_training": true,
371
+ "evaluator": {
372
+ "eval_every": 1000,
373
+ "num_inference_steps": 10,
374
+ "save_video": false,
375
+ "seed": 42,
376
+ "type": "training-eval",
377
+ "video_fps": 8
378
+ },
379
+ "grad_accumulation_steps": 1,
380
+ "lr_scheduler": {
381
+ "betas": [
382
+ 0.9,
383
+ 0.95
384
+ ],
385
+ "min_lr_ratio": 0.01,
386
+ "type": "linear-warmup+cosine-decay-min-lr",
387
+ "warmup_ratio": 0.05,
388
+ "weight_decay_style": "uniform"
389
+ },
390
+ "max_epochs": 5,
391
+ "max_grad_norm": 1.0,
392
+ "max_keep_ckpts": 3,
393
+ "max_steps": null,
394
+ "metric": {
395
+ "active_trackers": [
396
+ "jsonl",
397
+ "wandb"
398
+ ],
399
+ "run_dir": "work_dirs",
400
+ "type": "VLAMetric",
401
+ "window_size": 1
402
+ },
403
+ "mixed_precision_dtype": "bf16",
404
+ "optimizer": {
405
+ "lr": 0.0001,
406
+ "type": "AdamW",
407
+ "weight_decay": 0.01
408
+ },
409
+ "pre_fsdp_param_dtype": "bf16",
410
+ "reduce_in_full_precision": false,
411
+ "sampler": null,
412
+ "save_epoch_interval": 1,
413
+ "save_iter_interval": 10000000,
414
+ "sharding_strategy": "full-shard",
415
+ "tokenizer": {
416
+ "model_path": "./checkpoints/fastwam_base_full/tokenizer",
417
+ "type": "PretrainedTokenizer"
418
+ },
419
+ "type": "FSDPTrainRunner"
420
+ },
421
+ "seed": 42,
422
+ "train_dataloader": {
423
+ "dataset": {
424
+ "datasets": {
425
+ "action_key": "action",
426
+ "action_window_size": 32,
427
+ "data_root_path": [
428
+ "datasets/robotwin_clean_lerobotv2.1",
429
+ "datasets/robotwin_randomized_lerobotv2.1"
430
+ ],
431
+ "frame_sample_stride": 4,
432
+ "frame_window_size": 9,
433
+ "statistic_name": "robotwin_all",
434
+ "transforms": [
435
+ {
436
+ "embodiment_id": 0,
437
+ "name_mappings": {
438
+ "actions": [
439
+ "actions"
440
+ ],
441
+ "observation.state": [
442
+ "states"
443
+ ]
444
+ },
445
+ "parquet_keys": [
446
+ "observation.state",
447
+ "timestamp",
448
+ "actions",
449
+ "info",
450
+ "stats",
451
+ "action_masks"
452
+ ],
453
+ "type": "ProcessParquetInputs",
454
+ "video_backend": "torchcodec",
455
+ "video_keys": [
456
+ "observation.images.cam_high",
457
+ "observation.images.cam_left_wrist",
458
+ "observation.images.cam_right_wrist"
459
+ ]
460
+ },
461
+ {
462
+ "backend": "torchvision",
463
+ "height": 256,
464
+ "scale_to_unit_interval": true,
465
+ "type": "ResizeImages",
466
+ "width": 320
467
+ },
468
+ {
469
+ "means": [
470
+ 0.5,
471
+ 0.5,
472
+ 0.5
473
+ ],
474
+ "stds": [
475
+ 0.5,
476
+ 0.5,
477
+ 0.5
478
+ ],
479
+ "type": "NormalizeImages"
480
+ },
481
+ {
482
+ "action_dim": 14,
483
+ "action_key": "action",
484
+ "norm_type": "mean_std",
485
+ "state_dim": 14,
486
+ "state_key": "proprio",
487
+ "type": "NormalizeStatesAndActions"
488
+ },
489
+ {
490
+ "bottom_height_ratio": 0.5,
491
+ "bottom_views": [
492
+ 1,
493
+ 2
494
+ ],
495
+ "frame_window_size": 9,
496
+ "num_views": 3,
497
+ "tile_direction": "top_bottom_pair",
498
+ "top_view": 0,
499
+ "type": "PrepareVideo"
500
+ },
501
+ {
502
+ "max_len": 128,
503
+ "prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
504
+ "tokenizer": {
505
+ "model_path": "./checkpoints/fastwam_base_full/tokenizer",
506
+ "type": "PretrainedTokenizer"
507
+ },
508
+ "type": "LiberoPromptFromInputs",
509
+ "use_conversation": false
510
+ }
511
+ ],
512
+ "type": "ParquetDataset",
513
+ "use_delta": false,
514
+ "window_start_idx": 0
515
+ },
516
+ "name_mappings": {
517
+ "action": [
518
+ "action"
519
+ ],
520
+ "observation.state": [
521
+ "proprio"
522
+ ]
523
+ },
524
+ "reshuffle_each_epoch": true,
525
+ "seed": 42,
526
+ "statistic_keys": [
527
+ "observation.state",
528
+ "timestamp",
529
+ "action"
530
+ ],
531
+ "statistic_name": "robotwin_all",
532
+ "type": "DistributedRepeatingDataset"
533
+ },
534
+ "per_device_batch_size": 8,
535
+ "per_device_num_workers": 4
536
+ },
537
+ "val_dataloader": null
538
+ }
fastwam_robotwin_all_data_full_finetune_bs256/config.yaml ADDED
@@ -0,0 +1,456 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ACTION_DIM: 14
2
+ _ACTION_NORM_TYPE: mean_std
3
+ _ACTION_WINDOW_SIZE: 32
4
+ _CKPT_ROOT: ./checkpoints
5
+ _FASTWAM_CHECKPOINT: ./checkpoints/fastwam_base_full/fastwam_base_full.safetensors
6
+ _FASTWAM_ROOT: ./checkpoints/fastwam_base_full
7
+ _FASTWAM_TOKENIZER: ./checkpoints/fastwam_base_full/tokenizer
8
+ _FRAME_SAMPLE_STRIDE: 4
9
+ _FRAME_WINDOW_SIZE: 9
10
+ _ROBOTWIN_DATA_ROOTS:
11
+ - datasets/robotwin_clean_lerobotv2.1
12
+ - datasets/robotwin_randomized_lerobotv2.1
13
+ _ROBOTWIN_TASK_LIST:
14
+ - adjust_bottle
15
+ - beat_block_hammer
16
+ - blocks_ranking_rgb
17
+ - blocks_ranking_size
18
+ - click_alarmclock
19
+ - click_bell
20
+ - dump_bin_bigbin
21
+ - grab_roller
22
+ - handover_block
23
+ - handover_mic
24
+ - hanging_mug
25
+ - lift_pot
26
+ - move_can_pot
27
+ - move_pillbottle_pad
28
+ - move_playingcard_away
29
+ - move_stapler_pad
30
+ - open_laptop
31
+ - open_microwave
32
+ - pick_diverse_bottles
33
+ - pick_dual_bottles
34
+ - place_a2b_left
35
+ - place_a2b_right
36
+ - place_bread_basket
37
+ - place_bread_skillet
38
+ - place_burger_fries
39
+ - place_can_basket
40
+ - place_cans_plasticbox
41
+ - place_container_plate
42
+ - place_dual_shoes
43
+ - place_empty_cup
44
+ - place_fan
45
+ - place_mouse_pad
46
+ - place_object_basket
47
+ - place_object_scale
48
+ - place_object_stand
49
+ - place_phone_stand
50
+ - place_shoe
51
+ - press_stapler
52
+ - put_bottles_dustbin
53
+ - put_object_cabinet
54
+ - rotate_qrcode
55
+ - scan_object
56
+ - shake_bottle
57
+ - shake_bottle_horizontally
58
+ - stack_blocks_three
59
+ - stack_blocks_two
60
+ - stack_bowls_three
61
+ - stack_bowls_two
62
+ - stamp_seal
63
+ - turn_switch
64
+ _STATE_DIM: 14
65
+ _STATISTIC_NAME: robotwin_all
66
+ _TEXT_PROMPT_TEMPLATE: 'A video recorded from a robot''s point of view executing the
67
+ following instruction: {task}'
68
+ eval:
69
+ runner:
70
+ dataset:
71
+ img_keys:
72
+ - cam_high
73
+ - cam_left_wrist
74
+ - cam_right_wrist
75
+ transforms:
76
+ - action_dim: 14
77
+ action_key: action
78
+ norm_type: mean_std
79
+ state_dim: 14
80
+ state_key: proprio
81
+ type: NormalizeStatesAndActions
82
+ - max_len: 128
83
+ prompt_template: 'A video recorded from a robot''s point of view executing
84
+ the following instruction: {task}'
85
+ tokenizer:
86
+ model_path: ./checkpoints/fastwam_base_full/tokenizer
87
+ type: PretrainedTokenizer
88
+ type: LiberoPromptFromInputs
89
+ use_conversation: false
90
+ - height: 256
91
+ type: ResizeImages
92
+ width: 320
93
+ - type: SimpleNormalizeImages
94
+ - bottom_height_ratio: 0.5
95
+ bottom_views:
96
+ - 1
97
+ - 2
98
+ frame_window_size: 1
99
+ num_views: 3
100
+ tile_direction: top_bottom_pair
101
+ top_view: 0
102
+ type: PrepareVideo
103
+ type: PrivateInferenceDataset
104
+ denormalize_action:
105
+ action_dim: 14
106
+ norm_type: mean_std
107
+ type: DenormalizePrivateAction
108
+ eval_chunk_size: 24
109
+ instruction_type: unseen
110
+ mixed_precision_dtype: bf16
111
+ model_family: fastwam
112
+ num_trials_per_task: 100
113
+ save_video: false
114
+ seed: 42
115
+ task_list:
116
+ - adjust_bottle
117
+ - beat_block_hammer
118
+ - blocks_ranking_rgb
119
+ - blocks_ranking_size
120
+ - click_alarmclock
121
+ - click_bell
122
+ - dump_bin_bigbin
123
+ - grab_roller
124
+ - handover_block
125
+ - handover_mic
126
+ - hanging_mug
127
+ - lift_pot
128
+ - move_can_pot
129
+ - move_pillbottle_pad
130
+ - move_playingcard_away
131
+ - move_stapler_pad
132
+ - open_laptop
133
+ - open_microwave
134
+ - pick_diverse_bottles
135
+ - pick_dual_bottles
136
+ - place_a2b_left
137
+ - place_a2b_right
138
+ - place_bread_basket
139
+ - place_bread_skillet
140
+ - place_burger_fries
141
+ - place_can_basket
142
+ - place_cans_plasticbox
143
+ - place_container_plate
144
+ - place_dual_shoes
145
+ - place_empty_cup
146
+ - place_fan
147
+ - place_mouse_pad
148
+ - place_object_basket
149
+ - place_object_scale
150
+ - place_object_stand
151
+ - place_phone_stand
152
+ - place_shoe
153
+ - press_stapler
154
+ - put_bottles_dustbin
155
+ - put_object_cabinet
156
+ - rotate_qrcode
157
+ - scan_object
158
+ - shake_bottle
159
+ - shake_bottle_horizontally
160
+ - stack_blocks_three
161
+ - stack_blocks_two
162
+ - stack_bowls_three
163
+ - stack_bowls_two
164
+ - stamp_seal
165
+ - turn_switch
166
+ task_suite_name:
167
+ - clean
168
+ - random
169
+ type: RobotwinEvalRunner
170
+ unnorm_key: robotwin_all
171
+ eval_dataset: null
172
+ inference_model:
173
+ action_horizon: 32
174
+ frame_window_size: 9
175
+ mot_checkpoint_mixed_attn: true
176
+ num_views: 3
177
+ pretrained_name_or_path: ./checkpoints/fastwam_base_full/fastwam_base_full.safetensors
178
+ pretrained_skip_prefixes:
179
+ - vla_head.mot.mixtures.action.action_encoder.
180
+ - vla_head.mot.mixtures.action.head.
181
+ - vla_head.proprio_encoder.
182
+ proprio_dim: 14
183
+ torch_dtype: bf16
184
+ type: FastWAMVLA
185
+ vla_head:
186
+ action_dit_config:
187
+ action_dim: 14
188
+ attn_head_dim: 128
189
+ eps: 1.0e-06
190
+ ffn_dim: 4096
191
+ freq_dim: 256
192
+ hidden_dim: 1024
193
+ num_heads: 24
194
+ num_layers: 30
195
+ text_dim: 4096
196
+ use_gradient_checkpointing: true
197
+ action_scheduler:
198
+ infer_shift: 1.0
199
+ num_train_timesteps: 1000
200
+ train_shift: 1.0
201
+ loss:
202
+ lambda_action: 1.0
203
+ lambda_video: 1.0
204
+ type: FastWAMHead
205
+ video_dit_config:
206
+ action_conditioned: false
207
+ action_dim: 14
208
+ action_group_causal_mask_mode: group_diagonal
209
+ attn_head_dim: 128
210
+ eps: 1.0e-06
211
+ ffn_dim: 14336
212
+ freq_dim: 256
213
+ fuse_vae_embedding_in_latents: true
214
+ has_image_input: false
215
+ hidden_dim: 3072
216
+ in_dim: 48
217
+ num_heads: 24
218
+ num_layers: 30
219
+ out_dim: 48
220
+ patch_size:
221
+ - 1
222
+ - 2
223
+ - 2
224
+ require_clip_embedding: false
225
+ require_vae_embedding: false
226
+ seperated_timestep: true
227
+ text_dim: 4096
228
+ use_gradient_checkpointing: true
229
+ video_attention_mask_mode: first_frame_causal
230
+ video_scheduler:
231
+ infer_shift: 5.0
232
+ num_train_timesteps: 1000
233
+ train_shift: 5.0
234
+ vlm_backbone:
235
+ text_embed_cache_context_len: 128
236
+ text_embed_cache_device: cpu
237
+ text_embed_cache_size: 256
238
+ type: Wan22Backbone
239
+ model:
240
+ action_horizon: 32
241
+ frame_window_size: 9
242
+ mot_checkpoint_mixed_attn: true
243
+ num_views: 3
244
+ pretrained_name_or_path: ./checkpoints/fastwam_base_full/fastwam_base_full.safetensors
245
+ pretrained_skip_prefixes:
246
+ - vla_head.mot.mixtures.action.action_encoder.
247
+ - vla_head.mot.mixtures.action.head.
248
+ - vla_head.proprio_encoder.
249
+ proprio_dim: 14
250
+ torch_dtype: bf16
251
+ type: FastWAMVLA
252
+ vla_head:
253
+ action_dit_config:
254
+ action_dim: 14
255
+ attn_head_dim: 128
256
+ eps: 1.0e-06
257
+ ffn_dim: 4096
258
+ freq_dim: 256
259
+ hidden_dim: 1024
260
+ num_heads: 24
261
+ num_layers: 30
262
+ text_dim: 4096
263
+ use_gradient_checkpointing: true
264
+ action_scheduler:
265
+ infer_shift: 1.0
266
+ num_train_timesteps: 1000
267
+ train_shift: 1.0
268
+ loss:
269
+ lambda_action: 1.0
270
+ lambda_video: 1.0
271
+ type: FastWAMHead
272
+ video_dit_config:
273
+ action_conditioned: false
274
+ action_dim: 14
275
+ action_group_causal_mask_mode: group_diagonal
276
+ attn_head_dim: 128
277
+ eps: 1.0e-06
278
+ ffn_dim: 14336
279
+ freq_dim: 256
280
+ fuse_vae_embedding_in_latents: true
281
+ has_image_input: false
282
+ hidden_dim: 3072
283
+ in_dim: 48
284
+ num_heads: 24
285
+ num_layers: 30
286
+ out_dim: 48
287
+ patch_size:
288
+ - 1
289
+ - 2
290
+ - 2
291
+ require_clip_embedding: false
292
+ require_vae_embedding: false
293
+ seperated_timestep: true
294
+ text_dim: 4096
295
+ use_gradient_checkpointing: true
296
+ video_attention_mask_mode: first_frame_causal
297
+ video_scheduler:
298
+ infer_shift: 5.0
299
+ num_train_timesteps: 1000
300
+ train_shift: 5.0
301
+ vlm_backbone:
302
+ text_embed_cache_context_len: 128
303
+ text_embed_cache_device: cpu
304
+ text_embed_cache_size: 256
305
+ type: Wan22Backbone
306
+ runner:
307
+ collator:
308
+ keys:
309
+ - states
310
+ - images
311
+ - img_masks
312
+ - actions
313
+ - action_masks
314
+ - embodiment_ids
315
+ - frame_masks
316
+ - lang_tokens
317
+ - lang_masks
318
+ meta_keys:
319
+ - task_description
320
+ - info
321
+ - stats
322
+ - timestamp
323
+ type: DictCollator
324
+ dataset_sharding_strategy: blockwise
325
+ enable_gradient_checkpointing: false
326
+ enable_mixed_precision_training: true
327
+ evaluator:
328
+ eval_every: 1000
329
+ num_inference_steps: 10
330
+ save_video: false
331
+ seed: 42
332
+ type: training-eval
333
+ video_fps: 8
334
+ grad_accumulation_steps: 1
335
+ lr_scheduler:
336
+ betas:
337
+ - 0.9
338
+ - 0.95
339
+ min_lr_ratio: 0.01
340
+ type: linear-warmup+cosine-decay-min-lr
341
+ warmup_ratio: 0.05
342
+ weight_decay_style: uniform
343
+ max_epochs: 5
344
+ max_grad_norm: 1.0
345
+ max_keep_ckpts: 3
346
+ max_steps: null
347
+ metric:
348
+ active_trackers:
349
+ - jsonl
350
+ - wandb
351
+ run_dir: work_dirs
352
+ type: VLAMetric
353
+ window_size: 1
354
+ mixed_precision_dtype: bf16
355
+ optimizer:
356
+ lr: 0.0001
357
+ type: AdamW
358
+ weight_decay: 0.01
359
+ pre_fsdp_param_dtype: bf16
360
+ reduce_in_full_precision: false
361
+ sampler: null
362
+ save_epoch_interval: 1
363
+ save_iter_interval: 10000000
364
+ sharding_strategy: full-shard
365
+ tokenizer:
366
+ model_path: ./checkpoints/fastwam_base_full/tokenizer
367
+ type: PretrainedTokenizer
368
+ type: FSDPTrainRunner
369
+ seed: 42
370
+ train_dataloader:
371
+ dataset:
372
+ datasets:
373
+ action_key: action
374
+ action_window_size: 32
375
+ data_root_path:
376
+ - datasets/robotwin_clean_lerobotv2.1
377
+ - datasets/robotwin_randomized_lerobotv2.1
378
+ frame_sample_stride: 4
379
+ frame_window_size: 9
380
+ statistic_name: robotwin_all
381
+ transforms:
382
+ - embodiment_id: 0
383
+ name_mappings:
384
+ actions:
385
+ - actions
386
+ observation.state:
387
+ - states
388
+ parquet_keys:
389
+ - observation.state
390
+ - timestamp
391
+ - actions
392
+ - info
393
+ - stats
394
+ - action_masks
395
+ type: ProcessParquetInputs
396
+ video_backend: torchcodec
397
+ video_keys:
398
+ - observation.images.cam_high
399
+ - observation.images.cam_left_wrist
400
+ - observation.images.cam_right_wrist
401
+ - backend: torchvision
402
+ height: 256
403
+ scale_to_unit_interval: true
404
+ type: ResizeImages
405
+ width: 320
406
+ - means:
407
+ - 0.5
408
+ - 0.5
409
+ - 0.5
410
+ stds:
411
+ - 0.5
412
+ - 0.5
413
+ - 0.5
414
+ type: NormalizeImages
415
+ - action_dim: 14
416
+ action_key: action
417
+ norm_type: mean_std
418
+ state_dim: 14
419
+ state_key: proprio
420
+ type: NormalizeStatesAndActions
421
+ - bottom_height_ratio: 0.5
422
+ bottom_views:
423
+ - 1
424
+ - 2
425
+ frame_window_size: 9
426
+ num_views: 3
427
+ tile_direction: top_bottom_pair
428
+ top_view: 0
429
+ type: PrepareVideo
430
+ - max_len: 128
431
+ prompt_template: 'A video recorded from a robot''s point of view executing
432
+ the following instruction: {task}'
433
+ tokenizer:
434
+ model_path: ./checkpoints/fastwam_base_full/tokenizer
435
+ type: PretrainedTokenizer
436
+ type: LiberoPromptFromInputs
437
+ use_conversation: false
438
+ type: ParquetDataset
439
+ use_delta: false
440
+ window_start_idx: 0
441
+ name_mappings:
442
+ action:
443
+ - action
444
+ observation.state:
445
+ - proprio
446
+ reshuffle_each_epoch: true
447
+ seed: 42
448
+ statistic_keys:
449
+ - observation.state
450
+ - timestamp
451
+ - action
452
+ statistic_name: robotwin_all
453
+ type: DistributedRepeatingDataset
454
+ per_device_batch_size: 8
455
+ per_device_num_workers: 4
456
+ val_dataloader: null
fastwam_robotwin_all_data_full_finetune_bs256/dataset_statistics.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "robotwin_all": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.23836564500637852,
6
+ 1.129817402830952,
7
+ 0.8068359079301254,
8
+ -0.31024214960817226,
9
+ 0.05489044029082383,
10
+ -0.03797947365911228,
11
+ 0.6655638025405416,
12
+ 0.21664742843549212,
13
+ 1.0790448055651551,
14
+ 0.7875585893326063,
15
+ -0.3211320959513645,
16
+ -0.017501951884490514,
17
+ 0.03539706856287519,
18
+ 0.6794509037859313
19
+ ],
20
+ "std": [
21
+ 0.41515260848742136,
22
+ 1.0045809755922652,
23
+ 0.7768178536932145,
24
+ 0.6732816910017168,
25
+ 0.2708186547486596,
26
+ 0.6197771059972782,
27
+ 0.45465163653888563,
28
+ 0.34920798291604505,
29
+ 1.0249604849195586,
30
+ 0.794372303822,
31
+ 0.6847885016239902,
32
+ 0.24437403723179849,
33
+ 0.6142938232023921,
34
+ 0.44978408667126524
35
+ ],
36
+ "min": [
37
+ -7.552278995513916,
38
+ -0.36354875564575195,
39
+ -0.18577136099338531,
40
+ -1.956291913986206,
41
+ -1.6801013946533203,
42
+ -7.678869724273682,
43
+ 0.0,
44
+ -8.539926528930664,
45
+ -0.6294453740119934,
46
+ -0.07775841653347015,
47
+ -2.1328067779541016,
48
+ -2.1285502910614014,
49
+ -8.228925704956055,
50
+ 0.0
51
+ ],
52
+ "max": [
53
+ 6.45659065246582,
54
+ 4.179152488708496,
55
+ 5.346591472625732,
56
+ 1.7942548990249634,
57
+ 1.8604620695114136,
58
+ 5.43813943862915,
59
+ 1.0,
60
+ 7.142920017242432,
61
+ 4.157068729400635,
62
+ 5.672450065612793,
63
+ 1.95806884765625,
64
+ 1.5663840770721436,
65
+ 5.278968811035156,
66
+ 1.0
67
+ ],
68
+ "q01": null,
69
+ "q99": null
70
+ },
71
+ "timestamp": {
72
+ "mean": [
73
+ 9.822102670522625
74
+ ],
75
+ "std": [
76
+ 8.539596174071674
77
+ ],
78
+ "min": [
79
+ 0.0
80
+ ],
81
+ "max": [
82
+ 72.2
83
+ ],
84
+ "q01": null,
85
+ "q99": null
86
+ },
87
+ "action": {
88
+ "mean": [
89
+ -0.23943633195674233,
90
+ 1.1345611370099242,
91
+ 0.8102948556347407,
92
+ -0.31155664203396427,
93
+ 0.055179529382087596,
94
+ -0.03851684881837727,
95
+ 0.6643150995848328,
96
+ 0.2180408921138067,
97
+ 1.084594298787433,
98
+ 0.7916076777904834,
99
+ -0.3226336790356457,
100
+ -0.017651344197297695,
101
+ 0.036046095670276106,
102
+ 0.6783459021336998
103
+ ],
104
+ "std": [
105
+ 0.41571822839412337,
106
+ 1.0039769594416716,
107
+ 0.776858413838075,
108
+ 0.6748144778640579,
109
+ 0.271547410486253,
110
+ 0.6218771922320094,
111
+ 0.4551044161133153,
112
+ 0.3498656750012986,
113
+ 1.024847904429167,
114
+ 0.7946977748066826,
115
+ 0.6867041229584827,
116
+ 0.24531770744314874,
117
+ 0.6170235462820901,
118
+ 0.4502233751205138
119
+ ],
120
+ "min": [
121
+ -7.552278995513916,
122
+ -0.36354875564575195,
123
+ -0.18577136099338531,
124
+ -1.956291913986206,
125
+ -1.6801013946533203,
126
+ -7.678869724273682,
127
+ 0.0,
128
+ -8.539926528930664,
129
+ -0.6294453740119934,
130
+ -0.07775841653347015,
131
+ -2.1328067779541016,
132
+ -2.1285502910614014,
133
+ -8.228925704956055,
134
+ 0.0
135
+ ],
136
+ "max": [
137
+ 6.45659065246582,
138
+ 4.179152488708496,
139
+ 5.346591472625732,
140
+ 1.7942548990249634,
141
+ 1.8604620695114136,
142
+ 5.43813943862915,
143
+ 1.0,
144
+ 7.142920017242432,
145
+ 4.157068729400635,
146
+ 5.672450065612793,
147
+ 1.95806884765625,
148
+ 1.5663840770721436,
149
+ 5.278968811035156,
150
+ 1.0
151
+ ],
152
+ "q01": null,
153
+ "q99": null
154
+ }
155
+ }
156
+ }
fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/special_tokens_map.json ADDED
@@ -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
+ }
fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3909a67b780650b35cf529ac782ad2b6b26e6d1f849d3fbb6a872905f452458
3
+ size 4548313
fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e197b4d3dbd71da14b4eb255f4fa91c9c1f2068b20a2de2472967ca3d22602b
3
+ size 16837417
fastwam_robotwin_all_data_full_finetune_bs256/tokenizer/tokenizer_config.json ADDED
@@ -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
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/checkpoints/step-142386-epoch-03-loss=0.0027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85c9fc6d04095cdebf8de0ffc40365ebead8dde0bb75c9bb92f14a89b9710f4
3
+ size 10896783888
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/config.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_ROBOTWIN_TASK_LIST": [
3
+ "adjust_bottle",
4
+ "beat_block_hammer",
5
+ "blocks_ranking_rgb",
6
+ "blocks_ranking_size",
7
+ "click_alarmclock",
8
+ "click_bell",
9
+ "dump_bin_bigbin",
10
+ "grab_roller",
11
+ "handover_block",
12
+ "handover_mic",
13
+ "hanging_mug",
14
+ "lift_pot",
15
+ "move_can_pot",
16
+ "move_pillbottle_pad",
17
+ "move_playingcard_away",
18
+ "move_stapler_pad",
19
+ "open_laptop",
20
+ "open_microwave",
21
+ "pick_diverse_bottles",
22
+ "pick_dual_bottles",
23
+ "place_a2b_left",
24
+ "place_a2b_right",
25
+ "place_bread_basket",
26
+ "place_bread_skillet",
27
+ "place_burger_fries",
28
+ "place_can_basket",
29
+ "place_cans_plasticbox",
30
+ "place_container_plate",
31
+ "place_dual_shoes",
32
+ "place_empty_cup",
33
+ "place_fan",
34
+ "place_mouse_pad",
35
+ "place_object_basket",
36
+ "place_object_scale",
37
+ "place_object_stand",
38
+ "place_phone_stand",
39
+ "place_shoe",
40
+ "press_stapler",
41
+ "put_bottles_dustbin",
42
+ "put_object_cabinet",
43
+ "rotate_qrcode",
44
+ "scan_object",
45
+ "shake_bottle",
46
+ "shake_bottle_horizontally",
47
+ "stack_blocks_three",
48
+ "stack_blocks_two",
49
+ "stack_bowls_three",
50
+ "stack_bowls_two",
51
+ "stamp_seal",
52
+ "turn_switch"
53
+ ],
54
+ "eval": {
55
+ "dataset": {
56
+ "embodiment_id": 0,
57
+ "img_keys": [
58
+ "cam_high",
59
+ "cam_left_wrist",
60
+ "cam_right_wrist"
61
+ ],
62
+ "transforms": [
63
+ {
64
+ "max_len": 900,
65
+ "num_images": 3,
66
+ "tokenizer": {
67
+ "type": "PretrainedTokenizer"
68
+ },
69
+ "type": "ProcessPromptsWithImage"
70
+ },
71
+ {
72
+ "height": 224,
73
+ "type": "ResizeImages",
74
+ "width": 224
75
+ },
76
+ {
77
+ "means": [
78
+ [
79
+ 123.515625,
80
+ 116.04492188,
81
+ 103.59375
82
+ ],
83
+ [
84
+ 123.515625,
85
+ 116.04492188,
86
+ 103.59375
87
+ ],
88
+ [
89
+ 123.515625,
90
+ 116.04492188,
91
+ 103.59375
92
+ ]
93
+ ],
94
+ "stds": [
95
+ [
96
+ 58.27148438,
97
+ 57.02636719,
98
+ 57.27539062
99
+ ],
100
+ [
101
+ 58.27148438,
102
+ 57.02636719,
103
+ 57.27539062
104
+ ],
105
+ [
106
+ 58.27148438,
107
+ 57.02636719,
108
+ 57.27539062
109
+ ]
110
+ ],
111
+ "type": "NormalizeImages"
112
+ },
113
+ {
114
+ "action_key": "action",
115
+ "norm_type": "mean_std",
116
+ "state_dim": 64,
117
+ "state_key": "proprio",
118
+ "type": "NormalizeStatesAndActions"
119
+ }
120
+ ],
121
+ "type": "PrivateInferenceDataset"
122
+ },
123
+ "denormalize_action": {
124
+ "action_dim": 14,
125
+ "norm_type": "mean_std",
126
+ "type": "DenormalizePrivateAction"
127
+ },
128
+ "eval_chunk_size": 50,
129
+ "model_family": "groot",
130
+ "num_trials_per_task": 100,
131
+ "seed": 7,
132
+ "task_list": [
133
+ "adjust_bottle",
134
+ "beat_block_hammer",
135
+ "blocks_ranking_rgb",
136
+ "blocks_ranking_size",
137
+ "click_alarmclock",
138
+ "click_bell",
139
+ "dump_bin_bigbin",
140
+ "grab_roller",
141
+ "handover_block",
142
+ "handover_mic",
143
+ "hanging_mug",
144
+ "lift_pot",
145
+ "move_can_pot",
146
+ "move_pillbottle_pad",
147
+ "move_playingcard_away",
148
+ "move_stapler_pad",
149
+ "open_laptop",
150
+ "open_microwave",
151
+ "pick_diverse_bottles",
152
+ "pick_dual_bottles",
153
+ "place_a2b_left",
154
+ "place_a2b_right",
155
+ "place_bread_basket",
156
+ "place_bread_skillet",
157
+ "place_burger_fries",
158
+ "place_can_basket",
159
+ "place_cans_plasticbox",
160
+ "place_container_plate",
161
+ "place_dual_shoes",
162
+ "place_empty_cup",
163
+ "place_fan",
164
+ "place_mouse_pad",
165
+ "place_object_basket",
166
+ "place_object_scale",
167
+ "place_object_stand",
168
+ "place_phone_stand",
169
+ "place_shoe",
170
+ "press_stapler",
171
+ "put_bottles_dustbin",
172
+ "put_object_cabinet",
173
+ "rotate_qrcode",
174
+ "scan_object",
175
+ "shake_bottle",
176
+ "shake_bottle_horizontally",
177
+ "stack_blocks_three",
178
+ "stack_blocks_two",
179
+ "stack_bowls_three",
180
+ "stack_bowls_two",
181
+ "stamp_seal",
182
+ "turn_switch"
183
+ ],
184
+ "type": "RobotwinEvalRunner"
185
+ },
186
+ "inference_model": {
187
+ "pretrained_name_or_path": "./checkpoints/GR00T-N1.5-3B",
188
+ "type": "LlavaVLA",
189
+ "vla_head": {
190
+ "action_dim": 32,
191
+ "diffusion_model_cfg": {
192
+ "attention_head_dim": 48,
193
+ "cross_attention_dim": 2048,
194
+ "dropout": 0.2,
195
+ "final_dropout": true,
196
+ "interleave_self_attention": true,
197
+ "norm_type": "ada_norm",
198
+ "num_attention_heads": 32,
199
+ "num_layers": 16,
200
+ "output_dim": 1024,
201
+ "positional_embeddings": null
202
+ },
203
+ "hidden_size": 1024,
204
+ "input_embedding_dim": 1536,
205
+ "max_input_seq_len": 900,
206
+ "num_inference_timesteps": 4,
207
+ "num_steps": 50,
208
+ "ori_action_dim": 14,
209
+ "state_dim": 64,
210
+ "type": "FlowMatchingInferenceHead"
211
+ },
212
+ "vlm_backbone": {
213
+ "type": "EagleInferenceBackbone",
214
+ "vlm_config": {
215
+ "max_input_seq_len": 900
216
+ },
217
+ "vlm_path": "fluxvla/models/third_party_models/eagle2_hg_model"
218
+ }
219
+ },
220
+ "model": {
221
+ "freeze_projector": false,
222
+ "freeze_vlm_backbone": false,
223
+ "name_mapping": {
224
+ "vla_head": "action_head",
225
+ "vlm_backbone.vlm": "backbone.eagle_model"
226
+ },
227
+ "pretrained_name_or_path": "./checkpoints/GR00T-N1.5-3B",
228
+ "type": "LlavaVLA",
229
+ "vla_head": {
230
+ "action_dim": 32,
231
+ "hidden_size": 1024,
232
+ "input_embedding_dim": 1536,
233
+ "num_inference_timesteps": 4,
234
+ "num_steps": 50,
235
+ "ori_action_dim": 14,
236
+ "state_dim": 64,
237
+ "type": "FlowMatchingHead"
238
+ },
239
+ "vlm_backbone": {
240
+ "type": "EagleBackbone",
241
+ "vlm_config": {
242
+ "max_input_seq_len": 900
243
+ },
244
+ "vlm_path": "fluxvla/models/third_party_models/eagle2_hg_model"
245
+ }
246
+ },
247
+ "runner": {
248
+ "change_key_name": false,
249
+ "collator": {
250
+ "keys": [
251
+ "states",
252
+ "timestamp",
253
+ "images",
254
+ "img_masks",
255
+ "lang_tokens",
256
+ "lang_masks",
257
+ "actions",
258
+ "action_masks",
259
+ "embodiment_ids"
260
+ ],
261
+ "meta_keys": [
262
+ "task_description",
263
+ "prompt",
264
+ "info",
265
+ "stats"
266
+ ],
267
+ "type": "DictCollator"
268
+ },
269
+ "enable_gradient_checkpointing": false,
270
+ "enable_mixed_precision_training": true,
271
+ "lr_scheduler": {
272
+ "type": "linear-warmup+cosine-decay",
273
+ "warmup_ratio": 0.03
274
+ },
275
+ "max_epochs": 3,
276
+ "max_grad_norm": 1.0,
277
+ "max_keep_ckpts": 3,
278
+ "metric": {
279
+ "active_trackers": [
280
+ "jsonl",
281
+ "wandb"
282
+ ],
283
+ "grad_accumulation_steps": 1,
284
+ "run_dir": "work_dirs",
285
+ "type": "VLAMetric",
286
+ "window_size": 1
287
+ },
288
+ "mixed_precision_dtype": "bf16",
289
+ "optimizer": {
290
+ "lr": 1e-05,
291
+ "paramwise_learning_rate": {
292
+ "vla_head": 0.0001
293
+ },
294
+ "type": "AdamW",
295
+ "weight_decay": 0.0
296
+ },
297
+ "sampler": null,
298
+ "tokenizer": {
299
+ "model_path": "fluxvla/models/third_party_models/eagle2_hg_model",
300
+ "type": "PretrainedTokenizer"
301
+ },
302
+ "type": "FSDPTrainRunner"
303
+ },
304
+ "train_dataloader": {
305
+ "dataset": {
306
+ "datasets": [
307
+ {
308
+ "action_window_size": 50,
309
+ "data_root_path": [
310
+ "datasets/robotwin_clean_lerobotv2.1",
311
+ "datasets/robotwin_randomized_lerobotv2.1"
312
+ ],
313
+ "transforms": [
314
+ {
315
+ "embodiment_id": 0,
316
+ "name_mappings": {
317
+ "observation.state": [
318
+ "states"
319
+ ]
320
+ },
321
+ "parquet_keys": [
322
+ "observation.state",
323
+ "timestamp",
324
+ "actions",
325
+ "info",
326
+ "stats",
327
+ "action_masks"
328
+ ],
329
+ "type": "ProcessParquetInputs",
330
+ "video_keys": [
331
+ "observation.images.cam_high",
332
+ "observation.images.cam_left_wrist",
333
+ "observation.images.cam_right_wrist"
334
+ ]
335
+ },
336
+ {
337
+ "type": "ParquetPrompter"
338
+ },
339
+ {
340
+ "max_len": 900,
341
+ "num_images": 3,
342
+ "tokenizer": {
343
+ "model_path": "fluxvla/models/third_party_models/eagle2_hg_model",
344
+ "type": "PretrainedTokenizer"
345
+ },
346
+ "type": "ProcessPromptsWithImage"
347
+ },
348
+ {
349
+ "height": 224,
350
+ "type": "ResizeImages",
351
+ "width": 224
352
+ },
353
+ {
354
+ "means": [
355
+ [
356
+ 123.515625,
357
+ 116.04492188,
358
+ 103.59375
359
+ ],
360
+ [
361
+ 123.515625,
362
+ 116.04492188,
363
+ 103.59375
364
+ ],
365
+ [
366
+ 123.515625,
367
+ 116.04492188,
368
+ 103.59375
369
+ ]
370
+ ],
371
+ "stds": [
372
+ [
373
+ 58.27148438,
374
+ 57.02636719,
375
+ 57.27539062
376
+ ],
377
+ [
378
+ 58.27148438,
379
+ 57.02636719,
380
+ 57.27539062
381
+ ],
382
+ [
383
+ 58.27148438,
384
+ 57.02636719,
385
+ 57.27539062
386
+ ]
387
+ ],
388
+ "type": "NormalizeImages"
389
+ },
390
+ {
391
+ "action_dim": 32,
392
+ "action_key": "action",
393
+ "norm_type": "mean_std",
394
+ "state_dim": 64,
395
+ "state_key": "proprio",
396
+ "type": "NormalizeStatesAndActions"
397
+ }
398
+ ],
399
+ "type": "ParquetDataset"
400
+ }
401
+ ],
402
+ "name_mappings": {
403
+ "observation.state": [
404
+ "proprio",
405
+ "action"
406
+ ]
407
+ },
408
+ "reshuffle_each_epoch": true,
409
+ "seed": 7,
410
+ "statistic_keys": [
411
+ "observation.state",
412
+ "timestamp"
413
+ ],
414
+ "type": "DistributedRepeatingDataset"
415
+ },
416
+ "per_device_batch_size": 8,
417
+ "per_device_num_workers": 4
418
+ }
419
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/config.yaml ADDED
@@ -0,0 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ROBOTWIN_TASK_LIST:
2
+ - adjust_bottle
3
+ - beat_block_hammer
4
+ - blocks_ranking_rgb
5
+ - blocks_ranking_size
6
+ - click_alarmclock
7
+ - click_bell
8
+ - dump_bin_bigbin
9
+ - grab_roller
10
+ - handover_block
11
+ - handover_mic
12
+ - hanging_mug
13
+ - lift_pot
14
+ - move_can_pot
15
+ - move_pillbottle_pad
16
+ - move_playingcard_away
17
+ - move_stapler_pad
18
+ - open_laptop
19
+ - open_microwave
20
+ - pick_diverse_bottles
21
+ - pick_dual_bottles
22
+ - place_a2b_left
23
+ - place_a2b_right
24
+ - place_bread_basket
25
+ - place_bread_skillet
26
+ - place_burger_fries
27
+ - place_can_basket
28
+ - place_cans_plasticbox
29
+ - place_container_plate
30
+ - place_dual_shoes
31
+ - place_empty_cup
32
+ - place_fan
33
+ - place_mouse_pad
34
+ - place_object_basket
35
+ - place_object_scale
36
+ - place_object_stand
37
+ - place_phone_stand
38
+ - place_shoe
39
+ - press_stapler
40
+ - put_bottles_dustbin
41
+ - put_object_cabinet
42
+ - rotate_qrcode
43
+ - scan_object
44
+ - shake_bottle
45
+ - shake_bottle_horizontally
46
+ - stack_blocks_three
47
+ - stack_blocks_two
48
+ - stack_bowls_three
49
+ - stack_bowls_two
50
+ - stamp_seal
51
+ - turn_switch
52
+ eval:
53
+ dataset:
54
+ embodiment_id: 0
55
+ img_keys:
56
+ - cam_high
57
+ - cam_left_wrist
58
+ - cam_right_wrist
59
+ transforms:
60
+ - max_len: 900
61
+ num_images: 3
62
+ tokenizer:
63
+ type: PretrainedTokenizer
64
+ type: ProcessPromptsWithImage
65
+ - height: 224
66
+ type: ResizeImages
67
+ width: 224
68
+ - means:
69
+ - - 123.515625
70
+ - 116.04492188
71
+ - 103.59375
72
+ - - 123.515625
73
+ - 116.04492188
74
+ - 103.59375
75
+ - - 123.515625
76
+ - 116.04492188
77
+ - 103.59375
78
+ stds:
79
+ - - 58.27148438
80
+ - 57.02636719
81
+ - 57.27539062
82
+ - - 58.27148438
83
+ - 57.02636719
84
+ - 57.27539062
85
+ - - 58.27148438
86
+ - 57.02636719
87
+ - 57.27539062
88
+ type: NormalizeImages
89
+ - action_key: action
90
+ norm_type: mean_std
91
+ state_dim: 64
92
+ state_key: proprio
93
+ type: NormalizeStatesAndActions
94
+ type: PrivateInferenceDataset
95
+ denormalize_action:
96
+ action_dim: 14
97
+ norm_type: mean_std
98
+ type: DenormalizePrivateAction
99
+ eval_chunk_size: 50
100
+ model_family: groot
101
+ num_trials_per_task: 100
102
+ seed: 7
103
+ task_list:
104
+ - adjust_bottle
105
+ - beat_block_hammer
106
+ - blocks_ranking_rgb
107
+ - blocks_ranking_size
108
+ - click_alarmclock
109
+ - click_bell
110
+ - dump_bin_bigbin
111
+ - grab_roller
112
+ - handover_block
113
+ - handover_mic
114
+ - hanging_mug
115
+ - lift_pot
116
+ - move_can_pot
117
+ - move_pillbottle_pad
118
+ - move_playingcard_away
119
+ - move_stapler_pad
120
+ - open_laptop
121
+ - open_microwave
122
+ - pick_diverse_bottles
123
+ - pick_dual_bottles
124
+ - place_a2b_left
125
+ - place_a2b_right
126
+ - place_bread_basket
127
+ - place_bread_skillet
128
+ - place_burger_fries
129
+ - place_can_basket
130
+ - place_cans_plasticbox
131
+ - place_container_plate
132
+ - place_dual_shoes
133
+ - place_empty_cup
134
+ - place_fan
135
+ - place_mouse_pad
136
+ - place_object_basket
137
+ - place_object_scale
138
+ - place_object_stand
139
+ - place_phone_stand
140
+ - place_shoe
141
+ - press_stapler
142
+ - put_bottles_dustbin
143
+ - put_object_cabinet
144
+ - rotate_qrcode
145
+ - scan_object
146
+ - shake_bottle
147
+ - shake_bottle_horizontally
148
+ - stack_blocks_three
149
+ - stack_blocks_two
150
+ - stack_bowls_three
151
+ - stack_bowls_two
152
+ - stamp_seal
153
+ - turn_switch
154
+ type: RobotwinEvalRunner
155
+ inference_model:
156
+ pretrained_name_or_path: ./checkpoints/GR00T-N1.5-3B
157
+ type: LlavaVLA
158
+ vla_head:
159
+ action_dim: 32
160
+ diffusion_model_cfg:
161
+ attention_head_dim: 48
162
+ cross_attention_dim: 2048
163
+ dropout: 0.2
164
+ final_dropout: true
165
+ interleave_self_attention: true
166
+ norm_type: ada_norm
167
+ num_attention_heads: 32
168
+ num_layers: 16
169
+ output_dim: 1024
170
+ positional_embeddings: null
171
+ hidden_size: 1024
172
+ input_embedding_dim: 1536
173
+ max_input_seq_len: 900
174
+ num_inference_timesteps: 4
175
+ num_steps: 50
176
+ ori_action_dim: 14
177
+ state_dim: 64
178
+ type: FlowMatchingInferenceHead
179
+ vlm_backbone:
180
+ type: EagleInferenceBackbone
181
+ vlm_config:
182
+ max_input_seq_len: 900
183
+ vlm_path: fluxvla/models/third_party_models/eagle2_hg_model
184
+ model:
185
+ freeze_projector: false
186
+ freeze_vlm_backbone: false
187
+ name_mapping:
188
+ vla_head: action_head
189
+ vlm_backbone.vlm: backbone.eagle_model
190
+ pretrained_name_or_path: ./checkpoints/GR00T-N1.5-3B
191
+ type: LlavaVLA
192
+ vla_head:
193
+ action_dim: 32
194
+ hidden_size: 1024
195
+ input_embedding_dim: 1536
196
+ num_inference_timesteps: 4
197
+ num_steps: 50
198
+ ori_action_dim: 14
199
+ state_dim: 64
200
+ type: FlowMatchingHead
201
+ vlm_backbone:
202
+ type: EagleBackbone
203
+ vlm_config:
204
+ max_input_seq_len: 900
205
+ vlm_path: fluxvla/models/third_party_models/eagle2_hg_model
206
+ runner:
207
+ change_key_name: false
208
+ collator:
209
+ keys:
210
+ - states
211
+ - timestamp
212
+ - images
213
+ - img_masks
214
+ - lang_tokens
215
+ - lang_masks
216
+ - actions
217
+ - action_masks
218
+ - embodiment_ids
219
+ meta_keys:
220
+ - task_description
221
+ - prompt
222
+ - info
223
+ - stats
224
+ type: DictCollator
225
+ enable_gradient_checkpointing: false
226
+ enable_mixed_precision_training: true
227
+ lr_scheduler:
228
+ type: linear-warmup+cosine-decay
229
+ warmup_ratio: 0.03
230
+ max_epochs: 3
231
+ max_grad_norm: 1.0
232
+ max_keep_ckpts: 3
233
+ metric:
234
+ active_trackers:
235
+ - jsonl
236
+ - wandb
237
+ grad_accumulation_steps: 1
238
+ run_dir: work_dirs
239
+ type: VLAMetric
240
+ window_size: 1
241
+ mixed_precision_dtype: bf16
242
+ optimizer:
243
+ lr: 1.0e-05
244
+ paramwise_learning_rate:
245
+ vla_head: 0.0001
246
+ type: AdamW
247
+ weight_decay: 0.0
248
+ sampler: null
249
+ tokenizer:
250
+ model_path: fluxvla/models/third_party_models/eagle2_hg_model
251
+ type: PretrainedTokenizer
252
+ type: FSDPTrainRunner
253
+ train_dataloader:
254
+ dataset:
255
+ datasets:
256
+ - action_window_size: 50
257
+ data_root_path:
258
+ - datasets/robotwin_clean_lerobotv2.1
259
+ - datasets/robotwin_randomized_lerobotv2.1
260
+ transforms:
261
+ - embodiment_id: 0
262
+ name_mappings:
263
+ observation.state:
264
+ - states
265
+ parquet_keys:
266
+ - observation.state
267
+ - timestamp
268
+ - actions
269
+ - info
270
+ - stats
271
+ - action_masks
272
+ type: ProcessParquetInputs
273
+ video_keys:
274
+ - observation.images.cam_high
275
+ - observation.images.cam_left_wrist
276
+ - observation.images.cam_right_wrist
277
+ - type: ParquetPrompter
278
+ - max_len: 900
279
+ num_images: 3
280
+ tokenizer:
281
+ model_path: fluxvla/models/third_party_models/eagle2_hg_model
282
+ type: PretrainedTokenizer
283
+ type: ProcessPromptsWithImage
284
+ - height: 224
285
+ type: ResizeImages
286
+ width: 224
287
+ - means:
288
+ - - 123.515625
289
+ - 116.04492188
290
+ - 103.59375
291
+ - - 123.515625
292
+ - 116.04492188
293
+ - 103.59375
294
+ - - 123.515625
295
+ - 116.04492188
296
+ - 103.59375
297
+ stds:
298
+ - - 58.27148438
299
+ - 57.02636719
300
+ - 57.27539062
301
+ - - 58.27148438
302
+ - 57.02636719
303
+ - 57.27539062
304
+ - - 58.27148438
305
+ - 57.02636719
306
+ - 57.27539062
307
+ type: NormalizeImages
308
+ - action_dim: 32
309
+ action_key: action
310
+ norm_type: mean_std
311
+ state_dim: 64
312
+ state_key: proprio
313
+ type: NormalizeStatesAndActions
314
+ type: ParquetDataset
315
+ name_mappings:
316
+ observation.state:
317
+ - proprio
318
+ - action
319
+ reshuffle_each_epoch: true
320
+ seed: 7
321
+ statistic_keys:
322
+ - observation.state
323
+ - timestamp
324
+ type: DistributedRepeatingDataset
325
+ per_device_batch_size: 8
326
+ per_device_num_workers: 4
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/dataset_statistics.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "private": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.23836564500637852,
6
+ 1.129817402830952,
7
+ 0.8068359079301254,
8
+ -0.31024214960817226,
9
+ 0.05489044029082383,
10
+ -0.03797947365911228,
11
+ 0.6655638025405416,
12
+ 0.21664742843549212,
13
+ 1.0790448055651551,
14
+ 0.7875585893326063,
15
+ -0.3211320959513645,
16
+ -0.017501951884490514,
17
+ 0.03539706856287519,
18
+ 0.6794509037859313
19
+ ],
20
+ "std": [
21
+ 0.41515260848742136,
22
+ 1.0045809755922652,
23
+ 0.7768178536932145,
24
+ 0.6732816910017168,
25
+ 0.2708186547486596,
26
+ 0.6197771059972782,
27
+ 0.45465163653888563,
28
+ 0.34920798291604505,
29
+ 1.0249604849195586,
30
+ 0.794372303822,
31
+ 0.6847885016239902,
32
+ 0.24437403723179849,
33
+ 0.6142938232023921,
34
+ 0.44978408667126524
35
+ ],
36
+ "min": [
37
+ -7.552278995513916,
38
+ -0.36354875564575195,
39
+ -0.18577136099338531,
40
+ -1.956291913986206,
41
+ -1.6801013946533203,
42
+ -7.678869724273682,
43
+ 0.0,
44
+ -8.539926528930664,
45
+ -0.6294453740119934,
46
+ -0.07775841653347015,
47
+ -2.1328067779541016,
48
+ -2.1285502910614014,
49
+ -8.228925704956055,
50
+ 0.0
51
+ ],
52
+ "max": [
53
+ 6.45659065246582,
54
+ 4.179152488708496,
55
+ 5.346591472625732,
56
+ 1.7942548990249634,
57
+ 1.8604620695114136,
58
+ 5.43813943862915,
59
+ 1.0,
60
+ 7.142920017242432,
61
+ 4.157068729400635,
62
+ 5.672450065612793,
63
+ 1.95806884765625,
64
+ 1.5663840770721436,
65
+ 5.278968811035156,
66
+ 1.0
67
+ ],
68
+ "q01": null,
69
+ "q99": null
70
+ },
71
+ "action": {
72
+ "mean": [
73
+ -0.23836564500637852,
74
+ 1.129817402830952,
75
+ 0.8068359079301254,
76
+ -0.31024214960817226,
77
+ 0.05489044029082383,
78
+ -0.03797947365911228,
79
+ 0.6655638025405416,
80
+ 0.21664742843549212,
81
+ 1.0790448055651551,
82
+ 0.7875585893326063,
83
+ -0.3211320959513645,
84
+ -0.017501951884490514,
85
+ 0.03539706856287519,
86
+ 0.6794509037859313
87
+ ],
88
+ "std": [
89
+ 0.41515260848742136,
90
+ 1.0045809755922652,
91
+ 0.7768178536932145,
92
+ 0.6732816910017168,
93
+ 0.2708186547486596,
94
+ 0.6197771059972782,
95
+ 0.45465163653888563,
96
+ 0.34920798291604505,
97
+ 1.0249604849195586,
98
+ 0.794372303822,
99
+ 0.6847885016239902,
100
+ 0.24437403723179849,
101
+ 0.6142938232023921,
102
+ 0.44978408667126524
103
+ ],
104
+ "min": [
105
+ -7.552278995513916,
106
+ -0.36354875564575195,
107
+ -0.18577136099338531,
108
+ -1.956291913986206,
109
+ -1.6801013946533203,
110
+ -7.678869724273682,
111
+ 0.0,
112
+ -8.539926528930664,
113
+ -0.6294453740119934,
114
+ -0.07775841653347015,
115
+ -2.1328067779541016,
116
+ -2.1285502910614014,
117
+ -8.228925704956055,
118
+ 0.0
119
+ ],
120
+ "max": [
121
+ 6.45659065246582,
122
+ 4.179152488708496,
123
+ 5.346591472625732,
124
+ 1.7942548990249634,
125
+ 1.8604620695114136,
126
+ 5.43813943862915,
127
+ 1.0,
128
+ 7.142920017242432,
129
+ 4.157068729400635,
130
+ 5.672450065612793,
131
+ 1.95806884765625,
132
+ 1.5663840770721436,
133
+ 5.278968811035156,
134
+ 1.0
135
+ ],
136
+ "q01": null,
137
+ "q99": null
138
+ },
139
+ "timestamp": {
140
+ "mean": [
141
+ 9.822102670522625
142
+ ],
143
+ "std": [
144
+ 8.539596174071674
145
+ ],
146
+ "min": [
147
+ 0.0
148
+ ],
149
+ "max": [
150
+ 72.2
151
+ ],
152
+ "q01": null,
153
+ "q99": null
154
+ }
155
+ }
156
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/added_tokens.json ADDED
@@ -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
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<image {{ image_count.value }}>{% endif %}<image-{{ image_count.value }}>{% 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 %}<video-{{ video_count.value }}>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/special_tokens_map.json ADDED
@@ -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
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/tokenizer_config.json ADDED
@@ -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
+ }
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
gr00t_eagle_3b_robotwin_all_data_full_finetune_bs128/vlm_backbone_config.json ADDED
@@ -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
+ }
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/checkpoints/step-118655-epoch-05-loss=0.0067.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56d7f9ef83433b9eb76c9c7c77f829e08ec6f115366c0ea62b6482f4db541d0
3
+ size 13820861200
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/config.json ADDED
@@ -0,0 +1,1235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_ACTIVE_TRACKERS": [
3
+ "jsonl",
4
+ "wandb"
5
+ ],
6
+ "_DATA_PATHS": [
7
+ "datasets/robotwin_clean_lerobotv2.1",
8
+ "datasets/robotwin_randomized_lerobotv2.1"
9
+ ],
10
+ "_N17_INIT_CKPT": "./checkpoints/GR00T-N1.7-3B",
11
+ "_N17_MODALITY_CONFIGS": {
12
+ "robotwin": {
13
+ "action": {
14
+ "delta_indices": [
15
+ 0,
16
+ 1,
17
+ 2,
18
+ 3,
19
+ 4,
20
+ 5,
21
+ 6,
22
+ 7,
23
+ 8,
24
+ 9,
25
+ 10,
26
+ 11,
27
+ 12,
28
+ 13,
29
+ 14,
30
+ 15,
31
+ 16,
32
+ 17,
33
+ 18,
34
+ 19,
35
+ 20,
36
+ 21,
37
+ 22,
38
+ 23,
39
+ 24,
40
+ 25,
41
+ 26,
42
+ 27,
43
+ 28,
44
+ 29,
45
+ 30,
46
+ 31,
47
+ 32,
48
+ 33,
49
+ 34,
50
+ 35,
51
+ 36,
52
+ 37,
53
+ 38,
54
+ 39
55
+ ],
56
+ "modality_keys": [
57
+ "joints"
58
+ ]
59
+ },
60
+ "state": {
61
+ "delta_indices": [
62
+ 0
63
+ ],
64
+ "modality_keys": [
65
+ "joints"
66
+ ]
67
+ },
68
+ "video": {
69
+ "delta_indices": [
70
+ 0
71
+ ],
72
+ "modality_keys": [
73
+ "cam_high",
74
+ "cam_left_wrist",
75
+ "cam_right_wrist"
76
+ ]
77
+ }
78
+ }
79
+ },
80
+ "_PROCESSOR_KWARGS": {
81
+ "apply_sincos_state_encoding": false,
82
+ "clip_outliers": false,
83
+ "color_jitter_params": {
84
+ "brightness": 0.3,
85
+ "contrast": 0.4,
86
+ "hue": 0.08,
87
+ "saturation": 0.5
88
+ },
89
+ "crop_fraction": null,
90
+ "embodiment_id_mapping": {
91
+ "robotwin": 0
92
+ },
93
+ "formalize_language": true,
94
+ "image_crop_size": [
95
+ 230,
96
+ 230
97
+ ],
98
+ "image_target_size": [
99
+ 256,
100
+ 256
101
+ ],
102
+ "max_action_dim": 132,
103
+ "max_action_horizon": 40,
104
+ "max_state_dim": 132,
105
+ "modality_configs": {
106
+ "robotwin": {
107
+ "action": {
108
+ "delta_indices": [
109
+ 0,
110
+ 1,
111
+ 2,
112
+ 3,
113
+ 4,
114
+ 5,
115
+ 6,
116
+ 7,
117
+ 8,
118
+ 9,
119
+ 10,
120
+ 11,
121
+ 12,
122
+ 13,
123
+ 14,
124
+ 15,
125
+ 16,
126
+ 17,
127
+ 18,
128
+ 19,
129
+ 20,
130
+ 21,
131
+ 22,
132
+ 23,
133
+ 24,
134
+ 25,
135
+ 26,
136
+ 27,
137
+ 28,
138
+ 29,
139
+ 30,
140
+ 31,
141
+ 32,
142
+ 33,
143
+ 34,
144
+ 35,
145
+ 36,
146
+ 37,
147
+ 38,
148
+ 39
149
+ ],
150
+ "modality_keys": [
151
+ "joints"
152
+ ]
153
+ },
154
+ "state": {
155
+ "delta_indices": [
156
+ 0
157
+ ],
158
+ "modality_keys": [
159
+ "joints"
160
+ ]
161
+ },
162
+ "video": {
163
+ "delta_indices": [
164
+ 0
165
+ ],
166
+ "modality_keys": [
167
+ "cam_high",
168
+ "cam_left_wrist",
169
+ "cam_right_wrist"
170
+ ]
171
+ }
172
+ }
173
+ },
174
+ "shortest_image_edge": null,
175
+ "state_dropout_prob": 0.2,
176
+ "statistics": {
177
+ "robotwin": {}
178
+ },
179
+ "use_albumentations": true,
180
+ "use_mean_std": true,
181
+ "use_percentiles": false,
182
+ "use_relative_action": false
183
+ },
184
+ "_QWEN3_VL_CONFIG": {
185
+ "architectures": [
186
+ "Qwen3VLForConditionalGeneration"
187
+ ],
188
+ "image_token_id": 151655,
189
+ "text_config": {
190
+ "attention_bias": false,
191
+ "attention_dropout": 0.0,
192
+ "head_dim": 128,
193
+ "hidden_act": "silu",
194
+ "hidden_size": 2048,
195
+ "initializer_range": 0.02,
196
+ "intermediate_size": 6144,
197
+ "max_position_embeddings": 262144,
198
+ "model_type": "qwen3_vl_text",
199
+ "num_attention_heads": 16,
200
+ "num_hidden_layers": 28,
201
+ "num_key_value_heads": 8,
202
+ "rms_norm_eps": 1e-06,
203
+ "rope_parameters": {
204
+ "mrope_interleaved": true,
205
+ "mrope_section": [
206
+ 24,
207
+ 20,
208
+ 20
209
+ ],
210
+ "rope_theta": 5000000.0,
211
+ "rope_type": "default"
212
+ },
213
+ "use_cache": false,
214
+ "vocab_size": 151936
215
+ },
216
+ "tie_word_embeddings": false,
217
+ "video_token_id": 151656,
218
+ "vision_config": {
219
+ "deepstack_visual_indexes": [
220
+ 5,
221
+ 11,
222
+ 17
223
+ ],
224
+ "depth": 24,
225
+ "hidden_act": "gelu_pytorch_tanh",
226
+ "hidden_size": 1024,
227
+ "in_channels": 3,
228
+ "initializer_range": 0.02,
229
+ "intermediate_size": 4096,
230
+ "model_type": "qwen3_vl_vision",
231
+ "num_heads": 16,
232
+ "num_position_embeddings": 2304,
233
+ "out_hidden_size": 2048,
234
+ "patch_size": 16,
235
+ "spatial_merge_size": 2,
236
+ "temporal_patch_size": 2
237
+ },
238
+ "vision_end_token_id": 151653,
239
+ "vision_start_token_id": 151652
240
+ },
241
+ "_QWEN_TOKENIZER_PATH": "fluxvla/models/third_party_models/qwen3_tokenizer",
242
+ "_STATISTIC_NAME": "robotwin_all",
243
+ "_TASK_NAMES": [
244
+ "adjust_bottle",
245
+ "beat_block_hammer",
246
+ "blocks_ranking_rgb",
247
+ "blocks_ranking_size",
248
+ "click_alarmclock",
249
+ "click_bell",
250
+ "dump_bin_bigbin",
251
+ "grab_roller",
252
+ "handover_block",
253
+ "handover_mic",
254
+ "hanging_mug",
255
+ "lift_pot",
256
+ "move_can_pot",
257
+ "move_pillbottle_pad",
258
+ "move_playingcard_away",
259
+ "move_stapler_pad",
260
+ "open_laptop",
261
+ "open_microwave",
262
+ "pick_diverse_bottles",
263
+ "pick_dual_bottles",
264
+ "place_a2b_left",
265
+ "place_a2b_right",
266
+ "place_bread_basket",
267
+ "place_bread_skillet",
268
+ "place_burger_fries",
269
+ "place_can_basket",
270
+ "place_cans_plasticbox",
271
+ "place_container_plate",
272
+ "place_dual_shoes",
273
+ "place_empty_cup",
274
+ "place_fan",
275
+ "place_mouse_pad",
276
+ "place_object_basket",
277
+ "place_object_scale",
278
+ "place_object_stand",
279
+ "place_phone_stand",
280
+ "place_shoe",
281
+ "press_stapler",
282
+ "put_bottles_dustbin",
283
+ "put_object_cabinet",
284
+ "rotate_qrcode",
285
+ "scan_object",
286
+ "shake_bottle",
287
+ "shake_bottle_horizontally",
288
+ "stack_blocks_three",
289
+ "stack_blocks_two",
290
+ "stack_bowls_three",
291
+ "stack_bowls_two",
292
+ "stamp_seal",
293
+ "turn_switch"
294
+ ],
295
+ "eval": {
296
+ "dataset": {
297
+ "embodiment_id": 0,
298
+ "img_keys": [
299
+ "cam_high",
300
+ "cam_left_wrist",
301
+ "cam_right_wrist"
302
+ ],
303
+ "inject_model_path": false,
304
+ "transforms": [
305
+ {
306
+ "action_dim": 132,
307
+ "action_key": null,
308
+ "clip_norm": false,
309
+ "norm_type": "mean_std",
310
+ "normalization_epsilon": 1e-06,
311
+ "preserve_input_dtype": true,
312
+ "state_dim": 132,
313
+ "state_key": "proprio",
314
+ "type": "NormalizeStatesAndActions"
315
+ },
316
+ {
317
+ "action_horizon": 40,
318
+ "state_dropout_prob": 0.0,
319
+ "state_history_length": 1,
320
+ "type": "PrepareStateActionTargets",
321
+ "valid_action_dim": 14
322
+ },
323
+ {
324
+ "embodiment_tag": "robotwin",
325
+ "image_key": "images",
326
+ "output_image_key": "images",
327
+ "processor_kwargs": {
328
+ "apply_sincos_state_encoding": false,
329
+ "clip_outliers": false,
330
+ "color_jitter_params": {
331
+ "brightness": 0.3,
332
+ "contrast": 0.4,
333
+ "hue": 0.08,
334
+ "saturation": 0.5
335
+ },
336
+ "crop_fraction": null,
337
+ "embodiment_id_mapping": {
338
+ "robotwin": 0
339
+ },
340
+ "formalize_language": true,
341
+ "image_crop_size": [
342
+ 230,
343
+ 230
344
+ ],
345
+ "image_target_size": [
346
+ 256,
347
+ 256
348
+ ],
349
+ "max_action_dim": 132,
350
+ "max_action_horizon": 40,
351
+ "max_state_dim": 132,
352
+ "modality_configs": {
353
+ "robotwin": {
354
+ "action": {
355
+ "delta_indices": [
356
+ 0,
357
+ 1,
358
+ 2,
359
+ 3,
360
+ 4,
361
+ 5,
362
+ 6,
363
+ 7,
364
+ 8,
365
+ 9,
366
+ 10,
367
+ 11,
368
+ 12,
369
+ 13,
370
+ 14,
371
+ 15,
372
+ 16,
373
+ 17,
374
+ 18,
375
+ 19,
376
+ 20,
377
+ 21,
378
+ 22,
379
+ 23,
380
+ 24,
381
+ 25,
382
+ 26,
383
+ 27,
384
+ 28,
385
+ 29,
386
+ 30,
387
+ 31,
388
+ 32,
389
+ 33,
390
+ 34,
391
+ 35,
392
+ 36,
393
+ 37,
394
+ 38,
395
+ 39
396
+ ],
397
+ "modality_keys": [
398
+ "joints"
399
+ ]
400
+ },
401
+ "state": {
402
+ "delta_indices": [
403
+ 0
404
+ ],
405
+ "modality_keys": [
406
+ "joints"
407
+ ]
408
+ },
409
+ "video": {
410
+ "delta_indices": [
411
+ 0
412
+ ],
413
+ "modality_keys": [
414
+ "cam_high",
415
+ "cam_left_wrist",
416
+ "cam_right_wrist"
417
+ ]
418
+ }
419
+ }
420
+ },
421
+ "shortest_image_edge": null,
422
+ "state_dropout_prob": 0.2,
423
+ "statistics": {
424
+ "robotwin": {}
425
+ },
426
+ "use_albumentations": true,
427
+ "use_mean_std": true,
428
+ "use_percentiles": false,
429
+ "use_relative_action": false
430
+ },
431
+ "train_mode": false,
432
+ "type": "GrootN17ImageAugmentation"
433
+ },
434
+ {
435
+ "image_mean": [
436
+ 0.5,
437
+ 0.5,
438
+ 0.5
439
+ ],
440
+ "image_std": [
441
+ 0.5,
442
+ 0.5,
443
+ 0.5
444
+ ],
445
+ "img_key": "images",
446
+ "merge_size": 2,
447
+ "patch_size": 16,
448
+ "size": {
449
+ "longest_edge": 16777216,
450
+ "shortest_edge": 65536
451
+ },
452
+ "temporal_patch_size": 2,
453
+ "to_tensor": true,
454
+ "type": "QWen2VLImageTransform"
455
+ },
456
+ {
457
+ "add_assistant_stub": false,
458
+ "add_system": false,
459
+ "attention_mask_dtype": "int64",
460
+ "image_grid_thw_key": "image_grid_thw",
461
+ "image_merge_size": 2,
462
+ "image_tag_template": "",
463
+ "img_context_token": "<|image_pad|>",
464
+ "img_end": "<|vision_end|>",
465
+ "img_start": "<|vision_start|>",
466
+ "img_tokens_source": "from_image_grid_thw",
467
+ "lowercase_task_description": true,
468
+ "max_len": 512,
469
+ "output_keys": [
470
+ "lang_tokens",
471
+ "lang_masks",
472
+ "images",
473
+ "image_grid_thw",
474
+ "states",
475
+ "embodiment_ids"
476
+ ],
477
+ "padding_side": "left",
478
+ "strip_task_punctuation": true,
479
+ "task_pos": "after_images",
480
+ "tokenizer": {
481
+ "model_path": "fluxvla/models/third_party_models/qwen3_tokenizer",
482
+ "padding_side": "left",
483
+ "trust_remote_code": false,
484
+ "type": "PretrainedTokenizer"
485
+ },
486
+ "truncate": false,
487
+ "type": "ProcessPromptsWithImage",
488
+ "use_eos_as_pad": false
489
+ }
490
+ ],
491
+ "type": "PrivateInferenceDataset"
492
+ },
493
+ "denormalize_action": {
494
+ "action_dim": 14,
495
+ "invert_gripper_action": false,
496
+ "norm_type": "mean_std",
497
+ "normalize_gripper_action": false,
498
+ "type": "DenormalizePrivateAction"
499
+ },
500
+ "eval_chunk_size": 40,
501
+ "instruction_type": "unseen",
502
+ "mixed_precision_dtype": "bf16",
503
+ "model_family": "groot_n17",
504
+ "num_trials_per_task": 100,
505
+ "save_video": false,
506
+ "seed": 7,
507
+ "task_list": [
508
+ "adjust_bottle",
509
+ "beat_block_hammer",
510
+ "blocks_ranking_rgb",
511
+ "blocks_ranking_size",
512
+ "click_alarmclock",
513
+ "click_bell",
514
+ "dump_bin_bigbin",
515
+ "grab_roller",
516
+ "handover_block",
517
+ "handover_mic",
518
+ "hanging_mug",
519
+ "lift_pot",
520
+ "move_can_pot",
521
+ "move_pillbottle_pad",
522
+ "move_playingcard_away",
523
+ "move_stapler_pad",
524
+ "open_laptop",
525
+ "open_microwave",
526
+ "pick_diverse_bottles",
527
+ "pick_dual_bottles",
528
+ "place_a2b_left",
529
+ "place_a2b_right",
530
+ "place_bread_basket",
531
+ "place_bread_skillet",
532
+ "place_burger_fries",
533
+ "place_can_basket",
534
+ "place_cans_plasticbox",
535
+ "place_container_plate",
536
+ "place_dual_shoes",
537
+ "place_empty_cup",
538
+ "place_fan",
539
+ "place_mouse_pad",
540
+ "place_object_basket",
541
+ "place_object_scale",
542
+ "place_object_stand",
543
+ "place_phone_stand",
544
+ "place_shoe",
545
+ "press_stapler",
546
+ "put_bottles_dustbin",
547
+ "put_object_cabinet",
548
+ "rotate_qrcode",
549
+ "scan_object",
550
+ "shake_bottle",
551
+ "shake_bottle_horizontally",
552
+ "stack_blocks_three",
553
+ "stack_blocks_two",
554
+ "stack_bowls_three",
555
+ "stack_bowls_two",
556
+ "stamp_seal",
557
+ "turn_switch"
558
+ ],
559
+ "task_suite_name": [
560
+ "clean",
561
+ "random"
562
+ ],
563
+ "type": "RobotwinEvalRunner",
564
+ "unnorm_key": "robotwin_all"
565
+ },
566
+ "inference_model": {
567
+ "embodiment_tag": "robotwin",
568
+ "freeze_vlm_backbone": false,
569
+ "load_metadata": false,
570
+ "load_pretrained_weights": false,
571
+ "model_path": null,
572
+ "processor_kwargs": {
573
+ "apply_sincos_state_encoding": false,
574
+ "clip_outliers": false,
575
+ "color_jitter_params": {
576
+ "brightness": 0.3,
577
+ "contrast": 0.4,
578
+ "hue": 0.08,
579
+ "saturation": 0.5
580
+ },
581
+ "crop_fraction": null,
582
+ "embodiment_id_mapping": {
583
+ "robotwin": 0
584
+ },
585
+ "formalize_language": true,
586
+ "image_crop_size": [
587
+ 230,
588
+ 230
589
+ ],
590
+ "image_target_size": [
591
+ 256,
592
+ 256
593
+ ],
594
+ "max_action_dim": 132,
595
+ "max_action_horizon": 40,
596
+ "max_state_dim": 132,
597
+ "modality_configs": {
598
+ "robotwin": {
599
+ "action": {
600
+ "delta_indices": [
601
+ 0,
602
+ 1,
603
+ 2,
604
+ 3,
605
+ 4,
606
+ 5,
607
+ 6,
608
+ 7,
609
+ 8,
610
+ 9,
611
+ 10,
612
+ 11,
613
+ 12,
614
+ 13,
615
+ 14,
616
+ 15,
617
+ 16,
618
+ 17,
619
+ 18,
620
+ 19,
621
+ 20,
622
+ 21,
623
+ 22,
624
+ 23,
625
+ 24,
626
+ 25,
627
+ 26,
628
+ 27,
629
+ 28,
630
+ 29,
631
+ 30,
632
+ 31,
633
+ 32,
634
+ 33,
635
+ 34,
636
+ 35,
637
+ 36,
638
+ 37,
639
+ 38,
640
+ 39
641
+ ],
642
+ "modality_keys": [
643
+ "joints"
644
+ ]
645
+ },
646
+ "state": {
647
+ "delta_indices": [
648
+ 0
649
+ ],
650
+ "modality_keys": [
651
+ "joints"
652
+ ]
653
+ },
654
+ "video": {
655
+ "delta_indices": [
656
+ 0
657
+ ],
658
+ "modality_keys": [
659
+ "cam_high",
660
+ "cam_left_wrist",
661
+ "cam_right_wrist"
662
+ ]
663
+ }
664
+ }
665
+ },
666
+ "shortest_image_edge": null,
667
+ "state_dropout_prob": 0.2,
668
+ "statistics": {
669
+ "robotwin": {}
670
+ },
671
+ "use_albumentations": true,
672
+ "use_mean_std": true,
673
+ "use_percentiles": false,
674
+ "use_relative_action": false
675
+ },
676
+ "qwen3_runtime": "compat_457",
677
+ "state_dropout_prob": 0.2,
678
+ "type": "GrootN17VLA",
679
+ "use_relative_action": false,
680
+ "vla_head": {
681
+ "type": "GrootN17ActionHead"
682
+ },
683
+ "vlm_backbone": {
684
+ "load_bf16": false,
685
+ "model_config": {
686
+ "architectures": [
687
+ "Qwen3VLForConditionalGeneration"
688
+ ],
689
+ "image_token_id": 151655,
690
+ "text_config": {
691
+ "attention_bias": false,
692
+ "attention_dropout": 0.0,
693
+ "head_dim": 128,
694
+ "hidden_act": "silu",
695
+ "hidden_size": 2048,
696
+ "initializer_range": 0.02,
697
+ "intermediate_size": 6144,
698
+ "max_position_embeddings": 262144,
699
+ "model_type": "qwen3_vl_text",
700
+ "num_attention_heads": 16,
701
+ "num_hidden_layers": 28,
702
+ "num_key_value_heads": 8,
703
+ "rms_norm_eps": 1e-06,
704
+ "rope_parameters": {
705
+ "mrope_interleaved": true,
706
+ "mrope_section": [
707
+ 24,
708
+ 20,
709
+ 20
710
+ ],
711
+ "rope_theta": 5000000.0,
712
+ "rope_type": "default"
713
+ },
714
+ "use_cache": false,
715
+ "vocab_size": 151936
716
+ },
717
+ "tie_word_embeddings": false,
718
+ "video_token_id": 151656,
719
+ "vision_config": {
720
+ "deepstack_visual_indexes": [
721
+ 5,
722
+ 11,
723
+ 17
724
+ ],
725
+ "depth": 24,
726
+ "hidden_act": "gelu_pytorch_tanh",
727
+ "hidden_size": 1024,
728
+ "in_channels": 3,
729
+ "initializer_range": 0.02,
730
+ "intermediate_size": 4096,
731
+ "model_type": "qwen3_vl_vision",
732
+ "num_heads": 16,
733
+ "num_position_embeddings": 2304,
734
+ "out_hidden_size": 2048,
735
+ "patch_size": 16,
736
+ "spatial_merge_size": 2,
737
+ "temporal_patch_size": 2
738
+ },
739
+ "vision_end_token_id": 151653,
740
+ "vision_start_token_id": 151652
741
+ },
742
+ "qwen3_runtime": "compat_457",
743
+ "reproject_vision": false,
744
+ "select_layer": 16,
745
+ "type": "GrootN17Qwen3Backbone",
746
+ "use_flash_attention": true
747
+ }
748
+ },
749
+ "model": {
750
+ "embodiment_tag": "robotwin",
751
+ "freeze_vlm_backbone": false,
752
+ "load_metadata": true,
753
+ "model_path": "./checkpoints/GR00T-N1.7-3B",
754
+ "processor_kwargs": {
755
+ "apply_sincos_state_encoding": false,
756
+ "clip_outliers": false,
757
+ "color_jitter_params": {
758
+ "brightness": 0.3,
759
+ "contrast": 0.4,
760
+ "hue": 0.08,
761
+ "saturation": 0.5
762
+ },
763
+ "crop_fraction": null,
764
+ "embodiment_id_mapping": {
765
+ "robotwin": 0
766
+ },
767
+ "formalize_language": true,
768
+ "image_crop_size": [
769
+ 230,
770
+ 230
771
+ ],
772
+ "image_target_size": [
773
+ 256,
774
+ 256
775
+ ],
776
+ "max_action_dim": 132,
777
+ "max_action_horizon": 40,
778
+ "max_state_dim": 132,
779
+ "modality_configs": {
780
+ "robotwin": {
781
+ "action": {
782
+ "delta_indices": [
783
+ 0,
784
+ 1,
785
+ 2,
786
+ 3,
787
+ 4,
788
+ 5,
789
+ 6,
790
+ 7,
791
+ 8,
792
+ 9,
793
+ 10,
794
+ 11,
795
+ 12,
796
+ 13,
797
+ 14,
798
+ 15,
799
+ 16,
800
+ 17,
801
+ 18,
802
+ 19,
803
+ 20,
804
+ 21,
805
+ 22,
806
+ 23,
807
+ 24,
808
+ 25,
809
+ 26,
810
+ 27,
811
+ 28,
812
+ 29,
813
+ 30,
814
+ 31,
815
+ 32,
816
+ 33,
817
+ 34,
818
+ 35,
819
+ 36,
820
+ 37,
821
+ 38,
822
+ 39
823
+ ],
824
+ "modality_keys": [
825
+ "joints"
826
+ ]
827
+ },
828
+ "state": {
829
+ "delta_indices": [
830
+ 0
831
+ ],
832
+ "modality_keys": [
833
+ "joints"
834
+ ]
835
+ },
836
+ "video": {
837
+ "delta_indices": [
838
+ 0
839
+ ],
840
+ "modality_keys": [
841
+ "cam_high",
842
+ "cam_left_wrist",
843
+ "cam_right_wrist"
844
+ ]
845
+ }
846
+ }
847
+ },
848
+ "shortest_image_edge": null,
849
+ "state_dropout_prob": 0.2,
850
+ "statistics": {
851
+ "robotwin": {}
852
+ },
853
+ "use_albumentations": true,
854
+ "use_mean_std": true,
855
+ "use_percentiles": false,
856
+ "use_relative_action": false
857
+ },
858
+ "qwen3_runtime": "compat_457",
859
+ "state_dropout_prob": 0.2,
860
+ "type": "GrootN17VLA",
861
+ "use_relative_action": false,
862
+ "vla_head": {
863
+ "type": "GrootN17ActionHead"
864
+ },
865
+ "vlm_backbone": {
866
+ "load_bf16": false,
867
+ "model_config": {
868
+ "architectures": [
869
+ "Qwen3VLForConditionalGeneration"
870
+ ],
871
+ "image_token_id": 151655,
872
+ "text_config": {
873
+ "attention_bias": false,
874
+ "attention_dropout": 0.0,
875
+ "head_dim": 128,
876
+ "hidden_act": "silu",
877
+ "hidden_size": 2048,
878
+ "initializer_range": 0.02,
879
+ "intermediate_size": 6144,
880
+ "max_position_embeddings": 262144,
881
+ "model_type": "qwen3_vl_text",
882
+ "num_attention_heads": 16,
883
+ "num_hidden_layers": 28,
884
+ "num_key_value_heads": 8,
885
+ "rms_norm_eps": 1e-06,
886
+ "rope_parameters": {
887
+ "mrope_interleaved": true,
888
+ "mrope_section": [
889
+ 24,
890
+ 20,
891
+ 20
892
+ ],
893
+ "rope_theta": 5000000.0,
894
+ "rope_type": "default"
895
+ },
896
+ "use_cache": false,
897
+ "vocab_size": 151936
898
+ },
899
+ "tie_word_embeddings": false,
900
+ "video_token_id": 151656,
901
+ "vision_config": {
902
+ "deepstack_visual_indexes": [
903
+ 5,
904
+ 11,
905
+ 17
906
+ ],
907
+ "depth": 24,
908
+ "hidden_act": "gelu_pytorch_tanh",
909
+ "hidden_size": 1024,
910
+ "in_channels": 3,
911
+ "initializer_range": 0.02,
912
+ "intermediate_size": 4096,
913
+ "model_type": "qwen3_vl_vision",
914
+ "num_heads": 16,
915
+ "num_position_embeddings": 2304,
916
+ "out_hidden_size": 2048,
917
+ "patch_size": 16,
918
+ "spatial_merge_size": 2,
919
+ "temporal_patch_size": 2
920
+ },
921
+ "vision_end_token_id": 151653,
922
+ "vision_start_token_id": 151652
923
+ },
924
+ "qwen3_runtime": "compat_457",
925
+ "reproject_vision": false,
926
+ "select_layer": 16,
927
+ "type": "GrootN17Qwen3Backbone",
928
+ "use_flash_attention": true
929
+ }
930
+ },
931
+ "runner": {
932
+ "change_key_name": false,
933
+ "collator": {
934
+ "keys": [
935
+ "lang_tokens",
936
+ "lang_masks",
937
+ "images",
938
+ "image_grid_thw",
939
+ "states",
940
+ "actions",
941
+ "action_masks",
942
+ "embodiment_ids"
943
+ ],
944
+ "type": "DictCollator"
945
+ },
946
+ "enable_gradient_checkpointing": true,
947
+ "enable_mixed_precision_training": true,
948
+ "grad_accumulation_steps": 2,
949
+ "lr_scheduler": {
950
+ "type": "linear-warmup+cosine-decay",
951
+ "warmup_ratio": 0.05
952
+ },
953
+ "max_epochs": 5,
954
+ "max_grad_norm": 1.0,
955
+ "max_keep_ckpts": 3,
956
+ "max_steps": null,
957
+ "metric": {
958
+ "active_trackers": [
959
+ "jsonl",
960
+ "wandb"
961
+ ],
962
+ "grad_accumulation_steps": 2,
963
+ "run_dir": "work_dirs",
964
+ "type": "VLAMetric",
965
+ "window_size": 1
966
+ },
967
+ "mixed_precision_dtype": "bf16",
968
+ "optimizer": {
969
+ "lr": 1e-05,
970
+ "type": "AdamW",
971
+ "weight_decay": 1e-05
972
+ },
973
+ "sampler": null,
974
+ "save_epoch_interval": 1,
975
+ "save_iter_interval": 5000,
976
+ "sharding_strategy": "full-shard",
977
+ "type": "FSDPTrainRunner"
978
+ },
979
+ "train_dataloader": {
980
+ "dataset": {
981
+ "datasets": [
982
+ {
983
+ "action_key": "action",
984
+ "action_window_size": 40,
985
+ "data_root_path": [
986
+ "datasets/robotwin_clean_lerobotv2.1",
987
+ "datasets/robotwin_randomized_lerobotv2.1"
988
+ ],
989
+ "repeat_to_full_length": false,
990
+ "require_full_window": true,
991
+ "statistic_name": "robotwin_all",
992
+ "train_episode_fraction": 1.0,
993
+ "transforms": [
994
+ {
995
+ "embodiment_id": 0,
996
+ "name_mappings": {
997
+ "actions": [
998
+ "actions"
999
+ ],
1000
+ "observation.state": [
1001
+ "states"
1002
+ ]
1003
+ },
1004
+ "parquet_keys": [
1005
+ "observation.state",
1006
+ "timestamp",
1007
+ "actions",
1008
+ "info",
1009
+ "stats",
1010
+ "action_masks"
1011
+ ],
1012
+ "type": "ProcessParquetInputs",
1013
+ "video_backend": "torchcodec",
1014
+ "video_keys": [
1015
+ "observation.images.cam_high",
1016
+ "observation.images.cam_left_wrist",
1017
+ "observation.images.cam_right_wrist"
1018
+ ]
1019
+ },
1020
+ {
1021
+ "action_dim": 132,
1022
+ "action_key": "action",
1023
+ "clip_norm": false,
1024
+ "norm_type": "mean_std",
1025
+ "normalization_epsilon": 1e-06,
1026
+ "preserve_input_dtype": true,
1027
+ "state_dim": 132,
1028
+ "state_key": "proprio",
1029
+ "type": "NormalizeStatesAndActions"
1030
+ },
1031
+ {
1032
+ "action_horizon": 40,
1033
+ "state_dropout_prob": 0.2,
1034
+ "state_history_length": 1,
1035
+ "type": "PrepareStateActionTargets",
1036
+ "valid_action_dim": 14
1037
+ },
1038
+ {
1039
+ "embodiment_tag": "robotwin",
1040
+ "image_key": "images",
1041
+ "output_image_key": "images",
1042
+ "processor_kwargs": {
1043
+ "apply_sincos_state_encoding": false,
1044
+ "clip_outliers": false,
1045
+ "color_jitter_params": {
1046
+ "brightness": 0.3,
1047
+ "contrast": 0.4,
1048
+ "hue": 0.08,
1049
+ "saturation": 0.5
1050
+ },
1051
+ "crop_fraction": null,
1052
+ "embodiment_id_mapping": {
1053
+ "robotwin": 0
1054
+ },
1055
+ "formalize_language": true,
1056
+ "image_crop_size": [
1057
+ 230,
1058
+ 230
1059
+ ],
1060
+ "image_target_size": [
1061
+ 256,
1062
+ 256
1063
+ ],
1064
+ "max_action_dim": 132,
1065
+ "max_action_horizon": 40,
1066
+ "max_state_dim": 132,
1067
+ "modality_configs": {
1068
+ "robotwin": {
1069
+ "action": {
1070
+ "delta_indices": [
1071
+ 0,
1072
+ 1,
1073
+ 2,
1074
+ 3,
1075
+ 4,
1076
+ 5,
1077
+ 6,
1078
+ 7,
1079
+ 8,
1080
+ 9,
1081
+ 10,
1082
+ 11,
1083
+ 12,
1084
+ 13,
1085
+ 14,
1086
+ 15,
1087
+ 16,
1088
+ 17,
1089
+ 18,
1090
+ 19,
1091
+ 20,
1092
+ 21,
1093
+ 22,
1094
+ 23,
1095
+ 24,
1096
+ 25,
1097
+ 26,
1098
+ 27,
1099
+ 28,
1100
+ 29,
1101
+ 30,
1102
+ 31,
1103
+ 32,
1104
+ 33,
1105
+ 34,
1106
+ 35,
1107
+ 36,
1108
+ 37,
1109
+ 38,
1110
+ 39
1111
+ ],
1112
+ "modality_keys": [
1113
+ "joints"
1114
+ ]
1115
+ },
1116
+ "state": {
1117
+ "delta_indices": [
1118
+ 0
1119
+ ],
1120
+ "modality_keys": [
1121
+ "joints"
1122
+ ]
1123
+ },
1124
+ "video": {
1125
+ "delta_indices": [
1126
+ 0
1127
+ ],
1128
+ "modality_keys": [
1129
+ "cam_high",
1130
+ "cam_left_wrist",
1131
+ "cam_right_wrist"
1132
+ ]
1133
+ }
1134
+ }
1135
+ },
1136
+ "shortest_image_edge": null,
1137
+ "state_dropout_prob": 0.2,
1138
+ "statistics": {
1139
+ "robotwin": {}
1140
+ },
1141
+ "use_albumentations": true,
1142
+ "use_mean_std": true,
1143
+ "use_percentiles": false,
1144
+ "use_relative_action": false
1145
+ },
1146
+ "train_mode": true,
1147
+ "type": "GrootN17ImageAugmentation"
1148
+ },
1149
+ {
1150
+ "image_mean": [
1151
+ 0.5,
1152
+ 0.5,
1153
+ 0.5
1154
+ ],
1155
+ "image_std": [
1156
+ 0.5,
1157
+ 0.5,
1158
+ 0.5
1159
+ ],
1160
+ "img_key": "images",
1161
+ "merge_size": 2,
1162
+ "patch_size": 16,
1163
+ "size": {
1164
+ "longest_edge": 16777216,
1165
+ "shortest_edge": 65536
1166
+ },
1167
+ "temporal_patch_size": 2,
1168
+ "to_tensor": true,
1169
+ "type": "QWen2VLImageTransform"
1170
+ },
1171
+ {
1172
+ "add_assistant_stub": false,
1173
+ "add_system": false,
1174
+ "attention_mask_dtype": "int64",
1175
+ "image_grid_thw_key": "image_grid_thw",
1176
+ "image_merge_size": 2,
1177
+ "image_tag_template": "",
1178
+ "img_context_token": "<|image_pad|>",
1179
+ "img_end": "<|vision_end|>",
1180
+ "img_start": "<|vision_start|>",
1181
+ "img_tokens_source": "from_image_grid_thw",
1182
+ "lowercase_task_description": true,
1183
+ "max_len": 512,
1184
+ "output_keys": [
1185
+ "lang_tokens",
1186
+ "lang_masks",
1187
+ "images",
1188
+ "image_grid_thw",
1189
+ "states",
1190
+ "actions",
1191
+ "action_masks",
1192
+ "embodiment_ids"
1193
+ ],
1194
+ "padding_side": "left",
1195
+ "strip_task_punctuation": true,
1196
+ "task_pos": "after_images",
1197
+ "tokenizer": {
1198
+ "model_path": "fluxvla/models/third_party_models/qwen3_tokenizer",
1199
+ "padding_side": "left",
1200
+ "trust_remote_code": false,
1201
+ "type": "PretrainedTokenizer"
1202
+ },
1203
+ "truncate": false,
1204
+ "type": "ProcessPromptsWithImage",
1205
+ "use_eos_as_pad": false
1206
+ }
1207
+ ],
1208
+ "type": "ParquetDataset",
1209
+ "use_delta": false,
1210
+ "window_start_idx": 0
1211
+ }
1212
+ ],
1213
+ "name_mappings": {
1214
+ "action": [
1215
+ "action"
1216
+ ],
1217
+ "observation.state": [
1218
+ "proprio"
1219
+ ]
1220
+ },
1221
+ "reshuffle_each_epoch": true,
1222
+ "seed": 42,
1223
+ "shuffle": true,
1224
+ "statistic_keys": [
1225
+ "observation.state",
1226
+ "timestamp",
1227
+ "action"
1228
+ ],
1229
+ "statistic_name": "robotwin_all",
1230
+ "type": "DistributedRepeatingDataset"
1231
+ },
1232
+ "per_device_batch_size": 8,
1233
+ "per_device_num_workers": 4
1234
+ }
1235
+ }
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/config.yaml ADDED
@@ -0,0 +1,1045 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ACTIVE_TRACKERS:
2
+ - jsonl
3
+ - wandb
4
+ _DATA_PATHS:
5
+ - datasets/robotwin_clean_lerobotv2.1
6
+ - datasets/robotwin_randomized_lerobotv2.1
7
+ _N17_INIT_CKPT: ./checkpoints/GR00T-N1.7-3B
8
+ _N17_MODALITY_CONFIGS:
9
+ robotwin:
10
+ action:
11
+ delta_indices:
12
+ - 0
13
+ - 1
14
+ - 2
15
+ - 3
16
+ - 4
17
+ - 5
18
+ - 6
19
+ - 7
20
+ - 8
21
+ - 9
22
+ - 10
23
+ - 11
24
+ - 12
25
+ - 13
26
+ - 14
27
+ - 15
28
+ - 16
29
+ - 17
30
+ - 18
31
+ - 19
32
+ - 20
33
+ - 21
34
+ - 22
35
+ - 23
36
+ - 24
37
+ - 25
38
+ - 26
39
+ - 27
40
+ - 28
41
+ - 29
42
+ - 30
43
+ - 31
44
+ - 32
45
+ - 33
46
+ - 34
47
+ - 35
48
+ - 36
49
+ - 37
50
+ - 38
51
+ - 39
52
+ modality_keys:
53
+ - joints
54
+ state:
55
+ delta_indices:
56
+ - 0
57
+ modality_keys:
58
+ - joints
59
+ video:
60
+ delta_indices:
61
+ - 0
62
+ modality_keys:
63
+ - cam_high
64
+ - cam_left_wrist
65
+ - cam_right_wrist
66
+ _PROCESSOR_KWARGS:
67
+ apply_sincos_state_encoding: false
68
+ clip_outliers: false
69
+ color_jitter_params:
70
+ brightness: 0.3
71
+ contrast: 0.4
72
+ hue: 0.08
73
+ saturation: 0.5
74
+ crop_fraction: null
75
+ embodiment_id_mapping:
76
+ robotwin: 0
77
+ formalize_language: true
78
+ image_crop_size:
79
+ - 230
80
+ - 230
81
+ image_target_size:
82
+ - 256
83
+ - 256
84
+ max_action_dim: 132
85
+ max_action_horizon: 40
86
+ max_state_dim: 132
87
+ modality_configs:
88
+ robotwin:
89
+ action:
90
+ delta_indices:
91
+ - 0
92
+ - 1
93
+ - 2
94
+ - 3
95
+ - 4
96
+ - 5
97
+ - 6
98
+ - 7
99
+ - 8
100
+ - 9
101
+ - 10
102
+ - 11
103
+ - 12
104
+ - 13
105
+ - 14
106
+ - 15
107
+ - 16
108
+ - 17
109
+ - 18
110
+ - 19
111
+ - 20
112
+ - 21
113
+ - 22
114
+ - 23
115
+ - 24
116
+ - 25
117
+ - 26
118
+ - 27
119
+ - 28
120
+ - 29
121
+ - 30
122
+ - 31
123
+ - 32
124
+ - 33
125
+ - 34
126
+ - 35
127
+ - 36
128
+ - 37
129
+ - 38
130
+ - 39
131
+ modality_keys:
132
+ - joints
133
+ state:
134
+ delta_indices:
135
+ - 0
136
+ modality_keys:
137
+ - joints
138
+ video:
139
+ delta_indices:
140
+ - 0
141
+ modality_keys:
142
+ - cam_high
143
+ - cam_left_wrist
144
+ - cam_right_wrist
145
+ shortest_image_edge: null
146
+ state_dropout_prob: 0.2
147
+ statistics:
148
+ robotwin: {}
149
+ use_albumentations: true
150
+ use_mean_std: true
151
+ use_percentiles: false
152
+ use_relative_action: false
153
+ _QWEN3_VL_CONFIG:
154
+ architectures:
155
+ - Qwen3VLForConditionalGeneration
156
+ image_token_id: 151655
157
+ text_config:
158
+ attention_bias: false
159
+ attention_dropout: 0.0
160
+ head_dim: 128
161
+ hidden_act: silu
162
+ hidden_size: 2048
163
+ initializer_range: 0.02
164
+ intermediate_size: 6144
165
+ max_position_embeddings: 262144
166
+ model_type: qwen3_vl_text
167
+ num_attention_heads: 16
168
+ num_hidden_layers: 28
169
+ num_key_value_heads: 8
170
+ rms_norm_eps: 1.0e-06
171
+ rope_parameters:
172
+ mrope_interleaved: true
173
+ mrope_section:
174
+ - 24
175
+ - 20
176
+ - 20
177
+ rope_theta: 5000000.0
178
+ rope_type: default
179
+ use_cache: false
180
+ vocab_size: 151936
181
+ tie_word_embeddings: false
182
+ video_token_id: 151656
183
+ vision_config:
184
+ deepstack_visual_indexes:
185
+ - 5
186
+ - 11
187
+ - 17
188
+ depth: 24
189
+ hidden_act: gelu_pytorch_tanh
190
+ hidden_size: 1024
191
+ in_channels: 3
192
+ initializer_range: 0.02
193
+ intermediate_size: 4096
194
+ model_type: qwen3_vl_vision
195
+ num_heads: 16
196
+ num_position_embeddings: 2304
197
+ out_hidden_size: 2048
198
+ patch_size: 16
199
+ spatial_merge_size: 2
200
+ temporal_patch_size: 2
201
+ vision_end_token_id: 151653
202
+ vision_start_token_id: 151652
203
+ _QWEN_TOKENIZER_PATH: fluxvla/models/third_party_models/qwen3_tokenizer
204
+ _STATISTIC_NAME: robotwin_all
205
+ _TASK_NAMES:
206
+ - adjust_bottle
207
+ - beat_block_hammer
208
+ - blocks_ranking_rgb
209
+ - blocks_ranking_size
210
+ - click_alarmclock
211
+ - click_bell
212
+ - dump_bin_bigbin
213
+ - grab_roller
214
+ - handover_block
215
+ - handover_mic
216
+ - hanging_mug
217
+ - lift_pot
218
+ - move_can_pot
219
+ - move_pillbottle_pad
220
+ - move_playingcard_away
221
+ - move_stapler_pad
222
+ - open_laptop
223
+ - open_microwave
224
+ - pick_diverse_bottles
225
+ - pick_dual_bottles
226
+ - place_a2b_left
227
+ - place_a2b_right
228
+ - place_bread_basket
229
+ - place_bread_skillet
230
+ - place_burger_fries
231
+ - place_can_basket
232
+ - place_cans_plasticbox
233
+ - place_container_plate
234
+ - place_dual_shoes
235
+ - place_empty_cup
236
+ - place_fan
237
+ - place_mouse_pad
238
+ - place_object_basket
239
+ - place_object_scale
240
+ - place_object_stand
241
+ - place_phone_stand
242
+ - place_shoe
243
+ - press_stapler
244
+ - put_bottles_dustbin
245
+ - put_object_cabinet
246
+ - rotate_qrcode
247
+ - scan_object
248
+ - shake_bottle
249
+ - shake_bottle_horizontally
250
+ - stack_blocks_three
251
+ - stack_blocks_two
252
+ - stack_bowls_three
253
+ - stack_bowls_two
254
+ - stamp_seal
255
+ - turn_switch
256
+ eval:
257
+ dataset:
258
+ embodiment_id: 0
259
+ img_keys:
260
+ - cam_high
261
+ - cam_left_wrist
262
+ - cam_right_wrist
263
+ inject_model_path: false
264
+ transforms:
265
+ - action_dim: 132
266
+ action_key: null
267
+ clip_norm: false
268
+ norm_type: mean_std
269
+ normalization_epsilon: 1.0e-06
270
+ preserve_input_dtype: true
271
+ state_dim: 132
272
+ state_key: proprio
273
+ type: NormalizeStatesAndActions
274
+ - action_horizon: 40
275
+ state_dropout_prob: 0.0
276
+ state_history_length: 1
277
+ type: PrepareStateActionTargets
278
+ valid_action_dim: 14
279
+ - embodiment_tag: robotwin
280
+ image_key: images
281
+ output_image_key: images
282
+ processor_kwargs:
283
+ apply_sincos_state_encoding: false
284
+ clip_outliers: false
285
+ color_jitter_params:
286
+ brightness: 0.3
287
+ contrast: 0.4
288
+ hue: 0.08
289
+ saturation: 0.5
290
+ crop_fraction: null
291
+ embodiment_id_mapping:
292
+ robotwin: 0
293
+ formalize_language: true
294
+ image_crop_size:
295
+ - 230
296
+ - 230
297
+ image_target_size:
298
+ - 256
299
+ - 256
300
+ max_action_dim: 132
301
+ max_action_horizon: 40
302
+ max_state_dim: 132
303
+ modality_configs:
304
+ robotwin:
305
+ action:
306
+ delta_indices:
307
+ - 0
308
+ - 1
309
+ - 2
310
+ - 3
311
+ - 4
312
+ - 5
313
+ - 6
314
+ - 7
315
+ - 8
316
+ - 9
317
+ - 10
318
+ - 11
319
+ - 12
320
+ - 13
321
+ - 14
322
+ - 15
323
+ - 16
324
+ - 17
325
+ - 18
326
+ - 19
327
+ - 20
328
+ - 21
329
+ - 22
330
+ - 23
331
+ - 24
332
+ - 25
333
+ - 26
334
+ - 27
335
+ - 28
336
+ - 29
337
+ - 30
338
+ - 31
339
+ - 32
340
+ - 33
341
+ - 34
342
+ - 35
343
+ - 36
344
+ - 37
345
+ - 38
346
+ - 39
347
+ modality_keys:
348
+ - joints
349
+ state:
350
+ delta_indices:
351
+ - 0
352
+ modality_keys:
353
+ - joints
354
+ video:
355
+ delta_indices:
356
+ - 0
357
+ modality_keys:
358
+ - cam_high
359
+ - cam_left_wrist
360
+ - cam_right_wrist
361
+ shortest_image_edge: null
362
+ state_dropout_prob: 0.2
363
+ statistics:
364
+ robotwin: {}
365
+ use_albumentations: true
366
+ use_mean_std: true
367
+ use_percentiles: false
368
+ use_relative_action: false
369
+ train_mode: false
370
+ type: GrootN17ImageAugmentation
371
+ - image_mean:
372
+ - 0.5
373
+ - 0.5
374
+ - 0.5
375
+ image_std:
376
+ - 0.5
377
+ - 0.5
378
+ - 0.5
379
+ img_key: images
380
+ merge_size: 2
381
+ patch_size: 16
382
+ size:
383
+ longest_edge: 16777216
384
+ shortest_edge: 65536
385
+ temporal_patch_size: 2
386
+ to_tensor: true
387
+ type: QWen2VLImageTransform
388
+ - add_assistant_stub: false
389
+ add_system: false
390
+ attention_mask_dtype: int64
391
+ image_grid_thw_key: image_grid_thw
392
+ image_merge_size: 2
393
+ image_tag_template: ''
394
+ img_context_token: <|image_pad|>
395
+ img_end: <|vision_end|>
396
+ img_start: <|vision_start|>
397
+ img_tokens_source: from_image_grid_thw
398
+ lowercase_task_description: true
399
+ max_len: 512
400
+ output_keys:
401
+ - lang_tokens
402
+ - lang_masks
403
+ - images
404
+ - image_grid_thw
405
+ - states
406
+ - embodiment_ids
407
+ padding_side: left
408
+ strip_task_punctuation: true
409
+ task_pos: after_images
410
+ tokenizer:
411
+ model_path: fluxvla/models/third_party_models/qwen3_tokenizer
412
+ padding_side: left
413
+ trust_remote_code: false
414
+ type: PretrainedTokenizer
415
+ truncate: false
416
+ type: ProcessPromptsWithImage
417
+ use_eos_as_pad: false
418
+ type: PrivateInferenceDataset
419
+ denormalize_action:
420
+ action_dim: 14
421
+ invert_gripper_action: false
422
+ norm_type: mean_std
423
+ normalize_gripper_action: false
424
+ type: DenormalizePrivateAction
425
+ eval_chunk_size: 40
426
+ instruction_type: unseen
427
+ mixed_precision_dtype: bf16
428
+ model_family: groot_n17
429
+ num_trials_per_task: 100
430
+ save_video: false
431
+ seed: 7
432
+ task_list:
433
+ - adjust_bottle
434
+ - beat_block_hammer
435
+ - blocks_ranking_rgb
436
+ - blocks_ranking_size
437
+ - click_alarmclock
438
+ - click_bell
439
+ - dump_bin_bigbin
440
+ - grab_roller
441
+ - handover_block
442
+ - handover_mic
443
+ - hanging_mug
444
+ - lift_pot
445
+ - move_can_pot
446
+ - move_pillbottle_pad
447
+ - move_playingcard_away
448
+ - move_stapler_pad
449
+ - open_laptop
450
+ - open_microwave
451
+ - pick_diverse_bottles
452
+ - pick_dual_bottles
453
+ - place_a2b_left
454
+ - place_a2b_right
455
+ - place_bread_basket
456
+ - place_bread_skillet
457
+ - place_burger_fries
458
+ - place_can_basket
459
+ - place_cans_plasticbox
460
+ - place_container_plate
461
+ - place_dual_shoes
462
+ - place_empty_cup
463
+ - place_fan
464
+ - place_mouse_pad
465
+ - place_object_basket
466
+ - place_object_scale
467
+ - place_object_stand
468
+ - place_phone_stand
469
+ - place_shoe
470
+ - press_stapler
471
+ - put_bottles_dustbin
472
+ - put_object_cabinet
473
+ - rotate_qrcode
474
+ - scan_object
475
+ - shake_bottle
476
+ - shake_bottle_horizontally
477
+ - stack_blocks_three
478
+ - stack_blocks_two
479
+ - stack_bowls_three
480
+ - stack_bowls_two
481
+ - stamp_seal
482
+ - turn_switch
483
+ task_suite_name:
484
+ - clean
485
+ - random
486
+ type: RobotwinEvalRunner
487
+ unnorm_key: robotwin_all
488
+ inference_model:
489
+ embodiment_tag: robotwin
490
+ freeze_vlm_backbone: false
491
+ load_metadata: false
492
+ load_pretrained_weights: false
493
+ model_path: null
494
+ processor_kwargs:
495
+ apply_sincos_state_encoding: false
496
+ clip_outliers: false
497
+ color_jitter_params:
498
+ brightness: 0.3
499
+ contrast: 0.4
500
+ hue: 0.08
501
+ saturation: 0.5
502
+ crop_fraction: null
503
+ embodiment_id_mapping:
504
+ robotwin: 0
505
+ formalize_language: true
506
+ image_crop_size:
507
+ - 230
508
+ - 230
509
+ image_target_size:
510
+ - 256
511
+ - 256
512
+ max_action_dim: 132
513
+ max_action_horizon: 40
514
+ max_state_dim: 132
515
+ modality_configs:
516
+ robotwin:
517
+ action:
518
+ delta_indices:
519
+ - 0
520
+ - 1
521
+ - 2
522
+ - 3
523
+ - 4
524
+ - 5
525
+ - 6
526
+ - 7
527
+ - 8
528
+ - 9
529
+ - 10
530
+ - 11
531
+ - 12
532
+ - 13
533
+ - 14
534
+ - 15
535
+ - 16
536
+ - 17
537
+ - 18
538
+ - 19
539
+ - 20
540
+ - 21
541
+ - 22
542
+ - 23
543
+ - 24
544
+ - 25
545
+ - 26
546
+ - 27
547
+ - 28
548
+ - 29
549
+ - 30
550
+ - 31
551
+ - 32
552
+ - 33
553
+ - 34
554
+ - 35
555
+ - 36
556
+ - 37
557
+ - 38
558
+ - 39
559
+ modality_keys:
560
+ - joints
561
+ state:
562
+ delta_indices:
563
+ - 0
564
+ modality_keys:
565
+ - joints
566
+ video:
567
+ delta_indices:
568
+ - 0
569
+ modality_keys:
570
+ - cam_high
571
+ - cam_left_wrist
572
+ - cam_right_wrist
573
+ shortest_image_edge: null
574
+ state_dropout_prob: 0.2
575
+ statistics:
576
+ robotwin: {}
577
+ use_albumentations: true
578
+ use_mean_std: true
579
+ use_percentiles: false
580
+ use_relative_action: false
581
+ qwen3_runtime: compat_457
582
+ state_dropout_prob: 0.2
583
+ type: GrootN17VLA
584
+ use_relative_action: false
585
+ vla_head:
586
+ type: GrootN17ActionHead
587
+ vlm_backbone:
588
+ load_bf16: false
589
+ model_config:
590
+ architectures:
591
+ - Qwen3VLForConditionalGeneration
592
+ image_token_id: 151655
593
+ text_config:
594
+ attention_bias: false
595
+ attention_dropout: 0.0
596
+ head_dim: 128
597
+ hidden_act: silu
598
+ hidden_size: 2048
599
+ initializer_range: 0.02
600
+ intermediate_size: 6144
601
+ max_position_embeddings: 262144
602
+ model_type: qwen3_vl_text
603
+ num_attention_heads: 16
604
+ num_hidden_layers: 28
605
+ num_key_value_heads: 8
606
+ rms_norm_eps: 1.0e-06
607
+ rope_parameters:
608
+ mrope_interleaved: true
609
+ mrope_section:
610
+ - 24
611
+ - 20
612
+ - 20
613
+ rope_theta: 5000000.0
614
+ rope_type: default
615
+ use_cache: false
616
+ vocab_size: 151936
617
+ tie_word_embeddings: false
618
+ video_token_id: 151656
619
+ vision_config:
620
+ deepstack_visual_indexes:
621
+ - 5
622
+ - 11
623
+ - 17
624
+ depth: 24
625
+ hidden_act: gelu_pytorch_tanh
626
+ hidden_size: 1024
627
+ in_channels: 3
628
+ initializer_range: 0.02
629
+ intermediate_size: 4096
630
+ model_type: qwen3_vl_vision
631
+ num_heads: 16
632
+ num_position_embeddings: 2304
633
+ out_hidden_size: 2048
634
+ patch_size: 16
635
+ spatial_merge_size: 2
636
+ temporal_patch_size: 2
637
+ vision_end_token_id: 151653
638
+ vision_start_token_id: 151652
639
+ qwen3_runtime: compat_457
640
+ reproject_vision: false
641
+ select_layer: 16
642
+ type: GrootN17Qwen3Backbone
643
+ use_flash_attention: true
644
+ model:
645
+ embodiment_tag: robotwin
646
+ freeze_vlm_backbone: false
647
+ load_metadata: true
648
+ model_path: ./checkpoints/GR00T-N1.7-3B
649
+ processor_kwargs:
650
+ apply_sincos_state_encoding: false
651
+ clip_outliers: false
652
+ color_jitter_params:
653
+ brightness: 0.3
654
+ contrast: 0.4
655
+ hue: 0.08
656
+ saturation: 0.5
657
+ crop_fraction: null
658
+ embodiment_id_mapping:
659
+ robotwin: 0
660
+ formalize_language: true
661
+ image_crop_size:
662
+ - 230
663
+ - 230
664
+ image_target_size:
665
+ - 256
666
+ - 256
667
+ max_action_dim: 132
668
+ max_action_horizon: 40
669
+ max_state_dim: 132
670
+ modality_configs:
671
+ robotwin:
672
+ action:
673
+ delta_indices:
674
+ - 0
675
+ - 1
676
+ - 2
677
+ - 3
678
+ - 4
679
+ - 5
680
+ - 6
681
+ - 7
682
+ - 8
683
+ - 9
684
+ - 10
685
+ - 11
686
+ - 12
687
+ - 13
688
+ - 14
689
+ - 15
690
+ - 16
691
+ - 17
692
+ - 18
693
+ - 19
694
+ - 20
695
+ - 21
696
+ - 22
697
+ - 23
698
+ - 24
699
+ - 25
700
+ - 26
701
+ - 27
702
+ - 28
703
+ - 29
704
+ - 30
705
+ - 31
706
+ - 32
707
+ - 33
708
+ - 34
709
+ - 35
710
+ - 36
711
+ - 37
712
+ - 38
713
+ - 39
714
+ modality_keys:
715
+ - joints
716
+ state:
717
+ delta_indices:
718
+ - 0
719
+ modality_keys:
720
+ - joints
721
+ video:
722
+ delta_indices:
723
+ - 0
724
+ modality_keys:
725
+ - cam_high
726
+ - cam_left_wrist
727
+ - cam_right_wrist
728
+ shortest_image_edge: null
729
+ state_dropout_prob: 0.2
730
+ statistics:
731
+ robotwin: {}
732
+ use_albumentations: true
733
+ use_mean_std: true
734
+ use_percentiles: false
735
+ use_relative_action: false
736
+ qwen3_runtime: compat_457
737
+ state_dropout_prob: 0.2
738
+ type: GrootN17VLA
739
+ use_relative_action: false
740
+ vla_head:
741
+ type: GrootN17ActionHead
742
+ vlm_backbone:
743
+ load_bf16: false
744
+ model_config:
745
+ architectures:
746
+ - Qwen3VLForConditionalGeneration
747
+ image_token_id: 151655
748
+ text_config:
749
+ attention_bias: false
750
+ attention_dropout: 0.0
751
+ head_dim: 128
752
+ hidden_act: silu
753
+ hidden_size: 2048
754
+ initializer_range: 0.02
755
+ intermediate_size: 6144
756
+ max_position_embeddings: 262144
757
+ model_type: qwen3_vl_text
758
+ num_attention_heads: 16
759
+ num_hidden_layers: 28
760
+ num_key_value_heads: 8
761
+ rms_norm_eps: 1.0e-06
762
+ rope_parameters:
763
+ mrope_interleaved: true
764
+ mrope_section:
765
+ - 24
766
+ - 20
767
+ - 20
768
+ rope_theta: 5000000.0
769
+ rope_type: default
770
+ use_cache: false
771
+ vocab_size: 151936
772
+ tie_word_embeddings: false
773
+ video_token_id: 151656
774
+ vision_config:
775
+ deepstack_visual_indexes:
776
+ - 5
777
+ - 11
778
+ - 17
779
+ depth: 24
780
+ hidden_act: gelu_pytorch_tanh
781
+ hidden_size: 1024
782
+ in_channels: 3
783
+ initializer_range: 0.02
784
+ intermediate_size: 4096
785
+ model_type: qwen3_vl_vision
786
+ num_heads: 16
787
+ num_position_embeddings: 2304
788
+ out_hidden_size: 2048
789
+ patch_size: 16
790
+ spatial_merge_size: 2
791
+ temporal_patch_size: 2
792
+ vision_end_token_id: 151653
793
+ vision_start_token_id: 151652
794
+ qwen3_runtime: compat_457
795
+ reproject_vision: false
796
+ select_layer: 16
797
+ type: GrootN17Qwen3Backbone
798
+ use_flash_attention: true
799
+ runner:
800
+ change_key_name: false
801
+ collator:
802
+ keys:
803
+ - lang_tokens
804
+ - lang_masks
805
+ - images
806
+ - image_grid_thw
807
+ - states
808
+ - actions
809
+ - action_masks
810
+ - embodiment_ids
811
+ type: DictCollator
812
+ enable_gradient_checkpointing: true
813
+ enable_mixed_precision_training: true
814
+ grad_accumulation_steps: 2
815
+ lr_scheduler:
816
+ type: linear-warmup+cosine-decay
817
+ warmup_ratio: 0.05
818
+ max_epochs: 5
819
+ max_grad_norm: 1.0
820
+ max_keep_ckpts: 3
821
+ max_steps: null
822
+ metric:
823
+ active_trackers:
824
+ - jsonl
825
+ - wandb
826
+ grad_accumulation_steps: 2
827
+ run_dir: work_dirs
828
+ type: VLAMetric
829
+ window_size: 1
830
+ mixed_precision_dtype: bf16
831
+ optimizer:
832
+ lr: 1.0e-05
833
+ type: AdamW
834
+ weight_decay: 1.0e-05
835
+ sampler: null
836
+ save_epoch_interval: 1
837
+ save_iter_interval: 5000
838
+ sharding_strategy: full-shard
839
+ type: FSDPTrainRunner
840
+ train_dataloader:
841
+ dataset:
842
+ datasets:
843
+ - action_key: action
844
+ action_window_size: 40
845
+ data_root_path:
846
+ - datasets/robotwin_clean_lerobotv2.1
847
+ - datasets/robotwin_randomized_lerobotv2.1
848
+ repeat_to_full_length: false
849
+ require_full_window: true
850
+ statistic_name: robotwin_all
851
+ train_episode_fraction: 1.0
852
+ transforms:
853
+ - embodiment_id: 0
854
+ name_mappings:
855
+ actions:
856
+ - actions
857
+ observation.state:
858
+ - states
859
+ parquet_keys:
860
+ - observation.state
861
+ - timestamp
862
+ - actions
863
+ - info
864
+ - stats
865
+ - action_masks
866
+ type: ProcessParquetInputs
867
+ video_backend: torchcodec
868
+ video_keys:
869
+ - observation.images.cam_high
870
+ - observation.images.cam_left_wrist
871
+ - observation.images.cam_right_wrist
872
+ - action_dim: 132
873
+ action_key: action
874
+ clip_norm: false
875
+ norm_type: mean_std
876
+ normalization_epsilon: 1.0e-06
877
+ preserve_input_dtype: true
878
+ state_dim: 132
879
+ state_key: proprio
880
+ type: NormalizeStatesAndActions
881
+ - action_horizon: 40
882
+ state_dropout_prob: 0.2
883
+ state_history_length: 1
884
+ type: PrepareStateActionTargets
885
+ valid_action_dim: 14
886
+ - embodiment_tag: robotwin
887
+ image_key: images
888
+ output_image_key: images
889
+ processor_kwargs:
890
+ apply_sincos_state_encoding: false
891
+ clip_outliers: false
892
+ color_jitter_params:
893
+ brightness: 0.3
894
+ contrast: 0.4
895
+ hue: 0.08
896
+ saturation: 0.5
897
+ crop_fraction: null
898
+ embodiment_id_mapping:
899
+ robotwin: 0
900
+ formalize_language: true
901
+ image_crop_size:
902
+ - 230
903
+ - 230
904
+ image_target_size:
905
+ - 256
906
+ - 256
907
+ max_action_dim: 132
908
+ max_action_horizon: 40
909
+ max_state_dim: 132
910
+ modality_configs:
911
+ robotwin:
912
+ action:
913
+ delta_indices:
914
+ - 0
915
+ - 1
916
+ - 2
917
+ - 3
918
+ - 4
919
+ - 5
920
+ - 6
921
+ - 7
922
+ - 8
923
+ - 9
924
+ - 10
925
+ - 11
926
+ - 12
927
+ - 13
928
+ - 14
929
+ - 15
930
+ - 16
931
+ - 17
932
+ - 18
933
+ - 19
934
+ - 20
935
+ - 21
936
+ - 22
937
+ - 23
938
+ - 24
939
+ - 25
940
+ - 26
941
+ - 27
942
+ - 28
943
+ - 29
944
+ - 30
945
+ - 31
946
+ - 32
947
+ - 33
948
+ - 34
949
+ - 35
950
+ - 36
951
+ - 37
952
+ - 38
953
+ - 39
954
+ modality_keys:
955
+ - joints
956
+ state:
957
+ delta_indices:
958
+ - 0
959
+ modality_keys:
960
+ - joints
961
+ video:
962
+ delta_indices:
963
+ - 0
964
+ modality_keys:
965
+ - cam_high
966
+ - cam_left_wrist
967
+ - cam_right_wrist
968
+ shortest_image_edge: null
969
+ state_dropout_prob: 0.2
970
+ statistics:
971
+ robotwin: {}
972
+ use_albumentations: true
973
+ use_mean_std: true
974
+ use_percentiles: false
975
+ use_relative_action: false
976
+ train_mode: true
977
+ type: GrootN17ImageAugmentation
978
+ - image_mean:
979
+ - 0.5
980
+ - 0.5
981
+ - 0.5
982
+ image_std:
983
+ - 0.5
984
+ - 0.5
985
+ - 0.5
986
+ img_key: images
987
+ merge_size: 2
988
+ patch_size: 16
989
+ size:
990
+ longest_edge: 16777216
991
+ shortest_edge: 65536
992
+ temporal_patch_size: 2
993
+ to_tensor: true
994
+ type: QWen2VLImageTransform
995
+ - add_assistant_stub: false
996
+ add_system: false
997
+ attention_mask_dtype: int64
998
+ image_grid_thw_key: image_grid_thw
999
+ image_merge_size: 2
1000
+ image_tag_template: ''
1001
+ img_context_token: <|image_pad|>
1002
+ img_end: <|vision_end|>
1003
+ img_start: <|vision_start|>
1004
+ img_tokens_source: from_image_grid_thw
1005
+ lowercase_task_description: true
1006
+ max_len: 512
1007
+ output_keys:
1008
+ - lang_tokens
1009
+ - lang_masks
1010
+ - images
1011
+ - image_grid_thw
1012
+ - states
1013
+ - actions
1014
+ - action_masks
1015
+ - embodiment_ids
1016
+ padding_side: left
1017
+ strip_task_punctuation: true
1018
+ task_pos: after_images
1019
+ tokenizer:
1020
+ model_path: fluxvla/models/third_party_models/qwen3_tokenizer
1021
+ padding_side: left
1022
+ trust_remote_code: false
1023
+ type: PretrainedTokenizer
1024
+ truncate: false
1025
+ type: ProcessPromptsWithImage
1026
+ use_eos_as_pad: false
1027
+ type: ParquetDataset
1028
+ use_delta: false
1029
+ window_start_idx: 0
1030
+ name_mappings:
1031
+ action:
1032
+ - action
1033
+ observation.state:
1034
+ - proprio
1035
+ reshuffle_each_epoch: true
1036
+ seed: 42
1037
+ shuffle: true
1038
+ statistic_keys:
1039
+ - observation.state
1040
+ - timestamp
1041
+ - action
1042
+ statistic_name: robotwin_all
1043
+ type: DistributedRepeatingDataset
1044
+ per_device_batch_size: 8
1045
+ per_device_num_workers: 4
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/dataset_statistics.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "robotwin_all": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.23836564500637852,
6
+ 1.129817402830952,
7
+ 0.8068359079301254,
8
+ -0.31024214960817226,
9
+ 0.05489044029082383,
10
+ -0.03797947365911228,
11
+ 0.6655638025405416,
12
+ 0.21664742843549212,
13
+ 1.0790448055651551,
14
+ 0.7875585893326063,
15
+ -0.3211320959513645,
16
+ -0.017501951884490514,
17
+ 0.03539706856287519,
18
+ 0.6794509037859313
19
+ ],
20
+ "std": [
21
+ 0.41515260848742136,
22
+ 1.0045809755922652,
23
+ 0.7768178536932145,
24
+ 0.6732816910017168,
25
+ 0.2708186547486596,
26
+ 0.6197771059972782,
27
+ 0.45465163653888563,
28
+ 0.34920798291604505,
29
+ 1.0249604849195586,
30
+ 0.794372303822,
31
+ 0.6847885016239902,
32
+ 0.24437403723179849,
33
+ 0.6142938232023921,
34
+ 0.44978408667126524
35
+ ],
36
+ "min": [
37
+ -7.552278995513916,
38
+ -0.36354875564575195,
39
+ -0.18577136099338531,
40
+ -1.956291913986206,
41
+ -1.6801013946533203,
42
+ -7.678869724273682,
43
+ 0.0,
44
+ -8.539926528930664,
45
+ -0.6294453740119934,
46
+ -0.07775841653347015,
47
+ -2.1328067779541016,
48
+ -2.1285502910614014,
49
+ -8.228925704956055,
50
+ 0.0
51
+ ],
52
+ "max": [
53
+ 6.45659065246582,
54
+ 4.179152488708496,
55
+ 5.346591472625732,
56
+ 1.7942548990249634,
57
+ 1.8604620695114136,
58
+ 5.43813943862915,
59
+ 1.0,
60
+ 7.142920017242432,
61
+ 4.157068729400635,
62
+ 5.672450065612793,
63
+ 1.95806884765625,
64
+ 1.5663840770721436,
65
+ 5.278968811035156,
66
+ 1.0
67
+ ],
68
+ "q01": null,
69
+ "q99": null
70
+ },
71
+ "timestamp": {
72
+ "mean": [
73
+ 9.822102670522625
74
+ ],
75
+ "std": [
76
+ 8.539596174071674
77
+ ],
78
+ "min": [
79
+ 0.0
80
+ ],
81
+ "max": [
82
+ 72.2
83
+ ],
84
+ "q01": null,
85
+ "q99": null
86
+ },
87
+ "action": {
88
+ "mean": [
89
+ -0.23943633195674233,
90
+ 1.1345611370099242,
91
+ 0.8102948556347407,
92
+ -0.31155664203396427,
93
+ 0.055179529382087596,
94
+ -0.03851684881837727,
95
+ 0.6643150995848328,
96
+ 0.2180408921138067,
97
+ 1.084594298787433,
98
+ 0.7916076777904834,
99
+ -0.3226336790356457,
100
+ -0.017651344197297695,
101
+ 0.036046095670276106,
102
+ 0.6783459021336998
103
+ ],
104
+ "std": [
105
+ 0.41571822839412337,
106
+ 1.0039769594416716,
107
+ 0.776858413838075,
108
+ 0.6748144778640579,
109
+ 0.271547410486253,
110
+ 0.6218771922320094,
111
+ 0.4551044161133153,
112
+ 0.3498656750012986,
113
+ 1.024847904429167,
114
+ 0.7946977748066826,
115
+ 0.6867041229584827,
116
+ 0.24531770744314874,
117
+ 0.6170235462820901,
118
+ 0.4502233751205138
119
+ ],
120
+ "min": [
121
+ -7.552278995513916,
122
+ -0.36354875564575195,
123
+ -0.18577136099338531,
124
+ -1.956291913986206,
125
+ -1.6801013946533203,
126
+ -7.678869724273682,
127
+ 0.0,
128
+ -8.539926528930664,
129
+ -0.6294453740119934,
130
+ -0.07775841653347015,
131
+ -2.1328067779541016,
132
+ -2.1285502910614014,
133
+ -8.228925704956055,
134
+ 0.0
135
+ ],
136
+ "max": [
137
+ 6.45659065246582,
138
+ 4.179152488708496,
139
+ 5.346591472625732,
140
+ 1.7942548990249634,
141
+ 1.8604620695114136,
142
+ 5.43813943862915,
143
+ 1.0,
144
+ 7.142920017242432,
145
+ 4.157068729400635,
146
+ 5.672450065612793,
147
+ 1.95806884765625,
148
+ 1.5663840770721436,
149
+ 5.278968811035156,
150
+ 1.0
151
+ ],
152
+ "q01": null,
153
+ "q99": null
154
+ }
155
+ }
156
+ }
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_start|>": 151644,
4
+ "<|im_end|>": 151645,
5
+ "<|object_ref_start|>": 151646,
6
+ "<|object_ref_end|>": 151647,
7
+ "<|box_start|>": 151648,
8
+ "<|box_end|>": 151649,
9
+ "<|quad_start|>": 151650,
10
+ "<|quad_end|>": 151651,
11
+ "<|vision_start|>": 151652,
12
+ "<|vision_end|>": 151653,
13
+ "<|vision_pad|>": 151654,
14
+ "<|image_pad|>": 151655,
15
+ "<|video_pad|>": 151656,
16
+ "<tool_call>": 151657,
17
+ "</tool_call>": 151658,
18
+ "<|fim_prefix|>": 151659,
19
+ "<|fim_middle|>": 151660,
20
+ "<|fim_suffix|>": 151661,
21
+ "<|fim_pad|>": 151662,
22
+ "<|repo_name|>": 151663,
23
+ "<|file_sep|>": 151664,
24
+ "<tool_response>": 151665,
25
+ "</tool_response>": 151666,
26
+ "<think>": 151667,
27
+ "</think>": 151668,
28
+ "<IMG_CONTEXT>": 151669,
29
+ "<img>": 151670,
30
+ "</img>": 151671,
31
+ "<box>": 151672,
32
+ "</box>": 151673,
33
+ "<quad>": 151674,
34
+ "</quad>": 151675,
35
+ "<ref>": 151676,
36
+ "</ref>": 151677,
37
+ "<interval>": 151678,
38
+ "</interval>": 151679
39
+ }
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
gr00t_n17_qwen3vl_2b_robotwin_all_data_full_finetune_bs256/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff