RJK commited on
Commit
564d631
·
verified ·
1 Parent(s): 2263df2

upload SmolVLA LIBERO fine-tuned checkpoints (incremental cache)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. smolvla_libero_10_full_finetune_bs64/checkpoints/step-057096-epoch-36-loss=0.2340.safetensors +3 -0
  2. smolvla_libero_10_full_finetune_bs64/config.json +315 -0
  3. smolvla_libero_10_full_finetune_bs64/config.yaml +239 -0
  4. smolvla_libero_10_full_finetune_bs64/dataset_statistics.json +104 -0
  5. smolvla_libero_10_full_finetune_bs64/tokenizer/added_tokens.json +130 -0
  6. smolvla_libero_10_full_finetune_bs64/tokenizer/merges.txt +0 -0
  7. smolvla_libero_10_full_finetune_bs64/tokenizer/merges.txt.metadata +3 -0
  8. smolvla_libero_10_full_finetune_bs64/tokenizer/special_tokens_map.json +39 -0
  9. smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer.json +0 -0
  10. smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer.json.metadata +3 -0
  11. smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer_config.json +1192 -0
  12. smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata +3 -0
  13. smolvla_libero_10_full_finetune_bs64/tokenizer/vocab.json +0 -0
  14. smolvla_libero_10_full_finetune_bs64/tokenizer/vocab.json.metadata +3 -0
  15. smolvla_libero_10_full_finetune_bs64/vlm_backbone_config.json +25 -0
  16. smolvla_libero_goal_full_finetune_bs64/checkpoints/step-029772-epoch-36-loss=0.1831.safetensors +3 -0
  17. smolvla_libero_goal_full_finetune_bs64/config.json +315 -0
  18. smolvla_libero_goal_full_finetune_bs64/config.yaml +239 -0
  19. smolvla_libero_goal_full_finetune_bs64/dataset_statistics.json +138 -0
  20. smolvla_libero_goal_full_finetune_bs64/tokenizer/added_tokens.json +130 -0
  21. smolvla_libero_goal_full_finetune_bs64/tokenizer/merges.txt +0 -0
  22. smolvla_libero_goal_full_finetune_bs64/tokenizer/merges.txt.metadata +3 -0
  23. smolvla_libero_goal_full_finetune_bs64/tokenizer/special_tokens_map.json +39 -0
  24. smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer.json +0 -0
  25. smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer.json.metadata +3 -0
  26. smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer_config.json +1192 -0
  27. smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata +3 -0
  28. smolvla_libero_goal_full_finetune_bs64/tokenizer/vocab.json +0 -0
  29. smolvla_libero_goal_full_finetune_bs64/tokenizer/vocab.json.metadata +3 -0
  30. smolvla_libero_goal_full_finetune_bs64/vlm_backbone_config.json +25 -0
  31. smolvla_libero_object_full_finetune_bs64/checkpoints/step-025128-epoch-24-loss=0.2583.safetensors +3 -0
  32. smolvla_libero_object_full_finetune_bs64/config.json +315 -0
  33. smolvla_libero_object_full_finetune_bs64/config.yaml +239 -0
  34. smolvla_libero_object_full_finetune_bs64/dataset_statistics.json +104 -0
  35. smolvla_libero_object_full_finetune_bs64/tokenizer/added_tokens.json +130 -0
  36. smolvla_libero_object_full_finetune_bs64/tokenizer/merges.txt +0 -0
  37. smolvla_libero_object_full_finetune_bs64/tokenizer/merges.txt.metadata +3 -0
  38. smolvla_libero_object_full_finetune_bs64/tokenizer/special_tokens_map.json +39 -0
  39. smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer.json +0 -0
  40. smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer.json.metadata +3 -0
  41. smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer_config.json +1192 -0
  42. smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata +3 -0
  43. smolvla_libero_object_full_finetune_bs64/tokenizer/vocab.json +0 -0
  44. smolvla_libero_object_full_finetune_bs64/tokenizer/vocab.json.metadata +3 -0
  45. smolvla_libero_object_full_finetune_bs64/vlm_backbone_config.json +25 -0
  46. smolvla_libero_spatial_full_finetune_bs64/checkpoints/step-029808-epoch-36-loss=0.1997.safetensors +3 -0
  47. smolvla_libero_spatial_full_finetune_bs64/config.json +315 -0
  48. smolvla_libero_spatial_full_finetune_bs64/config.yaml +239 -0
  49. smolvla_libero_spatial_full_finetune_bs64/dataset_statistics.json +104 -0
  50. smolvla_libero_spatial_full_finetune_bs64/tokenizer/added_tokens.json +130 -0
smolvla_libero_10_full_finetune_bs64/checkpoints/step-057096-epoch-36-loss=0.2340.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c02d9e2a2aa1c5f279d38d0366d88b47e88c0e46ec44277bef6ac242ec796e
3
+ size 805540592
smolvla_libero_10_full_finetune_bs64/config.json ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval": {
3
+ "dataset": {
4
+ "transforms": [
5
+ {
6
+ "img_keys": [
7
+ "agentview_image",
8
+ "robot0_eye_in_hand_image"
9
+ ],
10
+ "resize_size": 512,
11
+ "type": "ProcessLiberoEvalInputs"
12
+ },
13
+ {
14
+ "image_resize_strategy": "letterbox",
15
+ "input_sizes": [
16
+ [
17
+ 3,
18
+ 512,
19
+ 512
20
+ ],
21
+ [
22
+ 3,
23
+ 512,
24
+ 512
25
+ ]
26
+ ],
27
+ "letterbox_fill": [
28
+ 0,
29
+ 0,
30
+ 0
31
+ ],
32
+ "letterbox_pad_position": "top-left",
33
+ "means": [
34
+ [
35
+ 127.5,
36
+ 127.5,
37
+ 127.5
38
+ ],
39
+ [
40
+ 127.5,
41
+ 127.5,
42
+ 127.5
43
+ ]
44
+ ],
45
+ "stds": [
46
+ [
47
+ 127.5,
48
+ 127.5,
49
+ 127.5
50
+ ],
51
+ [
52
+ 127.5,
53
+ 127.5,
54
+ 127.5
55
+ ]
56
+ ],
57
+ "type": "TransformImage"
58
+ },
59
+ {
60
+ "add_new_line": true,
61
+ "tokenizer": {
62
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
63
+ "type": "PretrainedTokenizer"
64
+ },
65
+ "type": "LiberoPromptFromInputs",
66
+ "use_conversation": false
67
+ },
68
+ {
69
+ "gripper_key": "robot0_gripper_qpos",
70
+ "norm_type": "mean_std",
71
+ "out_key": "states",
72
+ "pos_key": "robot0_eef_pos",
73
+ "quat_key": "robot0_eef_quat",
74
+ "state_dim": 32,
75
+ "type": "LiberoProprioFromInputs"
76
+ }
77
+ ],
78
+ "type": "LiberoParquetEvalDataset"
79
+ },
80
+ "denormalize_action": {
81
+ "action_dim": 7,
82
+ "norm_type": "mean_std",
83
+ "type": "DenormalizeLiberoAction"
84
+ },
85
+ "eval_chunk_size": 10,
86
+ "model_family": "smolvla",
87
+ "num_steps_wait": 10,
88
+ "num_trials_per_task": 50,
89
+ "seed": 7,
90
+ "task_suite_name": "libero_10",
91
+ "type": "LiberoEvalRunner"
92
+ },
93
+ "model": {
94
+ "action_in_proj": {
95
+ "in_dim": 32,
96
+ "out_dim": 720,
97
+ "type": "LinearProjector"
98
+ },
99
+ "action_out_proj": {
100
+ "in_dim": 720,
101
+ "out_dim": 32,
102
+ "type": "LinearProjector"
103
+ },
104
+ "action_time_mlp_in": {
105
+ "in_dim": 1440,
106
+ "out_dim": 720,
107
+ "type": "LinearProjector"
108
+ },
109
+ "action_time_mlp_out": {
110
+ "in_dim": 720,
111
+ "out_dim": 720,
112
+ "type": "LinearProjector"
113
+ },
114
+ "add_image_special_tokens": false,
115
+ "chunk_size": 50,
116
+ "freeze_vlm_backbone": true,
117
+ "llm_expert": {
118
+ "attention_bias": false,
119
+ "attention_mode": "cross_attn",
120
+ "head_dim": 64,
121
+ "hidden_act": "silu",
122
+ "hidden_size": 720,
123
+ "intermediate_size": -1,
124
+ "max_position_embeddings": 8192,
125
+ "num_attention_heads": 15,
126
+ "num_hidden_layers": 16,
127
+ "num_key_value_heads": 5,
128
+ "rms_norm_eps": 1e-05,
129
+ "self_attn_every_n_layers": 2,
130
+ "torch_dtype": "bfloat16",
131
+ "type": "SmolVLMExpert",
132
+ "vlm_kv_dim": 320,
133
+ "vocab_size": 49280
134
+ },
135
+ "max_action_dim": 32,
136
+ "name_mapping": {
137
+ "action_in_proj.projector": "model.action_in_proj",
138
+ "action_out_proj.projector": "model.action_out_proj",
139
+ "action_time_mlp_in.projector": "model.action_time_mlp_in",
140
+ "action_time_mlp_out.projector": "model.action_time_mlp_out",
141
+ "llm_expert.expert": "model.vlm_with_expert.lm_expert",
142
+ "state_proj.projector": "model.state_proj",
143
+ "vlm_backbone.vlm": "model.vlm_with_expert.vlm.model"
144
+ },
145
+ "num_steps": 10,
146
+ "ori_action_dim": 7,
147
+ "pretrained_name_or_path": "./checkpoints/smolvla_base/model.safetensors",
148
+ "state_proj": {
149
+ "in_dim": 32,
150
+ "out_dim": 960,
151
+ "type": "LinearProjector"
152
+ },
153
+ "type": "SmolVLAFlowMatching",
154
+ "vlm_backbone": {
155
+ "num_vlm_layers": 16,
156
+ "scale_factor": 4,
157
+ "text_config": {
158
+ "head_dim": 64,
159
+ "hidden_act": "silu",
160
+ "hidden_size": 960,
161
+ "intermediate_size": 2560,
162
+ "max_position_embeddings": 8192,
163
+ "num_attention_heads": 15,
164
+ "num_hidden_layers": 32,
165
+ "num_key_value_heads": 5,
166
+ "rms_norm_eps": 1e-05,
167
+ "vocab_size": 49280
168
+ },
169
+ "torch_dtype": "bfloat16",
170
+ "type": "SmolVLMBackbone",
171
+ "vision_config": {
172
+ "hidden_act": "gelu_pytorch_tanh",
173
+ "hidden_size": 768,
174
+ "image_size": 512,
175
+ "intermediate_size": 3072,
176
+ "layer_norm_eps": 1e-06,
177
+ "num_attention_heads": 12,
178
+ "num_hidden_layers": 12,
179
+ "patch_size": 16
180
+ }
181
+ }
182
+ },
183
+ "runner": {
184
+ "change_key_name": false,
185
+ "collator": {
186
+ "keys": [
187
+ "states",
188
+ "timestamp",
189
+ "images",
190
+ "img_masks",
191
+ "lang_tokens",
192
+ "lang_masks",
193
+ "actions",
194
+ "action_masks"
195
+ ],
196
+ "meta_keys": [
197
+ "task_description",
198
+ "prompt",
199
+ "info",
200
+ "stats"
201
+ ],
202
+ "type": "DictCollator"
203
+ },
204
+ "enable_gradient_checkpointing": true,
205
+ "enable_mixed_precision_training": true,
206
+ "learning_rate": 0.0002,
207
+ "lr_scheduler_type": "linear-warmup+cosine-decay",
208
+ "max_epochs": 36,
209
+ "max_grad_norm": 10.0,
210
+ "metric": {
211
+ "active_trackers": [
212
+ "jsonl",
213
+ "tensorboard"
214
+ ],
215
+ "grad_accumulation_steps": 1,
216
+ "run_dir": "work_dirs",
217
+ "type": "VLAMetric",
218
+ "window_size": 1
219
+ },
220
+ "mixed_precision_dtype": "bf16",
221
+ "sampler": null,
222
+ "sharding_strategy": "no-shard",
223
+ "tokenizer": {
224
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
225
+ "type": "PretrainedTokenizer"
226
+ },
227
+ "type": "FSDPTrainRunner",
228
+ "warmup_ratio": 0.03,
229
+ "weight_decay": 0.0
230
+ },
231
+ "train_dataloader": {
232
+ "dataset": {
233
+ "datasets": {
234
+ "action_key": "action",
235
+ "action_window_size": 50,
236
+ "data_root_path": "./datasets/libero_10_no_noops_lerobotv2.1",
237
+ "statistic_name": "libero_10_no_noops",
238
+ "transforms": [
239
+ {
240
+ "name_mappings": {
241
+ "actions": [
242
+ "actions"
243
+ ],
244
+ "observation.state": [
245
+ "states"
246
+ ]
247
+ },
248
+ "parquet_keys": [
249
+ "observation.state",
250
+ "timestamp",
251
+ "actions",
252
+ "info",
253
+ "stats",
254
+ "action_masks"
255
+ ],
256
+ "type": "ProcessParquetInputs",
257
+ "video_keys": [
258
+ "observation.images.image",
259
+ "observation.images.wrist_image"
260
+ ]
261
+ },
262
+ {
263
+ "add_new_line": true,
264
+ "type": "ParquetPrompter",
265
+ "use_conversation": false
266
+ },
267
+ {
268
+ "tokenizer": {
269
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
270
+ "type": "PretrainedTokenizer"
271
+ },
272
+ "type": "ProcessPrompts"
273
+ },
274
+ {
275
+ "height": 512,
276
+ "pad_direction": "top-left",
277
+ "type": "ResizeImagesWithPad",
278
+ "width": 512
279
+ },
280
+ {
281
+ "type": "SimpleNormalizeImages"
282
+ },
283
+ {
284
+ "action_dim": 32,
285
+ "action_key": "action",
286
+ "norm_type": "mean_std",
287
+ "state_dim": 32,
288
+ "state_key": "proprio",
289
+ "type": "NormalizeStatesAndActions"
290
+ }
291
+ ],
292
+ "type": "ParquetDataset",
293
+ "use_delta": false,
294
+ "window_start_idx": 0
295
+ },
296
+ "name_mappings": {
297
+ "action": [
298
+ "action"
299
+ ],
300
+ "observation.state": [
301
+ "proprio"
302
+ ]
303
+ },
304
+ "statistic_keys": [
305
+ "observation.state",
306
+ "timestamp",
307
+ "action"
308
+ ],
309
+ "statistic_name": "libero_10_no_noops",
310
+ "type": "DistributedRepeatingDataset"
311
+ },
312
+ "per_device_batch_size": 8,
313
+ "per_device_num_workers": 4
314
+ }
315
+ }
smolvla_libero_10_full_finetune_bs64/config.yaml ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eval:
2
+ dataset:
3
+ transforms:
4
+ - img_keys:
5
+ - agentview_image
6
+ - robot0_eye_in_hand_image
7
+ resize_size: 512
8
+ type: ProcessLiberoEvalInputs
9
+ - image_resize_strategy: letterbox
10
+ input_sizes:
11
+ - - 3
12
+ - 512
13
+ - 512
14
+ - - 3
15
+ - 512
16
+ - 512
17
+ letterbox_fill:
18
+ - 0
19
+ - 0
20
+ - 0
21
+ letterbox_pad_position: top-left
22
+ means:
23
+ - - 127.5
24
+ - 127.5
25
+ - 127.5
26
+ - - 127.5
27
+ - 127.5
28
+ - 127.5
29
+ stds:
30
+ - - 127.5
31
+ - 127.5
32
+ - 127.5
33
+ - - 127.5
34
+ - 127.5
35
+ - 127.5
36
+ type: TransformImage
37
+ - add_new_line: true
38
+ tokenizer:
39
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
40
+ type: PretrainedTokenizer
41
+ type: LiberoPromptFromInputs
42
+ use_conversation: false
43
+ - gripper_key: robot0_gripper_qpos
44
+ norm_type: mean_std
45
+ out_key: states
46
+ pos_key: robot0_eef_pos
47
+ quat_key: robot0_eef_quat
48
+ state_dim: 32
49
+ type: LiberoProprioFromInputs
50
+ type: LiberoParquetEvalDataset
51
+ denormalize_action:
52
+ action_dim: 7
53
+ norm_type: mean_std
54
+ type: DenormalizeLiberoAction
55
+ eval_chunk_size: 10
56
+ model_family: smolvla
57
+ num_steps_wait: 10
58
+ num_trials_per_task: 50
59
+ seed: 7
60
+ task_suite_name: libero_10
61
+ type: LiberoEvalRunner
62
+ model:
63
+ action_in_proj:
64
+ in_dim: 32
65
+ out_dim: 720
66
+ type: LinearProjector
67
+ action_out_proj:
68
+ in_dim: 720
69
+ out_dim: 32
70
+ type: LinearProjector
71
+ action_time_mlp_in:
72
+ in_dim: 1440
73
+ out_dim: 720
74
+ type: LinearProjector
75
+ action_time_mlp_out:
76
+ in_dim: 720
77
+ out_dim: 720
78
+ type: LinearProjector
79
+ add_image_special_tokens: false
80
+ chunk_size: 50
81
+ freeze_vlm_backbone: true
82
+ llm_expert:
83
+ attention_bias: false
84
+ attention_mode: cross_attn
85
+ head_dim: 64
86
+ hidden_act: silu
87
+ hidden_size: 720
88
+ intermediate_size: -1
89
+ max_position_embeddings: 8192
90
+ num_attention_heads: 15
91
+ num_hidden_layers: 16
92
+ num_key_value_heads: 5
93
+ rms_norm_eps: 1.0e-05
94
+ self_attn_every_n_layers: 2
95
+ torch_dtype: bfloat16
96
+ type: SmolVLMExpert
97
+ vlm_kv_dim: 320
98
+ vocab_size: 49280
99
+ max_action_dim: 32
100
+ name_mapping:
101
+ action_in_proj.projector: model.action_in_proj
102
+ action_out_proj.projector: model.action_out_proj
103
+ action_time_mlp_in.projector: model.action_time_mlp_in
104
+ action_time_mlp_out.projector: model.action_time_mlp_out
105
+ llm_expert.expert: model.vlm_with_expert.lm_expert
106
+ state_proj.projector: model.state_proj
107
+ vlm_backbone.vlm: model.vlm_with_expert.vlm.model
108
+ num_steps: 10
109
+ ori_action_dim: 7
110
+ pretrained_name_or_path: ./checkpoints/smolvla_base/model.safetensors
111
+ state_proj:
112
+ in_dim: 32
113
+ out_dim: 960
114
+ type: LinearProjector
115
+ type: SmolVLAFlowMatching
116
+ vlm_backbone:
117
+ num_vlm_layers: 16
118
+ scale_factor: 4
119
+ text_config:
120
+ head_dim: 64
121
+ hidden_act: silu
122
+ hidden_size: 960
123
+ intermediate_size: 2560
124
+ max_position_embeddings: 8192
125
+ num_attention_heads: 15
126
+ num_hidden_layers: 32
127
+ num_key_value_heads: 5
128
+ rms_norm_eps: 1.0e-05
129
+ vocab_size: 49280
130
+ torch_dtype: bfloat16
131
+ type: SmolVLMBackbone
132
+ vision_config:
133
+ hidden_act: gelu_pytorch_tanh
134
+ hidden_size: 768
135
+ image_size: 512
136
+ intermediate_size: 3072
137
+ layer_norm_eps: 1.0e-06
138
+ num_attention_heads: 12
139
+ num_hidden_layers: 12
140
+ patch_size: 16
141
+ runner:
142
+ change_key_name: false
143
+ collator:
144
+ keys:
145
+ - states
146
+ - timestamp
147
+ - images
148
+ - img_masks
149
+ - lang_tokens
150
+ - lang_masks
151
+ - actions
152
+ - action_masks
153
+ meta_keys:
154
+ - task_description
155
+ - prompt
156
+ - info
157
+ - stats
158
+ type: DictCollator
159
+ enable_gradient_checkpointing: true
160
+ enable_mixed_precision_training: true
161
+ learning_rate: 0.0002
162
+ lr_scheduler_type: linear-warmup+cosine-decay
163
+ max_epochs: 36
164
+ max_grad_norm: 10.0
165
+ metric:
166
+ active_trackers:
167
+ - jsonl
168
+ - tensorboard
169
+ grad_accumulation_steps: 1
170
+ run_dir: work_dirs
171
+ type: VLAMetric
172
+ window_size: 1
173
+ mixed_precision_dtype: bf16
174
+ sampler: null
175
+ sharding_strategy: no-shard
176
+ tokenizer:
177
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
178
+ type: PretrainedTokenizer
179
+ type: FSDPTrainRunner
180
+ warmup_ratio: 0.03
181
+ weight_decay: 0.0
182
+ train_dataloader:
183
+ dataset:
184
+ datasets:
185
+ action_key: action
186
+ action_window_size: 50
187
+ data_root_path: ./datasets/libero_10_no_noops_lerobotv2.1
188
+ statistic_name: libero_10_no_noops
189
+ transforms:
190
+ - name_mappings:
191
+ actions:
192
+ - actions
193
+ observation.state:
194
+ - states
195
+ parquet_keys:
196
+ - observation.state
197
+ - timestamp
198
+ - actions
199
+ - info
200
+ - stats
201
+ - action_masks
202
+ type: ProcessParquetInputs
203
+ video_keys:
204
+ - observation.images.image
205
+ - observation.images.wrist_image
206
+ - add_new_line: true
207
+ type: ParquetPrompter
208
+ use_conversation: false
209
+ - tokenizer:
210
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
211
+ type: PretrainedTokenizer
212
+ type: ProcessPrompts
213
+ - height: 512
214
+ pad_direction: top-left
215
+ type: ResizeImagesWithPad
216
+ width: 512
217
+ - type: SimpleNormalizeImages
218
+ - action_dim: 32
219
+ action_key: action
220
+ norm_type: mean_std
221
+ state_dim: 32
222
+ state_key: proprio
223
+ type: NormalizeStatesAndActions
224
+ type: ParquetDataset
225
+ use_delta: false
226
+ window_start_idx: 0
227
+ name_mappings:
228
+ action:
229
+ - action
230
+ observation.state:
231
+ - proprio
232
+ statistic_keys:
233
+ - observation.state
234
+ - timestamp
235
+ - action
236
+ statistic_name: libero_10_no_noops
237
+ type: DistributedRepeatingDataset
238
+ per_device_batch_size: 8
239
+ per_device_num_workers: 4
smolvla_libero_10_full_finetune_bs64/dataset_statistics.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "libero_10_no_noops": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.0419064655693921,
6
+ 0.0353943785769225,
7
+ 0.8257066448085474,
8
+ 2.908315654671235,
9
+ -0.5562158603122547,
10
+ -0.1664910329554594,
11
+ 0.02831534785236664,
12
+ -0.028561558922556265
13
+ ],
14
+ "std": [
15
+ 0.037983810285504724,
16
+ 0.05099922690402999,
17
+ 0.09094586143443492,
18
+ 0.12167118781966886,
19
+ 0.43643697181350727,
20
+ 0.12656789603066015,
21
+ 0.004705366661198258,
22
+ 0.004657921514447958
23
+ ],
24
+ "min": [
25
+ -0.4828203022480011,
26
+ -0.3255046010017395,
27
+ 0.445506751537323,
28
+ 1.1321442127227783,
29
+ -3.641430377960205,
30
+ -1.842738389968872,
31
+ -0.0010040868073701859,
32
+ -0.04111652821302414
33
+ ],
34
+ "max": [
35
+ 0.21031762659549713,
36
+ 0.39128610491752625,
37
+ 1.3332009315490723,
38
+ 3.6714255809783936,
39
+ 3.560650587081909,
40
+ 1.386339545249939,
41
+ 0.04160946607589722,
42
+ 0.0013633022317662835
43
+ ],
44
+ "q01": null,
45
+ "q99": null
46
+ },
47
+ "timestamp": {
48
+ "mean": [
49
+ 6.968810671239492
50
+ ],
51
+ "std": [
52
+ 4.4205853432820845
53
+ ],
54
+ "min": [
55
+ 0.0
56
+ ],
57
+ "max": [
58
+ 25.2
59
+ ],
60
+ "q01": null,
61
+ "q99": null
62
+ },
63
+ "action": {
64
+ "mean": [
65
+ 0.018203219580245917,
66
+ 0.05858386677049721,
67
+ -0.05592356325431262,
68
+ 0.004626933903665416,
69
+ 0.0028960781014207345,
70
+ -0.0076731359981381505,
71
+ 0.5457824565452817
72
+ ],
73
+ "std": [
74
+ 0.10678436772960577,
75
+ 0.13569355116695744,
76
+ 0.1388675428804427,
77
+ 0.014251597889066525,
78
+ 0.020520837090261576,
79
+ 0.03297657922665584,
80
+ 0.1881883528070125
81
+ ],
82
+ "min": [
83
+ -0.9375,
84
+ -0.9375,
85
+ -0.9375,
86
+ -0.23642857372760773,
87
+ -0.3053571283817291,
88
+ -0.3675000071525574,
89
+ 0.0
90
+ ],
91
+ "max": [
92
+ 0.9375,
93
+ 0.9375,
94
+ 0.9375,
95
+ 0.30000001192092896,
96
+ 0.29357144236564636,
97
+ 0.375,
98
+ 1.0
99
+ ],
100
+ "q01": null,
101
+ "q99": null
102
+ }
103
+ }
104
+ }
smolvla_libero_10_full_finetune_bs64/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
smolvla_libero_10_full_finetune_bs64/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_10_full_finetune_bs64/tokenizer/merges.txt.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 69503b13f727ba3812b6803e97442a6de05ef5eb
3
+ 1775642998.823851
smolvla_libero_10_full_finetune_bs64/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ a4005d1cf3170a31600a5c96f95768166cbc2b28
3
+ 1775643468.342801
smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "end_of_utterance_token": "<end_of_utterance>",
1174
+ "eos_token": "<end_of_utterance>",
1175
+ "extra_special_tokens": {
1176
+ "end_of_utterance_token": "<end_of_utterance>",
1177
+ "fake_image_token": "<fake_token_around_image>",
1178
+ "global_image_token": "<global-img>",
1179
+ "image_token": "<image>"
1180
+ },
1181
+ "fake_image_token": "<fake_token_around_image>",
1182
+ "global_image_token": "<global-img>",
1183
+ "image_token": "<image>",
1184
+ "legacy": false,
1185
+ "model_max_length": 8192,
1186
+ "pad_token": "<|im_end|>",
1187
+ "processor_class": "SmolVLMProcessor",
1188
+ "tokenizer_class": "GPT2Tokenizer",
1189
+ "truncation_side": "left",
1190
+ "unk_token": "<|endoftext|>",
1191
+ "vocab_size": 49152
1192
+ }
smolvla_libero_10_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ e4042a1126290fdb96ece2a4ad8dd7108c5de484
3
+ 1775643386.4143414
smolvla_libero_10_full_finetune_bs64/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_10_full_finetune_bs64/tokenizer/vocab.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 0ad5ecc2035b7031b88afb544ee95e2d49baa484
3
+ 1775643391.6237829
smolvla_libero_10_full_finetune_bs64/vlm_backbone_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 960,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2560,
11
+ "max_position_embeddings": 8192,
12
+ "mlp_bias": false,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 15,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 5,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "transformers_version": "4.53.2",
23
+ "use_cache": true,
24
+ "vocab_size": 49280
25
+ }
smolvla_libero_goal_full_finetune_bs64/checkpoints/step-029772-epoch-36-loss=0.1831.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c44ae463c7f3662aa73a37aa339d46b8abad2697ab568c032b94b12fd928fcb
3
+ size 805540592
smolvla_libero_goal_full_finetune_bs64/config.json ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval": {
3
+ "dataset": {
4
+ "transforms": [
5
+ {
6
+ "img_keys": [
7
+ "agentview_image",
8
+ "robot0_eye_in_hand_image"
9
+ ],
10
+ "resize_size": 512,
11
+ "type": "ProcessLiberoEvalInputs"
12
+ },
13
+ {
14
+ "image_resize_strategy": "letterbox",
15
+ "input_sizes": [
16
+ [
17
+ 3,
18
+ 512,
19
+ 512
20
+ ],
21
+ [
22
+ 3,
23
+ 512,
24
+ 512
25
+ ]
26
+ ],
27
+ "letterbox_fill": [
28
+ 0,
29
+ 0,
30
+ 0
31
+ ],
32
+ "letterbox_pad_position": "top-left",
33
+ "means": [
34
+ [
35
+ 127.5,
36
+ 127.5,
37
+ 127.5
38
+ ],
39
+ [
40
+ 127.5,
41
+ 127.5,
42
+ 127.5
43
+ ]
44
+ ],
45
+ "stds": [
46
+ [
47
+ 127.5,
48
+ 127.5,
49
+ 127.5
50
+ ],
51
+ [
52
+ 127.5,
53
+ 127.5,
54
+ 127.5
55
+ ]
56
+ ],
57
+ "type": "TransformImage"
58
+ },
59
+ {
60
+ "add_new_line": true,
61
+ "tokenizer": {
62
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
63
+ "type": "PretrainedTokenizer"
64
+ },
65
+ "type": "LiberoPromptFromInputs",
66
+ "use_conversation": false
67
+ },
68
+ {
69
+ "gripper_key": "robot0_gripper_qpos",
70
+ "norm_type": "mean_std",
71
+ "out_key": "states",
72
+ "pos_key": "robot0_eef_pos",
73
+ "quat_key": "robot0_eef_quat",
74
+ "state_dim": 32,
75
+ "type": "LiberoProprioFromInputs"
76
+ }
77
+ ],
78
+ "type": "LiberoParquetEvalDataset"
79
+ },
80
+ "denormalize_action": {
81
+ "action_dim": 7,
82
+ "norm_type": "mean_std",
83
+ "type": "DenormalizeLiberoAction"
84
+ },
85
+ "eval_chunk_size": 10,
86
+ "model_family": "smolvla",
87
+ "num_steps_wait": 10,
88
+ "num_trials_per_task": 50,
89
+ "seed": 7,
90
+ "task_suite_name": "libero_goal",
91
+ "type": "LiberoEvalRunner"
92
+ },
93
+ "model": {
94
+ "action_in_proj": {
95
+ "in_dim": 32,
96
+ "out_dim": 720,
97
+ "type": "LinearProjector"
98
+ },
99
+ "action_out_proj": {
100
+ "in_dim": 720,
101
+ "out_dim": 32,
102
+ "type": "LinearProjector"
103
+ },
104
+ "action_time_mlp_in": {
105
+ "in_dim": 1440,
106
+ "out_dim": 720,
107
+ "type": "LinearProjector"
108
+ },
109
+ "action_time_mlp_out": {
110
+ "in_dim": 720,
111
+ "out_dim": 720,
112
+ "type": "LinearProjector"
113
+ },
114
+ "add_image_special_tokens": false,
115
+ "chunk_size": 50,
116
+ "freeze_vlm_backbone": true,
117
+ "llm_expert": {
118
+ "attention_bias": false,
119
+ "attention_mode": "cross_attn",
120
+ "head_dim": 64,
121
+ "hidden_act": "silu",
122
+ "hidden_size": 720,
123
+ "intermediate_size": -1,
124
+ "max_position_embeddings": 8192,
125
+ "num_attention_heads": 15,
126
+ "num_hidden_layers": 16,
127
+ "num_key_value_heads": 5,
128
+ "rms_norm_eps": 1e-05,
129
+ "self_attn_every_n_layers": 2,
130
+ "torch_dtype": "bfloat16",
131
+ "type": "SmolVLMExpert",
132
+ "vlm_kv_dim": 320,
133
+ "vocab_size": 49280
134
+ },
135
+ "max_action_dim": 32,
136
+ "name_mapping": {
137
+ "action_in_proj.projector": "model.action_in_proj",
138
+ "action_out_proj.projector": "model.action_out_proj",
139
+ "action_time_mlp_in.projector": "model.action_time_mlp_in",
140
+ "action_time_mlp_out.projector": "model.action_time_mlp_out",
141
+ "llm_expert.expert": "model.vlm_with_expert.lm_expert",
142
+ "state_proj.projector": "model.state_proj",
143
+ "vlm_backbone.vlm": "model.vlm_with_expert.vlm.model"
144
+ },
145
+ "num_steps": 10,
146
+ "ori_action_dim": 7,
147
+ "pretrained_name_or_path": "./checkpoints/smolvla_base/model.safetensors",
148
+ "state_proj": {
149
+ "in_dim": 32,
150
+ "out_dim": 960,
151
+ "type": "LinearProjector"
152
+ },
153
+ "type": "SmolVLAFlowMatching",
154
+ "vlm_backbone": {
155
+ "num_vlm_layers": 16,
156
+ "scale_factor": 4,
157
+ "text_config": {
158
+ "head_dim": 64,
159
+ "hidden_act": "silu",
160
+ "hidden_size": 960,
161
+ "intermediate_size": 2560,
162
+ "max_position_embeddings": 8192,
163
+ "num_attention_heads": 15,
164
+ "num_hidden_layers": 32,
165
+ "num_key_value_heads": 5,
166
+ "rms_norm_eps": 1e-05,
167
+ "vocab_size": 49280
168
+ },
169
+ "torch_dtype": "bfloat16",
170
+ "type": "SmolVLMBackbone",
171
+ "vision_config": {
172
+ "hidden_act": "gelu_pytorch_tanh",
173
+ "hidden_size": 768,
174
+ "image_size": 512,
175
+ "intermediate_size": 3072,
176
+ "layer_norm_eps": 1e-06,
177
+ "num_attention_heads": 12,
178
+ "num_hidden_layers": 12,
179
+ "patch_size": 16
180
+ }
181
+ }
182
+ },
183
+ "runner": {
184
+ "change_key_name": false,
185
+ "collator": {
186
+ "keys": [
187
+ "states",
188
+ "timestamp",
189
+ "images",
190
+ "img_masks",
191
+ "lang_tokens",
192
+ "lang_masks",
193
+ "actions",
194
+ "action_masks"
195
+ ],
196
+ "meta_keys": [
197
+ "task_description",
198
+ "prompt",
199
+ "info",
200
+ "stats"
201
+ ],
202
+ "type": "DictCollator"
203
+ },
204
+ "enable_gradient_checkpointing": true,
205
+ "enable_mixed_precision_training": true,
206
+ "learning_rate": 0.0002,
207
+ "lr_scheduler_type": "linear-warmup+cosine-decay",
208
+ "max_epochs": 36,
209
+ "max_grad_norm": 10.0,
210
+ "metric": {
211
+ "active_trackers": [
212
+ "jsonl",
213
+ "tensorboard"
214
+ ],
215
+ "grad_accumulation_steps": 1,
216
+ "run_dir": "work_dirs",
217
+ "type": "VLAMetric",
218
+ "window_size": 1
219
+ },
220
+ "mixed_precision_dtype": "bf16",
221
+ "sampler": null,
222
+ "sharding_strategy": "no-shard",
223
+ "tokenizer": {
224
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
225
+ "type": "PretrainedTokenizer"
226
+ },
227
+ "type": "FSDPTrainRunner",
228
+ "warmup_ratio": 0.03,
229
+ "weight_decay": 0.0
230
+ },
231
+ "train_dataloader": {
232
+ "dataset": {
233
+ "datasets": {
234
+ "action_key": "action",
235
+ "action_window_size": 50,
236
+ "data_root_path": "./datasets/libero_goal_no_noops_lerobotv2.1",
237
+ "statistic_name": "libero_goal_no_noops",
238
+ "transforms": [
239
+ {
240
+ "name_mappings": {
241
+ "actions": [
242
+ "actions"
243
+ ],
244
+ "observation.state": [
245
+ "states"
246
+ ]
247
+ },
248
+ "parquet_keys": [
249
+ "observation.state",
250
+ "timestamp",
251
+ "actions",
252
+ "info",
253
+ "stats",
254
+ "action_masks"
255
+ ],
256
+ "type": "ProcessParquetInputs",
257
+ "video_keys": [
258
+ "observation.images.image",
259
+ "observation.images.wrist_image"
260
+ ]
261
+ },
262
+ {
263
+ "add_new_line": true,
264
+ "type": "ParquetPrompter",
265
+ "use_conversation": false
266
+ },
267
+ {
268
+ "tokenizer": {
269
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
270
+ "type": "PretrainedTokenizer"
271
+ },
272
+ "type": "ProcessPrompts"
273
+ },
274
+ {
275
+ "height": 512,
276
+ "pad_direction": "top-left",
277
+ "type": "ResizeImagesWithPad",
278
+ "width": 512
279
+ },
280
+ {
281
+ "type": "SimpleNormalizeImages"
282
+ },
283
+ {
284
+ "action_dim": 32,
285
+ "action_key": "action",
286
+ "norm_type": "mean_std",
287
+ "state_dim": 32,
288
+ "state_key": "proprio",
289
+ "type": "NormalizeStatesAndActions"
290
+ }
291
+ ],
292
+ "type": "ParquetDataset",
293
+ "use_delta": false,
294
+ "window_start_idx": 0
295
+ },
296
+ "name_mappings": {
297
+ "action": [
298
+ "action"
299
+ ],
300
+ "observation.state": [
301
+ "proprio"
302
+ ]
303
+ },
304
+ "statistic_keys": [
305
+ "observation.state",
306
+ "timestamp",
307
+ "action"
308
+ ],
309
+ "statistic_name": "libero_goal_no_noops",
310
+ "type": "DistributedRepeatingDataset"
311
+ },
312
+ "per_device_batch_size": 8,
313
+ "per_device_num_workers": 4
314
+ }
315
+ }
smolvla_libero_goal_full_finetune_bs64/config.yaml ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eval:
2
+ dataset:
3
+ transforms:
4
+ - img_keys:
5
+ - agentview_image
6
+ - robot0_eye_in_hand_image
7
+ resize_size: 512
8
+ type: ProcessLiberoEvalInputs
9
+ - image_resize_strategy: letterbox
10
+ input_sizes:
11
+ - - 3
12
+ - 512
13
+ - 512
14
+ - - 3
15
+ - 512
16
+ - 512
17
+ letterbox_fill:
18
+ - 0
19
+ - 0
20
+ - 0
21
+ letterbox_pad_position: top-left
22
+ means:
23
+ - - 127.5
24
+ - 127.5
25
+ - 127.5
26
+ - - 127.5
27
+ - 127.5
28
+ - 127.5
29
+ stds:
30
+ - - 127.5
31
+ - 127.5
32
+ - 127.5
33
+ - - 127.5
34
+ - 127.5
35
+ - 127.5
36
+ type: TransformImage
37
+ - add_new_line: true
38
+ tokenizer:
39
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
40
+ type: PretrainedTokenizer
41
+ type: LiberoPromptFromInputs
42
+ use_conversation: false
43
+ - gripper_key: robot0_gripper_qpos
44
+ norm_type: mean_std
45
+ out_key: states
46
+ pos_key: robot0_eef_pos
47
+ quat_key: robot0_eef_quat
48
+ state_dim: 32
49
+ type: LiberoProprioFromInputs
50
+ type: LiberoParquetEvalDataset
51
+ denormalize_action:
52
+ action_dim: 7
53
+ norm_type: mean_std
54
+ type: DenormalizeLiberoAction
55
+ eval_chunk_size: 10
56
+ model_family: smolvla
57
+ num_steps_wait: 10
58
+ num_trials_per_task: 50
59
+ seed: 7
60
+ task_suite_name: libero_goal
61
+ type: LiberoEvalRunner
62
+ model:
63
+ action_in_proj:
64
+ in_dim: 32
65
+ out_dim: 720
66
+ type: LinearProjector
67
+ action_out_proj:
68
+ in_dim: 720
69
+ out_dim: 32
70
+ type: LinearProjector
71
+ action_time_mlp_in:
72
+ in_dim: 1440
73
+ out_dim: 720
74
+ type: LinearProjector
75
+ action_time_mlp_out:
76
+ in_dim: 720
77
+ out_dim: 720
78
+ type: LinearProjector
79
+ add_image_special_tokens: false
80
+ chunk_size: 50
81
+ freeze_vlm_backbone: true
82
+ llm_expert:
83
+ attention_bias: false
84
+ attention_mode: cross_attn
85
+ head_dim: 64
86
+ hidden_act: silu
87
+ hidden_size: 720
88
+ intermediate_size: -1
89
+ max_position_embeddings: 8192
90
+ num_attention_heads: 15
91
+ num_hidden_layers: 16
92
+ num_key_value_heads: 5
93
+ rms_norm_eps: 1.0e-05
94
+ self_attn_every_n_layers: 2
95
+ torch_dtype: bfloat16
96
+ type: SmolVLMExpert
97
+ vlm_kv_dim: 320
98
+ vocab_size: 49280
99
+ max_action_dim: 32
100
+ name_mapping:
101
+ action_in_proj.projector: model.action_in_proj
102
+ action_out_proj.projector: model.action_out_proj
103
+ action_time_mlp_in.projector: model.action_time_mlp_in
104
+ action_time_mlp_out.projector: model.action_time_mlp_out
105
+ llm_expert.expert: model.vlm_with_expert.lm_expert
106
+ state_proj.projector: model.state_proj
107
+ vlm_backbone.vlm: model.vlm_with_expert.vlm.model
108
+ num_steps: 10
109
+ ori_action_dim: 7
110
+ pretrained_name_or_path: ./checkpoints/smolvla_base/model.safetensors
111
+ state_proj:
112
+ in_dim: 32
113
+ out_dim: 960
114
+ type: LinearProjector
115
+ type: SmolVLAFlowMatching
116
+ vlm_backbone:
117
+ num_vlm_layers: 16
118
+ scale_factor: 4
119
+ text_config:
120
+ head_dim: 64
121
+ hidden_act: silu
122
+ hidden_size: 960
123
+ intermediate_size: 2560
124
+ max_position_embeddings: 8192
125
+ num_attention_heads: 15
126
+ num_hidden_layers: 32
127
+ num_key_value_heads: 5
128
+ rms_norm_eps: 1.0e-05
129
+ vocab_size: 49280
130
+ torch_dtype: bfloat16
131
+ type: SmolVLMBackbone
132
+ vision_config:
133
+ hidden_act: gelu_pytorch_tanh
134
+ hidden_size: 768
135
+ image_size: 512
136
+ intermediate_size: 3072
137
+ layer_norm_eps: 1.0e-06
138
+ num_attention_heads: 12
139
+ num_hidden_layers: 12
140
+ patch_size: 16
141
+ runner:
142
+ change_key_name: false
143
+ collator:
144
+ keys:
145
+ - states
146
+ - timestamp
147
+ - images
148
+ - img_masks
149
+ - lang_tokens
150
+ - lang_masks
151
+ - actions
152
+ - action_masks
153
+ meta_keys:
154
+ - task_description
155
+ - prompt
156
+ - info
157
+ - stats
158
+ type: DictCollator
159
+ enable_gradient_checkpointing: true
160
+ enable_mixed_precision_training: true
161
+ learning_rate: 0.0002
162
+ lr_scheduler_type: linear-warmup+cosine-decay
163
+ max_epochs: 36
164
+ max_grad_norm: 10.0
165
+ metric:
166
+ active_trackers:
167
+ - jsonl
168
+ - tensorboard
169
+ grad_accumulation_steps: 1
170
+ run_dir: work_dirs
171
+ type: VLAMetric
172
+ window_size: 1
173
+ mixed_precision_dtype: bf16
174
+ sampler: null
175
+ sharding_strategy: no-shard
176
+ tokenizer:
177
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
178
+ type: PretrainedTokenizer
179
+ type: FSDPTrainRunner
180
+ warmup_ratio: 0.03
181
+ weight_decay: 0.0
182
+ train_dataloader:
183
+ dataset:
184
+ datasets:
185
+ action_key: action
186
+ action_window_size: 50
187
+ data_root_path: ./datasets/libero_goal_no_noops_lerobotv2.1
188
+ statistic_name: libero_goal_no_noops
189
+ transforms:
190
+ - name_mappings:
191
+ actions:
192
+ - actions
193
+ observation.state:
194
+ - states
195
+ parquet_keys:
196
+ - observation.state
197
+ - timestamp
198
+ - actions
199
+ - info
200
+ - stats
201
+ - action_masks
202
+ type: ProcessParquetInputs
203
+ video_keys:
204
+ - observation.images.image
205
+ - observation.images.wrist_image
206
+ - add_new_line: true
207
+ type: ParquetPrompter
208
+ use_conversation: false
209
+ - tokenizer:
210
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
211
+ type: PretrainedTokenizer
212
+ type: ProcessPrompts
213
+ - height: 512
214
+ pad_direction: top-left
215
+ type: ResizeImagesWithPad
216
+ width: 512
217
+ - type: SimpleNormalizeImages
218
+ - action_dim: 32
219
+ action_key: action
220
+ norm_type: mean_std
221
+ state_dim: 32
222
+ state_key: proprio
223
+ type: NormalizeStatesAndActions
224
+ type: ParquetDataset
225
+ use_delta: false
226
+ window_start_idx: 0
227
+ name_mappings:
228
+ action:
229
+ - action
230
+ observation.state:
231
+ - proprio
232
+ statistic_keys:
233
+ - observation.state
234
+ - timestamp
235
+ - action
236
+ statistic_name: libero_goal_no_noops
237
+ type: DistributedRepeatingDataset
238
+ per_device_batch_size: 8
239
+ per_device_num_workers: 4
smolvla_libero_goal_full_finetune_bs64/dataset_statistics.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "libero_goal_no_noops": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.09891432758878499,
6
+ 0.01489584178884142,
7
+ 1.067322519907531,
8
+ 2.8289916028867363,
9
+ 0.31907902813946676,
10
+ -0.2782741362135122,
11
+ 0.02821884616217808,
12
+ -0.02719759491844234
13
+ ],
14
+ "std": [
15
+ 0.04140466877133655,
16
+ 0.04117920944028847,
17
+ 0.037538661473221754,
18
+ 0.1955033740750787,
19
+ 0.2574273555156476,
20
+ 0.12620857483432396,
21
+ 0.0053229405182870755,
22
+ 0.005316267734440966
23
+ ],
24
+ "min": [
25
+ -0.46141287684440613,
26
+ -0.30136311054229736,
27
+ 0.9083037972450256,
28
+ 1.002794623374939,
29
+ -1.0517308712005615,
30
+ -1.5227035284042358,
31
+ -0.0021671096328645945,
32
+ -0.042015016078948975
33
+ ],
34
+ "max": [
35
+ 0.13241106271743774,
36
+ 0.3271525800228119,
37
+ 1.472778081893921,
38
+ 3.4731650352478027,
39
+ 2.676265239715576,
40
+ 0.6698114275932312,
41
+ 0.04232141748070717,
42
+ 0.001021005678921938
43
+ ],
44
+ "q01": [
45
+ -0.22800911694063627,
46
+ -0.10299188974829282,
47
+ 0.9455820491176684,
48
+ 2.608259821258135,
49
+ -0.18011099436472794,
50
+ -0.5618953405895196,
51
+ 0.012391739034799726,
52
+ -0.039969403267763146
53
+ ],
54
+ "q99": [
55
+ -0.01061282617817482,
56
+ 0.11139527808191847,
57
+ 1.2117906450921032,
58
+ 3.168615021869246,
59
+ 0.6706572281431679,
60
+ 0.05441701961452796,
61
+ 0.04007683324960615,
62
+ -0.009863127064877238
63
+ ]
64
+ },
65
+ "timestamp": {
66
+ "mean": [
67
+ 3.354542962472823
68
+ ],
69
+ "std": [
70
+ 2.391036718656464
71
+ ],
72
+ "min": [
73
+ 0.0
74
+ ],
75
+ "max": [
76
+ 17.3
77
+ ],
78
+ "q01": null,
79
+ "q99": null
80
+ },
81
+ "action": {
82
+ "mean": [
83
+ 0.04244028081958392,
84
+ 0.03443110282231447,
85
+ -0.15229553502677498,
86
+ -0.0024877518145540465,
87
+ 0.02584054000286765,
88
+ 0.026984970605938637,
89
+ 0.6345212227794035
90
+ ],
91
+ "std": [
92
+ 0.15081003273695404,
93
+ 0.13262089326077886,
94
+ 0.18549323777289492,
95
+ 0.020653428159559374,
96
+ 0.029405301079120767,
97
+ 0.03768659701327122,
98
+ 0.1820141409830254
99
+ ],
100
+ "min": [
101
+ -0.9375,
102
+ -0.9375,
103
+ -0.9375,
104
+ -0.24214285612106323,
105
+ -0.375,
106
+ -0.2871428430080414,
107
+ 0.0
108
+ ],
109
+ "max": [
110
+ 0.9375,
111
+ 0.9375,
112
+ 0.9375,
113
+ 0.3557142913341522,
114
+ 0.375,
115
+ 0.375,
116
+ 1.0
117
+ ],
118
+ "q01": [
119
+ -0.6000398242585724,
120
+ -0.4840628973395442,
121
+ -0.828284557604454,
122
+ -0.08435403729704126,
123
+ -0.10102247173430137,
124
+ -0.08468755117369905,
125
+ 0.22234615748180359
126
+ ],
127
+ "q99": [
128
+ 0.7428644945783142,
129
+ 0.5763548859545187,
130
+ 0.6755035821278529,
131
+ 0.09240677347557615,
132
+ 0.17272708537297377,
133
+ 0.14638082286503087,
134
+ 1.0
135
+ ]
136
+ }
137
+ }
138
+ }
smolvla_libero_goal_full_finetune_bs64/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
smolvla_libero_goal_full_finetune_bs64/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_goal_full_finetune_bs64/tokenizer/merges.txt.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 69503b13f727ba3812b6803e97442a6de05ef5eb
3
+ 1775642998.823851
smolvla_libero_goal_full_finetune_bs64/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ a4005d1cf3170a31600a5c96f95768166cbc2b28
3
+ 1775643468.342801
smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "end_of_utterance_token": "<end_of_utterance>",
1174
+ "eos_token": "<end_of_utterance>",
1175
+ "extra_special_tokens": {
1176
+ "end_of_utterance_token": "<end_of_utterance>",
1177
+ "fake_image_token": "<fake_token_around_image>",
1178
+ "global_image_token": "<global-img>",
1179
+ "image_token": "<image>"
1180
+ },
1181
+ "fake_image_token": "<fake_token_around_image>",
1182
+ "global_image_token": "<global-img>",
1183
+ "image_token": "<image>",
1184
+ "legacy": false,
1185
+ "model_max_length": 8192,
1186
+ "pad_token": "<|im_end|>",
1187
+ "processor_class": "SmolVLMProcessor",
1188
+ "tokenizer_class": "GPT2Tokenizer",
1189
+ "truncation_side": "left",
1190
+ "unk_token": "<|endoftext|>",
1191
+ "vocab_size": 49152
1192
+ }
smolvla_libero_goal_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ e4042a1126290fdb96ece2a4ad8dd7108c5de484
3
+ 1775643386.4143414
smolvla_libero_goal_full_finetune_bs64/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_goal_full_finetune_bs64/tokenizer/vocab.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 0ad5ecc2035b7031b88afb544ee95e2d49baa484
3
+ 1775643391.6237829
smolvla_libero_goal_full_finetune_bs64/vlm_backbone_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 960,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2560,
11
+ "max_position_embeddings": 8192,
12
+ "mlp_bias": false,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 15,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 5,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "transformers_version": "4.53.2",
23
+ "use_cache": true,
24
+ "vocab_size": 49280
25
+ }
smolvla_libero_object_full_finetune_bs64/checkpoints/step-025128-epoch-24-loss=0.2583.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6c7f2333eb21d19b0330fc28d245850bf959ccd136b738c3be159a0cb63fad
3
+ size 805540592
smolvla_libero_object_full_finetune_bs64/config.json ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval": {
3
+ "dataset": {
4
+ "transforms": [
5
+ {
6
+ "img_keys": [
7
+ "agentview_image",
8
+ "robot0_eye_in_hand_image"
9
+ ],
10
+ "resize_size": 512,
11
+ "type": "ProcessLiberoEvalInputs"
12
+ },
13
+ {
14
+ "image_resize_strategy": "letterbox",
15
+ "input_sizes": [
16
+ [
17
+ 3,
18
+ 512,
19
+ 512
20
+ ],
21
+ [
22
+ 3,
23
+ 512,
24
+ 512
25
+ ]
26
+ ],
27
+ "letterbox_fill": [
28
+ 0,
29
+ 0,
30
+ 0
31
+ ],
32
+ "letterbox_pad_position": "top-left",
33
+ "means": [
34
+ [
35
+ 127.5,
36
+ 127.5,
37
+ 127.5
38
+ ],
39
+ [
40
+ 127.5,
41
+ 127.5,
42
+ 127.5
43
+ ]
44
+ ],
45
+ "stds": [
46
+ [
47
+ 127.5,
48
+ 127.5,
49
+ 127.5
50
+ ],
51
+ [
52
+ 127.5,
53
+ 127.5,
54
+ 127.5
55
+ ]
56
+ ],
57
+ "type": "TransformImage"
58
+ },
59
+ {
60
+ "add_new_line": true,
61
+ "tokenizer": {
62
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
63
+ "type": "PretrainedTokenizer"
64
+ },
65
+ "type": "LiberoPromptFromInputs",
66
+ "use_conversation": false
67
+ },
68
+ {
69
+ "gripper_key": "robot0_gripper_qpos",
70
+ "norm_type": "mean_std",
71
+ "out_key": "states",
72
+ "pos_key": "robot0_eef_pos",
73
+ "quat_key": "robot0_eef_quat",
74
+ "state_dim": 32,
75
+ "type": "LiberoProprioFromInputs"
76
+ }
77
+ ],
78
+ "type": "LiberoParquetEvalDataset"
79
+ },
80
+ "denormalize_action": {
81
+ "action_dim": 7,
82
+ "norm_type": "mean_std",
83
+ "type": "DenormalizeLiberoAction"
84
+ },
85
+ "eval_chunk_size": 10,
86
+ "model_family": "smolvla",
87
+ "num_steps_wait": 10,
88
+ "num_trials_per_task": 50,
89
+ "seed": 7,
90
+ "task_suite_name": "libero_object",
91
+ "type": "LiberoEvalRunner"
92
+ },
93
+ "model": {
94
+ "action_in_proj": {
95
+ "in_dim": 32,
96
+ "out_dim": 720,
97
+ "type": "LinearProjector"
98
+ },
99
+ "action_out_proj": {
100
+ "in_dim": 720,
101
+ "out_dim": 32,
102
+ "type": "LinearProjector"
103
+ },
104
+ "action_time_mlp_in": {
105
+ "in_dim": 1440,
106
+ "out_dim": 720,
107
+ "type": "LinearProjector"
108
+ },
109
+ "action_time_mlp_out": {
110
+ "in_dim": 720,
111
+ "out_dim": 720,
112
+ "type": "LinearProjector"
113
+ },
114
+ "add_image_special_tokens": false,
115
+ "chunk_size": 50,
116
+ "freeze_vlm_backbone": true,
117
+ "llm_expert": {
118
+ "attention_bias": false,
119
+ "attention_mode": "cross_attn",
120
+ "head_dim": 64,
121
+ "hidden_act": "silu",
122
+ "hidden_size": 720,
123
+ "intermediate_size": -1,
124
+ "max_position_embeddings": 8192,
125
+ "num_attention_heads": 15,
126
+ "num_hidden_layers": 16,
127
+ "num_key_value_heads": 5,
128
+ "rms_norm_eps": 1e-05,
129
+ "self_attn_every_n_layers": 2,
130
+ "torch_dtype": "bfloat16",
131
+ "type": "SmolVLMExpert",
132
+ "vlm_kv_dim": 320,
133
+ "vocab_size": 49280
134
+ },
135
+ "max_action_dim": 32,
136
+ "name_mapping": {
137
+ "action_in_proj.projector": "model.action_in_proj",
138
+ "action_out_proj.projector": "model.action_out_proj",
139
+ "action_time_mlp_in.projector": "model.action_time_mlp_in",
140
+ "action_time_mlp_out.projector": "model.action_time_mlp_out",
141
+ "llm_expert.expert": "model.vlm_with_expert.lm_expert",
142
+ "state_proj.projector": "model.state_proj",
143
+ "vlm_backbone.vlm": "model.vlm_with_expert.vlm.model"
144
+ },
145
+ "num_steps": 10,
146
+ "ori_action_dim": 7,
147
+ "pretrained_name_or_path": "./checkpoints/smolvla_base/model.safetensors",
148
+ "state_proj": {
149
+ "in_dim": 32,
150
+ "out_dim": 960,
151
+ "type": "LinearProjector"
152
+ },
153
+ "type": "SmolVLAFlowMatching",
154
+ "vlm_backbone": {
155
+ "num_vlm_layers": 16,
156
+ "scale_factor": 4,
157
+ "text_config": {
158
+ "head_dim": 64,
159
+ "hidden_act": "silu",
160
+ "hidden_size": 960,
161
+ "intermediate_size": 2560,
162
+ "max_position_embeddings": 8192,
163
+ "num_attention_heads": 15,
164
+ "num_hidden_layers": 32,
165
+ "num_key_value_heads": 5,
166
+ "rms_norm_eps": 1e-05,
167
+ "vocab_size": 49280
168
+ },
169
+ "torch_dtype": "bfloat16",
170
+ "type": "SmolVLMBackbone",
171
+ "vision_config": {
172
+ "hidden_act": "gelu_pytorch_tanh",
173
+ "hidden_size": 768,
174
+ "image_size": 512,
175
+ "intermediate_size": 3072,
176
+ "layer_norm_eps": 1e-06,
177
+ "num_attention_heads": 12,
178
+ "num_hidden_layers": 12,
179
+ "patch_size": 16
180
+ }
181
+ }
182
+ },
183
+ "runner": {
184
+ "change_key_name": false,
185
+ "collator": {
186
+ "keys": [
187
+ "states",
188
+ "timestamp",
189
+ "images",
190
+ "img_masks",
191
+ "lang_tokens",
192
+ "lang_masks",
193
+ "actions",
194
+ "action_masks"
195
+ ],
196
+ "meta_keys": [
197
+ "task_description",
198
+ "prompt",
199
+ "info",
200
+ "stats"
201
+ ],
202
+ "type": "DictCollator"
203
+ },
204
+ "enable_gradient_checkpointing": true,
205
+ "enable_mixed_precision_training": true,
206
+ "learning_rate": 0.0002,
207
+ "lr_scheduler_type": "linear-warmup+cosine-decay",
208
+ "max_epochs": 24,
209
+ "max_grad_norm": 10.0,
210
+ "metric": {
211
+ "active_trackers": [
212
+ "jsonl",
213
+ "tensorboard"
214
+ ],
215
+ "grad_accumulation_steps": 1,
216
+ "run_dir": "work_dirs",
217
+ "type": "VLAMetric",
218
+ "window_size": 1
219
+ },
220
+ "mixed_precision_dtype": "bf16",
221
+ "sampler": null,
222
+ "sharding_strategy": "no-shard",
223
+ "tokenizer": {
224
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
225
+ "type": "PretrainedTokenizer"
226
+ },
227
+ "type": "FSDPTrainRunner",
228
+ "warmup_ratio": 0.03,
229
+ "weight_decay": 0.0
230
+ },
231
+ "train_dataloader": {
232
+ "dataset": {
233
+ "datasets": {
234
+ "action_key": "action",
235
+ "action_window_size": 50,
236
+ "data_root_path": "./datasets/libero_object_no_noops_lerobotv2.1",
237
+ "statistic_name": "libero_object_no_noops",
238
+ "transforms": [
239
+ {
240
+ "name_mappings": {
241
+ "actions": [
242
+ "actions"
243
+ ],
244
+ "observation.state": [
245
+ "states"
246
+ ]
247
+ },
248
+ "parquet_keys": [
249
+ "observation.state",
250
+ "timestamp",
251
+ "actions",
252
+ "info",
253
+ "stats",
254
+ "action_masks"
255
+ ],
256
+ "type": "ProcessParquetInputs",
257
+ "video_keys": [
258
+ "observation.images.image",
259
+ "observation.images.wrist_image"
260
+ ]
261
+ },
262
+ {
263
+ "add_new_line": true,
264
+ "type": "ParquetPrompter",
265
+ "use_conversation": false
266
+ },
267
+ {
268
+ "tokenizer": {
269
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
270
+ "type": "PretrainedTokenizer"
271
+ },
272
+ "type": "ProcessPrompts"
273
+ },
274
+ {
275
+ "height": 512,
276
+ "pad_direction": "top-left",
277
+ "type": "ResizeImagesWithPad",
278
+ "width": 512
279
+ },
280
+ {
281
+ "type": "SimpleNormalizeImages"
282
+ },
283
+ {
284
+ "action_dim": 32,
285
+ "action_key": "action",
286
+ "norm_type": "mean_std",
287
+ "state_dim": 32,
288
+ "state_key": "proprio",
289
+ "type": "NormalizeStatesAndActions"
290
+ }
291
+ ],
292
+ "type": "ParquetDataset",
293
+ "use_delta": false,
294
+ "window_start_idx": 0
295
+ },
296
+ "name_mappings": {
297
+ "action": [
298
+ "action"
299
+ ],
300
+ "observation.state": [
301
+ "proprio"
302
+ ]
303
+ },
304
+ "statistic_keys": [
305
+ "observation.state",
306
+ "timestamp",
307
+ "action"
308
+ ],
309
+ "statistic_name": "libero_object_no_noops",
310
+ "type": "DistributedRepeatingDataset"
311
+ },
312
+ "per_device_batch_size": 8,
313
+ "per_device_num_workers": 4
314
+ }
315
+ }
smolvla_libero_object_full_finetune_bs64/config.yaml ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eval:
2
+ dataset:
3
+ transforms:
4
+ - img_keys:
5
+ - agentview_image
6
+ - robot0_eye_in_hand_image
7
+ resize_size: 512
8
+ type: ProcessLiberoEvalInputs
9
+ - image_resize_strategy: letterbox
10
+ input_sizes:
11
+ - - 3
12
+ - 512
13
+ - 512
14
+ - - 3
15
+ - 512
16
+ - 512
17
+ letterbox_fill:
18
+ - 0
19
+ - 0
20
+ - 0
21
+ letterbox_pad_position: top-left
22
+ means:
23
+ - - 127.5
24
+ - 127.5
25
+ - 127.5
26
+ - - 127.5
27
+ - 127.5
28
+ - 127.5
29
+ stds:
30
+ - - 127.5
31
+ - 127.5
32
+ - 127.5
33
+ - - 127.5
34
+ - 127.5
35
+ - 127.5
36
+ type: TransformImage
37
+ - add_new_line: true
38
+ tokenizer:
39
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
40
+ type: PretrainedTokenizer
41
+ type: LiberoPromptFromInputs
42
+ use_conversation: false
43
+ - gripper_key: robot0_gripper_qpos
44
+ norm_type: mean_std
45
+ out_key: states
46
+ pos_key: robot0_eef_pos
47
+ quat_key: robot0_eef_quat
48
+ state_dim: 32
49
+ type: LiberoProprioFromInputs
50
+ type: LiberoParquetEvalDataset
51
+ denormalize_action:
52
+ action_dim: 7
53
+ norm_type: mean_std
54
+ type: DenormalizeLiberoAction
55
+ eval_chunk_size: 10
56
+ model_family: smolvla
57
+ num_steps_wait: 10
58
+ num_trials_per_task: 50
59
+ seed: 7
60
+ task_suite_name: libero_object
61
+ type: LiberoEvalRunner
62
+ model:
63
+ action_in_proj:
64
+ in_dim: 32
65
+ out_dim: 720
66
+ type: LinearProjector
67
+ action_out_proj:
68
+ in_dim: 720
69
+ out_dim: 32
70
+ type: LinearProjector
71
+ action_time_mlp_in:
72
+ in_dim: 1440
73
+ out_dim: 720
74
+ type: LinearProjector
75
+ action_time_mlp_out:
76
+ in_dim: 720
77
+ out_dim: 720
78
+ type: LinearProjector
79
+ add_image_special_tokens: false
80
+ chunk_size: 50
81
+ freeze_vlm_backbone: true
82
+ llm_expert:
83
+ attention_bias: false
84
+ attention_mode: cross_attn
85
+ head_dim: 64
86
+ hidden_act: silu
87
+ hidden_size: 720
88
+ intermediate_size: -1
89
+ max_position_embeddings: 8192
90
+ num_attention_heads: 15
91
+ num_hidden_layers: 16
92
+ num_key_value_heads: 5
93
+ rms_norm_eps: 1.0e-05
94
+ self_attn_every_n_layers: 2
95
+ torch_dtype: bfloat16
96
+ type: SmolVLMExpert
97
+ vlm_kv_dim: 320
98
+ vocab_size: 49280
99
+ max_action_dim: 32
100
+ name_mapping:
101
+ action_in_proj.projector: model.action_in_proj
102
+ action_out_proj.projector: model.action_out_proj
103
+ action_time_mlp_in.projector: model.action_time_mlp_in
104
+ action_time_mlp_out.projector: model.action_time_mlp_out
105
+ llm_expert.expert: model.vlm_with_expert.lm_expert
106
+ state_proj.projector: model.state_proj
107
+ vlm_backbone.vlm: model.vlm_with_expert.vlm.model
108
+ num_steps: 10
109
+ ori_action_dim: 7
110
+ pretrained_name_or_path: ./checkpoints/smolvla_base/model.safetensors
111
+ state_proj:
112
+ in_dim: 32
113
+ out_dim: 960
114
+ type: LinearProjector
115
+ type: SmolVLAFlowMatching
116
+ vlm_backbone:
117
+ num_vlm_layers: 16
118
+ scale_factor: 4
119
+ text_config:
120
+ head_dim: 64
121
+ hidden_act: silu
122
+ hidden_size: 960
123
+ intermediate_size: 2560
124
+ max_position_embeddings: 8192
125
+ num_attention_heads: 15
126
+ num_hidden_layers: 32
127
+ num_key_value_heads: 5
128
+ rms_norm_eps: 1.0e-05
129
+ vocab_size: 49280
130
+ torch_dtype: bfloat16
131
+ type: SmolVLMBackbone
132
+ vision_config:
133
+ hidden_act: gelu_pytorch_tanh
134
+ hidden_size: 768
135
+ image_size: 512
136
+ intermediate_size: 3072
137
+ layer_norm_eps: 1.0e-06
138
+ num_attention_heads: 12
139
+ num_hidden_layers: 12
140
+ patch_size: 16
141
+ runner:
142
+ change_key_name: false
143
+ collator:
144
+ keys:
145
+ - states
146
+ - timestamp
147
+ - images
148
+ - img_masks
149
+ - lang_tokens
150
+ - lang_masks
151
+ - actions
152
+ - action_masks
153
+ meta_keys:
154
+ - task_description
155
+ - prompt
156
+ - info
157
+ - stats
158
+ type: DictCollator
159
+ enable_gradient_checkpointing: true
160
+ enable_mixed_precision_training: true
161
+ learning_rate: 0.0002
162
+ lr_scheduler_type: linear-warmup+cosine-decay
163
+ max_epochs: 24
164
+ max_grad_norm: 10.0
165
+ metric:
166
+ active_trackers:
167
+ - jsonl
168
+ - tensorboard
169
+ grad_accumulation_steps: 1
170
+ run_dir: work_dirs
171
+ type: VLAMetric
172
+ window_size: 1
173
+ mixed_precision_dtype: bf16
174
+ sampler: null
175
+ sharding_strategy: no-shard
176
+ tokenizer:
177
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
178
+ type: PretrainedTokenizer
179
+ type: FSDPTrainRunner
180
+ warmup_ratio: 0.03
181
+ weight_decay: 0.0
182
+ train_dataloader:
183
+ dataset:
184
+ datasets:
185
+ action_key: action
186
+ action_window_size: 50
187
+ data_root_path: ./datasets/libero_object_no_noops_lerobotv2.1
188
+ statistic_name: libero_object_no_noops
189
+ transforms:
190
+ - name_mappings:
191
+ actions:
192
+ - actions
193
+ observation.state:
194
+ - states
195
+ parquet_keys:
196
+ - observation.state
197
+ - timestamp
198
+ - actions
199
+ - info
200
+ - stats
201
+ - action_masks
202
+ type: ProcessParquetInputs
203
+ video_keys:
204
+ - observation.images.image
205
+ - observation.images.wrist_image
206
+ - add_new_line: true
207
+ type: ParquetPrompter
208
+ use_conversation: false
209
+ - tokenizer:
210
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
211
+ type: PretrainedTokenizer
212
+ type: ProcessPrompts
213
+ - height: 512
214
+ pad_direction: top-left
215
+ type: ResizeImagesWithPad
216
+ width: 512
217
+ - type: SimpleNormalizeImages
218
+ - action_dim: 32
219
+ action_key: action
220
+ norm_type: mean_std
221
+ state_dim: 32
222
+ state_key: proprio
223
+ type: NormalizeStatesAndActions
224
+ type: ParquetDataset
225
+ use_delta: false
226
+ window_start_idx: 0
227
+ name_mappings:
228
+ action:
229
+ - action
230
+ observation.state:
231
+ - proprio
232
+ statistic_keys:
233
+ - observation.state
234
+ - timestamp
235
+ - action
236
+ statistic_name: libero_object_no_noops
237
+ type: DistributedRepeatingDataset
238
+ per_device_batch_size: 8
239
+ per_device_num_workers: 4
smolvla_libero_object_full_finetune_bs64/dataset_statistics.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "libero_object_no_noops": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.029990377887890714,
6
+ -0.007947119348036638,
7
+ 0.20293400450543442,
8
+ 3.108609864126749,
9
+ -0.2140478258736818,
10
+ -0.11307033080181891,
11
+ 0.02938040086729137,
12
+ -0.03055662046031239
13
+ ],
14
+ "std": [
15
+ 0.023670072817660013,
16
+ 0.06225550550101929,
17
+ 0.027602195887468282,
18
+ 0.030705662709939595,
19
+ 0.11858388544011475,
20
+ 0.0732862116780689,
21
+ 0.0033820150919409114,
22
+ 0.003251806898346789
23
+ ],
24
+ "min": [
25
+ -0.1765444278717041,
26
+ -0.29457300901412964,
27
+ 0.008128180168569088,
28
+ 2.2890501022338867,
29
+ -1.883241891860962,
30
+ -1.0600427389144897,
31
+ 0.0006495157140307128,
32
+ -0.041782498359680176
33
+ ],
34
+ "max": [
35
+ 0.14580604434013367,
36
+ 0.33216384053230286,
37
+ 0.3857804834842682,
38
+ 3.4003844261169434,
39
+ 0.7954911589622498,
40
+ 0.6642207503318787,
41
+ 0.04104341194033623,
42
+ -0.00018117300351150334
43
+ ],
44
+ "q01": null,
45
+ "q99": null
46
+ },
47
+ "timestamp": {
48
+ "mean": [
49
+ 3.721695479517497
50
+ ],
51
+ "std": [
52
+ 2.237081841546431
53
+ ],
54
+ "min": [
55
+ 0.0
56
+ ],
57
+ "max": [
58
+ 12.65
59
+ ],
60
+ "q01": null,
61
+ "q99": null
62
+ },
63
+ "action": {
64
+ "mean": [
65
+ 0.07096490746267721,
66
+ 0.13498889685796536,
67
+ -0.046013733641776924,
68
+ 0.0012352044345171392,
69
+ 0.006998803721298765,
70
+ -0.015027527802288103,
71
+ 0.46428998075465666
72
+ ],
73
+ "std": [
74
+ 0.10133946158044306,
75
+ 0.165716399861371,
76
+ 0.16914353294024564,
77
+ 0.009240558533809633,
78
+ 0.018657116474914717,
79
+ 0.015913625946349673,
80
+ 0.18849963395480163
81
+ ],
82
+ "min": [
83
+ -0.8839285969734192,
84
+ -0.9375,
85
+ -0.9375,
86
+ -0.15000000596046448,
87
+ -0.29035714268684387,
88
+ -0.32892856001853943,
89
+ 0.0
90
+ ],
91
+ "max": [
92
+ 0.9375,
93
+ 0.8919642567634583,
94
+ 0.9375,
95
+ 0.17678570747375488,
96
+ 0.35035714507102966,
97
+ 0.1810714304447174,
98
+ 1.0
99
+ ],
100
+ "q01": null,
101
+ "q99": null
102
+ }
103
+ }
104
+ }
smolvla_libero_object_full_finetune_bs64/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
smolvla_libero_object_full_finetune_bs64/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_object_full_finetune_bs64/tokenizer/merges.txt.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 69503b13f727ba3812b6803e97442a6de05ef5eb
3
+ 1775642998.823851
smolvla_libero_object_full_finetune_bs64/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ a4005d1cf3170a31600a5c96f95768166cbc2b28
3
+ 1775643468.342801
smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "end_of_utterance_token": "<end_of_utterance>",
1174
+ "eos_token": "<end_of_utterance>",
1175
+ "extra_special_tokens": {
1176
+ "end_of_utterance_token": "<end_of_utterance>",
1177
+ "fake_image_token": "<fake_token_around_image>",
1178
+ "global_image_token": "<global-img>",
1179
+ "image_token": "<image>"
1180
+ },
1181
+ "fake_image_token": "<fake_token_around_image>",
1182
+ "global_image_token": "<global-img>",
1183
+ "image_token": "<image>",
1184
+ "legacy": false,
1185
+ "model_max_length": 8192,
1186
+ "pad_token": "<|im_end|>",
1187
+ "processor_class": "SmolVLMProcessor",
1188
+ "tokenizer_class": "GPT2Tokenizer",
1189
+ "truncation_side": "left",
1190
+ "unk_token": "<|endoftext|>",
1191
+ "vocab_size": 49152
1192
+ }
smolvla_libero_object_full_finetune_bs64/tokenizer/tokenizer_config.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ e4042a1126290fdb96ece2a4ad8dd7108c5de484
3
+ 1775643386.4143414
smolvla_libero_object_full_finetune_bs64/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_libero_object_full_finetune_bs64/tokenizer/vocab.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 0ad5ecc2035b7031b88afb544ee95e2d49baa484
3
+ 1775643391.6237829
smolvla_libero_object_full_finetune_bs64/vlm_backbone_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 960,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2560,
11
+ "max_position_embeddings": 8192,
12
+ "mlp_bias": false,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 15,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 5,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "transformers_version": "4.53.2",
23
+ "use_cache": true,
24
+ "vocab_size": 49280
25
+ }
smolvla_libero_spatial_full_finetune_bs64/checkpoints/step-029808-epoch-36-loss=0.1997.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6b06642231f117bedcb868c930f286a10d7b14be70d6268d70a32c1125b621
3
+ size 805540592
smolvla_libero_spatial_full_finetune_bs64/config.json ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval": {
3
+ "dataset": {
4
+ "transforms": [
5
+ {
6
+ "img_keys": [
7
+ "agentview_image",
8
+ "robot0_eye_in_hand_image"
9
+ ],
10
+ "resize_size": 512,
11
+ "type": "ProcessLiberoEvalInputs"
12
+ },
13
+ {
14
+ "image_resize_strategy": "letterbox",
15
+ "input_sizes": [
16
+ [
17
+ 3,
18
+ 512,
19
+ 512
20
+ ],
21
+ [
22
+ 3,
23
+ 512,
24
+ 512
25
+ ]
26
+ ],
27
+ "letterbox_fill": [
28
+ 0,
29
+ 0,
30
+ 0
31
+ ],
32
+ "letterbox_pad_position": "top-left",
33
+ "means": [
34
+ [
35
+ 127.5,
36
+ 127.5,
37
+ 127.5
38
+ ],
39
+ [
40
+ 127.5,
41
+ 127.5,
42
+ 127.5
43
+ ]
44
+ ],
45
+ "stds": [
46
+ [
47
+ 127.5,
48
+ 127.5,
49
+ 127.5
50
+ ],
51
+ [
52
+ 127.5,
53
+ 127.5,
54
+ 127.5
55
+ ]
56
+ ],
57
+ "type": "TransformImage"
58
+ },
59
+ {
60
+ "add_new_line": true,
61
+ "tokenizer": {
62
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
63
+ "type": "PretrainedTokenizer"
64
+ },
65
+ "type": "LiberoPromptFromInputs",
66
+ "use_conversation": false
67
+ },
68
+ {
69
+ "gripper_key": "robot0_gripper_qpos",
70
+ "norm_type": "mean_std",
71
+ "out_key": "states",
72
+ "pos_key": "robot0_eef_pos",
73
+ "quat_key": "robot0_eef_quat",
74
+ "state_dim": 32,
75
+ "type": "LiberoProprioFromInputs"
76
+ }
77
+ ],
78
+ "type": "LiberoParquetEvalDataset"
79
+ },
80
+ "denormalize_action": {
81
+ "action_dim": 7,
82
+ "norm_type": "mean_std",
83
+ "type": "DenormalizeLiberoAction"
84
+ },
85
+ "eval_chunk_size": 10,
86
+ "model_family": "smolvla",
87
+ "num_steps_wait": 10,
88
+ "num_trials_per_task": 50,
89
+ "seed": 7,
90
+ "task_suite_name": "libero_spatial",
91
+ "type": "LiberoEvalRunner"
92
+ },
93
+ "model": {
94
+ "action_in_proj": {
95
+ "in_dim": 32,
96
+ "out_dim": 720,
97
+ "type": "LinearProjector"
98
+ },
99
+ "action_out_proj": {
100
+ "in_dim": 720,
101
+ "out_dim": 32,
102
+ "type": "LinearProjector"
103
+ },
104
+ "action_time_mlp_in": {
105
+ "in_dim": 1440,
106
+ "out_dim": 720,
107
+ "type": "LinearProjector"
108
+ },
109
+ "action_time_mlp_out": {
110
+ "in_dim": 720,
111
+ "out_dim": 720,
112
+ "type": "LinearProjector"
113
+ },
114
+ "add_image_special_tokens": false,
115
+ "chunk_size": 50,
116
+ "freeze_vlm_backbone": true,
117
+ "llm_expert": {
118
+ "attention_bias": false,
119
+ "attention_mode": "cross_attn",
120
+ "head_dim": 64,
121
+ "hidden_act": "silu",
122
+ "hidden_size": 720,
123
+ "intermediate_size": -1,
124
+ "max_position_embeddings": 8192,
125
+ "num_attention_heads": 15,
126
+ "num_hidden_layers": 16,
127
+ "num_key_value_heads": 5,
128
+ "rms_norm_eps": 1e-05,
129
+ "self_attn_every_n_layers": 2,
130
+ "torch_dtype": "bfloat16",
131
+ "type": "SmolVLMExpert",
132
+ "vlm_kv_dim": 320,
133
+ "vocab_size": 49280
134
+ },
135
+ "max_action_dim": 32,
136
+ "name_mapping": {
137
+ "action_in_proj.projector": "model.action_in_proj",
138
+ "action_out_proj.projector": "model.action_out_proj",
139
+ "action_time_mlp_in.projector": "model.action_time_mlp_in",
140
+ "action_time_mlp_out.projector": "model.action_time_mlp_out",
141
+ "llm_expert.expert": "model.vlm_with_expert.lm_expert",
142
+ "state_proj.projector": "model.state_proj",
143
+ "vlm_backbone.vlm": "model.vlm_with_expert.vlm.model"
144
+ },
145
+ "num_steps": 10,
146
+ "ori_action_dim": 7,
147
+ "pretrained_name_or_path": "./checkpoints/smolvla_base/model.safetensors",
148
+ "state_proj": {
149
+ "in_dim": 32,
150
+ "out_dim": 960,
151
+ "type": "LinearProjector"
152
+ },
153
+ "type": "SmolVLAFlowMatching",
154
+ "vlm_backbone": {
155
+ "num_vlm_layers": 16,
156
+ "scale_factor": 4,
157
+ "text_config": {
158
+ "head_dim": 64,
159
+ "hidden_act": "silu",
160
+ "hidden_size": 960,
161
+ "intermediate_size": 2560,
162
+ "max_position_embeddings": 8192,
163
+ "num_attention_heads": 15,
164
+ "num_hidden_layers": 32,
165
+ "num_key_value_heads": 5,
166
+ "rms_norm_eps": 1e-05,
167
+ "vocab_size": 49280
168
+ },
169
+ "torch_dtype": "bfloat16",
170
+ "type": "SmolVLMBackbone",
171
+ "vision_config": {
172
+ "hidden_act": "gelu_pytorch_tanh",
173
+ "hidden_size": 768,
174
+ "image_size": 512,
175
+ "intermediate_size": 3072,
176
+ "layer_norm_eps": 1e-06,
177
+ "num_attention_heads": 12,
178
+ "num_hidden_layers": 12,
179
+ "patch_size": 16
180
+ }
181
+ }
182
+ },
183
+ "runner": {
184
+ "change_key_name": false,
185
+ "collator": {
186
+ "keys": [
187
+ "states",
188
+ "timestamp",
189
+ "images",
190
+ "img_masks",
191
+ "lang_tokens",
192
+ "lang_masks",
193
+ "actions",
194
+ "action_masks"
195
+ ],
196
+ "meta_keys": [
197
+ "task_description",
198
+ "prompt",
199
+ "info",
200
+ "stats"
201
+ ],
202
+ "type": "DictCollator"
203
+ },
204
+ "enable_gradient_checkpointing": true,
205
+ "enable_mixed_precision_training": true,
206
+ "learning_rate": 0.0002,
207
+ "lr_scheduler_type": "linear-warmup+cosine-decay",
208
+ "max_epochs": 36,
209
+ "max_grad_norm": 10.0,
210
+ "metric": {
211
+ "active_trackers": [
212
+ "jsonl",
213
+ "tensorboard"
214
+ ],
215
+ "grad_accumulation_steps": 1,
216
+ "run_dir": "work_dirs",
217
+ "type": "VLAMetric",
218
+ "window_size": 1
219
+ },
220
+ "mixed_precision_dtype": "bf16",
221
+ "sampler": null,
222
+ "sharding_strategy": "no-shard",
223
+ "tokenizer": {
224
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
225
+ "type": "PretrainedTokenizer"
226
+ },
227
+ "type": "FSDPTrainRunner",
228
+ "warmup_ratio": 0.03,
229
+ "weight_decay": 0.0
230
+ },
231
+ "train_dataloader": {
232
+ "dataset": {
233
+ "datasets": {
234
+ "action_key": "action",
235
+ "action_window_size": 50,
236
+ "data_root_path": "./datasets/libero_spatial_no_noops_lerobotv2.1",
237
+ "statistic_name": "libero_spatial_no_noops",
238
+ "transforms": [
239
+ {
240
+ "name_mappings": {
241
+ "actions": [
242
+ "actions"
243
+ ],
244
+ "observation.state": [
245
+ "states"
246
+ ]
247
+ },
248
+ "parquet_keys": [
249
+ "observation.state",
250
+ "timestamp",
251
+ "actions",
252
+ "info",
253
+ "stats",
254
+ "action_masks"
255
+ ],
256
+ "type": "ProcessParquetInputs",
257
+ "video_keys": [
258
+ "observation.images.image",
259
+ "observation.images.wrist_image"
260
+ ]
261
+ },
262
+ {
263
+ "add_new_line": true,
264
+ "type": "ParquetPrompter",
265
+ "use_conversation": false
266
+ },
267
+ {
268
+ "tokenizer": {
269
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
270
+ "type": "PretrainedTokenizer"
271
+ },
272
+ "type": "ProcessPrompts"
273
+ },
274
+ {
275
+ "height": 512,
276
+ "pad_direction": "top-left",
277
+ "type": "ResizeImagesWithPad",
278
+ "width": 512
279
+ },
280
+ {
281
+ "type": "SimpleNormalizeImages"
282
+ },
283
+ {
284
+ "action_dim": 32,
285
+ "action_key": "action",
286
+ "norm_type": "mean_std",
287
+ "state_dim": 32,
288
+ "state_key": "proprio",
289
+ "type": "NormalizeStatesAndActions"
290
+ }
291
+ ],
292
+ "type": "ParquetDataset",
293
+ "use_delta": false,
294
+ "window_start_idx": 0
295
+ },
296
+ "name_mappings": {
297
+ "action": [
298
+ "action"
299
+ ],
300
+ "observation.state": [
301
+ "proprio"
302
+ ]
303
+ },
304
+ "statistic_keys": [
305
+ "observation.state",
306
+ "timestamp",
307
+ "action"
308
+ ],
309
+ "statistic_name": "libero_spatial_no_noops",
310
+ "type": "DistributedRepeatingDataset"
311
+ },
312
+ "per_device_batch_size": 8,
313
+ "per_device_num_workers": 4
314
+ }
315
+ }
smolvla_libero_spatial_full_finetune_bs64/config.yaml ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eval:
2
+ dataset:
3
+ transforms:
4
+ - img_keys:
5
+ - agentview_image
6
+ - robot0_eye_in_hand_image
7
+ resize_size: 512
8
+ type: ProcessLiberoEvalInputs
9
+ - image_resize_strategy: letterbox
10
+ input_sizes:
11
+ - - 3
12
+ - 512
13
+ - 512
14
+ - - 3
15
+ - 512
16
+ - 512
17
+ letterbox_fill:
18
+ - 0
19
+ - 0
20
+ - 0
21
+ letterbox_pad_position: top-left
22
+ means:
23
+ - - 127.5
24
+ - 127.5
25
+ - 127.5
26
+ - - 127.5
27
+ - 127.5
28
+ - 127.5
29
+ stds:
30
+ - - 127.5
31
+ - 127.5
32
+ - 127.5
33
+ - - 127.5
34
+ - 127.5
35
+ - 127.5
36
+ type: TransformImage
37
+ - add_new_line: true
38
+ tokenizer:
39
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
40
+ type: PretrainedTokenizer
41
+ type: LiberoPromptFromInputs
42
+ use_conversation: false
43
+ - gripper_key: robot0_gripper_qpos
44
+ norm_type: mean_std
45
+ out_key: states
46
+ pos_key: robot0_eef_pos
47
+ quat_key: robot0_eef_quat
48
+ state_dim: 32
49
+ type: LiberoProprioFromInputs
50
+ type: LiberoParquetEvalDataset
51
+ denormalize_action:
52
+ action_dim: 7
53
+ norm_type: mean_std
54
+ type: DenormalizeLiberoAction
55
+ eval_chunk_size: 10
56
+ model_family: smolvla
57
+ num_steps_wait: 10
58
+ num_trials_per_task: 50
59
+ seed: 7
60
+ task_suite_name: libero_spatial
61
+ type: LiberoEvalRunner
62
+ model:
63
+ action_in_proj:
64
+ in_dim: 32
65
+ out_dim: 720
66
+ type: LinearProjector
67
+ action_out_proj:
68
+ in_dim: 720
69
+ out_dim: 32
70
+ type: LinearProjector
71
+ action_time_mlp_in:
72
+ in_dim: 1440
73
+ out_dim: 720
74
+ type: LinearProjector
75
+ action_time_mlp_out:
76
+ in_dim: 720
77
+ out_dim: 720
78
+ type: LinearProjector
79
+ add_image_special_tokens: false
80
+ chunk_size: 50
81
+ freeze_vlm_backbone: true
82
+ llm_expert:
83
+ attention_bias: false
84
+ attention_mode: cross_attn
85
+ head_dim: 64
86
+ hidden_act: silu
87
+ hidden_size: 720
88
+ intermediate_size: -1
89
+ max_position_embeddings: 8192
90
+ num_attention_heads: 15
91
+ num_hidden_layers: 16
92
+ num_key_value_heads: 5
93
+ rms_norm_eps: 1.0e-05
94
+ self_attn_every_n_layers: 2
95
+ torch_dtype: bfloat16
96
+ type: SmolVLMExpert
97
+ vlm_kv_dim: 320
98
+ vocab_size: 49280
99
+ max_action_dim: 32
100
+ name_mapping:
101
+ action_in_proj.projector: model.action_in_proj
102
+ action_out_proj.projector: model.action_out_proj
103
+ action_time_mlp_in.projector: model.action_time_mlp_in
104
+ action_time_mlp_out.projector: model.action_time_mlp_out
105
+ llm_expert.expert: model.vlm_with_expert.lm_expert
106
+ state_proj.projector: model.state_proj
107
+ vlm_backbone.vlm: model.vlm_with_expert.vlm.model
108
+ num_steps: 10
109
+ ori_action_dim: 7
110
+ pretrained_name_or_path: ./checkpoints/smolvla_base/model.safetensors
111
+ state_proj:
112
+ in_dim: 32
113
+ out_dim: 960
114
+ type: LinearProjector
115
+ type: SmolVLAFlowMatching
116
+ vlm_backbone:
117
+ num_vlm_layers: 16
118
+ scale_factor: 4
119
+ text_config:
120
+ head_dim: 64
121
+ hidden_act: silu
122
+ hidden_size: 960
123
+ intermediate_size: 2560
124
+ max_position_embeddings: 8192
125
+ num_attention_heads: 15
126
+ num_hidden_layers: 32
127
+ num_key_value_heads: 5
128
+ rms_norm_eps: 1.0e-05
129
+ vocab_size: 49280
130
+ torch_dtype: bfloat16
131
+ type: SmolVLMBackbone
132
+ vision_config:
133
+ hidden_act: gelu_pytorch_tanh
134
+ hidden_size: 768
135
+ image_size: 512
136
+ intermediate_size: 3072
137
+ layer_norm_eps: 1.0e-06
138
+ num_attention_heads: 12
139
+ num_hidden_layers: 12
140
+ patch_size: 16
141
+ runner:
142
+ change_key_name: false
143
+ collator:
144
+ keys:
145
+ - states
146
+ - timestamp
147
+ - images
148
+ - img_masks
149
+ - lang_tokens
150
+ - lang_masks
151
+ - actions
152
+ - action_masks
153
+ meta_keys:
154
+ - task_description
155
+ - prompt
156
+ - info
157
+ - stats
158
+ type: DictCollator
159
+ enable_gradient_checkpointing: true
160
+ enable_mixed_precision_training: true
161
+ learning_rate: 0.0002
162
+ lr_scheduler_type: linear-warmup+cosine-decay
163
+ max_epochs: 36
164
+ max_grad_norm: 10.0
165
+ metric:
166
+ active_trackers:
167
+ - jsonl
168
+ - tensorboard
169
+ grad_accumulation_steps: 1
170
+ run_dir: work_dirs
171
+ type: VLAMetric
172
+ window_size: 1
173
+ mixed_precision_dtype: bf16
174
+ sampler: null
175
+ sharding_strategy: no-shard
176
+ tokenizer:
177
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
178
+ type: PretrainedTokenizer
179
+ type: FSDPTrainRunner
180
+ warmup_ratio: 0.03
181
+ weight_decay: 0.0
182
+ train_dataloader:
183
+ dataset:
184
+ datasets:
185
+ action_key: action
186
+ action_window_size: 50
187
+ data_root_path: ./datasets/libero_spatial_no_noops_lerobotv2.1
188
+ statistic_name: libero_spatial_no_noops
189
+ transforms:
190
+ - name_mappings:
191
+ actions:
192
+ - actions
193
+ observation.state:
194
+ - states
195
+ parquet_keys:
196
+ - observation.state
197
+ - timestamp
198
+ - actions
199
+ - info
200
+ - stats
201
+ - action_masks
202
+ type: ProcessParquetInputs
203
+ video_keys:
204
+ - observation.images.image
205
+ - observation.images.wrist_image
206
+ - add_new_line: true
207
+ type: ParquetPrompter
208
+ use_conversation: false
209
+ - tokenizer:
210
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
211
+ type: PretrainedTokenizer
212
+ type: ProcessPrompts
213
+ - height: 512
214
+ pad_direction: top-left
215
+ type: ResizeImagesWithPad
216
+ width: 512
217
+ - type: SimpleNormalizeImages
218
+ - action_dim: 32
219
+ action_key: action
220
+ norm_type: mean_std
221
+ state_dim: 32
222
+ state_key: proprio
223
+ type: NormalizeStatesAndActions
224
+ type: ParquetDataset
225
+ use_delta: false
226
+ window_start_idx: 0
227
+ name_mappings:
228
+ action:
229
+ - action
230
+ observation.state:
231
+ - proprio
232
+ statistic_keys:
233
+ - observation.state
234
+ - timestamp
235
+ - action
236
+ statistic_name: libero_spatial_no_noops
237
+ type: DistributedRepeatingDataset
238
+ per_device_batch_size: 8
239
+ per_device_num_workers: 4
smolvla_libero_spatial_full_finetune_bs64/dataset_statistics.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "libero_spatial_no_noops": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.024462566693947342,
6
+ 0.10653030478388664,
7
+ 1.0580495716300307,
8
+ 3.062855007870368,
9
+ -0.10464045916348884,
10
+ 0.08307320236969534,
11
+ 0.019954609054627596,
12
+ -0.02016269208612657
13
+ ],
14
+ "std": [
15
+ 0.03894316411915835,
16
+ 0.04873628070932603,
17
+ 0.03692094784082842,
18
+ 0.0369502396792774,
19
+ 0.14538513627309543,
20
+ 0.07695788947742314,
21
+ 0.006102641532497049,
22
+ 0.006049884044502419
23
+ ],
24
+ "min": [
25
+ -0.3095473051071167,
26
+ -0.29250794649124146,
27
+ 0.9095591306686401,
28
+ 2.497488260269165,
29
+ -1.8006486892700195,
30
+ -0.7207611203193665,
31
+ -0.0004703797458205372,
32
+ -0.041536275297403336
33
+ ],
34
+ "max": [
35
+ 0.1759040206670761,
36
+ 0.3904820382595062,
37
+ 1.3290715217590332,
38
+ 3.4566118717193604,
39
+ 1.2268599271774292,
40
+ 1.0429412126541138,
41
+ 0.041053611785173416,
42
+ 0.000775813648942858
43
+ ],
44
+ "q01": null,
45
+ "q99": null
46
+ },
47
+ "timestamp": {
48
+ "mean": [
49
+ 3.1281914291108173
50
+ ],
51
+ "std": [
52
+ 1.9190018719668336
53
+ ],
54
+ "min": [
55
+ 0.0
56
+ ],
57
+ "max": [
58
+ 9.6
59
+ ],
60
+ "q01": null,
61
+ "q99": null
62
+ },
63
+ "action": {
64
+ "mean": [
65
+ 0.15312488430795423,
66
+ 0.13707241597825376,
67
+ -0.15526779033841448,
68
+ -0.005176474488725037,
69
+ -0.011208756940533639,
70
+ -0.02019425420384803,
71
+ 0.4578818200364616
72
+ ],
73
+ "std": [
74
+ 0.15599777645651164,
75
+ 0.13125442554438385,
76
+ 0.19226097301543327,
77
+ 0.014084604392168992,
78
+ 0.02738322007326005,
79
+ 0.021779582921450876,
80
+ 0.18831055119433956
81
+ ],
82
+ "min": [
83
+ -0.9375,
84
+ -0.9375,
85
+ -0.9375,
86
+ -0.1875,
87
+ -0.3675000071525574,
88
+ -0.36000001430511475,
89
+ 0.0
90
+ ],
91
+ "max": [
92
+ 0.9375,
93
+ 0.9375,
94
+ 0.9375,
95
+ 0.1971428543329239,
96
+ 0.33642858266830444,
97
+ 0.375,
98
+ 1.0
99
+ ],
100
+ "q01": null,
101
+ "q99": null
102
+ }
103
+ }
104
+ }
smolvla_libero_spatial_full_finetune_bs64/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }